From 79ab80beb792fc56141ca9bc5675b2109b729955 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2014 17:06:38 -0500
Subject: [PATCH 001/898] [drbd] use sock_sendmsg()

... and keep ->msg_iter through the loop

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/drbd/drbd_main.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 83482721bc01..d96a41a7e257 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1846,7 +1846,7 @@ int drbd_send_out_of_sync(struct drbd_peer_device *peer_device, struct drbd_requ
 int drbd_send(struct drbd_connection *connection, struct socket *sock,
 	      void *buf, size_t size, unsigned msg_flags)
 {
-	struct kvec iov;
+	struct kvec iov = {.iov_base = buf, .iov_len = size};
 	struct msghdr msg;
 	int rv, sent = 0;
 
@@ -1855,15 +1855,14 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 
 	/* THINK  if (signal_pending) return ... ? */
 
-	iov.iov_base = buf;
-	iov.iov_len  = size;
-
 	msg.msg_name       = NULL;
 	msg.msg_namelen    = 0;
 	msg.msg_control    = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_flags      = msg_flags | MSG_NOSIGNAL;
 
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, size);
+
 	if (sock == connection->data.socket) {
 		rcu_read_lock();
 		connection->ko_count = rcu_dereference(connection->net_conf)->ko_count;
@@ -1871,7 +1870,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 		drbd_update_congested(connection);
 	}
 	do {
-		rv = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
+		rv = sock_sendmsg(sock, &msg);
 		if (rv == -EAGAIN) {
 			if (we_should_drop_the_connection(connection, sock))
 				break;
@@ -1885,8 +1884,6 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 		if (rv < 0)
 			break;
 		sent += rv;
-		iov.iov_base += rv;
-		iov.iov_len  -= rv;
 	} while (sent < size);
 
 	if (sock == connection->data.socket)
-- 
GitLab


From c1696cab700588f8493df7b51e096abf5bfb1d40 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 12 Nov 2015 04:51:19 -0500
Subject: [PATCH 002/898] [nbd] switch sock_xmit() to sock_{send,recv}msg()

Step 1 - don't reinintialize ->msg_iter on each iteration.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/nbd.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 38c576f76d36..8e63caecdd00 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -215,7 +215,7 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf,
 	struct socket *sock = nbd->socks[index]->sock;
 	int result;
 	struct msghdr msg;
-	struct kvec iov;
+	struct kvec iov = {.iov_base = buf, .iov_len = size};
 	unsigned long pflags = current->flags;
 
 	if (unlikely(!sock)) {
@@ -225,11 +225,12 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf,
 		return -EINVAL;
 	}
 
+	iov_iter_kvec(&msg.msg_iter, (send ? WRITE : READ) | ITER_KVEC,
+		      &iov, 1, size);
+
 	current->flags |= PF_MEMALLOC;
 	do {
 		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
-		iov.iov_base = buf;
-		iov.iov_len = size;
 		msg.msg_name = NULL;
 		msg.msg_namelen = 0;
 		msg.msg_control = NULL;
@@ -237,19 +238,16 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf,
 		msg.msg_flags = msg_flags | MSG_NOSIGNAL;
 
 		if (send)
-			result = kernel_sendmsg(sock, &msg, &iov, 1, size);
+			result = sock_sendmsg(sock, &msg);
 		else
-			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
-						msg.msg_flags);
+			result = sock_recvmsg(sock, &msg, msg.msg_flags);
 
 		if (result <= 0) {
 			if (result == 0)
 				result = -EPIPE; /* short read */
 			break;
 		}
-		size -= result;
-		buf += result;
-	} while (size > 0);
+	} while (msg_data_left(&msg));
 
 	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 
-- 
GitLab


From c9f2b6aeb92286f15ffc80d2ba16bc24e530f560 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 12 Nov 2015 05:09:35 -0500
Subject: [PATCH 003/898] [nbd] pass iov_iter to nbd_xmit()

... and don't mess with kmap() - just use BVEC_ITER for those parts.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/nbd.c | 66 +++++++++++++++++++--------------------------
 1 file changed, 27 insertions(+), 39 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 8e63caecdd00..3c2dbe412c02 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -209,13 +209,12 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 /*
  *  Send or receive packet.
  */
-static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf,
-		     int size, int msg_flags)
+static int sock_xmit(struct nbd_device *nbd, int index, int send,
+		     struct iov_iter *iter, int msg_flags)
 {
 	struct socket *sock = nbd->socks[index]->sock;
 	int result;
 	struct msghdr msg;
-	struct kvec iov = {.iov_base = buf, .iov_len = size};
 	unsigned long pflags = current->flags;
 
 	if (unlikely(!sock)) {
@@ -225,8 +224,7 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf,
 		return -EINVAL;
 	}
 
-	iov_iter_kvec(&msg.msg_iter, (send ? WRITE : READ) | ITER_KVEC,
-		      &iov, 1, size);
+	msg.msg_iter = *iter;
 
 	current->flags |= PF_MEMALLOC;
 	do {
@@ -254,28 +252,21 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf,
 	return result;
 }
 
-static inline int sock_send_bvec(struct nbd_device *nbd, int index,
-				 struct bio_vec *bvec, int flags)
-{
-	int result;
-	void *kaddr = kmap(bvec->bv_page);
-	result = sock_xmit(nbd, index, 1, kaddr + bvec->bv_offset,
-			   bvec->bv_len, flags);
-	kunmap(bvec->bv_page);
-	return result;
-}
-
 /* always call with the tx_lock held */
 static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 	int result, flags;
-	struct nbd_request request;
+	struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
+	struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
+	struct iov_iter from;
 	unsigned long size = blk_rq_bytes(req);
 	struct bio *bio;
 	u32 type;
 	u32 tag = blk_mq_unique_tag(req);
 
+	iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
+
 	if (req_op(req) == REQ_OP_DISCARD)
 		type = NBD_CMD_TRIM;
 	else if (req_op(req) == REQ_OP_FLUSH)
@@ -285,8 +276,6 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	else
 		type = NBD_CMD_READ;
 
-	memset(&request, 0, sizeof(request));
-	request.magic = htonl(NBD_REQUEST_MAGIC);
 	request.type = htonl(type);
 	if (type != NBD_CMD_FLUSH) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
@@ -297,7 +286,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
 		cmd, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
-	result = sock_xmit(nbd, index, 1, &request, sizeof(request),
+	result = sock_xmit(nbd, index, 1, &from,
 			(type == NBD_CMD_WRITE) ? MSG_MORE : 0);
 	if (result <= 0) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
@@ -322,7 +311,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				flags = MSG_MORE;
 			dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n",
 				cmd, bvec.bv_len);
-			result = sock_send_bvec(nbd, index, &bvec, flags);
+			iov_iter_bvec(&from, ITER_BVEC | WRITE,
+				      &bvec, 1, bvec.bv_len);
+			result = sock_xmit(nbd, index, 1, &from, flags);
 			if (result <= 0) {
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
@@ -343,17 +334,6 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	return 0;
 }
 
-static inline int sock_recv_bvec(struct nbd_device *nbd, int index,
-				 struct bio_vec *bvec)
-{
-	int result;
-	void *kaddr = kmap(bvec->bv_page);
-	result = sock_xmit(nbd, index, 0, kaddr + bvec->bv_offset,
-			   bvec->bv_len, MSG_WAITALL);
-	kunmap(bvec->bv_page);
-	return result;
-}
-
 /* NULL returned = something went wrong, inform userspace */
 static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 {
@@ -363,9 +343,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	struct request *req = NULL;
 	u16 hwq;
 	u32 tag;
+	struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
+	struct iov_iter to;
 
 	reply.magic = 0;
-	result = sock_xmit(nbd, index, 0, &reply, sizeof(reply), MSG_WAITALL);
+	iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
+	result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL);
 	if (result <= 0) {
 		if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) &&
 		    !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
@@ -405,7 +388,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		struct bio_vec bvec;
 
 		rq_for_each_segment(bvec, req, iter) {
-			result = sock_recv_bvec(nbd, index, &bvec);
+			iov_iter_bvec(&to, ITER_BVEC | READ,
+				      &bvec, 1, bvec.bv_len);
+			result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL);
 			if (result <= 0) {
 				dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
 					result);
@@ -645,14 +630,17 @@ static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
 
 static void send_disconnects(struct nbd_device *nbd)
 {
-	struct nbd_request request = {};
+	struct nbd_request request = {
+		.magic = htonl(NBD_REQUEST_MAGIC),
+		.type = htonl(NBD_CMD_DISC),
+	};
+	struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
+	struct iov_iter from;
 	int i, ret;
 
-	request.magic = htonl(NBD_REQUEST_MAGIC);
-	request.type = htonl(NBD_CMD_DISC);
-
 	for (i = 0; i < nbd->num_connections; i++) {
-		ret = sock_xmit(nbd, i, 1, &request, sizeof(request), 0);
+		iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
+		ret = sock_xmit(nbd, i, 1, &from, 0);
 		if (ret <= 0)
 			dev_err(disk_to_dev(nbd->disk),
 				"Send disconnect failed %d\n", ret);
-- 
GitLab


From 4113e47b3d0931879d75dc5ad7c4c294651b3c1d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 21 Dec 2014 02:14:47 -0500
Subject: [PATCH 004/898] iscsi_target: deal with short writes on the tx side

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/target/iscsi/iscsi_target_util.c | 64 +++++++++---------------
 1 file changed, 24 insertions(+), 40 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index b5a1b4ccba12..a9ba2479374f 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1304,39 +1304,6 @@ static int iscsit_do_rx_data(
 	return total_rx;
 }
 
-static int iscsit_do_tx_data(
-	struct iscsi_conn *conn,
-	struct iscsi_data_count *count)
-{
-	int ret, iov_len;
-	struct kvec *iov_p;
-	struct msghdr msg;
-
-	if (!conn || !conn->sock || !conn->conn_ops)
-		return -1;
-
-	if (count->data_length <= 0) {
-		pr_err("Data length is: %d\n", count->data_length);
-		return -1;
-	}
-
-	memset(&msg, 0, sizeof(struct msghdr));
-
-	iov_p = count->iov;
-	iov_len = count->iov_count;
-
-	ret = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len,
-			     count->data_length);
-	if (ret != count->data_length) {
-		pr_err("Unexpected ret: %d send data %d\n",
-		       ret, count->data_length);
-		return -EPIPE;
-	}
-	pr_debug("ret: %d, sent data: %d\n", ret, count->data_length);
-
-	return ret;
-}
-
 int rx_data(
 	struct iscsi_conn *conn,
 	struct kvec *iov,
@@ -1363,18 +1330,35 @@ int tx_data(
 	int iov_count,
 	int data)
 {
-	struct iscsi_data_count c;
+	struct msghdr msg;
+	int total_tx = 0;
 
 	if (!conn || !conn->sock || !conn->conn_ops)
 		return -1;
 
-	memset(&c, 0, sizeof(struct iscsi_data_count));
-	c.iov = iov;
-	c.iov_count = iov_count;
-	c.data_length = data;
-	c.type = ISCSI_TX_DATA;
+	if (data <= 0) {
+		pr_err("Data length is: %d\n", data);
+		return -1;
+	}
+
+	memset(&msg, 0, sizeof(struct msghdr));
+
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC,
+		      iov, iov_count, data);
+
+	while (msg_data_left(&msg)) {
+		int tx_loop = sock_sendmsg(conn->sock, &msg);
+		if (tx_loop <= 0) {
+			pr_debug("tx_loop: %d total_tx %d\n",
+				tx_loop, total_tx);
+			return tx_loop;
+		}
+		total_tx += tx_loop;
+		pr_debug("tx_loop: %d, total_tx: %d, data: %d\n",
+					tx_loop, total_tx, data);
+	}
 
-	return iscsit_do_tx_data(conn, &c);
+	return total_tx;
 }
 
 static bool sockaddr_equal(struct sockaddr_storage *x, struct sockaddr_storage *y)
-- 
GitLab


From 3995d1610713c1a62af687872e460c3dca82d17c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 21 Dec 2014 03:53:10 -0500
Subject: [PATCH 005/898] usbip_recv(): switch to sock_recvmsg()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/usb/usbip/usbip_common.c | 32 +++++++++++---------------------
 1 file changed, 11 insertions(+), 21 deletions(-)

diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index 8b232290be6b..f123bfee5d1b 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -327,13 +327,11 @@ EXPORT_SYMBOL_GPL(usbip_dump_header);
 int usbip_recv(struct socket *sock, void *buf, int size)
 {
 	int result;
-	struct msghdr msg;
-	struct kvec iov;
+	struct kvec iov = {.iov_base = buf, .iov_len = size};
+	struct msghdr msg = {.msg_flags = MSG_NOSIGNAL};
 	int total = 0;
 
-	/* for blocks of if (usbip_dbg_flag_xmit) */
-	char *bp = buf;
-	int osize = size;
+	iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size);
 
 	usbip_dbg_xmit("enter\n");
 
@@ -344,26 +342,18 @@ int usbip_recv(struct socket *sock, void *buf, int size)
 	}
 
 	do {
+		int sz = msg_data_left(&msg);
 		sock->sk->sk_allocation = GFP_NOIO;
-		iov.iov_base    = buf;
-		iov.iov_len     = size;
-		msg.msg_name    = NULL;
-		msg.msg_namelen = 0;
-		msg.msg_control = NULL;
-		msg.msg_controllen = 0;
-		msg.msg_flags      = MSG_NOSIGNAL;
-
-		result = kernel_recvmsg(sock, &msg, &iov, 1, size, MSG_WAITALL);
+
+		result = sock_recvmsg(sock, &msg, MSG_WAITALL);
 		if (result <= 0) {
 			pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
-				 sock, buf, size, result, total);
+				 sock, buf + total, sz, result, total);
 			goto err;
 		}
 
-		size -= result;
-		buf += result;
 		total += result;
-	} while (size > 0);
+	} while (msg_data_left(&msg));
 
 	if (usbip_dbg_flag_xmit) {
 		if (!in_interrupt())
@@ -372,9 +362,9 @@ int usbip_recv(struct socket *sock, void *buf, int size)
 			pr_debug("interrupt  :");
 
 		pr_debug("receiving....\n");
-		usbip_dump_buffer(bp, osize);
-		pr_debug("received, osize %d ret %d size %d total %d\n",
-			 osize, result, size, total);
+		usbip_dump_buffer(buf, size);
+		pr_debug("received, osize %d ret %d size %zd total %d\n",
+			 size, result, msg_data_left(&msg), total);
 	}
 
 	return total;
-- 
GitLab


From 100803a84d3cb84bd3ee36e8ec4274019ad667ac Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 15 Nov 2015 00:12:48 -0500
Subject: [PATCH 006/898] ceph: switch to sock_recvmsg()

... and use ITER_BVEC instead of playing with kmap()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 net/ceph/messenger.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 770c52701efa..9e46db7e5968 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -520,7 +520,8 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
 	int r;
 
-	r = kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags);
+	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len);
+	r = sock_recvmsg(sock, &msg, msg.msg_flags);
 	if (r == -EAGAIN)
 		r = 0;
 	return r;
@@ -529,17 +530,20 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
 static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
 		     int page_offset, size_t length)
 {
-	void *kaddr;
-	int ret;
+	struct bio_vec bvec = {
+		.bv_page = page,
+		.bv_offset = page_offset,
+		.bv_len = length
+	};
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	int r;
 
 	BUG_ON(page_offset + length > PAGE_SIZE);
-
-	kaddr = kmap(page);
-	BUG_ON(!kaddr);
-	ret = ceph_tcp_recvmsg(sock, kaddr + page_offset, length);
-	kunmap(page);
-
-	return ret;
+	iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length);
+	r = sock_recvmsg(sock, &msg, msg.msg_flags);
+	if (r == -EAGAIN)
+		r = 0;
+	return r;
 }
 
 /*
-- 
GitLab


From be6e4d66f01335827d734ee9bde79862ed8a235b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 15 Nov 2015 15:05:32 -0500
Subject: [PATCH 007/898] rds: remove dead code

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 net/rds/page.c | 29 -----------------------------
 net/rds/rds.h  |  7 -------
 2 files changed, 36 deletions(-)

diff --git a/net/rds/page.c b/net/rds/page.c
index e2b5a5832d3d..7cc57e098ddb 100644
--- a/net/rds/page.c
+++ b/net/rds/page.c
@@ -45,35 +45,6 @@ struct rds_page_remainder {
 static
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders);
 
-/*
- * returns 0 on success or -errno on failure.
- *
- * We don't have to worry about flush_dcache_page() as this only works
- * with private pages.  If, say, we were to do directed receive to pinned
- * user pages we'd have to worry more about cache coherence.  (Though
- * the flush_dcache_page() in get_user_pages() would probably be enough).
- */
-int rds_page_copy_user(struct page *page, unsigned long offset,
-		       void __user *ptr, unsigned long bytes,
-		       int to_user)
-{
-	unsigned long ret;
-	void *addr;
-
-	addr = kmap(page);
-	if (to_user) {
-		rds_stats_add(s_copy_to_user, bytes);
-		ret = copy_to_user(ptr, addr + offset, bytes);
-	} else {
-		rds_stats_add(s_copy_from_user, bytes);
-		ret = copy_from_user(addr + offset, ptr, bytes);
-	}
-	kunmap(page);
-
-	return ret ? -EFAULT : 0;
-}
-EXPORT_SYMBOL_GPL(rds_page_copy_user);
-
 /**
  * rds_page_remainder_alloc - build up regions of a message.
  *
diff --git a/net/rds/rds.h b/net/rds/rds.h
index ebbf909b87ec..8635993066ae 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -781,13 +781,6 @@ static inline int rds_message_verify_checksum(const struct rds_header *hdr)
 /* page.c */
 int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
 			     gfp_t gfp);
-int rds_page_copy_user(struct page *page, unsigned long offset,
-		       void __user *ptr, unsigned long bytes,
-		       int to_user);
-#define rds_page_copy_to_user(page, offset, ptr, bytes) \
-	rds_page_copy_user(page, offset, ptr, bytes, 1)
-#define rds_page_copy_from_user(page, offset, ptr, bytes) \
-	rds_page_copy_user(page, offset, ptr, bytes, 0)
 void rds_page_exit(void);
 
 /* recv.c */
-- 
GitLab


From 39c6aceae961776a11a3767553b0e295fc9d413b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jan 2016 20:36:51 -0500
Subject: [PATCH 008/898] afs_send_pages(): use ITER_BVEC

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/afs/rxrpc.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 25f05a8d21b1..bfba8f0c3d43 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -249,8 +249,7 @@ void afs_flat_call_destructor(struct afs_call *call)
 /*
  * attach the data from a bunch of pages on an inode to a call
  */
-static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
-			  struct kvec *iov)
+static int afs_send_pages(struct afs_call *call, struct msghdr *msg)
 {
 	struct page *pages[8];
 	unsigned count, n, loop, offset, to;
@@ -273,20 +272,21 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
 
 		loop = 0;
 		do {
+			struct bio_vec bvec = {.bv_page = pages[loop],
+					       .bv_offset = offset};
 			msg->msg_flags = 0;
 			to = PAGE_SIZE;
 			if (first + loop >= last)
 				to = call->last_to;
 			else
 				msg->msg_flags = MSG_MORE;
-			iov->iov_base = kmap(pages[loop]) + offset;
-			iov->iov_len = to - offset;
+			bvec.bv_len = to - offset;
 			offset = 0;
 
 			_debug("- range %u-%u%s",
 			       offset, to, msg->msg_flags ? " [more]" : "");
-			iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC,
-				      iov, 1, to - offset);
+			iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC,
+				      &bvec, 1, to - offset);
 
 			/* have to change the state *before* sending the last
 			 * packet as RxRPC might give us the reply before it
@@ -295,7 +295,6 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
 				call->state = AFS_CALL_AWAIT_REPLY;
 			ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
 						     msg, to - offset);
-			kunmap(pages[loop]);
 			if (ret < 0)
 				break;
 		} while (++loop < count);
@@ -379,7 +378,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 		goto error_do_abort;
 
 	if (call->send_pages) {
-		ret = afs_send_pages(call, &msg, iov);
+		ret = afs_send_pages(call, &msg);
 		if (ret < 0)
 			goto error_do_abort;
 	}
-- 
GitLab


From 61ff6e9b452d6158e0fd659c6d987f47cfcfbd7b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jan 2016 20:55:45 -0500
Subject: [PATCH 009/898] ceph_tcp_sendpage(): use ITER_BVEC sendmsg

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 net/ceph/messenger.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9e46db7e5968..6f3b5754cc7e 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -583,18 +583,28 @@ static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
 static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 		     int offset, size_t size, bool more)
 {
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	struct bio_vec bvec;
 	int ret;
-	struct kvec iov;
 
 	/* sendpage cannot properly handle pages with page_count == 0,
 	 * we need to fallback to sendmsg if that's the case */
 	if (page_count(page) >= 1)
 		return __ceph_tcp_sendpage(sock, page, offset, size, more);
 
-	iov.iov_base = kmap(page) + offset;
-	iov.iov_len = size;
-	ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
-	kunmap(page);
+	bvec.bv_page = page;
+	bvec.bv_offset = offset;
+	bvec.bv_len = size;
+
+	if (more)
+		msg.msg_flags |= MSG_MORE;
+	else
+		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
+
+	iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size);
+	ret = sock_sendmsg(sock, &msg);
+	if (ret == -EAGAIN)
+		ret = 0;
 
 	return ret;
 }
-- 
GitLab


From 4b4fbad37f70f1dca26e060cf8dc71371b01899c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jan 2016 21:12:37 -0500
Subject: [PATCH 010/898] ncpfs: sendmsg does *not* bugger iovec these days

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ncpfs/sock.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index f32f272ee501..97cfccefccc5 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -205,10 +205,7 @@ static inline void __ncptcp_abort(struct ncp_server *server)
 
 static int ncpdgram_send(struct socket *sock, struct ncp_request_reply *req)
 {
-	struct kvec vec[3];
-	/* sock_sendmsg updates iov pointers for us :-( */
-	memcpy(vec, req->tx_ciov, req->tx_iovlen * sizeof(vec[0]));
-	return do_send(sock, vec, req->tx_iovlen,
+	return do_send(sock, req->tx_ciov, req->tx_iovlen,
 		       req->tx_totallen, MSG_DONTWAIT);
 }
 
@@ -216,16 +213,13 @@ static void __ncptcp_try_send(struct ncp_server *server)
 {
 	struct ncp_request_reply *rq;
 	struct kvec *iov;
-	struct kvec iovc[3];
 	int result;
 
 	rq = server->tx.creq;
 	if (!rq)
 		return;
 
-	/* sock_sendmsg updates iov pointers for us :-( */
-	memcpy(iovc, rq->tx_ciov, rq->tx_iovlen * sizeof(iov[0]));
-	result = do_send(server->ncp_sock, iovc, rq->tx_iovlen,
+	result = do_send(server->ncp_sock, rq->tx_ciov, rq->tx_iovlen,
 			 rq->tx_totallen, MSG_NOSIGNAL | MSG_DONTWAIT);
 
 	if (result == -EAGAIN)
-- 
GitLab


From 2cebcc78fab5f56c9a9795fc49546d2436491312 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jan 2016 22:01:58 -0500
Subject: [PATCH 011/898] ncpfs: don't mess with manually advancing iovec on
 send

just keep iov_iter in req

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ncpfs/sock.c | 69 +++++++++++++++++++------------------------------
 1 file changed, 27 insertions(+), 42 deletions(-)

diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index 97cfccefccc5..a13c0b54f078 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -63,9 +63,7 @@ struct ncp_request_reply {
 	size_t datalen;
 	int result;
 	enum { RQ_DONE, RQ_INPROGRESS, RQ_QUEUED, RQ_IDLE, RQ_ABANDONED } status;
-	struct kvec* tx_ciov;
-	size_t tx_totallen;
-	size_t tx_iovlen;
+	struct iov_iter from;
 	struct kvec tx_iov[3];
 	u_int16_t tx_type;
 	u_int32_t sign[6];
@@ -205,22 +203,22 @@ static inline void __ncptcp_abort(struct ncp_server *server)
 
 static int ncpdgram_send(struct socket *sock, struct ncp_request_reply *req)
 {
-	return do_send(sock, req->tx_ciov, req->tx_iovlen,
-		       req->tx_totallen, MSG_DONTWAIT);
+	struct msghdr msg = { .msg_iter = req->from, .msg_flags = MSG_DONTWAIT };
+	return sock_sendmsg(sock, &msg);
 }
 
 static void __ncptcp_try_send(struct ncp_server *server)
 {
 	struct ncp_request_reply *rq;
-	struct kvec *iov;
+	struct msghdr msg = { .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT };
 	int result;
 
 	rq = server->tx.creq;
 	if (!rq)
 		return;
 
-	result = do_send(server->ncp_sock, rq->tx_ciov, rq->tx_iovlen,
-			 rq->tx_totallen, MSG_NOSIGNAL | MSG_DONTWAIT);
+	msg.msg_iter = rq->from;
+	result = sock_sendmsg(server->ncp_sock, &msg);
 
 	if (result == -EAGAIN)
 		return;
@@ -230,21 +228,12 @@ static void __ncptcp_try_send(struct ncp_server *server)
 		__ncp_abort_request(server, rq, result);
 		return;
 	}
-	if (result >= rq->tx_totallen) {
+	if (!msg_data_left(&msg)) {
 		server->rcv.creq = rq;
 		server->tx.creq = NULL;
 		return;
 	}
-	rq->tx_totallen -= result;
-	iov = rq->tx_ciov;
-	while (iov->iov_len <= result) {
-		result -= iov->iov_len;
-		iov++;
-		rq->tx_iovlen--;
-	}
-	iov->iov_base += result;
-	iov->iov_len -= result;
-	rq->tx_ciov = iov;
+	rq->from = msg.msg_iter;
 }
 
 static inline void ncp_init_header(struct ncp_server *server, struct ncp_request_reply *req, struct ncp_request_header *h)
@@ -257,22 +246,21 @@ static inline void ncp_init_header(struct ncp_server *server, struct ncp_request
 	
 static void ncpdgram_start_request(struct ncp_server *server, struct ncp_request_reply *req)
 {
-	size_t signlen;
-	struct ncp_request_header* h;
+	size_t signlen, len = req->tx_iov[1].iov_len;
+	struct ncp_request_header *h = req->tx_iov[1].iov_base;
 	
-	req->tx_ciov = req->tx_iov + 1;
-
-	h = req->tx_iov[1].iov_base;
 	ncp_init_header(server, req, h);
-	signlen = sign_packet(server, req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1, 
-			req->tx_iov[1].iov_len - sizeof(struct ncp_request_header) + 1,
-			cpu_to_le32(req->tx_totallen), req->sign);
+	signlen = sign_packet(server,
+			req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1, 
+			len - sizeof(struct ncp_request_header) + 1,
+			cpu_to_le32(len), req->sign);
 	if (signlen) {
-		req->tx_ciov[1].iov_base = req->sign;
-		req->tx_ciov[1].iov_len = signlen;
-		req->tx_iovlen += 1;
-		req->tx_totallen += signlen;
+		/* NCP over UDP appends signature */
+		req->tx_iov[2].iov_base = req->sign;
+		req->tx_iov[2].iov_len = signlen;
 	}
+	iov_iter_kvec(&req->from, WRITE | ITER_KVEC,
+			req->tx_iov + 1, signlen ? 2 : 1, len + signlen);
 	server->rcv.creq = req;
 	server->timeout_last = server->m.time_out;
 	server->timeout_retries = server->m.retry_count;
@@ -286,24 +274,23 @@ static void ncpdgram_start_request(struct ncp_server *server, struct ncp_request
 
 static void ncptcp_start_request(struct ncp_server *server, struct ncp_request_reply *req)
 {
-	size_t signlen;
-	struct ncp_request_header* h;
+	size_t signlen, len = req->tx_iov[1].iov_len;
+	struct ncp_request_header *h = req->tx_iov[1].iov_base;
 
-	req->tx_ciov = req->tx_iov;
-	h = req->tx_iov[1].iov_base;
 	ncp_init_header(server, req, h);
 	signlen = sign_packet(server, req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1,
-			req->tx_iov[1].iov_len - sizeof(struct ncp_request_header) + 1,
-			cpu_to_be32(req->tx_totallen + 24), req->sign + 4) + 16;
+			len - sizeof(struct ncp_request_header) + 1,
+			cpu_to_be32(len + 24), req->sign + 4) + 16;
 
 	req->sign[0] = htonl(NCP_TCP_XMIT_MAGIC);
-	req->sign[1] = htonl(req->tx_totallen + signlen);
+	req->sign[1] = htonl(len + signlen);
 	req->sign[2] = htonl(NCP_TCP_XMIT_VERSION);
 	req->sign[3] = htonl(req->datalen + 8);
+	/* NCP over TCP prepends signature */
 	req->tx_iov[0].iov_base = req->sign;
 	req->tx_iov[0].iov_len = signlen;
-	req->tx_iovlen += 1;
-	req->tx_totallen += signlen;
+	iov_iter_kvec(&req->from, WRITE | ITER_KVEC,
+			req->tx_iov, 2, len + signlen);
 
 	server->tx.creq = req;
 	__ncptcp_try_send(server);
@@ -705,8 +692,6 @@ static int do_ncp_rpc_call(struct ncp_server *server, int size,
 	req->datalen = max_reply_size;
 	req->tx_iov[1].iov_base = server->packet;
 	req->tx_iov[1].iov_len = size;
-	req->tx_iovlen = 1;
-	req->tx_totallen = size;
 	req->tx_type = *(u_int16_t*)server->packet;
 
 	result = ncp_add_request(server, req);
-- 
GitLab


From b8e2df1f812add27bfdb1e9d4fdf1051cc51fe1b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jan 2016 22:12:55 -0500
Subject: [PATCH 012/898] ncpfs: switch to sock_sendmsg()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ncpfs/sock.c | 36 ++++++++++++++----------------------
 1 file changed, 14 insertions(+), 22 deletions(-)

diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index a13c0b54f078..f013c92bb5d8 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -40,19 +40,12 @@ static int _recv(struct socket *sock, void *buf, int size, unsigned flags)
 	return kernel_recvmsg(sock, &msg, &iov, 1, size, flags);
 }
 
-static inline int do_send(struct socket *sock, struct kvec *vec, int count,
-			  int len, unsigned flags)
-{
-	struct msghdr msg = { .msg_flags = flags };
-	return kernel_sendmsg(sock, &msg, vec, count, len);
-}
-
 static int _send(struct socket *sock, const void *buff, int len)
 {
-	struct kvec vec;
-	vec.iov_base = (void *) buff;
-	vec.iov_len = len;
-	return do_send(sock, &vec, 1, len, 0);
+	struct msghdr msg = { .msg_flags = 0 };
+	struct kvec vec = {.iov_base = (void *)buff, .iov_len = len};
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &vec, 1, len);
+	return sock_sendmsg(sock, &msg);
 }
 
 struct ncp_request_reply {
@@ -345,18 +338,17 @@ static void __ncp_next_request(struct ncp_server *server)
 static void info_server(struct ncp_server *server, unsigned int id, const void * data, size_t len)
 {
 	if (server->info_sock) {
-		struct kvec iov[2];
-		__be32 hdr[2];
-	
-		hdr[0] = cpu_to_be32(len + 8);
-		hdr[1] = cpu_to_be32(id);
-	
-		iov[0].iov_base = hdr;
-		iov[0].iov_len = 8;
-		iov[1].iov_base = (void *) data;
-		iov[1].iov_len = len;
+		struct msghdr msg = { .msg_flags = MSG_NOSIGNAL };
+		__be32 hdr[2] = {cpu_to_be32(len + 8), cpu_to_be32(id)};
+		struct kvec iov[2] = {
+			{.iov_base = hdr, .iov_len = 8},
+			{.iov_base = (void *)data, .iov_len = len},
+		};
+
+		iov_iter_kvec(&msg.msg_iter, ITER_KVEC | WRITE,
+				iov, 2, len + 8);
 
-		do_send(server->info_sock, iov, 2, len + 8, MSG_NOSIGNAL);
+		sock_sendmsg(server->info_sock, &msg);
 	}
 }
 
-- 
GitLab


From ad1633a151df9869a222bd99ba04643dc2e0052b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 8 Jan 2017 22:35:31 -0500
Subject: [PATCH 013/898] namei: fold unlazy_link() into its sole caller

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 32 +++++++++++---------------------
 1 file changed, 11 insertions(+), 21 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index ad74877e1442..f08eca2b788b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -749,24 +749,6 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
 	return -ECHILD;
 }
 
-static int unlazy_link(struct nameidata *nd, struct path *link, unsigned seq)
-{
-	if (unlikely(!legitimize_path(nd, link, seq))) {
-		drop_links(nd);
-		nd->depth = 0;
-		nd->flags &= ~LOOKUP_RCU;
-		nd->path.mnt = NULL;
-		nd->path.dentry = NULL;
-		if (!(nd->flags & LOOKUP_ROOT))
-			nd->root.mnt = NULL;
-		rcu_read_unlock();
-	} else if (likely(unlazy_walk(nd, NULL, 0)) == 0) {
-		return 0;
-	}
-	path_put(link);
-	return -ECHILD;
-}
-
 static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	return dentry->d_op->d_revalidate(dentry, flags);
@@ -1706,9 +1688,17 @@ static int pick_link(struct nameidata *nd, struct path *link,
 	error = nd_alloc_stack(nd);
 	if (unlikely(error)) {
 		if (error == -ECHILD) {
-			if (unlikely(unlazy_link(nd, link, seq)))
-				return -ECHILD;
-			error = nd_alloc_stack(nd);
+			if (unlikely(!legitimize_path(nd, link, seq))) {
+				drop_links(nd);
+				nd->depth = 0;
+				nd->flags &= ~LOOKUP_RCU;
+				nd->path.mnt = NULL;
+				nd->path.dentry = NULL;
+				if (!(nd->flags & LOOKUP_ROOT))
+					nd->root.mnt = NULL;
+				rcu_read_unlock();
+			} else if (likely(unlazy_walk(nd, NULL, 0)) == 0)
+				error = nd_alloc_stack(nd);
 		}
 		if (error) {
 			path_put(link);
-- 
GitLab


From 209a7fb2104f2724f651870306c65f86850ee953 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jan 2017 01:35:39 -0500
Subject: [PATCH 014/898] lookup_fast(): clean up the logics around the
 fallback to non-rcu mode

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index f08eca2b788b..dfe6e32aeec6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1558,12 +1558,7 @@ static int lookup_fast(struct nameidata *nd,
 		*seqp = seq;
 		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
 			status = d_revalidate(dentry, nd->flags);
-		if (unlikely(status <= 0)) {
-			if (unlazy_walk(nd, dentry, seq))
-				return -ECHILD;
-			if (status == -ECHILD)
-				status = d_revalidate(dentry, nd->flags);
-		} else {
+		if (likely(status > 0)) {
 			/*
 			 * Note: do negative dentry check after revalidation in
 			 * case that drops it.
@@ -1574,9 +1569,12 @@ static int lookup_fast(struct nameidata *nd,
 			path->dentry = dentry;
 			if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
 				return 1;
-			if (unlazy_walk(nd, dentry, seq))
-				return -ECHILD;
 		}
+		if (unlazy_walk(nd, dentry, seq))
+			return -ECHILD;
+		if (unlikely(status == -ECHILD))
+			/* we'd been told to redo it in non-rcu mode */
+			status = d_revalidate(dentry, nd->flags);
 	} else {
 		dentry = __d_lookup(parent, &nd->last);
 		if (unlikely(!dentry))
-- 
GitLab


From a89f833737e6c75df0091ccf6c767b94745463c1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jan 2017 22:25:28 -0500
Subject: [PATCH 015/898] namei.c: fold the check for DCACHE_OP_REVALIDATE into
 d_revalidate()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 36 ++++++++++++++----------------------
 1 file changed, 14 insertions(+), 22 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index dfe6e32aeec6..2ed2701a74b5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -751,7 +751,10 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
 
 static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	return dentry->d_op->d_revalidate(dentry, flags);
+	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
+		return dentry->d_op->d_revalidate(dentry, flags);
+	else
+		return 1;
 }
 
 /**
@@ -1454,19 +1457,14 @@ static struct dentry *lookup_dcache(const struct qstr *name,
 				    struct dentry *dir,
 				    unsigned int flags)
 {
-	struct dentry *dentry;
-	int error;
-
-	dentry = d_lookup(dir, name);
+	struct dentry *dentry = d_lookup(dir, name);
 	if (dentry) {
-		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
-			error = d_revalidate(dentry, flags);
-			if (unlikely(error <= 0)) {
-				if (!error)
-					d_invalidate(dentry);
-				dput(dentry);
-				return ERR_PTR(error);
-			}
+		int error = d_revalidate(dentry, flags);
+		if (unlikely(error <= 0)) {
+			if (!error)
+				d_invalidate(dentry);
+			dput(dentry);
+			return ERR_PTR(error);
 		}
 	}
 	return dentry;
@@ -1556,8 +1554,7 @@ static int lookup_fast(struct nameidata *nd,
 			return -ECHILD;
 
 		*seqp = seq;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			status = d_revalidate(dentry, nd->flags);
+		status = d_revalidate(dentry, nd->flags);
 		if (likely(status > 0)) {
 			/*
 			 * Note: do negative dentry check after revalidation in
@@ -1579,8 +1576,7 @@ static int lookup_fast(struct nameidata *nd,
 		dentry = __d_lookup(parent, &nd->last);
 		if (unlikely(!dentry))
 			return 0;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			status = d_revalidate(dentry, nd->flags);
+		status = d_revalidate(dentry, nd->flags);
 	}
 	if (unlikely(status <= 0)) {
 		if (!status)
@@ -1619,8 +1615,7 @@ static struct dentry *lookup_slow(const struct qstr *name,
 	if (IS_ERR(dentry))
 		goto out;
 	if (unlikely(!d_in_lookup(dentry))) {
-		if ((dentry->d_flags & DCACHE_OP_REVALIDATE) &&
-		    !(flags & LOOKUP_NO_REVAL)) {
+		if (!(flags & LOOKUP_NO_REVAL)) {
 			int error = d_revalidate(dentry, flags);
 			if (unlikely(error <= 0)) {
 				if (!error) {
@@ -3057,9 +3052,6 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 		if (d_in_lookup(dentry))
 			break;
 
-		if (!(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			break;
-
 		error = d_revalidate(dentry, nd->flags);
 		if (likely(error > 0))
 			break;
-- 
GitLab


From 4675ac39b5dd5ff08dd8cb2be9ddd3cba778aa39 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jan 2017 22:29:15 -0500
Subject: [PATCH 016/898] namei.c: split unlazy_walk()

In all but one case, the last two arguments are NULL and 0 resp.;
almost everyone just wants to switch nameidata to non-RCU mode.
The only exception is lookup_fast(), where we have a child dentry
we want to legitimize as well.  Split these two cases.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 105 +++++++++++++++++++++++++++++++++--------------------
 1 file changed, 66 insertions(+), 39 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 2ed2701a74b5..76cfeb641e97 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -672,52 +672,83 @@ static bool legitimize_links(struct nameidata *nd)
 /**
  * unlazy_walk - try to switch to ref-walk mode.
  * @nd: nameidata pathwalk data
- * @dentry: child of nd->path.dentry or NULL
- * @seq: seq number to check dentry against
  * Returns: 0 on success, -ECHILD on failure
  *
- * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
- * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
- * @nd or NULL.  Must be called from rcu-walk context.
+ * unlazy_walk attempts to legitimize the current nd->path and nd->root
+ * for ref-walk mode.
+ * Must be called from rcu-walk context.
  * Nothing should touch nameidata between unlazy_walk() failure and
  * terminate_walk().
  */
-static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+static int unlazy_walk(struct nameidata *nd)
 {
 	struct dentry *parent = nd->path.dentry;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
+	nd->flags &= ~LOOKUP_RCU;
+	if (unlikely(!legitimize_links(nd)))
+		goto out2;
+	if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
+		goto out1;
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
+			goto out;
+	}
+	rcu_read_unlock();
+	BUG_ON(nd->inode != parent->d_inode);
+	return 0;
+
+out2:
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
+out1:
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
+out:
+	rcu_read_unlock();
+	return -ECHILD;
+}
+
+/**
+ * unlazy_child - try to switch to ref-walk mode.
+ * @nd: nameidata pathwalk data
+ * @dentry: child of nd->path.dentry
+ * @seq: seq number to check dentry against
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry
+ * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
+ * @nd.  Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_child() failure and
+ * terminate_walk().
+ */
+static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+{
+	BUG_ON(!(nd->flags & LOOKUP_RCU));
+
 	nd->flags &= ~LOOKUP_RCU;
 	if (unlikely(!legitimize_links(nd)))
 		goto out2;
 	if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
 		goto out2;
-	if (unlikely(!lockref_get_not_dead(&parent->d_lockref)))
+	if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
 		goto out1;
 
 	/*
-	 * For a negative lookup, the lookup sequence point is the parents
-	 * sequence point, and it only needs to revalidate the parent dentry.
-	 *
-	 * For a positive lookup, we need to move both the parent and the
-	 * dentry from the RCU domain to be properly refcounted. And the
-	 * sequence number in the dentry validates *both* dentry counters,
-	 * since we checked the sequence number of the parent after we got
-	 * the child sequence number. So we know the parent must still
-	 * be valid if the child sequence number is still valid.
+	 * We need to move both the parent and the dentry from the RCU domain
+	 * to be properly refcounted. And the sequence number in the dentry
+	 * validates *both* dentry counters, since we checked the sequence
+	 * number of the parent after we got the child sequence number. So we
+	 * know the parent must still be valid if the child sequence number is
 	 */
-	if (!dentry) {
-		if (read_seqcount_retry(&parent->d_seq, nd->seq))
-			goto out;
-		BUG_ON(nd->inode != parent->d_inode);
-	} else {
-		if (!lockref_get_not_dead(&dentry->d_lockref))
-			goto out;
-		if (read_seqcount_retry(&dentry->d_seq, seq))
-			goto drop_dentry;
+	if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
+		goto out;
+	if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) {
+		rcu_read_unlock();
+		dput(dentry);
+		goto drop_root_mnt;
 	}
-
 	/*
 	 * Sequence counts matched. Now make sure that the root is
 	 * still valid and get it if required.
@@ -733,10 +764,6 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
 	rcu_read_unlock();
 	return 0;
 
-drop_dentry:
-	rcu_read_unlock();
-	dput(dentry);
-	goto drop_root_mnt;
 out2:
 	nd->path.mnt = NULL;
 out1:
@@ -775,7 +802,7 @@ static int complete_walk(struct nameidata *nd)
 	if (nd->flags & LOOKUP_RCU) {
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
-		if (unlikely(unlazy_walk(nd, NULL, 0)))
+		if (unlikely(unlazy_walk(nd)))
 			return -ECHILD;
 	}
 
@@ -1001,7 +1028,7 @@ const char *get_link(struct nameidata *nd)
 		touch_atime(&last->link);
 		cond_resched();
 	} else if (atime_needs_update_rcu(&last->link, inode)) {
-		if (unlikely(unlazy_walk(nd, NULL, 0)))
+		if (unlikely(unlazy_walk(nd)))
 			return ERR_PTR(-ECHILD);
 		touch_atime(&last->link);
 	}
@@ -1020,7 +1047,7 @@ const char *get_link(struct nameidata *nd)
 		if (nd->flags & LOOKUP_RCU) {
 			res = get(NULL, inode, &last->done);
 			if (res == ERR_PTR(-ECHILD)) {
-				if (unlikely(unlazy_walk(nd, NULL, 0)))
+				if (unlikely(unlazy_walk(nd)))
 					return ERR_PTR(-ECHILD);
 				res = get(dentry, inode, &last->done);
 			}
@@ -1529,7 +1556,7 @@ static int lookup_fast(struct nameidata *nd,
 		bool negative;
 		dentry = __d_lookup_rcu(parent, &nd->last, &seq);
 		if (unlikely(!dentry)) {
-			if (unlazy_walk(nd, NULL, 0))
+			if (unlazy_walk(nd))
 				return -ECHILD;
 			return 0;
 		}
@@ -1567,7 +1594,7 @@ static int lookup_fast(struct nameidata *nd,
 			if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
 				return 1;
 		}
-		if (unlazy_walk(nd, dentry, seq))
+		if (unlazy_child(nd, dentry, seq))
 			return -ECHILD;
 		if (unlikely(status == -ECHILD))
 			/* we'd been told to redo it in non-rcu mode */
@@ -1646,7 +1673,7 @@ static inline int may_lookup(struct nameidata *nd)
 		int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
 		if (err != -ECHILD)
 			return err;
-		if (unlazy_walk(nd, NULL, 0))
+		if (unlazy_walk(nd))
 			return -ECHILD;
 	}
 	return inode_permission(nd->inode, MAY_EXEC);
@@ -1690,7 +1717,7 @@ static int pick_link(struct nameidata *nd, struct path *link,
 				if (!(nd->flags & LOOKUP_ROOT))
 					nd->root.mnt = NULL;
 				rcu_read_unlock();
-			} else if (likely(unlazy_walk(nd, NULL, 0)) == 0)
+			} else if (likely(unlazy_walk(nd)) == 0)
 				error = nd_alloc_stack(nd);
 		}
 		if (error) {
@@ -2108,7 +2135,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 		}
 		if (unlikely(!d_can_lookup(nd->path.dentry))) {
 			if (nd->flags & LOOKUP_RCU) {
-				if (unlazy_walk(nd, NULL, 0))
+				if (unlazy_walk(nd))
 					return -ECHILD;
 			}
 			return -ENOTDIR;
@@ -2565,7 +2592,7 @@ mountpoint_last(struct nameidata *nd)
 
 	/* If we're in rcuwalk, drop out of it to handle last component */
 	if (nd->flags & LOOKUP_RCU) {
-		if (unlazy_walk(nd, NULL, 0))
+		if (unlazy_walk(nd))
 			return -ECHILD;
 	}
 
-- 
GitLab


From 47961f1353b8195cb258ee3068d0969ef87acd20 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sat, 3 Dec 2016 00:08:48 +0100
Subject: [PATCH 017/898] ARM64: dts: meson-gx: move the SCPI and SRAM nodes to
 meson-gx

SCPI and SRAM are identical on GXBB and GXL. Moving the corresponding
nodes to meson-gx adds support for the thermal sensor on GXL based
devices.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Tested-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Neil Armstrong <narmstrong@baylibre.com>
[khilman: add scpi_clocks label]
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gx.dtsi   | 45 ++++++++++++++++
 arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 57 ---------------------
 2 files changed, 45 insertions(+), 57 deletions(-)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index eada0b58ba1c..be56b9fae2aa 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -65,6 +65,7 @@
 			reg = <0x0 0x0>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 0>;
 		};
 
 		cpu1: cpu@1 {
@@ -73,6 +74,7 @@
 			reg = <0x0 0x1>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 0>;
 		};
 
 		cpu2: cpu@2 {
@@ -81,6 +83,7 @@
 			reg = <0x0 0x2>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 0>;
 		};
 
 		cpu3: cpu@3 {
@@ -89,6 +92,7 @@
 			reg = <0x0 0x3>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 0>;
 		};
 
 		l2: l2-cache0 {
@@ -153,6 +157,28 @@
 		};
 	};
 
+	scpi {
+		compatible = "amlogic,meson-gxbb-scpi", "arm,scpi-pre-1.0";
+		mboxes = <&mailbox 1 &mailbox 2>;
+		shmem = <&cpu_scp_lpri &cpu_scp_hpri>;
+
+		scpi_clocks: clocks {
+			compatible = "arm,scpi-clocks";
+
+			scpi_dvfs: scpi_clocks@0 {
+				compatible = "arm,scpi-dvfs-clocks";
+				#clock-cells = <1>;
+				clock-indices = <0>;
+				clock-output-names = "vcpu";
+			};
+		};
+
+		scpi_sensors: sensors {
+			compatible = "arm,scpi-sensors";
+			#thermal-sensor-cells = <1>;
+		};
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -264,6 +290,25 @@
 			#address-cells = <0>;
 		};
 
+		sram: sram@c8000000 {
+			compatible = "amlogic,meson-gxbb-sram", "mmio-sram";
+			reg = <0x0 0xc8000000 0x0 0x14000>;
+
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x0 0xc8000000 0x14000>;
+
+			cpu_scp_lpri: scp-shmem@0 {
+				compatible = "amlogic,meson-gxbb-scp-shmem";
+				reg = <0x13000 0x400>;
+			};
+
+			cpu_scp_hpri: scp-shmem@200 {
+				compatible = "amlogic,meson-gxbb-scp-shmem";
+				reg = <0x13400 0x400>;
+			};
+		};
+
 		aobus: aobus@c8100000 {
 			compatible = "simple-bus";
 			reg = <0x0 0xc8100000 0x0 0x100000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 596240c38a9c..5d686334f692 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -50,28 +50,6 @@
 / {
 	compatible = "amlogic,meson-gxbb";
 
-	scpi {
-		compatible = "amlogic,meson-gxbb-scpi", "arm,scpi-pre-1.0";
-		mboxes = <&mailbox 1 &mailbox 2>;
-		shmem = <&cpu_scp_lpri &cpu_scp_hpri>;
-
-		clocks {
-			compatible = "arm,scpi-clocks";
-
-			scpi_dvfs: scpi_clocks@0 {
-				compatible = "arm,scpi-dvfs-clocks";
-				#clock-cells = <1>;
-				clock-indices = <0>;
-				clock-output-names = "vcpu";
-			};
-		};
-
-		scpi_sensors: sensors {
-			compatible = "arm,scpi-sensors";
-			#thermal-sensor-cells = <1>;
-		};
-	};
-
 	soc {
 		usb0_phy: phy@c0000000 {
 			compatible = "amlogic,meson-gxbb-usb2-phy";
@@ -93,25 +71,6 @@
 			status = "disabled";
 		};
 
-		sram: sram@c8000000 {
-			compatible = "amlogic,meson-gxbb-sram", "mmio-sram";
-			reg = <0x0 0xc8000000 0x0 0x14000>;
-
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0 0x0 0xc8000000 0x14000>;
-
-			cpu_scp_lpri: scp-shmem@0 {
-				compatible = "amlogic,meson-gxbb-scp-shmem";
-				reg = <0x13000 0x400>;
-			};
-
-			cpu_scp_hpri: scp-shmem@200 {
-				compatible = "amlogic,meson-gxbb-scp-shmem";
-				reg = <0x13400 0x400>;
-			};
-		};
-
 		usb0: usb@c9000000 {
 			compatible = "amlogic,meson-gxbb-usb", "snps,dwc2";
 			reg = <0x0 0xc9000000 0x0 0x40000>;
@@ -138,22 +97,6 @@
 	};
 };
 
-&cpu0 {
-	clocks = <&scpi_dvfs 0>;
-};
-
-&cpu1 {
-	clocks = <&scpi_dvfs 0>;
-};
-
-&cpu2 {
-	clocks = <&scpi_dvfs 0>;
-};
-
-&cpu3 {
-	clocks = <&scpi_dvfs 0>;
-};
-
 &cbus {
 	spifc: spi@8c80 {
 		compatible = "amlogic,meson-gxbb-spifc";
-- 
GitLab


From bd97abc0d04930d0369411824d437f19e72e13cc Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sat, 3 Dec 2016 00:08:49 +0100
Subject: [PATCH 018/898] ARM64: dts: meson-gxm: add SCPI configuration for GXM

This adds the SCPI DVFS clock index and configures the CPU cores
accordingly.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Tested-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gxm.dtsi | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
index eb2f0c3e5e53..4c55665a253f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
@@ -85,6 +85,7 @@
 			reg = <0x0 0x100>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 1>;
 		};
 
 		cpu5: cpu@101 {
@@ -93,6 +94,7 @@
 			reg = <0x0 0x101>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 1>;
 		};
 
 		cpu6: cpu@102 {
@@ -101,6 +103,7 @@
 			reg = <0x0 0x102>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 1>;
 		};
 
 		cpu7: cpu@103 {
@@ -109,10 +112,17 @@
 			reg = <0x0 0x103>;
 			enable-method = "psci";
 			next-level-cache = <&l2>;
+			clocks = <&scpi_dvfs 1>;
 		};
 	};
 };
 
+&scpi_dvfs {
+	clock-indices = <0 1>;
+	clock-output-names = "vbig", "vlittle";
+};
+
 &vpu {
 	compatible = "amlogic,meson-gxm-vpu", "amlogic,meson-gx-vpu";
 };
+
-- 
GitLab


From 7880b43bdfc9580700ee4568c75c383a5bcdd2ca Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 12 Jan 2017 04:01:17 -0500
Subject: [PATCH 019/898] 9p: constify ->d_name handling

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/9p/fid.c             | 10 +++++-----
 fs/9p/vfs_inode.c       | 10 +++++-----
 fs/9p/vfs_inode_dotl.c  | 20 ++++++++++----------
 include/net/9p/9p.h     |  8 ++++----
 include/net/9p/client.h | 18 +++++++++---------
 net/9p/client.c         | 18 +++++++++---------
 6 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 60fb47469c86..ed4f8519b627 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -91,10 +91,10 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
  * dentry names.
  */
 static int build_path_from_dentry(struct v9fs_session_info *v9ses,
-				  struct dentry *dentry, char ***names)
+				  struct dentry *dentry, const unsigned char ***names)
 {
 	int n = 0, i;
-	char **wnames;
+	const unsigned char **wnames;
 	struct dentry *ds;
 
 	for (ds = dentry; !IS_ROOT(ds); ds = ds->d_parent)
@@ -105,7 +105,7 @@ static int build_path_from_dentry(struct v9fs_session_info *v9ses,
 		goto err_out;
 
 	for (ds = dentry, i = (n-1); i >= 0; i--, ds = ds->d_parent)
-		wnames[i] = (char  *)ds->d_name.name;
+		wnames[i] = ds->d_name.name;
 
 	*names = wnames;
 	return n;
@@ -117,7 +117,7 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
 					       kuid_t uid, int any)
 {
 	struct dentry *ds;
-	char **wnames, *uname;
+	const unsigned char **wnames, *uname;
 	int i, n, l, clone, access;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid, *old_fid = NULL;
@@ -137,7 +137,7 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
 	fid = v9fs_fid_find(ds, uid, any);
 	if (fid) {
 		/* Found the parent fid do a lookup with that */
-		fid = p9_client_walk(fid, 1, (char **)&dentry->d_name.name, 1);
+		fid = p9_client_walk(fid, 1, &dentry->d_name.name, 1);
 		goto fid_out;
 	}
 	up_read(&v9ses->rename_sem);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index f4f4450119e4..e3e0d6581d4c 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -643,7 +643,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 		struct dentry *dentry, char *extension, u32 perm, u8 mode)
 {
 	int err;
-	char *name;
+	const unsigned char *name;
 	struct p9_fid *dfid, *ofid, *fid;
 	struct inode *inode;
 
@@ -652,7 +652,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	err = 0;
 	ofid = NULL;
 	fid = NULL;
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	dfid = v9fs_parent_fid(dentry);
 	if (IS_ERR(dfid)) {
 		err = PTR_ERR(dfid);
@@ -788,7 +788,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *dfid, *fid;
 	struct inode *inode;
-	char *name;
+	const unsigned char *name;
 
 	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%pd) %p flags: %x\n",
 		 dir, dentry, dentry, flags);
@@ -802,7 +802,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(dfid))
 		return ERR_CAST(dfid);
 
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	fid = p9_client_walk(dfid, 1, &name, 1);
 	if (IS_ERR(fid)) {
 		if (fid == ERR_PTR(-ENOENT)) {
@@ -1012,7 +1012,7 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 	v9fs_blank_wstat(&wstat);
 	wstat.muid = v9ses->uname;
-	wstat.name = (char *) new_dentry->d_name.name;
+	wstat.name = new_dentry->d_name.name;
 	retval = p9_client_wstat(oldfid, &wstat);
 
 clunk_newdir:
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 5999bd050678..28130b1e53e4 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -244,7 +244,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	int err = 0;
 	kgid_t gid;
 	umode_t mode;
-	char *name = NULL;
+	const unsigned char *name = NULL;
 	struct p9_qid qid;
 	struct inode *inode;
 	struct p9_fid *fid = NULL;
@@ -269,7 +269,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 
 	v9ses = v9fs_inode2v9ses(dir);
 
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
 		 name, flags, omode);
 
@@ -385,7 +385,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL, *dfid = NULL;
 	kgid_t gid;
-	char *name;
+	const unsigned char *name;
 	umode_t mode;
 	struct inode *inode;
 	struct p9_qid qid;
@@ -416,7 +416,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 			 err);
 		goto error;
 	}
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid);
 	if (err < 0)
 		goto error;
@@ -678,14 +678,14 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
 {
 	int err;
 	kgid_t gid;
-	char *name;
+	const unsigned char *name;
 	struct p9_qid qid;
 	struct inode *inode;
 	struct p9_fid *dfid;
 	struct p9_fid *fid = NULL;
 	struct v9fs_session_info *v9ses;
 
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	p9_debug(P9_DEBUG_VFS, "%lu,%s,%s\n", dir->i_ino, name, symname);
 	v9ses = v9fs_inode2v9ses(dir);
 
@@ -699,7 +699,7 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
 	gid = v9fs_get_fsgid_for_create(dir);
 
 	/* Server doesn't alter fid on TSYMLINK. Hence no need to clone it. */
-	err = p9_client_symlink(dfid, name, (char *)symname, gid, &qid);
+	err = p9_client_symlink(dfid, name, symname, gid, &qid);
 
 	if (err < 0) {
 		p9_debug(P9_DEBUG_VFS, "p9_client_symlink failed %d\n", err);
@@ -775,7 +775,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 	if (IS_ERR(oldfid))
 		return PTR_ERR(oldfid);
 
-	err = p9_client_link(dfid, oldfid, (char *)dentry->d_name.name);
+	err = p9_client_link(dfid, oldfid, dentry->d_name.name);
 
 	if (err < 0) {
 		p9_debug(P9_DEBUG_VFS, "p9_client_link failed %d\n", err);
@@ -812,7 +812,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 {
 	int err;
 	kgid_t gid;
-	char *name;
+	const unsigned char *name;
 	umode_t mode;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL, *dfid = NULL;
@@ -842,7 +842,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 			 err);
 		goto error;
 	}
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 
 	err = p9_client_mknod_dotl(dfid, name, mode, rdev, gid, &qid);
 	if (err < 0)
diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index 27dfe85772b1..b8eb51a661e5 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -402,10 +402,10 @@ struct p9_wstat {
 	u32 atime;
 	u32 mtime;
 	u64 length;
-	char *name;
-	char *uid;
-	char *gid;
-	char *muid;
+	const char *name;
+	const char *uid;
+	const char *gid;
+	const char *muid;
 	char *extension;	/* 9p2000.u extensions */
 	kuid_t n_uid;		/* 9p2000.u extensions */
 	kgid_t n_gid;		/* 9p2000.u extensions */
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index c6b97e58cf84..b582339ccef5 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -223,16 +223,16 @@ void p9_client_destroy(struct p9_client *clnt);
 void p9_client_disconnect(struct p9_client *clnt);
 void p9_client_begin_disconnect(struct p9_client *clnt);
 struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
-				char *uname, kuid_t n_uname, char *aname);
+				const char *uname, kuid_t n_uname, const char *aname);
 struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
-		char **wnames, int clone);
+		const unsigned char * const *wnames, int clone);
 int p9_client_open(struct p9_fid *fid, int mode);
-int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
+int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 							char *extension);
-int p9_client_link(struct p9_fid *fid, struct p9_fid *oldfid, char *newname);
-int p9_client_symlink(struct p9_fid *fid, char *name, char *symname, kgid_t gid,
-							struct p9_qid *qid);
-int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode,
+int p9_client_link(struct p9_fid *fid, struct p9_fid *oldfid, const char *newname);
+int p9_client_symlink(struct p9_fid *fid, const char *name, const char *symname,
+		kgid_t gid, struct p9_qid *qid);
+int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode,
 		kgid_t gid, struct p9_qid *qid);
 int p9_client_clunk(struct p9_fid *fid);
 int p9_client_fsync(struct p9_fid *fid, int datasync);
@@ -250,9 +250,9 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *attr);
 struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
 							u64 request_mask);
 
-int p9_client_mknod_dotl(struct p9_fid *oldfid, char *name, int mode,
+int p9_client_mknod_dotl(struct p9_fid *oldfid, const char *name, int mode,
 			dev_t rdev, kgid_t gid, struct p9_qid *);
-int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode,
+int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
 				kgid_t gid, struct p9_qid *);
 int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status);
 int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *fl);
diff --git a/net/9p/client.c b/net/9p/client.c
index 3fc94a49ccd5..5a0c3a64af14 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1101,7 +1101,7 @@ void p9_client_begin_disconnect(struct p9_client *clnt)
 EXPORT_SYMBOL(p9_client_begin_disconnect);
 
 struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
-	char *uname, kuid_t n_uname, char *aname)
+	const char *uname, kuid_t n_uname, const char *aname)
 {
 	int err = 0;
 	struct p9_req_t *req;
@@ -1149,7 +1149,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 EXPORT_SYMBOL(p9_client_attach);
 
 struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
-		char **wnames, int clone)
+		const unsigned char * const *wnames, int clone)
 {
 	int err;
 	struct p9_client *clnt;
@@ -1271,7 +1271,7 @@ int p9_client_open(struct p9_fid *fid, int mode)
 }
 EXPORT_SYMBOL(p9_client_open);
 
-int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode,
+int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode,
 		kgid_t gid, struct p9_qid *qid)
 {
 	int err = 0;
@@ -1316,7 +1316,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode,
 }
 EXPORT_SYMBOL(p9_client_create_dotl);
 
-int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
+int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 		     char *extension)
 {
 	int err;
@@ -1361,8 +1361,8 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
 }
 EXPORT_SYMBOL(p9_client_fcreate);
 
-int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, kgid_t gid,
-		struct p9_qid *qid)
+int p9_client_symlink(struct p9_fid *dfid, const char *name,
+		const char *symtgt, kgid_t gid, struct p9_qid *qid)
 {
 	int err = 0;
 	struct p9_client *clnt;
@@ -1395,7 +1395,7 @@ int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, kgid_t gid,
 }
 EXPORT_SYMBOL(p9_client_symlink);
 
-int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, char *newname)
+int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, const char *newname)
 {
 	struct p9_client *clnt;
 	struct p9_req_t *req;
@@ -2117,7 +2117,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 }
 EXPORT_SYMBOL(p9_client_readdir);
 
-int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode,
+int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode,
 			dev_t rdev, kgid_t gid, struct p9_qid *qid)
 {
 	int err;
@@ -2148,7 +2148,7 @@ int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode,
 }
 EXPORT_SYMBOL(p9_client_mknod_dotl);
 
-int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode,
+int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
 				kgid_t gid, struct p9_qid *qid)
 {
 	int err;
-- 
GitLab


From 5a582cff47c90af29ecb293caa2f667bd4d45e54 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Tue, 17 Jan 2017 13:08:48 +0100
Subject: [PATCH 020/898] clk: meson-gxbb: Export HDMI clocks

Export HDMI clock from internal to dt-bindings.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 drivers/clk/meson/gxbb.h              | 4 ++--
 include/dt-bindings/clock/gxbb-clkc.h | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
index 0252939ba58f..2139e97f5e39 100644
--- a/drivers/clk/meson/gxbb.h
+++ b/drivers/clk/meson/gxbb.h
@@ -231,7 +231,7 @@
 #define CLKID_AHB_DATA_BUS	  60
 #define CLKID_AHB_CTRL_BUS	  61
 #define CLKID_HDMI_INTR_SYNC	  62
-#define CLKID_HDMI_PCLK		  63
+/* CLKID_HDMI_PCLK */
 /* CLKID_USB1_DDR_BRIDGE */
 /* CLKID_USB0_DDR_BRIDGE */
 #define CLKID_MMC_PCLK		  66
@@ -245,7 +245,7 @@
 #define CLKID_VCLK2_VENCI1	  74
 #define CLKID_VCLK2_VENCP0	  75
 #define CLKID_VCLK2_VENCP1	  76
-#define CLKID_GCLK_VENCI_INT0	  77
+/* CLKID_GCLK_VENCI_INT0 */
 #define CLKID_GCLK_VENCI_INT	  78
 #define CLKID_DAC_CLK		  79
 #define CLKID_AOCLK_GATE	  80
diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h
index baade6f429d0..da1d473a5a3a 100644
--- a/include/dt-bindings/clock/gxbb-clkc.h
+++ b/include/dt-bindings/clock/gxbb-clkc.h
@@ -18,8 +18,10 @@
 #define CLKID_USB0		50
 #define CLKID_USB1		51
 #define CLKID_USB		55
+#define CLKID_HDMI_PCLK		63
 #define CLKID_USB1_DDR_BRIDGE	64
 #define CLKID_USB0_DDR_BRIDGE	65
+#define CLKID_GCLK_VENCI_INT0	77
 #define CLKID_AO_I2C		93
 #define CLKID_SD_EMMC_A		94
 #define CLKID_SD_EMMC_B		95
-- 
GitLab


From 890a96a257b497e8361055ffbf66e2fd08833074 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 15 Jan 2017 23:20:29 +0100
Subject: [PATCH 021/898] ARM64: dts: meson-gx: add the missing uart_AO_B

This adds the missing node for the uart_AO_B port to the meson-gx.dtsi
(as this is supported by GXBB, GXL and GXM) along with the required
pinctrl pins. This is required as some boards are using it (the boards
from the Khadas VIM series for example have it exposed on the pin
headers).

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gx.dtsi   | 8 ++++++++
 arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 7 +++++++
 arch/arm64/boot/dts/amlogic/meson-gxl.dtsi  | 7 +++++++
 3 files changed, 22 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index be56b9fae2aa..9212fca6eb94 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -324,6 +324,14 @@
 				status = "disabled";
 			};
 
+			uart_AO_B: serial@4e0 {
+				compatible = "amlogic,meson-uart";
+				reg = <0x0 0x004e0 0x0 0x14>;
+				interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&xtal>;
+				status = "disabled";
+			};
+
 			ir: ir@580 {
 				compatible = "amlogic,meson-gxbb-ir";
 				reg = <0x0 0x00580 0x0 0x40>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 5d686334f692..474435e21759 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -138,6 +138,13 @@
 			};
 		};
 
+		uart_ao_b_pins: uart_ao_b {
+			mux {
+				groups = "uart_tx_ao_b", "uart_rx_ao_b";
+				function = "uart_ao_b";
+			};
+		};
+
 		remote_input_ao_pins: remote_input_ao {
 			mux {
 				groups = "remote_input_ao";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 69216246275d..6d815f9930c9 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -88,6 +88,13 @@
 			};
 		};
 
+		uart_ao_b_pins: uart_ao_b {
+			mux {
+				groups = "uart_tx_ao_b", "uart_rx_ao_b";
+				function = "uart_ao_b";
+			};
+		};
+
 		remote_input_ao_pins: remote_input_ao {
 			mux {
 				groups = "remote_input_ao";
-- 
GitLab


From 261e1d5cc5ee994f17089d8f0d4f8443743d732d Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 15 Jan 2017 23:32:53 +0100
Subject: [PATCH 022/898] ARM64: dts: meson-gx: add the serial CTS and RTS pin
 groups
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds pinctrl group nodes for the CTS and RTS pins of each serial
controller. This makes it possible to enable the CTS and RTS pins which
are controlled by the serial controller hardware (through the meson_uart
driver).

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Tested-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 40 +++++++++++++++++++++
 arch/arm64/boot/dts/amlogic/meson-gxl.dtsi  | 40 +++++++++++++++++++++
 2 files changed, 80 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 474435e21759..f001c4d007bc 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -138,6 +138,14 @@
 			};
 		};
 
+		uart_ao_a_cts_rts_pins: uart_ao_a_cts_rts {
+			mux {
+				groups = "uart_cts_ao_a",
+				       "uart_rts_ao_a";
+				function = "uart_ao";
+			};
+		};
+
 		uart_ao_b_pins: uart_ao_b {
 			mux {
 				groups = "uart_tx_ao_b", "uart_rx_ao_b";
@@ -145,6 +153,14 @@
 			};
 		};
 
+		uart_ao_b_cts_rts_pins: uart_ao_b_cts_rts {
+			mux {
+				groups = "uart_cts_ao_b",
+				       "uart_rts_ao_b";
+				function = "uart_ao_b";
+			};
+		};
+
 		remote_input_ao_pins: remote_input_ao {
 			mux {
 				groups = "remote_input_ao";
@@ -290,6 +306,14 @@
 			};
 		};
 
+		uart_a_cts_rts_pins: uart_a_cts_rts {
+			mux {
+				groups = "uart_cts_a",
+				       "uart_rts_a";
+				function = "uart_a";
+			};
+		};
+
 		uart_b_pins: uart_b {
 			mux {
 				groups = "uart_tx_b",
@@ -298,6 +322,14 @@
 			};
 		};
 
+		uart_b_cts_rts_pins: uart_b_cts_rts {
+			mux {
+				groups = "uart_cts_b",
+				       "uart_rts_b";
+				function = "uart_b";
+			};
+		};
+
 		uart_c_pins: uart_c {
 			mux {
 				groups = "uart_tx_c",
@@ -306,6 +338,14 @@
 			};
 		};
 
+		uart_c_cts_rts_pins: uart_c_cts_rts {
+			mux {
+				groups = "uart_cts_c",
+				       "uart_rts_c";
+				function = "uart_c";
+			};
+		};
+
 		i2c_a_pins: i2c_a {
 			mux {
 				groups = "i2c_sck_a",
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 6d815f9930c9..f3d1566c0a09 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -88,6 +88,14 @@
 			};
 		};
 
+		uart_ao_a_cts_rts_pins: uart_ao_a_cts_rts {
+			mux {
+				groups = "uart_cts_ao_a",
+				       "uart_rts_ao_a";
+				function = "uart_ao";
+			};
+		};
+
 		uart_ao_b_pins: uart_ao_b {
 			mux {
 				groups = "uart_tx_ao_b", "uart_rx_ao_b";
@@ -95,6 +103,14 @@
 			};
 		};
 
+		uart_ao_b_cts_rts_pins: uart_ao_b_cts_rts {
+			mux {
+				groups = "uart_cts_ao_b",
+				       "uart_rts_ao_b";
+				function = "uart_ao_b";
+			};
+		};
+
 		remote_input_ao_pins: remote_input_ao {
 			mux {
 				groups = "remote_input_ao";
@@ -170,6 +186,14 @@
 			};
 		};
 
+		uart_a_cts_rts_pins: uart_a_cts_rts {
+			mux {
+				groups = "uart_cts_a",
+				       "uart_rts_a";
+				function = "uart_a";
+			};
+		};
+
 		uart_b_pins: uart_b {
 			mux {
 				groups = "uart_tx_b",
@@ -178,6 +202,14 @@
 			};
 		};
 
+		uart_b_cts_rts_pins: uart_b_cts_rts {
+			mux {
+				groups = "uart_cts_b",
+				       "uart_rts_b";
+				function = "uart_b";
+			};
+		};
+
 		uart_c_pins: uart_c {
 			mux {
 				groups = "uart_tx_c",
@@ -186,6 +218,14 @@
 			};
 		};
 
+		uart_c_cts_rts_pins: uart_c_cts_rts {
+			mux {
+				groups = "uart_cts_c",
+				       "uart_rts_c";
+				function = "uart_c";
+			};
+		};
+
 		i2c_a_pins: i2c_a {
 			mux {
 				groups = "i2c_sck_a",
-- 
GitLab


From 2fbbc4bf69f293df317559a267f4120f290b8fc4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andreas=20F=C3=A4rber?= <afaerber@suse.de>
Date: Tue, 17 Jan 2017 02:17:53 +0100
Subject: [PATCH 023/898] ARM64: dts: meson-gxbb-vega-s95: Add LED
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is one blue LED on the front of the device. Keep it lit and
configure it as panic indicator.

Signed-off-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
index e59ad308192f..86709929fd20 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
@@ -53,6 +53,17 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	leds {
+		compatible = "gpio-leds";
+
+		blue {
+			label = "vega-s95:blue:on";
+			gpios = <&gpio_ao GPIOAO_13 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+			panic-indicator;
+		};
+	};
+
 	usb_vbus: regulator-usb0-vbus {
 		compatible = "regulator-fixed";
 
-- 
GitLab


From b949165c86cdd230fbb7997a2b2966e860caf372 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Tue, 17 Jan 2017 13:05:38 +0100
Subject: [PATCH 024/898] ARM64: dts: meson-gx: Add HDMI HPD/DDC pinctrl nodes

Add pinctrl nodes for HDMI HPD and DDC pins modes for Amlogic Meson GXL
and GXBB SoCs.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 14 ++++++++++++++
 arch/arm64/boot/dts/amlogic/meson-gxl.dtsi  | 14 ++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index f001c4d007bc..39a774ad83ce 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -453,6 +453,20 @@
 				function = "pwm_f_y";
 			};
 		};
+
+		hdmi_hpd_pins: hdmi_hpd {
+			mux {
+				groups = "hdmi_hpd";
+				function = "hdmi_hpd";
+			};
+		};
+
+		hdmi_i2c_pins: hdmi_i2c {
+			mux {
+				groups = "hdmi_sda", "hdmi_scl";
+				function = "hdmi_i2c";
+			};
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index f3d1566c0a09..bdf2305a2e25 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -276,6 +276,20 @@
 				function = "pwm_e";
 			};
 		};
+
+		hdmi_hpd_pins: hdmi_hpd {
+			mux {
+				groups = "hdmi_hpd";
+				function = "hdmi_hpd";
+			};
+		};
+
+		hdmi_i2c_pins: hdmi_i2c {
+			mux {
+				groups = "hdmi_sda", "hdmi_scl";
+				function = "hdmi_i2c";
+			};
+		};
 	};
 
 	eth-phy-mux {
-- 
GitLab


From 3d071d8da1f586c24863a57349586a1611b9aa67 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <stephan.mueller@atsec.com>
Date: Thu, 15 Dec 2016 12:42:33 +0100
Subject: [PATCH 025/898] random: remove stale maybe_reseed_primary_crng

The function maybe_reseed_primary_crng is not used anywhere and thus can
be removed.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 1ef26403bcc8..8e5ab20848c0 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -855,13 +855,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 	spin_unlock_irqrestore(&primary_crng.lock, flags);
 }
 
-static inline void maybe_reseed_primary_crng(void)
-{
-	if (crng_init > 2 &&
-	    time_after(jiffies, primary_crng.init_time + CRNG_RESEED_INTERVAL))
-		crng_reseed(&primary_crng, &input_pool);
-}
-
 static inline void crng_wait_ready(void)
 {
 	wait_event_interruptible(crng_init_wait, crng_ready());
-- 
GitLab


From 2e03c36f25ebb52d3358b8baebcdf96895c33a87 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Stephan=20M=C3=BCller?= <smueller@chronox.de>
Date: Tue, 27 Dec 2016 23:39:31 +0100
Subject: [PATCH 026/898] random: remove stale urandom_init_wait

The urandom_init_wait wait queue is a left over from the pre-ChaCha20
times and can therefore be savely removed.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 8e5ab20848c0..482531d87fb8 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -409,7 +409,6 @@ static struct poolinfo {
  */
 static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
 static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
-static DECLARE_WAIT_QUEUE_HEAD(urandom_init_wait);
 static struct fasync_struct *fasync;
 
 static DEFINE_SPINLOCK(random_ready_list_lock);
-- 
GitLab


From 43d8a72cd985ca5279a9eb84d61fcbb3ee3d3774 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Stephan=20M=C3=BCller?= <smueller@chronox.de>
Date: Tue, 27 Dec 2016 23:40:59 +0100
Subject: [PATCH 027/898] random: remove variable limit

The variable limit was used to identify the nonblocking pool's unlimited
random number generation. As the nonblocking pool is a thing of the
past, remove the limit variable and any conditions around it (i.e.
preserve the branches for limit == 1).

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c | 30 +++++++-----------------------
 1 file changed, 7 insertions(+), 23 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 482531d87fb8..92d6dd24c86e 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -466,7 +466,6 @@ struct entropy_store {
 	int entropy_count;
 	int entropy_total;
 	unsigned int initialized:1;
-	unsigned int limit:1;
 	unsigned int last_data_init:1;
 	__u8 last_data[EXTRACT_SIZE];
 };
@@ -484,7 +483,6 @@ static __u32 blocking_pool_data[OUTPUT_POOL_WORDS] __latent_entropy;
 static struct entropy_store input_pool = {
 	.poolinfo = &poolinfo_table[0],
 	.name = "input",
-	.limit = 1,
 	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
 	.pool = input_pool_data
 };
@@ -492,7 +490,6 @@ static struct entropy_store input_pool = {
 static struct entropy_store blocking_pool = {
 	.poolinfo = &poolinfo_table[1],
 	.name = "blocking",
-	.limit = 1,
 	.pull = &input_pool,
 	.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
 	.pool = blocking_pool_data,
@@ -1212,15 +1209,6 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 	    r->entropy_count > r->poolinfo->poolfracbits)
 		return;
 
-	if (r->limit == 0 && random_min_urandom_seed) {
-		unsigned long now = jiffies;
-
-		if (time_before(now,
-				r->last_pulled + random_min_urandom_seed * HZ))
-			return;
-		r->last_pulled = now;
-	}
-
 	_xfer_secondary_pool(r, nbytes);
 }
 
@@ -1228,8 +1216,6 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
 	__u32	tmp[OUTPUT_POOL_WORDS];
 
-	/* For /dev/random's pool, always leave two wakeups' worth */
-	int rsvd_bytes = r->limit ? 0 : random_read_wakeup_bits / 4;
 	int bytes = nbytes;
 
 	/* pull at least as much as a wakeup */
@@ -1240,7 +1226,7 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 	trace_xfer_secondary_pool(r->name, bytes * 8, nbytes * 8,
 				  ENTROPY_BITS(r), ENTROPY_BITS(r->pull));
 	bytes = extract_entropy(r->pull, tmp, bytes,
-				random_read_wakeup_bits / 8, rsvd_bytes);
+				random_read_wakeup_bits / 8, 0);
 	mix_pool_bytes(r, tmp, bytes);
 	credit_entropy_bits(r, bytes*8);
 }
@@ -1268,7 +1254,7 @@ static void push_to_pool(struct work_struct *work)
 static size_t account(struct entropy_store *r, size_t nbytes, int min,
 		      int reserved)
 {
-	int entropy_count, orig;
+	int entropy_count, orig, have_bytes;
 	size_t ibytes, nfrac;
 
 	BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
@@ -1277,14 +1263,12 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 retry:
 	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 	ibytes = nbytes;
-	/* If limited, never pull more than available */
-	if (r->limit) {
-		int have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
+	/* never pull more than available */
+	have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
 
-		if ((have_bytes -= reserved) < 0)
-			have_bytes = 0;
-		ibytes = min_t(size_t, ibytes, have_bytes);
-	}
+	if ((have_bytes -= reserved) < 0)
+		have_bytes = 0;
+	ibytes = min_t(size_t, ibytes, have_bytes);
 	if (ibytes < min)
 		ibytes = 0;
 
-- 
GitLab


From 5d0e5ea343a0f70351428476bcf8715e0731f26a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Stephan=20M=C3=BCller?= <smueller@chronox.de>
Date: Tue, 27 Dec 2016 23:41:22 +0100
Subject: [PATCH 028/898] random: fix comment for unused
 random_min_urandom_seed

The variable random_min_urandom_seed is not needed any more as it
defined the reseeding behavior of the nonblocking pool. Though it is not
needed any more, it is left in the code for user space interface
compatibility.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 92d6dd24c86e..9d147d456598 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -313,9 +313,7 @@ static int random_read_wakeup_bits = 64;
 static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
 
 /*
- * The minimum number of seconds between urandom pool reseeding.  We
- * do this to limit the amount of entropy that can be drained from the
- * input pool even if there are heavy demands on /dev/urandom.
+ * Variable is currently unused by left for user space compatibility.
  */
 static int random_min_urandom_seed = 60;
 
-- 
GitLab


From 4e6118974c7ab5d65e77fe8c47c87a85e9c7ed7d Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Thu, 19 Jan 2017 09:21:57 +0100
Subject: [PATCH 029/898] ARM64: dts: meson-gxm: Rename q200 and q201 DT files
 for consistency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to keep consistency naming with the Nexbox A1 DTS file, remove the
S912 SoC name in the GXM DT files.

Suggested-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/Makefile                          | 4 ++--
 .../amlogic/{meson-gxm-s912-q200.dts => meson-gxm-q200.dts}   | 0
 .../amlogic/{meson-gxm-s912-q201.dts => meson-gxm-q201.dts}   | 0
 3 files changed, 2 insertions(+), 2 deletions(-)
 rename arch/arm64/boot/dts/amlogic/{meson-gxm-s912-q200.dts => meson-gxm-q200.dts} (100%)
 rename arch/arm64/boot/dts/amlogic/{meson-gxm-s912-q201.dts => meson-gxm-q201.dts} (100%)

diff --git a/arch/arm64/boot/dts/amlogic/Makefile b/arch/arm64/boot/dts/amlogic/Makefile
index 0d7bfbf7d922..1aca8e58ad2b 100644
--- a/arch/arm64/boot/dts/amlogic/Makefile
+++ b/arch/arm64/boot/dts/amlogic/Makefile
@@ -9,8 +9,8 @@ dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-p212.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p230.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p231.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-nexbox-a95x.dtb
-dtb-$(CONFIG_ARCH_MESON) += meson-gxm-s912-q200.dtb
-dtb-$(CONFIG_ARCH_MESON) += meson-gxm-s912-q201.dtb
+dtb-$(CONFIG_ARCH_MESON) += meson-gxm-q200.dtb
+dtb-$(CONFIG_ARCH_MESON) += meson-gxm-q201.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxm-nexbox-a1.dtb
 
 always		:= $(dtb-y)
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-s912-q200.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts
similarity index 100%
rename from arch/arm64/boot/dts/amlogic/meson-gxm-s912-q200.dts
rename to arch/arm64/boot/dts/amlogic/meson-gxm-q200.dts
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-s912-q201.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-q201.dts
similarity index 100%
rename from arch/arm64/boot/dts/amlogic/meson-gxm-s912-q201.dts
rename to arch/arm64/boot/dts/amlogic/meson-gxm-q201.dts
-- 
GitLab


From 100bd9a961e368490daa8cdbb2f41b03ef50164a Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Wed, 18 Jan 2017 11:50:40 +0100
Subject: [PATCH 030/898] dt-bindings: vendor-prefix: Add wetek vendor prefix

Add prefix for WeTek Electronics, limited, a company producing multimedia
Set-Top-Boxes and supporting KODI and LibreELEC distributions.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 16d3b5e7f5d1..0c16d8581d13 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -320,6 +320,7 @@ virtio	Virtual I/O Device Specification, developed by the OASIS consortium
 vivante	Vivante Corporation
 voipac	Voipac Technologies s.r.o.
 wd	Western Digital Corp.
+wetek	WeTek Electronics, limited.
 wexler	Wexler
 winbond Winbond Electronics corp.
 wlf	Wolfson Microelectronics
-- 
GitLab


From d537d289de06f57f5342106208ecf17ea83f23e2 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Wed, 18 Jan 2017 11:50:41 +0100
Subject: [PATCH 031/898] ARM64: dts: meson-gxbb: Add support for WeTek Hub and
 Play

Adds support for the WeTek Hub and Play2 boards.
The Hub is an extremely small IPTv Set-Top-Box and the Play2 is a more
traditionnal Satellite or Terrestrial and IPTv Set-Top-Box.

Both are based on the p200 Reference Design and out-of-tree support is
based on LibreELEC kernel at [1].

[1] https://github.com/wetek-enigma/linux-amlogic

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/Makefile          |  2 +
 .../boot/dts/amlogic/meson-gxbb-wetek-hub.dts | 66 +++++++++++++
 .../dts/amlogic/meson-gxbb-wetek-play2.dts    | 94 +++++++++++++++++++
 3 files changed, 162 insertions(+)
 create mode 100644 arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts
 create mode 100644 arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts

diff --git a/arch/arm64/boot/dts/amlogic/Makefile b/arch/arm64/boot/dts/amlogic/Makefile
index 1aca8e58ad2b..293e985e3dfa 100644
--- a/arch/arm64/boot/dts/amlogic/Makefile
+++ b/arch/arm64/boot/dts/amlogic/Makefile
@@ -5,6 +5,8 @@ dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-p201.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-vega-s95-pro.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-vega-s95-meta.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-vega-s95-telos.dtb
+dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-wetek-hub.dtb
+dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-wetek-play2.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-p212.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p230.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p231.dtb
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts
new file mode 100644
index 000000000000..56f855901262
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-hub.dts
@@ -0,0 +1,66 @@
+/*
+ * Copyright (c) 2016 BayLibre, Inc.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include "meson-gxbb-p20x.dtsi"
+
+/ {
+	compatible = "wetek,hub", "amlogic,meson-gxbb";
+	model = "WeTek Hub";
+
+	leds {
+		compatible = "gpio-leds";
+
+		system {
+			label = "wetek-play:system-status";
+			gpios = <&gpio_ao GPIOAO_13 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+			panic-indicator;
+		};
+	};
+
+	cvbs-connector {
+		status = "disabled";
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts
new file mode 100644
index 000000000000..ea79fdd2c248
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek-play2.dts
@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2016 BayLibre, Inc.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This library is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include "meson-gxbb-p20x.dtsi"
+#include <dt-bindings/input/input.h>
+
+/ {
+	compatible = "wetek,play2", "amlogic,meson-gxbb";
+	model = "WeTek Play 2";
+
+	leds {
+		compatible = "gpio-leds";
+
+		system {
+			label = "wetek-play:system-status";
+			gpios = <&gpio_ao GPIOAO_13 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+			panic-indicator;
+		};
+
+		wifi {
+			label = "wetek-play:wifi-status";
+			gpios = <&gpio GPIODV_26 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		ethernet {
+			label = "wetek-play:ethernet-status";
+			gpios = <&gpio GPIODV_27 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+	};
+
+	gpio-keys-polled {
+		compatible = "gpio-keys-polled";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		poll-interval = <100>;
+
+		button@0 {
+			label = "reset";
+			linux,code = <KEY_RESTART>;
+			gpios = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&i2c_A {
+	status = "okay";
+	pinctrl-0 = <&i2c_a_pins>;
+	pinctrl-names = "default";
+};
-- 
GitLab


From 0264a88d6153e6cd5ee61239058b2002f36dde6b Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Wed, 18 Jan 2017 11:50:42 +0100
Subject: [PATCH 032/898] dt-bindings: amlogic: Add WeTek boards

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 Documentation/devicetree/bindings/arm/amlogic.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/amlogic.txt b/Documentation/devicetree/bindings/arm/amlogic.txt
index 9b2b41ab6817..c246cd2730d9 100644
--- a/Documentation/devicetree/bindings/arm/amlogic.txt
+++ b/Documentation/devicetree/bindings/arm/amlogic.txt
@@ -40,6 +40,8 @@ Board compatible values:
   - "hardkernel,odroid-c2" (Meson gxbb)
   - "amlogic,p200" (Meson gxbb)
   - "amlogic,p201" (Meson gxbb)
+  - "wetek,hub" (Meson gxbb)
+  - "wetek,play2" (Meson gxbb)
   - "amlogic,p212" (Meson gxl s905x)
   - "amlogic,p230" (Meson gxl s905d)
   - "amlogic,p231" (Meson gxl s905d)
-- 
GitLab


From 33d0fcdfe0e87070d96c678e554d711ae15b9fa6 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 19 Jan 2017 15:58:20 +0100
Subject: [PATCH 033/898] clk: gxbb: add the SAR ADC clocks and expose them

The HHI_SAR_CLK_CNTL contains three SAR ADC specific clocks:
- a mux clock to choose between different ADC reference clocks (this is
  2-bit wide, but the datasheet only lists the parents for the first
  bit)
- a divider for the input/reference clock
- a gate which enables the ADC clock

Additionally this exposes the ADC core clock (CLKID_SAR_ADC) and
CLKID_SANA (which seems to enable the analog inputs, but unfortunately
there is no documentation for this - we just mimic what the vendor
driver does).

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Tested-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 drivers/clk/meson/gxbb.c              | 48 +++++++++++++++++++++++++++
 drivers/clk/meson/gxbb.h              |  9 +++--
 include/dt-bindings/clock/gxbb-clkc.h |  4 +++
 3 files changed, 58 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 9d9af446bafc..1c1ec137a3cc 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -564,6 +564,46 @@ static struct clk_gate gxbb_clk81 = {
 	},
 };
 
+static struct clk_mux gxbb_sar_adc_clk_sel = {
+	.reg = (void *)HHI_SAR_CLK_CNTL,
+	.mask = 0x3,
+	.shift = 9,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sar_adc_clk_sel",
+		.ops = &clk_mux_ops,
+		/* NOTE: The datasheet doesn't list the parents for bit 10 */
+		.parent_names = (const char *[]){ "xtal", "clk81", },
+		.num_parents = 2,
+	},
+};
+
+static struct clk_divider gxbb_sar_adc_clk_div = {
+	.reg = (void *)HHI_SAR_CLK_CNTL,
+	.shift = 0,
+	.width = 8,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sar_adc_clk_div",
+		.ops = &clk_divider_ops,
+		.parent_names = (const char *[]){ "sar_adc_clk_sel" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_gate gxbb_sar_adc_clk = {
+	.reg = (void *)HHI_SAR_CLK_CNTL,
+	.bit_idx = 8,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sar_adc_clk",
+		.ops = &clk_gate_ops,
+		.parent_names = (const char *[]){ "sar_adc_clk_div" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 /* Everything Else (EE) domain gates */
 static MESON_GATE(gxbb_ddr, HHI_GCLK_MPEG0, 0);
 static MESON_GATE(gxbb_dos, HHI_GCLK_MPEG0, 1);
@@ -754,6 +794,9 @@ static struct clk_hw_onecell_data gxbb_hw_onecell_data = {
 		[CLKID_SD_EMMC_A]	    = &gxbb_emmc_a.hw,
 		[CLKID_SD_EMMC_B]	    = &gxbb_emmc_b.hw,
 		[CLKID_SD_EMMC_C]	    = &gxbb_emmc_c.hw,
+		[CLKID_SAR_ADC_CLK]	    = &gxbb_sar_adc_clk.hw,
+		[CLKID_SAR_ADC_SEL]	    = &gxbb_sar_adc_clk_sel.hw,
+		[CLKID_SAR_ADC_DIV]	    = &gxbb_sar_adc_clk_div.hw,
 	},
 	.num = NR_CLKS,
 };
@@ -856,6 +899,7 @@ static struct clk_gate *gxbb_clk_gates[] = {
 	&gxbb_emmc_a,
 	&gxbb_emmc_b,
 	&gxbb_emmc_c,
+	&gxbb_sar_adc_clk,
 };
 
 static int gxbb_clkc_probe(struct platform_device *pdev)
@@ -888,6 +932,10 @@ static int gxbb_clkc_probe(struct platform_device *pdev)
 	gxbb_mpeg_clk_sel.reg = clk_base + (u64)gxbb_mpeg_clk_sel.reg;
 	gxbb_mpeg_clk_div.reg = clk_base + (u64)gxbb_mpeg_clk_div.reg;
 
+	/* Populate the base address for the SAR ADC clks */
+	gxbb_sar_adc_clk_sel.reg = clk_base + (u64)gxbb_sar_adc_clk_sel.reg;
+	gxbb_sar_adc_clk_div.reg = clk_base + (u64)gxbb_sar_adc_clk_div.reg;
+
 	/* Populate base address for gates */
 	for (i = 0; i < ARRAY_SIZE(gxbb_clk_gates); i++)
 		gxbb_clk_gates[i]->reg = clk_base +
diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
index 2139e97f5e39..dc487180f847 100644
--- a/drivers/clk/meson/gxbb.h
+++ b/drivers/clk/meson/gxbb.h
@@ -191,7 +191,7 @@
 #define CLKID_PERIPHS		  20
 #define CLKID_SPICC		  21
 /* CLKID_I2C */
-#define CLKID_SAR_ADC		  23
+/* #define CLKID_SAR_ADC */
 #define CLKID_SMART_CARD	  24
 #define CLKID_RNG0		  25
 #define CLKID_UART0		  26
@@ -237,7 +237,7 @@
 #define CLKID_MMC_PCLK		  66
 #define CLKID_DVIN		  67
 #define CLKID_UART2		  68
-#define CLKID_SANA		  69
+/* #define CLKID_SANA */
 #define CLKID_VPU_INTR		  70
 #define CLKID_SEC_AHB_AHB3_BRIDGE 71
 #define CLKID_CLK81_A53		  72
@@ -265,8 +265,11 @@
 /* CLKID_SD_EMMC_A */
 /* CLKID_SD_EMMC_B */
 /* CLKID_SD_EMMC_C */
+/* CLKID_SAR_ADC_CLK */
+/* CLKID_SAR_ADC_SEL */
+#define CLKID_SAR_ADC_DIV	  99
 
-#define NR_CLKS			  97
+#define NR_CLKS			  100
 
 /* include the CLKIDs that have been made part of the stable DT binding */
 #include <dt-bindings/clock/gxbb-clkc.h>
diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h
index da1d473a5a3a..692846c7941b 100644
--- a/include/dt-bindings/clock/gxbb-clkc.h
+++ b/include/dt-bindings/clock/gxbb-clkc.h
@@ -14,6 +14,7 @@
 #define CLKID_MPLL2		15
 #define CLKID_SPI		34
 #define CLKID_I2C		22
+#define CLKID_SAR_ADC		23
 #define CLKID_ETH		36
 #define CLKID_USB0		50
 #define CLKID_USB1		51
@@ -21,10 +22,13 @@
 #define CLKID_HDMI_PCLK		63
 #define CLKID_USB1_DDR_BRIDGE	64
 #define CLKID_USB0_DDR_BRIDGE	65
+#define CLKID_SANA		69
 #define CLKID_GCLK_VENCI_INT0	77
 #define CLKID_AO_I2C		93
 #define CLKID_SD_EMMC_A		94
 #define CLKID_SD_EMMC_B		95
 #define CLKID_SD_EMMC_C		96
+#define CLKID_SAR_ADC_CLK	97
+#define CLKID_SAR_ADC_SEL	98
 
 #endif /* __GXBB_CLKC_H */
-- 
GitLab


From 7eea67101b9713ae438955e8899b3c4b078419f9 Mon Sep 17 00:00:00 2001
From: Kevin Hilman <khilman@baylibre.com>
Date: Fri, 20 Jan 2017 07:57:52 -0800
Subject: [PATCH 034/898] ARM64: dts: meson-gxl: rename Nexbox A95x for
 consistency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the GXL family has S905X and S905D SoCs, we're keeping the SoC
name in the DTS filename for clarity.  Rename this file accordingly to
be consistent with the rest of the GXL DTS files.

Cc: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/Makefile                            | 2 +-
 ...eson-gxl-nexbox-a95x.dts => meson-gxl-s905x-nexbox-a95x.dts} | 0
 2 files changed, 1 insertion(+), 1 deletion(-)
 rename arch/arm64/boot/dts/amlogic/{meson-gxl-nexbox-a95x.dts => meson-gxl-s905x-nexbox-a95x.dts} (100%)

diff --git a/arch/arm64/boot/dts/amlogic/Makefile b/arch/arm64/boot/dts/amlogic/Makefile
index 293e985e3dfa..3f94bce33b7f 100644
--- a/arch/arm64/boot/dts/amlogic/Makefile
+++ b/arch/arm64/boot/dts/amlogic/Makefile
@@ -10,7 +10,7 @@ dtb-$(CONFIG_ARCH_MESON) += meson-gxbb-wetek-play2.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-p212.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p230.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905d-p231.dtb
-dtb-$(CONFIG_ARCH_MESON) += meson-gxl-nexbox-a95x.dtb
+dtb-$(CONFIG_ARCH_MESON) += meson-gxl-s905x-nexbox-a95x.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxm-q200.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxm-q201.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-gxm-nexbox-a1.dtb
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
similarity index 100%
rename from arch/arm64/boot/dts/amlogic/meson-gxl-nexbox-a95x.dts
rename to arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
-- 
GitLab


From 2d3b74d3836901c8601e147b1ae24170f9fa2982 Mon Sep 17 00:00:00 2001
From: jbrunet <jbrunet@baylibre.com>
Date: Thu, 26 Jan 2017 17:05:49 +0100
Subject: [PATCH 035/898] clk: gxbb: fix CLKID_ETH defined twice

CLKID_ETH is define in the dt-bindings but has not be commented out in the
clock driver. Just do it now.

Fixes: 738f66d3211d ("clk: gxbb: add AmLogic GXBB clk controller driver")
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Acked-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 drivers/clk/meson/gxbb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
index dc487180f847..8ee2022ce5d5 100644
--- a/drivers/clk/meson/gxbb.h
+++ b/drivers/clk/meson/gxbb.h
@@ -204,7 +204,7 @@
 #define CLKID_ASSIST_MISC	  33
 /* CLKID_SPI */
 #define CLKID_I2S_SPDIF		  35
-#define CLKID_ETH		  36
+/* CLKID_ETH */
 #define CLKID_DEMUX		  37
 #define CLKID_AIU_GLUE		  38
 #define CLKID_IEC958		  39
-- 
GitLab


From e48512244f653960cfbb002597686362558533d1 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 22 Jan 2017 22:05:26 +0100
Subject: [PATCH 036/898] ARM64: dts: meson-gx: add the missing pwm_AO_ab node

All Meson GX SoCs (GXBB, GXL and GXM) have a PWM controller within the
AO domain. When one of the board's LEDs is connected to one of the AO
PWM pins then this can be used to dim that LED (when the leds-pwm driver
is used).
Add the pwm_AO_ab to allow such devices to use the leds-pwm driver.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 9212fca6eb94..9110dc1a2481 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -332,6 +332,13 @@
 				status = "disabled";
 			};
 
+			pwm_AO_ab: pwm@550 {
+				compatible = "amlogic,meson-gx-pwm", "amlogic,meson-gxbb-pwm";
+				reg = <0x0 0x00550 0x0 0x10>;
+				#pwm-cells = <3>;
+				status = "disabled";
+			};
+
 			ir: ir@580 {
 				compatible = "amlogic,meson-gxbb-ir";
 				reg = <0x0 0x00580 0x0 0x40>;
-- 
GitLab


From 249a2243e97edcd2cb0bef01a934d4ba21fb167f Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 22 Jan 2017 22:05:28 +0100
Subject: [PATCH 037/898] ARM64: dts: meson-gxl: add the pwm_ao_b pin

This adds the pwm_ao_b pin to allow boards which have an LED connected
to GPIOAO_9 to use the leds-pwm driver (by activating the pwm_AO_ab node
and passing the pwm_ao_b_pin pinctrl-reference).

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gxl.dtsi | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index bdf2305a2e25..5f1100af72b1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -117,6 +117,13 @@
 				function = "remote_input_ao";
 			};
 		};
+
+		pwm_ao_b_pins: pwm_ao_b {
+			mux {
+				groups = "pwm_ao_b";
+				function = "pwm_ao_b";
+			};
+		};
 	};
 };
 
-- 
GitLab


From f5b98461cb8167ba362ad9f74c41d126b7becea7 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Fri, 6 Jan 2017 19:32:01 +0100
Subject: [PATCH 038/898] random: use chacha20 for get_random_int/long

Now that our crng uses chacha20, we can rely on its speedy
characteristics for replacing MD5, while simultaneously achieving a
higher security guarantee. Before the idea was to use these functions if
you wanted random integers that aren't stupidly insecure but aren't
necessarily secure either, a vague gray zone, that hopefully was "good
enough" for its users. With chacha20, we can strengthen this claim,
since either we're using an rdrand-like instruction, or we're using the
same crng as /dev/urandom. And it's faster than what was before.

We could have chosen to replace this with a SipHash-derived function,
which might be slightly faster, but at the cost of having yet another
RNG construction in the kernel. By moving to chacha20, we have a single
RNG to analyze and verify, and we also already get good performance
improvements on all platforms.

Implementation-wise, rather than use a generic buffer for both
get_random_int/long and memcpy based on the size needs, we use a
specific buffer for 32-bit reads and for 64-bit reads. This way, we're
guaranteed to always have aligned accesses on all platforms. While
slightly more verbose in C, the assembly this generates is a lot
simpler than otherwise.

Finally, on 32-bit platforms where longs and ints are the same size,
we simply alias get_random_int to get_random_long.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Suggested-by: Theodore Ts'o <tytso@mit.edu>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c  | 84 +++++++++++++++++++++---------------------
 include/linux/random.h |  1 -
 init/main.c            |  1 -
 3 files changed, 43 insertions(+), 43 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 9d147d456598..b800e5479b7d 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -2016,63 +2016,65 @@ struct ctl_table random_table[] = {
 };
 #endif 	/* CONFIG_SYSCTL */
 
-static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
-
-int random_int_secret_init(void)
-{
-	get_random_bytes(random_int_secret, sizeof(random_int_secret));
-	return 0;
-}
-
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
-		__aligned(sizeof(unsigned long));
+struct batched_entropy {
+	union {
+		unsigned long entropy_long[CHACHA20_BLOCK_SIZE / sizeof(unsigned long)];
+		unsigned int entropy_int[CHACHA20_BLOCK_SIZE / sizeof(unsigned int)];
+	};
+	unsigned int position;
+};
 
 /*
- * Get a random word for internal kernel use only. Similar to urandom but
- * with the goal of minimal entropy pool depletion. As a result, the random
- * value is not cryptographically secure but for several uses the cost of
- * depleting entropy is too high
+ * Get a random word for internal kernel use only. The quality of the random
+ * number is either as good as RDRAND or as good as /dev/urandom, with the
+ * goal of being quite fast and not depleting entropy.
  */
-unsigned int get_random_int(void)
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_long);
+unsigned long get_random_long(void)
 {
-	__u32 *hash;
-	unsigned int ret;
+	unsigned long ret;
+	struct batched_entropy *batch;
 
-	if (arch_get_random_int(&ret))
+	if (arch_get_random_long(&ret))
 		return ret;
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = hash[0];
-	put_cpu_var(get_random_int_hash);
-
+	batch = &get_cpu_var(batched_entropy_long);
+	if (batch->position % ARRAY_SIZE(batch->entropy_long) == 0) {
+		extract_crng((u8 *)batch->entropy_long);
+		batch->position = 0;
+	}
+	ret = batch->entropy_long[batch->position++];
+	put_cpu_var(batched_entropy_long);
 	return ret;
 }
-EXPORT_SYMBOL(get_random_int);
+EXPORT_SYMBOL(get_random_long);
 
-/*
- * Same as get_random_int(), but returns unsigned long.
- */
-unsigned long get_random_long(void)
+#if BITS_PER_LONG == 32
+unsigned int get_random_int(void)
 {
-	__u32 *hash;
-	unsigned long ret;
+	return get_random_long();
+}
+#else
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_int);
+unsigned int get_random_int(void)
+{
+	unsigned int ret;
+	struct batched_entropy *batch;
 
-	if (arch_get_random_long(&ret))
+	if (arch_get_random_int(&ret))
 		return ret;
 
-	hash = get_cpu_var(get_random_int_hash);
-
-	hash[0] += current->pid + jiffies + random_get_entropy();
-	md5_transform(hash, random_int_secret);
-	ret = *(unsigned long *)hash;
-	put_cpu_var(get_random_int_hash);
-
+	batch = &get_cpu_var(batched_entropy_int);
+	if (batch->position % ARRAY_SIZE(batch->entropy_int) == 0) {
+		extract_crng((u8 *)batch->entropy_int);
+		batch->position = 0;
+	}
+	ret = batch->entropy_int[batch->position++];
+	put_cpu_var(batched_entropy_int);
 	return ret;
 }
-EXPORT_SYMBOL(get_random_long);
+#endif
+EXPORT_SYMBOL(get_random_int);
 
 /**
  * randomize_page - Generate a random, page aligned address
diff --git a/include/linux/random.h b/include/linux/random.h
index 7bd2403e4fef..16ab429735a7 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -37,7 +37,6 @@ extern void get_random_bytes(void *buf, int nbytes);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
 extern void del_random_ready_callback(struct random_ready_callback *rdy);
 extern void get_random_bytes_arch(void *buf, int nbytes);
-extern int random_int_secret_init(void);
 
 #ifndef MODULE
 extern const struct file_operations random_fops, urandom_fops;
diff --git a/init/main.c b/init/main.c
index b0c9d6facef9..09beb7fc6e8c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -879,7 +879,6 @@ static void __init do_basic_setup(void)
 	do_ctors();
 	usermodehelper_enable();
 	do_initcalls();
-	random_int_secret_init();
 }
 
 static void __init do_pre_smp_initcalls(void)
-- 
GitLab


From c440408cf6901eeb2c09563397e24a9097907078 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sun, 22 Jan 2017 16:34:08 +0100
Subject: [PATCH 039/898] random: convert get_random_int/long into
 get_random_u32/u64

Many times, when a user wants a random number, he wants a random number
of a guaranteed size. So, thinking of get_random_int and get_random_long
in terms of get_random_u32 and get_random_u64 makes it much easier to
achieve this. It also makes the code simpler.

On 32-bit platforms, get_random_int and get_random_long are both aliased
to get_random_u32. On 64-bit platforms, int->u32 and long->u64.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c  | 55 +++++++++++++++++++++---------------------
 include/linux/random.h | 17 +++++++++++--
 2 files changed, 42 insertions(+), 30 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index b800e5479b7d..066ae125f2c8 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -2018,8 +2018,8 @@ struct ctl_table random_table[] = {
 
 struct batched_entropy {
 	union {
-		unsigned long entropy_long[CHACHA20_BLOCK_SIZE / sizeof(unsigned long)];
-		unsigned int entropy_int[CHACHA20_BLOCK_SIZE / sizeof(unsigned int)];
+		u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)];
+		u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)];
 	};
 	unsigned int position;
 };
@@ -2029,52 +2029,51 @@ struct batched_entropy {
  * number is either as good as RDRAND or as good as /dev/urandom, with the
  * goal of being quite fast and not depleting entropy.
  */
-static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_long);
-unsigned long get_random_long(void)
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64);
+u64 get_random_u64(void)
 {
-	unsigned long ret;
+	u64 ret;
 	struct batched_entropy *batch;
 
-	if (arch_get_random_long(&ret))
+#if BITS_PER_LONG == 64
+	if (arch_get_random_long((unsigned long *)&ret))
 		return ret;
+#else
+	if (arch_get_random_long((unsigned long *)&ret) &&
+	    arch_get_random_long((unsigned long *)&ret + 1))
+	    return ret;
+#endif
 
-	batch = &get_cpu_var(batched_entropy_long);
-	if (batch->position % ARRAY_SIZE(batch->entropy_long) == 0) {
-		extract_crng((u8 *)batch->entropy_long);
+	batch = &get_cpu_var(batched_entropy_u64);
+	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
+		extract_crng((u8 *)batch->entropy_u64);
 		batch->position = 0;
 	}
-	ret = batch->entropy_long[batch->position++];
-	put_cpu_var(batched_entropy_long);
+	ret = batch->entropy_u64[batch->position++];
+	put_cpu_var(batched_entropy_u64);
 	return ret;
 }
-EXPORT_SYMBOL(get_random_long);
+EXPORT_SYMBOL(get_random_u64);
 
-#if BITS_PER_LONG == 32
-unsigned int get_random_int(void)
-{
-	return get_random_long();
-}
-#else
-static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_int);
-unsigned int get_random_int(void)
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32);
+u32 get_random_u32(void)
 {
-	unsigned int ret;
+	u32 ret;
 	struct batched_entropy *batch;
 
 	if (arch_get_random_int(&ret))
 		return ret;
 
-	batch = &get_cpu_var(batched_entropy_int);
-	if (batch->position % ARRAY_SIZE(batch->entropy_int) == 0) {
-		extract_crng((u8 *)batch->entropy_int);
+	batch = &get_cpu_var(batched_entropy_u32);
+	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
+		extract_crng((u8 *)batch->entropy_u32);
 		batch->position = 0;
 	}
-	ret = batch->entropy_int[batch->position++];
-	put_cpu_var(batched_entropy_int);
+	ret = batch->entropy_u32[batch->position++];
+	put_cpu_var(batched_entropy_u32);
 	return ret;
 }
-#endif
-EXPORT_SYMBOL(get_random_int);
+EXPORT_SYMBOL(get_random_u32);
 
 /**
  * randomize_page - Generate a random, page aligned address
diff --git a/include/linux/random.h b/include/linux/random.h
index 16ab429735a7..ed5c3838780d 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -42,8 +42,21 @@ extern void get_random_bytes_arch(void *buf, int nbytes);
 extern const struct file_operations random_fops, urandom_fops;
 #endif
 
-unsigned int get_random_int(void);
-unsigned long get_random_long(void);
+u32 get_random_u32(void);
+u64 get_random_u64(void);
+static inline unsigned int get_random_int(void)
+{
+	return get_random_u32();
+}
+static inline unsigned long get_random_long(void)
+{
+#if BITS_PER_LONG == 64
+	return get_random_u64();
+#else
+	return get_random_u32();
+#endif
+}
+
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
 u32 prandom_u32(void);
-- 
GitLab


From bd80ef5ed46233d90f216805ff40aba326ff1bdd Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 22 Jan 2017 19:17:14 +0100
Subject: [PATCH 040/898] ARM64: dts: meson: meson-gx: add the SAR ADC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the SAR ADC to meson-gxbb.dtsi and meson-gxl.dtsi. GXBB provides a
10-bit ADC while GXL and GXM provide a 12-bit ADC.
Some boards use resistor ladder buttons connected through one of the ADC
channels. On newer devices (GXL and GXM) some boards use pull-ups/downs
to change the resistance (and thus the ADC value) on one of the ADC
channels to indicate the board revision.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Tested-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 arch/arm64/boot/dts/amlogic/meson-gx.dtsi   |  8 ++++++++
 arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 10 ++++++++++
 arch/arm64/boot/dts/amlogic/meson-gxl.dtsi  | 10 ++++++++++
 arch/arm64/boot/dts/amlogic/meson-gxm.dtsi  |  4 ++++
 4 files changed, 32 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 9110dc1a2481..f100d0b013b4 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -237,6 +237,14 @@
 				status = "disabled";
 			};
 
+			saradc: adc@8680 {
+				compatible = "amlogic,meson-saradc";
+				reg = <0x0 0x8680 0x0 0x34>;
+				#io-channel-cells = <1>;
+				interrupts = <GIC_SPI 73 IRQ_TYPE_EDGE_RISING>;
+				status = "disabled";
+			};
+
 			pwm_ef: pwm@86c0 {
 				compatible = "amlogic,meson-gx-pwm", "amlogic,meson-gxbb-pwm";
 				reg = <0x0 0x086c0 0x0 0x10>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 39a774ad83ce..04b3324bc132 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -490,6 +490,16 @@
 	clocks = <&clkc CLKID_I2C>;
 };
 
+&saradc {
+	compatible = "amlogic,meson-gxbb-saradc", "amlogic,meson-saradc";
+	clocks = <&xtal>,
+		 <&clkc CLKID_SAR_ADC>,
+		 <&clkc CLKID_SANA>,
+		 <&clkc CLKID_SAR_ADC_CLK>,
+		 <&clkc CLKID_SAR_ADC_SEL>;
+	clock-names = "clkin", "core", "sana", "adc_clk", "adc_sel";
+};
+
 &sd_emmc_a {
 	clocks = <&clkc CLKID_SD_EMMC_A>,
 		 <&xtal>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 5f1100af72b1..fe11b5fc61f7 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -347,6 +347,16 @@
 	clocks = <&clkc CLKID_I2C>;
 };
 
+&saradc {
+	compatible = "amlogic,meson-gxl-saradc", "amlogic,meson-saradc";
+	clocks = <&xtal>,
+		 <&clkc CLKID_SAR_ADC>,
+		 <&clkc CLKID_SANA>,
+		 <&clkc CLKID_SAR_ADC_CLK>,
+		 <&clkc CLKID_SAR_ADC_SEL>;
+	clock-names = "clkin", "core", "sana", "adc_clk", "adc_sel";
+};
+
 &sd_emmc_a {
 	clocks = <&clkc CLKID_SD_EMMC_A>,
 		 <&xtal>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
index 4c55665a253f..ddea7305c644 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
@@ -117,6 +117,10 @@
 	};
 };
 
+&saradc {
+	compatible = "amlogic,meson-gxm-saradc", "amlogic,meson-saradc";
+};
+
 &scpi_dvfs {
 	clock-indices = <0 1>;
 	clock-output-names = "vbig", "vlittle";
-- 
GitLab


From 6b6a1867667a90f399762dc1ee6add5b4aa646c9 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Mon, 16 Jan 2017 11:22:45 +0100
Subject: [PATCH 041/898] ARM64: dts: meson-gxbb-p200: add ADC laddered keys

Add the 5 buttons connected to a resistor laddered matrix and sampled
by the SAR ADC channel 0.

Only the p200 board has these buttons, the P201 doesn't.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
---
 .../boot/dts/amlogic/meson-gxbb-p200.dts      | 50 +++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
index 03e3d76626dd..fc0e86cb4cde 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
@@ -45,10 +45,55 @@
 /dts-v1/;
 
 #include "meson-gxbb-p20x.dtsi"
+#include <dt-bindings/input/input.h>
 
 / {
 	compatible = "amlogic,p200", "amlogic,meson-gxbb";
 	model = "Amlogic Meson GXBB P200 Development Board";
+
+	avdd18_usb_adc: regulator-avdd18_usb_adc {
+		compatible = "regulator-fixed";
+		regulator-name = "AVDD18_USB_ADC";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	adc_keys {
+		compatible = "adc-keys";
+		io-channels = <&saradc 0>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+
+		button-home {
+			label = "Home";
+			linux,code = <KEY_HOME>;
+			press-threshold-microvolt = <900000>; /* 50% */
+		};
+
+		button-esc {
+			label = "Esc";
+			linux,code = <KEY_ESC>;
+			press-threshold-microvolt = <684000>; /* 38% */
+		};
+
+		button-up {
+			label = "Volume Up";
+			linux,code = <KEY_VOLUMEUP>;
+			press-threshold-microvolt = <468000>; /* 26% */
+		};
+
+		button-down {
+			label = "Volume Down";
+			linux,code = <KEY_VOLUMEDOWN>;
+			press-threshold-microvolt = <252000>; /* 14% */
+		};
+
+		button-menu {
+			label = "Menu";
+			linux,code = <KEY_MENU>;
+			press-threshold-microvolt = <0>; /* 0% */
+		};
+	};
 };
 
 &i2c_B {
@@ -56,3 +101,8 @@
 	pinctrl-0 = <&i2c_b_pins>;
 	pinctrl-names = "default";
 };
+
+&saradc {
+	status = "okay";
+	vref-supply = <&avdd18_usb_adc>;
+};
-- 
GitLab


From d1160ebff1fea7ac7f6e6533b43144d377b56e6f Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 30 Jan 2017 11:57:36 +0100
Subject: [PATCH 042/898] arm64: dts: exynos: Add initial configuration for
 DISP clocks for TM2/TM2e

Add initial clock configuration for display subsystem for Exynos5433
based TM2/TM2e boards in device tree in order to avoid dependency on the
configuration left by the bootloader. This initial configuration is also
needed to ensure that display subsystem is operational if display power
domain gets turned off before clock controller is probed and the inital
clock configuration left by the bootloader saved.

TM2 and TM2e uses different rate for DISP PLL clock, but for better
maintainability all 'assigned-clocks-*' properties for DISP CMU are
defines in each board dts instead of redefining the rates property.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 .../dts/exynos/exynos5433-tm2-common.dtsi     | 12 -------
 arch/arm64/boot/dts/exynos/exynos5433-tm2.dts | 34 +++++++++++++++++++
 .../arm64/boot/dts/exynos/exynos5433-tm2e.dts | 34 +++++++++++++++++++
 3 files changed, 68 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
index 53fd0683d400..098ad557fee3 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
@@ -217,18 +217,6 @@
 	assigned-clock-parents = <&cmu_top CLK_FOUT_AUD_PLL>;
 };
 
-&cmu_disp {
-	assigned-clocks = <&cmu_mif CLK_MOUT_SCLK_DECON_TV_ECLK_A>,
-			  <&cmu_mif CLK_DIV_SCLK_DECON_TV_ECLK>,
-			  <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK_USER>,
-			  <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK>;
-	assigned-clock-parents = <&cmu_mif CLK_MOUT_BUS_PLL_DIV2>,
-				 <0>,
-				 <&cmu_mif CLK_SCLK_DECON_TV_ECLK_DISP>,
-				 <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK_USER>;
-	assigned-clock-rates = <0>, <400000000>;
-};
-
 &cmu_fsys {
 	assigned-clocks = <&cmu_top CLK_MOUT_SCLK_USBDRD30>,
 		<&cmu_top CLK_MOUT_SCLK_USBHOST30>,
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts b/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts
index ddba2f889326..dea0a6f5bc18 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2.dts
@@ -18,6 +18,40 @@
 	compatible = "samsung,tm2", "samsung,exynos5433";
 };
 
+&cmu_disp {
+	/*
+	 * TM2 and TM2e differ only by DISP_PLL rate, but define all assigned
+	 * clocks properties for DISP CMU for each board to keep them together
+	 * for easier review and maintenance.
+	 */
+	assigned-clocks = <&cmu_disp CLK_FOUT_DISP_PLL>,
+			  <&cmu_mif CLK_DIV_SCLK_DECON_TV_ECLK>,
+			  <&cmu_disp CLK_MOUT_ACLK_DISP_333_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DSIM0_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DSIM0>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_ECLK_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_ECLK>,
+			  <&cmu_disp CLK_MOUT_PHYCLK_MIPIDPHY0_RXCLKESC0_USER>,
+			  <&cmu_disp CLK_MOUT_PHYCLK_MIPIDPHY0_BITCLKDIV8_USER>,
+			  <&cmu_disp CLK_MOUT_DISP_PLL>,
+			  <&cmu_mif CLK_MOUT_SCLK_DECON_TV_ECLK_A>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK>;
+	assigned-clock-parents = <0>, <0>,
+				 <&cmu_mif CLK_ACLK_DISP_333>,
+				 <&cmu_mif CLK_SCLK_DSIM0_DISP>,
+				 <&cmu_disp CLK_MOUT_SCLK_DSIM0_USER>,
+				 <&cmu_mif CLK_SCLK_DECON_ECLK_DISP>,
+				 <&cmu_disp CLK_MOUT_SCLK_DECON_ECLK_USER>,
+				 <&cmu_disp CLK_PHYCLK_MIPIDPHY0_RXCLKESC0_PHY>,
+				 <&cmu_disp CLK_PHYCLK_MIPIDPHY0_BITCLKDIV8_PHY>,
+				 <&cmu_disp CLK_FOUT_DISP_PLL>,
+				 <&cmu_mif CLK_MOUT_BUS_PLL_DIV2>,
+				 <&cmu_mif CLK_SCLK_DECON_TV_ECLK_DISP>,
+				 <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK_USER>;
+	assigned-clock-rates = <250000000>, <400000000>;
+};
+
 &hsi2c_9 {
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts b/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts
index 2fbf3a860316..7891a31adc17 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2e.dts
@@ -18,6 +18,40 @@
 	compatible = "samsung,tm2e", "samsung,exynos5433";
 };
 
+&cmu_disp {
+	/*
+	 * TM2 and TM2e differ only by DISP_PLL rate, but define all assigned
+	 * clocks properties for DISP CMU for each board to keep them together
+	 * for easier review and maintenance.
+	 */
+	assigned-clocks = <&cmu_disp CLK_FOUT_DISP_PLL>,
+			  <&cmu_mif CLK_DIV_SCLK_DECON_TV_ECLK>,
+			  <&cmu_disp CLK_MOUT_ACLK_DISP_333_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DSIM0_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DSIM0>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_ECLK_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_ECLK>,
+			  <&cmu_disp CLK_MOUT_PHYCLK_MIPIDPHY0_RXCLKESC0_USER>,
+			  <&cmu_disp CLK_MOUT_PHYCLK_MIPIDPHY0_BITCLKDIV8_USER>,
+			  <&cmu_disp CLK_MOUT_DISP_PLL>,
+			  <&cmu_mif CLK_MOUT_SCLK_DECON_TV_ECLK_A>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK_USER>,
+			  <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK>;
+	assigned-clock-parents = <0>, <0>,
+				 <&cmu_mif CLK_ACLK_DISP_333>,
+				 <&cmu_mif CLK_SCLK_DSIM0_DISP>,
+				 <&cmu_disp CLK_MOUT_SCLK_DSIM0_USER>,
+				 <&cmu_mif CLK_SCLK_DECON_ECLK_DISP>,
+				 <&cmu_disp CLK_MOUT_SCLK_DECON_ECLK_USER>,
+				 <&cmu_disp CLK_PHYCLK_MIPIDPHY0_RXCLKESC0_PHY>,
+				 <&cmu_disp CLK_PHYCLK_MIPIDPHY0_BITCLKDIV8_PHY>,
+				 <&cmu_disp CLK_FOUT_DISP_PLL>,
+				 <&cmu_mif CLK_MOUT_BUS_PLL_DIV2>,
+				 <&cmu_mif CLK_SCLK_DECON_TV_ECLK_DISP>,
+				 <&cmu_disp CLK_MOUT_SCLK_DECON_TV_ECLK_USER>;
+	assigned-clock-rates = <278000000>, <400000000>;
+};
+
 &ldo31_reg {
 	regulator-name = "TSP_VDD_1.8V_AP";
 	regulator-min-microvolt = <1800000>;
-- 
GitLab


From 860ac88abecab5d3d0e07306365f55cbc690c220 Mon Sep 17 00:00:00 2001
From: Pankaj Dubey <pankaj.dubey@samsung.com>
Date: Fri, 20 Jan 2017 09:49:56 +0530
Subject: [PATCH 043/898] pinctrl: dt-bindings: samsung: Add Exynos7 specific
 pinctrl macro definitions

Exynos7 SoC pinctrl configurations are similar to existing Exynos4/5 except
for FSYS1 pinctrl drive strengths. So adding Exynos7 specific FSYS1 blocks
pinctrl driver strength related macros which will be used in Exynos7
DTSi files.

Signed-off-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 include/dt-bindings/pinctrl/samsung.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/dt-bindings/pinctrl/samsung.h b/include/dt-bindings/pinctrl/samsung.h
index e0ebb20ffdd3..b7aa3646208b 100644
--- a/include/dt-bindings/pinctrl/samsung.h
+++ b/include/dt-bindings/pinctrl/samsung.h
@@ -68,4 +68,12 @@
 #define EXYNOS_PIN_FUNC_6		6
 #define EXYNOS_PIN_FUNC_F		0xf
 
+/* Drive strengths for Exynos7 FSYS1 block */
+#define EXYNOS7_FSYS1_PIN_DRV_LV1	0
+#define EXYNOS7_FSYS1_PIN_DRV_LV2	4
+#define EXYNOS7_FSYS1_PIN_DRV_LV3	2
+#define EXYNOS7_FSYS1_PIN_DRV_LV4	6
+#define EXYNOS7_FSYS1_PIN_DRV_LV5	1
+#define EXYNOS7_FSYS1_PIN_DRV_LV6	5
+
 #endif /* __DT_BINDINGS_PINCTRL_SAMSUNG_H__ */
-- 
GitLab


From 51a2de551755c28c98191f80537acd3c7e1adda4 Mon Sep 17 00:00:00 2001
From: Pankaj Dubey <pankaj.dubey@samsung.com>
Date: Fri, 20 Jan 2017 09:49:57 +0530
Subject: [PATCH 044/898] arm64: dts: exynos: Use macros for pinctrl
 configuration on Exynos7

Usage of DTS macros instead of hard-coded numbers makes code easier to
read.  One does not have to remember which value means pull-up/down or
specific driver strength.

Signed-off-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 .../boot/dts/exynos/exynos7-espresso.dts      |   4 +-
 .../boot/dts/exynos/exynos7-pinctrl.dtsi      | 302 +++++++++---------
 2 files changed, 154 insertions(+), 152 deletions(-)

diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
index c528dd52ba2d..25d9b4aa0ff6 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
+++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
@@ -328,8 +328,8 @@
 &pinctrl_alive {
 	pmic_irq: pmic-irq {
 		samsung,pins = "gpa0-2";
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV4>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
index 7ebb93927f13..8f58850cd28c 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi
@@ -12,6 +12,8 @@
  * published by the Free Software Foundation.
 */
 
+#include <dt-bindings/pinctrl/samsung.h>
+
 &pinctrl_alive {
 	gpa0: gpa0 {
 		gpio-controller;
@@ -187,163 +189,163 @@
 
 	hs_i2c10_bus: hs-i2c10-bus {
 		samsung,pins = "gpb0-1", "gpb0-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c11_bus: hs-i2c11-bus {
 		samsung,pins = "gpb0-3", "gpb0-2";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c2_bus: hs-i2c2-bus {
 		samsung,pins = "gpd0-3", "gpd0-2";
-		samsung,pin-function = <3>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	uart0_data: uart0-data {
 		samsung,pins = "gpd0-0", "gpd0-1";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	uart0_fctl: uart0-fctl {
 		samsung,pins = "gpd0-2", "gpd0-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	uart2_data: uart2-data {
 		samsung,pins = "gpd1-4", "gpd1-5";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c3_bus: hs-i2c3-bus {
 		samsung,pins = "gpd1-3", "gpd1-2";
-		samsung,pin-function = <3>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	uart1_data: uart1-data {
 		samsung,pins = "gpd1-0", "gpd1-1";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	uart1_fctl: uart1-fctl {
 		samsung,pins = "gpd1-2", "gpd1-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c0_bus: hs-i2c0-bus {
 		samsung,pins = "gpd2-1", "gpd2-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c1_bus: hs-i2c1-bus {
 		samsung,pins = "gpd2-3", "gpd2-2";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c9_bus: hs-i2c9-bus {
 		samsung,pins = "gpd2-7", "gpd2-6";
-		samsung,pin-function = <3>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	pwm0_out: pwm0-out {
 		samsung,pins = "gpd2-4";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	pwm1_out: pwm1-out {
 		samsung,pins = "gpd2-5";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	pwm2_out: pwm2-out {
 		samsung,pins = "gpd2-6";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	pwm3_out: pwm3-out {
 		samsung,pins = "gpd2-7";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c8_bus: hs-i2c8-bus {
 		samsung,pins = "gpd5-3", "gpd5-2";
-		samsung,pin-function = <3>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	uart3_data: uart3-data {
 		samsung,pins = "gpd5-0", "gpd5-1";
-		samsung,pin-function = <3>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_3>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	spi2_bus: spi2-bus {
 		samsung,pins = "gpd5-0", "gpd5-1", "gpd5-2", "gpd5-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	spi1_bus: spi1-bus {
 		samsung,pins = "gpd6-2", "gpd6-3", "gpd6-4", "gpd6-5";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	spi0_bus: spi0-bus {
 		samsung,pins = "gpd8-0", "gpd8-1", "gpd6-0", "gpd6-1";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c4_bus: hs-i2c4-bus {
 		samsung,pins = "gpg3-1", "gpg3-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	hs_i2c5_bus: hs-i2c5-bus {
 		samsung,pins = "gpg3-3", "gpg3-2";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 };
 
@@ -358,9 +360,9 @@
 
 	hs_i2c6_bus: hs-i2c6-bus {
 		samsung,pins = "gpj0-1", "gpj0-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 };
 
@@ -375,9 +377,9 @@
 
 	hs_i2c7_bus: hs-i2c7-bus {
 		samsung,pins = "gpj1-1", "gpj1-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 };
 
@@ -392,9 +394,9 @@
 
 	spi3_bus: spi3-bus {
 		samsung,pins = "gpg4-0", "gpg4-1", "gpg4-2", "gpg4-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 };
 
@@ -409,9 +411,9 @@
 
 	spi4_bus: spi4-bus {
 		samsung,pins = "gpv7-0", "gpv7-1", "gpv7-2", "gpv7-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 };
 
@@ -426,37 +428,37 @@
 
 	sd2_clk: sd2-clk {
 		samsung,pins = "gpr4-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <3>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV4>;
 	};
 
 	sd2_cmd: sd2-cmd {
 		samsung,pins = "gpr4-1";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <3>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV4>;
 	};
 
 	sd2_cd: sd2-cd {
 		samsung,pins = "gpr4-2";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <3>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV4>;
 	};
 
 	sd2_bus1: sd2-bus-width1 {
 		samsung,pins = "gpr4-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <3>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV4>;
 	};
 
 	sd2_bus4: sd2-bus-width4 {
 		samsung,pins = "gpr4-4", "gpr4-5", "gpr4-6";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <3>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV4>;
 	};
 };
 
@@ -495,107 +497,107 @@
 
 	sd0_clk: sd0-clk {
 		samsung,pins = "gpr0-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <4>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV2>;
 	};
 
 	sd0_cmd: sd0-cmd {
 		samsung,pins = "gpr0-1";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <4>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV2>;
 	};
 
 	sd0_ds: sd0-ds {
 		samsung,pins = "gpr0-2";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <1>;
-		samsung,pin-drv = <4>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV2>;
 	};
 
 	sd0_qrdy: sd0-qrdy {
 		samsung,pins = "gpr0-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <1>;
-		samsung,pin-drv = <4>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV2>;
 	};
 
 	sd0_bus1: sd0-bus-width1 {
 		samsung,pins = "gpr1-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <4>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV2>;
 	};
 
 	sd0_bus4: sd0-bus-width4 {
 		samsung,pins = "gpr1-1", "gpr1-2", "gpr1-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <4>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV2>;
 	};
 
 	sd0_bus8: sd0-bus-width8 {
 		samsung,pins = "gpr1-4", "gpr1-5", "gpr1-6", "gpr1-7";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <4>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV2>;
 	};
 
 	sd1_clk: sd1-clk {
 		samsung,pins = "gpr2-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <2>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV3>;
 	};
 
 	sd1_cmd: sd1-cmd {
 		samsung,pins = "gpr2-1";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <2>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV3>;
 	};
 
 	sd1_ds: sd1-ds {
 		samsung,pins = "gpr2-2";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <1>;
-		samsung,pin-drv = <6>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV4>;
 	};
 
 	sd1_qrdy: sd1-qrdy {
 		samsung,pins = "gpr2-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <1>;
-		samsung,pin-drv = <6>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV4>;
 	};
 
 	sd1_int: sd1-int {
 		samsung,pins = "gpr2-4";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <1>;
-		samsung,pin-drv = <6>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV4>;
 	};
 
 	sd1_bus1: sd1-bus-width1 {
 		samsung,pins = "gpr3-0";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <2>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV3>;
 	};
 
 	sd1_bus4: sd1-bus-width4 {
 		samsung,pins = "gpr3-1", "gpr3-2", "gpr3-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <2>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV3>;
 	};
 
 	sd1_bus8: sd1-bus-width8 {
 		samsung,pins = "gpr3-4", "gpr3-5", "gpr3-6", "gpr3-7";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <2>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_FSYS1_PIN_DRV_LV3>;
 	};
 };
 
@@ -682,22 +684,22 @@
 
 	spi5_bus: spi5-bus {
 		samsung,pins = "gpf2-0", "gpf2-1", "gpf2-2", "gpf2-3";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 
 	ufs_refclk_out: ufs-refclk-out {
 		samsung,pins = "gpg2-4";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
-		samsung,pin-drv = <2>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV2>;
 	};
 
 	ufs_rst_n: ufs-rst-n {
 		samsung,pins = "gph1-5";
-		samsung,pin-function = <2>;
-		samsung,pin-pud = <3>;
-		samsung,pin-drv = <0>;
+		samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
 	};
 };
-- 
GitLab


From ad6afec832a77845a9a0f9353fe049225a976b16 Mon Sep 17 00:00:00 2001
From: Vivek Gautam <gautamvivek1987@gmail.com>
Date: Wed, 18 Jan 2017 12:02:52 +0530
Subject: [PATCH 045/898] arm64: dts: exynos: Add USB 3.0 controller node for
 Exynos7

Add USB 3.0 DRD controller device node, with its clock
and phy information to enable the same on Exynos7.

Signed-off-by: Vivek Gautam <gautamvivek1987@gmail.com>
Signed-off-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Reviewed-by: Javier Martinez Canillas <javier@osg.samsung.com>
Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm64/boot/dts/exynos/exynos7.dtsi | 34 +++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi
index 80aa60e38237..9a3fbed1765a 100644
--- a/arch/arm64/boot/dts/exynos/exynos7.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi
@@ -603,6 +603,40 @@
 				#include "exynos7-trip-points.dtsi"
 			};
 		};
+
+		usbdrd_phy: phy@15500000 {
+			compatible = "samsung,exynos7-usbdrd-phy";
+			reg = <0x15500000 0x100>;
+			clocks = <&clock_fsys0 ACLK_USBDRD300>,
+			       <&clock_fsys0 OSCCLK_PHY_CLKOUT_USB30_PHY>,
+			       <&clock_fsys0 PHYCLK_USBDRD300_UDRD30_PIPE_PCLK_USER>,
+			       <&clock_fsys0 PHYCLK_USBDRD300_UDRD30_PHYCLK_USER>,
+			       <&clock_fsys0 SCLK_USBDRD300_REFCLK>;
+			clock-names = "phy", "ref", "phy_pipe",
+				"phy_utmi", "itp";
+			samsung,pmu-syscon = <&pmu_system_controller>;
+			#phy-cells = <1>;
+		};
+
+		usbdrd3 {
+			compatible = "samsung,exynos7-dwusb3";
+			clocks = <&clock_fsys0 ACLK_USBDRD300>,
+			       <&clock_fsys0 SCLK_USBDRD300_SUSPENDCLK>,
+			       <&clock_fsys0 ACLK_AXIUS_USBDRD30X_FSYS0X>;
+			clock-names = "usbdrd30", "usbdrd30_susp_clk",
+				"usbdrd30_axius_clk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			dwc3@15400000 {
+				compatible = "snps,dwc3";
+				reg = <0x15400000 0x10000>;
+				interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>;
+				phys = <&usbdrd_phy 0>, <&usbdrd_phy 1>;
+				phy-names = "usb2-phy", "usb3-phy";
+			};
+		};
 	};
 };
 
-- 
GitLab


From 6629490aa027a8af3160e63cffcddc97c1602c96 Mon Sep 17 00:00:00 2001
From: Vivek Gautam <gautamvivek1987@gmail.com>
Date: Wed, 18 Jan 2017 12:02:53 +0530
Subject: [PATCH 046/898] arm64: dts: exynos: Add regulators for Vbus and
 Vbus-Boost

Adding fixed voltage regulators for Vbus and Vbus-boost required
by USB 3.0 DRD controller on Exynos7-espresso board.

Signed-off-by: Vivek Gautam <gautamvivek1987@gmail.com>
Signed-off-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Reviewed-by: Javier Martinez Canillas <javier@osg.samsung.com>
Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 .../boot/dts/exynos/exynos7-espresso.dts      | 45 +++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
index 25d9b4aa0ff6..e5892bb0ae6e 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
+++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
@@ -13,6 +13,7 @@
 #include "exynos7.dtsi"
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/clock/samsung,s2mps11.h>
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "Samsung Exynos7 Espresso board based on EXYNOS7";
@@ -32,6 +33,29 @@
 		device_type = "memory";
 		reg = <0x0 0x40000000 0x0 0xC0000000>;
 	};
+
+	usb30_vbus_reg: regulator-usb30 {
+		compatible = "regulator-fixed";
+		regulator-name = "VBUS_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gph1 1 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb30_vbus_en>;
+		enable-active-high;
+	};
+
+	usb3drd_boost_5v: regulator-usb3drd-boost {
+		compatible = "regulator-fixed";
+		regulator-name = "VUSB_VBUS_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpf4 1 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb3drd_boost_en>;
+		enable-active-high;
+	};
+
 };
 
 &fin_pll {
@@ -365,3 +389,24 @@
 	vqmmc-supply = <&ldo2_reg>;
 	disable-wp;
 };
+
+&pinctrl_bus1 {
+	usb30_vbus_en: usb30-vbus-en {
+		samsung,pins = "gph1-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
+	};
+
+	usb3drd_boost_en: usb3drd-boost-en {
+		samsung,pins = "gpf4-1";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
+	};
+};
+
+&usbdrd_phy {
+	vbus-supply = <&usb30_vbus_reg>;
+	vbus-boost-supply = <&usb3drd_boost_5v>;
+};
-- 
GitLab


From 17fa2dcbd6325ab877651bef04fca9dd828a2758 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 3 Feb 2017 18:01:23 +0100
Subject: [PATCH 047/898] iio: adc: handle unknow of_device_id data

If we get an unknown 'childmode' value, a number of variables are not
initialized properly:

drivers/iio/adc/rcar-gyroadc.c: In function 'rcar_gyroadc_probe':
drivers/iio/adc/rcar-gyroadc.c:390:5: error: 'num_channels' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/iio/adc/rcar-gyroadc.c:426:22: error: 'sample_width' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/iio/adc/rcar-gyroadc.c:428:23: error: 'channels' may be used uninitialized in this function [-Werror=maybe-uninitialized]

The driver is currently correct, but handling this properly is more robust
for possible modifications.

There is also a false-positive warning about adcmode being possibly uninitialized,
but that cannot happen as we also check the 'first' flag:

drivers/iio/adc/rcar-gyroadc.c:398:26: error: 'adcmode' may be used uninitialized in this function [-Werror=maybe-uninitialized]

This adds an initialization for 'adcmode' and bails out for any unknown childmode.

Fixes: 059c53b32329 ("iio: adc: Add Renesas GyroADC driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Marek Vasut <marek.vasut@gmail.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/adc/rcar-gyroadc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/adc/rcar-gyroadc.c b/drivers/iio/adc/rcar-gyroadc.c
index 0c44f72c32a8..018ed360e717 100644
--- a/drivers/iio/adc/rcar-gyroadc.c
+++ b/drivers/iio/adc/rcar-gyroadc.c
@@ -336,7 +336,7 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev)
 	struct device_node *child;
 	struct regulator *vref;
 	unsigned int reg;
-	unsigned int adcmode, childmode;
+	unsigned int adcmode = -1, childmode;
 	unsigned int sample_width;
 	unsigned int num_channels;
 	int ret, first = 1;
@@ -366,6 +366,8 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev)
 			channels = rcar_gyroadc_iio_channels_3;
 			num_channels = ARRAY_SIZE(rcar_gyroadc_iio_channels_3);
 			break;
+		default:
+			return -EINVAL;
 		}
 
 		/*
-- 
GitLab


From db61ffe3a71c697aaa91c42c862a5f7557a0e562 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 31 Jan 2017 14:36:07 -0200
Subject: [PATCH 048/898] random: move random_min_urandom_seed into
 CONFIG_SYSCTL ifdef block

Building arm allnodefconfig causes the following build warning:

drivers/char/random.c:318:12: warning: 'random_min_urandom_seed' defined but not used [-Wunused-variable]

Fix the warning by moving 'random_min_urandom_seed' declaration inside
the CONFIG_SYSCTL ifdef block, where it is actually used.

While at it, remove the comment prior to the variable declaration.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 066ae125f2c8..0ab024918907 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -312,11 +312,6 @@ static int random_read_wakeup_bits = 64;
  */
 static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
 
-/*
- * Variable is currently unused by left for user space compatibility.
- */
-static int random_min_urandom_seed = 60;
-
 /*
  * Originally, we used a primitive polynomial of degree .poolwords
  * over GF(2).  The taps for various sizes are defined below.  They
@@ -1886,6 +1881,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
 static int min_read_thresh = 8, min_write_thresh;
 static int max_read_thresh = OUTPUT_POOL_WORDS * 32;
 static int max_write_thresh = INPUT_POOL_WORDS * 32;
+static int random_min_urandom_seed = 60;
 static char sysctl_bootid[16];
 
 /*
-- 
GitLab


From af7bd4dc13093bf1477f370722bbab24cf457b91 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 17 Jan 2017 06:34:52 +0200
Subject: [PATCH 049/898] vfs: create vfs helper vfs_tmpfile()

Factor out some common vfs bits from do_tmpfile()
to be used by overlayfs for concurrent copy up.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/namei.c         | 68 +++++++++++++++++++++++++++++-----------------
 include/linux/fs.h |  3 ++
 2 files changed, 46 insertions(+), 25 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index ad74877e1442..7d87699c3e2e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3353,13 +3353,50 @@ static int do_last(struct nameidata *nd,
 	return error;
 }
 
+struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
+{
+	static const struct qstr name = QSTR_INIT("/", 1);
+	struct dentry *child = NULL;
+	struct inode *dir = dentry->d_inode;
+	struct inode *inode;
+	int error;
+
+	/* we want directory to be writable */
+	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	if (error)
+		goto out_err;
+	error = -EOPNOTSUPP;
+	if (!dir->i_op->tmpfile)
+		goto out_err;
+	error = -ENOMEM;
+	child = d_alloc(dentry, &name);
+	if (unlikely(!child))
+		goto out_err;
+	error = dir->i_op->tmpfile(dir, child, mode);
+	if (error)
+		goto out_err;
+	error = -ENOENT;
+	inode = child->d_inode;
+	if (unlikely(!inode))
+		goto out_err;
+	if (!(open_flag & O_EXCL)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state |= I_LINKABLE;
+		spin_unlock(&inode->i_lock);
+	}
+	return child;
+
+out_err:
+	dput(child);
+	return ERR_PTR(error);
+}
+EXPORT_SYMBOL(vfs_tmpfile);
+
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
 		struct file *file, int *opened)
 {
-	static const struct qstr name = QSTR_INIT("/", 1);
 	struct dentry *child;
-	struct inode *dir;
 	struct path path;
 	int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
 	if (unlikely(error))
@@ -3367,25 +3404,12 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	error = mnt_want_write(path.mnt);
 	if (unlikely(error))
 		goto out;
-	dir = path.dentry->d_inode;
-	/* we want directory to be writable */
-	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
-	if (error)
-		goto out2;
-	if (!dir->i_op->tmpfile) {
-		error = -EOPNOTSUPP;
-		goto out2;
-	}
-	child = d_alloc(path.dentry, &name);
-	if (unlikely(!child)) {
-		error = -ENOMEM;
+	child = vfs_tmpfile(path.dentry, op->mode, op->open_flag);
+	error = PTR_ERR(child);
+	if (unlikely(IS_ERR(child)))
 		goto out2;
-	}
 	dput(path.dentry);
 	path.dentry = child;
-	error = dir->i_op->tmpfile(dir, child, op->mode);
-	if (error)
-		goto out2;
 	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
 	error = may_open(&path, 0, op->open_flag);
@@ -3396,14 +3420,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	error = open_check_o_direct(file);
-	if (error) {
+	if (error)
 		fput(file);
-	} else if (!(op->open_flag & O_EXCL)) {
-		struct inode *inode = file_inode(file);
-		spin_lock(&inode->i_lock);
-		inode->i_state |= I_LINKABLE;
-		spin_unlock(&inode->i_lock);
-	}
 out2:
 	mnt_drop_write(path.mnt);
 out:
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2ba074328894..4a7f3cc9edab 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1561,6 +1561,9 @@ extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
 extern int vfs_whiteout(struct inode *, struct dentry *);
 
+extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
+				  int open_flag);
+
 /*
  * VFS file helper functions.
  */
-- 
GitLab


From 9e79b1326302589a035fe20e8cce7c1a7d8333ed Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 31 Jan 2017 10:34:55 +0200
Subject: [PATCH 050/898] vfs: deny fallocate() on directory

There was an obscure use case of fallocate of directory inode
in the vfs helper with the comment:
"Let individual file system decide if it supports preallocation
 for directories or not."

But there is no in-tree file system that implements fallocate
for directory operations.

Deny an attempt to fallocate a directory with EISDIR error.

This change is needed prior to converting sb_start_write()
to  file_start_write(), so freeze protection is correctly
handled for cases of fallocate file and blockdev.

Cc: linux-api@vger.kernel.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/open.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/open.c b/fs/open.c
index 9921f70bc5ca..f9118f4113e7 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -301,12 +301,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (S_ISFIFO(inode->i_mode))
 		return -ESPIPE;
 
-	/*
-	 * Let individual file system decide if it supports preallocation
-	 * for directories or not.
-	 */
-	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) &&
-	    !S_ISBLK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode))
+		return -EISDIR;
+
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
 		return -ENODEV;
 
 	/* Check for wrap through zero too */
-- 
GitLab


From 11cbfb10775aa2a01cee966d118049ede9d0bdf2 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 31 Jan 2017 10:34:56 +0200
Subject: [PATCH 051/898] vfs: deny copy_file_range() for non regular files

There is no in-tree file system that implements copy_file_range()
for non regular files.

Deny an attempt to copy_file_range() a directory with EISDIR
and any other non regualr file with EINVAL to conform with
behavior of vfs_{clone,dedup}_file_range().

This change is needed prior to converting sb_start_write()
to  file_start_write() in the vfs helper.

Cc: linux-api@vger.kernel.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/read_write.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/read_write.c b/fs/read_write.c
index 5816d4c4cab0..511178d7723b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1518,6 +1518,11 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (flags != 0)
 		return -EINVAL;
 
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
 	ret = rw_verify_area(READ, file_in, &pos_in, len);
 	if (unlikely(ret))
 		return ret;
-- 
GitLab


From bfe219d373cadab761373aeea4c70406bc27ea2c Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 31 Jan 2017 10:34:57 +0200
Subject: [PATCH 052/898] vfs: wrap write f_ops with file_{start,end}_write()

Before calling write f_ops, call file_start_write() instead
of sb_start_write().

Replace {sb,file}_start_write() for {copy,clone}_file_range() and
for fallocate().

Beyond correct semantics, this avoids freeze protection to sb when
operating on special inodes, such as fallocate() on a blockdev.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/open.c          |  4 ++--
 fs/read_write.c    |  4 ++--
 include/linux/fs.h | 26 +++++++++++++-------------
 3 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/fs/open.c b/fs/open.c
index f9118f4113e7..949cef29c3bb 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -314,7 +314,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (!file->f_op->fallocate)
 		return -EOPNOTSUPP;
 
-	sb_start_write(inode->i_sb);
+	file_start_write(file);
 	ret = file->f_op->fallocate(file, mode, offset, len);
 
 	/*
@@ -327,7 +327,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (ret == 0)
 		fsnotify_modify(file);
 
-	sb_end_write(inode->i_sb);
+	file_end_write(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vfs_fallocate);
diff --git a/fs/read_write.c b/fs/read_write.c
index 511178d7723b..820a3f06c46a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1543,7 +1543,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (len == 0)
 		return 0;
 
-	sb_start_write(inode_out->i_sb);
+	file_start_write(file_out);
 
 	/*
 	 * Try cloning first, this is supported by more file systems, and
@@ -1579,7 +1579,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	inc_syscr(current);
 	inc_syscw(current);
 
-	sb_end_write(inode_out->i_sb);
+	file_end_write(file_out);
 
 	return ret;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4a7f3cc9edab..78c81e6f5d76 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1741,19 +1741,6 @@ extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
 
-static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
-				      struct file *file_out, loff_t pos_out,
-				      u64 len)
-{
-	int ret;
-
-	sb_start_write(file_inode(file_out)->i_sb);
-	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
-	sb_end_write(file_inode(file_out)->i_sb);
-
-	return ret;
-}
-
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
@@ -2564,6 +2551,19 @@ static inline void file_end_write(struct file *file)
 	__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 }
 
+static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
+				      struct file *file_out, loff_t pos_out,
+				      u64 len)
+{
+	int ret;
+
+	file_start_write(file_out);
+	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+	file_end_write(file_out);
+
+	return ret;
+}
+
 /*
  * get_write_access() gets write permission for a file.
  * put_write_access() releases this write permission.
-- 
GitLab


From e7f52429b4a5b2e3224948d1737eb264c8f7e15f Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 17 Jan 2017 06:34:53 +0200
Subject: [PATCH 053/898] ovl: check if upperdir fs supports O_TMPFILE

This is needed for choosing between concurrent copyup
using O_TMPFILE and legacy copyup using workdir+rename.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/overlayfs.h |  9 +++++++++
 fs/overlayfs/ovl_entry.h |  1 +
 fs/overlayfs/super.c     | 10 ++++++++++
 3 files changed, 20 insertions(+)

diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8af450b0e57a..3822a909ce1f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -127,6 +127,15 @@ static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
 	return err;
 }
 
+static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode)
+{
+	struct dentry *ret = vfs_tmpfile(dentry, mode, 0);
+	int err = IS_ERR(ret) ? PTR_ERR(ret) : 0;
+
+	pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return ret;
+}
+
 static inline struct inode *ovl_inode_real(struct inode *inode, bool *is_upper)
 {
 	unsigned long x = (unsigned long) READ_ONCE(inode->i_private);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index d14bca1850d9..65f240001aa6 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -27,6 +27,7 @@ struct ovl_fs {
 	struct ovl_config config;
 	/* creds of process who forced instantiation of super block */
 	const struct cred *creator_cred;
+	bool tmpfile;
 };
 
 /* private information held for every overlayfs dentry */
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 20f48abbb82f..ff05065b510f 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -825,6 +825,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		 * creation of workdir in previous step.
 		 */
 		if (ufs->workdir) {
+			struct dentry *temp;
+
 			err = ovl_check_d_type_supported(&workpath);
 			if (err < 0)
 				goto out_put_workdir;
@@ -836,6 +838,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			 */
 			if (!err)
 				pr_warn("overlayfs: upper fs needs to support d_type.\n");
+
+			/* Check if upper/work fs supports O_TMPFILE */
+			temp = ovl_do_tmpfile(ufs->workdir, S_IFREG | 0);
+			ufs->tmpfile = !IS_ERR(temp);
+			if (ufs->tmpfile)
+				dput(temp);
+			else
+				pr_warn("overlayfs: upper fs does not support tmpfile.\n");
 		}
 	}
 
-- 
GitLab


From 42f269b925405d9dd45014823e5057786d6ca452 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 17 Jan 2017 06:34:54 +0200
Subject: [PATCH 054/898] ovl: rearrange code in ovl_copy_up_locked()

As preparation to implementing copy up with O_TMPFILE,
name the variable for dentry before final rename 'temp' and
assign it to 'newdentry' only after rename.

Also lookup upper dentry before looking up temp dentry and
move ovl_set_timestamps() into ovl_copy_up_locked(), because
that is going to be more convenient for upcoming change.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/copy_up.c | 49 +++++++++++++++++++++---------------------
 1 file changed, 25 insertions(+), 24 deletions(-)

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index f57043dace62..01e332725e94 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -232,12 +232,14 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 
 static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 			      struct dentry *dentry, struct path *lowerpath,
-			      struct kstat *stat, const char *link)
+			      struct kstat *stat, const char *link,
+			      struct kstat *pstat)
 {
 	struct inode *wdir = workdir->d_inode;
 	struct inode *udir = upperdir->d_inode;
 	struct dentry *newdentry = NULL;
 	struct dentry *upper = NULL;
+	struct dentry *temp = NULL;
 	int err;
 	const struct cred *old_creds = NULL;
 	struct cred *new_creds = NULL;
@@ -248,25 +250,25 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 		.link = link
 	};
 
-	newdentry = ovl_lookup_temp(workdir, dentry);
-	err = PTR_ERR(newdentry);
-	if (IS_ERR(newdentry))
-		goto out;
-
 	upper = lookup_one_len(dentry->d_name.name, upperdir,
 			       dentry->d_name.len);
 	err = PTR_ERR(upper);
 	if (IS_ERR(upper))
-		goto out1;
+		goto out;
 
 	err = security_inode_copy_up(dentry, &new_creds);
 	if (err < 0)
-		goto out2;
+		goto out1;
 
 	if (new_creds)
 		old_creds = override_creds(new_creds);
 
-	err = ovl_create_real(wdir, newdentry, &cattr, NULL, true);
+	temp = ovl_lookup_temp(workdir, dentry);
+	err = PTR_ERR(temp);
+	if (IS_ERR(temp))
+		goto out1;
+
+	err = ovl_create_real(wdir, temp, &cattr, NULL, true);
 
 	if (new_creds) {
 		revert_creds(old_creds);
@@ -281,39 +283,42 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 
 		ovl_path_upper(dentry, &upperpath);
 		BUG_ON(upperpath.dentry != NULL);
-		upperpath.dentry = newdentry;
+		upperpath.dentry = temp;
 
 		err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
 		if (err)
 			goto out_cleanup;
 	}
 
-	err = ovl_copy_xattr(lowerpath->dentry, newdentry);
+	err = ovl_copy_xattr(lowerpath->dentry, temp);
 	if (err)
 		goto out_cleanup;
 
-	inode_lock(newdentry->d_inode);
-	err = ovl_set_attr(newdentry, stat);
-	inode_unlock(newdentry->d_inode);
+	inode_lock(temp->d_inode);
+	err = ovl_set_attr(temp, stat);
+	inode_unlock(temp->d_inode);
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+	err = ovl_do_rename(wdir, temp, udir, upper, 0);
 	if (err)
 		goto out_cleanup;
 
+	newdentry = dget(temp);
 	ovl_dentry_update(dentry, newdentry);
 	ovl_inode_update(d_inode(dentry), d_inode(newdentry));
-	newdentry = NULL;
+
+	/* Restore timestamps on parent (best effort) */
+	ovl_set_timestamps(upperdir, pstat);
 out2:
-	dput(upper);
+	dput(temp);
 out1:
-	dput(newdentry);
+	dput(upper);
 out:
 	return err;
 
 out_cleanup:
-	ovl_cleanup(wdir, newdentry);
+	ovl_cleanup(wdir, temp);
 	goto out2;
 }
 
@@ -368,11 +373,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	}
 
 	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-				 stat, link);
-	if (!err) {
-		/* Restore timestamps on parent (best effort) */
-		ovl_set_timestamps(upperdir, &pstat);
-	}
+				 stat, link, &pstat);
 out_unlock:
 	unlock_rename(workdir, upperdir);
 	do_delayed_call(&done);
-- 
GitLab


From d8514d8edb5b045cf7f708e14f888ce760d60f0b Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 17 Jan 2017 06:34:55 +0200
Subject: [PATCH 055/898] ovl: copy up regular file using O_TMPFILE

In preparation for concurrent copy up, implement copy up
of regular file as O_TMPFILE that is linked to upperdir
instead of a file in workdir that is moved to upperdir.

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/copy_up.c | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 01e332725e94..6e39e90b5605 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -20,6 +20,7 @@
 #include <linux/fdtable.h>
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
+#include "ovl_entry.h"
 
 #define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
 
@@ -233,7 +234,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 			      struct dentry *dentry, struct path *lowerpath,
 			      struct kstat *stat, const char *link,
-			      struct kstat *pstat)
+			      struct kstat *pstat, bool tmpfile)
 {
 	struct inode *wdir = workdir->d_inode;
 	struct inode *udir = upperdir->d_inode;
@@ -263,12 +264,17 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 	if (new_creds)
 		old_creds = override_creds(new_creds);
 
-	temp = ovl_lookup_temp(workdir, dentry);
+	if (tmpfile)
+		temp = ovl_do_tmpfile(upperdir, stat->mode);
+	else
+		temp = ovl_lookup_temp(workdir, dentry);
 	err = PTR_ERR(temp);
 	if (IS_ERR(temp))
 		goto out1;
 
-	err = ovl_create_real(wdir, temp, &cattr, NULL, true);
+	err = 0;
+	if (!tmpfile)
+		err = ovl_create_real(wdir, temp, &cattr, NULL, true);
 
 	if (new_creds) {
 		revert_creds(old_creds);
@@ -300,11 +306,14 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(wdir, temp, udir, upper, 0);
+	if (tmpfile)
+		err = ovl_do_link(temp, udir, upper, true);
+	else
+		err = ovl_do_rename(wdir, temp, udir, upper, 0);
 	if (err)
 		goto out_cleanup;
 
-	newdentry = dget(temp);
+	newdentry = dget(tmpfile ? upper : temp);
 	ovl_dentry_update(dentry, newdentry);
 	ovl_inode_update(d_inode(dentry), d_inode(newdentry));
 
@@ -318,7 +327,8 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 	return err;
 
 out_cleanup:
-	ovl_cleanup(wdir, temp);
+	if (!tmpfile)
+		ovl_cleanup(wdir, temp);
 	goto out2;
 }
 
@@ -342,6 +352,9 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	struct dentry *lowerdentry = lowerpath->dentry;
 	struct dentry *upperdir;
 	const char *link = NULL;
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	/* Should we copyup with O_TMPFILE or with workdir? */
+	bool tmpfile = S_ISREG(stat->mode) && ofs->tmpfile;
 
 	if (WARN_ON(!workdir))
 		return -EROFS;
@@ -373,7 +386,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	}
 
 	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-				 stat, link, &pstat);
+				 stat, link, &pstat, tmpfile);
 out_unlock:
 	unlock_rename(workdir, upperdir);
 	do_delayed_call(&done);
-- 
GitLab


From 39d3d60a54df05a1a32fa71159d7a26a530dee6c Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 17 Jan 2017 06:34:56 +0200
Subject: [PATCH 056/898] ovl: introduce copy up waitqueue

The overlay sb 'copyup_wq' and overlay inode 'copying' condition
variable are about to replace the upper sb rename_lock, as finer
grained synchronization objects for concurrent copy up.

Suggested-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/overlayfs.h |  2 ++
 fs/overlayfs/ovl_entry.h |  2 ++
 fs/overlayfs/super.c     |  1 +
 fs/overlayfs/util.c      | 30 ++++++++++++++++++++++++++++++
 4 files changed, 35 insertions(+)

diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 3822a909ce1f..741dc0b6931f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -178,6 +178,8 @@ void ovl_dentry_version_inc(struct dentry *dentry);
 u64 ovl_dentry_version_get(struct dentry *dentry);
 bool ovl_is_whiteout(struct dentry *dentry);
 struct file *ovl_path_open(struct path *path, int flags);
+int ovl_copy_up_start(struct dentry *dentry);
+void ovl_copy_up_end(struct dentry *dentry);
 
 /* namei.c */
 int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 65f240001aa6..59614faa14c3 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -28,6 +28,7 @@ struct ovl_fs {
 	/* creds of process who forced instantiation of super block */
 	const struct cred *creator_cred;
 	bool tmpfile;
+	wait_queue_head_t copyup_wq;
 };
 
 /* private information held for every overlayfs dentry */
@@ -39,6 +40,7 @@ struct ovl_entry {
 			u64 version;
 			const char *redirect;
 			bool opaque;
+			bool copying;
 		};
 		struct rcu_head rcu;
 	};
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index ff05065b510f..6792bb70b4ac 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -708,6 +708,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ufs)
 		goto out;
 
+	init_waitqueue_head(&ufs->copyup_wq);
 	ufs->config.redirect_dir = ovl_redirect_dir_def;
 	err = ovl_parse_opt((char *) data, &ufs->config);
 	if (err)
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 952286f4826c..01157d6e8cfe 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -263,3 +263,33 @@ struct file *ovl_path_open(struct path *path, int flags)
 {
 	return dentry_open(path, flags | O_NOATIME, current_cred());
 }
+
+int ovl_copy_up_start(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+	int err;
+
+	spin_lock(&ofs->copyup_wq.lock);
+	err = wait_event_interruptible_locked(ofs->copyup_wq, !oe->copying);
+	if (!err) {
+		if (oe->__upperdentry)
+			err = 1; /* Already copied up */
+		else
+			oe->copying = true;
+	}
+	spin_unlock(&ofs->copyup_wq.lock);
+
+	return err;
+}
+
+void ovl_copy_up_end(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	spin_lock(&ofs->copyup_wq.lock);
+	oe->copying = false;
+	wake_up_locked(&ofs->copyup_wq);
+	spin_unlock(&ofs->copyup_wq.lock);
+}
-- 
GitLab


From 01ad3eb8a07385bc8849f0ee7c800e7c8bd7287e Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 17 Jan 2017 06:34:57 +0200
Subject: [PATCH 057/898] ovl: concurrent copy up of regular files

Now that copy up of regular file is done using O_TMPFILE,
we don't need to hold rename_lock throughout copy up.

Use the copy up waitqueue to synchronize concurrent copy up
of the same file. Different regular files can be copied up
concurrently.

The upper dir inode_lock is taken instead of rename_lock,
because it is needed for lookup and later for linking the
temp file, but it is released while copying up data.

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/copy_up.c | 35 +++++++++++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 4 deletions(-)

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 6e39e90b5605..48eb8812ac5b 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -291,7 +291,16 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 		BUG_ON(upperpath.dentry != NULL);
 		upperpath.dentry = temp;
 
-		err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
+		if (tmpfile) {
+			inode_unlock(udir);
+			err = ovl_copy_up_data(lowerpath, &upperpath,
+					       stat->size);
+			inode_lock_nested(udir, I_MUTEX_PARENT);
+		} else {
+			err = ovl_copy_up_data(lowerpath, &upperpath,
+					       stat->size);
+		}
+
 		if (err)
 			goto out_cleanup;
 	}
@@ -353,8 +362,6 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	struct dentry *upperdir;
 	const char *link = NULL;
 	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
-	/* Should we copyup with O_TMPFILE or with workdir? */
-	bool tmpfile = S_ISREG(stat->mode) && ofs->tmpfile;
 
 	if (WARN_ON(!workdir))
 		return -EROFS;
@@ -374,6 +381,25 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 			return PTR_ERR(link);
 	}
 
+	/* Should we copyup with O_TMPFILE or with workdir? */
+	if (S_ISREG(stat->mode) && ofs->tmpfile) {
+		err = ovl_copy_up_start(dentry);
+		/* err < 0: interrupted, err > 0: raced with another copy-up */
+		if (unlikely(err)) {
+			pr_debug("ovl_copy_up_start(%pd2) = %i\n", dentry, err);
+			if (err > 0)
+				err = 0;
+			goto out_done;
+		}
+
+		inode_lock_nested(upperdir->d_inode, I_MUTEX_PARENT);
+		err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
+					 stat, link, &pstat, true);
+		inode_unlock(upperdir->d_inode);
+		ovl_copy_up_end(dentry);
+		goto out_done;
+	}
+
 	err = -EIO;
 	if (lock_rename(workdir, upperdir) != NULL) {
 		pr_err("overlayfs: failed to lock workdir+upperdir\n");
@@ -386,9 +412,10 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	}
 
 	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-				 stat, link, &pstat, tmpfile);
+				 stat, link, &pstat, false);
 out_unlock:
 	unlock_rename(workdir, upperdir);
+out_done:
 	do_delayed_call(&done);
 
 	return err;
-- 
GitLab


From e593b2bf513dd4d3fbfa0f435392eea2c7f776f0 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 23 Jan 2017 14:32:21 +0200
Subject: [PATCH 058/898] ovl: properly implement sync_filesystem()

overlayfs syncs all inode pages on sync_filesystem(), but it also
needs to call s_op->sync_fs() of upper fs for metadata sync.

This fixes correctness of syncfs(2) as demonstrated by following
xfs specific test:

xfs_sync_stats()
{
	echo $1
	echo -n "xfs_log_force = "
	grep log /proc/fs/xfs/stat  | awk '{ print $5 }'
}

xfs_sync_stats "before touch"
touch x
xfs_sync_stats "after touch"
xfs_io -c syncfs .
xfs_sync_stats "after syncfs"
xfs_io -c fsync x
xfs_sync_stats "after fsync"
xfs_io -c fsync x
xfs_sync_stats "after fsync #2"

When this test is run in overlay mount over xfs, log force
count does not increase with syncfs command.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/super.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 6792bb70b4ac..346f668e7df0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -160,6 +160,25 @@ static void ovl_put_super(struct super_block *sb)
 	kfree(ufs);
 }
 
+static int ovl_sync_fs(struct super_block *sb, int wait)
+{
+	struct ovl_fs *ufs = sb->s_fs_info;
+	struct super_block *upper_sb;
+	int ret;
+
+	if (!ufs->upper_mnt)
+		return 0;
+	upper_sb = ufs->upper_mnt->mnt_sb;
+	if (!upper_sb->s_op->sync_fs)
+		return 0;
+
+	/* real inodes have already been synced by sync_filesystem(ovl_sb) */
+	down_read(&upper_sb->s_umount);
+	ret = upper_sb->s_op->sync_fs(upper_sb, wait);
+	up_read(&upper_sb->s_umount);
+	return ret;
+}
+
 /**
  * ovl_statfs
  * @sb: The overlayfs super block
@@ -222,6 +241,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data)
 
 static const struct super_operations ovl_super_operations = {
 	.put_super	= ovl_put_super,
+	.sync_fs	= ovl_sync_fs,
 	.statfs		= ovl_statfs,
 	.show_options	= ovl_show_options,
 	.remount_fs	= ovl_remount,
-- 
GitLab


From 51f8f3c4e22535933ef9aecc00e9a6069e051b57 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Tue, 10 Jan 2017 21:30:21 +0300
Subject: [PATCH 059/898] ovl: drop CAP_SYS_RESOURCE from saved mounter's
 credentials

If overlay was mounted by root then quota set for upper layer does not work
because overlay now always use mounter's credentials for operations.
Also overlay might deplete reserved space and inodes in ext4.

This patch drops capability SYS_RESOURCE from saved credentials.
This affects creation new files, whiteouts, and copy-up operations.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 1175b6b8d963 ("ovl: do operations on underlying file system in mounter's context")
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/super.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 346f668e7df0..7b2188181367 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -721,6 +721,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int stacklen = 0;
 	unsigned int i;
 	bool remote = false;
+	struct cred *cred;
 	int err;
 
 	err = -ENOMEM;
@@ -901,10 +902,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	else
 		sb->s_d_op = &ovl_dentry_operations;
 
-	ufs->creator_cred = prepare_creds();
-	if (!ufs->creator_cred)
+	ufs->creator_cred = cred = prepare_creds();
+	if (!cred)
 		goto out_put_lower_mnt;
 
+	/* Never override disk quota limits or use reserved space */
+	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
+
 	err = -ENOMEM;
 	oe = ovl_alloc_entry(numlower);
 	if (!oe)
-- 
GitLab


From df2e32c5ada8590b859863cf89f418c7962b9a21 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:27:53 -0800
Subject: [PATCH 060/898] qla2xxx: Remove direct access of scsi_status field in
 se_cmd

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_def.h    | 1 +
 drivers/scsi/qla2xxx/qla_target.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 5b1287a63c49..4aae861a6713 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1794,6 +1794,7 @@ typedef struct {
 #define SS_RESIDUAL_OVER		BIT_10
 #define SS_SENSE_LEN_VALID		BIT_9
 #define SS_RESPONSE_INFO_LEN_VALID	BIT_8
+#define SS_SCSI_STATUS_BYTE	0xff
 
 #define SS_RESERVE_CONFLICT		(BIT_4 | BIT_3)
 #define SS_BUSY_CONDITION		BIT_3
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index e4fda84b959e..439c1fc44c7a 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -2288,7 +2288,7 @@ static void qlt_24xx_init_ctio_to_isp(struct ctio7_to_24xx *ctio,
 		int i;
 
 		if (qlt_need_explicit_conf(prm->tgt->ha, prm->cmd, 1)) {
-			if (prm->cmd->se_cmd.scsi_status != 0) {
+			if ((prm->rq_result & SS_SCSI_STATUS_BYTE) != 0) {
 				ql_dbg(ql_dbg_tgt, prm->cmd->vha, 0xe017,
 				    "Skipping EXPLICIT_CONFORM and "
 				    "CTIO7_FLAGS_CONFORM_REQ for FCP READ w/ "
-- 
GitLab


From be92fc3fde95c94bb54ff471219552a581640a6b Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:27:54 -0800
Subject: [PATCH 061/898] qla2xxx: Cleanup TMF code translation from qla_target

Move code code which converts Task Mgmt Command flags for
ATIO to TCM #defines, from qla2xxx driver to tcm_qla2xxx
driver.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_target.c  | 75 +++---------------------------
 drivers/scsi/qla2xxx/qla_target.h  |  6 ++-
 drivers/scsi/qla2xxx/tcm_qla2xxx.c | 40 +++++++++++++++-
 3 files changed, 49 insertions(+), 72 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 439c1fc44c7a..fcdd5c9ed3bf 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1592,8 +1592,9 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	mcmd->sess = sess;
 	memcpy(&mcmd->orig_iocb.abts, abts, sizeof(mcmd->orig_iocb.abts));
 	mcmd->reset_count = vha->hw->chip_reset;
+	mcmd->tmr_func = QLA_TGT_ABTS;
 
-	rc = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, TMR_ABORT_TASK,
+	rc = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, mcmd->tmr_func,
 	    abts->exchange_addr_to_abort);
 	if (rc != 0) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf052,
@@ -4051,7 +4052,6 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	struct qla_tgt_mgmt_cmd *mcmd;
 	struct atio_from_isp *a = (struct atio_from_isp *)iocb;
 	int res;
-	uint8_t tmr_func;
 
 	mcmd = mempool_alloc(qla_tgt_mgmt_cmd_mempool, GFP_ATOMIC);
 	if (!mcmd) {
@@ -4073,74 +4073,12 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	mcmd->reset_count = vha->hw->chip_reset;
 
 	switch (fn) {
-	case QLA_TGT_CLEAR_ACA:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10000,
-		    "qla_target(%d): CLEAR_ACA received\n", sess->vha->vp_idx);
-		tmr_func = TMR_CLEAR_ACA;
-		break;
-
-	case QLA_TGT_TARGET_RESET:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10001,
-		    "qla_target(%d): TARGET_RESET received\n",
-		    sess->vha->vp_idx);
-		tmr_func = TMR_TARGET_WARM_RESET;
-		break;
-
 	case QLA_TGT_LUN_RESET:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10002,
-		    "qla_target(%d): LUN_RESET received\n", sess->vha->vp_idx);
-		tmr_func = TMR_LUN_RESET;
-		abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id);
-		break;
-
-	case QLA_TGT_CLEAR_TS:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10003,
-		    "qla_target(%d): CLEAR_TS received\n", sess->vha->vp_idx);
-		tmr_func = TMR_CLEAR_TASK_SET;
-		break;
-
-	case QLA_TGT_ABORT_TS:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10004,
-		    "qla_target(%d): ABORT_TS received\n", sess->vha->vp_idx);
-		tmr_func = TMR_ABORT_TASK_SET;
-		break;
-#if 0
-	case QLA_TGT_ABORT_ALL:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10005,
-		    "qla_target(%d): Doing ABORT_ALL_TASKS\n",
-		    sess->vha->vp_idx);
-		tmr_func = 0;
-		break;
-
-	case QLA_TGT_ABORT_ALL_SESS:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10006,
-		    "qla_target(%d): Doing ABORT_ALL_TASKS_SESS\n",
-		    sess->vha->vp_idx);
-		tmr_func = 0;
-		break;
-
-	case QLA_TGT_NEXUS_LOSS_SESS:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10007,
-		    "qla_target(%d): Doing NEXUS_LOSS_SESS\n",
-		    sess->vha->vp_idx);
-		tmr_func = 0;
-		break;
-
-	case QLA_TGT_NEXUS_LOSS:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10008,
-		    "qla_target(%d): Doing NEXUS_LOSS\n", sess->vha->vp_idx);
-		tmr_func = 0;
-		break;
-#endif
-	default:
-		ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000a,
-		    "qla_target(%d): Unknown task mgmt fn 0x%x\n",
-		    sess->vha->vp_idx, fn);
-		mempool_free(mcmd, qla_tgt_mgmt_cmd_mempool);
-		return -ENOSYS;
+	    abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id);
+	    break;
 	}
 
-	res = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, tmr_func, 0);
+	res = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, mcmd->tmr_func, 0);
 	if (res != 0) {
 		ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000b,
 		    "qla_target(%d): tgt.tgt_ops->handle_tmr() failed: %d\n",
@@ -4215,8 +4153,9 @@ static int __qlt_abort_task(struct scsi_qla_host *vha,
 	lun = a->u.isp24.fcp_cmnd.lun;
 	unpacked_lun = scsilun_to_int((struct scsi_lun *)&lun);
 	mcmd->reset_count = vha->hw->chip_reset;
+	mcmd->tmr_func = QLA_TGT_2G_ABORT_TASK;
 
-	rc = ha->tgt.tgt_ops->handle_tmr(mcmd, unpacked_lun, TMR_ABORT_TASK,
+	rc = ha->tgt.tgt_ops->handle_tmr(mcmd, unpacked_lun, mcmd->tmr_func,
 	    le16_to_cpu(iocb->u.isp2x.seq_id));
 	if (rc != 0) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf060,
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 0824a8164a24..14f2e241db8c 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -744,7 +744,7 @@ struct qla_tgt_func_tmpl {
 			unsigned char *, uint32_t, int, int, int);
 	void (*handle_data)(struct qla_tgt_cmd *);
 	void (*handle_dif_err)(struct qla_tgt_cmd *);
-	int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint8_t,
+	int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint16_t,
 			uint32_t);
 	void (*free_cmd)(struct qla_tgt_cmd *);
 	void (*free_mcmd)(struct qla_tgt_mgmt_cmd *);
@@ -795,6 +795,8 @@ int qla2x00_wait_for_hba_online(struct scsi_qla_host *);
 #define QLA_TGT_ABORT_ALL               0xFFFE
 #define QLA_TGT_NEXUS_LOSS_SESS         0xFFFD
 #define QLA_TGT_NEXUS_LOSS              0xFFFC
+#define QLA_TGT_ABTS					0xFFFB
+#define QLA_TGT_2G_ABORT_TASK			0xFFFA
 
 /* Notify Acknowledge flags */
 #define NOTIFY_ACK_RES_COUNT        BIT_8
@@ -1056,7 +1058,7 @@ struct qla_tgt_sess_work_param {
 };
 
 struct qla_tgt_mgmt_cmd {
-	uint8_t tmr_func;
+	uint16_t tmr_func;
 	uint8_t fc_tm_rsp;
 	struct qla_tgt_sess *sess;
 	struct se_cmd se_cmd;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index d925910be761..1bec6ab66aaf 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -563,13 +563,49 @@ static void tcm_qla2xxx_handle_dif_err(struct qla_tgt_cmd *cmd)
  * Called from qla_target.c:qlt_issue_task_mgmt()
  */
 static int tcm_qla2xxx_handle_tmr(struct qla_tgt_mgmt_cmd *mcmd, uint32_t lun,
-	uint8_t tmr_func, uint32_t tag)
+	uint16_t tmr_func, uint32_t tag)
 {
 	struct qla_tgt_sess *sess = mcmd->sess;
 	struct se_cmd *se_cmd = &mcmd->se_cmd;
+	int transl_tmr_func = 0;
+
+	switch (tmr_func) {
+	case QLA_TGT_ABTS:
+		pr_debug("%ld: ABTS received\n", sess->vha->host_no);
+		transl_tmr_func = TMR_ABORT_TASK;
+		break;
+	case QLA_TGT_2G_ABORT_TASK:
+		pr_debug("%ld: 2G Abort Task received\n", sess->vha->host_no);
+		transl_tmr_func = TMR_ABORT_TASK;
+		break;
+	case QLA_TGT_CLEAR_ACA:
+		pr_debug("%ld: CLEAR_ACA received\n", sess->vha->host_no);
+		transl_tmr_func = TMR_CLEAR_ACA;
+		break;
+	case QLA_TGT_TARGET_RESET:
+		pr_debug("%ld: TARGET_RESET received\n", sess->vha->host_no);
+		transl_tmr_func = TMR_TARGET_WARM_RESET;
+		break;
+	case QLA_TGT_LUN_RESET:
+		pr_debug("%ld: LUN_RESET received\n", sess->vha->host_no);
+		transl_tmr_func = TMR_LUN_RESET;
+		break;
+	case QLA_TGT_CLEAR_TS:
+		pr_debug("%ld: CLEAR_TS received\n", sess->vha->host_no);
+		transl_tmr_func = TMR_CLEAR_TASK_SET;
+		break;
+	case QLA_TGT_ABORT_TS:
+		pr_debug("%ld: ABORT_TS received\n", sess->vha->host_no);
+		transl_tmr_func = TMR_ABORT_TASK_SET;
+		break;
+	default:
+		pr_debug("%ld: Unknown task mgmt fn 0x%x\n",
+		    sess->vha->host_no, tmr_func);
+		return -ENOSYS;
+	}
 
 	return target_submit_tmr(se_cmd, sess->se_sess, NULL, lun, mcmd,
-			tmr_func, GFP_ATOMIC, tag, TARGET_SCF_ACK_KREF);
+	    transl_tmr_func, GFP_ATOMIC, tag, TARGET_SCF_ACK_KREF);
 }
 
 static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
-- 
GitLab


From 1eb42f965cedafb700e9c902ddafb1c51e3117f7 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:27:55 -0800
Subject: [PATCH 062/898] qla2xxx: Make trace flags more readable

Trace flags are useful during debugging crash dumps
using crash utility. These trace flags makes it easier
to understand various states a command has successfully
completed.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_target.c  | 28 +++++++--------
 drivers/scsi/qla2xxx/qla_target.h  | 55 ++++++++++++++----------------
 drivers/scsi/qla2xxx/tcm_qla2xxx.c | 43 +++++++++++------------
 3 files changed, 59 insertions(+), 67 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index fcdd5c9ed3bf..5f31ae99fbe2 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3297,7 +3297,7 @@ int qlt_abort_cmd(struct qla_tgt_cmd *cmd)
 		return EIO;
 	}
 	cmd->aborted = 1;
-	cmd->cmd_flags |= BIT_6;
+	cmd->trc_flags |= TRC_ABORT;
 	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
 
 	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0, 1);
@@ -3345,7 +3345,7 @@ static int qlt_prepare_srr_ctio(struct scsi_qla_host *vha,
 	struct qla_tgt_srr_imm *imm;
 
 	tgt->ctio_srr_id++;
-	cmd->cmd_flags |= BIT_15;
+	cmd->trc_flags |= TRC_SRR_CTIO;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf019,
 	    "qla_target(%d): CTIO with SRR status received\n", vha->vp_idx);
@@ -3528,7 +3528,7 @@ qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd)
 		dump_stack();
 	}
 
-	cmd->cmd_flags |= BIT_17;
+	cmd->trc_flags |= TRC_FLUSH;
 	ha->tgt.tgt_ops->free_cmd(cmd);
 }
 
@@ -3694,7 +3694,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 		 */
 		if ((cmd->state != QLA_TGT_STATE_NEED_DATA) &&
 		    (!cmd->aborted)) {
-			cmd->cmd_flags |= BIT_13;
+			cmd->trc_flags |= TRC_CTIO_ERR;
 			if (qlt_term_ctio_exchange(vha, ctio, cmd, status))
 				return;
 		}
@@ -3702,7 +3702,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 skip_term:
 
 	if (cmd->state == QLA_TGT_STATE_PROCESSED) {
-		cmd->cmd_flags |= BIT_12;
+		cmd->trc_flags |= TRC_CTIO_DONE;
 	} else if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
 		cmd->state = QLA_TGT_STATE_DATA_IN;
 
@@ -3712,11 +3712,11 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 		ha->tgt.tgt_ops->handle_data(cmd);
 		return;
 	} else if (cmd->aborted) {
-		cmd->cmd_flags |= BIT_18;
+		cmd->trc_flags |= TRC_CTIO_ABORTED;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01e,
 		  "Aborted command %p (tag %lld) finished\n", cmd, se_cmd->tag);
 	} else {
-		cmd->cmd_flags |= BIT_19;
+		cmd->trc_flags |= TRC_CTIO_STRANGE;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05c,
 		    "qla_target(%d): A command in state (%d) should "
 		    "not return a CTIO complete\n", vha->vp_idx, cmd->state);
@@ -3781,7 +3781,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 	int ret, fcp_task_attr, data_dir, bidi = 0;
 
 	cmd->cmd_in_wq = 0;
-	cmd->cmd_flags |= BIT_1;
+	cmd->trc_flags |= TRC_DO_WORK;
 	if (tgt->tgt_stop)
 		goto out_term;
 
@@ -3833,7 +3833,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 	 * cmd has not sent to target yet, so pass NULL as the second
 	 * argument to qlt_send_term_exchange() and free the memory here.
 	 */
-	cmd->cmd_flags |= BIT_2;
+	cmd->trc_flags |= TRC_DO_WORK_ERR;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1, 0);
 
@@ -3884,7 +3884,7 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
 	cmd->loop_id = sess->loop_id;
 	cmd->conf_compl_supported = sess->conf_compl_supported;
 
-	cmd->cmd_flags = 0;
+	cmd->trc_flags = 0;
 	cmd->jiffies_at_alloc = get_jiffies_64();
 
 	cmd->reset_count = vha->hw->chip_reset;
@@ -4020,7 +4020,7 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 	}
 
 	cmd->cmd_in_wq = 1;
-	cmd->cmd_flags |= BIT_0;
+	cmd->trc_flags |= TRC_NEW_CMD;
 	cmd->se_cmd.cpuid = ha->msix_count ?
 		ha->tgt.rspq_vector_cpuid : WORK_CPU_UNBOUND;
 
@@ -4712,7 +4712,7 @@ static void qlt_handle_srr(struct scsi_qla_host *vha,
 			    0, 0, 0, NOTIFY_ACK_SRR_FLAGS_ACCEPT, 0, 0);
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 			if (xmit_type & QLA_TGT_XMIT_DATA) {
-				cmd->cmd_flags |= BIT_8;
+				cmd->trc_flags |= TRC_SRR_XRDY;
 				qlt_rdy_to_xfer(cmd);
 			}
 		} else {
@@ -4731,7 +4731,7 @@ static void qlt_handle_srr(struct scsi_qla_host *vha,
 
 	/* Transmit response in case of status and data-in cases */
 	if (resp) {
-		cmd->cmd_flags |= BIT_7;
+		cmd->trc_flags |= TRC_SRR_RSP;
 		qlt_xmit_response(cmd, xmit_type, se_cmd->scsi_status);
 	}
 
@@ -4747,7 +4747,7 @@ static void qlt_handle_srr(struct scsi_qla_host *vha,
 		cmd->state = QLA_TGT_STATE_DATA_IN;
 		dump_stack();
 	} else {
-		cmd->cmd_flags |= BIT_9;
+		cmd->trc_flags |= TRC_SRR_TERM;
 		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 14f2e241db8c..5d00529b68c4 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -965,35 +965,28 @@ struct qla_tgt_sess {
 	qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
 };
 
-typedef enum {
-	/*
-	 * BIT_0 - Atio Arrival / schedule to work
-	 * BIT_1 - qlt_do_work
-	 * BIT_2 - qlt_do work failed
-	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
-	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
-	 * BIT_5 - status respond / tcm_qla2xx_queue_status
-	 * BIT_6 - tcm request to abort/Term exchange.
-	 *	pre_xmit_response->qlt_send_term_exchange
-	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
-	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
-	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
-	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
-
-	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
-	 * BIT_13 - Bad completion -
-	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
-	 * BIT_14 - Back end data received/sent.
-	 * BIT_15 - SRR prepare ctio
-	 * BIT_16 - complete free
-	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
-	 * BIT_18 - completion w/abort status
-	 * BIT_19 - completion w/unknown status
-	 * BIT_20 - tcm_qla2xxx_free_cmd
-	 */
-	CMD_FLAG_DATA_WORK = BIT_11,
-	CMD_FLAG_DATA_WORK_FREE = BIT_21,
-} cmd_flags_t;
+enum trace_flags {
+	TRC_NEW_CMD = BIT_0,
+	TRC_DO_WORK = BIT_1,
+	TRC_DO_WORK_ERR = BIT_2,
+	TRC_XFR_RDY = BIT_3,
+	TRC_XMIT_DATA = BIT_4,
+	TRC_XMIT_STATUS = BIT_5,
+	TRC_SRR_RSP =  BIT_6,
+	TRC_SRR_XRDY = BIT_7,
+	TRC_SRR_TERM = BIT_8,
+	TRC_SRR_CTIO = BIT_9,
+	TRC_FLUSH = BIT_10,
+	TRC_CTIO_ERR = BIT_11,
+	TRC_CTIO_DONE = BIT_12,
+	TRC_CTIO_ABORTED =  BIT_13,
+	TRC_CTIO_STRANGE= BIT_14,
+	TRC_CMD_DONE = BIT_15,
+	TRC_CMD_CHK_STOP = BIT_16,
+	TRC_CMD_FREE = BIT_17,
+	TRC_DATA_IN = BIT_18,
+	TRC_ABORT = BIT_19,
+};
 
 struct qla_tgt_cmd {
 	struct se_cmd se_cmd;
@@ -1016,6 +1009,8 @@ struct qla_tgt_cmd {
 	unsigned int cmd_sent_to_fw:1;
 	unsigned int cmd_in_wq:1;
 	unsigned int aborted:1;
+	unsigned int data_work:1;
+	unsigned int data_work_free:1;
 
 	struct scatterlist *sg;	/* cmd data buffer SG vector */
 	int sg_cnt;		/* SG segments count */
@@ -1040,7 +1035,7 @@ struct qla_tgt_cmd {
 	uint64_t jiffies_at_alloc;
 	uint64_t jiffies_at_free;
 
-	cmd_flags_t cmd_flags;
+	enum trace_flags trc_flags;
 };
 
 struct qla_tgt_sess_work_param {
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 1bec6ab66aaf..af4a198e5537 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -282,10 +282,10 @@ static void tcm_qla2xxx_complete_free(struct work_struct *work)
 
 	cmd->cmd_in_wq = 0;
 
-	WARN_ON(cmd->cmd_flags &  BIT_16);
+	WARN_ON(cmd->trc_flags & TRC_CMD_FREE);
 
 	cmd->vha->tgt_counters.qla_core_ret_sta_ctio++;
-	cmd->cmd_flags |= BIT_16;
+	cmd->trc_flags |= TRC_CMD_FREE;
 	transport_generic_free_cmd(&cmd->se_cmd, 0);
 }
 
@@ -299,8 +299,8 @@ static void tcm_qla2xxx_free_cmd(struct qla_tgt_cmd *cmd)
 	cmd->vha->tgt_counters.core_qla_free_cmd++;
 	cmd->cmd_in_wq = 1;
 
-	BUG_ON(cmd->cmd_flags & BIT_20);
-	cmd->cmd_flags |= BIT_20;
+	WARN_ON(cmd->trc_flags & TRC_CMD_DONE);
+	cmd->trc_flags |= TRC_CMD_DONE;
 
 	INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free);
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
@@ -315,7 +315,7 @@ static int tcm_qla2xxx_check_stop_free(struct se_cmd *se_cmd)
 
 	if ((se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) == 0) {
 		cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd);
-		cmd->cmd_flags |= BIT_14;
+		cmd->trc_flags |= TRC_CMD_CHK_STOP;
 	}
 
 	return target_put_sess_cmd(se_cmd);
@@ -377,7 +377,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 			cmd->se_cmd.se_cmd_flags);
 		return 0;
 	}
-	cmd->cmd_flags |= BIT_3;
+	cmd->trc_flags |= TRC_XFR_RDY;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
 
@@ -493,9 +493,9 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 	cmd->cmd_in_wq = 0;
 
 	spin_lock_irqsave(&cmd->cmd_lock, flags);
-	cmd->cmd_flags |= CMD_FLAG_DATA_WORK;
+	cmd->data_work = 1;
 	if (cmd->aborted) {
-		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		cmd->data_work_free = 1;
 		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
 
 		tcm_qla2xxx_free_cmd(cmd);
@@ -532,7 +532,7 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
  */
 static void tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd)
 {
-	cmd->cmd_flags |= BIT_10;
+	cmd->trc_flags |= TRC_DATA_IN;
 	cmd->cmd_in_wq = 1;
 	INIT_WORK(&cmd->work, tcm_qla2xxx_handle_data_work);
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
@@ -627,7 +627,7 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 		return 0;
 	}
 
-	cmd->cmd_flags |= BIT_4;
+	cmd->trc_flags |= TRC_XMIT_DATA;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
 
@@ -658,11 +658,11 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd)
 	cmd->sg_cnt = 0;
 	cmd->offset = 0;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	if (cmd->cmd_flags &  BIT_5) {
-		pr_crit("Bit_5 already set for cmd = %p.\n", cmd);
+	if (cmd->trc_flags & TRC_XMIT_STATUS) {
+		pr_crit("Multiple calls for status = %p.\n", cmd);
 		dump_stack();
 	}
-	cmd->cmd_flags |= BIT_5;
+	cmd->trc_flags |= TRC_XMIT_STATUS;
 
 	if (se_cmd->data_direction == DMA_FROM_DEVICE) {
 		/*
@@ -718,10 +718,7 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd)
 	qlt_xmit_tm_rsp(mcmd);
 }
 
-
-#define DATA_WORK_NOT_FREE(_flags) \
-	(( _flags & (CMD_FLAG_DATA_WORK|CMD_FLAG_DATA_WORK_FREE)) == \
-	 CMD_FLAG_DATA_WORK)
+#define DATA_WORK_NOT_FREE(_cmd) (_cmd->data_work && !_cmd->data_work_free)
 static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
@@ -733,13 +730,13 @@ static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 
 	spin_lock_irqsave(&cmd->cmd_lock, flags);
 	if ((cmd->state == QLA_TGT_STATE_NEW)||
-		((cmd->state == QLA_TGT_STATE_DATA_IN) &&
-		 DATA_WORK_NOT_FREE(cmd->cmd_flags)) ) {
-
-		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+	    ((cmd->state == QLA_TGT_STATE_DATA_IN) &&
+		DATA_WORK_NOT_FREE(cmd))) {
+		cmd->data_work_free = 1;
 		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
-		/* Cmd have not reached firmware.
-		 * Use this trigger to free it. */
+		/*
+		 * cmd has not reached fw, Use this trigger to free it.
+		 */
 		tcm_qla2xxx_free_cmd(cmd);
 		return;
 	}
-- 
GitLab


From 2c39b5ca2a8cb99fc463fd622e8ea3b9fbb980a2 Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <himanshu.madhani@cavium.com>
Date: Thu, 19 Jan 2017 22:27:56 -0800
Subject: [PATCH 063/898] qla2xxx: Remove SRR code

During initial implementation, tape support was included but not
enabled by default on target. So far, we don't see any target
customer requesting this support. Since this code is not being
used actively, we want to remove it and we will add back if there
are any request in future for SRR support.

Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Giridhar Malavali <giridhar.malavali@cavium.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_target.c | 641 ------------------------------
 drivers/scsi/qla2xxx/qla_target.h |  21 -
 2 files changed, 662 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 5f31ae99fbe2..119a445a82f6 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -106,8 +106,6 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	int fn, void *iocb, int flags);
 static void qlt_send_term_exchange(struct scsi_qla_host *ha, struct qla_tgt_cmd
 	*cmd, struct atio_from_isp *atio, int ha_locked, int ul_abort);
-static void qlt_reject_free_srr_imm(struct scsi_qla_host *ha,
-	struct qla_tgt_srr_imm *imm, int ha_lock);
 static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd);
 static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
@@ -2183,95 +2181,6 @@ static inline int qlt_need_explicit_conf(struct qla_hw_data *ha,
 		    cmd->conf_compl_supported;
 }
 
-#ifdef CONFIG_QLA_TGT_DEBUG_SRR
-/*
- *  Original taken from the XFS code
- */
-static unsigned long qlt_srr_random(void)
-{
-	static int Inited;
-	static unsigned long RandomValue;
-	static DEFINE_SPINLOCK(lock);
-	/* cycles pseudo-randomly through all values between 1 and 2^31 - 2 */
-	register long rv;
-	register long lo;
-	register long hi;
-	unsigned long flags;
-
-	spin_lock_irqsave(&lock, flags);
-	if (!Inited) {
-		RandomValue = jiffies;
-		Inited = 1;
-	}
-	rv = RandomValue;
-	hi = rv / 127773;
-	lo = rv % 127773;
-	rv = 16807 * lo - 2836 * hi;
-	if (rv <= 0)
-		rv += 2147483647;
-	RandomValue = rv;
-	spin_unlock_irqrestore(&lock, flags);
-	return rv;
-}
-
-static void qlt_check_srr_debug(struct qla_tgt_cmd *cmd, int *xmit_type)
-{
-#if 0 /* This is not a real status packets lost, so it won't lead to SRR */
-	if ((*xmit_type & QLA_TGT_XMIT_STATUS) && (qlt_srr_random() % 200)
-	    == 50) {
-		*xmit_type &= ~QLA_TGT_XMIT_STATUS;
-		ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf015,
-		    "Dropping cmd %p (tag %d) status", cmd, se_cmd->tag);
-	}
-#endif
-	/*
-	 * It's currently not possible to simulate SRRs for FCP_WRITE without
-	 * a physical link layer failure, so don't even try here..
-	 */
-	if (cmd->dma_data_direction != DMA_FROM_DEVICE)
-		return;
-
-	if (qlt_has_data(cmd) && (cmd->sg_cnt > 1) &&
-	    ((qlt_srr_random() % 100) == 20)) {
-		int i, leave = 0;
-		unsigned int tot_len = 0;
-
-		while (leave == 0)
-			leave = qlt_srr_random() % cmd->sg_cnt;
-
-		for (i = 0; i < leave; i++)
-			tot_len += cmd->sg[i].length;
-
-		ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf016,
-		    "Cutting cmd %p (tag %d) buffer"
-		    " tail to len %d, sg_cnt %d (cmd->bufflen %d,"
-		    " cmd->sg_cnt %d)", cmd, se_cmd->tag, tot_len, leave,
-		    cmd->bufflen, cmd->sg_cnt);
-
-		cmd->bufflen = tot_len;
-		cmd->sg_cnt = leave;
-	}
-
-	if (qlt_has_data(cmd) && ((qlt_srr_random() % 100) == 70)) {
-		unsigned int offset = qlt_srr_random() % cmd->bufflen;
-
-		ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf017,
-		    "Cutting cmd %p (tag %d) buffer head "
-		    "to offset %d (cmd->bufflen %d)", cmd, se_cmd->tag, offset,
-		    cmd->bufflen);
-		if (offset == 0)
-			*xmit_type &= ~QLA_TGT_XMIT_DATA;
-		else if (qlt_set_data_offset(cmd, offset)) {
-			ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf018,
-			    "qlt_set_data_offset() failed (tag %d)", se_cmd->tag);
-		}
-	}
-}
-#else
-static inline void qlt_check_srr_debug(struct qla_tgt_cmd *cmd, int *xmit_type)
-{}
-#endif
-
 static void qlt_24xx_init_ctio_to_isp(struct ctio7_to_24xx *ctio,
 	struct qla_tgt_prm *prm)
 {
@@ -2686,7 +2595,6 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	memset(&prm, 0, sizeof(prm));
-	qlt_check_srr_debug(cmd, &xmit_type);
 
 	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe018,
 	    "is_send_status=%d, cmd->bufflen=%d, cmd->sg_cnt=%d, cmd->dma_data_direction=%d se_cmd[%p]\n",
@@ -3336,90 +3244,6 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 }
 EXPORT_SYMBOL(qlt_free_cmd);
 
-/* ha->hardware_lock supposed to be held on entry */
-static int qlt_prepare_srr_ctio(struct scsi_qla_host *vha,
-	struct qla_tgt_cmd *cmd, void *ctio)
-{
-	struct qla_tgt_srr_ctio *sc;
-	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
-	struct qla_tgt_srr_imm *imm;
-
-	tgt->ctio_srr_id++;
-	cmd->trc_flags |= TRC_SRR_CTIO;
-
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf019,
-	    "qla_target(%d): CTIO with SRR status received\n", vha->vp_idx);
-
-	if (!ctio) {
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf055,
-		    "qla_target(%d): SRR CTIO, but ctio is NULL\n",
-		    vha->vp_idx);
-		return -EINVAL;
-	}
-
-	sc = kzalloc(sizeof(*sc), GFP_ATOMIC);
-	if (sc != NULL) {
-		sc->cmd = cmd;
-		/* IRQ is already OFF */
-		spin_lock(&tgt->srr_lock);
-		sc->srr_id = tgt->ctio_srr_id;
-		list_add_tail(&sc->srr_list_entry,
-		    &tgt->srr_ctio_list);
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01a,
-		    "CTIO SRR %p added (id %d)\n", sc, sc->srr_id);
-		if (tgt->imm_srr_id == tgt->ctio_srr_id) {
-			int found = 0;
-			list_for_each_entry(imm, &tgt->srr_imm_list,
-			    srr_list_entry) {
-				if (imm->srr_id == sc->srr_id) {
-					found = 1;
-					break;
-				}
-			}
-			if (found) {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01b,
-				    "Scheduling srr work\n");
-				schedule_work(&tgt->srr_work);
-			} else {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf056,
-				    "qla_target(%d): imm_srr_id "
-				    "== ctio_srr_id (%d), but there is no "
-				    "corresponding SRR IMM, deleting CTIO "
-				    "SRR %p\n", vha->vp_idx,
-				    tgt->ctio_srr_id, sc);
-				list_del(&sc->srr_list_entry);
-				spin_unlock(&tgt->srr_lock);
-
-				kfree(sc);
-				return -EINVAL;
-			}
-		}
-		spin_unlock(&tgt->srr_lock);
-	} else {
-		struct qla_tgt_srr_imm *ti;
-
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf057,
-		    "qla_target(%d): Unable to allocate SRR CTIO entry\n",
-		    vha->vp_idx);
-		spin_lock(&tgt->srr_lock);
-		list_for_each_entry_safe(imm, ti, &tgt->srr_imm_list,
-		    srr_list_entry) {
-			if (imm->srr_id == tgt->ctio_srr_id) {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01c,
-				    "IMM SRR %p deleted (id %d)\n",
-				    imm, imm->srr_id);
-				list_del(&imm->srr_list_entry);
-				qlt_reject_free_srr_imm(vha, imm, 1);
-			}
-		}
-		spin_unlock(&tgt->srr_lock);
-
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
 /*
  * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire
  */
@@ -3637,16 +3461,6 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 			}
 			break;
 		}
-		case CTIO_SRR_RECEIVED:
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05a,
-			    "qla_target(%d): CTIO with SRR_RECEIVED"
-			    " status %x received (state %x, se_cmd %p)\n",
-			    vha->vp_idx, status, cmd->state, se_cmd);
-			if (qlt_prepare_srr_ctio(vha, cmd, ctio) != 0)
-				break;
-			else
-				return;
-
 		case CTIO_DIF_ERROR: {
 			struct ctio_crc_from_fw *crc =
 				(struct ctio_crc_from_fw *)ctio;
@@ -4499,451 +4313,6 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 	return res;
 }
 
-static int qlt_set_data_offset(struct qla_tgt_cmd *cmd, uint32_t offset)
-{
-#if 1
-	/*
-	 * FIXME: Reject non zero SRR relative offset until we can test
-	 * this code properly.
-	 */
-	pr_debug("Rejecting non zero SRR rel_offs: %u\n", offset);
-	return -1;
-#else
-	struct scatterlist *sg, *sgp, *sg_srr, *sg_srr_start = NULL;
-	size_t first_offset = 0, rem_offset = offset, tmp = 0;
-	int i, sg_srr_cnt, bufflen = 0;
-
-	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe023,
-	    "Entering qla_tgt_set_data_offset: cmd: %p, cmd->sg: %p, "
-	    "cmd->sg_cnt: %u, direction: %d\n",
-	    cmd, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction);
-
-	if (!cmd->sg || !cmd->sg_cnt) {
-		ql_dbg(ql_dbg_tgt, cmd->vha, 0xe055,
-		    "Missing cmd->sg or zero cmd->sg_cnt in"
-		    " qla_tgt_set_data_offset\n");
-		return -EINVAL;
-	}
-	/*
-	 * Walk the current cmd->sg list until we locate the new sg_srr_start
-	 */
-	for_each_sg(cmd->sg, sg, cmd->sg_cnt, i) {
-		ql_dbg(ql_dbg_tgt, cmd->vha, 0xe024,
-		    "sg[%d]: %p page: %p, length: %d, offset: %d\n",
-		    i, sg, sg_page(sg), sg->length, sg->offset);
-
-		if ((sg->length + tmp) > offset) {
-			first_offset = rem_offset;
-			sg_srr_start = sg;
-			ql_dbg(ql_dbg_tgt, cmd->vha, 0xe025,
-			    "Found matching sg[%d], using %p as sg_srr_start, "
-			    "and using first_offset: %zu\n", i, sg,
-			    first_offset);
-			break;
-		}
-		tmp += sg->length;
-		rem_offset -= sg->length;
-	}
-
-	if (!sg_srr_start) {
-		ql_dbg(ql_dbg_tgt, cmd->vha, 0xe056,
-		    "Unable to locate sg_srr_start for offset: %u\n", offset);
-		return -EINVAL;
-	}
-	sg_srr_cnt = (cmd->sg_cnt - i);
-
-	sg_srr = kzalloc(sizeof(struct scatterlist) * sg_srr_cnt, GFP_KERNEL);
-	if (!sg_srr) {
-		ql_dbg(ql_dbg_tgt, cmd->vha, 0xe057,
-		    "Unable to allocate sgp\n");
-		return -ENOMEM;
-	}
-	sg_init_table(sg_srr, sg_srr_cnt);
-	sgp = &sg_srr[0];
-	/*
-	 * Walk the remaining list for sg_srr_start, mapping to the newly
-	 * allocated sg_srr taking first_offset into account.
-	 */
-	for_each_sg(sg_srr_start, sg, sg_srr_cnt, i) {
-		if (first_offset) {
-			sg_set_page(sgp, sg_page(sg),
-			    (sg->length - first_offset), first_offset);
-			first_offset = 0;
-		} else {
-			sg_set_page(sgp, sg_page(sg), sg->length, 0);
-		}
-		bufflen += sgp->length;
-
-		sgp = sg_next(sgp);
-		if (!sgp)
-			break;
-	}
-
-	cmd->sg = sg_srr;
-	cmd->sg_cnt = sg_srr_cnt;
-	cmd->bufflen = bufflen;
-	cmd->offset += offset;
-	cmd->free_sg = 1;
-
-	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe026, "New cmd->sg: %p\n", cmd->sg);
-	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe027, "New cmd->sg_cnt: %u\n",
-	    cmd->sg_cnt);
-	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe028, "New cmd->bufflen: %u\n",
-	    cmd->bufflen);
-	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe029, "New cmd->offset: %u\n",
-	    cmd->offset);
-
-	if (cmd->sg_cnt < 0)
-		BUG();
-
-	if (cmd->bufflen < 0)
-		BUG();
-
-	return 0;
-#endif
-}
-
-static inline int qlt_srr_adjust_data(struct qla_tgt_cmd *cmd,
-	uint32_t srr_rel_offs, int *xmit_type)
-{
-	int res = 0, rel_offs;
-
-	rel_offs = srr_rel_offs - cmd->offset;
-	ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf027, "srr_rel_offs=%d, rel_offs=%d",
-	    srr_rel_offs, rel_offs);
-
-	*xmit_type = QLA_TGT_XMIT_ALL;
-
-	if (rel_offs < 0) {
-		ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf062,
-		    "qla_target(%d): SRR rel_offs (%d) < 0",
-		    cmd->vha->vp_idx, rel_offs);
-		res = -1;
-	} else if (rel_offs == cmd->bufflen)
-		*xmit_type = QLA_TGT_XMIT_STATUS;
-	else if (rel_offs > 0)
-		res = qlt_set_data_offset(cmd, rel_offs);
-
-	return res;
-}
-
-/* No locks, thread context */
-static void qlt_handle_srr(struct scsi_qla_host *vha,
-	struct qla_tgt_srr_ctio *sctio, struct qla_tgt_srr_imm *imm)
-{
-	struct imm_ntfy_from_isp *ntfy =
-	    (struct imm_ntfy_from_isp *)&imm->imm_ntfy;
-	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_cmd *cmd = sctio->cmd;
-	struct se_cmd *se_cmd = &cmd->se_cmd;
-	unsigned long flags;
-	int xmit_type = 0, resp = 0;
-	uint32_t offset;
-	uint16_t srr_ui;
-
-	offset = le32_to_cpu(ntfy->u.isp24.srr_rel_offs);
-	srr_ui = ntfy->u.isp24.srr_ui;
-
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf028, "SRR cmd %p, srr_ui %x\n",
-	    cmd, srr_ui);
-
-	switch (srr_ui) {
-	case SRR_IU_STATUS:
-		spin_lock_irqsave(&ha->hardware_lock, flags);
-		qlt_send_notify_ack(vha, ntfy,
-		    0, 0, 0, NOTIFY_ACK_SRR_FLAGS_ACCEPT, 0, 0);
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
-		xmit_type = QLA_TGT_XMIT_STATUS;
-		resp = 1;
-		break;
-	case SRR_IU_DATA_IN:
-		if (!cmd->sg || !cmd->sg_cnt) {
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf063,
-			    "Unable to process SRR_IU_DATA_IN due to"
-			    " missing cmd->sg, state: %d\n", cmd->state);
-			dump_stack();
-			goto out_reject;
-		}
-		if (se_cmd->scsi_status != 0) {
-			ql_dbg(ql_dbg_tgt, vha, 0xe02a,
-			    "Rejecting SRR_IU_DATA_IN with non GOOD "
-			    "scsi_status\n");
-			goto out_reject;
-		}
-		cmd->bufflen = se_cmd->data_length;
-
-		if (qlt_has_data(cmd)) {
-			if (qlt_srr_adjust_data(cmd, offset, &xmit_type) != 0)
-				goto out_reject;
-			spin_lock_irqsave(&ha->hardware_lock, flags);
-			qlt_send_notify_ack(vha, ntfy,
-			    0, 0, 0, NOTIFY_ACK_SRR_FLAGS_ACCEPT, 0, 0);
-			spin_unlock_irqrestore(&ha->hardware_lock, flags);
-			resp = 1;
-		} else {
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf064,
-			       "qla_target(%d): SRR for in data for cmd without them (tag %lld, SCSI status %d), reject",
-			       vha->vp_idx, se_cmd->tag,
-			    cmd->se_cmd.scsi_status);
-			goto out_reject;
-		}
-		break;
-	case SRR_IU_DATA_OUT:
-		if (!cmd->sg || !cmd->sg_cnt) {
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf065,
-			    "Unable to process SRR_IU_DATA_OUT due to"
-			    " missing cmd->sg\n");
-			dump_stack();
-			goto out_reject;
-		}
-		if (se_cmd->scsi_status != 0) {
-			ql_dbg(ql_dbg_tgt, vha, 0xe02b,
-			    "Rejecting SRR_IU_DATA_OUT"
-			    " with non GOOD scsi_status\n");
-			goto out_reject;
-		}
-		cmd->bufflen = se_cmd->data_length;
-
-		if (qlt_has_data(cmd)) {
-			if (qlt_srr_adjust_data(cmd, offset, &xmit_type) != 0)
-				goto out_reject;
-			spin_lock_irqsave(&ha->hardware_lock, flags);
-			qlt_send_notify_ack(vha, ntfy,
-			    0, 0, 0, NOTIFY_ACK_SRR_FLAGS_ACCEPT, 0, 0);
-			spin_unlock_irqrestore(&ha->hardware_lock, flags);
-			if (xmit_type & QLA_TGT_XMIT_DATA) {
-				cmd->trc_flags |= TRC_SRR_XRDY;
-				qlt_rdy_to_xfer(cmd);
-			}
-		} else {
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf066,
-			    "qla_target(%d): SRR for out data for cmd without them (tag %lld, SCSI status %d), reject",
-			       vha->vp_idx, se_cmd->tag, cmd->se_cmd.scsi_status);
-			goto out_reject;
-		}
-		break;
-	default:
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf067,
-		    "qla_target(%d): Unknown srr_ui value %x",
-		    vha->vp_idx, srr_ui);
-		goto out_reject;
-	}
-
-	/* Transmit response in case of status and data-in cases */
-	if (resp) {
-		cmd->trc_flags |= TRC_SRR_RSP;
-		qlt_xmit_response(cmd, xmit_type, se_cmd->scsi_status);
-	}
-
-	return;
-
-out_reject:
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_notify_ack(vha, ntfy, 0, 0, 0,
-	    NOTIFY_ACK_SRR_FLAGS_REJECT,
-	    NOTIFY_ACK_SRR_REJECT_REASON_UNABLE_TO_PERFORM,
-	    NOTIFY_ACK_SRR_FLAGS_REJECT_EXPL_NO_EXPL);
-	if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
-		cmd->state = QLA_TGT_STATE_DATA_IN;
-		dump_stack();
-	} else {
-		cmd->trc_flags |= TRC_SRR_TERM;
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
-	}
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-}
-
-static void qlt_reject_free_srr_imm(struct scsi_qla_host *vha,
-	struct qla_tgt_srr_imm *imm, int ha_locked)
-{
-	struct qla_hw_data *ha = vha->hw;
-	unsigned long flags = 0;
-
-#ifndef __CHECKER__
-	if (!ha_locked)
-		spin_lock_irqsave(&ha->hardware_lock, flags);
-#endif
-
-	qlt_send_notify_ack(vha, (void *)&imm->imm_ntfy, 0, 0, 0,
-	    NOTIFY_ACK_SRR_FLAGS_REJECT,
-	    NOTIFY_ACK_SRR_REJECT_REASON_UNABLE_TO_PERFORM,
-	    NOTIFY_ACK_SRR_FLAGS_REJECT_EXPL_NO_EXPL);
-
-#ifndef __CHECKER__
-	if (!ha_locked)
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
-#endif
-
-	kfree(imm);
-}
-
-static void qlt_handle_srr_work(struct work_struct *work)
-{
-	struct qla_tgt *tgt = container_of(work, struct qla_tgt, srr_work);
-	struct scsi_qla_host *vha = tgt->vha;
-	struct qla_tgt_srr_ctio *sctio;
-	unsigned long flags;
-
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf029, "Entering SRR work (tgt %p)\n",
-	    tgt);
-
-restart:
-	spin_lock_irqsave(&tgt->srr_lock, flags);
-	list_for_each_entry(sctio, &tgt->srr_ctio_list, srr_list_entry) {
-		struct qla_tgt_srr_imm *imm, *i, *ti;
-		struct qla_tgt_cmd *cmd;
-		struct se_cmd *se_cmd;
-
-		imm = NULL;
-		list_for_each_entry_safe(i, ti, &tgt->srr_imm_list,
-						srr_list_entry) {
-			if (i->srr_id == sctio->srr_id) {
-				list_del(&i->srr_list_entry);
-				if (imm) {
-					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf068,
-					  "qla_target(%d): There must be "
-					  "only one IMM SRR per CTIO SRR "
-					  "(IMM SRR %p, id %d, CTIO %p\n",
-					  vha->vp_idx, i, i->srr_id, sctio);
-					qlt_reject_free_srr_imm(tgt->vha, i, 0);
-				} else
-					imm = i;
-			}
-		}
-
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02a,
-		    "IMM SRR %p, CTIO SRR %p (id %d)\n", imm, sctio,
-		    sctio->srr_id);
-
-		if (imm == NULL) {
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02b,
-			    "Not found matching IMM for SRR CTIO (id %d)\n",
-			    sctio->srr_id);
-			continue;
-		} else
-			list_del(&sctio->srr_list_entry);
-
-		spin_unlock_irqrestore(&tgt->srr_lock, flags);
-
-		cmd = sctio->cmd;
-		/*
-		 * Reset qla_tgt_cmd SRR values and SGL pointer+count to follow
-		 * tcm_qla2xxx_write_pending() and tcm_qla2xxx_queue_data_in()
-		 * logic..
-		 */
-		cmd->offset = 0;
-		if (cmd->free_sg) {
-			kfree(cmd->sg);
-			cmd->sg = NULL;
-			cmd->free_sg = 0;
-		}
-		se_cmd = &cmd->se_cmd;
-
-		cmd->sg_cnt = se_cmd->t_data_nents;
-		cmd->sg = se_cmd->t_data_sg;
-
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c,
-		       "SRR cmd %p (se_cmd %p, tag %lld, op %x), sg_cnt=%d, offset=%d",
-		       cmd, &cmd->se_cmd, se_cmd->tag, se_cmd->t_task_cdb ?
-		       se_cmd->t_task_cdb[0] : 0, cmd->sg_cnt, cmd->offset);
-
-		qlt_handle_srr(vha, sctio, imm);
-
-		kfree(imm);
-		kfree(sctio);
-		goto restart;
-	}
-	spin_unlock_irqrestore(&tgt->srr_lock, flags);
-}
-
-/* ha->hardware_lock supposed to be held on entry */
-static void qlt_prepare_srr_imm(struct scsi_qla_host *vha,
-	struct imm_ntfy_from_isp *iocb)
-{
-	struct qla_tgt_srr_imm *imm;
-	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
-	struct qla_tgt_srr_ctio *sctio;
-
-	tgt->imm_srr_id++;
-
-	ql_log(ql_log_warn, vha, 0xf02d, "qla_target(%d): SRR received\n",
-	    vha->vp_idx);
-
-	imm = kzalloc(sizeof(*imm), GFP_ATOMIC);
-	if (imm != NULL) {
-		memcpy(&imm->imm_ntfy, iocb, sizeof(imm->imm_ntfy));
-
-		/* IRQ is already OFF */
-		spin_lock(&tgt->srr_lock);
-		imm->srr_id = tgt->imm_srr_id;
-		list_add_tail(&imm->srr_list_entry,
-		    &tgt->srr_imm_list);
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02e,
-		    "IMM NTFY SRR %p added (id %d, ui %x)\n",
-		    imm, imm->srr_id, iocb->u.isp24.srr_ui);
-		if (tgt->imm_srr_id == tgt->ctio_srr_id) {
-			int found = 0;
-			list_for_each_entry(sctio, &tgt->srr_ctio_list,
-			    srr_list_entry) {
-				if (sctio->srr_id == imm->srr_id) {
-					found = 1;
-					break;
-				}
-			}
-			if (found) {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02f, "%s",
-				    "Scheduling srr work\n");
-				schedule_work(&tgt->srr_work);
-			} else {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf030,
-				    "qla_target(%d): imm_srr_id "
-				    "== ctio_srr_id (%d), but there is no "
-				    "corresponding SRR CTIO, deleting IMM "
-				    "SRR %p\n", vha->vp_idx, tgt->ctio_srr_id,
-				    imm);
-				list_del(&imm->srr_list_entry);
-
-				kfree(imm);
-
-				spin_unlock(&tgt->srr_lock);
-				goto out_reject;
-			}
-		}
-		spin_unlock(&tgt->srr_lock);
-	} else {
-		struct qla_tgt_srr_ctio *ts;
-
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf069,
-		    "qla_target(%d): Unable to allocate SRR IMM "
-		    "entry, SRR request will be rejected\n", vha->vp_idx);
-
-		/* IRQ is already OFF */
-		spin_lock(&tgt->srr_lock);
-		list_for_each_entry_safe(sctio, ts, &tgt->srr_ctio_list,
-		    srr_list_entry) {
-			if (sctio->srr_id == tgt->imm_srr_id) {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf031,
-				    "CTIO SRR %p deleted (id %d)\n",
-				    sctio, sctio->srr_id);
-				list_del(&sctio->srr_list_entry);
-				qlt_send_term_exchange(vha, sctio->cmd,
-				    &sctio->cmd->atio, 1, 0);
-				kfree(sctio);
-			}
-		}
-		spin_unlock(&tgt->srr_lock);
-		goto out_reject;
-	}
-
-	return;
-
-out_reject:
-	qlt_send_notify_ack(vha, iocb, 0, 0, 0,
-	    NOTIFY_ACK_SRR_FLAGS_REJECT,
-	    NOTIFY_ACK_SRR_REJECT_REASON_UNABLE_TO_PERFORM,
-	    NOTIFY_ACK_SRR_FLAGS_REJECT_EXPL_NO_EXPL);
-}
-
 /*
  * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire
  */
@@ -5065,12 +4434,6 @@ static void qlt_handle_imm_notify(struct scsi_qla_host *vha,
 		if (qlt_24xx_handle_els(vha, iocb) == 0)
 			send_notify_ack = 0;
 		break;
-
-	case IMM_NTFY_SRR:
-		qlt_prepare_srr_imm(vha, iocb);
-		send_notify_ack = 0;
-		break;
-
 	default:
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf06d,
 		    "qla_target(%d): Received unknown immediate "
@@ -6021,10 +5384,6 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
 	spin_lock_init(&tgt->sess_work_lock);
 	INIT_WORK(&tgt->sess_work, qlt_sess_work_fn);
 	INIT_LIST_HEAD(&tgt->sess_works_list);
-	spin_lock_init(&tgt->srr_lock);
-	INIT_LIST_HEAD(&tgt->srr_ctio_list);
-	INIT_LIST_HEAD(&tgt->srr_imm_list);
-	INIT_WORK(&tgt->srr_work, qlt_handle_srr_work);
 	atomic_set(&tgt->tgt_global_resets_count, 0);
 
 	base_vha->vha_tgt.qla_tgt = tgt;
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 5d00529b68c4..f72bd0755a59 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -890,16 +890,7 @@ struct qla_tgt {
 	int notify_ack_expected;
 	int abts_resp_expected;
 	int modify_lun_expected;
-
-	int ctio_srr_id;
-	int imm_srr_id;
-	spinlock_t srr_lock;
-	struct list_head srr_ctio_list;
-	struct list_head srr_imm_list;
-	struct work_struct srr_work;
-
 	atomic_t tgt_global_resets_count;
-
 	struct list_head tgt_list_entry;
 };
 
@@ -1087,18 +1078,6 @@ struct qla_tgt_prm {
 	uint16_t tot_dsds;
 };
 
-struct qla_tgt_srr_imm {
-	struct list_head srr_list_entry;
-	int srr_id;
-	struct imm_ntfy_from_isp imm_ntfy;
-};
-
-struct qla_tgt_srr_ctio {
-	struct list_head srr_list_entry;
-	int srr_id;
-	struct qla_tgt_cmd *cmd;
-};
-
 /* Check for Switch reserved address */
 #define IS_SW_RESV_ADDR(_s_id) \
 	((_s_id.b.domain == 0xff) && (_s_id.b.area == 0xfc))
-- 
GitLab


From 5e4deaf6a47f397af68d3297bdc2913ae890bd4a Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:27:57 -0800
Subject: [PATCH 064/898] qla2xxx: Fix wrong argument in sp done callback

Callback for sp->done expects scsi_qla_host is passed in as argument,
Instead qla_hw_data is passed in.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_isr.c | 8 ++++----
 drivers/scsi/qla2xxx/qla_mr.c  | 6 +++---
 drivers/scsi/qla2xxx/qla_os.c  | 2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index dc88a09f9043..802b50cc89d0 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1212,7 +1212,7 @@ qla2x00_process_completed_request(struct scsi_qla_host *vha,
 		req->outstanding_cmds[index] = NULL;
 
 		/* Save ISP completion status */
-		sp->done(ha, sp, DID_OK << 16);
+		sp->done(vha, sp, DID_OK << 16);
 	} else {
 		ql_log(ql_log_warn, vha, 0x3016, "Invalid SCSI SRB.\n");
 
@@ -2405,7 +2405,7 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 		    resid_len, fw_resid_len, sp, cp);
 
 	if (rsp->status_srb == NULL)
-		sp->done(ha, sp, res);
+		sp->done(vha, sp, res);
 }
 
 /**
@@ -2462,7 +2462,7 @@ qla2x00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt)
 	/* Place command on done queue. */
 	if (sense_len == 0) {
 		rsp->status_srb = NULL;
-		sp->done(ha, sp, cp->result);
+		sp->done(vha, sp, cp->result);
 	}
 }
 
@@ -2498,7 +2498,7 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt)
 
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (sp) {
-		sp->done(ha, sp, res);
+		sp->done(vha, sp, res);
 		return;
 	}
 fatal:
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index 02f1de18bc2b..d38bc6452abd 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -2537,7 +2537,7 @@ qlafx00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 		    par_sense_len, rsp_info_len);
 
 	if (rsp->status_srb == NULL)
-		sp->done(ha, sp, res);
+		sp->done(vha, sp, res);
 }
 
 /**
@@ -2614,7 +2614,7 @@ qlafx00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt)
 	/* Place command on done queue. */
 	if (sense_len == 0) {
 		rsp->status_srb = NULL;
-		sp->done(ha, sp, cp->result);
+		sp->done(vha, sp, cp->result);
 	}
 }
 
@@ -2695,7 +2695,7 @@ qlafx00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp,
 
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (sp) {
-		sp->done(ha, sp, res);
+		sp->done(vha, sp, res);
 		return;
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 0a000ecf0881..62ca1ddb0cc7 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1203,7 +1203,7 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 	}
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	sp->done(ha, sp, 0);
+	sp->done(vha, sp, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	/* Did the command return during mailbox execution? */
-- 
GitLab


From 37cacc0a13012eee9fa0b07563eb149ec9244b1e Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:27:58 -0800
Subject: [PATCH 065/898] qla2xxx: Use d_id instead of s_id for more clarity

Updated code with d_id from s_id for better readability and
clarity.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[ bvanassche: fixed spelling of patch description ]
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_dfs.c     |  9 +++----
 drivers/scsi/qla2xxx/qla_target.c  | 24 ++++++++---------
 drivers/scsi/qla2xxx/qla_target.h  |  2 +-
 drivers/scsi/qla2xxx/tcm_qla2xxx.c | 41 ++++++++++++++++--------------
 4 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index 34272fde8a5b..98550c9b6161 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -26,12 +26,11 @@ qla2x00_dfs_tgt_sess_show(struct seq_file *s, void *unused)
 		seq_printf(s, "Port ID   Port Name                Handle\n");
 
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-		list_for_each_entry(sess, &tgt->sess_list, sess_list_entry) {
+		list_for_each_entry(sess, &tgt->sess_list, sess_list_entry)
 			seq_printf(s, "%02x:%02x:%02x  %8phC  %d\n",
-					   sess->s_id.b.domain,sess->s_id.b.area,
-					   sess->s_id.b.al_pa,	sess->port_name,
-					   sess->loop_id);
-		}
+			    sess->d_id.b.domain, sess->d_id.b.area,
+			    sess->d_id.b.al_pa, sess->port_name,
+			    sess->loop_id);
 		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 119a445a82f6..671875a50951 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -530,7 +530,7 @@ static void qlt_free_session_done(struct work_struct *work)
 		"%s: se_sess %p / sess %p from port %8phC loop_id %#04x"
 		" s_id %02x:%02x:%02x logout %d keep %d els_logo %d\n",
 		__func__, sess->se_sess, sess, sess->port_name, sess->loop_id,
-		sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+		sess->d_id.b.domain, sess->d_id.b.area, sess->d_id.b.al_pa,
 		sess->logout_on_delete, sess->keep_nport_handle,
 		sess->send_els_logo);
 
@@ -538,7 +538,7 @@ static void qlt_free_session_done(struct work_struct *work)
 
 	if (sess->send_els_logo) {
 		qlt_port_logo_t logo;
-		logo.id = sess->s_id;
+		logo.id = sess->d_id;
 		logo.cmd_count = 0;
 		qlt_send_first_logo(vha, &logo);
 	}
@@ -548,7 +548,7 @@ static void qlt_free_session_done(struct work_struct *work)
 
 		memset(&fcport, 0, sizeof(fcport));
 		fcport.loop_id = sess->loop_id;
-		fcport.d_id = sess->s_id;
+		fcport.d_id = sess->d_id;
 		memcpy(fcport.port_name, sess->port_name, WWN_SIZE);
 		fcport.vha = vha;
 		fcport.tgt_session = sess;
@@ -757,7 +757,7 @@ static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess,
 	    "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)"
 	    " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n",
 	    sess->vha->vp_idx, sess->port_name, sess->loop_id,
-	    sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+	    sess->d_id.b.domain, sess->d_id.b.area, sess->d_id.b.al_pa,
 	    dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete,
 	    sess->generation);
 
@@ -892,8 +892,8 @@ static struct qla_tgt_sess *qlt_create_sess(
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf005,
 			    "Double sess %p found (s_id %x:%x:%x, "
 			    "loop_id %d), updating to d_id %x:%x:%x, "
-			    "loop_id %d", sess, sess->s_id.b.domain,
-			    sess->s_id.b.al_pa, sess->s_id.b.area,
+			    "loop_id %d", sess, sess->d_id.b.domain,
+			    sess->d_id.b.al_pa, sess->d_id.b.area,
 			    sess->loop_id, fcport->d_id.b.domain,
 			    fcport->d_id.b.al_pa, fcport->d_id.b.area,
 			    fcport->loop_id);
@@ -943,7 +943,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 	}
 	sess->tgt = vha->vha_tgt.qla_tgt;
 	sess->vha = vha;
-	sess->s_id = fcport->d_id;
+	sess->d_id = fcport->d_id;
 	sess->loop_id = fcport->loop_id;
 	sess->local = local;
 	kref_init(&sess->sess_kref);
@@ -974,8 +974,8 @@ static struct qla_tgt_sess *qlt_create_sess(
 	    "qla_target(%d): %ssession for wwn %8phC (loop_id %d, "
 	    "s_id %x:%x:%x, confirmed completion %ssupported) added\n",
 	    vha->vp_idx, local ?  "local " : "", fcport->port_name,
-	    fcport->loop_id, sess->s_id.b.domain, sess->s_id.b.area,
-	    sess->s_id.b.al_pa, sess->conf_compl_supported ?  "" : "not ");
+	    fcport->loop_id, sess->d_id.b.domain, sess->d_id.b.area,
+	    sess->d_id.b.al_pa, sess->conf_compl_supported ?  "" : "not ");
 
 	/*
 	 * Determine if this fc_port->port_name is allowed to access
@@ -4055,7 +4055,7 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
 		}
 
 		/* find other sess with nport_id collision */
-		if (port_id.b24 == other_sess->s_id.b24) {
+		if (port_id.b24 == other_sess->d_id.b24) {
 			if (loop_id != other_sess->loop_id) {
 				ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c,
 				    "Invalidating sess %p loop_id %d wwn %llx.\n",
@@ -4216,7 +4216,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		  *    PLOGI and situation will correct itself.
 		  */
 		sess->keep_nport_handle = ((sess->loop_id == loop_id) &&
-					   (sess->s_id.b24 == port_id.b24));
+					   (sess->d_id.b24 == port_id.b24));
 		qlt_schedule_sess_for_deletion(sess, true);
 		break;
 
@@ -4264,7 +4264,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 
 			sess->local = 0;
 			sess->loop_id = loop_id;
-			sess->s_id = port_id;
+			sess->d_id = port_id;
 
 			if (wd3_lo & BIT_7)
 				sess->conf_compl_supported = 1;
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index f72bd0755a59..07ccf81f6d22 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -928,7 +928,7 @@ typedef struct {
  */
 struct qla_tgt_sess {
 	uint16_t loop_id;
-	port_id_t s_id;
+	port_id_t d_id;
 
 	unsigned int conf_compl_supported:1;
 	unsigned int deleted:2;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index af4a198e5537..c96de1cfbd85 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1388,9 +1388,9 @@ static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *lport,
 	struct se_session *se_sess = sess->se_sess;
 	unsigned char be_sid[3];
 
-	be_sid[0] = sess->s_id.b.domain;
-	be_sid[1] = sess->s_id.b.area;
-	be_sid[2] = sess->s_id.b.al_pa;
+	be_sid[0] = sess->d_id.b.domain;
+	be_sid[1] = sess->d_id.b.area;
+	be_sid[2] = sess->d_id.b.al_pa;
 
 	tcm_qla2xxx_set_sess_by_s_id(lport, NULL, nacl, se_sess,
 				sess, be_sid);
@@ -1442,9 +1442,9 @@ static int tcm_qla2xxx_session_cb(struct se_portal_group *se_tpg,
 	unsigned long flags;
 	unsigned char be_sid[3];
 
-	be_sid[0] = qlat_sess->s_id.b.domain;
-	be_sid[1] = qlat_sess->s_id.b.area;
-	be_sid[2] = qlat_sess->s_id.b.al_pa;
+	be_sid[0] = qlat_sess->d_id.b.domain;
+	be_sid[1] = qlat_sess->d_id.b.area;
+	be_sid[2] = qlat_sess->d_id.b.al_pa;
 
 	/*
 	 * And now setup se_nacl and session pointers into HW lport internal
@@ -1524,11 +1524,11 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id,
 	u32 key;
 
 
-	if (sess->loop_id != loop_id || sess->s_id.b24 != s_id.b24)
+	if (sess->loop_id != loop_id || sess->d_id.b24 != s_id.b24)
 		pr_info("Updating session %p from port %8phC loop_id %d -> %d s_id %x:%x:%x -> %x:%x:%x\n",
 		    sess, sess->port_name,
-		    sess->loop_id, loop_id, sess->s_id.b.domain,
-		    sess->s_id.b.area, sess->s_id.b.al_pa, s_id.b.domain,
+		    sess->loop_id, loop_id, sess->d_id.b.domain,
+		    sess->d_id.b.area, sess->d_id.b.al_pa, s_id.b.domain,
 		    s_id.b.area, s_id.b.al_pa);
 
 	if (sess->loop_id != loop_id) {
@@ -1548,18 +1548,20 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id,
 		sess->loop_id = loop_id;
 	}
 
-	if (sess->s_id.b24 != s_id.b24) {
-		key = (((u32) sess->s_id.b.domain << 16) |
-		       ((u32) sess->s_id.b.area   <<  8) |
-		       ((u32) sess->s_id.b.al_pa));
+	if (sess->d_id.b24 != s_id.b24) {
+		key = (((u32) sess->d_id.b.domain << 16) |
+		       ((u32) sess->d_id.b.area   <<  8) |
+		       ((u32) sess->d_id.b.al_pa));
 
 		if (btree_lookup32(&lport->lport_fcport_map, key))
-			WARN(btree_remove32(&lport->lport_fcport_map, key) != se_nacl,
-			     "Found wrong se_nacl when updating s_id %x:%x:%x\n",
-			     sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa);
+			WARN(btree_remove32(&lport->lport_fcport_map, key) !=
+			    se_nacl, "Found wrong se_nacl when updating s_id %x:%x:%x\n",
+			    sess->d_id.b.domain, sess->d_id.b.area,
+			    sess->d_id.b.al_pa);
 		else
 			WARN(1, "No lport_fcport_map entry for s_id %x:%x:%x\n",
-			     sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa);
+			     sess->d_id.b.domain, sess->d_id.b.area,
+			     sess->d_id.b.al_pa);
 
 		key = (((u32) s_id.b.domain << 16) |
 		       ((u32) s_id.b.area   <<  8) |
@@ -1570,10 +1572,11 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id,
 			     s_id.b.domain, s_id.b.area, s_id.b.al_pa);
 			btree_update32(&lport->lport_fcport_map, key, se_nacl);
 		} else {
-			btree_insert32(&lport->lport_fcport_map, key, se_nacl, GFP_ATOMIC);
+			btree_insert32(&lport->lport_fcport_map, key, se_nacl,
+			    GFP_ATOMIC);
 		}
 
-		sess->s_id = s_id;
+		sess->d_id = s_id;
 		nacl->nport_id = key;
 	}
 
-- 
GitLab


From 5d964837c6a743193c63c8912f98834c7457ba5c Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:27:59 -0800
Subject: [PATCH 066/898] qla2xxx: Track I-T nexus as single fc_port struct

Current code merges qla_tgt_sess and fc_port structure
into single fc_port structure representing same I-T nexus.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
[ bvanassche: fixed spelling of patch description ]
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_def.h     | 112 +++++++++-
 drivers/scsi/qla2xxx/qla_dfs.c     |   4 +-
 drivers/scsi/qla2xxx/qla_init.c    |  12 --
 drivers/scsi/qla2xxx/qla_iocb.c    |   2 +-
 drivers/scsi/qla2xxx/qla_target.c  | 326 ++++++++++-------------------
 drivers/scsi/qla2xxx/qla_target.h  | 150 ++-----------
 drivers/scsi/qla2xxx/tcm_qla2xxx.c | 130 +++++++-----
 drivers/scsi/qla2xxx/tcm_qla2xxx.h |   4 +-
 8 files changed, 310 insertions(+), 430 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 4aae861a6713..1bdcc7e010ff 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1976,6 +1976,84 @@ struct mbx_entry {
 	uint8_t port_name[WWN_SIZE];
 };
 
+#ifndef IMMED_NOTIFY_TYPE
+#define IMMED_NOTIFY_TYPE 0x0D		/* Immediate notify entry. */
+/*
+ * ISP queue -	immediate notify entry structure definition.
+ *		This is sent by the ISP to the Target driver.
+ *		This IOCB would have report of events sent by the
+ *		initiator, that needs to be handled by the target
+ *		driver immediately.
+ */
+struct imm_ntfy_from_isp {
+	uint8_t	 entry_type;		    /* Entry type. */
+	uint8_t	 entry_count;		    /* Entry count. */
+	uint8_t	 sys_define;		    /* System defined. */
+	uint8_t	 entry_status;		    /* Entry Status. */
+	union {
+		struct {
+			uint32_t sys_define_2; /* System defined. */
+			target_id_t target;
+			uint16_t lun;
+			uint8_t  target_id;
+			uint8_t  reserved_1;
+			uint16_t status_modifier;
+			uint16_t status;
+			uint16_t task_flags;
+			uint16_t seq_id;
+			uint16_t srr_rx_id;
+			uint32_t srr_rel_offs;
+			uint16_t srr_ui;
+#define SRR_IU_DATA_IN	0x1
+#define SRR_IU_DATA_OUT	0x5
+#define SRR_IU_STATUS	0x7
+			uint16_t srr_ox_id;
+			uint8_t reserved_2[28];
+		} isp2x;
+		struct {
+			uint32_t reserved;
+			uint16_t nport_handle;
+			uint16_t reserved_2;
+			uint16_t flags;
+#define NOTIFY24XX_FLAGS_GLOBAL_TPRLO   BIT_1
+#define NOTIFY24XX_FLAGS_PUREX_IOCB     BIT_0
+			uint16_t srr_rx_id;
+			uint16_t status;
+			uint8_t  status_subcode;
+			uint8_t  fw_handle;
+			uint32_t exchange_address;
+			uint32_t srr_rel_offs;
+			uint16_t srr_ui;
+			uint16_t srr_ox_id;
+			union {
+				struct {
+					uint8_t node_name[8];
+				} plogi; /* PLOGI/ADISC/PDISC */
+				struct {
+					/* PRLI word 3 bit 0-15 */
+					uint16_t wd3_lo;
+					uint8_t resv0[6];
+				} prli;
+				struct {
+					uint8_t port_id[3];
+					uint8_t resv1;
+					uint16_t nport_handle;
+					uint16_t resv2;
+				} req_els;
+			} u;
+			uint8_t port_name[8];
+			uint8_t resv3[3];
+			uint8_t  vp_index;
+			uint32_t reserved_5;
+			uint8_t  port_id[3];
+			uint8_t  reserved_6;
+		} isp24;
+	} u;
+	uint16_t reserved_7;
+	uint16_t ox_id;
+} __packed;
+#endif
+
 /*
  * ISP request and response queue entry sizes
  */
@@ -2026,7 +2104,7 @@ typedef struct {
 /*
  * Fibre channel port type.
  */
- typedef enum {
+typedef enum {
 	FCT_UNKNOWN,
 	FCT_RSCN,
 	FCT_SWITCH,
@@ -2035,6 +2113,19 @@ typedef struct {
 	FCT_TARGET
 } fc_port_type_t;
 
+enum qlt_plogi_link_t {
+	QLT_PLOGI_LINK_SAME_WWN,
+	QLT_PLOGI_LINK_CONFLICT,
+	QLT_PLOGI_LINK_MAX
+};
+
+struct qlt_plogi_ack_t {
+	struct list_head	list;
+	struct imm_ntfy_from_isp iocb;
+	port_id_t	id;
+	int		ref_count;
+};
+
 /*
  * Fibre channel port structure.
  */
@@ -2048,6 +2139,25 @@ typedef struct fc_port {
 	uint16_t loop_id;
 	uint16_t old_loop_id;
 
+	unsigned int conf_compl_supported:1;
+	unsigned int deleted:2;
+	unsigned int local:1;
+	unsigned int logout_on_delete:1;
+	unsigned int keep_nport_handle:1;
+	unsigned int send_els_logo:1;
+
+	unsigned char logout_completed;
+	int generation;
+
+	struct se_session *se_sess;
+	struct kref sess_kref;
+	struct qla_tgt *tgt;
+	unsigned long expires;
+	struct list_head del_list_entry;
+	struct work_struct free_work;
+
+	struct qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
+
 	uint16_t tgt_id;
 	uint16_t old_tgt_id;
 
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index 98550c9b6161..b48cce696bac 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -18,7 +18,7 @@ qla2x00_dfs_tgt_sess_show(struct seq_file *s, void *unused)
 	scsi_qla_host_t *vha = s->private;
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
-	struct qla_tgt_sess *sess = NULL;
+	struct fc_port *sess = NULL;
 	struct qla_tgt *tgt= vha->vha_tgt.qla_tgt;
 
 	seq_printf(s, "%s\n",vha->host_str);
@@ -26,7 +26,7 @@ qla2x00_dfs_tgt_sess_show(struct seq_file *s, void *unused)
 		seq_printf(s, "Port ID   Port Name                Handle\n");
 
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-		list_for_each_entry(sess, &tgt->sess_list, sess_list_entry)
+		list_for_each_entry(sess, &vha->vp_fcports, list)
 			seq_printf(s, "%02x:%02x:%02x  %8phC  %d\n",
 			    sess->d_id.b.domain, sess->d_id.b.area,
 			    sess->d_id.b.al_pa, sess->port_name,
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 7b6317c8c2e9..5978b79d4a61 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -3352,12 +3352,6 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 		    "Unable to allocate fc remote port.\n");
 		return;
 	}
-	/*
-	 * Create target mode FC NEXUS in qla_target.c if target mode is
-	 * enabled..
-	 */
-
-	qlt_fc_port_added(vha, fcport);
 
 	spin_lock_irqsave(fcport->vha->host->host_lock, flags);
 	*((fc_port_t **)rport->dd_data) = fcport;
@@ -3407,12 +3401,6 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 reg_port:
 	if (qla_ini_mode_enabled(vha))
 		qla2x00_reg_remote_port(vha, fcport);
-	else {
-		/*
-		 * Create target mode FC NEXUS in qla_target.c
-		 */
-		qlt_fc_port_added(vha, fcport);
-	}
 }
 
 /*
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 58e49a3e1de8..834e22197842 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2248,7 +2248,7 @@ qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	logio->control_flags =
 	    cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO);
 	if (!sp->fcport->tgt_session ||
-	    !sp->fcport->tgt_session->keep_nport_handle)
+	    !sp->fcport->keep_nport_handle)
 		logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 671875a50951..40b61a327786 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -102,7 +102,7 @@ enum fcp_resp_rsp_codes {
 static void qlt_24xx_atio_pkt(struct scsi_qla_host *ha,
 	struct atio_from_isp *pkt, uint8_t);
 static void qlt_response_pkt(struct scsi_qla_host *ha, response_t *pkt);
-static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
+static int qlt_issue_task_mgmt(struct fc_port *sess, u64 lun,
 	int fn, void *iocb, int flags);
 static void qlt_send_term_exchange(struct scsi_qla_host *ha, struct qla_tgt_cmd
 	*cmd, struct atio_from_isp *atio, int ha_locked, int ul_abort);
@@ -138,21 +138,6 @@ void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest)
 	wmb();
 }
 
-/* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) */
-static struct qla_tgt_sess *qlt_find_sess_by_port_name(
-	struct qla_tgt *tgt,
-	const uint8_t *port_name)
-{
-	struct qla_tgt_sess *sess;
-
-	list_for_each_entry(sess, &tgt->sess_list, sess_list_entry) {
-		if (!memcmp(sess->port_name, port_name, WWN_SIZE))
-			return sess;
-	}
-
-	return NULL;
-}
-
 /* Might release hw lock, then reaquire!! */
 static inline int qlt_issue_marker(struct scsi_qla_host *vha, int vha_locked)
 {
@@ -399,16 +384,16 @@ void qlt_response_pkt_all_vps(struct scsi_qla_host *vha, response_t *pkt)
  * guarantees that ref_count is not modified concurrently.
  * Upon successful return content of iocb is undefined
  */
-static qlt_plogi_ack_t *
+static struct qlt_plogi_ack_t *
 qlt_plogi_ack_find_add(struct scsi_qla_host *vha, port_id_t *id,
 		       struct imm_ntfy_from_isp *iocb)
 {
-	qlt_plogi_ack_t *pla;
+	struct qlt_plogi_ack_t *pla;
 
 	list_for_each_entry(pla, &vha->plogi_ack_list, list) {
 		if (pla->id.b24 == id->b24) {
 			qlt_send_term_imm_notif(vha, &pla->iocb, 1);
-			pla->iocb = *iocb;
+			memcpy(&pla->iocb, iocb, sizeof(pla->iocb));
 			return pla;
 		}
 	}
@@ -421,15 +406,17 @@ qlt_plogi_ack_find_add(struct scsi_qla_host *vha, port_id_t *id,
 		return NULL;
 	}
 
-	pla->iocb = *iocb;
+	memcpy(&pla->iocb, iocb, sizeof(pla->iocb));
 	pla->id = *id;
 	list_add_tail(&pla->list, &vha->plogi_ack_list);
 
 	return pla;
 }
 
-static void qlt_plogi_ack_unref(struct scsi_qla_host *vha, qlt_plogi_ack_t *pla)
+static void qlt_plogi_ack_unref(struct scsi_qla_host *vha,
+    struct qlt_plogi_ack_t *pla)
 {
+	struct imm_ntfy_from_isp *iocb = &pla->iocb;
 	BUG_ON(!pla->ref_count);
 	pla->ref_count--;
 
@@ -438,21 +425,22 @@ static void qlt_plogi_ack_unref(struct scsi_qla_host *vha, qlt_plogi_ack_t *pla)
 
 	ql_dbg(ql_dbg_async, vha, 0x5089,
 	    "Sending PLOGI ACK to wwn %8phC s_id %02x:%02x:%02x loop_id %#04x"
-	    " exch %#x ox_id %#x\n", pla->iocb.u.isp24.port_name,
-	    pla->iocb.u.isp24.port_id[2], pla->iocb.u.isp24.port_id[1],
-	    pla->iocb.u.isp24.port_id[0],
-	    le16_to_cpu(pla->iocb.u.isp24.nport_handle),
-	    pla->iocb.u.isp24.exchange_address, pla->iocb.ox_id);
-	qlt_send_notify_ack(vha, &pla->iocb, 0, 0, 0, 0, 0, 0);
+	    " exch %#x ox_id %#x\n", iocb->u.isp24.port_name,
+	    iocb->u.isp24.port_id[2], iocb->u.isp24.port_id[1],
+	    iocb->u.isp24.port_id[0],
+	    le16_to_cpu(iocb->u.isp24.nport_handle),
+	    iocb->u.isp24.exchange_address, iocb->ox_id);
+	qlt_send_notify_ack(vha, iocb, 0, 0, 0, 0, 0, 0);
 
 	list_del(&pla->list);
 	kmem_cache_free(qla_tgt_plogi_cachep, pla);
 }
 
 static void
-qlt_plogi_ack_link(struct scsi_qla_host *vha, qlt_plogi_ack_t *pla,
-    struct qla_tgt_sess *sess, qlt_plogi_link_t link)
+qlt_plogi_ack_link(struct scsi_qla_host *vha, struct qlt_plogi_ack_t *pla,
+    struct fc_port *sess, enum qlt_plogi_link_t link)
 {
+	struct imm_ntfy_from_isp *iocb = &pla->iocb;
 	/* Inc ref_count first because link might already be pointing at pla */
 	pla->ref_count++;
 
@@ -462,8 +450,8 @@ qlt_plogi_ack_link(struct scsi_qla_host *vha, qlt_plogi_ack_t *pla,
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf097,
 	    "Linking sess %p [%d] wwn %8phC with PLOGI ACK to wwn %8phC"
 	    " s_id %02x:%02x:%02x, ref=%d\n", sess, link, sess->port_name,
-	    pla->iocb.u.isp24.port_name, pla->iocb.u.isp24.port_id[2],
-	    pla->iocb.u.isp24.port_id[1], pla->iocb.u.isp24.port_id[0],
+	    iocb->u.isp24.port_name, iocb->u.isp24.port_id[2],
+	    iocb->u.isp24.port_id[1], iocb->u.isp24.port_id[0],
 	    pla->ref_count);
 
 	sess->plogi_link[link] = pla;
@@ -517,7 +505,7 @@ qlt_send_first_logo(struct scsi_qla_host *vha, qlt_port_logo_t *logo)
 
 static void qlt_free_session_done(struct work_struct *work)
 {
-	struct qla_tgt_sess *sess = container_of(work, struct qla_tgt_sess,
+	struct fc_port *sess = container_of(work, struct fc_port,
 	    free_work);
 	struct qla_tgt *tgt = sess->tgt;
 	struct scsi_qla_host *vha = sess->vha;
@@ -551,7 +539,6 @@ static void qlt_free_session_done(struct work_struct *work)
 		fcport.d_id = sess->d_id;
 		memcpy(fcport.port_name, sess->port_name, WWN_SIZE);
 		fcport.vha = vha;
-		fcport.tgt_session = sess;
 
 		rc = qla2x00_post_async_logout_work(vha, &fcport, NULL);
 		if (rc != QLA_SUCCESS)
@@ -587,22 +574,22 @@ static void qlt_free_session_done(struct work_struct *work)
 	}
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-
 	{
-		qlt_plogi_ack_t *own =
+		struct qlt_plogi_ack_t *own =
 		    sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN];
-		qlt_plogi_ack_t *con =
+		struct qlt_plogi_ack_t *con =
 		    sess->plogi_link[QLT_PLOGI_LINK_CONFLICT];
+		struct imm_ntfy_from_isp *iocb;
 
 		if (con) {
+			iocb = &con->iocb;
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf099,
-			    "se_sess %p / sess %p port %8phC is gone,"
-			    " %s (ref=%d), releasing PLOGI for %8phC (ref=%d)\n",
-			    sess->se_sess, sess, sess->port_name,
-			    own ? "releasing own PLOGI" :
-			    "no own PLOGI pending",
-			    own ? own->ref_count : -1,
-			    con->iocb.u.isp24.port_name, con->ref_count);
+				 "se_sess %p / sess %p port %8phC is gone,"
+				 " %s (ref=%d), releasing PLOGI for %8phC (ref=%d)\n",
+				 sess->se_sess, sess, sess->port_name,
+				 own ? "releasing own PLOGI" : "no own PLOGI pending",
+				 own ? own->ref_count : -1,
+				 iocb->u.isp24.port_name, con->ref_count);
 			qlt_plogi_ack_unref(vha, con);
 		} else {
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf09a,
@@ -616,15 +603,15 @@ static void qlt_free_session_done(struct work_struct *work)
 		if (own)
 			qlt_plogi_ack_unref(vha, own);
 	}
-
-	list_del(&sess->sess_list_entry);
-
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+	sess->se_sess = NULL;
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
 	    "Unregistration of sess %p finished\n", sess);
 
-	kfree(sess);
 	/*
 	 * We need to protect against race, when tgt is freed before or
 	 * inside wake_up()
@@ -635,37 +622,30 @@ static void qlt_free_session_done(struct work_struct *work)
 }
 
 /* ha->tgt.sess_lock supposed to be held on entry */
-static void qlt_release_session(struct kref *kref)
+void qlt_unreg_sess(struct fc_port *sess)
 {
-	struct qla_tgt_sess *sess =
-		container_of(kref, struct qla_tgt_sess, sess_kref);
 	struct scsi_qla_host *vha = sess->vha;
 
+	ql_dbg(ql_dbg_disc, sess->vha, 0xffff,
+	    "%s sess %p for deletion %8phC\n",
+	    __func__, sess, sess->port_name);
+
 	if (sess->se_sess)
 		vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
-	if (!list_empty(&sess->del_list_entry))
-		list_del_init(&sess->del_list_entry);
+	qla2x00_mark_device_lost(vha, sess, 1, 1);
+
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 
 	INIT_WORK(&sess->free_work, qlt_free_session_done);
 	schedule_work(&sess->free_work);
 }
-
-void qlt_put_sess(struct qla_tgt_sess *sess)
-{
-	if (!sess)
-		return;
-
-	assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
-	kref_put(&sess->sess_kref, qlt_release_session);
-}
-EXPORT_SYMBOL(qlt_put_sess);
+EXPORT_SYMBOL(qlt_unreg_sess);
 
 static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess = NULL;
+	struct fc_port *sess = NULL;
 	uint16_t loop_id;
 	int res = 0;
 	struct imm_ntfy_from_isp *n = (struct imm_ntfy_from_isp *)iocb;
@@ -678,31 +658,6 @@ static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd)
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 		qlt_clear_tgt_db(vha->vha_tgt.qla_tgt);
 		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-#if 0 /* FIXME: do we need to choose a session here? */
-		if (!list_empty(&ha->tgt.qla_tgt->sess_list)) {
-			sess = list_entry(ha->tgt.qla_tgt->sess_list.next,
-			    typeof(*sess), sess_list_entry);
-			switch (mcmd) {
-			case QLA_TGT_NEXUS_LOSS_SESS:
-				mcmd = QLA_TGT_NEXUS_LOSS;
-				break;
-			case QLA_TGT_ABORT_ALL_SESS:
-				mcmd = QLA_TGT_ABORT_ALL;
-				break;
-			case QLA_TGT_NEXUS_LOSS:
-			case QLA_TGT_ABORT_ALL:
-				break;
-			default:
-				ql_dbg(ql_dbg_tgt, vha, 0xe046,
-				    "qla_target(%d): Not allowed "
-				    "command %x in %s", vha->vp_idx,
-				    mcmd, __func__);
-				sess = NULL;
-				break;
-			}
-		} else
-			sess = NULL;
-#endif
 	} else {
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 		sess = ha->tgt.tgt_ops->find_sess_by_loop_id(vha, loop_id);
@@ -725,7 +680,7 @@ static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd)
 }
 
 /* ha->tgt.sess_lock supposed to be held on entry */
-static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess,
+static void qlt_schedule_sess_for_deletion(struct fc_port *sess,
 	bool immediate)
 {
 	struct qla_tgt *tgt = sess->tgt;
@@ -771,10 +726,13 @@ static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess,
 /* ha->tgt.sess_lock supposed to be held on entry */
 static void qlt_clear_tgt_db(struct qla_tgt *tgt)
 {
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
+	scsi_qla_host_t *vha = tgt->vha;
 
-	list_for_each_entry(sess, &tgt->sess_list, sess_list_entry)
-		qlt_schedule_sess_for_deletion(sess, true);
+	list_for_each_entry(sess, &vha->vp_fcports, list) {
+		if (sess->se_sess)
+			qlt_schedule_sess_for_deletion(sess, true);
+	}
 
 	/* At this point tgt could be already dead */
 }
@@ -829,7 +787,7 @@ static int qla24xx_get_loop_id(struct scsi_qla_host *vha, const uint8_t *s_id,
 }
 
 /* ha->tgt.sess_lock supposed to be held on entry */
-static void qlt_undelete_sess(struct qla_tgt_sess *sess)
+static void qlt_undelete_sess(struct fc_port *sess)
 {
 	BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING);
 
@@ -843,7 +801,7 @@ static void qlt_del_sess_work_fn(struct delayed_work *work)
 	    sess_del_work);
 	struct scsi_qla_host *vha = tgt->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	unsigned long flags, elapsed;
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
@@ -861,7 +819,7 @@ static void qlt_del_sess_work_fn(struct delayed_work *work)
 			    sess);
 			if (sess->se_sess)
 				ha->tgt.tgt_ops->shutdown_sess(sess);
-			qlt_put_sess(sess);
+			ha->tgt.tgt_ops->put_sess(sess);
 		} else {
 			schedule_delayed_work(&tgt->sess_del_work,
 			    sess->expires - elapsed);
@@ -875,19 +833,18 @@ static void qlt_del_sess_work_fn(struct delayed_work *work)
  * Adds an extra ref to allow to drop hw lock after adding sess to the list.
  * Caller must put it.
  */
-static struct qla_tgt_sess *qlt_create_sess(
+static struct fc_port *qlt_create_sess(
 	struct scsi_qla_host *vha,
 	fc_port_t *fcport,
 	bool local)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	unsigned long flags;
 
 	/* Check to avoid double sessions */
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	list_for_each_entry(sess, &vha->vha_tgt.qla_tgt->sess_list,
-				sess_list_entry) {
+	list_for_each_entry(sess, &vha->vp_fcports, list) {
 		if (!memcmp(sess->port_name, fcport->port_name, WWN_SIZE)) {
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf005,
 			    "Double sess %p found (s_id %x:%x:%x, "
@@ -965,7 +922,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 	memcpy(sess->port_name, fcport->port_name, sizeof(sess->port_name));
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list);
+	list_add_tail(&sess->list, &vha->vp_fcports);
 	vha->vha_tgt.qla_tgt->sess_count++;
 	qlt_do_generation_tick(vha, &sess->generation);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
@@ -988,7 +945,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 		return NULL;
 	} else {
 		/*
-		 * Take an extra reference to ->sess_kref here to handle qla_tgt_sess
+		 * Take an extra reference to ->sess_kref here to handle fc_port
 		 * access across ->tgt.sess_lock reaquire.
 		 */
 		kref_get(&sess->sess_kref);
@@ -997,73 +954,6 @@ static struct qla_tgt_sess *qlt_create_sess(
 	return sess;
 }
 
-/*
- * Called from qla2x00_reg_remote_port()
- */
-void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
-{
-	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
-	struct qla_tgt_sess *sess;
-	unsigned long flags;
-
-	if (!vha->hw->tgt.tgt_ops)
-		return;
-
-	if (!tgt || (fcport->port_type != FCT_INITIATOR))
-		return;
-
-	if (qla_ini_mode_enabled(vha))
-		return;
-
-	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	if (tgt->tgt_stop) {
-		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-		return;
-	}
-	sess = qlt_find_sess_by_port_name(tgt, fcport->port_name);
-	if (!sess) {
-		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-
-		mutex_lock(&vha->vha_tgt.tgt_mutex);
-		sess = qlt_create_sess(vha, fcport, false);
-		mutex_unlock(&vha->vha_tgt.tgt_mutex);
-
-		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	} else if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
-		/* Point of no return */
-		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-		return;
-	} else {
-		kref_get(&sess->sess_kref);
-
-		if (sess->deleted) {
-			qlt_undelete_sess(sess);
-
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04c,
-			    "qla_target(%u): %ssession for port %8phC "
-			    "(loop ID %d) reappeared\n", vha->vp_idx,
-			    sess->local ? "local " : "", sess->port_name,
-			    sess->loop_id);
-
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf007,
-			    "Reappeared sess %p\n", sess);
-		}
-		ha->tgt.tgt_ops->update_sess(sess, fcport->d_id, fcport->loop_id,
-					(fcport->flags & FCF_CONF_COMP_SUPPORTED));
-	}
-
-	if (sess && sess->local) {
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04d,
-		    "qla_target(%u): local session for "
-		    "port %8phC (loop ID %d) became global\n", vha->vp_idx,
-		    fcport->port_name, sess->loop_id);
-		sess->local = 0;
-	}
-	qlt_put_sess(sess);
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-}
-
 /*
  * max_gen - specifies maximum session generation
  * at which this deletion requestion is still valid
@@ -1072,7 +962,7 @@ void
 qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen)
 {
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess = fcport;
 	unsigned long flags;
 
 	if (!vha->hw->tgt.tgt_ops)
@@ -1086,8 +976,7 @@ qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen)
 		spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 		return;
 	}
-	sess = qlt_find_sess_by_port_name(tgt, fcport->port_name);
-	if (!sess) {
+	if (!sess->se_sess) {
 		spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 		return;
 	}
@@ -1120,8 +1009,8 @@ static inline int test_tgt_sess_count(struct qla_tgt *tgt)
 	 */
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	ql_dbg(ql_dbg_tgt, tgt->vha, 0xe002,
-	    "tgt %p, empty(sess_list)=%d sess_count=%d\n",
-	    tgt, list_empty(&tgt->sess_list), tgt->sess_count);
+	    "tgt %p, sess_count=%d\n",
+	    tgt, tgt->sess_count);
 	res = (tgt->sess_count == 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
@@ -1184,9 +1073,7 @@ int qlt_stop_phase1(struct qla_tgt *tgt)
 	spin_unlock_irqrestore(&tgt->sess_work_lock, flags);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00a,
-	    "Waiting for tgt %p: list_empty(sess_list)=%d "
-	    "sess_count=%d\n", tgt, list_empty(&tgt->sess_list),
-	    tgt->sess_count);
+	    "Waiting for tgt %p: sess_count=%d\n", tgt, tgt->sess_count);
 
 	wait_event(tgt->waitQ, test_tgt_sess_count(tgt));
 
@@ -1538,7 +1425,7 @@ static void abort_cmds_for_lun(struct scsi_qla_host *vha,
 
 /* ha->hardware_lock supposed to be held on entry */
 static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
-	struct abts_recv_from_24xx *abts, struct qla_tgt_sess *sess)
+	struct abts_recv_from_24xx *abts, struct fc_port *sess)
 {
 	struct qla_hw_data *ha = vha->hw;
 	struct se_session *se_sess = sess->se_sess;
@@ -1547,8 +1434,9 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	u32 lun = 0;
 	int rc;
 	bool found_lun = false;
+	unsigned long flags;
 
-	spin_lock(&se_sess->sess_cmd_lock);
+	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) {
 		struct qla_tgt_cmd *cmd =
 			container_of(se_cmd, struct qla_tgt_cmd, se_cmd);
@@ -1558,7 +1446,7 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 			break;
 		}
 	}
-	spin_unlock(&se_sess->sess_cmd_lock);
+	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 	/* cmd not in LIO lists, look in qla list */
 	if (!found_lun) {
@@ -1612,7 +1500,7 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	struct abts_recv_from_24xx *abts)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	uint32_t tag = abts->exchange_addr_to_abort;
 	uint8_t s_id[3];
 	int rc;
@@ -3215,7 +3103,7 @@ EXPORT_SYMBOL(qlt_abort_cmd);
 
 void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 {
-	struct qla_tgt_sess *sess = cmd->sess;
+	struct fc_port *sess = cmd->sess;
 
 	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe074,
 	    "%s: se_cmd[%p] ox_id %04x\n",
@@ -3577,7 +3465,7 @@ static inline int qlt_get_fcp_task_attr(struct scsi_qla_host *vha,
 	return fcp_task_attr;
 }
 
-static struct qla_tgt_sess *qlt_make_local_sess(struct scsi_qla_host *,
+static struct fc_port *qlt_make_local_sess(struct scsi_qla_host *,
 					uint8_t *);
 /*
  * Process context for I/O path into tcm_qla2xxx code
@@ -3587,7 +3475,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 	scsi_qla_host_t *vha = cmd->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
-	struct qla_tgt_sess *sess = cmd->sess;
+	struct fc_port *sess = cmd->sess;
 	struct atio_from_isp *atio = &cmd->atio;
 	unsigned char *cdb;
 	unsigned long flags;
@@ -3637,7 +3525,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 	 * Drop extra session reference from qla_tgt_handle_cmd_for_atio*(
 	 */
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	qlt_put_sess(sess);
+	ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	return;
 
@@ -3656,7 +3544,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	qlt_put_sess(sess);
+	ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 }
 
@@ -3674,7 +3562,7 @@ static void qlt_do_work(struct work_struct *work)
 }
 
 static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
-				       struct qla_tgt_sess *sess,
+				       struct fc_port *sess,
 				       struct atio_from_isp *atio)
 {
 	struct se_session *se_sess = sess->se_sess;
@@ -3715,7 +3603,7 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 					struct qla_tgt_sess_op, work);
 	scsi_qla_host_t *vha = op->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	struct qla_tgt_cmd *cmd;
 	unsigned long flags;
 	uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id;
@@ -3756,7 +3644,7 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 	if (!cmd) {
 		spin_lock_irqsave(&ha->hardware_lock, flags);
 		qlt_send_busy(vha, &op->atio, SAM_STAT_BUSY);
-		qlt_put_sess(sess);
+		ha->tgt.tgt_ops->put_sess(sess);
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		kfree(op);
 		return;
@@ -3783,8 +3671,9 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 {
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	struct qla_tgt_cmd *cmd;
+	unsigned long flags;
 
 	if (unlikely(tgt->tgt_stop)) {
 		ql_dbg(ql_dbg_io, vha, 0x3061,
@@ -3829,7 +3718,9 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 	if (!cmd) {
 		ql_dbg(ql_dbg_io, vha, 0x3062,
 		    "qla_target(%d): Allocation of cmd failed\n", vha->vp_idx);
-		qlt_put_sess(sess);
+		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+		ha->tgt.tgt_ops->put_sess(sess);
+		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 		return -ENOMEM;
 	}
 
@@ -3858,7 +3749,7 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 }
 
 /* ha->hardware_lock supposed to be held on entry */
-static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
+static int qlt_issue_task_mgmt(struct fc_port *sess, u64 lun,
 	int fn, void *iocb, int flags)
 {
 	struct scsi_qla_host *vha = sess->vha;
@@ -3910,7 +3801,7 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb)
 	struct atio_from_isp *a = (struct atio_from_isp *)iocb;
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	uint32_t lun, unpacked_lun;
 	int fn;
 	unsigned long flags;
@@ -3943,7 +3834,7 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb)
 
 /* ha->hardware_lock supposed to be held on entry */
 static int __qlt_abort_task(struct scsi_qla_host *vha,
-	struct imm_ntfy_from_isp *iocb, struct qla_tgt_sess *sess)
+	struct imm_ntfy_from_isp *iocb, struct fc_port *sess)
 {
 	struct atio_from_isp *a = (struct atio_from_isp *)iocb;
 	struct qla_hw_data *ha = vha->hw;
@@ -3987,7 +3878,7 @@ static int qlt_abort_task(struct scsi_qla_host *vha,
 	struct imm_ntfy_from_isp *iocb)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	int loop_id;
 	unsigned long flags;
 
@@ -4017,14 +3908,14 @@ void qlt_logo_completion_handler(fc_port_t *fcport, int rc)
 				" port %8phC loop_id %#04x s_id %02x:%02x:%02x"
 				" LOGO failed: %#x\n",
 				__func__,
-				fcport->tgt_session->se_sess,
+				fcport->se_sess,
 				fcport->tgt_session,
 				fcport->port_name, fcport->loop_id,
 				fcport->d_id.b.domain, fcport->d_id.b.area,
 				fcport->d_id.b.al_pa, rc);
 		}
 
-		fcport->tgt_session->logout_completed = 1;
+		fcport->logout_completed = 1;
 	}
 }
 
@@ -4035,16 +3926,17 @@ void qlt_logo_completion_handler(fc_port_t *fcport, int rc)
 * deletion. Returns existing session with matching wwn if present.
 * Null otherwise.
 */
-static struct qla_tgt_sess *
+static struct fc_port *
 qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
-    port_id_t port_id, uint16_t loop_id, struct qla_tgt_sess **conflict_sess)
+    port_id_t port_id, uint16_t loop_id, struct fc_port **conflict_sess)
 {
-	struct qla_tgt_sess *sess = NULL, *other_sess;
+	struct fc_port *sess = NULL, *other_sess;
 	uint64_t other_wwn;
+	scsi_qla_host_t *vha = tgt->vha;
 
 	*conflict_sess = NULL;
 
-	list_for_each_entry(other_sess, &tgt->sess_list, sess_list_entry) {
+	list_for_each_entry(other_sess, &vha->vp_fcports, list) {
 
 		other_wwn = wwn_to_u64(other_sess->port_name);
 
@@ -4136,13 +4028,13 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 {
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess = NULL, *conflict_sess = NULL;
+	struct fc_port *sess = NULL, *conflict_sess = NULL;
 	uint64_t wwn;
 	port_id_t port_id;
 	uint16_t loop_id;
 	uint16_t wd3_lo;
 	int res = 0;
-	qlt_plogi_ack_t *pla;
+	struct qlt_plogi_ack_t *pla;
 	unsigned long flags;
 
 	wwn = wwn_to_u64(iocb->u.isp24.port_name);
@@ -4455,7 +4347,7 @@ static int __qlt_send_busy(struct scsi_qla_host *vha,
 	struct ctio7_to_24xx *ctio24;
 	struct qla_hw_data *ha = vha->hw;
 	request_t *pkt;
-	struct qla_tgt_sess *sess = NULL;
+	struct fc_port *sess = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
@@ -4516,7 +4408,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 {
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	struct se_session *se_sess;
 	struct qla_tgt_cmd *cmd;
 	int tag;
@@ -5112,10 +5004,10 @@ static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha,
 }
 
 /* Must be called under tgt_mutex */
-static struct qla_tgt_sess *qlt_make_local_sess(struct scsi_qla_host *vha,
+static struct fc_port *qlt_make_local_sess(struct scsi_qla_host *vha,
 	uint8_t *s_id)
 {
-	struct qla_tgt_sess *sess = NULL;
+	struct fc_port *sess = NULL;
 	fc_port_t *fcport = NULL;
 	int rc, global_resets;
 	uint16_t loop_id = 0;
@@ -5177,7 +5069,6 @@ static struct qla_tgt_sess *qlt_make_local_sess(struct scsi_qla_host *vha,
 
 	mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
-	kfree(fcport);
 	return sess;
 }
 
@@ -5186,7 +5077,7 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 {
 	struct scsi_qla_host *vha = tgt->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess = NULL;
+	struct fc_port *sess = NULL;
 	unsigned long flags = 0, flags2 = 0;
 	uint32_t be_s_id;
 	uint8_t s_id[3];
@@ -5230,8 +5121,8 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 	if (rc != 0)
 		goto out_term;
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-
-	qlt_put_sess(sess);
+	if (sess)
+		ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
 	return;
 
@@ -5242,7 +5133,7 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 	qlt_24xx_send_abts_resp(vha, &prm->abts, FCP_TMF_REJECTED, false);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-	qlt_put_sess(sess);
+	ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
 }
 
@@ -5252,7 +5143,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	struct atio_from_isp *a = &prm->tm_iocb2;
 	struct scsi_qla_host *vha = tgt->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt_sess *sess = NULL;
+	struct fc_port *sess = NULL;
 	unsigned long flags;
 	uint8_t *s_id = NULL; /* to hide compiler warnings */
 	int rc;
@@ -5294,13 +5185,14 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	if (rc != 0)
 		goto out_term;
 
-	qlt_put_sess(sess);
+	ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	return;
 
 out_term:
 	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
-	qlt_put_sess(sess);
+	if (sess)
+		ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 }
 
@@ -5377,7 +5269,6 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
 	tgt->ha = ha;
 	tgt->vha = base_vha;
 	init_waitqueue_head(&tgt->waitQ);
-	INIT_LIST_HEAD(&tgt->sess_list);
 	INIT_LIST_HEAD(&tgt->del_sess_list);
 	INIT_DELAYED_WORK(&tgt->sess_del_work,
 		(void (*)(struct work_struct *))qlt_del_sess_work_fn);
@@ -6233,9 +6124,8 @@ int __init qlt_init(void)
 	}
 
 	qla_tgt_plogi_cachep = kmem_cache_create("qla_tgt_plogi_cachep",
-						 sizeof(qlt_plogi_ack_t),
-						 __alignof__(qlt_plogi_ack_t),
-						 0, NULL);
+	    sizeof(struct qlt_plogi_ack_t), __alignof__(struct qlt_plogi_ack_t),
+	    0, NULL);
 
 	if (!qla_tgt_plogi_cachep) {
 		ql_log(ql_log_fatal, NULL, 0xe06d,
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 07ccf81f6d22..9c35ba15c687 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -118,84 +118,6 @@
 			 ? le16_to_cpu((iocb)->u.isp2x.target.extended)	\
 			 : (uint16_t)(iocb)->u.isp2x.target.id.standard)
 
-#ifndef IMMED_NOTIFY_TYPE
-#define IMMED_NOTIFY_TYPE 0x0D		/* Immediate notify entry. */
-/*
- * ISP queue -	immediate notify entry structure definition.
- *		This is sent by the ISP to the Target driver.
- *		This IOCB would have report of events sent by the
- *		initiator, that needs to be handled by the target
- *		driver immediately.
- */
-struct imm_ntfy_from_isp {
-	uint8_t	 entry_type;		    /* Entry type. */
-	uint8_t	 entry_count;		    /* Entry count. */
-	uint8_t	 sys_define;		    /* System defined. */
-	uint8_t	 entry_status;		    /* Entry Status. */
-	union {
-		struct {
-			uint32_t sys_define_2; /* System defined. */
-			target_id_t target;
-			uint16_t lun;
-			uint8_t  target_id;
-			uint8_t  reserved_1;
-			uint16_t status_modifier;
-			uint16_t status;
-			uint16_t task_flags;
-			uint16_t seq_id;
-			uint16_t srr_rx_id;
-			uint32_t srr_rel_offs;
-			uint16_t srr_ui;
-#define SRR_IU_DATA_IN	0x1
-#define SRR_IU_DATA_OUT	0x5
-#define SRR_IU_STATUS	0x7
-			uint16_t srr_ox_id;
-			uint8_t reserved_2[28];
-		} isp2x;
-		struct {
-			uint32_t reserved;
-			uint16_t nport_handle;
-			uint16_t reserved_2;
-			uint16_t flags;
-#define NOTIFY24XX_FLAGS_GLOBAL_TPRLO   BIT_1
-#define NOTIFY24XX_FLAGS_PUREX_IOCB     BIT_0
-			uint16_t srr_rx_id;
-			uint16_t status;
-			uint8_t  status_subcode;
-			uint8_t  fw_handle;
-			uint32_t exchange_address;
-			uint32_t srr_rel_offs;
-			uint16_t srr_ui;
-			uint16_t srr_ox_id;
-			union {
-				struct {
-					uint8_t node_name[8];
-				} plogi; /* PLOGI/ADISC/PDISC */
-				struct {
-					/* PRLI word 3 bit 0-15 */
-					uint16_t wd3_lo;
-					uint8_t resv0[6];
-				} prli;
-				struct {
-					uint8_t port_id[3];
-					uint8_t resv1;
-					uint16_t nport_handle;
-					uint16_t resv2;
-				} req_els;
-			} u;
-			uint8_t port_name[8];
-			uint8_t resv3[3];
-			uint8_t  vp_index;
-			uint32_t reserved_5;
-			uint8_t  port_id[3];
-			uint8_t  reserved_6;
-		} isp24;
-	} u;
-	uint16_t reserved_7;
-	uint16_t ox_id;
-} __packed;
-#endif
-
 #ifndef NOTIFY_ACK_TYPE
 #define NOTIFY_ACK_TYPE 0x0E	  /* Notify acknowledge entry. */
 /*
@@ -731,7 +653,7 @@ struct abts_resp_from_24xx_fw {
 \********************************************************************/
 
 struct qla_tgt_mgmt_cmd;
-struct qla_tgt_sess;
+struct fc_port;
 
 /*
  * This structure provides a template of function calls that the
@@ -748,17 +670,18 @@ struct qla_tgt_func_tmpl {
 			uint32_t);
 	void (*free_cmd)(struct qla_tgt_cmd *);
 	void (*free_mcmd)(struct qla_tgt_mgmt_cmd *);
-	void (*free_session)(struct qla_tgt_sess *);
+	void (*free_session)(struct fc_port *);
 
 	int (*check_initiator_node_acl)(struct scsi_qla_host *, unsigned char *,
-					struct qla_tgt_sess *);
-	void (*update_sess)(struct qla_tgt_sess *, port_id_t, uint16_t, bool);
-	struct qla_tgt_sess *(*find_sess_by_loop_id)(struct scsi_qla_host *,
+					struct fc_port *);
+	void (*update_sess)(struct fc_port *, port_id_t, uint16_t, bool);
+	struct fc_port *(*find_sess_by_loop_id)(struct scsi_qla_host *,
 						const uint16_t);
-	struct qla_tgt_sess *(*find_sess_by_s_id)(struct scsi_qla_host *,
+	struct fc_port *(*find_sess_by_s_id)(struct scsi_qla_host *,
 						const uint8_t *);
-	void (*clear_nacl_from_fcport_map)(struct qla_tgt_sess *);
-	void (*shutdown_sess)(struct qla_tgt_sess *);
+	void (*clear_nacl_from_fcport_map)(struct fc_port *);
+	void (*put_sess)(struct fc_port *);
+	void (*shutdown_sess)(struct fc_port *);
 };
 
 int qla2x00_wait_for_hba_online(struct scsi_qla_host *);
@@ -874,9 +797,6 @@ struct qla_tgt {
 	/* Count of sessions refering qla_tgt. Protected by hardware_lock. */
 	int sess_count;
 
-	/* Protected by hardware_lock. Addition also protected by tgt_mutex. */
-	struct list_head sess_list;
-
 	/* Protected by hardware_lock */
 	struct list_head del_sess_list;
 	struct delayed_work sess_del_work;
@@ -910,52 +830,6 @@ enum qla_sess_deletion {
 	QLA_SESS_DELETION_IN_PROGRESS	= 2,
 };
 
-typedef enum {
-	QLT_PLOGI_LINK_SAME_WWN,
-	QLT_PLOGI_LINK_CONFLICT,
-	QLT_PLOGI_LINK_MAX
-} qlt_plogi_link_t;
-
-typedef struct {
-	struct list_head		list;
-	struct imm_ntfy_from_isp	iocb;
-	port_id_t			id;
-	int				ref_count;
-} qlt_plogi_ack_t;
-
-/*
- * Equivilant to IT Nexus (Initiator-Target)
- */
-struct qla_tgt_sess {
-	uint16_t loop_id;
-	port_id_t d_id;
-
-	unsigned int conf_compl_supported:1;
-	unsigned int deleted:2;
-	unsigned int local:1;
-	unsigned int logout_on_delete:1;
-	unsigned int keep_nport_handle:1;
-	unsigned int send_els_logo:1;
-
-	unsigned char logout_completed;
-
-	int generation;
-
-	struct se_session *se_sess;
-	struct kref sess_kref;
-	struct scsi_qla_host *vha;
-	struct qla_tgt *tgt;
-
-	struct list_head sess_list_entry;
-	unsigned long expires;
-	struct list_head del_list_entry;
-
-	uint8_t port_name[WWN_SIZE];
-	struct work_struct free_work;
-
-	qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
-};
-
 enum trace_flags {
 	TRC_NEW_CMD = BIT_0,
 	TRC_DO_WORK = BIT_1,
@@ -981,7 +855,7 @@ enum trace_flags {
 
 struct qla_tgt_cmd {
 	struct se_cmd se_cmd;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	int state;
 	struct work_struct free_work;
 	struct work_struct work;
@@ -1046,7 +920,7 @@ struct qla_tgt_sess_work_param {
 struct qla_tgt_mgmt_cmd {
 	uint16_t tmr_func;
 	uint8_t fc_tm_rsp;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 	struct se_cmd se_cmd;
 	struct work_struct free_work;
 	unsigned int flags;
@@ -1097,7 +971,7 @@ extern int qlt_remove_target(struct qla_hw_data *, struct scsi_qla_host *);
 extern int qlt_lport_register(void *, u64, u64, u64,
 			int (*callback)(struct scsi_qla_host *, void *, u64, u64));
 extern void qlt_lport_deregister(struct scsi_qla_host *);
-void qlt_put_sess(struct qla_tgt_sess *sess);
+extern void qlt_unreg_sess(struct fc_port *);
 extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *);
 extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int);
 extern int __init qlt_init(void);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index c96de1cfbd85..e37d7ee95473 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -339,9 +339,26 @@ static void tcm_qla2xxx_release_cmd(struct se_cmd *se_cmd)
 	qlt_free_cmd(cmd);
 }
 
+static void tcm_qla2xxx_release_session(struct kref *kref)
+{
+	struct fc_port  *sess = container_of(kref,
+	    struct fc_port, sess_kref);
+
+	qlt_unreg_sess(sess);
+}
+
+static void tcm_qla2xxx_put_sess(struct fc_port *sess)
+{
+	if (!sess)
+		return;
+
+	assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
+	kref_put(&sess->sess_kref, tcm_qla2xxx_release_session);
+}
+
 static void tcm_qla2xxx_close_session(struct se_session *se_sess)
 {
-	struct qla_tgt_sess *sess = se_sess->fabric_sess_ptr;
+	struct fc_port *sess = se_sess->fabric_sess_ptr;
 	struct scsi_qla_host *vha;
 	unsigned long flags;
 
@@ -350,7 +367,7 @@ static void tcm_qla2xxx_close_session(struct se_session *se_sess)
 
 	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 	target_sess_cmd_list_set_waiting(se_sess);
-	qlt_put_sess(sess);
+	tcm_qla2xxx_put_sess(sess);
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 }
 
@@ -441,7 +458,7 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 {
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 	struct se_session *se_sess;
-	struct qla_tgt_sess *sess;
+	struct fc_port *sess;
 #ifdef CONFIG_TCM_QLA2XXX_DEBUG
 	struct se_portal_group *se_tpg;
 	struct tcm_qla2xxx_tpg *tpg;
@@ -456,7 +473,7 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 
 	sess = cmd->sess;
 	if (!sess) {
-		pr_err("Unable to locate struct qla_tgt_sess from qla_tgt_cmd\n");
+		pr_err("Unable to locate struct fc_port from qla_tgt_cmd\n");
 		return -EINVAL;
 	}
 
@@ -565,7 +582,7 @@ static void tcm_qla2xxx_handle_dif_err(struct qla_tgt_cmd *cmd)
 static int tcm_qla2xxx_handle_tmr(struct qla_tgt_mgmt_cmd *mcmd, uint32_t lun,
 	uint16_t tmr_func, uint32_t tag)
 {
-	struct qla_tgt_sess *sess = mcmd->sess;
+	struct fc_port *sess = mcmd->sess;
 	struct se_cmd *se_cmd = &mcmd->se_cmd;
 	int transl_tmr_func = 0;
 
@@ -746,11 +763,11 @@ static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,
-			struct tcm_qla2xxx_nacl *, struct qla_tgt_sess *);
+			struct tcm_qla2xxx_nacl *, struct fc_port *);
 /*
  * Expected to be called with struct qla_hw_data->tgt.sess_lock held
  */
-static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess)
+static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct fc_port *sess)
 {
 	struct se_node_acl *se_nacl = sess->se_sess->se_node_acl;
 	struct se_portal_group *se_tpg = se_nacl->se_tpg;
@@ -789,7 +806,7 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess)
 	tcm_qla2xxx_clear_sess_lookup(lport, nacl, sess);
 }
 
-static void tcm_qla2xxx_shutdown_sess(struct qla_tgt_sess *sess)
+static void tcm_qla2xxx_shutdown_sess(struct fc_port *sess)
 {
 	assert_spin_locked(&sess->vha->hw->tgt.sess_lock);
 	target_sess_cmd_list_set_waiting(sess->se_sess);
@@ -1174,7 +1191,7 @@ static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(
 /*
  * Expected to be called with struct qla_hw_data->tgt.sess_lock held
  */
-static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id(
+static struct fc_port *tcm_qla2xxx_find_sess_by_s_id(
 	scsi_qla_host_t *vha,
 	const uint8_t *s_id)
 {
@@ -1202,12 +1219,12 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id(
 	    se_nacl, se_nacl->initiatorname);
 
 	nacl = container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl);
-	if (!nacl->qla_tgt_sess) {
-		pr_err("Unable to locate struct qla_tgt_sess\n");
+	if (!nacl->fc_port) {
+		pr_err("Unable to locate struct fc_port\n");
 		return NULL;
 	}
 
-	return nacl->qla_tgt_sess;
+	return nacl->fc_port;
 }
 
 /*
@@ -1218,7 +1235,7 @@ static void tcm_qla2xxx_set_sess_by_s_id(
 	struct se_node_acl *new_se_nacl,
 	struct tcm_qla2xxx_nacl *nacl,
 	struct se_session *se_sess,
-	struct qla_tgt_sess *qla_tgt_sess,
+	struct fc_port *fc_port,
 	uint8_t *s_id)
 {
 	u32 key;
@@ -1242,22 +1259,22 @@ static void tcm_qla2xxx_set_sess_by_s_id(
 			pr_debug("Wiping nonexisting fc_port entry\n");
 		}
 
-		qla_tgt_sess->se_sess = se_sess;
-		nacl->qla_tgt_sess = qla_tgt_sess;
+		fc_port->se_sess = se_sess;
+		nacl->fc_port = fc_port;
 		return;
 	}
 
-	if (nacl->qla_tgt_sess) {
+	if (nacl->fc_port) {
 		if (new_se_nacl == NULL) {
-			pr_debug("Clearing existing nacl->qla_tgt_sess and fc_port entry\n");
+			pr_debug("Clearing existing nacl->fc_port and fc_port entry\n");
 			btree_remove32(&lport->lport_fcport_map, key);
-			nacl->qla_tgt_sess = NULL;
+			nacl->fc_port = NULL;
 			return;
 		}
-		pr_debug("Replacing existing nacl->qla_tgt_sess and fc_port entry\n");
+		pr_debug("Replacing existing nacl->fc_port and fc_port entry\n");
 		btree_update32(&lport->lport_fcport_map, key, new_se_nacl);
-		qla_tgt_sess->se_sess = se_sess;
-		nacl->qla_tgt_sess = qla_tgt_sess;
+		fc_port->se_sess = se_sess;
+		nacl->fc_port = fc_port;
 		return;
 	}
 
@@ -1267,19 +1284,19 @@ static void tcm_qla2xxx_set_sess_by_s_id(
 		return;
 	}
 
-	pr_debug("Replacing existing fc_port entry w/o active nacl->qla_tgt_sess\n");
+	pr_debug("Replacing existing fc_port entry w/o active nacl->fc_port\n");
 	btree_update32(&lport->lport_fcport_map, key, new_se_nacl);
-	qla_tgt_sess->se_sess = se_sess;
-	nacl->qla_tgt_sess = qla_tgt_sess;
+	fc_port->se_sess = se_sess;
+	nacl->fc_port = fc_port;
 
-	pr_debug("Setup nacl->qla_tgt_sess %p by s_id for se_nacl: %p, initiatorname: %s\n",
-	    nacl->qla_tgt_sess, new_se_nacl, new_se_nacl->initiatorname);
+	pr_debug("Setup nacl->fc_port %p by s_id for se_nacl: %p, initiatorname: %s\n",
+	    nacl->fc_port, new_se_nacl, new_se_nacl->initiatorname);
 }
 
 /*
  * Expected to be called with struct qla_hw_data->tgt.sess_lock held
  */
-static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_loop_id(
+static struct fc_port *tcm_qla2xxx_find_sess_by_loop_id(
 	scsi_qla_host_t *vha,
 	const uint16_t loop_id)
 {
@@ -1307,12 +1324,12 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_loop_id(
 
 	nacl = container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl);
 
-	if (!nacl->qla_tgt_sess) {
-		pr_err("Unable to locate struct qla_tgt_sess\n");
+	if (!nacl->fc_port) {
+		pr_err("Unable to locate struct fc_port\n");
 		return NULL;
 	}
 
-	return nacl->qla_tgt_sess;
+	return nacl->fc_port;
 }
 
 /*
@@ -1323,7 +1340,7 @@ static void tcm_qla2xxx_set_sess_by_loop_id(
 	struct se_node_acl *new_se_nacl,
 	struct tcm_qla2xxx_nacl *nacl,
 	struct se_session *se_sess,
-	struct qla_tgt_sess *qla_tgt_sess,
+	struct fc_port *fc_port,
 	uint16_t loop_id)
 {
 	struct se_node_acl *saved_nacl;
@@ -1338,27 +1355,27 @@ static void tcm_qla2xxx_set_sess_by_loop_id(
 	if (!saved_nacl) {
 		pr_debug("Setting up new fc_loopid->se_nacl to new_se_nacl\n");
 		fc_loopid->se_nacl = new_se_nacl;
-		if (qla_tgt_sess->se_sess != se_sess)
-			qla_tgt_sess->se_sess = se_sess;
-		if (nacl->qla_tgt_sess != qla_tgt_sess)
-			nacl->qla_tgt_sess = qla_tgt_sess;
+		if (fc_port->se_sess != se_sess)
+			fc_port->se_sess = se_sess;
+		if (nacl->fc_port != fc_port)
+			nacl->fc_port = fc_port;
 		return;
 	}
 
-	if (nacl->qla_tgt_sess) {
+	if (nacl->fc_port) {
 		if (new_se_nacl == NULL) {
-			pr_debug("Clearing nacl->qla_tgt_sess and fc_loopid->se_nacl\n");
+			pr_debug("Clearing nacl->fc_port and fc_loopid->se_nacl\n");
 			fc_loopid->se_nacl = NULL;
-			nacl->qla_tgt_sess = NULL;
+			nacl->fc_port = NULL;
 			return;
 		}
 
-		pr_debug("Replacing existing nacl->qla_tgt_sess and fc_loopid->se_nacl\n");
+		pr_debug("Replacing existing nacl->fc_port and fc_loopid->se_nacl\n");
 		fc_loopid->se_nacl = new_se_nacl;
-		if (qla_tgt_sess->se_sess != se_sess)
-			qla_tgt_sess->se_sess = se_sess;
-		if (nacl->qla_tgt_sess != qla_tgt_sess)
-			nacl->qla_tgt_sess = qla_tgt_sess;
+		if (fc_port->se_sess != se_sess)
+			fc_port->se_sess = se_sess;
+		if (nacl->fc_port != fc_port)
+			nacl->fc_port = fc_port;
 		return;
 	}
 
@@ -1368,22 +1385,22 @@ static void tcm_qla2xxx_set_sess_by_loop_id(
 		return;
 	}
 
-	pr_debug("Replacing existing fc_loopid->se_nacl w/o active nacl->qla_tgt_sess\n");
+	pr_debug("Replacing existing fc_loopid->se_nacl w/o active nacl->fc_port\n");
 	fc_loopid->se_nacl = new_se_nacl;
-	if (qla_tgt_sess->se_sess != se_sess)
-		qla_tgt_sess->se_sess = se_sess;
-	if (nacl->qla_tgt_sess != qla_tgt_sess)
-		nacl->qla_tgt_sess = qla_tgt_sess;
+	if (fc_port->se_sess != se_sess)
+		fc_port->se_sess = se_sess;
+	if (nacl->fc_port != fc_port)
+		nacl->fc_port = fc_port;
 
-	pr_debug("Setup nacl->qla_tgt_sess %p by loop_id for se_nacl: %p, initiatorname: %s\n",
-	    nacl->qla_tgt_sess, new_se_nacl, new_se_nacl->initiatorname);
+	pr_debug("Setup nacl->fc_port %p by loop_id for se_nacl: %p, initiatorname: %s\n",
+	    nacl->fc_port, new_se_nacl, new_se_nacl->initiatorname);
 }
 
 /*
  * Should always be called with qla_hw_data->tgt.sess_lock held.
  */
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *lport,
-		struct tcm_qla2xxx_nacl *nacl, struct qla_tgt_sess *sess)
+		struct tcm_qla2xxx_nacl *nacl, struct fc_port *sess)
 {
 	struct se_session *se_sess = sess->se_sess;
 	unsigned char be_sid[3];
@@ -1398,7 +1415,7 @@ static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *lport,
 				sess, sess->loop_id);
 }
 
-static void tcm_qla2xxx_free_session(struct qla_tgt_sess *sess)
+static void tcm_qla2xxx_free_session(struct fc_port *sess)
 {
 	struct qla_tgt *tgt = sess->tgt;
 	struct qla_hw_data *ha = tgt->ha;
@@ -1410,7 +1427,7 @@ static void tcm_qla2xxx_free_session(struct qla_tgt_sess *sess)
 
 	se_sess = sess->se_sess;
 	if (!se_sess) {
-		pr_err("struct qla_tgt_sess->se_sess is NULL\n");
+		pr_err("struct fc_port->se_sess is NULL\n");
 		dump_stack();
 		return;
 	}
@@ -1437,7 +1454,7 @@ static int tcm_qla2xxx_session_cb(struct se_portal_group *se_tpg,
 	struct se_node_acl *se_nacl = se_sess->se_node_acl;
 	struct tcm_qla2xxx_nacl *nacl = container_of(se_nacl,
 				struct tcm_qla2xxx_nacl, se_node_acl);
-	struct qla_tgt_sess *qlat_sess = p;
+	struct fc_port *qlat_sess = p;
 	uint16_t loop_id = qlat_sess->loop_id;
 	unsigned long flags;
 	unsigned char be_sid[3];
@@ -1467,7 +1484,7 @@ static int tcm_qla2xxx_session_cb(struct se_portal_group *se_tpg,
 static int tcm_qla2xxx_check_initiator_node_acl(
 	scsi_qla_host_t *vha,
 	unsigned char *fc_wwpn,
-	struct qla_tgt_sess *qlat_sess)
+	struct fc_port *qlat_sess)
 {
 	struct qla_hw_data *ha = vha->hw;
 	struct tcm_qla2xxx_lport *lport;
@@ -1511,7 +1528,7 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	return 0;
 }
 
-static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id,
+static void tcm_qla2xxx_update_sess(struct fc_port *sess, port_id_t s_id,
 				    uint16_t loop_id, bool conf_compl_supported)
 {
 	struct qla_tgt *tgt = sess->tgt;
@@ -1603,6 +1620,7 @@ static struct qla_tgt_func_tmpl tcm_qla2xxx_template = {
 	.find_sess_by_s_id	= tcm_qla2xxx_find_sess_by_s_id,
 	.find_sess_by_loop_id	= tcm_qla2xxx_find_sess_by_loop_id,
 	.clear_nacl_from_fcport_map = tcm_qla2xxx_clear_nacl_from_fcport_map,
+	.put_sess		= tcm_qla2xxx_put_sess,
 	.shutdown_sess		= tcm_qla2xxx_shutdown_sess,
 };
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index cf8430be183b..071035dfa99a 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -20,8 +20,8 @@ struct tcm_qla2xxx_nacl {
 	u64 nport_wwnn;
 	/* ASCII formatted WWPN for FC Initiator Nport */
 	char nport_name[TCM_QLA2XXX_NAMELEN];
-	/* Pointer to qla_tgt_sess */
-	struct qla_tgt_sess *qla_tgt_sess;
+	/* Pointer to fc_port */
+	struct fc_port *fc_port;
 	/* Pointer to TCM FC nexus */
 	struct se_session *nport_nexus;
 };
-- 
GitLab


From 726b85487067d7f5b23495bc33c484b8517c4074 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:28:00 -0800
Subject: [PATCH 067/898] qla2xxx: Add framework for async fabric discovery

Currently code performs a full scan of the fabric for
every RSCN. Its an expensive process in a noisy large SAN.

This patch optimizes expensive fabric discovery process by
scanning switch for the affected port when RSCN is received.

Currently Initiator Mode code makes login/logout decision without
knowledge of target mode. This causes driver and firmware to go
out-of-sync. This framework synchronizes both initiator mode
personality and target mode personality in making login/logout
decision.

This patch adds following capabilities in the driver

- Send Notification Acknowledgement asynchronously.
- Update session/fcport state asynchronously.
- Create a session or fcport struct asynchronously.
- Send GNL asynchronously. The command will ask FW to
  provide a list of FC Port entries FW knows about.
- Send GPDB asynchronously. The command will ask FW to
  provide detail data of an FC Port FW knows about or
  perform ADISC to verify the state of the session.
- Send GPNID asynchronously. The command will ask switch
  to provide WWPN for provided NPort ID.
- Send GPSC asynchronously. The command will ask switch
  to provide registered port speed for provided WWPN.
- Send GIDPN asynchronously. The command will ask the
  switch to provide Nport ID for provided WWPN.
- In driver unload path, schedule all session for deletion
  and wait for deletion to complete before allowing driver
  unload to proceed.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
[ bvanassche: fixed spelling in patch description ]
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_attr.c   |    3 +
 drivers/scsi/qla2xxx/qla_def.h    |  175 +++-
 drivers/scsi/qla2xxx/qla_fw.h     |   31 +
 drivers/scsi/qla2xxx/qla_gbl.h    |   56 +-
 drivers/scsi/qla2xxx/qla_gs.c     |  724 +++++++++++++--
 drivers/scsi/qla2xxx/qla_init.c   | 1396 ++++++++++++++++++++++-------
 drivers/scsi/qla2xxx/qla_inline.h |    7 +-
 drivers/scsi/qla2xxx/qla_iocb.c   |   71 +-
 drivers/scsi/qla2xxx/qla_isr.c    |  260 ++++--
 drivers/scsi/qla2xxx/qla_mbx.c    |   88 --
 drivers/scsi/qla2xxx/qla_os.c     |  271 ++++--
 drivers/scsi/qla2xxx/qla_target.c | 1002 ++++++++++++++-------
 drivers/scsi/qla2xxx/qla_target.h |   17 +-
 13 files changed, 3114 insertions(+), 987 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index f201f4099620..f610103994af 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2163,6 +2163,9 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 	clear_bit(vha->vp_idx, ha->vp_idx_map);
 	mutex_unlock(&ha->vport_lock);
 
+	dma_free_coherent(&ha->pdev->dev, vha->gnl.size, vha->gnl.l,
+	    vha->gnl.ldma);
+
 	if (vha->qpair->vp_idx == vha->vp_idx) {
 		if (qla2xxx_delete_qpair(vha, vha->qpair) != QLA_SUCCESS)
 			ql_log(ql_log_warn, vha, 0x7087,
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 1bdcc7e010ff..79b4e88db3b1 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -55,6 +55,8 @@
 
 #include "qla_settings.h"
 
+#define MODE_DUAL (MODE_TARGET | MODE_INITIATOR)
+
 /*
  * Data bit definitions
  */
@@ -251,6 +253,14 @@
 
 #define MAX_CMDSZ	16		/* SCSI maximum CDB size. */
 #include "qla_fw.h"
+
+struct name_list_extended {
+	struct get_name_list_extended *l;
+	dma_addr_t		ldma;
+	struct list_head 	fcports;	/* protect by sess_list */
+	u32			size;
+	u8			sent;
+};
 /*
  * Timeout timer counts in seconds
  */
@@ -309,6 +319,17 @@ struct els_logo_payload {
 	uint8_t wwpn[WWN_SIZE];
 };
 
+struct ct_arg {
+	void		*iocb;
+	u16		nport_handle;
+	dma_addr_t	req_dma;
+	dma_addr_t	rsp_dma;
+	u32		req_size;
+	u32		rsp_size;
+	void		*req;
+	void		*rsp;
+};
+
 /*
  * SRB extensions.
  */
@@ -320,6 +341,7 @@ struct srb_iocb {
 #define SRB_LOGIN_COND_PLOGI	BIT_1
 #define SRB_LOGIN_SKIP_PRLI	BIT_2
 			uint16_t data[2];
+			u32 iop[2];
 		} logio;
 		struct {
 #define ELS_DCMD_TIMEOUT 20
@@ -372,6 +394,16 @@ struct srb_iocb {
 			__le16 comp_status;
 			struct completion comp;
 		} abt;
+		struct ct_arg ctarg;
+		struct {
+			__le16 in_mb[28]; 	/* fr fw */
+			__le16 out_mb[28];	/* to fw */
+			void *out, *in;
+			dma_addr_t out_dma, in_dma;
+		} mbx;
+		struct {
+			struct imm_ntfy_from_isp *ntfy;
+		} nack;
 	} u;
 
 	struct timer_list timer;
@@ -392,16 +424,24 @@ struct srb_iocb {
 #define SRB_FXIOCB_BCMD	11
 #define SRB_ABT_CMD	12
 #define SRB_ELS_DCMD	13
+#define SRB_MB_IOCB	14
+#define SRB_CT_PTHRU_CMD 15
+#define SRB_NACK_PLOGI	16
+#define SRB_NACK_PRLI	17
+#define SRB_NACK_LOGO	18
 
 typedef struct srb {
 	atomic_t ref_count;
 	struct fc_port *fcport;
+	void *vha;
 	uint32_t handle;
 	uint16_t flags;
 	uint16_t type;
 	char *name;
 	int iocbs;
 	struct qla_qpair *qpair;
+	u32 gen1;	/* scratch */
+	u32 gen2;	/* scratch */
 	union {
 		struct srb_iocb iocb_cmd;
 		struct bsg_job *bsg_job;
@@ -2101,6 +2141,18 @@ typedef struct {
 #define FC4_TYPE_OTHER		0x0
 #define FC4_TYPE_UNKNOWN	0xff
 
+/* mailbox command 4G & above */
+struct mbx_24xx_entry {
+	uint8_t		entry_type;
+	uint8_t		entry_count;
+	uint8_t		sys_define1;
+	uint8_t		entry_status;
+	uint32_t	handle;
+	uint16_t	mb[28];
+};
+
+#define IOCB_SIZE 64
+
 /*
  * Fibre channel port type.
  */
@@ -2113,6 +2165,12 @@ typedef enum {
 	FCT_TARGET
 } fc_port_type_t;
 
+enum qla_sess_deletion {
+	QLA_SESS_DELETION_NONE		= 0,
+	QLA_SESS_DELETION_IN_PROGRESS,
+	QLA_SESS_DELETED,
+};
+
 enum qlt_plogi_link_t {
 	QLT_PLOGI_LINK_SAME_WWN,
 	QLT_PLOGI_LINK_CONFLICT,
@@ -2124,6 +2182,48 @@ struct qlt_plogi_ack_t {
 	struct imm_ntfy_from_isp iocb;
 	port_id_t	id;
 	int		ref_count;
+	void		*fcport;
+};
+
+struct ct_sns_desc {
+	struct ct_sns_pkt	*ct_sns;
+	dma_addr_t		ct_sns_dma;
+};
+
+enum discovery_state {
+	DSC_DELETED,
+	DSC_GID_PN,
+	DSC_GNL,
+	DSC_LOGIN_PEND,
+	DSC_LOGIN_FAILED,
+	DSC_GPDB,
+	DSC_GPSC,
+	DSC_UPD_FCPORT,
+	DSC_LOGIN_COMPLETE,
+	DSC_DELETE_PEND,
+};
+
+enum login_state {	/* FW control Target side */
+	DSC_LS_LLIOCB_SENT = 2,
+	DSC_LS_PLOGI_PEND,
+	DSC_LS_PLOGI_COMP,
+	DSC_LS_PRLI_PEND,
+	DSC_LS_PRLI_COMP,
+	DSC_LS_PORT_UNAVAIL,
+	DSC_LS_PRLO_PEND = 9,
+	DSC_LS_LOGO_PEND,
+};
+
+enum fcport_mgt_event {
+	FCME_RELOGIN = 1,
+	FCME_RSCN,
+	FCME_GIDPN_DONE,
+	FCME_PLOGI_DONE,	/* Initiator side sent LLIOCB */
+	FCME_GNL_DONE,
+	FCME_GPSC_DONE,
+	FCME_GPDB_DONE,
+	FCME_GPNID_DONE,
+	FCME_DELETE_DONE,
 };
 
 /*
@@ -2143,9 +2243,13 @@ typedef struct fc_port {
 	unsigned int deleted:2;
 	unsigned int local:1;
 	unsigned int logout_on_delete:1;
+	unsigned int logo_ack_needed:1;
 	unsigned int keep_nport_handle:1;
 	unsigned int send_els_logo:1;
+	unsigned int login_pause:1;
+	unsigned int login_succ:1;
 
+	struct fc_port *conflict;
 	unsigned char logout_completed;
 	int generation;
 
@@ -2186,8 +2290,30 @@ typedef struct fc_port {
 
 	unsigned long retry_delay_timestamp;
 	struct qla_tgt_sess *tgt_session;
+	struct ct_sns_desc ct_desc;
+	enum discovery_state disc_state;
+	enum login_state fw_login_state;
+	u32 login_gen, last_login_gen;
+	u32 rscn_gen, last_rscn_gen;
+	u32 chip_reset;
+	struct list_head gnl_entry;
+	struct work_struct del_work;
+	u8 iocb[IOCB_SIZE];
 } fc_port_t;
 
+#define QLA_FCPORT_SCAN		1
+#define QLA_FCPORT_FOUND	2
+
+struct event_arg {
+	enum fcport_mgt_event	event;
+	fc_port_t		*fcport;
+	srb_t			*sp;
+	port_id_t		id;
+	u16			data[2], rc;
+	u8			port_name[WWN_SIZE];
+	u32			iop[2];
+};
+
 #include "qla_mr.h"
 
 /*
@@ -2265,6 +2391,10 @@ static const char * const port_state_str[] = {
 #define	GFT_ID_REQ_SIZE	(16 + 4)
 #define	GFT_ID_RSP_SIZE	(16 + 32)
 
+#define GID_PN_CMD 0x121
+#define GID_PN_REQ_SIZE (16 + 8)
+#define GID_PN_RSP_SIZE (16 + 4)
+
 #define	RFT_ID_CMD	0x217
 #define	RFT_ID_REQ_SIZE	(16 + 4 + 32)
 #define	RFT_ID_RSP_SIZE	16
@@ -2590,6 +2720,10 @@ struct ct_sns_req {
 			uint8_t reserved;
 			uint8_t port_name[3];
 		} gff_id;
+
+		struct {
+			uint8_t port_name[8];
+		} gid_pn;
 	} req;
 };
 
@@ -2669,6 +2803,10 @@ struct ct_sns_rsp {
 		struct {
 			uint8_t fc4_features[128];
 		} gff_id;
+		struct {
+			uint8_t reserved;
+			uint8_t port_id[3];
+		} gid_pn;
 	} rsp;
 };
 
@@ -2810,11 +2948,11 @@ struct isp_operations {
 
 	uint16_t (*calc_req_entries) (uint16_t);
 	void (*build_iocbs) (srb_t *, cmd_entry_t *, uint16_t);
-	void * (*prep_ms_iocb) (struct scsi_qla_host *, uint32_t, uint32_t);
-	void * (*prep_ms_fdmi_iocb) (struct scsi_qla_host *, uint32_t,
+	void *(*prep_ms_iocb) (struct scsi_qla_host *, struct ct_arg *);
+	void *(*prep_ms_fdmi_iocb) (struct scsi_qla_host *, uint32_t,
 	    uint32_t);
 
-	uint8_t * (*read_nvram) (struct scsi_qla_host *, uint8_t *,
+	uint8_t *(*read_nvram) (struct scsi_qla_host *, uint8_t *,
 		uint32_t, uint32_t);
 	int (*write_nvram) (struct scsi_qla_host *, uint8_t *, uint32_t,
 		uint32_t);
@@ -2876,13 +3014,21 @@ enum qla_work_type {
 	QLA_EVT_AEN,
 	QLA_EVT_IDC_ACK,
 	QLA_EVT_ASYNC_LOGIN,
-	QLA_EVT_ASYNC_LOGIN_DONE,
 	QLA_EVT_ASYNC_LOGOUT,
 	QLA_EVT_ASYNC_LOGOUT_DONE,
 	QLA_EVT_ASYNC_ADISC,
 	QLA_EVT_ASYNC_ADISC_DONE,
 	QLA_EVT_UEVENT,
 	QLA_EVT_AENFX,
+	QLA_EVT_GIDPN,
+	QLA_EVT_GPNID,
+	QLA_EVT_GPNID_DONE,
+	QLA_EVT_NEW_SESS,
+	QLA_EVT_GPDB,
+	QLA_EVT_GPSC,
+	QLA_EVT_UPD_FCPORT,
+	QLA_EVT_GNL,
+	QLA_EVT_NACK,
 };
 
 
@@ -2918,6 +3064,23 @@ struct qla_work_evt {
 		struct {
 			srb_t *sp;
 		} iosb;
+		struct {
+			port_id_t id;
+		} gpnid;
+		struct {
+			port_id_t id;
+			u8 port_name[8];
+			void *pla;
+		} new_sess;
+		struct { /*Get PDB, Get Speed, update fcport, gnl, gidpn */
+			fc_port_t *fcport;
+			u8 opt;
+		} fcport;
+		struct {
+			fc_port_t *fcport;
+			u8 iocb[IOCB_SIZE];
+			int type;
+		} nack;
 	 } u;
 };
 
@@ -3899,6 +4062,10 @@ typedef struct scsi_qla_host {
 	struct qla8044_reset_template reset_tmplt;
 	struct qla_tgt_counters tgt_counters;
 	uint16_t	bbcr;
+	struct name_list_extended gnl;
+	/* Count of active session/fcport */
+	int fcport_count;
+	wait_queue_head_t fcport_waitQ;
 } scsi_qla_host_t;
 
 struct qla27xx_image_status {
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 8a2368b32dec..ee135cf96aee 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -72,6 +72,37 @@ struct port_database_24xx {
 	uint8_t reserved_3[24];
 };
 
+/*
+ * MB 75h returns a list of DB entries similar to port_database_24xx(64B).
+ * However, in this case it returns 1st 40 bytes.
+ */
+struct get_name_list_extended {
+	__le16 flags;
+	u8 current_login_state;
+	u8 last_login_state;
+	u8 hard_address[3];
+	u8 reserved_1;
+	u8 port_id[3];
+	u8 sequence_id;
+	__le16 port_timer;
+	__le16 nport_handle;			/* N_PORT handle. */
+	__le16 receive_data_size;
+	__le16 reserved_2;
+
+	/* PRLI SVC Param are Big endian */
+	u8 prli_svc_param_word_0[2]; /* Bits 15-0 of word 0 */
+	u8 prli_svc_param_word_3[2]; /* Bits 15-0 of word 3 */
+	u8 port_name[WWN_SIZE];
+	u8 node_name[WWN_SIZE];
+};
+
+/* MB 75h: This is the short version of the database */
+struct get_name_list {
+	u8 port_node_name[WWN_SIZE]; /* B7 most sig, B0 least sig */
+	__le16 nport_handle;
+	u8 reserved;
+};
+
 struct vp_database_24xx {
 	uint16_t vp_status;
 	uint8_t  options;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index afa0116a163b..dd95ff620ae3 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -73,6 +73,10 @@ extern void qla2x00_async_logout_done(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
 extern void qla2x00_async_adisc_done(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
+struct qla_work_evt *qla2x00_alloc_work(struct scsi_qla_host *,
+    enum qla_work_type);
+extern int qla24xx_async_gnl(struct scsi_qla_host *, fc_port_t *);
+int qla2x00_post_work(struct scsi_qla_host *vha, struct qla_work_evt *e);
 extern void *qla2x00_alloc_iocbs(struct scsi_qla_host *, srb_t *);
 extern void *qla2x00_alloc_iocbs_ready(struct scsi_qla_host *, srb_t *);
 extern int qla24xx_update_fcport_fcp_prio(scsi_qla_host_t *, fc_port_t *);
@@ -94,6 +98,13 @@ extern uint8_t qla27xx_find_valid_image(struct scsi_qla_host *);
 extern struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *,
 	int, int);
 extern int qla2xxx_delete_qpair(struct scsi_qla_host *, struct qla_qpair *);
+void qla2x00_fcport_event_handler(scsi_qla_host_t *, struct event_arg *);
+int qla24xx_async_gpdb(struct scsi_qla_host *, fc_port_t *, u8);
+int qla24xx_async_notify_ack(scsi_qla_host_t *, fc_port_t *,
+	struct imm_ntfy_from_isp *, int);
+int qla24xx_post_newsess_work(struct scsi_qla_host *, port_id_t *, u8 *,
+    void *);
+int qla24xx_fcport_handle_login(struct scsi_qla_host *, fc_port_t *);
 
 /*
  * Global Data in qla_os.c source file.
@@ -135,8 +146,6 @@ extern int qla2x00_post_aen_work(struct scsi_qla_host *, enum
 extern int qla2x00_post_idc_ack_work(struct scsi_qla_host *, uint16_t *);
 extern int qla2x00_post_async_login_work(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
-extern int qla2x00_post_async_login_done_work(struct scsi_qla_host *,
-    fc_port_t *, uint16_t *);
 extern int qla2x00_post_async_logout_work(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
 extern int qla2x00_post_async_logout_done_work(struct scsi_qla_host *,
@@ -179,6 +188,10 @@ extern void qla2x00_disable_board_on_pci_error(struct work_struct *);
 extern void qla2x00_sp_compl(void *, void *, int);
 extern void qla2xxx_qpair_sp_free_dma(void *, void *);
 extern void qla2xxx_qpair_sp_compl(void *, void *, int);
+extern int qla24xx_post_upd_fcport_work(struct scsi_qla_host *, fc_port_t *);
+void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *,
+	uint16_t *);
+int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *);
 
 /*
  * Global Functions in qla_mid.c source file.
@@ -301,9 +314,6 @@ qla2x00_get_retry_cnt(scsi_qla_host_t *, uint8_t *, uint8_t *, uint16_t *);
 extern int
 qla2x00_init_firmware(scsi_qla_host_t *, uint16_t);
 
-extern int
-qla2x00_get_node_name_list(scsi_qla_host_t *, void **, int *);
-
 extern int
 qla2x00_get_port_database(scsi_qla_host_t *, fc_port_t *, uint8_t);
 
@@ -483,6 +493,9 @@ qla2x00_process_completed_request(struct scsi_qla_host *, struct req_que *,
 	uint32_t);
 extern irqreturn_t
 qla2xxx_msix_rsp_q(int irq, void *dev_id);
+fc_port_t *qla2x00_find_fcport_by_loopid(scsi_qla_host_t *, uint16_t);
+fc_port_t *qla2x00_find_fcport_by_wwpn(scsi_qla_host_t *, u8 *, u8);
+fc_port_t *qla2x00_find_fcport_by_nportid(scsi_qla_host_t *, port_id_t *, u8);
 
 /*
  * Global Function Prototypes in qla_sup.c source file.
@@ -574,8 +587,8 @@ extern void qla2xxx_dump_post_process(scsi_qla_host_t *, int);
 /*
  * Global Function Prototypes in qla_gs.c source file.
  */
-extern void *qla2x00_prep_ms_iocb(scsi_qla_host_t *, uint32_t, uint32_t);
-extern void *qla24xx_prep_ms_iocb(scsi_qla_host_t *, uint32_t, uint32_t);
+extern void *qla2x00_prep_ms_iocb(scsi_qla_host_t *, struct ct_arg *);
+extern void *qla24xx_prep_ms_iocb(scsi_qla_host_t *, struct ct_arg *);
 extern int qla2x00_ga_nxt(scsi_qla_host_t *, fc_port_t *);
 extern int qla2x00_gid_pt(scsi_qla_host_t *, sw_info_t *);
 extern int qla2x00_gpn_id(scsi_qla_host_t *, sw_info_t *);
@@ -591,6 +604,23 @@ extern int qla2x00_fdmi_register(scsi_qla_host_t *);
 extern int qla2x00_gfpn_id(scsi_qla_host_t *, sw_info_t *);
 extern int qla2x00_gpsc(scsi_qla_host_t *, sw_info_t *);
 extern void qla2x00_get_sym_node_name(scsi_qla_host_t *, uint8_t *, size_t);
+extern int qla2x00_chk_ms_status(scsi_qla_host_t *, ms_iocb_entry_t *,
+	struct ct_sns_rsp *, const char *);
+extern void qla2x00_async_iocb_timeout(void *data);
+extern int qla24xx_async_gidpn(scsi_qla_host_t *, fc_port_t *);
+int qla24xx_post_gidpn_work(struct scsi_qla_host *, fc_port_t *);
+void qla24xx_handle_gidpn_event(scsi_qla_host_t *, struct event_arg *);
+
+extern void qla2x00_free_fcport(fc_port_t *);
+
+extern int qla24xx_post_gpnid_work(struct scsi_qla_host *, port_id_t *);
+extern int qla24xx_async_gpnid(scsi_qla_host_t *, port_id_t *);
+void qla24xx_async_gpnid_done(scsi_qla_host_t *, srb_t*);
+void qla24xx_handle_gpnid_event(scsi_qla_host_t *, struct event_arg *);
+
+int qla24xx_post_gpsc_work(struct scsi_qla_host *, fc_port_t *);
+int qla24xx_async_gpsc(scsi_qla_host_t *, fc_port_t *);
+int qla2x00_mgmt_svr_login(scsi_qla_host_t *);
 
 /*
  * Global Function Prototypes in qla_attr.c source file.
@@ -803,4 +833,16 @@ extern int qla_get_exchoffld_status(scsi_qla_host_t *, uint16_t *, uint16_t *);
 extern int qla_set_exchoffld_mem_cfg(scsi_qla_host_t *, dma_addr_t);
 extern void qlt_handle_abts_recv(struct scsi_qla_host *, response_t *);
 
+int qla24xx_async_notify_ack(scsi_qla_host_t *, fc_port_t *,
+	struct imm_ntfy_from_isp *, int);
+void qla24xx_do_nack_work(struct scsi_qla_host *, struct qla_work_evt *);
+void qlt_plogi_ack_link(struct scsi_qla_host *, struct qlt_plogi_ack_t *,
+	struct fc_port *, enum qlt_plogi_link_t);
+void qlt_plogi_ack_unref(struct scsi_qla_host *, struct qlt_plogi_ack_t *);
+extern void qlt_schedule_sess_for_deletion(struct fc_port *, bool);
+extern void qlt_schedule_sess_for_deletion_lock(struct fc_port *);
+extern struct fc_port *qlt_find_sess_invalidate_other(scsi_qla_host_t *,
+	uint64_t wwn, port_id_t port_id, uint16_t loop_id, struct fc_port **);
+void qla24xx_delete_sess_fn(struct work_struct *);
+
 #endif /* _QLA_GBL_H */
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 94e8a8592f69..8f7054dc742b 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -24,12 +24,12 @@ static int qla2x00_sns_rnn_id(scsi_qla_host_t *);
  * Returns a pointer to the @ha's ms_iocb.
  */
 void *
-qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size)
+qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, struct ct_arg *arg)
 {
 	struct qla_hw_data *ha = vha->hw;
 	ms_iocb_entry_t *ms_pkt;
 
-	ms_pkt = ha->ms_iocb;
+	ms_pkt = (ms_iocb_entry_t *)arg->iocb;
 	memset(ms_pkt, 0, sizeof(ms_iocb_entry_t));
 
 	ms_pkt->entry_type = MS_IOCB_TYPE;
@@ -39,15 +39,15 @@ qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size)
 	ms_pkt->timeout = cpu_to_le16(ha->r_a_tov / 10 * 2);
 	ms_pkt->cmd_dsd_count = cpu_to_le16(1);
 	ms_pkt->total_dsd_count = cpu_to_le16(2);
-	ms_pkt->rsp_bytecount = cpu_to_le32(rsp_size);
-	ms_pkt->req_bytecount = cpu_to_le32(req_size);
+	ms_pkt->rsp_bytecount = cpu_to_le32(arg->rsp_size);
+	ms_pkt->req_bytecount = cpu_to_le32(arg->req_size);
 
-	ms_pkt->dseg_req_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma));
-	ms_pkt->dseg_req_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma));
+	ms_pkt->dseg_req_address[0] = cpu_to_le32(LSD(arg->req_dma));
+	ms_pkt->dseg_req_address[1] = cpu_to_le32(MSD(arg->req_dma));
 	ms_pkt->dseg_req_length = ms_pkt->req_bytecount;
 
-	ms_pkt->dseg_rsp_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma));
-	ms_pkt->dseg_rsp_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma));
+	ms_pkt->dseg_rsp_address[0] = cpu_to_le32(LSD(arg->rsp_dma));
+	ms_pkt->dseg_rsp_address[1] = cpu_to_le32(MSD(arg->rsp_dma));
 	ms_pkt->dseg_rsp_length = ms_pkt->rsp_bytecount;
 
 	vha->qla_stats.control_requests++;
@@ -64,29 +64,29 @@ qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size)
  * Returns a pointer to the @ha's ms_iocb.
  */
 void *
-qla24xx_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size)
+qla24xx_prep_ms_iocb(scsi_qla_host_t *vha, struct ct_arg *arg)
 {
 	struct qla_hw_data *ha = vha->hw;
 	struct ct_entry_24xx *ct_pkt;
 
-	ct_pkt = (struct ct_entry_24xx *)ha->ms_iocb;
+	ct_pkt = (struct ct_entry_24xx *)arg->iocb;
 	memset(ct_pkt, 0, sizeof(struct ct_entry_24xx));
 
 	ct_pkt->entry_type = CT_IOCB_TYPE;
 	ct_pkt->entry_count = 1;
-	ct_pkt->nport_handle = cpu_to_le16(NPH_SNS);
+	ct_pkt->nport_handle = cpu_to_le16(arg->nport_handle);
 	ct_pkt->timeout = cpu_to_le16(ha->r_a_tov / 10 * 2);
 	ct_pkt->cmd_dsd_count = cpu_to_le16(1);
 	ct_pkt->rsp_dsd_count = cpu_to_le16(1);
-	ct_pkt->rsp_byte_count = cpu_to_le32(rsp_size);
-	ct_pkt->cmd_byte_count = cpu_to_le32(req_size);
+	ct_pkt->rsp_byte_count = cpu_to_le32(arg->rsp_size);
+	ct_pkt->cmd_byte_count = cpu_to_le32(arg->req_size);
 
-	ct_pkt->dseg_0_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma));
-	ct_pkt->dseg_0_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma));
+	ct_pkt->dseg_0_address[0] = cpu_to_le32(LSD(arg->req_dma));
+	ct_pkt->dseg_0_address[1] = cpu_to_le32(MSD(arg->req_dma));
 	ct_pkt->dseg_0_len = ct_pkt->cmd_byte_count;
 
-	ct_pkt->dseg_1_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma));
-	ct_pkt->dseg_1_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma));
+	ct_pkt->dseg_1_address[0] = cpu_to_le32(LSD(arg->rsp_dma));
+	ct_pkt->dseg_1_address[1] = cpu_to_le32(MSD(arg->rsp_dma));
 	ct_pkt->dseg_1_len = ct_pkt->rsp_byte_count;
 	ct_pkt->vp_index = vha->vp_idx;
 
@@ -117,7 +117,7 @@ qla2x00_prep_ct_req(struct ct_sns_pkt *p, uint16_t cmd, uint16_t rsp_size)
 	return &p->p.req;
 }
 
-static int
+int
 qla2x00_chk_ms_status(scsi_qla_host_t *vha, ms_iocb_entry_t *ms_pkt,
     struct ct_sns_rsp *ct_rsp, const char *routine)
 {
@@ -183,14 +183,21 @@ qla2x00_ga_nxt(scsi_qla_host_t *vha, fc_port_t *fcport)
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
 	struct qla_hw_data *ha = vha->hw;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return qla2x00_sns_ga_nxt(vha, fcport);
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = GA_NXT_REQ_SIZE;
+	arg.rsp_size = GA_NXT_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	/* Issue GA_NXT */
 	/* Prepare common MS IOCB */
-	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GA_NXT_REQ_SIZE,
-	    GA_NXT_RSP_SIZE);
+	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 	/* Prepare CT request */
 	ct_req = qla2x00_prep_ct_req(ha->ct_sns, GA_NXT_CMD,
@@ -269,16 +276,24 @@ qla2x00_gid_pt(scsi_qla_host_t *vha, sw_info_t *list)
 	struct ct_sns_gid_pt_data *gid_data;
 	struct qla_hw_data *ha = vha->hw;
 	uint16_t gid_pt_rsp_size;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return qla2x00_sns_gid_pt(vha, list);
 
 	gid_data = NULL;
 	gid_pt_rsp_size = qla2x00_gid_pt_rsp_size(vha);
+
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = GID_PT_REQ_SIZE;
+	arg.rsp_size = gid_pt_rsp_size;
+	arg.nport_handle = NPH_SNS;
+
 	/* Issue GID_PT */
 	/* Prepare common MS IOCB */
-	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GID_PT_REQ_SIZE,
-	    gid_pt_rsp_size);
+	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 	/* Prepare CT request */
 	ct_req = qla2x00_prep_ct_req(ha->ct_sns, GID_PT_CMD, gid_pt_rsp_size);
@@ -344,15 +359,22 @@ qla2x00_gpn_id(scsi_qla_host_t *vha, sw_info_t *list)
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
 	struct qla_hw_data *ha = vha->hw;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return qla2x00_sns_gpn_id(vha, list);
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = GPN_ID_REQ_SIZE;
+	arg.rsp_size = GPN_ID_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	for (i = 0; i < ha->max_fibre_devices; i++) {
 		/* Issue GPN_ID */
 		/* Prepare common MS IOCB */
-		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GPN_ID_REQ_SIZE,
-		    GPN_ID_RSP_SIZE);
+		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 		/* Prepare CT request */
 		ct_req = qla2x00_prep_ct_req(ha->ct_sns, GPN_ID_CMD,
@@ -406,15 +428,22 @@ qla2x00_gnn_id(scsi_qla_host_t *vha, sw_info_t *list)
 	ms_iocb_entry_t	*ms_pkt;
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return qla2x00_sns_gnn_id(vha, list);
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = GNN_ID_REQ_SIZE;
+	arg.rsp_size = GNN_ID_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	for (i = 0; i < ha->max_fibre_devices; i++) {
 		/* Issue GNN_ID */
 		/* Prepare common MS IOCB */
-		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GNN_ID_REQ_SIZE,
-		    GNN_ID_RSP_SIZE);
+		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 		/* Prepare CT request */
 		ct_req = qla2x00_prep_ct_req(ha->ct_sns, GNN_ID_CMD,
@@ -473,14 +502,21 @@ qla2x00_rft_id(scsi_qla_host_t *vha)
 	ms_iocb_entry_t	*ms_pkt;
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return qla2x00_sns_rft_id(vha);
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = RFT_ID_REQ_SIZE;
+	arg.rsp_size = RFT_ID_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	/* Issue RFT_ID */
 	/* Prepare common MS IOCB */
-	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, RFT_ID_REQ_SIZE,
-	    RFT_ID_RSP_SIZE);
+	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 	/* Prepare CT request */
 	ct_req = qla2x00_prep_ct_req(ha->ct_sns, RFT_ID_CMD,
@@ -526,6 +562,7 @@ qla2x00_rff_id(scsi_qla_host_t *vha)
 	ms_iocb_entry_t	*ms_pkt;
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha)) {
 		ql_dbg(ql_dbg_disc, vha, 0x2046,
@@ -533,10 +570,16 @@ qla2x00_rff_id(scsi_qla_host_t *vha)
 		return (QLA_SUCCESS);
 	}
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = RFF_ID_REQ_SIZE;
+	arg.rsp_size = RFF_ID_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	/* Issue RFF_ID */
 	/* Prepare common MS IOCB */
-	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, RFF_ID_REQ_SIZE,
-	    RFF_ID_RSP_SIZE);
+	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 	/* Prepare CT request */
 	ct_req = qla2x00_prep_ct_req(ha->ct_sns, RFF_ID_CMD,
@@ -584,14 +627,21 @@ qla2x00_rnn_id(scsi_qla_host_t *vha)
 	ms_iocb_entry_t	*ms_pkt;
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return qla2x00_sns_rnn_id(vha);
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = RNN_ID_REQ_SIZE;
+	arg.rsp_size = RNN_ID_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	/* Issue RNN_ID */
 	/* Prepare common MS IOCB */
-	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, RNN_ID_REQ_SIZE,
-	    RNN_ID_RSP_SIZE);
+	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 	/* Prepare CT request */
 	ct_req = qla2x00_prep_ct_req(ha->ct_sns, RNN_ID_CMD, RNN_ID_RSP_SIZE);
@@ -651,6 +701,7 @@ qla2x00_rsnn_nn(scsi_qla_host_t *vha)
 	ms_iocb_entry_t	*ms_pkt;
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
+	struct ct_arg arg;
 
 	if (IS_QLA2100(ha) || IS_QLA2200(ha)) {
 		ql_dbg(ql_dbg_disc, vha, 0x2050,
@@ -658,10 +709,17 @@ qla2x00_rsnn_nn(scsi_qla_host_t *vha)
 		return (QLA_SUCCESS);
 	}
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = 0;
+	arg.rsp_size = RSNN_NN_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	/* Issue RSNN_NN */
 	/* Prepare common MS IOCB */
 	/*   Request size adjusted after CT preparation */
-	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, 0, RSNN_NN_RSP_SIZE);
+	ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 	/* Prepare CT request */
 	ct_req = qla2x00_prep_ct_req(ha->ct_sns, RSNN_NN_CMD,
@@ -1103,7 +1161,7 @@ qla2x00_sns_rnn_id(scsi_qla_host_t *vha)
  *
  * Returns 0 on success.
  */
-static int
+int
 qla2x00_mgmt_svr_login(scsi_qla_host_t *vha)
 {
 	int ret, rval;
@@ -2425,15 +2483,22 @@ qla2x00_gfpn_id(scsi_qla_host_t *vha, sw_info_t *list)
 	ms_iocb_entry_t	*ms_pkt;
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
+	struct ct_arg arg;
 
 	if (!IS_IIDMA_CAPABLE(ha))
 		return QLA_FUNCTION_FAILED;
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = GFPN_ID_REQ_SIZE;
+	arg.rsp_size = GFPN_ID_RSP_SIZE;
+	arg.nport_handle = NPH_SNS;
+
 	for (i = 0; i < ha->max_fibre_devices; i++) {
 		/* Issue GFPN_ID */
 		/* Prepare common MS IOCB */
-		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GFPN_ID_REQ_SIZE,
-		    GFPN_ID_RSP_SIZE);
+		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 		/* Prepare CT request */
 		ct_req = qla2x00_prep_ct_req(ha->ct_sns, GFPN_ID_CMD,
@@ -2471,36 +2536,6 @@ qla2x00_gfpn_id(scsi_qla_host_t *vha, sw_info_t *list)
 	return (rval);
 }
 
-static inline void *
-qla24xx_prep_ms_fm_iocb(scsi_qla_host_t *vha, uint32_t req_size,
-    uint32_t rsp_size)
-{
-	struct ct_entry_24xx *ct_pkt;
-	struct qla_hw_data *ha = vha->hw;
-	ct_pkt = (struct ct_entry_24xx *)ha->ms_iocb;
-	memset(ct_pkt, 0, sizeof(struct ct_entry_24xx));
-
-	ct_pkt->entry_type = CT_IOCB_TYPE;
-	ct_pkt->entry_count = 1;
-	ct_pkt->nport_handle = cpu_to_le16(vha->mgmt_svr_loop_id);
-	ct_pkt->timeout = cpu_to_le16(ha->r_a_tov / 10 * 2);
-	ct_pkt->cmd_dsd_count = cpu_to_le16(1);
-	ct_pkt->rsp_dsd_count = cpu_to_le16(1);
-	ct_pkt->rsp_byte_count = cpu_to_le32(rsp_size);
-	ct_pkt->cmd_byte_count = cpu_to_le32(req_size);
-
-	ct_pkt->dseg_0_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma));
-	ct_pkt->dseg_0_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma));
-	ct_pkt->dseg_0_len = ct_pkt->cmd_byte_count;
-
-	ct_pkt->dseg_1_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma));
-	ct_pkt->dseg_1_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma));
-	ct_pkt->dseg_1_len = ct_pkt->rsp_byte_count;
-	ct_pkt->vp_index = vha->vp_idx;
-
-	return ct_pkt;
-}
-
 
 static inline struct ct_sns_req *
 qla24xx_prep_ct_fm_req(struct ct_sns_pkt *p, uint16_t cmd,
@@ -2530,9 +2565,10 @@ qla2x00_gpsc(scsi_qla_host_t *vha, sw_info_t *list)
 	int		rval;
 	uint16_t	i;
 	struct qla_hw_data *ha = vha->hw;
-	ms_iocb_entry_t	*ms_pkt;
+	ms_iocb_entry_t *ms_pkt;
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
+	struct ct_arg arg;
 
 	if (!IS_IIDMA_CAPABLE(ha))
 		return QLA_FUNCTION_FAILED;
@@ -2543,11 +2579,17 @@ qla2x00_gpsc(scsi_qla_host_t *vha, sw_info_t *list)
 	if (rval)
 		return rval;
 
+	arg.iocb = ha->ms_iocb;
+	arg.req_dma = ha->ct_sns_dma;
+	arg.rsp_dma = ha->ct_sns_dma;
+	arg.req_size = GPSC_REQ_SIZE;
+	arg.rsp_size = GPSC_RSP_SIZE;
+	arg.nport_handle = vha->mgmt_svr_loop_id;
+
 	for (i = 0; i < ha->max_fibre_devices; i++) {
 		/* Issue GFPN_ID */
 		/* Prepare common MS IOCB */
-		ms_pkt = qla24xx_prep_ms_fm_iocb(vha, GPSC_REQ_SIZE,
-		    GPSC_RSP_SIZE);
+		ms_pkt = qla24xx_prep_ms_iocb(vha, &arg);
 
 		/* Prepare CT request */
 		ct_req = qla24xx_prep_ct_fm_req(ha->ct_sns, GPSC_CMD,
@@ -2641,6 +2683,7 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list)
 	struct ct_sns_rsp	*ct_rsp;
 	struct qla_hw_data *ha = vha->hw;
 	uint8_t fcp_scsi_features = 0;
+	struct ct_arg arg;
 
 	for (i = 0; i < ha->max_fibre_devices; i++) {
 		/* Set default FC4 Type as UNKNOWN so the default is to
@@ -2651,9 +2694,15 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list)
 		if (!IS_FWI2_CAPABLE(ha))
 			continue;
 
+		arg.iocb = ha->ms_iocb;
+		arg.req_dma = ha->ct_sns_dma;
+		arg.rsp_dma = ha->ct_sns_dma;
+		arg.req_size = GFF_ID_REQ_SIZE;
+		arg.rsp_size = GFF_ID_RSP_SIZE;
+		arg.nport_handle = NPH_SNS;
+
 		/* Prepare common MS IOCB */
-		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GFF_ID_REQ_SIZE,
-		    GFF_ID_RSP_SIZE);
+		ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg);
 
 		/* Prepare CT request */
 		ct_req = qla2x00_prep_ct_req(ha->ct_sns, GFF_ID_CMD,
@@ -2692,3 +2741,536 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list)
 			break;
 	}
 }
+
+/* GID_PN completion processing. */
+void qla24xx_handle_gidpn_event(scsi_qla_host_t *vha, struct event_arg *ea)
+{
+	fc_port_t *fcport = ea->fcport;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"%s %8phC login state %d \n",
+		__func__, fcport->port_name, fcport->fw_login_state);
+
+	if (ea->sp->gen2 != fcport->login_gen) {
+		/* PLOGI/PRLI/LOGO came in while cmd was out.*/
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+		    "%s %8phC generation changed rscn %d|%d login %d|%d \n",
+		    __func__, fcport->port_name, fcport->last_rscn_gen,
+		    fcport->rscn_gen, fcport->last_login_gen, fcport->login_gen);
+		return;
+	}
+
+	if (!ea->rc) {
+		if (ea->sp->gen1 == fcport->rscn_gen) {
+			fcport->scan_state = QLA_FCPORT_FOUND;
+			fcport->flags |= FCF_FABRIC_DEVICE;
+
+			if (fcport->d_id.b24 == ea->id.b24) {
+				/* cable plugged into the same place */
+				switch (vha->host->active_mode) {
+				case MODE_TARGET:
+					/* NOOP. let the other guy login to us.*/
+					break;
+				case MODE_INITIATOR:
+				case MODE_DUAL:
+				default:
+					if (atomic_read(&fcport->state) ==
+					    FCS_ONLINE)
+						break;
+					ql_dbg(ql_dbg_disc, vha, 0xffff,
+					    "%s %d %8phC post gnl\n",
+					    __func__, __LINE__, fcport->port_name);
+					qla24xx_post_gnl_work(vha, fcport);
+					break;
+				}
+			} else { /* fcport->d_id.b24 != ea->id.b24 */
+				fcport->d_id.b24 = ea->id.b24;
+				if (fcport->deleted == QLA_SESS_DELETED) {
+					ql_dbg(ql_dbg_disc, vha, 0xffff,
+					    "%s %d %8phC post del sess\n",
+					    __func__, __LINE__, fcport->port_name);
+					qlt_schedule_sess_for_deletion_lock(fcport);
+				}
+			}
+		} else { /* ea->sp->gen1 != fcport->rscn_gen */
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "%s %d %8phC post gidpn\n",
+			    __func__, __LINE__, fcport->port_name);
+			/* rscn came in while cmd was out */
+			qla24xx_post_gidpn_work(vha, fcport);
+		}
+	} else { /* ea->rc */
+		/* cable pulled */
+		if (ea->sp->gen1 == fcport->rscn_gen) {
+			if (ea->sp->gen2 == fcport->login_gen) {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "%s %d %8phC post del sess\n", __func__,
+				    __LINE__, fcport->port_name);
+				qlt_schedule_sess_for_deletion_lock(fcport);
+			} else {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "%s %d %8phC login\n", __func__, __LINE__,
+				    fcport->port_name);
+				qla24xx_fcport_handle_login(vha, fcport);
+			}
+		} else {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "%s %d %8phC post gidpn\n", __func__, __LINE__,
+			    fcport->port_name);
+			qla24xx_post_gidpn_work(vha, fcport);
+		}
+	}
+} /* gidpn_event */
+
+static void qla2x00_async_gidpn_sp_done(void *v, void *s, int res)
+{
+	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
+	struct srb *sp = (struct srb *)s;
+	fc_port_t *fcport = sp->fcport;
+	u8 *id = fcport->ct_desc.ct_sns->p.rsp.rsp.gid_pn.port_id;
+	struct event_arg ea;
+
+	fcport->flags &= ~FCF_ASYNC_SENT;
+
+	memset(&ea, 0, sizeof(ea));
+	ea.fcport = fcport;
+	ea.id.b.domain = id[0];
+	ea.id.b.area = id[1];
+	ea.id.b.al_pa = id[2];
+	ea.sp = sp;
+	ea.rc = res;
+	ea.event = FCME_GIDPN_DONE;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "Async done-%s res %x, WWPN %8phC ID %3phC \n",
+	    sp->name, res, fcport->port_name, id);
+
+	qla2x00_fcport_event_handler(vha, &ea);
+
+	sp->free(vha, sp);
+}
+
+int qla24xx_async_gidpn(scsi_qla_host_t *vha, fc_port_t *fcport)
+{
+	int rval = QLA_FUNCTION_FAILED;
+	struct ct_sns_req       *ct_req;
+	srb_t *sp;
+
+	if (!vha->flags.online)
+		goto done;
+
+	fcport->flags |= FCF_ASYNC_SENT;
+	fcport->disc_state = DSC_GID_PN;
+	fcport->scan_state = QLA_FCPORT_SCAN;
+	sp = qla2x00_get_sp(vha, fcport, GFP_ATOMIC);
+	if (!sp)
+		goto done;
+
+	sp->type = SRB_CT_PTHRU_CMD;
+	sp->name = "gidpn";
+	sp->gen1 = fcport->rscn_gen;
+	sp->gen2 = fcport->login_gen;
+
+	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
+
+	/* CT_IU preamble  */
+	ct_req = qla2x00_prep_ct_req(fcport->ct_desc.ct_sns, GID_PN_CMD,
+		GID_PN_RSP_SIZE);
+
+	/* GIDPN req */
+	memcpy(ct_req->req.gid_pn.port_name, fcport->port_name,
+		WWN_SIZE);
+
+	/* req & rsp use the same buffer */
+	sp->u.iocb_cmd.u.ctarg.req = fcport->ct_desc.ct_sns;
+	sp->u.iocb_cmd.u.ctarg.req_dma = fcport->ct_desc.ct_sns_dma;
+	sp->u.iocb_cmd.u.ctarg.rsp = fcport->ct_desc.ct_sns;
+	sp->u.iocb_cmd.u.ctarg.rsp_dma = fcport->ct_desc.ct_sns_dma;
+	sp->u.iocb_cmd.u.ctarg.req_size = GID_PN_REQ_SIZE;
+	sp->u.iocb_cmd.u.ctarg.rsp_size = GID_PN_RSP_SIZE;
+	sp->u.iocb_cmd.u.ctarg.nport_handle = NPH_SNS;
+
+	sp->u.iocb_cmd.timeout = qla2x00_async_iocb_timeout;
+	sp->done = qla2x00_async_gidpn_sp_done;
+
+	rval = qla2x00_start_sp(sp);
+	if (rval != QLA_SUCCESS)
+		goto done_free_sp;
+
+	ql_dbg(ql_dbg_disc, vha, 0x206f,
+		"Async-%s - %8phC hdl=%x loopid=%x portid %02x%02x%02x.\n",
+		sp->name, fcport->port_name,
+		sp->handle, fcport->loop_id, fcport->d_id.b.domain,
+		fcport->d_id.b.area, fcport->d_id.b.al_pa);
+	return rval;
+
+done_free_sp:
+	sp->free(vha, sp);
+done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
+	return rval;
+}
+
+int qla24xx_post_gidpn_work(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	struct qla_work_evt *e;
+
+	if ((atomic_read(&vha->loop_state) != LOOP_READY) ||
+		test_bit(UNLOADING, &vha->dpc_flags))
+		return 0;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_GIDPN);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.fcport.fcport = fcport;
+	return qla2x00_post_work(vha, e);
+}
+
+int qla24xx_post_gpsc_work(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	struct qla_work_evt *e;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_GPSC);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.fcport.fcport = fcport;
+	return qla2x00_post_work(vha, e);
+}
+
+static void qla24xx_async_gpsc_sp_done(void *v, void *s, int res)
+{
+	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
+	struct qla_hw_data *ha = vha->hw;
+	struct srb *sp = (struct srb *)s;
+	fc_port_t *fcport = sp->fcport;
+	struct ct_sns_rsp       *ct_rsp;
+	struct event_arg ea;
+
+	ct_rsp = &fcport->ct_desc.ct_sns->p.rsp;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "Async done-%s res %x, WWPN %8phC \n",
+	    sp->name, res, fcport->port_name);
+
+	fcport->flags &= ~FCF_ASYNC_SENT;
+
+	if (res == (DID_ERROR << 16)) {
+		/* entry status error */
+		goto done;
+	} else if (res) {
+		if ((ct_rsp->header.reason_code ==
+			 CT_REASON_INVALID_COMMAND_CODE) ||
+			(ct_rsp->header.reason_code ==
+			 CT_REASON_COMMAND_UNSUPPORTED)) {
+			ql_dbg(ql_dbg_disc, vha, 0x205a,
+				"GPSC command unsupported, disabling "
+				"query.\n");
+			ha->flags.gpsc_supported = 0;
+			res = QLA_SUCCESS;
+		}
+	} else {
+		switch (be16_to_cpu(ct_rsp->rsp.gpsc.speed)) {
+		case BIT_15:
+			fcport->fp_speed = PORT_SPEED_1GB;
+			break;
+		case BIT_14:
+			fcport->fp_speed = PORT_SPEED_2GB;
+			break;
+		case BIT_13:
+			fcport->fp_speed = PORT_SPEED_4GB;
+			break;
+		case BIT_12:
+			fcport->fp_speed = PORT_SPEED_10GB;
+			break;
+		case BIT_11:
+			fcport->fp_speed = PORT_SPEED_8GB;
+			break;
+		case BIT_10:
+			fcport->fp_speed = PORT_SPEED_16GB;
+			break;
+		case BIT_8:
+			fcport->fp_speed = PORT_SPEED_32GB;
+			break;
+		}
+
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async-%s OUT WWPN %8phC speeds=%04x speed=%04x.\n",
+			sp->name,
+			fcport->fabric_port_name,
+			be16_to_cpu(ct_rsp->rsp.gpsc.speeds),
+			be16_to_cpu(ct_rsp->rsp.gpsc.speed));
+	}
+done:
+	memset(&ea, 0, sizeof(ea));
+	ea.event = FCME_GPSC_DONE;
+	ea.rc = res;
+	ea.fcport = fcport;
+	qla2x00_fcport_event_handler(vha, &ea);
+
+	sp->free(vha, sp);
+}
+
+int qla24xx_async_gpsc(scsi_qla_host_t *vha, fc_port_t *fcport)
+{
+	int rval = QLA_FUNCTION_FAILED;
+	struct ct_sns_req       *ct_req;
+	srb_t *sp;
+
+	if (!vha->flags.online)
+		goto done;
+
+	fcport->flags |= FCF_ASYNC_SENT;
+	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
+	if (!sp)
+		goto done;
+
+	sp->type = SRB_CT_PTHRU_CMD;
+	sp->name = "gpsc";
+	sp->gen1 = fcport->rscn_gen;
+	sp->gen2 = fcport->login_gen;
+
+	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
+
+	/* CT_IU preamble  */
+	ct_req = qla24xx_prep_ct_fm_req(fcport->ct_desc.ct_sns, GPSC_CMD,
+		GPSC_RSP_SIZE);
+
+	/* GPSC req */
+	memcpy(ct_req->req.gpsc.port_name, fcport->port_name,
+		WWN_SIZE);
+
+	sp->u.iocb_cmd.u.ctarg.req = fcport->ct_desc.ct_sns;
+	sp->u.iocb_cmd.u.ctarg.req_dma = fcport->ct_desc.ct_sns_dma;
+	sp->u.iocb_cmd.u.ctarg.rsp = fcport->ct_desc.ct_sns;
+	sp->u.iocb_cmd.u.ctarg.rsp_dma = fcport->ct_desc.ct_sns_dma;
+	sp->u.iocb_cmd.u.ctarg.req_size = GPSC_REQ_SIZE;
+	sp->u.iocb_cmd.u.ctarg.rsp_size = GPSC_RSP_SIZE;
+	sp->u.iocb_cmd.u.ctarg.nport_handle = vha->mgmt_svr_loop_id;
+
+	sp->u.iocb_cmd.timeout = qla2x00_async_iocb_timeout;
+	sp->done = qla24xx_async_gpsc_sp_done;
+
+	rval = qla2x00_start_sp(sp);
+	if (rval != QLA_SUCCESS)
+		goto done_free_sp;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async-%s %8phC hdl=%x loopid=%x portid=%02x%02x%02x.\n",
+		sp->name, fcport->port_name, sp->handle,
+		fcport->loop_id, fcport->d_id.b.domain,
+		fcport->d_id.b.area, fcport->d_id.b.al_pa);
+	return rval;
+
+done_free_sp:
+	sp->free(vha, sp);
+done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
+	return rval;
+}
+
+int qla24xx_post_gpnid_work(struct scsi_qla_host *vha, port_id_t *id)
+{
+	struct qla_work_evt *e;
+
+	if (test_bit(UNLOADING, &vha->dpc_flags))
+		return 0;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_GPNID);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.gpnid.id = *id;
+	return qla2x00_post_work(vha, e);
+}
+
+void qla24xx_async_gpnid_done(scsi_qla_host_t *vha, srb_t *sp)
+{
+	if (sp->u.iocb_cmd.u.ctarg.req) {
+		dma_free_coherent(&vha->hw->pdev->dev,
+			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.req,
+			sp->u.iocb_cmd.u.ctarg.req_dma);
+		sp->u.iocb_cmd.u.ctarg.req = NULL;
+	}
+	if (sp->u.iocb_cmd.u.ctarg.rsp) {
+		dma_free_coherent(&vha->hw->pdev->dev,
+			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.rsp,
+			sp->u.iocb_cmd.u.ctarg.rsp_dma);
+		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+	}
+
+	sp->free(vha, sp);
+}
+
+void qla24xx_handle_gpnid_event(scsi_qla_host_t *vha, struct event_arg *ea)
+{
+	fc_port_t *fcport;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	fcport = qla2x00_find_fcport_by_wwpn(vha, ea->port_name, 1);
+	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+	if (fcport) {
+		/* cable moved. just plugged in */
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post del sess\n",
+			   __func__, __LINE__, fcport->port_name);
+
+		fcport->rscn_gen++;
+		fcport->d_id = ea->id;
+		fcport->scan_state = QLA_FCPORT_FOUND;
+		fcport->flags |= FCF_FABRIC_DEVICE;
+
+		qlt_schedule_sess_for_deletion_lock(fcport);
+	} else {
+		/* create new fcport */
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post new sess\n",
+			   __func__, __LINE__, ea->port_name);
+
+		qla24xx_post_newsess_work(vha, &ea->id, ea->port_name, NULL);
+	}
+}
+
+static void qla2x00_async_gpnid_sp_done(void *v, void *s, int res)
+{
+	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
+	struct srb *sp = (struct srb *)s;
+	struct ct_sns_req *ct_req =
+	    (struct ct_sns_req *)sp->u.iocb_cmd.u.ctarg.req;
+	struct ct_sns_rsp *ct_rsp =
+	    (struct ct_sns_rsp *)sp->u.iocb_cmd.u.ctarg.rsp;
+	struct event_arg ea;
+	struct qla_work_evt *e;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async done-%s res %x ID %3phC. %8phC\n",
+		sp->name, res, ct_req->req.port_id.port_id,
+		ct_rsp->rsp.gpn_id.port_name);
+
+	memset(&ea, 0, sizeof(ea));
+	memcpy(ea.port_name, ct_rsp->rsp.gpn_id.port_name, WWN_SIZE);
+	ea.sp = sp;
+	ea.id.b.domain = ct_req->req.port_id.port_id[0];
+	ea.id.b.area = ct_req->req.port_id.port_id[1];
+	ea.id.b.al_pa = ct_req->req.port_id.port_id[2];
+	ea.rc = res;
+	ea.event = FCME_GPNID_DONE;
+
+	qla2x00_fcport_event_handler(vha, &ea);
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_GPNID_DONE);
+	if (!e) {
+		/* please ignore kernel warning. otherwise, we have mem leak. */
+		if (sp->u.iocb_cmd.u.ctarg.req) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+				sizeof(struct ct_sns_pkt),
+				sp->u.iocb_cmd.u.ctarg.req,
+				sp->u.iocb_cmd.u.ctarg.req_dma);
+			sp->u.iocb_cmd.u.ctarg.req = NULL;
+		}
+		if (sp->u.iocb_cmd.u.ctarg.rsp) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+				sizeof(struct ct_sns_pkt),
+				sp->u.iocb_cmd.u.ctarg.rsp,
+				sp->u.iocb_cmd.u.ctarg.rsp_dma);
+			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+		}
+
+		sp->free(vha, sp);
+		return;
+	}
+
+	e->u.iosb.sp = sp;
+	qla2x00_post_work(vha, e);
+}
+
+/* Get WWPN with Nport ID. */
+int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id)
+{
+	int rval = QLA_FUNCTION_FAILED;
+	struct ct_sns_req       *ct_req;
+	srb_t *sp;
+	struct ct_sns_pkt *ct_sns;
+
+	if (!vha->flags.online)
+		goto done;
+
+	sp = qla2x00_get_sp(vha, NULL, GFP_KERNEL);
+	if (!sp)
+		goto done;
+
+	sp->type = SRB_CT_PTHRU_CMD;
+	sp->name = "gpnid";
+	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
+
+	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
+		sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
+		GFP_KERNEL);
+	if (!sp->u.iocb_cmd.u.ctarg.req) {
+		ql_log(ql_log_warn, vha, 0xffff,
+			"Failed to allocate ct_sns request.\n");
+		goto done_free_sp;
+	}
+
+	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
+		sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
+		GFP_KERNEL);
+	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
+		ql_log(ql_log_warn, vha, 0xffff,
+			"Failed to allocate ct_sns request.\n");
+		goto done_free_sp;
+	}
+
+	ct_sns = (struct ct_sns_pkt *)sp->u.iocb_cmd.u.ctarg.rsp;
+	memset(ct_sns, 0, sizeof(*ct_sns));
+
+	ct_sns = (struct ct_sns_pkt *)sp->u.iocb_cmd.u.ctarg.req;
+	/* CT_IU preamble  */
+	ct_req = qla2x00_prep_ct_req(ct_sns, GPN_ID_CMD, GPN_ID_RSP_SIZE);
+
+	/* GPN_ID req */
+	ct_req->req.port_id.port_id[0] = id->b.domain;
+	ct_req->req.port_id.port_id[1] = id->b.area;
+	ct_req->req.port_id.port_id[2] = id->b.al_pa;
+
+	sp->u.iocb_cmd.u.ctarg.req_size = GPN_ID_REQ_SIZE;
+	sp->u.iocb_cmd.u.ctarg.rsp_size = GPN_ID_RSP_SIZE;
+	sp->u.iocb_cmd.u.ctarg.nport_handle = NPH_SNS;
+
+	sp->u.iocb_cmd.timeout = qla2x00_async_iocb_timeout;
+	sp->done = qla2x00_async_gpnid_sp_done;
+
+	rval = qla2x00_start_sp(sp);
+	if (rval != QLA_SUCCESS)
+		goto done_free_sp;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async-%s hdl=%x ID %3phC.\n", sp->name,
+		sp->handle, ct_req->req.port_id.port_id);
+	return rval;
+
+done_free_sp:
+	if (sp->u.iocb_cmd.u.ctarg.req) {
+		dma_free_coherent(&vha->hw->pdev->dev,
+			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.req,
+			sp->u.iocb_cmd.u.ctarg.req_dma);
+		sp->u.iocb_cmd.u.ctarg.req = NULL;
+	}
+	if (sp->u.iocb_cmd.u.ctarg.rsp) {
+		dma_free_coherent(&vha->hw->pdev->dev,
+			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.rsp,
+			sp->u.iocb_cmd.u.ctarg.rsp_dma);
+		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+	}
+
+	sp->free(vha, sp);
+done:
+	return rval;
+}
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 5978b79d4a61..8b7c0468a0e0 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -30,15 +30,15 @@ static int qla2x00_configure_hba(scsi_qla_host_t *);
 static int qla2x00_configure_loop(scsi_qla_host_t *);
 static int qla2x00_configure_local_loop(scsi_qla_host_t *);
 static int qla2x00_configure_fabric(scsi_qla_host_t *);
-static int qla2x00_find_all_fabric_devs(scsi_qla_host_t *, struct list_head *);
-static int qla2x00_fabric_dev_login(scsi_qla_host_t *, fc_port_t *,
-    uint16_t *);
-
+static int qla2x00_find_all_fabric_devs(scsi_qla_host_t *);
 static int qla2x00_restart_isp(scsi_qla_host_t *);
 
 static struct qla_chip_state_84xx *qla84xx_get_chip(struct scsi_qla_host *);
 static int qla84xx_init_chip(scsi_qla_host_t *);
 static int qla25xx_init_queues(struct qla_hw_data *);
+static int qla24xx_post_gpdb_work(struct scsi_qla_host *, fc_port_t *, u8);
+static void qla24xx_handle_plogi_done_event(struct scsi_qla_host *,
+    struct event_arg *);
 
 /* SRB Extensions ---------------------------------------------------------- */
 
@@ -47,8 +47,8 @@ qla2x00_sp_timeout(unsigned long __data)
 {
 	srb_t *sp = (srb_t *)__data;
 	struct srb_iocb *iocb;
-	fc_port_t *fcport = sp->fcport;
-	struct qla_hw_data *ha = fcport->vha->hw;
+	scsi_qla_host_t *vha = (scsi_qla_host_t *)sp->vha;
+	struct qla_hw_data *ha = vha->hw;
 	struct req_que *req;
 	unsigned long flags;
 
@@ -57,7 +57,7 @@ qla2x00_sp_timeout(unsigned long __data)
 	req->outstanding_cmds[sp->handle] = NULL;
 	iocb = &sp->u.iocb_cmd;
 	iocb->timeout(sp);
-	sp->free(fcport->vha, sp);
+	sp->free(vha, sp);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
@@ -94,29 +94,44 @@ qla2x00_get_async_timeout(struct scsi_qla_host *vha)
 	return tmo;
 }
 
-static void
+void
 qla2x00_async_iocb_timeout(void *data)
 {
 	srb_t *sp = (srb_t *)data;
 	fc_port_t *fcport = sp->fcport;
+	struct srb_iocb *lio = &sp->u.iocb_cmd;
+	struct event_arg ea;
 
 	ql_dbg(ql_dbg_disc, fcport->vha, 0x2071,
-	    "Async-%s timeout - hdl=%x portid=%02x%02x%02x.\n",
-	    sp->name, sp->handle, fcport->d_id.b.domain, fcport->d_id.b.area,
-	    fcport->d_id.b.al_pa);
+	    "Async-%s timeout - hdl=%x portid=%06x %8phC.\n",
+	    sp->name, sp->handle, fcport->d_id.b24, fcport->port_name);
 
 	fcport->flags &= ~FCF_ASYNC_SENT;
-	if (sp->type == SRB_LOGIN_CMD) {
-		struct srb_iocb *lio = &sp->u.iocb_cmd;
-		qla2x00_post_async_logout_work(fcport->vha, fcport, NULL);
+
+	switch (sp->type) {
+	case SRB_LOGIN_CMD:
 		/* Retry as needed. */
 		lio->u.logio.data[0] = MBS_COMMAND_ERROR;
 		lio->u.logio.data[1] = lio->u.logio.flags & SRB_LOGIN_RETRIED ?
 			QLA_LOGIO_LOGIN_RETRIED : 0;
-		qla2x00_post_async_login_done_work(fcport->vha, fcport,
-			lio->u.logio.data);
-	} else if (sp->type == SRB_LOGOUT_CMD) {
+		memset(&ea, 0, sizeof(ea));
+		ea.event = FCME_PLOGI_DONE;
+		ea.fcport = sp->fcport;
+		ea.data[0] = lio->u.logio.data[0];
+		ea.data[1] = lio->u.logio.data[1];
+		ea.sp = sp;
+		qla24xx_handle_plogi_done_event(fcport->vha, &ea);
+		break;
+	case SRB_LOGOUT_CMD:
 		qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT);
+		break;
+	case SRB_CT_PTHRU_CMD:
+	case SRB_MB_IOCB:
+	case SRB_NACK_PLOGI:
+	case SRB_NACK_PRLI:
+	case SRB_NACK_LOGO:
+		sp->done(sp->vha, sp, QLA_FUNCTION_TIMEOUT);
+		break;
 	}
 }
 
@@ -126,10 +141,25 @@ qla2x00_async_login_sp_done(void *data, void *ptr, int res)
 	srb_t *sp = (srb_t *)ptr;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
+	struct event_arg ea;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"%s %8phC res %d \n",
+		   __func__, sp->fcport->port_name, res);
+
+	sp->fcport->flags &= ~FCF_ASYNC_SENT;
+	if (!test_bit(UNLOADING, &vha->dpc_flags)) {
+		memset(&ea, 0, sizeof(ea));
+		ea.event = FCME_PLOGI_DONE;
+		ea.fcport = sp->fcport;
+		ea.data[0] = lio->u.logio.data[0];
+		ea.data[1] = lio->u.logio.data[1];
+		ea.iop[0] = lio->u.logio.iop[0];
+		ea.iop[1] = lio->u.logio.iop[1];
+		ea.sp = sp;
+		qla2x00_fcport_event_handler(vha, &ea);
+	}
 
-	if (!test_bit(UNLOADING, &vha->dpc_flags))
-		qla2x00_post_async_login_done_work(sp->fcport->vha, sp->fcport,
-		    lio->u.logio.data);
 	sp->free(sp->fcport->vha, sp);
 }
 
@@ -139,13 +169,23 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 {
 	srb_t *sp;
 	struct srb_iocb *lio;
-	int rval;
+	int rval = QLA_FUNCTION_FAILED;
+
+	if (!vha->flags.online)
+		goto done;
+
+	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
+	    (fcport->fw_login_state == DSC_LS_PLOGI_COMP) ||
+	    (fcport->fw_login_state == DSC_LS_PRLI_PEND))
+		goto done;
 
-	rval = QLA_FUNCTION_FAILED;
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp)
 		goto done;
 
+	fcport->flags |= FCF_ASYNC_SENT;
+	fcport->logout_completed = 0;
+
 	sp->type = SRB_LOGIN_CMD;
 	sp->name = "login";
 	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
@@ -165,8 +205,8 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 	}
 
 	ql_dbg(ql_dbg_disc, vha, 0x2072,
-	    "Async-login - hdl=%x, loopid=%x portid=%02x%02x%02x "
-	    "retries=%d.\n", sp->handle, fcport->loop_id,
+	    "Async-login - %8phC hdl=%x, loopid=%x portid=%02x%02x%02x "
+		"retries=%d.\n", fcport->port_name, sp->handle, fcport->loop_id,
 	    fcport->d_id.b.domain, fcport->d_id.b.area, fcport->d_id.b.al_pa,
 	    fcport->login_retry);
 	return rval;
@@ -174,6 +214,7 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 done_free_sp:
 	sp->free(fcport->vha, sp);
 done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
 }
 
@@ -184,6 +225,7 @@ qla2x00_async_logout_sp_done(void *data, void *ptr, int res)
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
 
+	sp->fcport->flags &= ~FCF_ASYNC_SENT;
 	if (!test_bit(UNLOADING, &vha->dpc_flags))
 		qla2x00_post_async_logout_done_work(sp->fcport->vha, sp->fcport,
 		    lio->u.logio.data);
@@ -198,6 +240,7 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport)
 	int rval;
 
 	rval = QLA_FUNCTION_FAILED;
+	fcport->flags |= FCF_ASYNC_SENT;
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp)
 		goto done;
@@ -214,14 +257,16 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport)
 		goto done_free_sp;
 
 	ql_dbg(ql_dbg_disc, vha, 0x2070,
-	    "Async-logout - hdl=%x loop-id=%x portid=%02x%02x%02x.\n",
+	    "Async-logout - hdl=%x loop-id=%x portid=%02x%02x%02x %8phC.\n",
 	    sp->handle, fcport->loop_id, fcport->d_id.b.domain,
-	    fcport->d_id.b.area, fcport->d_id.b.al_pa);
+		fcport->d_id.b.area, fcport->d_id.b.al_pa,
+		fcport->port_name);
 	return rval;
 
 done_free_sp:
 	sp->free(fcport->vha, sp);
 done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
 }
 
@@ -247,6 +292,7 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport,
 	int rval;
 
 	rval = QLA_FUNCTION_FAILED;
+	fcport->flags |= FCF_ASYNC_SENT;
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp)
 		goto done;
@@ -273,9 +319,817 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport,
 done_free_sp:
 	sp->free(fcport->vha, sp);
 done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
+	return rval;
+}
+
+static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
+	struct event_arg *ea)
+{
+	fc_port_t *fcport, *conflict_fcport;
+	struct get_name_list_extended *e;
+	u16 i, n, found = 0, loop_id;
+	port_id_t id;
+	u64 wwn;
+	u8 opt = 0;
+
+	fcport = ea->fcport;
+
+	if (ea->rc) { /* rval */
+		if (fcport->login_retry == 0) {
+			fcport->login_retry = vha->hw->login_retry_count;
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+				"GNL failed Port login retry %8phN, retry cnt=%d.\n",
+				fcport->port_name, fcport->login_retry);
+		}
+		return;
+	}
+
+	if (fcport->last_rscn_gen != fcport->rscn_gen) {
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+		    "%s %8phC rscn gen changed rscn %d|%d \n",
+		    __func__, fcport->port_name,
+		    fcport->last_rscn_gen, fcport->rscn_gen);
+		qla24xx_post_gidpn_work(vha, fcport);
+		return;
+	} else if (fcport->last_login_gen != fcport->login_gen) {
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			"%s %8phC login gen changed login %d|%d \n",
+			__func__, fcport->port_name,
+			fcport->last_login_gen, fcport->login_gen);
+		return;
+	}
+
+	n = ea->data[0] / sizeof(struct get_name_list_extended);
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "%s %d %8phC n %d %02x%02x%02x lid %d \n",
+	    __func__, __LINE__, fcport->port_name, n,
+	    fcport->d_id.b.domain, fcport->d_id.b.area,
+	    fcport->d_id.b.al_pa, fcport->loop_id);
+
+	for (i = 0; i < n; i++) {
+		e = &vha->gnl.l[i];
+		wwn = wwn_to_u64(e->port_name);
+
+		if (memcmp((u8 *)&wwn, fcport->port_name, WWN_SIZE))
+			continue;
+
+		found = 1;
+		id.b.domain = e->port_id[2];
+		id.b.area = e->port_id[1];
+		id.b.al_pa = e->port_id[0];
+		id.b.rsvd_1 = 0;
+
+		loop_id = le16_to_cpu(e->nport_handle);
+		loop_id = (loop_id & 0x7fff);
+
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			"%s found %8phC CLS [%d|%d] ID[%02x%02x%02x|%02x%02x%02x] lid[%d|%d]\n",
+			   __func__, fcport->port_name,
+			e->current_login_state, fcport->fw_login_state,
+			id.b.domain, id.b.area, id.b.al_pa,
+			fcport->d_id.b.domain, fcport->d_id.b.area,
+			fcport->d_id.b.al_pa, loop_id, fcport->loop_id);
+
+		if ((id.b24 != fcport->d_id.b24) ||
+		    ((fcport->loop_id != FC_NO_LOOP_ID) &&
+			(fcport->loop_id != loop_id))) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post del sess\n",
+			   __func__, __LINE__, fcport->port_name);
+			qlt_schedule_sess_for_deletion(fcport, 1);
+			return;
+		}
+
+		fcport->loop_id = loop_id;
+
+		wwn = wwn_to_u64(fcport->port_name);
+		qlt_find_sess_invalidate_other(vha, wwn,
+			id, loop_id, &conflict_fcport);
+
+		if (conflict_fcport) {
+			/*
+			 * Another share fcport share the same loop_id &
+			 * nport id. Conflict fcport needs to finish
+			 * cleanup before this fcport can proceed to login.
+			 */
+			conflict_fcport->conflict = fcport;
+			fcport->login_pause = 1;
+		}
+
+		switch (e->current_login_state) {
+		case DSC_LS_PRLI_COMP:
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post gpdb\n",
+			   __func__, __LINE__, fcport->port_name);
+			opt = PDO_FORCE_ADISC;
+			qla24xx_post_gpdb_work(vha, fcport, opt);
+			break;
+
+		case DSC_LS_PORT_UNAVAIL:
+		default:
+			if (fcport->loop_id == FC_NO_LOOP_ID) {
+				qla2x00_find_new_loop_id(vha, fcport);
+				fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
+			}
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC \n",
+			   __func__, __LINE__, fcport->port_name);
+			qla24xx_fcport_handle_login(vha, fcport);
+			break;
+		}
+	}
+
+	if (!found) {
+		/* fw has no record of this port */
+		if (fcport->loop_id == FC_NO_LOOP_ID) {
+			qla2x00_find_new_loop_id(vha, fcport);
+			fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
+		} else {
+			for (i = 0; i < n; i++) {
+				e = &vha->gnl.l[i];
+				id.b.domain = e->port_id[0];
+				id.b.area = e->port_id[1];
+				id.b.al_pa = e->port_id[2];
+				id.b.rsvd_1 = 0;
+				loop_id = le16_to_cpu(e->nport_handle);
+
+				if (fcport->d_id.b24 == id.b24) {
+					conflict_fcport =
+					    qla2x00_find_fcport_by_wwpn(vha,
+						e->port_name, 0);
+
+					ql_dbg(ql_dbg_disc, vha, 0xffff,
+					    "%s %d %8phC post del sess\n",
+					    __func__, __LINE__,
+					    conflict_fcport->port_name);
+					qlt_schedule_sess_for_deletion
+						(conflict_fcport, 1);
+				}
+
+				if (fcport->loop_id == loop_id) {
+					/* FW already picked this loop id for another fcport */
+					qla2x00_find_new_loop_id(vha, fcport);
+				}
+			}
+		}
+		qla24xx_fcport_handle_login(vha, fcport);
+	}
+} /* gnl_event */
+
+static void
+qla24xx_async_gnl_sp_done(void *v, void *s, int res)
+{
+	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
+	struct srb *sp = (struct srb *)s;
+	unsigned long flags;
+	struct fc_port *fcport = NULL, *tf;
+	u16 i, n = 0, loop_id;
+	struct event_arg ea;
+	struct get_name_list_extended *e;
+	u64 wwn;
+	struct list_head h;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "Async done-%s res %x mb[1]=%x mb[2]=%x \n",
+	    sp->name, res, sp->u.iocb_cmd.u.mbx.in_mb[1],
+	    sp->u.iocb_cmd.u.mbx.in_mb[2]);
+
+	memset(&ea, 0, sizeof(ea));
+	ea.sp = sp;
+	ea.rc = res;
+	ea.event = FCME_GNL_DONE;
+
+	if (sp->u.iocb_cmd.u.mbx.in_mb[1] >=
+	    sizeof(struct get_name_list_extended)) {
+		n = sp->u.iocb_cmd.u.mbx.in_mb[1] /
+		    sizeof(struct get_name_list_extended);
+		ea.data[0] = sp->u.iocb_cmd.u.mbx.in_mb[1]; /* amnt xfered */
+	}
+
+	for (i = 0; i < n; i++) {
+		e = &vha->gnl.l[i];
+		loop_id = le16_to_cpu(e->nport_handle);
+		/* mask out reserve bit */
+		loop_id = (loop_id & 0x7fff);
+		set_bit(loop_id, vha->hw->loop_id_map);
+		wwn = wwn_to_u64(e->port_name);
+
+		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
+		    "%s %8phC %02x:%02x:%02x state %d/%d lid %x \n",
+		    __func__, (void *)&wwn, e->port_id[2], e->port_id[1],
+		    e->port_id[0], e->current_login_state, e->last_login_state,
+		    (loop_id & 0x7fff));
+	}
+
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	vha->gnl.sent = 0;
+
+	INIT_LIST_HEAD(&h);
+	fcport = tf = NULL;
+	if (!list_empty(&vha->gnl.fcports))
+		list_splice_init(&vha->gnl.fcports, &h);
+
+	list_for_each_entry_safe(fcport, tf, &h, gnl_entry) {
+		list_del_init(&fcport->gnl_entry);
+		fcport->flags &= ~FCF_ASYNC_SENT;
+		ea.fcport = fcport;
+
+		qla2x00_fcport_event_handler(vha, &ea);
+	}
+
+	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+	sp->free(vha, sp);
+}
+
+int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	srb_t *sp;
+	struct srb_iocb *mbx;
+	int rval = QLA_FUNCTION_FAILED;
+	unsigned long flags;
+	u16 *mb;
+
+	if (!vha->flags.online)
+		goto done;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "Async-gnlist WWPN %8phC \n", fcport->port_name);
+
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	fcport->flags |= FCF_ASYNC_SENT;
+	fcport->disc_state = DSC_GNL;
+	fcport->last_rscn_gen = fcport->rscn_gen;
+	fcport->last_login_gen = fcport->login_gen;
+
+	list_add_tail(&fcport->gnl_entry, &vha->gnl.fcports);
+	if (vha->gnl.sent) {
+		spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+		rval = QLA_SUCCESS;
+		goto done;
+	}
+	vha->gnl.sent = 1;
+	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
+	if (!sp)
+		goto done;
+	sp->type = SRB_MB_IOCB;
+	sp->name = "gnlist";
+	sp->gen1 = fcport->rscn_gen;
+	sp->gen2 = fcport->login_gen;
+
+	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha)+2);
+
+	mb = sp->u.iocb_cmd.u.mbx.out_mb;
+	mb[0] = MBC_PORT_NODE_NAME_LIST;
+	mb[1] = BIT_2 | BIT_3;
+	mb[2] = MSW(vha->gnl.ldma);
+	mb[3] = LSW(vha->gnl.ldma);
+	mb[6] = MSW(MSD(vha->gnl.ldma));
+	mb[7] = LSW(MSD(vha->gnl.ldma));
+	mb[8] = vha->gnl.size;
+	mb[9] = vha->vp_idx;
+
+	mbx = &sp->u.iocb_cmd;
+	mbx->timeout = qla2x00_async_iocb_timeout;
+
+	sp->done = qla24xx_async_gnl_sp_done;
+
+	rval = qla2x00_start_sp(sp);
+	if (rval != QLA_SUCCESS)
+		goto done_free_sp;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async-%s - OUT WWPN %8phC hndl %x\n",
+		sp->name, fcport->port_name, sp->handle);
+
+	return rval;
+
+done_free_sp:
+	sp->free(fcport->vha, sp);
+done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
+	return rval;
+}
+
+int qla24xx_post_gnl_work(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	struct qla_work_evt *e;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_GNL);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.fcport.fcport = fcport;
+	return qla2x00_post_work(vha, e);
+}
+
+static
+void qla24xx_async_gpdb_sp_done(void *v, void *s, int res)
+{
+	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
+	struct srb *sp = (struct srb *)s;
+	struct qla_hw_data *ha = vha->hw;
+	uint64_t zero = 0;
+	struct port_database_24xx *pd;
+	fc_port_t *fcport = sp->fcport;
+	u16 *mb = sp->u.iocb_cmd.u.mbx.in_mb;
+	int rval = QLA_SUCCESS;
+	struct event_arg ea;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "Async done-%s res %x, WWPN %8phC mb[1]=%x mb[2]=%x \n",
+	    sp->name, res, fcport->port_name, mb[1], mb[2]);
+
+	fcport->flags &= ~FCF_ASYNC_SENT;
+
+	if (res) {
+		rval = res;
+		goto gpd_error_out;
+	}
+
+	pd = (struct port_database_24xx *)sp->u.iocb_cmd.u.mbx.in;
+
+	/* Check for logged in state. */
+	if (pd->current_login_state != PDS_PRLI_COMPLETE &&
+	    pd->last_login_state != PDS_PRLI_COMPLETE) {
+		ql_dbg(ql_dbg_mbx, vha, 0xffff,
+		    "Unable to verify login-state (%x/%x) for "
+		    "loop_id %x.\n", pd->current_login_state,
+		    pd->last_login_state, fcport->loop_id);
+		rval = QLA_FUNCTION_FAILED;
+		goto gpd_error_out;
+	}
+
+	if (fcport->loop_id == FC_NO_LOOP_ID ||
+	    (memcmp(fcport->port_name, (uint8_t *)&zero, 8) &&
+		memcmp(fcport->port_name, pd->port_name, 8))) {
+		/* We lost the device mid way. */
+		rval = QLA_NOT_LOGGED_IN;
+		goto gpd_error_out;
+	}
+
+	/* Names are little-endian. */
+	memcpy(fcport->node_name, pd->node_name, WWN_SIZE);
+
+	/* Get port_id of device. */
+	fcport->d_id.b.domain = pd->port_id[0];
+	fcport->d_id.b.area = pd->port_id[1];
+	fcport->d_id.b.al_pa = pd->port_id[2];
+	fcport->d_id.b.rsvd_1 = 0;
+
+	/* If not target must be initiator or unknown type. */
+	if ((pd->prli_svc_param_word_3[0] & BIT_4) == 0)
+		fcport->port_type = FCT_INITIATOR;
+	else
+		fcport->port_type = FCT_TARGET;
+
+	/* Passback COS information. */
+	fcport->supported_classes = (pd->flags & PDF_CLASS_2) ?
+		FC_COS_CLASS2 : FC_COS_CLASS3;
+
+	if (pd->prli_svc_param_word_3[0] & BIT_7) {
+		fcport->flags |= FCF_CONF_COMP_SUPPORTED;
+		fcport->conf_compl_supported = 1;
+	}
+
+gpd_error_out:
+	memset(&ea, 0, sizeof(ea));
+	ea.event = FCME_GPDB_DONE;
+	ea.rc = rval;
+	ea.fcport = fcport;
+	ea.sp = sp;
+
+	qla2x00_fcport_event_handler(vha, &ea);
+
+	dma_pool_free(ha->s_dma_pool, sp->u.iocb_cmd.u.mbx.in,
+		sp->u.iocb_cmd.u.mbx.in_dma);
+
+	sp->free(vha, sp);
+}
+
+static int qla24xx_post_gpdb_work(struct scsi_qla_host *vha, fc_port_t *fcport,
+    u8 opt)
+{
+	struct qla_work_evt *e;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_GPDB);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.fcport.fcport = fcport;
+	e->u.fcport.opt = opt;
+	return qla2x00_post_work(vha, e);
+}
+
+int qla24xx_async_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport, u8 opt)
+{
+	srb_t *sp;
+	struct srb_iocb *mbx;
+	int rval = QLA_FUNCTION_FAILED;
+	u16 *mb;
+	dma_addr_t pd_dma;
+	struct port_database_24xx *pd;
+	struct qla_hw_data *ha = vha->hw;
+
+	if (!vha->flags.online)
+		goto done;
+
+	fcport->flags |= FCF_ASYNC_SENT;
+	fcport->disc_state = DSC_GPDB;
+
+	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
+	if (!sp)
+		goto done;
+
+	pd = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &pd_dma);
+	if (pd == NULL) {
+		ql_log(ql_log_warn, vha, 0xffff,
+			"Failed to allocate port database structure.\n");
+		goto done_free_sp;
+	}
+	memset(pd, 0, max(PORT_DATABASE_SIZE, PORT_DATABASE_24XX_SIZE));
+
+	sp->type = SRB_MB_IOCB;
+	sp->name = "gpdb";
+	sp->gen1 = fcport->rscn_gen;
+	sp->gen2 = fcport->login_gen;
+	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
+
+	mb = sp->u.iocb_cmd.u.mbx.out_mb;
+	mb[0] = MBC_GET_PORT_DATABASE;
+	mb[1] = fcport->loop_id;
+	mb[2] = MSW(pd_dma);
+	mb[3] = LSW(pd_dma);
+	mb[6] = MSW(MSD(pd_dma));
+	mb[7] = LSW(MSD(pd_dma));
+	mb[9] = vha->vp_idx;
+	mb[10] = opt;
+
+	mbx = &sp->u.iocb_cmd;
+	mbx->timeout = qla2x00_async_iocb_timeout;
+	mbx->u.mbx.in = (void *)pd;
+	mbx->u.mbx.in_dma = pd_dma;
+
+	sp->done = qla24xx_async_gpdb_sp_done;
+
+	rval = qla2x00_start_sp(sp);
+	if (rval != QLA_SUCCESS)
+		goto done_free_sp;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async-%s %8phC hndl %x opt %x\n",
+		sp->name, fcport->port_name, sp->handle, opt);
+
+	return rval;
+
+done_free_sp:
+	if (pd)
+		dma_pool_free(ha->s_dma_pool, pd, pd_dma);
+
+	sp->free(vha, sp);
+done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
+	qla24xx_post_gpdb_work(vha, fcport, opt);
 	return rval;
 }
 
+static
+void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
+{
+	int rval = ea->rc;
+	fc_port_t *fcport = ea->fcport;
+	unsigned long flags;
+
+	fcport->flags &= ~FCF_ASYNC_SENT;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "%s %8phC DS %d LS %d rval %d\n", __func__, fcport->port_name,
+	    fcport->disc_state, fcport->fw_login_state, rval);
+
+	if (ea->sp->gen2 != fcport->login_gen) {
+		/* target side must have changed it. */
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+		    "%s %8phC generation changed rscn %d|%d login %d|%d \n",
+		    __func__, fcport->port_name, fcport->last_rscn_gen,
+		    fcport->rscn_gen, fcport->last_login_gen,
+		    fcport->login_gen);
+		return;
+	} else if (ea->sp->gen1 != fcport->rscn_gen) {
+		ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC post gidpn\n",
+		    __func__, __LINE__, fcport->port_name);
+		qla24xx_post_gidpn_work(vha, fcport);
+		return;
+	}
+
+	if (rval != QLA_SUCCESS) {
+		ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC post del sess\n",
+		    __func__, __LINE__, fcport->port_name);
+		qlt_schedule_sess_for_deletion_lock(fcport);
+		return;
+	}
+
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	ea->fcport->login_gen++;
+	ea->fcport->deleted = 0;
+	ea->fcport->logout_on_delete = 1;
+
+	if (!ea->fcport->login_succ && !IS_SW_RESV_ADDR(ea->fcport->d_id)) {
+		vha->fcport_count++;
+		ea->fcport->login_succ = 1;
+
+		if (!IS_IIDMA_CAPABLE(vha->hw) ||
+		    !vha->hw->flags.gpsc_supported) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "%s %d %8phC post upd_fcport fcp_cnt %d\n",
+			    __func__, __LINE__, fcport->port_name,
+			    vha->fcport_count);
+
+			qla24xx_post_upd_fcport_work(vha, fcport);
+		} else {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "%s %d %8phC post gpsc fcp_cnt %d\n",
+			    __func__, __LINE__, fcport->port_name,
+			    vha->fcport_count);
+
+			qla24xx_post_gpsc_work(vha, fcport);
+		}
+	}
+	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+} /* gpdb event */
+
+int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	if (fcport->login_retry == 0)
+		return 0;
+
+	if (fcport->scan_state != QLA_FCPORT_FOUND)
+		return 0;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	    "%s %8phC DS %d LS %d P %d fl %x confl %p rscn %d|%d login %d|%d retry %d lid %d\n",
+	    __func__, fcport->port_name, fcport->disc_state,
+	    fcport->fw_login_state, fcport->login_pause, fcport->flags,
+	    fcport->conflict, fcport->last_rscn_gen, fcport->rscn_gen,
+	    fcport->last_login_gen, fcport->login_gen, fcport->login_retry,
+	    fcport->loop_id);
+
+	fcport->login_retry--;
+
+	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
+	    (fcport->fw_login_state == DSC_LS_PLOGI_COMP) ||
+	    (fcport->fw_login_state == DSC_LS_PRLI_PEND))
+		return 0;
+
+	/* for pure Target Mode. Login will not be initiated */
+	if (vha->host->active_mode == MODE_TARGET)
+		return 0;
+
+	if (fcport->flags & FCF_ASYNC_SENT) {
+		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		return 0;
+	}
+
+	switch (fcport->disc_state) {
+	case DSC_DELETED:
+		if (fcport->loop_id == FC_NO_LOOP_ID) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post gnl\n",
+			   __func__, __LINE__, fcport->port_name);
+			qla24xx_async_gnl(vha, fcport);
+		} else {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post login\n",
+			   __func__, __LINE__, fcport->port_name);
+			fcport->disc_state = DSC_LOGIN_PEND;
+			qla2x00_post_async_login_work(vha, fcport, NULL);
+		}
+		break;
+
+	case DSC_GNL:
+		if (fcport->login_pause) {
+			fcport->last_rscn_gen = fcport->rscn_gen;
+			fcport->last_login_gen = fcport->login_gen;
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+			break;
+		}
+
+		if (fcport->flags & FCF_FCP2_DEVICE) {
+			u8 opt = PDO_FORCE_ADISC;
+
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post gpdb\n",
+			   __func__, __LINE__, fcport->port_name);
+
+			fcport->disc_state = DSC_GPDB;
+			qla24xx_post_gpdb_work(vha, fcport, opt);
+		} else {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post login \n",
+			   __func__, __LINE__, fcport->port_name);
+			fcport->disc_state = DSC_LOGIN_PEND;
+			qla2x00_post_async_login_work(vha, fcport, NULL);
+		}
+
+		break;
+
+	case DSC_LOGIN_FAILED:
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post gidpn \n",
+			   __func__, __LINE__, fcport->port_name);
+
+		qla24xx_post_gidpn_work(vha, fcport);
+		break;
+
+	case DSC_LOGIN_COMPLETE:
+		/* recheck login state */
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post gpdb \n",
+			   __func__, __LINE__, fcport->port_name);
+
+		qla24xx_post_gpdb_work(vha, fcport, PDO_FORCE_ADISC);
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static
+void qla24xx_handle_rscn_event(fc_port_t *fcport, struct event_arg *ea)
+{
+	fcport->rscn_gen++;
+
+	ql_dbg(ql_dbg_disc, fcport->vha, 0xffff,
+		"%s %8phC DS %d LS %d\n",
+		__func__, fcport->port_name, fcport->disc_state,
+		fcport->fw_login_state);
+
+	if (fcport->flags & FCF_ASYNC_SENT)
+		return;
+
+	switch (fcport->disc_state) {
+	case DSC_DELETED:
+	case DSC_LOGIN_COMPLETE:
+		qla24xx_post_gidpn_work(fcport->vha, fcport);
+		break;
+
+	default:
+		break;
+	}
+}
+
+int qla24xx_post_newsess_work(struct scsi_qla_host *vha, port_id_t *id,
+	u8 *port_name, void *pla)
+{
+	struct qla_work_evt *e;
+	e = qla2x00_alloc_work(vha, QLA_EVT_NEW_SESS);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.new_sess.id = *id;
+	e->u.new_sess.pla = pla;
+	memcpy(e->u.new_sess.port_name, port_name, WWN_SIZE);
+
+	return qla2x00_post_work(vha, e);
+}
+
+static
+int qla24xx_handle_delete_done_event(scsi_qla_host_t *vha,
+	struct event_arg *ea)
+{
+	fc_port_t *fcport = ea->fcport;
+
+	if (test_bit(UNLOADING, &vha->dpc_flags))
+		return 0;
+
+	switch (vha->host->active_mode) {
+	case MODE_INITIATOR:
+	case MODE_DUAL:
+		if (fcport->scan_state == QLA_FCPORT_FOUND)
+			qla24xx_fcport_handle_login(vha, fcport);
+		break;
+
+	case MODE_TARGET:
+	default:
+		/* no-op */
+		break;
+	}
+
+	return 0;
+}
+
+static
+void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
+	struct event_arg *ea)
+{
+	fc_port_t *fcport = ea->fcport;
+
+	if (fcport->scan_state != QLA_FCPORT_FOUND) {
+		fcport->login_retry++;
+		return;
+	}
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"%s %8phC DS %d LS %d P %d del %d cnfl %p rscn %d|%d login %d|%d fl %x\n",
+		__func__, fcport->port_name, fcport->disc_state,
+		fcport->fw_login_state, fcport->login_pause,
+		fcport->deleted, fcport->conflict,
+		fcport->last_rscn_gen, fcport->rscn_gen,
+		fcport->last_login_gen, fcport->login_gen,
+		fcport->flags);
+
+	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
+	    (fcport->fw_login_state == DSC_LS_PLOGI_COMP) ||
+	    (fcport->fw_login_state == DSC_LS_PRLI_PEND))
+		return;
+
+	if (fcport->flags & FCF_ASYNC_SENT) {
+		fcport->login_retry++;
+		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		return;
+	}
+
+	if (fcport->disc_state == DSC_DELETE_PEND) {
+		fcport->login_retry++;
+		return;
+	}
+
+	if (fcport->last_rscn_gen != fcport->rscn_gen) {
+		ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC post gidpn\n",
+		    __func__, __LINE__, fcport->port_name);
+
+		qla24xx_async_gidpn(vha, fcport);
+		return;
+	}
+
+	qla24xx_fcport_handle_login(vha, fcport);
+}
+
+void qla2x00_fcport_event_handler(scsi_qla_host_t *vha,
+	struct event_arg *ea)
+{
+	fc_port_t *fcport;
+	int rc;
+
+	switch (ea->event) {
+	case FCME_RELOGIN:
+		if (test_bit(UNLOADING, &vha->dpc_flags))
+			return;
+
+		qla24xx_handle_relogin_event(vha, ea);
+		break;
+	case FCME_RSCN:
+		if (test_bit(UNLOADING, &vha->dpc_flags))
+			return;
+
+		fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1);
+		if (!fcport) {
+			/* cable moved */
+			rc = qla24xx_post_gpnid_work(vha, &ea->id);
+			if (rc) {
+				ql_log(ql_log_warn, vha, 0xffff,
+					"RSCN GPNID work failed %02x%02x%02x\n",
+					ea->id.b.domain, ea->id.b.area,
+					ea->id.b.al_pa);
+			}
+		} else {
+			ea->fcport = fcport;
+			qla24xx_handle_rscn_event(fcport, ea);
+		}
+		break;
+	case FCME_GIDPN_DONE:
+		qla24xx_handle_gidpn_event(vha, ea);
+		break;
+	case FCME_GNL_DONE:
+		qla24xx_handle_gnl_done_event(vha, ea);
+		break;
+	case FCME_GPSC_DONE:
+		qla24xx_post_upd_fcport_work(vha, ea->fcport);
+		break;
+	case FCME_PLOGI_DONE:	/* Initiator side sent LLIOCB */
+		qla24xx_handle_plogi_done_event(vha, ea);
+		break;
+	case FCME_GPDB_DONE:
+		qla24xx_handle_gpdb_event(vha, ea);
+		break;
+	case FCME_GPNID_DONE:
+		qla24xx_handle_gpnid_event(vha, ea);
+		break;
+	case FCME_DELETE_DONE:
+		qla24xx_handle_delete_done_event(vha, ea);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+}
+
 static void
 qla2x00_tmf_iocb_timeout(void *data)
 {
@@ -441,59 +1295,65 @@ qla24xx_async_abort_command(srb_t *sp)
 	return qla24xx_async_abort_cmd(sp);
 }
 
-void
-qla2x00_async_login_done(struct scsi_qla_host *vha, fc_port_t *fcport,
-    uint16_t *data)
+static void
+qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 {
-	int rval;
+	port_id_t cid;	/* conflict Nport id */
 
-	switch (data[0]) {
+	switch (ea->data[0]) {
 	case MBS_COMMAND_COMPLETE:
 		/*
 		 * Driver must validate login state - If PRLI not complete,
 		 * force a relogin attempt via implicit LOGO, PLOGI, and PRLI
 		 * requests.
 		 */
-		rval = qla2x00_get_port_database(vha, fcport, 0);
-		if (rval == QLA_NOT_LOGGED_IN) {
-			fcport->flags &= ~FCF_ASYNC_SENT;
-			fcport->flags |= FCF_LOGIN_NEEDED;
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-			break;
-		}
-
-		if (rval != QLA_SUCCESS) {
-			qla2x00_post_async_logout_work(vha, fcport, NULL);
-			qla2x00_post_async_login_work(vha, fcport, NULL);
-			break;
-		}
-		if (fcport->flags & FCF_FCP2_DEVICE) {
-			qla2x00_post_async_adisc_work(vha, fcport, data);
-			break;
-		}
-		qla2x00_update_fcport(vha, fcport);
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			   "%s %d %8phC post gpdb\n",
+			   __func__, __LINE__, ea->fcport->port_name);
+		ea->fcport->chip_reset = vha->hw->chip_reset;
+		ea->fcport->logout_on_delete = 1;
+		qla24xx_post_gpdb_work(vha, ea->fcport, 0);
 		break;
 	case MBS_COMMAND_ERROR:
-		fcport->flags &= ~FCF_ASYNC_SENT;
-		if (data[1] & QLA_LOGIO_LOGIN_RETRIED)
+		ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC cmd error %x\n",
+		    __func__, __LINE__, ea->fcport->port_name, ea->data[1]);
+
+		ea->fcport->flags &= ~FCF_ASYNC_SENT;
+		ea->fcport->disc_state = DSC_LOGIN_FAILED;
+		if (ea->data[1] & QLA_LOGIO_LOGIN_RETRIED)
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 		else
-			qla2x00_mark_device_lost(vha, fcport, 1, 0);
-		break;
-	case MBS_PORT_ID_USED:
-		fcport->loop_id = data[1];
-		qla2x00_post_async_logout_work(vha, fcport, NULL);
-		qla2x00_post_async_login_work(vha, fcport, NULL);
+			qla2x00_mark_device_lost(vha, ea->fcport, 1, 0);
 		break;
 	case MBS_LOOP_ID_USED:
-		fcport->loop_id++;
-		rval = qla2x00_find_new_loop_id(vha, fcport);
-		if (rval != QLA_SUCCESS) {
-			fcport->flags &= ~FCF_ASYNC_SENT;
-			qla2x00_mark_device_lost(vha, fcport, 1, 0);
-			break;
+		/* data[1] = IO PARAM 1 = nport ID  */
+		cid.b.domain = (ea->iop[1] >> 16) & 0xff;
+		cid.b.area   = (ea->iop[1] >>  8) & 0xff;
+		cid.b.al_pa  = ea->iop[1] & 0xff;
+		cid.b.rsvd_1 = 0;
+
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			"%s %d %8phC LoopID 0x%x in use post gnl\n",
+			__func__, __LINE__, ea->fcport->port_name,
+			ea->fcport->loop_id);
+
+		if (IS_SW_RESV_ADDR(cid)) {
+			set_bit(ea->fcport->loop_id, vha->hw->loop_id_map);
+			ea->fcport->loop_id = FC_NO_LOOP_ID;
+		} else {
+			qla2x00_clear_loop_id(ea->fcport);
 		}
-		qla2x00_post_async_login_work(vha, fcport, NULL);
+		qla24xx_post_gnl_work(vha, ea->fcport);
+		break;
+	case MBS_PORT_ID_USED:
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+			"%s %d %8phC NPortId %02x%02x%02x inuse post gidpn\n",
+			__func__, __LINE__, ea->fcport->port_name,
+			ea->fcport->d_id.b.domain, ea->fcport->d_id.b.area,
+			ea->fcport->d_id.b.al_pa);
+
+		qla2x00_clear_loop_id(ea->fcport);
+		qla24xx_post_gidpn_work(vha, ea->fcport);
 		break;
 	}
 	return;
@@ -503,10 +1363,9 @@ void
 qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
-	/* Don't re-login in target mode */
-	if (!fcport->tgt_session)
-		qla2x00_mark_device_lost(vha, fcport, 1, 0);
+	qla2x00_mark_device_lost(vha, fcport, 1, 0);
 	qlt_logo_completion_handler(fcport, data[0]);
+	fcport->login_gen++;
 	return;
 }
 
@@ -709,7 +1568,8 @@ qla2x00_initialize_adapter(scsi_qla_host_t *vha)
 		}
 	}
 
-	if (qla_ini_mode_enabled(vha))
+	if (qla_ini_mode_enabled(vha) ||
+		qla_dual_mode_enabled(vha))
 		rval = qla2x00_init_rings(vha);
 
 	ha->flags.chip_reset_done = 1;
@@ -2968,8 +3828,14 @@ qla2x00_rport_del(void *data)
 	rport = fcport->drport ? fcport->drport: fcport->rport;
 	fcport->drport = NULL;
 	spin_unlock_irqrestore(fcport->vha->host->host_lock, flags);
-	if (rport)
+	if (rport) {
+		ql_dbg(ql_dbg_disc, fcport->vha, 0xffff,
+			"%s %8phN. rport %p roles %x \n",
+			__func__, fcport->port_name, rport,
+			rport->roles);
+
 		fc_remote_port_delete(rport);
+	}
 }
 
 /**
@@ -2995,9 +3861,42 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags)
 	qla2x00_set_fcport_state(fcport, FCS_UNCONFIGURED);
 	fcport->supported_classes = FC_COS_UNSPECIFIED;
 
+	fcport->ct_desc.ct_sns = dma_alloc_coherent(&vha->hw->pdev->dev,
+		sizeof(struct ct_sns_pkt), &fcport->ct_desc.ct_sns_dma,
+			GFP_ATOMIC);
+	fcport->disc_state = DSC_DELETED;
+	fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
+	fcport->deleted = QLA_SESS_DELETED;
+	fcport->login_retry = vha->hw->login_retry_count;
+	fcport->login_retry = 5;
+	fcport->logout_on_delete = 1;
+
+	if (!fcport->ct_desc.ct_sns) {
+		ql_log(ql_log_warn, vha, 0xffff,
+		    "Failed to allocate ct_sns request.\n");
+		kfree(fcport);
+		fcport = NULL;
+	}
+	INIT_WORK(&fcport->del_work, qla24xx_delete_sess_fn);
+	INIT_LIST_HEAD(&fcport->gnl_entry);
+	INIT_LIST_HEAD(&fcport->list);
+
 	return fcport;
 }
 
+void
+qla2x00_free_fcport(fc_port_t *fcport)
+{
+	if (fcport->ct_desc.ct_sns) {
+		dma_free_coherent(&fcport->vha->hw->pdev->dev,
+			sizeof(struct ct_sns_pkt), fcport->ct_desc.ct_sns,
+			fcport->ct_desc.ct_sns_dma);
+
+		fcport->ct_desc.ct_sns = NULL;
+	}
+	kfree(fcport);
+}
+
 /*
  * qla2x00_configure_loop
  *      Updates Fibre Channel Device Database with what is actually on loop.
@@ -3334,6 +4233,7 @@ qla2x00_iidma_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	}
 }
 
+/* qla2x00_reg_remote_port is reserved for Initiator Mode only.*/
 static void
 qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 {
@@ -3364,6 +4264,12 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 		rport_ids.roles |= FC_RPORT_ROLE_FCP_INITIATOR;
 	if (fcport->port_type == FCT_TARGET)
 		rport_ids.roles |= FC_RPORT_ROLE_FCP_TARGET;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"%s %8phN. rport %p is %s mode \n",
+		__func__, fcport->port_name, rport,
+		(fcport->port_type == FCT_TARGET) ? "tgt" : "ini");
+
 	fc_remote_port_rolechg(rport, rport_ids.roles);
 }
 
@@ -3387,20 +4293,45 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 {
 	fcport->vha = vha;
 
+	if (IS_SW_RESV_ADDR(fcport->d_id))
+		return;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %8phC \n",
+	    __func__, fcport->port_name);
+
 	if (IS_QLAFX00(vha->hw)) {
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 		goto reg_port;
 	}
 	fcport->login_retry = 0;
 	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
+	fcport->disc_state = DSC_LOGIN_COMPLETE;
+	fcport->deleted = 0;
+	fcport->logout_on_delete = 1;
 
 	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	qla2x00_iidma_fcport(vha, fcport);
 	qla24xx_update_fcport_fcp_prio(vha, fcport);
 
 reg_port:
-	if (qla_ini_mode_enabled(vha))
+	switch (vha->host->active_mode) {
+	case MODE_INITIATOR:
+		qla2x00_reg_remote_port(vha, fcport);
+		break;
+	case MODE_TARGET:
+		if (!vha->vha_tgt.qla_tgt->tgt_stop &&
+			!vha->vha_tgt.qla_tgt->tgt_stopped)
+			qlt_fc_port_added(vha, fcport);
+		break;
+	case MODE_DUAL:
 		qla2x00_reg_remote_port(vha, fcport);
+		if (!vha->vha_tgt.qla_tgt->tgt_stop &&
+			!vha->vha_tgt.qla_tgt->tgt_stopped)
+			qlt_fc_port_added(vha, fcport);
+		break;
+	default:
+		break;
+	}
 }
 
 /*
@@ -3418,13 +4349,11 @@ static int
 qla2x00_configure_fabric(scsi_qla_host_t *vha)
 {
 	int	rval;
-	fc_port_t	*fcport, *fcptemp;
-	uint16_t	next_loopid;
+	fc_port_t	*fcport;
 	uint16_t	mb[MAILBOX_REGISTER_COUNT];
 	uint16_t	loop_id;
 	LIST_HEAD(new_fcports);
 	struct qla_hw_data *ha = vha->hw;
-	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
 	int		discovery_gen;
 
 	/* If FL port exists, then SNS is present */
@@ -3443,6 +4372,8 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 	vha->device_flags |= SWITCH_FOUND;
 
 	do {
+		qla2x00_mgmt_svr_login(vha);
+
 		/* FDMI support. */
 		if (ql2xfdmienable &&
 		    test_and_clear_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags))
@@ -3489,9 +4420,6 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 			}
 		}
 
-#define QLA_FCPORT_SCAN		1
-#define QLA_FCPORT_FOUND	2
-
 		list_for_each_entry(fcport, &vha->vp_fcports, list) {
 			fcport->scan_state = QLA_FCPORT_SCAN;
 		}
@@ -3504,174 +4432,14 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 		 * will be newer than discovery_gen. */
 		qlt_do_generation_tick(vha, &discovery_gen);
 
-		rval = qla2x00_find_all_fabric_devs(vha, &new_fcports);
+		rval = qla2x00_find_all_fabric_devs(vha);
 		if (rval != QLA_SUCCESS)
 			break;
-
-		/*
-		 * Logout all previous fabric devices marked lost, except
-		 * FCP2 devices.
-		 */
-		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
-				break;
-
-			if ((fcport->flags & FCF_FABRIC_DEVICE) == 0)
-				continue;
-
-			if (fcport->scan_state == QLA_FCPORT_SCAN) {
-				if (qla_ini_mode_enabled(base_vha) &&
-				    atomic_read(&fcport->state) == FCS_ONLINE) {
-					qla2x00_mark_device_lost(vha, fcport,
-					    ql2xplogiabsentdevice, 0);
-					if (fcport->loop_id != FC_NO_LOOP_ID &&
-					    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
-					    fcport->port_type != FCT_INITIATOR &&
-					    fcport->port_type != FCT_BROADCAST) {
-						ha->isp_ops->fabric_logout(vha,
-						    fcport->loop_id,
-						    fcport->d_id.b.domain,
-						    fcport->d_id.b.area,
-						    fcport->d_id.b.al_pa);
-						qla2x00_clear_loop_id(fcport);
-					}
-				} else if (!qla_ini_mode_enabled(base_vha)) {
-					/*
-					 * In target mode, explicitly kill
-					 * sessions and log out of devices
-					 * that are gone, so that we don't
-					 * end up with an initiator using the
-					 * wrong ACL (if the fabric recycles
-					 * an FC address and we have a stale
-					 * session around) and so that we don't
-					 * report initiators that are no longer
-					 * on the fabric.
-					 */
-					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf077,
-					    "port gone, logging out/killing session: "
-					    "%8phC state 0x%x flags 0x%x fc4_type 0x%x "
-					    "scan_state %d\n",
-					    fcport->port_name,
-					    atomic_read(&fcport->state),
-					    fcport->flags, fcport->fc4_type,
-					    fcport->scan_state);
-					qlt_fc_port_deleted(vha, fcport,
-					    discovery_gen);
-				}
-			}
-		}
-
-		/* Starting free loop ID. */
-		next_loopid = ha->min_external_loopid;
-
-		/*
-		 * Scan through our port list and login entries that need to be
-		 * logged in.
-		 */
-		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (atomic_read(&vha->loop_down_timer) ||
-			    test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
-				break;
-
-			if ((fcport->flags & FCF_FABRIC_DEVICE) == 0 ||
-			    (fcport->flags & FCF_LOGIN_NEEDED) == 0)
-				continue;
-
-			/*
-			 * If we're not an initiator, skip looking for devices
-			 * and logging in.  There's no reason for us to do it,
-			 * and it seems to actively cause problems in target
-			 * mode if we race with the initiator logging into us
-			 * (we might get the "port ID used" status back from
-			 * our login command and log out the initiator, which
-			 * seems to cause havoc).
-			 */
-			if (!qla_ini_mode_enabled(base_vha)) {
-				if (fcport->scan_state == QLA_FCPORT_FOUND) {
-					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf078,
-					    "port %8phC state 0x%x flags 0x%x fc4_type 0x%x "
-					    "scan_state %d (initiator mode disabled; skipping "
-					    "login)\n", fcport->port_name,
-					    atomic_read(&fcport->state),
-					    fcport->flags, fcport->fc4_type,
-					    fcport->scan_state);
-				}
-				continue;
-			}
-
-			if (fcport->loop_id == FC_NO_LOOP_ID) {
-				fcport->loop_id = next_loopid;
-				rval = qla2x00_find_new_loop_id(
-				    base_vha, fcport);
-				if (rval != QLA_SUCCESS) {
-					/* Ran out of IDs to use */
-					break;
-				}
-			}
-			/* Login and update database */
-			qla2x00_fabric_dev_login(vha, fcport, &next_loopid);
-		}
-
-		/* Exit if out of loop IDs. */
-		if (rval != QLA_SUCCESS) {
-			break;
-		}
-
-		/*
-		 * Login and add the new devices to our port list.
-		 */
-		list_for_each_entry_safe(fcport, fcptemp, &new_fcports, list) {
-			if (atomic_read(&vha->loop_down_timer) ||
-			    test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
-				break;
-
-			/*
-			 * If we're not an initiator, skip looking for devices
-			 * and logging in.  There's no reason for us to do it,
-			 * and it seems to actively cause problems in target
-			 * mode if we race with the initiator logging into us
-			 * (we might get the "port ID used" status back from
-			 * our login command and log out the initiator, which
-			 * seems to cause havoc).
-			 */
-			if (qla_ini_mode_enabled(base_vha)) {
-				/* Find a new loop ID to use. */
-				fcport->loop_id = next_loopid;
-				rval = qla2x00_find_new_loop_id(base_vha,
-				    fcport);
-				if (rval != QLA_SUCCESS) {
-					/* Ran out of IDs to use */
-					break;
-				}
-
-				/* Login and update database */
-				qla2x00_fabric_dev_login(vha, fcport,
-				    &next_loopid);
-			} else {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf079,
-					"new port %8phC state 0x%x flags 0x%x fc4_type "
-					"0x%x scan_state %d (initiator mode disabled; "
-					"skipping login)\n",
-					fcport->port_name,
-					atomic_read(&fcport->state),
-					fcport->flags, fcport->fc4_type,
-					fcport->scan_state);
-			}
-
-			list_move_tail(&fcport->list, &vha->vp_fcports);
-		}
 	} while (0);
 
-	/* Free all new device structures not processed. */
-	list_for_each_entry_safe(fcport, fcptemp, &new_fcports, list) {
-		list_del(&fcport->list);
-		kfree(fcport);
-	}
-
-	if (rval) {
+	if (rval)
 		ql_dbg(ql_dbg_disc, vha, 0x2068,
 		    "Configure fabric error exit rval=%d.\n", rval);
-	}
 
 	return (rval);
 }
@@ -3690,12 +4458,11 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
  *	Kernel context.
  */
 static int
-qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
-	struct list_head *new_fcports)
+qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 {
 	int		rval;
 	uint16_t	loop_id;
-	fc_port_t	*fcport, *new_fcport, *fcptemp;
+	fc_port_t	*fcport, *new_fcport;
 	int		found;
 
 	sw_info_t	*swl;
@@ -3704,6 +4471,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 	port_id_t	wrap = {}, nxt_d_id;
 	struct qla_hw_data *ha = vha->hw;
 	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+	unsigned long flags;
 
 	rval = QLA_SUCCESS;
 
@@ -3724,9 +4492,8 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 			swl = NULL;
 		} else if (qla2x00_gnn_id(vha, swl) != QLA_SUCCESS) {
 			swl = NULL;
-		} else if (ql2xiidmaenable &&
-		    qla2x00_gfpn_id(vha, swl) == QLA_SUCCESS) {
-			qla2x00_gpsc(vha, swl);
+		} else if (qla2x00_gfpn_id(vha, swl) != QLA_SUCCESS) {
+			swl = NULL;
 		}
 
 		/* If other queries succeeded probe for FC-4 type */
@@ -3788,11 +4555,6 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 				ql_log(ql_log_warn, vha, 0x2064,
 				    "SNS scan failed -- assuming "
 				    "zero-entry result.\n");
-				list_for_each_entry_safe(fcport, fcptemp,
-				    new_fcports, list) {
-					list_del(&fcport->list);
-					kfree(fcport);
-				}
 				rval = QLA_SUCCESS;
 				break;
 			}
@@ -3835,6 +4597,8 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 		    new_fcport->fc4_type != FC4_TYPE_UNKNOWN))
 			continue;
 
+		spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+
 		/* Locate matching device in database. */
 		found = 0;
 		list_for_each_entry(fcport, &vha->vp_fcports, list) {
@@ -3857,7 +4621,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 			 */
 			if (fcport->d_id.b24 == new_fcport->d_id.b24 &&
 			    (atomic_read(&fcport->state) == FCS_ONLINE ||
-			     !qla_ini_mode_enabled(base_vha))) {
+			     (vha->host->active_mode == MODE_TARGET))) {
 				break;
 			}
 
@@ -3877,7 +4641,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 			 * Log it out if still logged in and mark it for
 			 * relogin later.
 			 */
-			if (!qla_ini_mode_enabled(base_vha)) {
+			if (qla_tgt_mode_enabled(base_vha)) {
 				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf080,
 					 "port changed FC ID, %8phC"
 					 " old %x:%x:%x (loop_id 0x%04x)-> new %x:%x:%x\n",
@@ -3895,25 +4659,19 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 
 			fcport->d_id.b24 = new_fcport->d_id.b24;
 			fcport->flags |= FCF_LOGIN_NEEDED;
-			if (fcport->loop_id != FC_NO_LOOP_ID &&
-			    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
-			    (fcport->flags & FCF_ASYNC_SENT) == 0 &&
-			    fcport->port_type != FCT_INITIATOR &&
-			    fcport->port_type != FCT_BROADCAST) {
-				ha->isp_ops->fabric_logout(vha, fcport->loop_id,
-				    fcport->d_id.b.domain, fcport->d_id.b.area,
-				    fcport->d_id.b.al_pa);
-				qla2x00_clear_loop_id(fcport);
-			}
-
 			break;
 		}
 
-		if (found)
+		if (found) {
+			spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 			continue;
+		}
 		/* If device was not in our fcports list, then add it. */
 		new_fcport->scan_state = QLA_FCPORT_FOUND;
-		list_add_tail(&new_fcport->list, new_fcports);
+		list_add_tail(&new_fcport->list, &vha->vp_fcports);
+
+		spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
 
 		/* Allocate a new replacement fcport. */
 		nxt_d_id.b24 = new_fcport->d_id.b24;
@@ -3927,8 +4685,44 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 		new_fcport->d_id.b24 = nxt_d_id.b24;
 	}
 
-	kfree(new_fcport);
+	qla2x00_free_fcport(new_fcport);
+
+	/*
+	 * Logout all previous fabric dev marked lost, except FCP2 devices.
+	 */
+	list_for_each_entry(fcport, &vha->vp_fcports, list) {
+		if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
+			break;
+
+		if ((fcport->flags & FCF_FABRIC_DEVICE) == 0 ||
+		    (fcport->flags & FCF_LOGIN_NEEDED) == 0)
+			continue;
+
+		if (fcport->scan_state == QLA_FCPORT_SCAN) {
+			if ((qla_dual_mode_enabled(vha) ||
+			    qla_ini_mode_enabled(vha)) &&
+			    atomic_read(&fcport->state) == FCS_ONLINE) {
+				qla2x00_mark_device_lost(vha, fcport,
+					ql2xplogiabsentdevice, 0);
+				if (fcport->loop_id != FC_NO_LOOP_ID &&
+				    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
+				    fcport->port_type != FCT_INITIATOR &&
+				    fcport->port_type != FCT_BROADCAST) {
+					ql_dbg(ql_dbg_disc, vha, 0xffff,
+					    "%s %d %8phC post del sess\n",
+					    __func__, __LINE__,
+					    fcport->port_name);
+
+					qlt_schedule_sess_for_deletion_lock
+						(fcport);
+					continue;
+				}
+			}
+		}
 
+		if (fcport->scan_state == QLA_FCPORT_FOUND)
+			qla24xx_fcport_handle_login(vha, fcport);
+	}
 	return (rval);
 }
 
@@ -3980,64 +4774,6 @@ qla2x00_find_new_loop_id(scsi_qla_host_t *vha, fc_port_t *dev)
 	return (rval);
 }
 
-/*
- * qla2x00_fabric_dev_login
- *	Login fabric target device and update FC port database.
- *
- * Input:
- *	ha:		adapter state pointer.
- *	fcport:		port structure list pointer.
- *	next_loopid:	contains value of a new loop ID that can be used
- *			by the next login attempt.
- *
- * Returns:
- *	qla2x00 local function return status code.
- *
- * Context:
- *	Kernel context.
- */
-static int
-qla2x00_fabric_dev_login(scsi_qla_host_t *vha, fc_port_t *fcport,
-    uint16_t *next_loopid)
-{
-	int	rval;
-	uint8_t opts;
-	struct qla_hw_data *ha = vha->hw;
-
-	rval = QLA_SUCCESS;
-
-	if (IS_ALOGIO_CAPABLE(ha)) {
-		if (fcport->flags & FCF_ASYNC_SENT)
-			return rval;
-		fcport->flags |= FCF_ASYNC_SENT;
-		rval = qla2x00_post_async_login_work(vha, fcport, NULL);
-		if (!rval)
-			return rval;
-	}
-
-	fcport->flags &= ~FCF_ASYNC_SENT;
-	rval = qla2x00_fabric_login(vha, fcport, next_loopid);
-	if (rval == QLA_SUCCESS) {
-		/* Send an ADISC to FCP2 devices.*/
-		opts = 0;
-		if (fcport->flags & FCF_FCP2_DEVICE)
-			opts |= BIT_1;
-		rval = qla2x00_get_port_database(vha, fcport, opts);
-		if (rval != QLA_SUCCESS) {
-			ha->isp_ops->fabric_logout(vha, fcport->loop_id,
-			    fcport->d_id.b.domain, fcport->d_id.b.area,
-			    fcport->d_id.b.al_pa);
-			qla2x00_mark_device_lost(vha, fcport, 1, 0);
-		} else {
-			qla2x00_update_fcport(vha, fcport);
-		}
-	} else {
-		/* Retry Login. */
-		qla2x00_mark_device_lost(vha, fcport, 1, 0);
-	}
-
-	return (rval);
-}
 
 /*
  * qla2x00_fabric_login
@@ -4329,13 +5065,6 @@ qla2x00_update_fcports(scsi_qla_host_t *base_vha)
 				spin_unlock_irqrestore(&ha->vport_slock, flags);
 				qla2x00_rport_del(fcport);
 
-				/*
-				 * Release the target mode FC NEXUS in
-				 * qla_target.c, if target mod is enabled.
-				 */
-				qlt_fc_port_deleted(vha, fcport,
-				    base_vha->total_fcport_update_gen);
-
 				spin_lock_irqsave(&ha->vport_slock, flags);
 			}
 		}
@@ -4718,6 +5447,8 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	if (!(IS_P3P_TYPE(ha)))
 		ha->isp_ops->reset_chip(vha);
 
+	ha->chip_reset++;
+
 	atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
 	if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
@@ -4772,8 +5503,6 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 		/* Requeue all commands in outstanding command list. */
 		qla2x00_abort_all_cmds(vha, DID_RESET << 16);
 	}
-
-	ha->chip_reset++;
 	/* memory barrier */
 	wmb();
 }
@@ -4969,7 +5698,6 @@ qla2x00_restart_isp(scsi_qla_host_t *vha)
 		if (!status) {
 			/* Issue a marker after FW becomes ready. */
 			qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL);
-
 			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		}
 
@@ -5197,7 +5925,7 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 		rval = 1;
 	}
 
-	if (!qla_ini_mode_enabled(vha)) {
+	if (qla_tgt_mode_enabled(vha)) {
 		/* Don't enable full login after initial LIP */
 		nv->firmware_options_1 &= cpu_to_le32(~BIT_13);
 		/* Don't enable LIP full login for initiator */
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 44e404583c86..647828b9e622 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -166,8 +166,8 @@ qla2x00_set_fcport_state(fc_port_t *fcport, int state)
 	/* Don't print state transitions during initial allocation of fcport */
 	if (old_state && old_state != state) {
 		ql_dbg(ql_dbg_disc, fcport->vha, 0x207d,
-		    "FCPort state transitioned from %s to %s - "
-		    "portid=%02x%02x%02x.\n",
+		    "FCPort %8phC state transitioned from %s to %s - "
+			"portid=%02x%02x%02x.\n", fcport->port_name,
 		    port_state_str[old_state], port_state_str[state],
 		    fcport->d_id.b.domain, fcport->d_id.b.area,
 		    fcport->d_id.b.al_pa);
@@ -263,6 +263,7 @@ qla2x00_get_sp(scsi_qla_host_t *vha, fc_port_t *fcport, gfp_t flag)
 	memset(sp, 0, sizeof(*sp));
 	sp->fcport = fcport;
 	sp->iocbs = 1;
+	sp->vha = vha;
 done:
 	if (!sp)
 		QLA_VHA_MARK_NOT_BUSY(vha);
@@ -285,7 +286,7 @@ qla2x00_init_timer(srb_t *sp, unsigned long tmo)
 	sp->u.iocb_cmd.timer.function = qla2x00_sp_timeout;
 	add_timer(&sp->u.iocb_cmd.timer);
 	sp->free = qla2x00_sp_free;
-	if ((IS_QLAFX00(sp->fcport->vha->hw)) &&
+	if ((IS_QLAFX00(((scsi_qla_host_t *)sp->vha)->hw)) &&
 	    (sp->type == SRB_FXIOCB_DCMD))
 		init_completion(&sp->u.iocb_cmd.u.fxiocb.fxiocb_comp);
 	if (sp->type == SRB_ELS_DCMD)
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 834e22197842..33d3d90c089b 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2247,7 +2247,7 @@ qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
 	logio->control_flags =
 	    cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO);
-	if (!sp->fcport->tgt_session ||
+	if (!sp->fcport->se_sess ||
 	    !sp->fcport->keep_nport_handle)
 		logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
@@ -3079,19 +3079,69 @@ qla24xx_abort_iocb(srb_t *sp, struct abort_entry_24xx *abt_iocb)
 	wmb();
 }
 
+static void
+qla2x00_mb_iocb(srb_t *sp, struct mbx_24xx_entry *mbx)
+{
+	int i, sz;
+
+	mbx->entry_type = MBX_IOCB_TYPE;
+	mbx->handle = sp->handle;
+	sz = min(ARRAY_SIZE(mbx->mb), ARRAY_SIZE(sp->u.iocb_cmd.u.mbx.out_mb));
+
+	for (i = 0; i < sz; i++)
+		mbx->mb[i] = cpu_to_le16(sp->u.iocb_cmd.u.mbx.out_mb[i]);
+}
+
+static void
+qla2x00_ctpthru_cmd_iocb(srb_t *sp, struct ct_entry_24xx *ct_pkt)
+{
+	sp->u.iocb_cmd.u.ctarg.iocb = ct_pkt;
+	qla24xx_prep_ms_iocb(sp->vha, &sp->u.iocb_cmd.u.ctarg);
+	ct_pkt->handle = sp->handle;
+}
+
+static void qla2x00_send_notify_ack_iocb(srb_t *sp,
+	struct nack_to_isp *nack)
+{
+	struct imm_ntfy_from_isp *ntfy = sp->u.iocb_cmd.u.nack.ntfy;
+
+	nack->entry_type = NOTIFY_ACK_TYPE;
+	nack->entry_count = 1;
+	nack->ox_id = ntfy->ox_id;
+
+	nack->u.isp24.handle = sp->handle;
+	nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle;
+	if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) {
+		nack->u.isp24.flags = ntfy->u.isp24.flags &
+			cpu_to_le32(NOTIFY24XX_FLAGS_PUREX_IOCB);
+	}
+	nack->u.isp24.srr_rx_id = ntfy->u.isp24.srr_rx_id;
+	nack->u.isp24.status = ntfy->u.isp24.status;
+	nack->u.isp24.status_subcode = ntfy->u.isp24.status_subcode;
+	nack->u.isp24.fw_handle = ntfy->u.isp24.fw_handle;
+	nack->u.isp24.exchange_address = ntfy->u.isp24.exchange_address;
+	nack->u.isp24.srr_rel_offs = ntfy->u.isp24.srr_rel_offs;
+	nack->u.isp24.srr_ui = ntfy->u.isp24.srr_ui;
+	nack->u.isp24.srr_flags = 0;
+	nack->u.isp24.srr_reject_code = 0;
+	nack->u.isp24.srr_reject_code_expl = 0;
+	nack->u.isp24.vp_index = ntfy->u.isp24.vp_index;
+}
+
 int
 qla2x00_start_sp(srb_t *sp)
 {
 	int rval;
-	struct qla_hw_data *ha = sp->fcport->vha->hw;
+	scsi_qla_host_t *vha = (scsi_qla_host_t *)sp->vha;
+	struct qla_hw_data *ha = vha->hw;
 	void *pkt;
 	unsigned long flags;
 
 	rval = QLA_FUNCTION_FAILED;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	pkt = qla2x00_alloc_iocbs(sp->fcport->vha, sp);
+	pkt = qla2x00_alloc_iocbs(vha, sp);
 	if (!pkt) {
-		ql_log(ql_log_warn, sp->fcport->vha, 0x700c,
+		ql_log(ql_log_warn, vha, 0x700c,
 		    "qla2x00_alloc_iocbs failed.\n");
 		goto done;
 	}
@@ -3139,12 +3189,23 @@ qla2x00_start_sp(srb_t *sp)
 	case SRB_ELS_DCMD:
 		qla24xx_els_logo_iocb(sp, pkt);
 		break;
+	case SRB_CT_PTHRU_CMD:
+		qla2x00_ctpthru_cmd_iocb(sp, pkt);
+		break;
+	case SRB_MB_IOCB:
+		qla2x00_mb_iocb(sp, pkt);
+		break;
+	case SRB_NACK_PLOGI:
+	case SRB_NACK_PRLI:
+	case SRB_NACK_LOGO:
+		qla2x00_send_notify_ack_iocb(sp, pkt);
+		break;
 	default:
 		break;
 	}
 
 	wmb();
-	qla2x00_start_iocbs(sp->fcport->vha, ha->req_q_map[0]);
+	qla2x00_start_iocbs(vha, ha->req_q_map[0]);
 done:
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	return rval;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 802b50cc89d0..bb747d7ebdab 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -561,14 +561,50 @@ qla2x00_is_a_vp_did(scsi_qla_host_t *vha, uint32_t rscn_entry)
 	return ret;
 }
 
-static inline fc_port_t *
+fc_port_t *
 qla2x00_find_fcport_by_loopid(scsi_qla_host_t *vha, uint16_t loop_id)
 {
-	fc_port_t *fcport;
+	fc_port_t *f, *tf;
+
+	f = tf = NULL;
+	list_for_each_entry_safe(f, tf, &vha->vp_fcports, list)
+		if (f->loop_id == loop_id)
+			return f;
+	return NULL;
+}
+
+fc_port_t *
+qla2x00_find_fcport_by_wwpn(scsi_qla_host_t *vha, u8 *wwpn, u8 incl_deleted)
+{
+	fc_port_t *f, *tf;
+
+	f = tf = NULL;
+	list_for_each_entry_safe(f, tf, &vha->vp_fcports, list) {
+		if (memcmp(f->port_name, wwpn, WWN_SIZE) == 0) {
+			if (incl_deleted)
+				return f;
+			else if (f->deleted == 0)
+				return f;
+		}
+	}
+	return NULL;
+}
 
-	list_for_each_entry(fcport, &vha->vp_fcports, list)
-		if (fcport->loop_id == loop_id)
-			return fcport;
+fc_port_t *
+qla2x00_find_fcport_by_nportid(scsi_qla_host_t *vha, port_id_t *id,
+	u8 incl_deleted)
+{
+	fc_port_t *f, *tf;
+
+	f = tf = NULL;
+	list_for_each_entry_safe(f, tf, &vha->vp_fcports, list) {
+		if (f->d_id.b24 == id->b24) {
+			if (incl_deleted)
+				return f;
+			else if (f->deleted == 0)
+				return f;
+		}
+	}
 	return NULL;
 }
 
@@ -934,7 +970,11 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 			ql_dbg(ql_dbg_async, vha, 0x508a,
 			    "Marking port lost loopid=%04x portid=%06x.\n",
 			    fcport->loop_id, fcport->d_id.b24);
-			qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1);
+			if (qla_ini_mode_enabled(vha)) {
+				qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1);
+				fcport->logout_on_delete = 0;
+				qlt_schedule_sess_for_deletion_lock(fcport);
+			}
 			break;
 
 global_port_update:
@@ -1024,27 +1064,17 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 		if (qla2x00_is_a_vp_did(vha, rscn_entry))
 			break;
 
-		/*
-		 * Search for the rport related to this RSCN entry and mark it
-		 * as lost.
-		 */
-		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (atomic_read(&fcport->state) != FCS_ONLINE)
-				continue;
-			if (fcport->d_id.b24 == rscn_entry) {
-				qla2x00_mark_device_lost(vha, fcport, 0, 0);
-				break;
-			}
-		}
-
 		atomic_set(&vha->loop_down_timer, 0);
 		vha->flags.management_server_logged_in = 0;
+		{
+			struct event_arg ea;
 
-		set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
-		set_bit(RSCN_UPDATE, &vha->dpc_flags);
-		qla2x00_post_aen_work(vha, FCH_EVT_RSCN, rscn_entry);
+			memset(&ea, 0, sizeof(ea));
+			ea.event = FCME_RSCN;
+			ea.id.b24 = rscn_entry;
+			qla2x00_fcport_event_handler(vha, &ea);
+		}
 		break;
-
 	/* case MBA_RIO_RESPONSE: */
 	case MBA_ZIO_RESPONSE:
 		ql_dbg(ql_dbg_async, vha, 0x5015,
@@ -1235,7 +1265,8 @@ qla2x00_get_sp_from_handle(scsi_qla_host_t *vha, const char *func,
 	index = LSW(pkt->handle);
 	if (index >= req->num_outstanding_cmds) {
 		ql_log(ql_log_warn, vha, 0x5031,
-		    "Invalid command index (%x).\n", index);
+			   "Invalid command index (%x) type %8ph.\n",
+			   index, iocb);
 		if (IS_P3P_TYPE(ha))
 			set_bit(FCOE_CTX_RESET_NEEDED, &vha->dpc_flags);
 		else
@@ -1346,6 +1377,49 @@ qla2x00_mbx_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 	sp->done(vha, sp, 0);
 }
 
+static void
+qla24xx_mbx_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
+    struct mbx_24xx_entry *pkt)
+{
+	const char func[] = "MBX-IOCB2";
+	srb_t *sp;
+	struct srb_iocb *si;
+	u16 sz, i;
+	int res;
+
+	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
+	if (!sp)
+		return;
+
+	si = &sp->u.iocb_cmd;
+	sz = min(ARRAY_SIZE(pkt->mb), ARRAY_SIZE(sp->u.iocb_cmd.u.mbx.in_mb));
+
+	for (i = 0; i < sz; i++)
+		si->u.mbx.in_mb[i] = le16_to_cpu(pkt->mb[i]);
+
+	res = (si->u.mbx.in_mb[0] & MBS_MASK);
+
+	sp->done(vha, sp, res);
+}
+
+static void
+qla24xxx_nack_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
+    struct nack_to_isp *pkt)
+{
+	const char func[] = "nack";
+	srb_t *sp;
+	int res = 0;
+
+	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
+	if (!sp)
+		return;
+
+	if (pkt->u.isp2x.status != cpu_to_le16(NOTIFY_ACK_SUCCESS))
+		res = QLA_FUNCTION_FAILED;
+
+	sp->done(vha, sp, res);
+}
+
 static void
 qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
     sts_entry_t *pkt, int iocb_type)
@@ -1356,50 +1430,63 @@ qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	struct bsg_job *bsg_job;
 	struct fc_bsg_reply *bsg_reply;
 	uint16_t comp_status;
-	int res;
+	int res = 0;
 
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (!sp)
 		return;
 
-	bsg_job = sp->u.bsg_job;
-	bsg_reply = bsg_job->reply;
-
-	type = "ct pass-through";
-
-	comp_status = le16_to_cpu(pkt->comp_status);
-
-	/* return FC_CTELS_STATUS_OK and leave the decoding of the ELS/CT
-	 * fc payload  to the caller
-	 */
-	bsg_reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
-	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-
-	if (comp_status != CS_COMPLETE) {
-		if (comp_status == CS_DATA_UNDERRUN) {
-			res = DID_OK << 16;
-			bsg_reply->reply_payload_rcv_len =
-			    le16_to_cpu(((sts_entry_t *)pkt)->rsp_info_len);
-
-			ql_log(ql_log_warn, vha, 0x5048,
-			    "CT pass-through-%s error "
-			    "comp_status-status=0x%x total_byte = 0x%x.\n",
-			    type, comp_status,
-			    bsg_reply->reply_payload_rcv_len);
-		} else {
-			ql_log(ql_log_warn, vha, 0x5049,
-			    "CT pass-through-%s error "
-			    "comp_status-status=0x%x.\n", type, comp_status);
-			res = DID_ERROR << 16;
-			bsg_reply->reply_payload_rcv_len = 0;
-		}
-		ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x5035,
-		    (uint8_t *)pkt, sizeof(*pkt));
-	} else {
-		res = DID_OK << 16;
-		bsg_reply->reply_payload_rcv_len =
-		    bsg_job->reply_payload.payload_len;
-		bsg_job->reply_len = 0;
+	switch (sp->type) {
+	case SRB_CT_CMD:
+	    bsg_job = sp->u.bsg_job;
+	    bsg_reply = bsg_job->reply;
+
+	    type = "ct pass-through";
+
+	    comp_status = le16_to_cpu(pkt->comp_status);
+
+	    /*
+	     * return FC_CTELS_STATUS_OK and leave the decoding of the ELS/CT
+	     * fc payload  to the caller
+	     */
+	    bsg_reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
+	    bsg_job->reply_len = sizeof(struct fc_bsg_reply);
+
+	    if (comp_status != CS_COMPLETE) {
+		    if (comp_status == CS_DATA_UNDERRUN) {
+			    res = DID_OK << 16;
+			    bsg_reply->reply_payload_rcv_len =
+				le16_to_cpu(((sts_entry_t *)pkt)->rsp_info_len);
+
+			    ql_log(ql_log_warn, vha, 0x5048,
+				"CT pass-through-%s error comp_status=0x%x total_byte=0x%x.\n",
+				type, comp_status,
+				bsg_reply->reply_payload_rcv_len);
+		    } else {
+			    ql_log(ql_log_warn, vha, 0x5049,
+				"CT pass-through-%s error comp_status=0x%x.\n",
+				type, comp_status);
+			    res = DID_ERROR << 16;
+			    bsg_reply->reply_payload_rcv_len = 0;
+		    }
+		    ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x5035,
+			(uint8_t *)pkt, sizeof(*pkt));
+	    } else {
+		    res = DID_OK << 16;
+		    bsg_reply->reply_payload_rcv_len =
+			bsg_job->reply_payload.payload_len;
+		    bsg_job->reply_len = 0;
+	    }
+	    break;
+	case SRB_CT_PTHRU_CMD:
+	    /*
+	     * borrowing sts_entry_24xx.comp_status.
+	     * same location as ct_entry_24xx.comp_status
+	     */
+	     res = qla2x00_chk_ms_status(vha, (ms_iocb_entry_t *)pkt,
+		 (struct ct_sns_rsp *)sp->u.iocb_cmd.u.ctarg.rsp,
+		 sp->name);
+	     break;
 	}
 
 	sp->done(vha, sp, res);
@@ -1440,6 +1527,15 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 		    "Completing %s: (%p) type=%d.\n", type, sp, sp->type);
 		sp->done(vha, sp, 0);
 		return;
+	case SRB_CT_PTHRU_CMD:
+		/* borrowing sts_entry_24xx.comp_status.
+		   same location as ct_entry_24xx.comp_status
+		 */
+		res = qla2x00_chk_ms_status(vha, (ms_iocb_entry_t *)pkt,
+			(struct ct_sns_rsp *)sp->u.iocb_cmd.u.ctarg.rsp,
+			sp->name);
+		sp->done(vha, sp, res);
+		return;
 	default:
 		ql_dbg(ql_dbg_user, vha, 0x503e,
 		    "Unrecognized SRB: (%p) type=%d.\n", sp, sp->type);
@@ -1566,6 +1662,8 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 
 	iop[0] = le32_to_cpu(logio->io_parameter[0]);
 	iop[1] = le32_to_cpu(logio->io_parameter[1]);
+	lio->u.logio.iop[0] = iop[0];
+	lio->u.logio.iop[1] = iop[1];
 	switch (iop[0]) {
 	case LSC_SCODE_PORTID_USED:
 		data[0] = MBS_PORT_ID_USED;
@@ -2074,6 +2172,7 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 	int res = 0;
 	uint16_t state_flags = 0;
 	uint16_t retry_delay = 0;
+	uint8_t no_logout = 0;
 
 	sts = (sts_entry_t *) pkt;
 	sts24 = (struct sts_entry_24xx *) pkt;
@@ -2334,6 +2433,7 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 		break;
 
 	case CS_PORT_LOGGED_OUT:
+		no_logout = 1;
 	case CS_PORT_CONFIG_CHG:
 	case CS_PORT_BUSY:
 	case CS_INCOMPLETE:
@@ -2356,14 +2456,21 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 				break;
 		}
 
-		ql_dbg(ql_dbg_io, fcport->vha, 0x3021,
-		    "Port to be marked lost on fcport=%02x%02x%02x, current "
-		    "port state= %s.\n", fcport->d_id.b.domain,
-		    fcport->d_id.b.area, fcport->d_id.b.al_pa,
-		    port_state_str[atomic_read(&fcport->state)]);
+		if (atomic_read(&fcport->state) == FCS_ONLINE) {
+			ql_dbg(ql_dbg_disc, fcport->vha, 0x3021,
+				"Port to be marked lost on fcport=%02x%02x%02x, current "
+				"port state= %s comp_status %x.\n", fcport->d_id.b.domain,
+				fcport->d_id.b.area, fcport->d_id.b.al_pa,
+				port_state_str[atomic_read(&fcport->state)],
+				comp_status);
+
+			if (no_logout)
+				fcport->logout_on_delete = 0;
 
-		if (atomic_read(&fcport->state) == FCS_ONLINE)
 			qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1);
+			qlt_schedule_sess_for_deletion_lock(fcport);
+		}
+
 		break;
 
 	case CS_ABORTED:
@@ -2627,10 +2734,16 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 			}
 		case ABTS_RESP_24XX:
 		case CTIO_TYPE7:
-		case NOTIFY_ACK_TYPE:
 		case CTIO_CRC2:
 			qlt_response_pkt_all_vps(vha, (response_t *)pkt);
 			break;
+		case NOTIFY_ACK_TYPE:
+			if (pkt->handle == QLA_TGT_SKIP_HANDLE)
+				qlt_response_pkt_all_vps(vha, (response_t *)pkt);
+			else
+				qla24xxx_nack_iocb_entry(vha, rsp->req,
+					(struct nack_to_isp *)pkt);
+			break;
 		case MARKER_TYPE:
 			/* Do nothing in this case, this check is to prevent it
 			 * from falling into default case
@@ -2640,6 +2753,10 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 			qla24xx_abort_iocb_entry(vha, rsp->req,
 			    (struct abort_entry_24xx *)pkt);
 			break;
+		case MBX_IOCB_TYPE:
+			qla24xx_mbx_iocb_entry(vha, rsp->req,
+			    (struct mbx_24xx_entry *)pkt);
+			break;
 		default:
 			/* Type Not Supported. */
 			ql_dbg(ql_dbg_async, vha, 0x5042,
@@ -2656,8 +2773,9 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 	if (IS_P3P_TYPE(ha)) {
 		struct device_reg_82xx __iomem *reg = &ha->iobase->isp82;
 		WRT_REG_DWORD(&reg->rsp_q_out[0], rsp->ring_index);
-	} else
+	} else {
 		WRT_REG_DWORD(rsp->rsp_q_out, rsp->ring_index);
+	}
 }
 
 static void
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 67f64db390b0..64f04aa2a503 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -1637,94 +1637,6 @@ qla2x00_init_firmware(scsi_qla_host_t *vha, uint16_t size)
 	return rval;
 }
 
-/*
- * qla2x00_get_node_name_list
- *      Issue get node name list mailbox command, kmalloc()
- *      and return the resulting list. Caller must kfree() it!
- *
- * Input:
- *      ha = adapter state pointer.
- *      out_data = resulting list
- *      out_len = length of the resulting list
- *
- * Returns:
- *      qla2x00 local function return status code.
- *
- * Context:
- *      Kernel context.
- */
-int
-qla2x00_get_node_name_list(scsi_qla_host_t *vha, void **out_data, int *out_len)
-{
-	struct qla_hw_data *ha = vha->hw;
-	struct qla_port_24xx_data *list = NULL;
-	void *pmap;
-	mbx_cmd_t mc;
-	dma_addr_t pmap_dma;
-	ulong dma_size;
-	int rval, left;
-
-	left = 1;
-	while (left > 0) {
-		dma_size = left * sizeof(*list);
-		pmap = dma_alloc_coherent(&ha->pdev->dev, dma_size,
-					 &pmap_dma, GFP_KERNEL);
-		if (!pmap) {
-			ql_log(ql_log_warn, vha, 0x113f,
-			    "%s(%ld): DMA Alloc failed of %ld\n",
-			    __func__, vha->host_no, dma_size);
-			rval = QLA_MEMORY_ALLOC_FAILED;
-			goto out;
-		}
-
-		mc.mb[0] = MBC_PORT_NODE_NAME_LIST;
-		mc.mb[1] = BIT_1 | BIT_3;
-		mc.mb[2] = MSW(pmap_dma);
-		mc.mb[3] = LSW(pmap_dma);
-		mc.mb[6] = MSW(MSD(pmap_dma));
-		mc.mb[7] = LSW(MSD(pmap_dma));
-		mc.mb[8] = dma_size;
-		mc.out_mb = MBX_0|MBX_1|MBX_2|MBX_3|MBX_6|MBX_7|MBX_8;
-		mc.in_mb = MBX_0|MBX_1;
-		mc.tov = 30;
-		mc.flags = MBX_DMA_IN;
-
-		rval = qla2x00_mailbox_command(vha, &mc);
-		if (rval != QLA_SUCCESS) {
-			if ((mc.mb[0] == MBS_COMMAND_ERROR) &&
-			    (mc.mb[1] == 0xA)) {
-				left += le16_to_cpu(mc.mb[2]) /
-				    sizeof(struct qla_port_24xx_data);
-				goto restart;
-			}
-			goto out_free;
-		}
-
-		left = 0;
-
-		list = kmemdup(pmap, dma_size, GFP_KERNEL);
-		if (!list) {
-			ql_log(ql_log_warn, vha, 0x1140,
-			    "%s(%ld): failed to allocate node names list "
-			    "structure.\n", __func__, vha->host_no);
-			rval = QLA_MEMORY_ALLOC_FAILED;
-			goto out_free;
-		}
-
-restart:
-		dma_free_coherent(&ha->pdev->dev, dma_size, pmap, pmap_dma);
-	}
-
-	*out_data = list;
-	*out_len = dma_size;
-
-out:
-	return rval;
-
-out_free:
-	dma_free_coherent(&ha->pdev->dev, dma_size, pmap, pmap_dma);
-	return rval;
-}
 
 /*
  * qla2x00_get_port_database
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 62ca1ddb0cc7..9c4699623410 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1043,6 +1043,34 @@ qla2x00_wait_for_hba_online(scsi_qla_host_t *vha)
 	return (return_status);
 }
 
+static inline int test_fcport_count(scsi_qla_host_t *vha)
+{
+	struct qla_hw_data *ha = vha->hw;
+	unsigned long flags;
+	int res;
+
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+	ql_dbg(ql_dbg_init, vha, 0xffff,
+		"tgt %p, fcport_count=%d\n",
+		vha, vha->fcport_count);
+	res = (vha->fcport_count == 0);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+
+	return res;
+}
+
+/*
+ * qla2x00_wait_for_sess_deletion can only be called from remove_one.
+ * it has dependency on UNLOADING flag to stop device discovery
+ */
+static void
+qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha)
+{
+	qla2x00_mark_all_devices_lost(vha, 0);
+
+	wait_event(vha->fcport_waitQ, test_fcport_count(vha));
+}
+
 /*
  * qla2x00_wait_for_hba_ready
  * Wait till the HBA is ready before doing driver unload
@@ -2904,6 +2932,18 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto probe_init_failed;
 
+	base_vha->gnl.size = (ha->max_loop_id + 1) *
+		sizeof(struct get_name_list_extended);
+	base_vha->gnl.l = dma_alloc_coherent(&ha->pdev->dev,
+		base_vha->gnl.size, &base_vha->gnl.ldma, GFP_KERNEL);
+	INIT_LIST_HEAD(&base_vha->gnl.fcports);
+
+	if (base_vha->gnl.l == NULL) {
+		ql_log(ql_log_fatal, base_vha, 0xffff,
+			"Alloc failed for name list.\n");
+		goto probe_init_failed;
+	}
+
 	/* Alloc arrays of request and response ring ptrs */
 	if (!qla2x00_alloc_queues(ha, req, rsp)) {
 		ql_log(ql_log_fatal, base_vha, 0x003d,
@@ -3123,7 +3163,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ql_dbg(ql_dbg_init, base_vha, 0x00f2,
 	    "Init done and hba is online.\n");
 
-	if (qla_ini_mode_enabled(base_vha))
+	if (qla_ini_mode_enabled(base_vha) ||
+		qla_dual_mode_enabled(base_vha))
 		scsi_scan_host(host);
 	else
 		ql_dbg(ql_dbg_init, base_vha, 0x0122,
@@ -3372,21 +3413,26 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	 * resources.
 	 */
 	if (!atomic_read(&pdev->enable_cnt)) {
+		dma_free_coherent(&ha->pdev->dev, base_vha->gnl.size,
+		    base_vha->gnl.l, base_vha->gnl.ldma);
+
 		scsi_host_put(base_vha->host);
 		kfree(ha);
 		pci_set_drvdata(pdev, NULL);
 		return;
 	}
-
 	qla2x00_wait_for_hba_ready(base_vha);
 
-	/* if UNLOAD flag is already set, then continue unload,
+	/*
+	 * if UNLOAD flag is already set, then continue unload,
 	 * where it was set first.
 	 */
 	if (test_bit(UNLOADING, &base_vha->dpc_flags))
 		return;
 
 	set_bit(UNLOADING, &base_vha->dpc_flags);
+	dma_free_coherent(&ha->pdev->dev,
+		base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma);
 
 	if (IS_QLAFX00(ha))
 		qlafx00_driver_shutdown(base_vha, 20);
@@ -3535,10 +3581,14 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport,
 		qla2xxx_wake_dpc(base_vha);
 	} else {
 		int now;
-		if (rport)
+		if (rport) {
+			ql_dbg(ql_dbg_disc, fcport->vha, 0xffff,
+				"%s %8phN. rport %p roles %x \n",
+				__func__, fcport->port_name, rport,
+				rport->roles);
 			fc_remote_port_delete(rport);
+		}
 		qlt_do_generation_tick(vha, &now);
-		qlt_fc_port_deleted(vha, fcport, now);
 	}
 }
 
@@ -3581,7 +3631,7 @@ void qla2x00_mark_device_lost(scsi_qla_host_t *vha, fc_port_t *fcport,
 		fcport->login_retry = vha->hw->login_retry_count;
 
 		ql_dbg(ql_dbg_disc, vha, 0x2067,
-		    "Port login retry %8phN, id = 0x%04x retry cnt=%d.\n",
+		    "Port login retry %8phN, lid 0x%04x retry cnt=%d.\n",
 		    fcport->port_name, fcport->loop_id, fcport->login_retry);
 	}
 }
@@ -3604,7 +3654,13 @@ qla2x00_mark_all_devices_lost(scsi_qla_host_t *vha, int defer)
 {
 	fc_port_t *fcport;
 
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		   "Mark all dev lost\n");
+
 	list_for_each_entry(fcport, &vha->vp_fcports, list) {
+		fcport->scan_state = 0;
+		qlt_schedule_sess_for_deletion_lock(fcport);
+
 		if (vha->vp_idx != 0 && vha->vp_idx != fcport->vha->vp_idx)
 			continue;
 
@@ -4219,6 +4275,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 
 	spin_lock_init(&vha->work_lock);
 	spin_lock_init(&vha->cmd_list_lock);
+	init_waitqueue_head(&vha->fcport_waitQ);
 
 	sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no);
 	ql_dbg(ql_dbg_init, vha, 0x0041,
@@ -4232,7 +4289,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	return vha;
 }
 
-static struct qla_work_evt *
+struct qla_work_evt *
 qla2x00_alloc_work(struct scsi_qla_host *vha, enum qla_work_type type)
 {
 	struct qla_work_evt *e;
@@ -4254,7 +4311,7 @@ qla2x00_alloc_work(struct scsi_qla_host *vha, enum qla_work_type type)
 	return e;
 }
 
-static int
+int
 qla2x00_post_work(struct scsi_qla_host *vha, struct qla_work_evt *e)
 {
 	unsigned long flags;
@@ -4315,7 +4372,6 @@ int qla2x00_post_async_##name##_work(		\
 }
 
 qla2x00_post_async_work(login, QLA_EVT_ASYNC_LOGIN);
-qla2x00_post_async_work(login_done, QLA_EVT_ASYNC_LOGIN_DONE);
 qla2x00_post_async_work(logout, QLA_EVT_ASYNC_LOGOUT);
 qla2x00_post_async_work(logout_done, QLA_EVT_ASYNC_LOGOUT_DONE);
 qla2x00_post_async_work(adisc, QLA_EVT_ASYNC_ADISC);
@@ -4368,6 +4424,67 @@ qlafx00_post_aenfx_work(struct scsi_qla_host *vha,  uint32_t evtcode,
 	return qla2x00_post_work(vha, e);
 }
 
+int qla24xx_post_upd_fcport_work(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	struct qla_work_evt *e;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_UPD_FCPORT);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.fcport.fcport = fcport;
+	return qla2x00_post_work(vha, e);
+}
+
+static
+void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
+{
+	unsigned long flags;
+	fc_port_t *fcport =  NULL;
+	struct qlt_plogi_ack_t *pla =
+	    (struct qlt_plogi_ack_t *)e->u.new_sess.pla;
+
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	fcport = qla2x00_find_fcport_by_wwpn(vha, e->u.new_sess.port_name, 1);
+	if (fcport) {
+		fcport->d_id = e->u.new_sess.id;
+		if (pla) {
+			fcport->fw_login_state = DSC_LS_PLOGI_PEND;
+			qlt_plogi_ack_link(vha, pla, fcport, QLT_PLOGI_LINK_SAME_WWN);
+			/* we took an extra ref_count to prevent PLOGI ACK when
+			 * fcport/sess has not been created.
+			 */
+			pla->ref_count--;
+		}
+	} else {
+		fcport = qla2x00_alloc_fcport(vha, GFP_KERNEL);
+		if (fcport) {
+			fcport->d_id = e->u.new_sess.id;
+			fcport->scan_state = QLA_FCPORT_FOUND;
+			fcport->flags |= FCF_FABRIC_DEVICE;
+			fcport->fw_login_state = DSC_LS_PLOGI_PEND;
+
+			memcpy(fcport->port_name, e->u.new_sess.port_name,
+			    WWN_SIZE);
+			list_add_tail(&fcport->list, &vha->vp_fcports);
+
+			if (pla) {
+				qlt_plogi_ack_link(vha, pla, fcport,
+				    QLT_PLOGI_LINK_SAME_WWN);
+				pla->ref_count--;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+	if (fcport) {
+		if (pla)
+			qlt_plogi_ack_unref(vha, pla);
+		else
+			qla24xx_async_gnl(vha, fcport);
+	}
+}
+
 void
 qla2x00_do_work(struct scsi_qla_host *vha)
 {
@@ -4394,10 +4511,6 @@ qla2x00_do_work(struct scsi_qla_host *vha)
 			qla2x00_async_login(vha, e->u.logio.fcport,
 			    e->u.logio.data);
 			break;
-		case QLA_EVT_ASYNC_LOGIN_DONE:
-			qla2x00_async_login_done(vha, e->u.logio.fcport,
-			    e->u.logio.data);
-			break;
 		case QLA_EVT_ASYNC_LOGOUT:
 			qla2x00_async_logout(vha, e->u.logio.fcport);
 			break;
@@ -4419,6 +4532,34 @@ qla2x00_do_work(struct scsi_qla_host *vha)
 		case QLA_EVT_AENFX:
 			qlafx00_process_aen(vha, e);
 			break;
+		case QLA_EVT_GIDPN:
+			qla24xx_async_gidpn(vha, e->u.fcport.fcport);
+			break;
+		case QLA_EVT_GPNID:
+			qla24xx_async_gpnid(vha, &e->u.gpnid.id);
+			break;
+		case QLA_EVT_GPNID_DONE:
+			qla24xx_async_gpnid_done(vha, e->u.iosb.sp);
+			break;
+		case QLA_EVT_NEW_SESS:
+			qla24xx_create_new_sess(vha, e);
+			break;
+		case QLA_EVT_GPDB:
+			qla24xx_async_gpdb(vha, e->u.fcport.fcport,
+			    e->u.fcport.opt);
+			break;
+		case QLA_EVT_GPSC:
+			qla24xx_async_gpsc(vha, e->u.fcport.fcport);
+			break;
+		case QLA_EVT_UPD_FCPORT:
+			qla2x00_update_fcport(vha, e->u.fcport.fcport);
+			break;
+		case QLA_EVT_GNL:
+			qla24xx_async_gnl(vha, e->u.fcport.fcport);
+			break;
+		case QLA_EVT_NACK:
+			qla24xx_do_nack_work(vha, e);
+			break;
 		}
 		if (e->flags & QLA_EVT_FLAG_FREE)
 			kfree(e);
@@ -4435,9 +4576,7 @@ void qla2x00_relogin(struct scsi_qla_host *vha)
 {
 	fc_port_t       *fcport;
 	int status;
-	uint16_t        next_loopid = 0;
-	struct qla_hw_data *ha = vha->hw;
-	uint16_t data[2];
+	struct event_arg ea;
 
 	list_for_each_entry(fcport, &vha->vp_fcports, list) {
 	/*
@@ -4448,77 +4587,38 @@ void qla2x00_relogin(struct scsi_qla_host *vha)
 		    fcport->login_retry && !(fcport->flags & FCF_ASYNC_SENT)) {
 			fcport->login_retry--;
 			if (fcport->flags & FCF_FABRIC_DEVICE) {
-				if (fcport->flags & FCF_FCP2_DEVICE)
-					ha->isp_ops->fabric_logout(vha,
-							fcport->loop_id,
-							fcport->d_id.b.domain,
-							fcport->d_id.b.area,
-							fcport->d_id.b.al_pa);
-
-				if (fcport->loop_id == FC_NO_LOOP_ID) {
-					fcport->loop_id = next_loopid =
-					    ha->min_external_loopid;
-					status = qla2x00_find_new_loop_id(
-					    vha, fcport);
-					if (status != QLA_SUCCESS) {
-						/* Ran out of IDs to use */
-						break;
-					}
-				}
-
-				if (IS_ALOGIO_CAPABLE(ha)) {
-					fcport->flags |= FCF_ASYNC_SENT;
-					data[0] = 0;
-					data[1] = QLA_LOGIO_LOGIN_RETRIED;
-					status = qla2x00_post_async_login_work(
-					    vha, fcport, data);
-					if (status == QLA_SUCCESS)
-						continue;
-					/* Attempt a retry. */
-					status = 1;
-				} else {
-					status = qla2x00_fabric_login(vha,
-					    fcport, &next_loopid);
-					if (status ==  QLA_SUCCESS) {
-						int status2;
-						uint8_t opts;
-
-						opts = 0;
-						if (fcport->flags &
-						    FCF_FCP2_DEVICE)
-							opts |= BIT_1;
-						status2 =
-						    qla2x00_get_port_database(
-							vha, fcport, opts);
-						if (status2 != QLA_SUCCESS)
-							status = 1;
-					}
-				}
-			} else
+				ql_dbg(ql_dbg_disc, fcport->vha, 0xffff,
+				    "%s %8phC DS %d LS %d\n", __func__,
+				    fcport->port_name, fcport->disc_state,
+				    fcport->fw_login_state);
+				memset(&ea, 0, sizeof(ea));
+				ea.event = FCME_RELOGIN;
+				ea.fcport = fcport;
+				qla2x00_fcport_event_handler(vha, &ea);
+			} else {
 				status = qla2x00_local_device_login(vha,
 								fcport);
+				if (status == QLA_SUCCESS) {
+					fcport->old_loop_id = fcport->loop_id;
+					ql_dbg(ql_dbg_disc, vha, 0x2003,
+					    "Port login OK: logged in ID 0x%x.\n",
+					    fcport->loop_id);
+					qla2x00_update_fcport(vha, fcport);
+				} else if (status == 1) {
+					set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+					/* retry the login again */
+					ql_dbg(ql_dbg_disc, vha, 0x2007,
+					    "Retrying %d login again loop_id 0x%x.\n",
+					    fcport->login_retry,
+					    fcport->loop_id);
+				} else {
+					fcport->login_retry = 0;
+				}
 
-			if (status == QLA_SUCCESS) {
-				fcport->old_loop_id = fcport->loop_id;
-
-				ql_dbg(ql_dbg_disc, vha, 0x2003,
-				    "Port login OK: logged in ID 0x%x.\n",
-				    fcport->loop_id);
-
-				qla2x00_update_fcport(vha, fcport);
-
-			} else if (status == 1) {
-				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-				/* retry the login again */
-				ql_dbg(ql_dbg_disc, vha, 0x2007,
-				    "Retrying %d login again loop_id 0x%x.\n",
-				    fcport->login_retry, fcport->loop_id);
-			} else {
-				fcport->login_retry = 0;
+				if (fcport->login_retry == 0 &&
+				    status != QLA_SUCCESS)
+					qla2x00_clear_loop_id(fcport);
 			}
-
-			if (fcport->login_retry == 0 && status != QLA_SUCCESS)
-				qla2x00_clear_loop_id(fcport);
 		}
 		if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
 			break;
@@ -5182,7 +5282,8 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 	struct pci_dev *pdev = ha->pdev;
 	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
 
-	/* if UNLOAD flag is already set, then continue unload,
+	/*
+	 * if UNLOAD flag is already set, then continue unload,
 	 * where it was set first.
 	 */
 	if (test_bit(UNLOADING, &base_vha->dpc_flags))
@@ -5191,6 +5292,8 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 	ql_log(ql_log_warn, base_vha, 0x015b,
 	    "Disabling adapter.\n");
 
+	qla2x00_wait_for_sess_deletion(base_vha);
+
 	set_bit(UNLOADING, &base_vha->dpc_flags);
 
 	qla2x00_delete_all_vps(ha, base_vha);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 40b61a327786..e4d7d32c82e7 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -118,6 +118,9 @@ static void qlt_send_notify_ack(struct scsi_qla_host *vha,
 	uint16_t srr_flags, uint16_t srr_reject_code, uint8_t srr_explan);
 static void qlt_send_term_imm_notif(struct scsi_qla_host *vha,
 	struct imm_ntfy_from_isp *imm, int ha_locked);
+static struct fc_port *qlt_create_sess(struct scsi_qla_host *vha,
+	fc_port_t *fcport, bool local);
+void qlt_unreg_sess(struct fc_port *sess);
 /*
  * Global Variables
  */
@@ -378,6 +381,247 @@ void qlt_response_pkt_all_vps(struct scsi_qla_host *vha, response_t *pkt)
 /*
  * All qlt_plogi_ack_t operations are protected by hardware_lock
  */
+static int qla24xx_post_nack_work(struct scsi_qla_host *vha, fc_port_t *fcport,
+	struct imm_ntfy_from_isp *ntfy, int type)
+{
+	struct qla_work_evt *e;
+	e = qla2x00_alloc_work(vha, QLA_EVT_NACK);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.nack.fcport = fcport;
+	e->u.nack.type = type;
+	memcpy(e->u.nack.iocb, ntfy, sizeof(struct imm_ntfy_from_isp));
+	return qla2x00_post_work(vha, e);
+}
+
+static
+void qla2x00_async_nack_sp_done(void *v, void *s, int res)
+{
+	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
+	struct srb *sp = (struct srb *)s;
+	unsigned long flags;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async done-%s res %x %8phC  type %d\n",
+		sp->name, res, sp->fcport->port_name, sp->type);
+
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	sp->fcport->flags &= ~FCF_ASYNC_SENT;
+	sp->fcport->chip_reset = vha->hw->chip_reset;
+
+	switch (sp->type) {
+	case SRB_NACK_PLOGI:
+		sp->fcport->login_gen++;
+		sp->fcport->fw_login_state = DSC_LS_PLOGI_COMP;
+		sp->fcport->logout_on_delete = 1;
+		break;
+
+	case SRB_NACK_PRLI:
+		sp->fcport->fw_login_state = DSC_LS_PRLI_COMP;
+		sp->fcport->deleted = 0;
+
+		if (!sp->fcport->login_succ &&
+		    !IS_SW_RESV_ADDR(sp->fcport->d_id)) {
+			sp->fcport->login_succ = 1;
+
+			vha->fcport_count++;
+
+			if (!IS_IIDMA_CAPABLE(vha->hw) ||
+			    !vha->hw->flags.gpsc_supported) {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+					"%s %d %8phC post upd_fcport fcp_cnt %d\n",
+					__func__, __LINE__,
+					sp->fcport->port_name,
+					vha->fcport_count);
+
+				qla24xx_post_upd_fcport_work(vha, sp->fcport);
+			} else {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+					"%s %d %8phC post gpsc fcp_cnt %d\n",
+					__func__, __LINE__,
+					sp->fcport->port_name,
+					vha->fcport_count);
+
+				qla24xx_post_gpsc_work(vha, sp->fcport);
+			}
+		}
+		break;
+
+	case SRB_NACK_LOGO:
+		sp->fcport->login_gen++;
+		sp->fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
+		qlt_logo_completion_handler(sp->fcport, MBS_COMMAND_COMPLETE);
+		break;
+	}
+	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+	sp->free(vha, sp);
+}
+
+int qla24xx_async_notify_ack(scsi_qla_host_t *vha, fc_port_t *fcport,
+	struct imm_ntfy_from_isp *ntfy, int type)
+{
+	int rval = QLA_FUNCTION_FAILED;
+	srb_t *sp;
+	char *c = NULL;
+
+	fcport->flags |= FCF_ASYNC_SENT;
+	switch (type) {
+	case SRB_NACK_PLOGI:
+		fcport->fw_login_state = DSC_LS_PLOGI_PEND;
+		c = "PLOGI";
+		break;
+	case SRB_NACK_PRLI:
+		fcport->fw_login_state = DSC_LS_PRLI_PEND;
+		c = "PRLI";
+		break;
+	case SRB_NACK_LOGO:
+		fcport->fw_login_state = DSC_LS_LOGO_PEND;
+		c = "LOGO";
+		break;
+	}
+
+	sp = qla2x00_get_sp(vha, fcport, GFP_ATOMIC);
+	if (!sp)
+		goto done;
+
+	sp->type = type;
+	sp->name = "nack";
+
+	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha)+2);
+
+	sp->u.iocb_cmd.u.nack.ntfy = ntfy;
+
+	sp->done = qla2x00_async_nack_sp_done;
+
+	rval = qla2x00_start_sp(sp);
+	if (rval != QLA_SUCCESS)
+		goto done_free_sp;
+
+	ql_dbg(ql_dbg_disc, vha, 0xffff,
+		"Async-%s %8phC hndl %x %s\n",
+		sp->name, fcport->port_name, sp->handle, c);
+
+	return rval;
+
+done_free_sp:
+	sp->free(vha, sp);
+done:
+	fcport->flags &= ~FCF_ASYNC_SENT;
+	return rval;
+}
+
+void qla24xx_do_nack_work(struct scsi_qla_host *vha, struct qla_work_evt *e)
+{
+	fc_port_t *t;
+	unsigned long flags;
+
+	switch (e->u.nack.type) {
+	case SRB_NACK_PRLI:
+		mutex_lock(&vha->vha_tgt.tgt_mutex);
+		t = qlt_create_sess(vha, e->u.nack.fcport, 0);
+		mutex_unlock(&vha->vha_tgt.tgt_mutex);
+		if (t) {
+			ql_log(ql_log_info, vha, 0xffff,
+			    "%s create sess success %p", __func__, t);
+			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+			/* create sess has an extra kref */
+			vha->hw->tgt.tgt_ops->put_sess(e->u.nack.fcport);
+			spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+		}
+		break;
+	}
+	qla24xx_async_notify_ack(vha, e->u.nack.fcport,
+	    (struct imm_ntfy_from_isp*)e->u.nack.iocb, e->u.nack.type);
+}
+
+void qla24xx_delete_sess_fn(struct work_struct *work)
+{
+	fc_port_t *fcport = container_of(work, struct fc_port, del_work);
+	struct qla_hw_data *ha = fcport->vha->hw;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+
+	if (fcport->se_sess) {
+		ha->tgt.tgt_ops->shutdown_sess(fcport);
+		ha->tgt.tgt_ops->put_sess(fcport);
+	} else {
+		qlt_unreg_sess(fcport);
+	}
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+}
+
+/*
+ * Called from qla2x00_reg_remote_port()
+ */
+void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+	struct fc_port *sess = fcport;
+	unsigned long flags;
+
+	if (!vha->hw->tgt.tgt_ops)
+		return;
+
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+	if (tgt->tgt_stop) {
+		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+		return;
+	}
+
+	if (fcport->disc_state == DSC_DELETE_PEND) {
+		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+		return;
+	}
+
+	if (!sess->se_sess) {
+		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+
+		mutex_lock(&vha->vha_tgt.tgt_mutex);
+		sess = qlt_create_sess(vha, fcport, false);
+		mutex_unlock(&vha->vha_tgt.tgt_mutex);
+
+		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+	} else {
+		if (fcport->fw_login_state == DSC_LS_PRLI_COMP) {
+			spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+			return;
+		}
+
+		if (!kref_get_unless_zero(&sess->sess_kref)) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "%s: kref_get fail sess %8phC \n",
+			    __func__, sess->port_name);
+			spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+			return;
+		}
+
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04c,
+		    "qla_target(%u): %ssession for port %8phC "
+		    "(loop ID %d) reappeared\n", vha->vp_idx,
+		    sess->local ? "local " : "", sess->port_name, sess->loop_id);
+
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf007,
+		    "Reappeared sess %p\n", sess);
+
+		ha->tgt.tgt_ops->update_sess(sess, fcport->d_id,
+		    fcport->loop_id,
+		    (fcport->flags & FCF_CONF_COMP_SUPPORTED));
+	}
+
+	if (sess && sess->local) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04d,
+		    "qla_target(%u): local session for "
+		    "port %8phC (loop ID %d) became global\n", vha->vp_idx,
+		    fcport->port_name, sess->loop_id);
+		sess->local = 0;
+	}
+	ha->tgt.tgt_ops->put_sess(sess);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+}
 
 /*
  * This is a zero-base ref-counting solution, since hardware_lock
@@ -413,30 +657,51 @@ qlt_plogi_ack_find_add(struct scsi_qla_host *vha, port_id_t *id,
 	return pla;
 }
 
-static void qlt_plogi_ack_unref(struct scsi_qla_host *vha,
+void qlt_plogi_ack_unref(struct scsi_qla_host *vha,
     struct qlt_plogi_ack_t *pla)
 {
 	struct imm_ntfy_from_isp *iocb = &pla->iocb;
+	port_id_t port_id;
+	uint16_t loop_id;
+	fc_port_t *fcport = pla->fcport;
+
 	BUG_ON(!pla->ref_count);
 	pla->ref_count--;
 
 	if (pla->ref_count)
 		return;
 
-	ql_dbg(ql_dbg_async, vha, 0x5089,
+	ql_dbg(ql_dbg_disc, vha, 0x5089,
 	    "Sending PLOGI ACK to wwn %8phC s_id %02x:%02x:%02x loop_id %#04x"
 	    " exch %#x ox_id %#x\n", iocb->u.isp24.port_name,
 	    iocb->u.isp24.port_id[2], iocb->u.isp24.port_id[1],
 	    iocb->u.isp24.port_id[0],
 	    le16_to_cpu(iocb->u.isp24.nport_handle),
 	    iocb->u.isp24.exchange_address, iocb->ox_id);
-	qlt_send_notify_ack(vha, iocb, 0, 0, 0, 0, 0, 0);
+
+	port_id.b.domain = iocb->u.isp24.port_id[2];
+	port_id.b.area   = iocb->u.isp24.port_id[1];
+	port_id.b.al_pa  = iocb->u.isp24.port_id[0];
+	port_id.b.rsvd_1 = 0;
+
+	loop_id = le16_to_cpu(iocb->u.isp24.nport_handle);
+
+	fcport->loop_id = loop_id;
+	fcport->d_id = port_id;
+	qla24xx_post_nack_work(vha, fcport, iocb, SRB_NACK_PLOGI);
+
+	list_for_each_entry(fcport, &vha->vp_fcports, list) {
+		if (fcport->plogi_link[QLT_PLOGI_LINK_SAME_WWN] == pla)
+			fcport->plogi_link[QLT_PLOGI_LINK_SAME_WWN] = NULL;
+		if (fcport->plogi_link[QLT_PLOGI_LINK_CONFLICT] == pla)
+			fcport->plogi_link[QLT_PLOGI_LINK_CONFLICT] = NULL;
+	}
 
 	list_del(&pla->list);
 	kmem_cache_free(qla_tgt_plogi_cachep, pla);
 }
 
-static void
+void
 qlt_plogi_ack_link(struct scsi_qla_host *vha, struct qlt_plogi_ack_t *pla,
     struct fc_port *sess, enum qlt_plogi_link_t link)
 {
@@ -444,15 +709,19 @@ qlt_plogi_ack_link(struct scsi_qla_host *vha, struct qlt_plogi_ack_t *pla,
 	/* Inc ref_count first because link might already be pointing at pla */
 	pla->ref_count++;
 
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf097,
+		"Linking sess %p [%d] wwn %8phC with PLOGI ACK to wwn %8phC"
+		" s_id %02x:%02x:%02x, ref=%d pla %p link %d\n",
+		sess, link, sess->port_name,
+		iocb->u.isp24.port_name, iocb->u.isp24.port_id[2],
+		iocb->u.isp24.port_id[1], iocb->u.isp24.port_id[0],
+		pla->ref_count, pla, link);
+
 	if (sess->plogi_link[link])
 		qlt_plogi_ack_unref(vha, sess->plogi_link[link]);
 
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf097,
-	    "Linking sess %p [%d] wwn %8phC with PLOGI ACK to wwn %8phC"
-	    " s_id %02x:%02x:%02x, ref=%d\n", sess, link, sess->port_name,
-	    iocb->u.isp24.port_name, iocb->u.isp24.port_id[2],
-	    iocb->u.isp24.port_id[1], iocb->u.isp24.port_id[0],
-	    pla->ref_count);
+	if (link == QLT_PLOGI_LINK_SAME_WWN)
+		pla->fcport = sess;
 
 	sess->plogi_link[link] = pla;
 }
@@ -512,7 +781,7 @@ static void qlt_free_session_done(struct work_struct *work)
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
 	bool logout_started = false;
-	fc_port_t fcport;
+	struct event_arg ea;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084,
 		"%s: se_sess %p / sess %p from port %8phC loop_id %#04x"
@@ -522,8 +791,8 @@ static void qlt_free_session_done(struct work_struct *work)
 		sess->logout_on_delete, sess->keep_nport_handle,
 		sess->send_els_logo);
 
-	BUG_ON(!tgt);
 
+	if (!IS_SW_RESV_ADDR(sess->d_id)) {
 	if (sess->send_els_logo) {
 		qlt_port_logo_t logo;
 		logo.id = sess->d_id;
@@ -533,14 +802,7 @@ static void qlt_free_session_done(struct work_struct *work)
 
 	if (sess->logout_on_delete) {
 		int rc;
-
-		memset(&fcport, 0, sizeof(fcport));
-		fcport.loop_id = sess->loop_id;
-		fcport.d_id = sess->d_id;
-		memcpy(fcport.port_name, sess->port_name, WWN_SIZE);
-		fcport.vha = vha;
-
-		rc = qla2x00_post_async_logout_work(vha, &fcport, NULL);
+		rc = qla2x00_post_async_logout_work(vha, sess, NULL);
 		if (rc != QLA_SUCCESS)
 			ql_log(ql_log_warn, vha, 0xf085,
 			       "Schedule logo failed sess %p rc %d\n",
@@ -548,6 +810,7 @@ static void qlt_free_session_done(struct work_struct *work)
 		else
 			logout_started = true;
 	}
+	}
 
 	/*
 	 * Release the target session for FC Nexus from fabric module code.
@@ -568,12 +831,38 @@ static void qlt_free_session_done(struct work_struct *work)
 			msleep(100);
 		}
 
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf087,
+		ql_dbg(ql_dbg_disc, vha, 0xf087,
 			"%s: sess %p logout completed\n",
 			__func__, sess);
 	}
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+	if (sess->se_sess) {
+		sess->se_sess = NULL;
+		if (tgt && !IS_SW_RESV_ADDR(sess->d_id))
+			tgt->sess_count--;
+	}
+
+	sess->disc_state = DSC_DELETED;
+	sess->fw_login_state = DSC_LS_PORT_UNAVAIL;
+	sess->deleted = QLA_SESS_DELETED;
+	sess->login_retry = vha->hw->login_retry_count;
+
+	if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) {
+		vha->fcport_count--;
+		sess->login_succ = 0;
+	}
+
+	if (sess->chip_reset != sess->vha->hw->chip_reset)
+		qla2x00_clear_loop_id(sess);
+
+	if (sess->conflict) {
+		sess->conflict->login_pause = 0;
+		sess->conflict = NULL;
+		if (!test_bit(UNLOADING, &vha->dpc_flags))
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+	}
+
 	{
 		struct qlt_plogi_ack_t *own =
 		    sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN];
@@ -591,6 +880,7 @@ static void qlt_free_session_done(struct work_struct *work)
 				 own ? own->ref_count : -1,
 				 iocb->u.isp24.port_name, con->ref_count);
 			qlt_plogi_ack_unref(vha, con);
+			sess->plogi_link[QLT_PLOGI_LINK_CONFLICT] = NULL;
 		} else {
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf09a,
 			    "se_sess %p / sess %p port %8phC is gone, %s (ref=%d)\n",
@@ -600,25 +890,30 @@ static void qlt_free_session_done(struct work_struct *work)
 			    own ? own->ref_count : -1);
 		}
 
-		if (own)
+		if (own) {
+			sess->fw_login_state = DSC_LS_PLOGI_PEND;
 			qlt_plogi_ack_unref(vha, own);
+			sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN] = NULL;
+		}
 	}
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-
-	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	sess->se_sess = NULL;
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
-	    "Unregistration of sess %p finished\n", sess);
+	    "Unregistration of sess %p %8phC finished fcp_cnt %d\n",
+		sess, sess->port_name, vha->fcport_count);
 
-	/*
-	 * We need to protect against race, when tgt is freed before or
-	 * inside wake_up()
-	 */
-	tgt->sess_count--;
-	if (tgt->sess_count == 0)
+	if (tgt && (tgt->sess_count == 0))
 		wake_up_all(&tgt->waitQ);
+
+	if (vha->fcport_count == 0)
+		wake_up_all(&vha->fcport_waitQ);
+
+	if (!tgt || !tgt->tgt_stop) {
+		memset(&ea, 0, sizeof(ea));
+		ea.event = FCME_DELETE_DONE;
+		ea.fcport = sess;
+		qla2x00_fcport_event_handler(vha, &ea);
+	}
 }
 
 /* ha->tgt.sess_lock supposed to be held on entry */
@@ -636,6 +931,9 @@ void qlt_unreg_sess(struct fc_port *sess)
 	qla2x00_mark_device_lost(vha, sess, 1, 1);
 
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
+	sess->disc_state = DSC_DELETE_PEND;
+	sess->last_rscn_gen = sess->rscn_gen;
+	sess->last_login_gen = sess->login_gen;
 
 	INIT_WORK(&sess->free_work, qlt_free_session_done);
 	schedule_work(&sess->free_work);
@@ -679,48 +977,57 @@ static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd)
 	return qlt_issue_task_mgmt(sess, 0, mcmd, iocb, QLA24XX_MGMT_SEND_NACK);
 }
 
+static void qla24xx_chk_fcp_state(struct fc_port *sess)
+{
+	if (sess->chip_reset != sess->vha->hw->chip_reset) {
+		sess->logout_on_delete = 0;
+		sess->logo_ack_needed = 0;
+		sess->fw_login_state = DSC_LS_PORT_UNAVAIL;
+		sess->scan_state = 0;
+	}
+}
+
 /* ha->tgt.sess_lock supposed to be held on entry */
-static void qlt_schedule_sess_for_deletion(struct fc_port *sess,
+void qlt_schedule_sess_for_deletion(struct fc_port *sess,
 	bool immediate)
 {
 	struct qla_tgt *tgt = sess->tgt;
-	uint32_t dev_loss_tmo = tgt->ha->port_down_retry_count + 5;
 
-	if (sess->deleted) {
-		/* Upgrade to unconditional deletion in case it was temporary */
-		if (immediate && sess->deleted == QLA_SESS_DELETION_PENDING)
-			list_del(&sess->del_list_entry);
-		else
+	if (sess->disc_state == DSC_DELETE_PEND)
+		return;
+
+	if (sess->disc_state == DSC_DELETED) {
+		if (tgt && tgt->tgt_stop && (tgt->sess_count == 0))
+			wake_up_all(&tgt->waitQ);
+		if (sess->vha->fcport_count == 0)
+			wake_up_all(&sess->vha->fcport_waitQ);
+
+		if (!sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN] &&
+			!sess->plogi_link[QLT_PLOGI_LINK_CONFLICT])
 			return;
 	}
 
-	ql_dbg(ql_dbg_tgt, sess->vha, 0xe001,
-	    "Scheduling sess %p for deletion\n", sess);
+	sess->disc_state = DSC_DELETE_PEND;
 
-	if (immediate) {
-		dev_loss_tmo = 0;
-		sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
-		list_add(&sess->del_list_entry, &tgt->del_sess_list);
-	} else {
-		sess->deleted = QLA_SESS_DELETION_PENDING;
-		list_add_tail(&sess->del_list_entry, &tgt->del_sess_list);
-	}
+	if (sess->deleted == QLA_SESS_DELETED)
+		sess->logout_on_delete = 0;
+
+	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
+	qla24xx_chk_fcp_state(sess);
 
-	sess->expires = jiffies + dev_loss_tmo * HZ;
+	ql_dbg(ql_dbg_tgt, sess->vha, 0xe001,
+	    "Scheduling sess %p for deletion\n", sess);
 
-	ql_dbg(ql_dbg_tgt, sess->vha, 0xe048,
-	    "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)"
-	    " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n",
-	    sess->vha->vp_idx, sess->port_name, sess->loop_id,
-	    sess->d_id.b.domain, sess->d_id.b.area, sess->d_id.b.al_pa,
-	    dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete,
-	    sess->generation);
+	schedule_work(&sess->del_work);
+}
 
-	if (immediate)
-		mod_delayed_work(system_wq, &tgt->sess_del_work, 0);
-	else
-		schedule_delayed_work(&tgt->sess_del_work,
-		    sess->expires - jiffies);
+void qlt_schedule_sess_for_deletion_lock(struct fc_port *sess)
+{
+	unsigned long flags;
+	struct qla_hw_data *ha = sess->vha->hw;
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+	qlt_schedule_sess_for_deletion(sess, 1);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 }
 
 /* ha->tgt.sess_lock supposed to be held on entry */
@@ -731,7 +1038,7 @@ static void qlt_clear_tgt_db(struct qla_tgt *tgt)
 
 	list_for_each_entry(sess, &vha->vp_fcports, list) {
 		if (sess->se_sess)
-			qlt_schedule_sess_for_deletion(sess, true);
+			qlt_schedule_sess_for_deletion(sess, 1);
 	}
 
 	/* At this point tgt could be already dead */
@@ -786,49 +1093,6 @@ static int qla24xx_get_loop_id(struct scsi_qla_host *vha, const uint8_t *s_id,
 	return res;
 }
 
-/* ha->tgt.sess_lock supposed to be held on entry */
-static void qlt_undelete_sess(struct fc_port *sess)
-{
-	BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING);
-
-	list_del_init(&sess->del_list_entry);
-	sess->deleted = 0;
-}
-
-static void qlt_del_sess_work_fn(struct delayed_work *work)
-{
-	struct qla_tgt *tgt = container_of(work, struct qla_tgt,
-	    sess_del_work);
-	struct scsi_qla_host *vha = tgt->vha;
-	struct qla_hw_data *ha = vha->hw;
-	struct fc_port *sess;
-	unsigned long flags, elapsed;
-
-	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	while (!list_empty(&tgt->del_sess_list)) {
-		sess = list_entry(tgt->del_sess_list.next, typeof(*sess),
-		    del_list_entry);
-		elapsed = jiffies;
-		if (time_after_eq(elapsed, sess->expires)) {
-			/* No turning back */
-			list_del_init(&sess->del_list_entry);
-			sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
-
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004,
-			    "Timeout: sess %p about to be deleted\n",
-			    sess);
-			if (sess->se_sess)
-				ha->tgt.tgt_ops->shutdown_sess(sess);
-			ha->tgt.tgt_ops->put_sess(sess);
-		} else {
-			schedule_delayed_work(&tgt->sess_del_work,
-			    sess->expires - elapsed);
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-}
-
 /*
  * Adds an extra ref to allow to drop hw lock after adding sess to the list.
  * Caller must put it.
@@ -839,93 +1103,65 @@ static struct fc_port *qlt_create_sess(
 	bool local)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct fc_port *sess;
+	struct fc_port *sess = fcport;
 	unsigned long flags;
 
-	/* Check to avoid double sessions */
-	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	list_for_each_entry(sess, &vha->vp_fcports, list) {
-		if (!memcmp(sess->port_name, fcport->port_name, WWN_SIZE)) {
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf005,
-			    "Double sess %p found (s_id %x:%x:%x, "
-			    "loop_id %d), updating to d_id %x:%x:%x, "
-			    "loop_id %d", sess, sess->d_id.b.domain,
-			    sess->d_id.b.al_pa, sess->d_id.b.area,
-			    sess->loop_id, fcport->d_id.b.domain,
-			    fcport->d_id.b.al_pa, fcport->d_id.b.area,
-			    fcport->loop_id);
-
-			/* Cannot undelete at this point */
-			if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
-				spin_unlock_irqrestore(&ha->tgt.sess_lock,
-				    flags);
-				return NULL;
-			}
-
-			if (sess->deleted)
-				qlt_undelete_sess(sess);
-
-			if (!sess->se_sess) {
-				if (ha->tgt.tgt_ops->check_initiator_node_acl(vha,
-				    &sess->port_name[0], sess) < 0) {
-					spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-					return NULL;
-				}
-			}
-
-			kref_get(&sess->sess_kref);
-			ha->tgt.tgt_ops->update_sess(sess, fcport->d_id, fcport->loop_id,
-						(fcport->flags & FCF_CONF_COMP_SUPPORTED));
-
-			if (sess->local && !local)
-				sess->local = 0;
-
-			qlt_do_generation_tick(vha, &sess->generation);
-
-			spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+	if (vha->vha_tgt.qla_tgt->tgt_stop)
+		return NULL;
 
-			return sess;
+	if (fcport->se_sess) {
+		if (!kref_get_unless_zero(&sess->sess_kref)) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "%s: kref_get_unless_zero failed for %8phC\n",
+			    __func__, sess->port_name);
+			return NULL;
 		}
-	}
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
-
-	sess = kzalloc(sizeof(*sess), GFP_KERNEL);
-	if (!sess) {
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04a,
-		    "qla_target(%u): session allocation failed, all commands "
-		    "from port %8phC will be refused", vha->vp_idx,
-		    fcport->port_name);
-
-		return NULL;
+		return fcport;
 	}
 	sess->tgt = vha->vha_tgt.qla_tgt;
-	sess->vha = vha;
-	sess->d_id = fcport->d_id;
-	sess->loop_id = fcport->loop_id;
 	sess->local = local;
-	kref_init(&sess->sess_kref);
-	INIT_LIST_HEAD(&sess->del_list_entry);
 
-	/* Under normal circumstances we want to logout from firmware when
+	/*
+	 * Under normal circumstances we want to logout from firmware when
 	 * session eventually ends and release corresponding nport handle.
 	 * In the exception cases (e.g. when new PLOGI is waiting) corresponding
-	 * code will adjust these flags as necessary. */
+	 * code will adjust these flags as necessary.
+	 */
 	sess->logout_on_delete = 1;
 	sess->keep_nport_handle = 0;
+	sess->logout_completed = 0;
 
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006,
-	    "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n",
-	    sess, vha->vha_tgt.qla_tgt);
+	if (ha->tgt.tgt_ops->check_initiator_node_acl(vha,
+	    &fcport->port_name[0], sess) < 0) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+		    "(%d) %8phC check_initiator_node_acl failed\n",
+		    vha->vp_idx, fcport->port_name);
+		return NULL;
+	} else {
+		kref_init(&fcport->sess_kref);
+		/*
+		 * Take an extra reference to ->sess_kref here to handle
+		 * fc_port access across ->tgt.sess_lock reaquire.
+		 */
+		if (!kref_get_unless_zero(&sess->sess_kref)) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "%s: kref_get_unless_zero failed for %8phC\n",
+			    __func__, sess->port_name);
+			return NULL;
+		}
 
-	sess->conf_compl_supported = (fcport->flags & FCF_CONF_COMP_SUPPORTED);
-	BUILD_BUG_ON(sizeof(sess->port_name) != sizeof(fcport->port_name));
-	memcpy(sess->port_name, fcport->port_name, sizeof(sess->port_name));
+		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+		if (!IS_SW_RESV_ADDR(sess->d_id))
+			vha->vha_tgt.qla_tgt->sess_count++;
 
-	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
-	list_add_tail(&sess->list, &vha->vp_fcports);
-	vha->vha_tgt.qla_tgt->sess_count++;
-	qlt_do_generation_tick(vha, &sess->generation);
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+		qlt_do_generation_tick(vha, &sess->generation);
+		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+	}
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006,
+	    "Adding sess %p se_sess %p  to tgt %p sess_count %d\n",
+	    sess, sess->se_sess, vha->vha_tgt.qla_tgt,
+	    vha->vha_tgt.qla_tgt->sess_count);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b,
 	    "qla_target(%d): %ssession for wwn %8phC (loop_id %d, "
@@ -934,23 +1170,6 @@ static struct fc_port *qlt_create_sess(
 	    fcport->loop_id, sess->d_id.b.domain, sess->d_id.b.area,
 	    sess->d_id.b.al_pa, sess->conf_compl_supported ?  "" : "not ");
 
-	/*
-	 * Determine if this fc_port->port_name is allowed to access
-	 * target mode using explict NodeACLs+MappedLUNs, or using
-	 * TPG demo mode.  If this is successful a target mode FC nexus
-	 * is created.
-	 */
-	if (ha->tgt.tgt_ops->check_initiator_node_acl(vha,
-	    &fcport->port_name[0], sess) < 0) {
-		return NULL;
-	} else {
-		/*
-		 * Take an extra reference to ->sess_kref here to handle fc_port
-		 * access across ->tgt.sess_lock reaquire.
-		 */
-		kref_get(&sess->sess_kref);
-	}
-
 	return sess;
 }
 
@@ -1007,12 +1226,12 @@ static inline int test_tgt_sess_count(struct qla_tgt *tgt)
 	 * We need to protect against race, when tgt is freed before or
 	 * inside wake_up()
 	 */
-	spin_lock_irqsave(&ha->hardware_lock, flags);
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 	ql_dbg(ql_dbg_tgt, tgt->vha, 0xe002,
 	    "tgt %p, sess_count=%d\n",
 	    tgt, tgt->sess_count);
 	res = (tgt->sess_count == 0);
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 
 	return res;
 }
@@ -1060,8 +1279,6 @@ int qlt_stop_phase1(struct qla_tgt *tgt)
 	mutex_unlock(&vha->vha_tgt.tgt_mutex);
 	mutex_unlock(&qla_tgt_mutex);
 
-	flush_delayed_work(&tgt->sess_del_work);
-
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf009,
 	    "Waiting for sess works (tgt %p)", tgt);
 	spin_lock_irqsave(&tgt->sess_work_lock, flags);
@@ -1205,6 +1422,7 @@ static void qlt_send_notify_ack(struct scsi_qla_host *vha,
 	nack = (struct nack_to_isp *)pkt;
 	nack->ox_id = ntfy->ox_id;
 
+	nack->u.isp24.handle = QLA_TGT_SKIP_HANDLE;
 	nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle;
 	if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) {
 		nack->u.isp24.flags = ntfy->u.isp24.flags &
@@ -1552,7 +1770,7 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 
 
-	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+	if (sess->deleted) {
 		qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED, false);
 		return;
 	}
@@ -1650,10 +1868,19 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 		return;
 	}
 
-	if (mcmd->flags == QLA24XX_MGMT_SEND_NACK)
-		qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy,
-		    0, 0, 0, 0, 0, 0);
-	else {
+	if (mcmd->flags == QLA24XX_MGMT_SEND_NACK) {
+		if (mcmd->orig_iocb.imm_ntfy.u.isp24.status_subcode ==
+		    ELS_LOGO) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+			    "TM response logo %phC status %#x state %#x",
+			    mcmd->sess->port_name, mcmd->fc_tm_rsp,
+			    mcmd->flags);
+			qlt_schedule_sess_for_deletion_lock(mcmd->sess);
+		} else {
+			qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy,
+				0, 0, 0, 0, 0, 0);
+		}
+	} else {
 		if (mcmd->orig_iocb.atio.u.raw.entry_type == ABTS_RECV_24XX)
 			qlt_24xx_send_abts_resp(vha, &mcmd->orig_iocb.abts,
 			    mcmd->fc_tm_rsp, false);
@@ -2470,7 +2697,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	int res;
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	if (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+	if (cmd->sess && cmd->sess->deleted) {
 		cmd->state = QLA_TGT_STATE_PROCESSED;
 		if (cmd->sess->logout_completed)
 			/* no need to terminate. FW already freed exchange. */
@@ -2645,7 +2872,7 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
 	if (!vha->flags.online || (cmd->reset_count != ha->chip_reset) ||
-	    (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)) {
+	    (cmd->sess && cmd->sess->deleted)) {
 		/*
 		 * Either the port is not online or this request was from
 		 * previous life, just abort the processing.
@@ -3345,7 +3572,11 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 				 */
 				cmd->sess->logout_on_delete = 0;
 				cmd->sess->send_els_logo = 1;
-				qlt_schedule_sess_for_deletion(cmd->sess, true);
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "%s %d %8phC post del sess\n",
+				    __func__, __LINE__, cmd->sess->port_name);
+
+				qlt_schedule_sess_for_deletion_lock(cmd->sess);
 			}
 			break;
 		}
@@ -3649,6 +3880,7 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 		kfree(op);
 		return;
 	}
+
 	/*
 	 * __qlt_do_work() will call qlt_put_sess() to release
 	 * the extra reference taken above by qlt_make_local_sess()
@@ -3656,13 +3888,11 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 	__qlt_do_work(cmd);
 	kfree(op);
 	return;
-
 out_term:
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	qlt_send_term_exchange(vha, NULL, &op->atio, 1, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	kfree(op);
-
 }
 
 /* ha->hardware_lock supposed to be held on entry */
@@ -3702,7 +3932,7 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	/* Another WWN used to have our s_id. Our PLOGI scheduled its
 	 * session deletion, but it's still in sess_del_work wq */
-	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+	if (sess->deleted) {
 		ql_dbg(ql_dbg_io, vha, 0x3061,
 		    "New command while old session %p is being deleted\n",
 		    sess);
@@ -3712,7 +3942,13 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 	/*
 	 * Do kref_get() before returning + dropping qla_hw_data->hardware_lock.
 	 */
-	kref_get(&sess->sess_kref);
+	if (!kref_get_unless_zero(&sess->sess_kref)) {
+		ql_dbg(ql_dbg_tgt, vha, 0xffff,
+		    "%s: kref_get fail, %8phC oxid %x \n",
+		    __func__, sess->port_name,
+		     be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id));
+		return -EFAULT;
+	}
 
 	cmd = qlt_get_tag(vha, sess, atio);
 	if (!cmd) {
@@ -3729,9 +3965,9 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 	cmd->se_cmd.cpuid = ha->msix_count ?
 		ha->tgt.rspq_vector_cpuid : WORK_CPU_UNBOUND;
 
-	spin_lock(&vha->cmd_list_lock);
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
 	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
-	spin_unlock(&vha->cmd_list_lock);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
 
 	INIT_WORK(&cmd->work, qlt_do_work);
 	if (ha->msix_count) {
@@ -3826,7 +4062,7 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb)
 		    sizeof(struct atio_from_isp));
 	}
 
-	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)
+	if (sess->deleted)
 		return -EFAULT;
 
 	return qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0);
@@ -3901,22 +4137,20 @@ static int qlt_abort_task(struct scsi_qla_host *vha,
 
 void qlt_logo_completion_handler(fc_port_t *fcport, int rc)
 {
-	if (fcport->tgt_session) {
-		if (rc != MBS_COMMAND_COMPLETE) {
-			ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093,
-				"%s: se_sess %p / sess %p from"
-				" port %8phC loop_id %#04x s_id %02x:%02x:%02x"
-				" LOGO failed: %#x\n",
-				__func__,
-				fcport->se_sess,
-				fcport->tgt_session,
-				fcport->port_name, fcport->loop_id,
-				fcport->d_id.b.domain, fcport->d_id.b.area,
-				fcport->d_id.b.al_pa, rc);
-		}
-
-		fcport->logout_completed = 1;
+	if (rc != MBS_COMMAND_COMPLETE) {
+		ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093,
+			"%s: se_sess %p / sess %p from"
+			" port %8phC loop_id %#04x s_id %02x:%02x:%02x"
+			" LOGO failed: %#x\n",
+			__func__,
+			fcport->se_sess,
+			fcport,
+			fcport->port_name, fcport->loop_id,
+			fcport->d_id.b.domain, fcport->d_id.b.area,
+			fcport->d_id.b.al_pa, rc);
 	}
+
+	fcport->logout_completed = 1;
 }
 
 /*
@@ -3926,13 +4160,12 @@ void qlt_logo_completion_handler(fc_port_t *fcport, int rc)
 * deletion. Returns existing session with matching wwn if present.
 * Null otherwise.
 */
-static struct fc_port *
-qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
+struct fc_port *
+qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn,
     port_id_t port_id, uint16_t loop_id, struct fc_port **conflict_sess)
 {
 	struct fc_port *sess = NULL, *other_sess;
 	uint64_t other_wwn;
-	scsi_qla_host_t *vha = tgt->vha;
 
 	*conflict_sess = NULL;
 
@@ -3949,7 +4182,7 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
 		/* find other sess with nport_id collision */
 		if (port_id.b24 == other_sess->d_id.b24) {
 			if (loop_id != other_sess->loop_id) {
-				ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c,
+				ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000c,
 				    "Invalidating sess %p loop_id %d wwn %llx.\n",
 				    other_sess, other_sess->loop_id, other_wwn);
 
@@ -3965,6 +4198,11 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
 				 * Another wwn used to have our s_id/loop_id
 				 * kill the session, but don't free the loop_id
 				 */
+				ql_dbg(ql_dbg_tgt_tmr, vha, 0xffff,
+				    "Invalidating sess %p loop_id %d wwn %llx.\n",
+				    other_sess, other_sess->loop_id, other_wwn);
+
+
 				other_sess->keep_nport_handle = 1;
 				*conflict_sess = other_sess;
 				qlt_schedule_sess_for_deletion(other_sess,
@@ -3974,8 +4212,9 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
 		}
 
 		/* find other sess with nport handle collision */
-		if (loop_id == other_sess->loop_id) {
-			ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000d,
+		if ((loop_id == other_sess->loop_id) &&
+			(loop_id != FC_NO_LOOP_ID)) {
+			ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000d,
 			       "Invalidating sess %p loop_id %d wwn %llx.\n",
 			       other_sess, other_sess->loop_id, other_wwn);
 
@@ -4046,9 +4285,12 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 
 	loop_id = le16_to_cpu(iocb->u.isp24.nport_handle);
 
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026,
-	    "qla_target(%d): Port ID: 0x%3phC ELS opcode: 0x%02x\n",
-	    vha->vp_idx, iocb->u.isp24.port_id, iocb->u.isp24.status_subcode);
+	ql_dbg(ql_dbg_disc, vha, 0xf026,
+	    "qla_target(%d): Port ID: %02x:%02x:%02x ELS opcode: 0x%02x lid %d %8phC\n",
+	    vha->vp_idx, iocb->u.isp24.port_id[2],
+		iocb->u.isp24.port_id[1], iocb->u.isp24.port_id[0],
+		   iocb->u.isp24.status_subcode, loop_id,
+		iocb->u.isp24.port_name);
 
 	/* res = 1 means ack at the end of thread
 	 * res = 0 means ack async/later.
@@ -4061,12 +4303,12 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 
 		if (wwn) {
 			spin_lock_irqsave(&tgt->ha->tgt.sess_lock, flags);
-			sess = qlt_find_sess_invalidate_other(tgt, wwn,
-			    port_id, loop_id, &conflict_sess);
+			sess = qlt_find_sess_invalidate_other(vha, wwn,
+				port_id, loop_id, &conflict_sess);
 			spin_unlock_irqrestore(&tgt->ha->tgt.sess_lock, flags);
 		}
 
-		if (IS_SW_RESV_ADDR(port_id) || (!sess && !conflict_sess)) {
+		if (IS_SW_RESV_ADDR(port_id)) {
 			res = 1;
 			break;
 		}
@@ -4074,42 +4316,66 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		pla = qlt_plogi_ack_find_add(vha, &port_id, iocb);
 		if (!pla) {
 			qlt_send_term_imm_notif(vha, iocb, 1);
-
-			res = 0;
 			break;
 		}
 
 		res = 0;
 
-		if (conflict_sess)
+		if (conflict_sess) {
+			conflict_sess->login_gen++;
 			qlt_plogi_ack_link(vha, pla, conflict_sess,
-			    QLT_PLOGI_LINK_CONFLICT);
+				QLT_PLOGI_LINK_CONFLICT);
+		}
 
-		if (!sess)
+		if (!sess) {
+			pla->ref_count++;
+			qla24xx_post_newsess_work(vha, &port_id,
+				iocb->u.isp24.port_name, pla);
+			res = 0;
 			break;
+		}
 
 		qlt_plogi_ack_link(vha, pla, sess, QLT_PLOGI_LINK_SAME_WWN);
-		 /*
-		  * Under normal circumstances we want to release nport handle
-		  * during LOGO process to avoid nport handle leaks inside FW.
-		  * The exception is when LOGO is done while another PLOGI with
-		  * the same nport handle is waiting as might be the case here.
-		  * Note: there is always a possibily of a race where session
-		  * deletion has already started for other reasons (e.g. ACL
-		  * removal) and now PLOGI arrives:
-		  * 1. if PLOGI arrived in FW after nport handle has been freed,
-		  *    FW must have assigned this PLOGI a new/same handle and we
-		  *    can proceed ACK'ing it as usual when session deletion
-		  *    completes.
-		  * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT
-		  *    bit reached it, the handle has now been released. We'll
-		  *    get an error when we ACK this PLOGI. Nothing will be sent
-		  *    back to initiator. Initiator should eventually retry
-		  *    PLOGI and situation will correct itself.
-		  */
-		sess->keep_nport_handle = ((sess->loop_id == loop_id) &&
-					   (sess->d_id.b24 == port_id.b24));
-		qlt_schedule_sess_for_deletion(sess, true);
+		sess->fw_login_state = DSC_LS_PLOGI_PEND;
+		sess->d_id = port_id;
+		sess->login_gen++;
+
+		switch (sess->disc_state) {
+		case DSC_DELETED:
+			qlt_plogi_ack_unref(vha, pla);
+			break;
+
+		default:
+			/*
+			 * Under normal circumstances we want to release nport handle
+			 * during LOGO process to avoid nport handle leaks inside FW.
+			 * The exception is when LOGO is done while another PLOGI with
+			 * the same nport handle is waiting as might be the case here.
+			 * Note: there is always a possibily of a race where session
+			 * deletion has already started for other reasons (e.g. ACL
+			 * removal) and now PLOGI arrives:
+			 * 1. if PLOGI arrived in FW after nport handle has been freed,
+			 *    FW must have assigned this PLOGI a new/same handle and we
+			 *    can proceed ACK'ing it as usual when session deletion
+			 *    completes.
+			 * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT
+			 *    bit reached it, the handle has now been released. We'll
+			 *    get an error when we ACK this PLOGI. Nothing will be sent
+			 *    back to initiator. Initiator should eventually retry
+			 *    PLOGI and situation will correct itself.
+			 */
+			sess->keep_nport_handle = ((sess->loop_id == loop_id) &&
+			   (sess->d_id.b24 == port_id.b24));
+
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+				   "%s %d %8phC post del sess\n",
+				   __func__, __LINE__, sess->port_name);
+
+
+			qlt_schedule_sess_for_deletion_lock(sess);
+			break;
+		}
+
 		break;
 
 	case ELS_PRLI:
@@ -4117,8 +4383,8 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 
 		if (wwn) {
 			spin_lock_irqsave(&tgt->ha->tgt.sess_lock, flags);
-			sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id,
-			    loop_id, &conflict_sess);
+			sess = qlt_find_sess_invalidate_other(vha, wwn, port_id,
+				loop_id, &conflict_sess);
 			spin_unlock_irqrestore(&tgt->ha->tgt.sess_lock, flags);
 		}
 
@@ -4132,7 +4398,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		}
 
 		if (sess != NULL) {
-			if (sess->deleted) {
+			if (sess->fw_login_state == DSC_LS_PLOGI_PEND) {
 				/*
 				 * Impatient initiator sent PRLI before last
 				 * PLOGI could finish. Will force him to re-try,
@@ -4157,10 +4423,15 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 			sess->local = 0;
 			sess->loop_id = loop_id;
 			sess->d_id = port_id;
+			sess->fw_login_state = DSC_LS_PRLI_PEND;
 
 			if (wd3_lo & BIT_7)
 				sess->conf_compl_supported = 1;
 
+			if ((wd3_lo & BIT_4) == 0)
+				sess->port_type = FCT_INITIATOR;
+			else
+				sess->port_type = FCT_TARGET;
 		}
 		res = 1; /* send notify ack */
 
@@ -4170,15 +4441,50 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
 			qla2xxx_wake_dpc(vha);
 		} else {
-			/* todo: else - create sess here. */
-			res = 1; /* send notify ack */
-		}
+			if (sess) {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+					   "%s %d %8phC post nack\n",
+					   __func__, __LINE__, sess->port_name);
 
+				qla24xx_post_nack_work(vha, sess, iocb,
+					SRB_NACK_PRLI);
+				res = 0;
+			}
+		}
 		break;
 
 	case ELS_LOGO:
 	case ELS_PRLO:
+		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
+		sess = qla2x00_find_fcport_by_loopid(vha, loop_id);
+		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+
+		if (sess) {
+			sess->login_gen++;
+			sess->fw_login_state = DSC_LS_LOGO_PEND;
+			sess->logout_on_delete = 0;
+			sess->logo_ack_needed = 1;
+			memcpy(sess->iocb, iocb, IOCB_SIZE);
+		}
+
 		res = qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS_SESS);
+
+		ql_dbg(ql_dbg_disc, vha, 0xffff,
+		    "%s: logo %llx res %d sess %p ",
+		    __func__, wwn, res, sess);
+		if (res == 0) {
+			/* cmd went up to ULP. look for qlt_xmit_tm_rsp()
+			   for LOGO_ACK */
+			BUG_ON(!sess);
+			res = 0;
+		} else {
+			/* cmd did not go upstair. */
+			if (sess) {
+				qlt_schedule_sess_for_deletion_lock(sess);
+				res = 0;
+			}
+			/* else logo will be ack */
+		}
 		break;
 	case ELS_PDISC:
 	case ELS_ADISC:
@@ -4189,6 +4495,16 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 			    0, 0, 0, 0, 0, 0);
 			tgt->link_reinit_iocb_pending = 0;
 		}
+
+		sess = qla2x00_find_fcport_by_wwpn(vha,
+		    iocb->u.isp24.port_name, 1);
+		if (sess) {
+			ql_dbg(ql_dbg_disc, vha, 0xffff,
+				"sess %p lid %d|%d DS %d LS %d\n",
+				sess, sess->loop_id, loop_id,
+				sess->disc_state, sess->fw_login_state);
+		}
+
 		res = 1; /* send notify ack */
 		break;
 	}
@@ -4966,7 +5282,6 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha,
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03f,
 			    "Async MB 2: Port Logged Out\n");
 		break;
-
 	default:
 		break;
 	}
@@ -4977,8 +5292,10 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha,
 static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha,
 	uint16_t loop_id)
 {
-	fc_port_t *fcport;
+	fc_port_t *fcport, *tfcp, *del;
 	int rc;
+	unsigned long flags;
+	u8 newfcport = 0;
 
 	fcport = kzalloc(sizeof(*fcport), GFP_KERNEL);
 	if (!fcport) {
@@ -5000,6 +5317,59 @@ static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha,
 		return NULL;
 	}
 
+	del = NULL;
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	tfcp = qla2x00_find_fcport_by_wwpn(vha, fcport->port_name, 1);
+
+	if (tfcp) {
+		tfcp->d_id = fcport->d_id;
+		tfcp->port_type = fcport->port_type;
+		tfcp->supported_classes = fcport->supported_classes;
+		tfcp->flags |= fcport->flags;
+
+		del = fcport;
+		fcport = tfcp;
+	} else {
+		if (vha->hw->current_topology == ISP_CFG_F)
+			fcport->flags |= FCF_FABRIC_DEVICE;
+
+		list_add_tail(&fcport->list, &vha->vp_fcports);
+		if (!IS_SW_RESV_ADDR(fcport->d_id))
+		   vha->fcport_count++;
+		fcport->login_gen++;
+		fcport->disc_state = DSC_LOGIN_COMPLETE;
+		fcport->login_succ = 1;
+		newfcport = 1;
+	}
+
+	fcport->deleted = 0;
+	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+	switch (vha->host->active_mode) {
+	case MODE_INITIATOR:
+	case MODE_DUAL:
+		if (newfcport) {
+			if (!IS_IIDMA_CAPABLE(vha->hw) || !vha->hw->flags.gpsc_supported) {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				   "%s %d %8phC post upd_fcport fcp_cnt %d\n",
+				   __func__, __LINE__, fcport->port_name, vha->fcport_count);
+				qla24xx_post_upd_fcport_work(vha, fcport);
+			} else {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				   "%s %d %8phC post gpsc fcp_cnt %d\n",
+				   __func__, __LINE__, fcport->port_name, vha->fcport_count);
+				qla24xx_post_gpsc_work(vha, fcport);
+			}
+		}
+		break;
+
+	case MODE_TARGET:
+	default:
+		break;
+	}
+	if (del)
+		qla2x00_free_fcport(del);
+
 	return fcport;
 }
 
@@ -5012,6 +5382,17 @@ static struct fc_port *qlt_make_local_sess(struct scsi_qla_host *vha,
 	int rc, global_resets;
 	uint16_t loop_id = 0;
 
+	if ((s_id[0] == 0xFF) && (s_id[1] == 0xFC)) {
+		/*
+		 * This is Domain Controller, so it should be
+		 * OK to drop SCSI commands from it.
+		 */
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf042,
+		    "Unable to find initiator with S_ID %x:%x:%x",
+		    s_id[0], s_id[1], s_id[2]);
+		return NULL;
+	}
+
 	mutex_lock(&vha->vha_tgt.tgt_mutex);
 
 retry:
@@ -5022,21 +5403,11 @@ static struct fc_port *qlt_make_local_sess(struct scsi_qla_host *vha,
 	if (rc != 0) {
 		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
-		if ((s_id[0] == 0xFF) &&
-		    (s_id[1] == 0xFC)) {
-			/*
-			 * This is Domain Controller, so it should be
-			 * OK to drop SCSI commands from it.
-			 */
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf042,
-			    "Unable to find initiator with S_ID %x:%x:%x",
-			    s_id[0], s_id[1], s_id[2]);
-		} else
-			ql_log(ql_log_info, vha, 0xf071,
-			    "qla_target(%d): Unable to find "
-			    "initiator with S_ID %x:%x:%x",
-			    vha->vp_idx, s_id[0], s_id[1],
-			    s_id[2]);
+		ql_log(ql_log_info, vha, 0xf071,
+		    "qla_target(%d): Unable to find "
+		    "initiator with S_ID %x:%x:%x",
+		    vha->vp_idx, s_id[0], s_id[1],
+		    s_id[2]);
 
 		if (rc == -ENOENT) {
 			qlt_port_logo_t logo;
@@ -5104,12 +5475,18 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 		if (!sess)
 			goto out_term2;
 	} else {
-		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		if (sess->deleted) {
 			sess = NULL;
 			goto out_term2;
 		}
 
-		kref_get(&sess->sess_kref);
+		if (!kref_get_unless_zero(&sess->sess_kref)) {
+			ql_dbg(ql_dbg_tgt_tmr, vha, 0xffff,
+			    "%s: kref_get fail %8phC \n",
+			     __func__, sess->port_name);
+			sess = NULL;
+			goto out_term2;
+		}
 	}
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -5133,7 +5510,8 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 	qlt_24xx_send_abts_resp(vha, &prm->abts, FCP_TMF_REJECTED, false);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-	ha->tgt.tgt_ops->put_sess(sess);
+	if (sess)
+		ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
 }
 
@@ -5168,12 +5546,18 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 		if (!sess)
 			goto out_term;
 	} else {
-		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		if (sess->deleted) {
 			sess = NULL;
 			goto out_term;
 		}
 
-		kref_get(&sess->sess_kref);
+		if (!kref_get_unless_zero(&sess->sess_kref)) {
+			ql_dbg(ql_dbg_tgt_tmr, vha, 0xffff,
+			    "%s: kref_get fail %8phC\n",
+			     __func__, sess->port_name);
+			sess = NULL;
+			goto out_term;
+		}
 	}
 
 	iocb = a;
@@ -5191,8 +5575,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 
 out_term:
 	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
-	if (sess)
-		ha->tgt.tgt_ops->put_sess(sess);
+	ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 }
 
@@ -5270,8 +5653,6 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
 	tgt->vha = base_vha;
 	init_waitqueue_head(&tgt->waitQ);
 	INIT_LIST_HEAD(&tgt->del_sess_list);
-	INIT_DELAYED_WORK(&tgt->sess_del_work,
-		(void (*)(struct work_struct *))qlt_del_sess_work_fn);
 	spin_lock_init(&tgt->sess_work_lock);
 	INIT_WORK(&tgt->sess_work, qlt_sess_work_fn);
 	INIT_LIST_HEAD(&tgt->sess_works_list);
@@ -5472,6 +5853,7 @@ static void qlt_clear_mode(struct scsi_qla_host *vha)
 		break;
 	case QLA2XXX_INI_MODE_ENABLED:
 		vha->host->active_mode &= ~MODE_TARGET;
+		vha->host->active_mode |= MODE_INITIATOR;
 		break;
 	default:
 		break;
@@ -5594,13 +5976,12 @@ qlt_rff_id(struct scsi_qla_host *vha, struct ct_sns_req *ct_req)
 	 * FC-4 Feature bit 0 indicates target functionality to the name server.
 	 */
 	if (qla_tgt_mode_enabled(vha)) {
-		if (qla_ini_mode_enabled(vha))
-			ct_req->req.rff_id.fc4_feature = BIT_0 | BIT_1;
-		else
-			ct_req->req.rff_id.fc4_feature = BIT_0;
+		ct_req->req.rff_id.fc4_feature = BIT_0;
 	} else if (qla_ini_mode_enabled(vha)) {
 		ct_req->req.rff_id.fc4_feature = BIT_1;
-	}
+	} else if (qla_dual_mode_enabled(vha))
+		ct_req->req.rff_id.fc4_feature = BIT_0 | BIT_1;
+
 }
 
 /*
@@ -5732,7 +6113,7 @@ qlt_24xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_24xx *nv)
 		nv->firmware_options_1 |= cpu_to_le32(BIT_4);
 
 		/* Disable ini mode, if requested */
-		if (!qla_ini_mode_enabled(vha))
+		if (qla_tgt_mode_enabled(vha))
 			nv->firmware_options_1 |= cpu_to_le32(BIT_5);
 
 		/* Disable Full Login after LIP */
@@ -5834,7 +6215,7 @@ qlt_81xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_81xx *nv)
 		nv->firmware_options_1 |= cpu_to_le32(BIT_4);
 
 		/* Disable ini mode, if requested */
-		if (!qla_ini_mode_enabled(vha))
+		if (qla_tgt_mode_enabled(vha))
 			nv->firmware_options_1 |= cpu_to_le32(BIT_5);
 		/* Disable Full Login after LIP */
 		nv->firmware_options_1 &= cpu_to_le32(~BIT_13);
@@ -5940,8 +6321,9 @@ qlt_modify_vp_config(struct scsi_qla_host *vha,
 {
 	if (qla_tgt_mode_enabled(vha))
 		vpmod->options_idx1 &= ~BIT_5;
-	/* Disable ini mode, if requested */
-	if (!qla_ini_mode_enabled(vha))
+
+	/* Disable ini mode, if requested. */
+	if (qla_tgt_mode_enabled(vha))
 		vpmod->options_idx1 &= ~BIT_4;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 9c35ba15c687..5e56192a4877 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -799,7 +799,6 @@ struct qla_tgt {
 
 	/* Protected by hardware_lock */
 	struct list_head del_sess_list;
-	struct delayed_work sess_del_work;
 
 	spinlock_t sess_work_lock;
 	struct list_head sess_works_list;
@@ -823,13 +822,6 @@ struct qla_tgt_sess_op {
 	bool aborted;
 };
 
-enum qla_sess_deletion {
-	QLA_SESS_DELETION_NONE		= 0,
-	QLA_SESS_DELETION_PENDING	= 1, /* hopefully we can get rid of
-					      * this one */
-	QLA_SESS_DELETION_IN_PROGRESS	= 2,
-};
-
 enum trace_flags {
 	TRC_NEW_CMD = BIT_0,
 	TRC_DO_WORK = BIT_1,
@@ -987,12 +979,17 @@ extern int ql2x_ini_mode;
 
 static inline bool qla_tgt_mode_enabled(struct scsi_qla_host *ha)
 {
-	return ha->host->active_mode & MODE_TARGET;
+	return ha->host->active_mode == MODE_TARGET;
 }
 
 static inline bool qla_ini_mode_enabled(struct scsi_qla_host *ha)
 {
-	return ha->host->active_mode & MODE_INITIATOR;
+	return ha->host->active_mode == MODE_INITIATOR;
+}
+
+static inline bool qla_dual_mode_enabled(struct scsi_qla_host *ha)
+{
+	return (ha->host->active_mode == MODE_DUAL);
 }
 
 static inline void qla_reverse_ini_mode(struct scsi_qla_host *ha)
-- 
GitLab


From ead038556f646788e22ad7f0398556d10981ca5f Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:28:01 -0800
Subject: [PATCH 068/898] qla2xxx: Add Dual mode support in the driver

Add switch to allow both Initiator Mode & Target
mode to operate at the same time.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_def.h     |   1 +
 drivers/scsi/qla2xxx/qla_init.c    |   6 +-
 drivers/scsi/qla2xxx/qla_isr.c     |  19 ++++-
 drivers/scsi/qla2xxx/qla_target.c  | 110 ++++++++++++++++++++++++-----
 drivers/scsi/qla2xxx/qla_target.h  |   3 +
 drivers/scsi/qla2xxx/tcm_qla2xxx.c |   2 +-
 6 files changed, 119 insertions(+), 22 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 79b4e88db3b1..f67a1c82502c 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3389,6 +3389,7 @@ struct qla_hw_data {
 #define FLOGI_SP_SUPPORT        BIT_13
 
 	uint8_t		port_no;		/* Physical port of adapter */
+	uint8_t		exch_starvation;
 
 	/* Timeout timers. */
 	uint8_t 	loop_down_abort_time;    /* port down timer */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 8b7c0468a0e0..4c0a2d8aa964 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1568,8 +1568,7 @@ qla2x00_initialize_adapter(scsi_qla_host_t *vha)
 		}
 	}
 
-	if (qla_ini_mode_enabled(vha) ||
-		qla_dual_mode_enabled(vha))
+	if (qla_ini_mode_enabled(vha) || qla_dual_mode_enabled(vha))
 		rval = qla2x00_init_rings(vha);
 
 	ha->flags.chip_reset_done = 1;
@@ -3994,7 +3993,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 			 * Process any ATIO queue entries that came in
 			 * while we weren't online.
 			 */
-			if (qla_tgt_mode_enabled(vha)) {
+			if (qla_tgt_mode_enabled(vha) ||
+			    qla_dual_mode_enabled(vha)) {
 				if (IS_QLA27XX(ha) || IS_QLA83XX(ha)) {
 					spin_lock_irqsave(&ha->tgt.atio_lock,
 					    flags);
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index bb747d7ebdab..a0a3412030cb 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1025,7 +1025,8 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 
 		qla2x00_mark_all_devices_lost(vha, 1);
 
-		if (vha->vp_idx == 0 && !qla_ini_mode_enabled(vha))
+		if (vha->vp_idx == 0 &&
+		    (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)))
 			set_bit(SCR_PENDING, &vha->dpc_flags);
 
 		set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
@@ -1637,6 +1638,7 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 		    fcport->d_id.b.area, fcport->d_id.b.al_pa,
 		    le32_to_cpu(logio->io_parameter[0]));
 
+		vha->hw->exch_starvation = 0;
 		data[0] = MBS_COMMAND_COMPLETE;
 		if (sp->type != SRB_LOGIN_CMD)
 			goto logio_done;
@@ -1672,6 +1674,21 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 	case LSC_SCODE_NPORT_USED:
 		data[0] = MBS_LOOP_ID_USED;
 		break;
+	case LSC_SCODE_NOXCB:
+		vha->hw->exch_starvation++;
+		if (vha->hw->exch_starvation > 5) {
+			ql_log(ql_log_warn, vha, 0xffff,
+			    "Exchange starvation. Resetting RISC\n");
+
+			vha->hw->exch_starvation = 0;
+
+			if (IS_P3P_TYPE(vha->hw))
+				set_bit(FCOE_CTX_RESET_NEEDED, &vha->dpc_flags);
+			else
+				set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
+		/* drop through */
 	default:
 		data[0] = MBS_COMMAND_ERROR;
 		break;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index e4d7d32c82e7..c8f312f8e0ff 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -55,8 +55,17 @@ MODULE_PARM_DESC(qlini_mode,
 	"disabled on enabling target mode and then on disabling target mode "
 	"enabled back; "
 	"\"disabled\" - initiator mode will never be enabled; "
+	"\"dual\" - Initiator Modes will be enabled. Target Mode can be activated "
+	"when ready "
 	"\"enabled\" (default) - initiator mode will always stay enabled.");
 
+static int ql_dm_tgt_ex_pct = 50;
+module_param(ql_dm_tgt_ex_pct, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(ql_dm_tgt_ex_pct,
+	"For Dual Mode (qlini_mode=dual), this parameter determines "
+	"the percentage of exchanges/cmds FW will allocate resources "
+	"for Target mode.");
+
 int ql2x_ini_mode = QLA2XXX_INI_MODE_EXCLUSIVE;
 
 static int temp_sam_status = SAM_STAT_BUSY;
@@ -1295,7 +1304,8 @@ int qlt_stop_phase1(struct qla_tgt *tgt)
 	wait_event(tgt->waitQ, test_tgt_sess_count(tgt));
 
 	/* Big hammer */
-	if (!ha->flags.host_shutting_down && qla_tgt_mode_enabled(vha))
+	if (!ha->flags.host_shutting_down &&
+	    (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)))
 		qlt_disable_vha(vha);
 
 	/* Wait for sessions to clear out (just in case) */
@@ -5266,6 +5276,32 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha,
 		    le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3]));
 		break;
 
+	case MBA_REJECTED_FCP_CMD:
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			"qla_target(%d): Async event LS_REJECT occurred "
+			"(m[0]=%x, m[1]=%x, m[2]=%x, m[3]=%x)", vha->vp_idx,
+			le16_to_cpu(mailbox[0]), le16_to_cpu(mailbox[1]),
+			le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3]));
+
+		if (le16_to_cpu(mailbox[3]) == 1) {
+			/* exchange starvation. */
+			vha->hw->exch_starvation++;
+			if (vha->hw->exch_starvation > 5) {
+				ql_log(ql_log_warn, vha, 0xffff,
+				    "Exchange starvation-. Resetting RISC\n");
+
+				vha->hw->exch_starvation = 0;
+				if (IS_P3P_TYPE(vha->hw))
+					set_bit(FCOE_CTX_RESET_NEEDED,
+					    &vha->dpc_flags);
+				else
+					set_bit(ISP_ABORT_NEEDED,
+					    &vha->dpc_flags);
+				qla2xxx_wake_dpc(vha);
+			}
+		}
+		break;
+
 	case MBA_PORT_UPDATE:
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03d,
 		    "qla_target(%d): Port update async event %#x "
@@ -5275,10 +5311,11 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha,
 		    le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3]));
 
 		login_code = le16_to_cpu(mailbox[2]);
-		if (login_code == 0x4)
+		if (login_code == 0x4) {
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03e,
 			    "Async MB 2: Got PLOGI Complete\n");
-		else if (login_code == 0x7)
+			vha->hw->exch_starvation = 0;
+		} else if (login_code == 0x7)
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03f,
 			    "Async MB 2: Port Logged Out\n");
 		break;
@@ -5829,7 +5866,10 @@ static void qlt_set_mode(struct scsi_qla_host *vha)
 		vha->host->active_mode = MODE_TARGET;
 		break;
 	case QLA2XXX_INI_MODE_ENABLED:
-		vha->host->active_mode |= MODE_TARGET;
+		vha->host->active_mode = MODE_UNKNOWN;
+		break;
+	case QLA2XXX_INI_MODE_DUAL:
+		vha->host->active_mode = MODE_DUAL;
 		break;
 	default:
 		break;
@@ -5852,8 +5892,8 @@ static void qlt_clear_mode(struct scsi_qla_host *vha)
 		vha->host->active_mode = MODE_INITIATOR;
 		break;
 	case QLA2XXX_INI_MODE_ENABLED:
-		vha->host->active_mode &= ~MODE_TARGET;
-		vha->host->active_mode |= MODE_INITIATOR;
+	case QLA2XXX_INI_MODE_DUAL:
+		vha->host->active_mode = MODE_INITIATOR;
 		break;
 	default:
 		break;
@@ -5948,9 +5988,6 @@ static void qlt_disable_vha(struct scsi_qla_host *vha)
 void
 qlt_vport_create(struct scsi_qla_host *vha, struct qla_hw_data *ha)
 {
-	if (!qla_tgt_mode_enabled(vha))
-		return;
-
 	vha->vha_tgt.qla_tgt = NULL;
 
 	mutex_init(&vha->vha_tgt.tgt_mutex);
@@ -5981,7 +6018,6 @@ qlt_rff_id(struct scsi_qla_host *vha, struct ct_sns_req *ct_req)
 		ct_req->req.rff_id.fc4_feature = BIT_1;
 	} else if (qla_dual_mode_enabled(vha))
 		ct_req->req.rff_id.fc4_feature = BIT_0 | BIT_1;
-
 }
 
 /*
@@ -6000,7 +6036,7 @@ qlt_init_atio_q_entries(struct scsi_qla_host *vha)
 	uint16_t cnt;
 	struct atio_from_isp *pkt = (struct atio_from_isp *)ha->tgt.atio_ring;
 
-	if (!qla_tgt_mode_enabled(vha))
+	if (qla_ini_mode_enabled(vha))
 		return;
 
 	for (cnt = 0; cnt < ha->tgt.atio_q_length; cnt++) {
@@ -6093,8 +6129,10 @@ void
 qlt_24xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_24xx *nv)
 {
 	struct qla_hw_data *ha = vha->hw;
+	u32 tmp;
+	u16 t;
 
-	if (qla_tgt_mode_enabled(vha)) {
+	if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) {
 		if (!ha->tgt.saved_set) {
 			/* We save only once */
 			ha->tgt.saved_exchange_count = nv->exchange_count;
@@ -6107,7 +6145,24 @@ qlt_24xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_24xx *nv)
 			ha->tgt.saved_set = 1;
 		}
 
-		nv->exchange_count = cpu_to_le16(0xFFFF);
+		if (qla_tgt_mode_enabled(vha)) {
+			nv->exchange_count = cpu_to_le16(0xFFFF);
+		} else {			/* dual */
+			if (ql_dm_tgt_ex_pct > 100) {
+				ql_dm_tgt_ex_pct = 50;
+			} else if (ql_dm_tgt_ex_pct == 100) {
+				/* leave some for FW */
+				ql_dm_tgt_ex_pct = 95;
+			}
+
+			tmp = ha->orig_fw_xcb_count * ql_dm_tgt_ex_pct;
+			tmp = tmp/100;
+			if (tmp > 0xffff)
+				tmp = 0xffff;
+
+			t = tmp & 0xffff;
+			nv->exchange_count = cpu_to_le16(t);
+		}
 
 		/* Enable target mode */
 		nv->firmware_options_1 |= cpu_to_le32(BIT_4);
@@ -6192,11 +6247,13 @@ void
 qlt_81xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_81xx *nv)
 {
 	struct qla_hw_data *ha = vha->hw;
+	u32 tmp;
+	u16 t;
 
 	if (!QLA_TGT_MODE_ENABLED())
 		return;
 
-	if (qla_tgt_mode_enabled(vha)) {
+	if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) {
 		if (!ha->tgt.saved_set) {
 			/* We save only once */
 			ha->tgt.saved_exchange_count = nv->exchange_count;
@@ -6209,7 +6266,23 @@ qlt_81xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_81xx *nv)
 			ha->tgt.saved_set = 1;
 		}
 
-		nv->exchange_count = cpu_to_le16(0xFFFF);
+		if (qla_tgt_mode_enabled(vha)) {
+			nv->exchange_count = cpu_to_le16(0xFFFF);
+		} else {			/* dual */
+			if (ql_dm_tgt_ex_pct > 100) {
+				ql_dm_tgt_ex_pct = 50;
+			} else if (ql_dm_tgt_ex_pct == 100) {
+				/* leave some for FW */
+				ql_dm_tgt_ex_pct = 95;
+			}
+
+			tmp = ha->orig_fw_xcb_count * ql_dm_tgt_ex_pct;
+			tmp = tmp/100;
+			if (tmp > 0xffff)
+				tmp = 0xffff;
+			t = tmp & 0xffff;
+			nv->exchange_count = cpu_to_le16(t);
+		}
 
 		/* Enable target mode */
 		nv->firmware_options_1 |= cpu_to_le32(BIT_4);
@@ -6319,10 +6392,11 @@ void
 qlt_modify_vp_config(struct scsi_qla_host *vha,
 	struct vp_config_entry_24xx *vpmod)
 {
-	if (qla_tgt_mode_enabled(vha))
+	/* enable target mode.  Bit5 = 1 => disable */
+	if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha))
 		vpmod->options_idx1 &= ~BIT_5;
 
-	/* Disable ini mode, if requested. */
+	/* Disable ini mode, if requested.  bit4 = 1 => disable */
 	if (qla_tgt_mode_enabled(vha))
 		vpmod->options_idx1 &= ~BIT_4;
 }
@@ -6477,6 +6551,8 @@ static int __init qlt_parse_ini_mode(void)
 		ql2x_ini_mode = QLA2XXX_INI_MODE_DISABLED;
 	else if (strcasecmp(qlini_mode, QLA2XXX_INI_MODE_STR_ENABLED) == 0)
 		ql2x_ini_mode = QLA2XXX_INI_MODE_ENABLED;
+	else if (strcasecmp(qlini_mode, QLA2XXX_INI_MODE_STR_DUAL) == 0)
+		ql2x_ini_mode = QLA2XXX_INI_MODE_DUAL;
 	else
 		return false;
 
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 5e56192a4877..ac86b379a269 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -45,10 +45,12 @@
 #define QLA2XXX_INI_MODE_STR_EXCLUSIVE	"exclusive"
 #define QLA2XXX_INI_MODE_STR_DISABLED	"disabled"
 #define QLA2XXX_INI_MODE_STR_ENABLED	"enabled"
+#define QLA2XXX_INI_MODE_STR_DUAL		"dual"
 
 #define QLA2XXX_INI_MODE_EXCLUSIVE	0
 #define QLA2XXX_INI_MODE_DISABLED	1
 #define QLA2XXX_INI_MODE_ENABLED	2
+#define QLA2XXX_INI_MODE_DUAL	3
 
 #define QLA2XXX_COMMAND_COUNT_INIT	250
 #define QLA2XXX_IMMED_NOTIFY_COUNT_INIT 250
@@ -975,6 +977,7 @@ extern void qlt_update_vp_map(struct scsi_qla_host *, int);
  * is not set. Right now, ha value is ignored.
  */
 #define QLA_TGT_MODE_ENABLED() (ql2x_ini_mode != QLA2XXX_INI_MODE_ENABLED)
+
 extern int ql2x_ini_mode;
 
 static inline bool qla_tgt_mode_enabled(struct scsi_qla_host *ha)
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index e37d7ee95473..8b878a2d7304 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1744,7 +1744,7 @@ static int tcm_qla2xxx_lport_register_npiv_cb(struct scsi_qla_host *base_vha,
 			(struct tcm_qla2xxx_lport *)base_vha->vha_tgt.target_lport_ptr;
 	struct fc_vport_identifiers vport_id;
 
-	if (!qla_tgt_mode_enabled(base_vha)) {
+	if (qla_ini_mode_enabled(base_vha)) {
 		pr_err("qla2xxx base_vha not enabled for target mode\n");
 		return -EPERM;
 	}
-- 
GitLab


From 0ca55938497412f9ffdbcb5cb7c4f8d6d28356ee Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <himanshu.madhani@cavium.com>
Date: Thu, 19 Jan 2017 22:28:02 -0800
Subject: [PATCH 069/898] qla2xxx: Remove unused reverse_ini_mode

With support for dual mode in the driver, this mode becomes
dead code. Remove reverse_ini_mode from code.

Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_def.h    |  1 -
 drivers/scsi/qla2xxx/qla_target.c | 10 ----------
 drivers/scsi/qla2xxx/qla_target.h |  8 --------
 3 files changed, 19 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index f67a1c82502c..4ff30d136924 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3237,7 +3237,6 @@ struct qlt_hw_data {
 	/* Protected by hw lock */
 	uint32_t enable_class_2:1;
 	uint32_t enable_explicit_conf:1;
-	uint32_t ini_mode_force_reverse:1;
 	uint32_t node_name_set:1;
 
 	dma_addr_t atio_dma;	/* Physical address. */
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index c8f312f8e0ff..6571869c676a 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -5858,8 +5858,6 @@ EXPORT_SYMBOL(qlt_lport_deregister);
 /* Must be called under HW lock */
 static void qlt_set_mode(struct scsi_qla_host *vha)
 {
-	struct qla_hw_data *ha = vha->hw;
-
 	switch (ql2x_ini_mode) {
 	case QLA2XXX_INI_MODE_DISABLED:
 	case QLA2XXX_INI_MODE_EXCLUSIVE:
@@ -5874,16 +5872,11 @@ static void qlt_set_mode(struct scsi_qla_host *vha)
 	default:
 		break;
 	}
-
-	if (ha->tgt.ini_mode_force_reverse)
-		qla_reverse_ini_mode(vha);
 }
 
 /* Must be called under HW lock */
 static void qlt_clear_mode(struct scsi_qla_host *vha)
 {
-	struct qla_hw_data *ha = vha->hw;
-
 	switch (ql2x_ini_mode) {
 	case QLA2XXX_INI_MODE_DISABLED:
 		vha->host->active_mode = MODE_UNKNOWN;
@@ -5898,9 +5891,6 @@ static void qlt_clear_mode(struct scsi_qla_host *vha)
 	default:
 		break;
 	}
-
-	if (ha->tgt.ini_mode_force_reverse)
-		qla_reverse_ini_mode(vha);
 }
 
 /*
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index ac86b379a269..a7f90dcaae37 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -995,14 +995,6 @@ static inline bool qla_dual_mode_enabled(struct scsi_qla_host *ha)
 	return (ha->host->active_mode == MODE_DUAL);
 }
 
-static inline void qla_reverse_ini_mode(struct scsi_qla_host *ha)
-{
-	if (ha->host->active_mode & MODE_INITIATOR)
-		ha->host->active_mode &= ~MODE_INITIATOR;
-	else
-		ha->host->active_mode |= MODE_INITIATOR;
-}
-
 static inline uint32_t sid_to_key(const uint8_t *s_id)
 {
 	uint32_t key;
-- 
GitLab


From 41dc529a4602ac737020f423f84686a81de38e6d Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 19 Jan 2017 22:28:03 -0800
Subject: [PATCH 070/898] qla2xxx: Improve RSCN handling in driver

Current code blindly does State Change Registration when
the link is up. Move SCR behind fabric scan, so that arbitrated
loop scan would not get erroneous error message.

Some of the other improvements are as follows

- Add session deletion for TPRLO and send acknowledgment for TPRLO.
- Enable FW option to move ABTS, RIDA & PUREX from RSPQ to ATIOQ.
- Save NPort ID early in link init.
- Move ABTS & RIDA to ATIOQ helps in keeping command ordering and
  link up sequence ordering.
- Save Nport ID and update VP map so that SCSI CMD/ATIO won't be dropped.
- fcport alloc does the initializes memory to zero. Remove memset to
  zero since It might corrupt link list.
- Turn off Registration for State Change MB in loop mode.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_def.h    |  11 +-
 drivers/scsi/qla2xxx/qla_fw.h     |  75 ++++++++--
 drivers/scsi/qla2xxx/qla_gbl.h    |   2 +
 drivers/scsi/qla2xxx/qla_gs.c     |   4 +-
 drivers/scsi/qla2xxx/qla_init.c   | 150 +++++++++++++++----
 drivers/scsi/qla2xxx/qla_isr.c    |   6 +-
 drivers/scsi/qla2xxx/qla_mbx.c    | 144 +++++++++++-------
 drivers/scsi/qla2xxx/qla_os.c     |  48 +++---
 drivers/scsi/qla2xxx/qla_target.c | 238 +++++++++++++++++++++++++++---
 9 files changed, 533 insertions(+), 145 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 4ff30d136924..3881790e80da 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2226,6 +2226,13 @@ enum fcport_mgt_event {
 	FCME_DELETE_DONE,
 };
 
+enum rscn_addr_format {
+	RSCN_PORT_ADDR,
+	RSCN_AREA_ADDR,
+	RSCN_DOM_ADDR,
+	RSCN_FAB_ADDR,
+};
+
 /*
  * Fibre channel port structure.
  */
@@ -3956,7 +3963,7 @@ typedef struct scsi_qla_host {
 #define FCOE_CTX_RESET_NEEDED	18	/* Initiate FCoE context reset */
 #define MPI_RESET_NEEDED	19	/* Initiate MPI FW reset */
 #define ISP_QUIESCE_NEEDED	20	/* Driver need some quiescence */
-#define SCR_PENDING		21	/* SCR in target mode */
+#define FREE_BIT 21
 #define PORT_UPDATE_NEEDED	22
 #define FX00_RESET_RECOVERY	23
 #define FX00_TARGET_SCAN	24
@@ -4010,7 +4017,9 @@ typedef struct scsi_qla_host {
 	/* list of commands waiting on workqueue */
 	struct list_head	qla_cmd_list;
 	struct list_head	qla_sess_op_cmd_list;
+	struct list_head	unknown_atio_list;
 	spinlock_t		cmd_list_lock;
+	struct delayed_work	unknown_atio_work;
 
 	/* Counter to detect races between ELS and RSCN events */
 	atomic_t		generation_tick;
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index ee135cf96aee..1f808928763b 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -1301,27 +1301,76 @@ struct vp_config_entry_24xx {
 };
 
 #define VP_RPT_ID_IOCB_TYPE	0x32	/* Report ID Acquisition entry. */
+enum VP_STATUS {
+	VP_STAT_COMPL,
+	VP_STAT_FAIL,
+	VP_STAT_ID_CHG,
+	VP_STAT_SNS_TO,				/* timeout */
+	VP_STAT_SNS_RJT,
+	VP_STAT_SCR_TO,				/* timeout */
+	VP_STAT_SCR_RJT,
+};
+
+enum VP_FLAGS {
+	VP_FLAGS_CON_FLOOP = 1,
+	VP_FLAGS_CON_P2P = 2,
+	VP_FLAGS_CON_FABRIC = 3,
+	VP_FLAGS_NAME_VALID = BIT_5,
+};
+
 struct vp_rpt_id_entry_24xx {
 	uint8_t entry_type;		/* Entry type. */
 	uint8_t entry_count;		/* Entry count. */
 	uint8_t sys_define;		/* System defined. */
 	uint8_t entry_status;		/* Entry Status. */
-
-	uint32_t handle;		/* System handle. */
-
-	uint16_t vp_count;		/* Format 0 -- | VP setup | VP acq |. */
-					/* Format 1 -- | VP count |. */
-	uint16_t vp_idx;		/* Format 0 -- Reserved. */
-					/* Format 1 -- VP status and index. */
+	uint32_t resv1;
+	uint8_t vp_acquired;
+	uint8_t vp_setup;
+	uint8_t vp_idx;		/* Format 0=reserved */
+	uint8_t vp_status;	/* Format 0=reserved */
 
 	uint8_t port_id[3];
 	uint8_t format;
-
-	uint8_t vp_idx_map[16];
-
-	uint8_t reserved_4[24];
-	uint16_t bbcr;
-	uint8_t reserved_5[6];
+	union {
+		struct {
+			/* format 0 loop */
+			uint8_t vp_idx_map[16];
+			uint8_t reserved_4[32];
+		} f0;
+		struct {
+			/* format 1 fabric */
+			uint8_t vpstat1_subcode; /* vp_status=1 subcode */
+			uint8_t flags;
+			uint16_t fip_flags;
+			uint8_t rsv2[12];
+
+			uint8_t ls_rjt_vendor;
+			uint8_t ls_rjt_explanation;
+			uint8_t ls_rjt_reason;
+			uint8_t rsv3[5];
+
+			uint8_t port_name[8];
+			uint8_t node_name[8];
+			uint16_t bbcr;
+			uint8_t reserved_5[6];
+		} f1;
+		struct { /* format 2: N2N direct connect */
+		    uint8_t vpstat1_subcode;
+		    uint8_t flags;
+		    uint16_t rsv6;
+		    uint8_t rsv2[12];
+
+		    uint8_t ls_rjt_vendor;
+		    uint8_t ls_rjt_explanation;
+		    uint8_t ls_rjt_reason;
+		    uint8_t rsv3[5];
+
+		    uint8_t port_name[8];
+		    uint8_t node_name[8];
+		    uint32_t remote_nport_id;
+		    uint32_t reserved_5;
+		} f2;
+	} u;
 };
 
 #define VF_EVFP_IOCB_TYPE       0x26    /* Exchange Virtual Fabric Parameters entry. */
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index dd95ff620ae3..e0914575aab3 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -138,6 +138,7 @@ extern int ql2xmdenable;
 extern int ql2xexlogins;
 extern int ql2xexchoffld;
 extern int ql2xfwholdabts;
+extern int ql2xmvasynctoatio;
 
 extern int qla2x00_loop_reset(scsi_qla_host_t *);
 extern void qla2x00_abort_all_cmds(scsi_qla_host_t *, int);
@@ -844,5 +845,6 @@ extern void qlt_schedule_sess_for_deletion_lock(struct fc_port *);
 extern struct fc_port *qlt_find_sess_invalidate_other(scsi_qla_host_t *,
 	uint64_t wwn, port_id_t port_id, uint16_t loop_id, struct fc_port **);
 void qla24xx_delete_sess_fn(struct work_struct *);
+void qlt_unknown_atio_work_fn(struct work_struct *);
 
 #endif /* _QLA_GBL_H */
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 8f7054dc742b..d1074fb0fff8 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -2914,8 +2914,10 @@ int qla24xx_async_gidpn(scsi_qla_host_t *vha, fc_port_t *fcport)
 int qla24xx_post_gidpn_work(struct scsi_qla_host *vha, fc_port_t *fcport)
 {
 	struct qla_work_evt *e;
+	int ls;
 
-	if ((atomic_read(&vha->loop_state) != LOOP_READY) ||
+	ls = atomic_read(&vha->loop_state);
+	if (((ls != LOOP_READY) && (ls != LOOP_UP)) ||
 		test_bit(UNLOADING, &vha->dpc_flags))
 		return 0;
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 4c0a2d8aa964..68430934fa8d 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1071,10 +1071,10 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
 	qla24xx_fcport_handle_login(vha, fcport);
 }
 
-void qla2x00_fcport_event_handler(scsi_qla_host_t *vha,
-	struct event_arg *ea)
+void qla2x00_fcport_event_handler(scsi_qla_host_t *vha, struct event_arg *ea)
 {
-	fc_port_t *fcport;
+	fc_port_t *fcport, *f, *tf;
+	uint32_t id = 0, mask, rid;
 	int rc;
 
 	switch (ea->event) {
@@ -1087,20 +1087,55 @@ void qla2x00_fcport_event_handler(scsi_qla_host_t *vha,
 	case FCME_RSCN:
 		if (test_bit(UNLOADING, &vha->dpc_flags))
 			return;
+		switch (ea->id.b.rsvd_1) {
+		case RSCN_PORT_ADDR:
+			fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1);
+			if (!fcport) {
+				/* cable moved */
+				rc = qla24xx_post_gpnid_work(vha, &ea->id);
+				if (rc) {
+					ql_log(ql_log_warn, vha, 0xffff,
+						"RSCN GPNID work failed %02x%02x%02x\n",
+						ea->id.b.domain, ea->id.b.area,
+						ea->id.b.al_pa);
+				}
+			} else {
+				ea->fcport = fcport;
+				qla24xx_handle_rscn_event(fcport, ea);
+			}
+			break;
+		case RSCN_AREA_ADDR:
+		case RSCN_DOM_ADDR:
+			if (ea->id.b.rsvd_1 == RSCN_AREA_ADDR) {
+				mask = 0xffff00;
+				ql_log(ql_dbg_async, vha, 0xffff,
+					   "RSCN: Area 0x%06x was affected\n",
+					   ea->id.b24);
+			} else {
+				mask = 0xff0000;
+				ql_log(ql_dbg_async, vha, 0xffff,
+					   "RSCN: Domain 0x%06x was affected\n",
+					   ea->id.b24);
+			}
 
-		fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1);
-		if (!fcport) {
-			/* cable moved */
-			rc = qla24xx_post_gpnid_work(vha, &ea->id);
-			if (rc) {
-				ql_log(ql_log_warn, vha, 0xffff,
-					"RSCN GPNID work failed %02x%02x%02x\n",
-					ea->id.b.domain, ea->id.b.area,
-					ea->id.b.al_pa);
+			rid = ea->id.b24 & mask;
+			list_for_each_entry_safe(f, tf, &vha->vp_fcports,
+			    list) {
+				id = f->d_id.b24 & mask;
+				if (rid == id) {
+					ea->fcport = f;
+					qla24xx_handle_rscn_event(f, ea);
+				}
 			}
-		} else {
-			ea->fcport = fcport;
-			qla24xx_handle_rscn_event(fcport, ea);
+			break;
+		case RSCN_FAB_ADDR:
+		default:
+			ql_log(ql_log_warn, vha, 0xffff,
+				"RSCN: Fabric was affected. Addr format %d\n",
+				ea->id.b.rsvd_1);
+			qla2x00_mark_all_devices_lost(vha, 1);
+			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
 		}
 		break;
 	case FCME_GIDPN_DONE:
@@ -2947,6 +2982,21 @@ qla24xx_update_fw_options(scsi_qla_host_t *vha)
 			__func__, ha->fw_options[2]);
 	}
 
+	/* Move PUREX, ABTS RX & RIDA to ATIOQ */
+	if (ql2xmvasynctoatio) {
+		if (qla_tgt_mode_enabled(vha) ||
+		    qla_dual_mode_enabled(vha))
+			ha->fw_options[2] |= BIT_11;
+		else
+			ha->fw_options[2] &= ~BIT_11;
+	}
+
+	ql_dbg(ql_dbg_init, vha, 0xffff,
+		"%s, add FW options 1-3 = 0x%04x 0x%04x 0x%04x mode %x\n",
+		__func__, ha->fw_options[1], ha->fw_options[2],
+		ha->fw_options[3], vha->host->active_mode);
+	qla2x00_set_fw_options(vha, ha->fw_options);
+
 	/* Update Serial Link options. */
 	if ((le16_to_cpu(ha->fw_seriallink_options24[0]) & BIT_0) == 0)
 		return;
@@ -3953,10 +4003,11 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 
 	} else if (ha->current_topology == ISP_CFG_N) {
 		clear_bit(RSCN_UPDATE, &flags);
-
+	} else if (ha->current_topology == ISP_CFG_NL) {
+		clear_bit(RSCN_UPDATE, &flags);
+		set_bit(LOCAL_LOOP_UPDATE, &flags);
 	} else if (!vha->flags.online ||
 	    (test_bit(ABORT_ISP_ACTIVE, &flags))) {
-
 		set_bit(RSCN_UPDATE, &flags);
 		set_bit(LOCAL_LOOP_UPDATE, &flags);
 	}
@@ -4058,6 +4109,7 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 	uint16_t	loop_id;
 	uint8_t		domain, area, al_pa;
 	struct qla_hw_data *ha = vha->hw;
+	unsigned long flags;
 
 	found_devs = 0;
 	new_fcport = NULL;
@@ -4098,7 +4150,7 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 			    "Marking port lost loop_id=0x%04x.\n",
 			    fcport->loop_id);
 
-			qla2x00_set_fcport_state(fcport, FCS_DEVICE_LOST);
+			qla2x00_mark_device_lost(vha, fcport, 0, 0);
 		}
 	}
 
@@ -4129,13 +4181,14 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 		if (loop_id > LAST_LOCAL_LOOP_ID)
 			continue;
 
-		memset(new_fcport, 0, sizeof(fc_port_t));
+		memset(new_fcport->port_name, 0, WWN_SIZE);
 
 		/* Fill in member data. */
 		new_fcport->d_id.b.domain = domain;
 		new_fcport->d_id.b.area = area;
 		new_fcport->d_id.b.al_pa = al_pa;
 		new_fcport->loop_id = loop_id;
+
 		rval2 = qla2x00_get_port_database(vha, new_fcport, 0);
 		if (rval2 != QLA_SUCCESS) {
 			ql_dbg(ql_dbg_disc, vha, 0x201a,
@@ -4148,6 +4201,7 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 			continue;
 		}
 
+		spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 		/* Check for matching device in port list. */
 		found = 0;
 		fcport = NULL;
@@ -4163,6 +4217,12 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 			memcpy(fcport->node_name, new_fcport->node_name,
 			    WWN_SIZE);
 
+			if (!fcport->login_succ) {
+				vha->fcport_count++;
+				fcport->login_succ = 1;
+				fcport->disc_state = DSC_LOGIN_COMPLETE;
+			}
+
 			found++;
 			break;
 		}
@@ -4173,16 +4233,28 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 
 			/* Allocate a new replacement fcport. */
 			fcport = new_fcport;
+			if (!fcport->login_succ) {
+				vha->fcport_count++;
+				fcport->login_succ = 1;
+				fcport->disc_state = DSC_LOGIN_COMPLETE;
+			}
+
+			spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
 			new_fcport = qla2x00_alloc_fcport(vha, GFP_KERNEL);
+
 			if (new_fcport == NULL) {
 				ql_log(ql_log_warn, vha, 0x201c,
 				    "Failed to allocate memory for fcport.\n");
 				rval = QLA_MEMORY_ALLOC_FAILED;
 				goto cleanup_allocation;
 			}
+			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 			new_fcport->flags &= ~FCF_FABRIC_DEVICE;
 		}
 
+		spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
 		/* Base iIDMA settings on HBA port speed. */
 		fcport->fp_speed = ha->link_data_rate;
 
@@ -4371,6 +4443,16 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 	}
 	vha->device_flags |= SWITCH_FOUND;
 
+
+	if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) {
+		rval = qla2x00_send_change_request(vha, 0x3, 0);
+		if (rval != QLA_SUCCESS)
+			ql_log(ql_log_warn, vha, 0x121,
+				"Failed to enable receiving of RSCN requests: 0x%x.\n",
+				rval);
+	}
+
+
 	do {
 		qla2x00_mgmt_svr_login(vha);
 
@@ -6116,6 +6198,7 @@ uint8_t qla27xx_find_valid_image(struct scsi_qla_host *vha)
 
 	for (chksum = 0; cnt--; wptr++)
 		chksum += le32_to_cpu(*wptr);
+
 	if (chksum) {
 		ql_dbg(ql_dbg_init, vha, 0x018c,
 		    "Checksum validation failed for primary image (0x%x)\n",
@@ -7128,6 +7211,10 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 		vha->flags.process_response_queue = 1;
 	}
 
+	 /* enable RIDA Format2 */
+	if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha))
+		icb->firmware_options_3 |= BIT_0;
+
 	if (rval) {
 		ql_log(ql_log_warn, vha, 0x0076,
 		    "NVRAM configuration failed.\n");
@@ -7252,13 +7339,26 @@ qla81xx_update_fw_options(scsi_qla_host_t *vha)
 			__func__, ha->fw_options[2]);
 	}
 
-	if (!ql2xetsenable)
-		goto out;
+	/* Move PUREX, ABTS RX & RIDA to ATIOQ */
+	if (ql2xmvasynctoatio) {
+		if (qla_tgt_mode_enabled(vha) ||
+		    qla_dual_mode_enabled(vha))
+			ha->fw_options[2] |= BIT_11;
+		else
+			ha->fw_options[2] &= ~BIT_11;
+	}
+
+	if (ql2xetsenable) {
+		/* Enable ETS Burst. */
+		memset(ha->fw_options, 0, sizeof(ha->fw_options));
+		ha->fw_options[2] |= BIT_9;
+	}
+
+	ql_dbg(ql_dbg_init, vha, 0xffff,
+		"%s, add FW options 1-3 = 0x%04x 0x%04x 0x%04x mode %x\n",
+		__func__, ha->fw_options[1], ha->fw_options[2],
+		ha->fw_options[3], vha->host->active_mode);
 
-	/* Enable ETS Burst. */
-	memset(ha->fw_options, 0, sizeof(ha->fw_options));
-	ha->fw_options[2] |= BIT_9;
-out:
 	qla2x00_set_fw_options(vha, ha->fw_options);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index a0a3412030cb..d9577db7ddbb 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1025,10 +1025,6 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 
 		qla2x00_mark_all_devices_lost(vha, 1);
 
-		if (vha->vp_idx == 0 &&
-		    (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)))
-			set_bit(SCR_PENDING, &vha->dpc_flags);
-
 		set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
 		set_bit(VP_CONFIG_OK, &vha->vp_flags);
@@ -1073,7 +1069,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
 			memset(&ea, 0, sizeof(ea));
 			ea.event = FCME_RSCN;
 			ea.id.b24 = rscn_entry;
+			ea.id.b.rsvd_1 = rscn_entry >> 24;
 			qla2x00_fcport_event_handler(vha, &ea);
+			qla2x00_post_aen_work(vha, FCH_EVT_RSCN, rscn_entry);
 		}
 		break;
 	/* case MBA_RIO_RESPONSE: */
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 64f04aa2a503..35079f417417 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -3599,10 +3599,8 @@ void
 qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 	struct vp_rpt_id_entry_24xx *rptid_entry)
 {
-	uint8_t vp_idx;
-	uint16_t stat = le16_to_cpu(rptid_entry->vp_idx);
 	struct qla_hw_data *ha = vha->hw;
-	scsi_qla_host_t *vp;
+	scsi_qla_host_t *vp = NULL;
 	unsigned long   flags;
 	int found;
 
@@ -3613,80 +3611,124 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		return;
 
 	if (rptid_entry->format == 0) {
+		/* loop */
 		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b7,
 		    "Format 0 : Number of VPs setup %d, number of "
-		    "VPs acquired %d.\n",
-		    MSB(le16_to_cpu(rptid_entry->vp_count)),
-		    LSB(le16_to_cpu(rptid_entry->vp_count)));
+		    "VPs acquired %d.\n", rptid_entry->vp_setup,
+		    rptid_entry->vp_acquired);
 		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b8,
 		    "Primary port id %02x%02x%02x.\n",
 		    rptid_entry->port_id[2], rptid_entry->port_id[1],
 		    rptid_entry->port_id[0]);
+
+		vha->d_id.b.domain = rptid_entry->port_id[2];
+		vha->d_id.b.area = rptid_entry->port_id[1];
+		vha->d_id.b.al_pa = rptid_entry->port_id[0];
+
+		spin_lock_irqsave(&ha->vport_slock, flags);
+		qlt_update_vp_map(vha, SET_AL_PA);
+		spin_unlock_irqrestore(&ha->vport_slock, flags);
+
 	} else if (rptid_entry->format == 1) {
-		vp_idx = LSB(stat);
+		/* fabric */
 		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b9,
 		    "Format 1: VP[%d] enabled - status %d - with "
-		    "port id %02x%02x%02x.\n", vp_idx, MSB(stat),
+		    "port id %02x%02x%02x.\n", rptid_entry->vp_idx,
+			rptid_entry->vp_status,
 		    rptid_entry->port_id[2], rptid_entry->port_id[1],
 		    rptid_entry->port_id[0]);
 
 		/* buffer to buffer credit flag */
-		vha->flags.bbcr_enable = (rptid_entry->bbcr & 0xf) != 0;
-
-		/* FA-WWN is only for physical port */
-		if (!vp_idx) {
-			void *wwpn = ha->init_cb->port_name;
+		vha->flags.bbcr_enable = (rptid_entry->u.f1.bbcr & 0xf) != 0;
+
+		if (rptid_entry->vp_idx == 0) {
+			if (rptid_entry->vp_status == VP_STAT_COMPL) {
+				/* FA-WWN is only for physical port */
+				if (qla_ini_mode_enabled(vha) &&
+				    ha->flags.fawwpn_enabled &&
+				    (rptid_entry->u.f1.flags &
+				     VP_FLAGS_NAME_VALID)) {
+					memcpy(vha->port_name,
+					    rptid_entry->u.f1.port_name,
+					    WWN_SIZE);
+				}
 
-			if (!MSB(stat)) {
-				if (rptid_entry->vp_idx_map[1] & BIT_6)
-					wwpn = rptid_entry->reserved_4 + 8;
+				vha->d_id.b.domain = rptid_entry->port_id[2];
+				vha->d_id.b.area = rptid_entry->port_id[1];
+				vha->d_id.b.al_pa = rptid_entry->port_id[0];
+				spin_lock_irqsave(&ha->vport_slock, flags);
+				qlt_update_vp_map(vha, SET_AL_PA);
+				spin_unlock_irqrestore(&ha->vport_slock, flags);
 			}
-			memcpy(vha->port_name, wwpn, WWN_SIZE);
+
 			fc_host_port_name(vha->host) =
 			    wwn_to_u64(vha->port_name);
-			ql_dbg(ql_dbg_mbx, vha, 0x1018,
-			    "FA-WWN portname %016llx (%x)\n",
-			    fc_host_port_name(vha->host), MSB(stat));
-		}
-
-		vp = vha;
-		if (vp_idx == 0)
-			goto reg_needed;
 
-		if (MSB(stat) != 0 && MSB(stat) != 2) {
-			ql_dbg(ql_dbg_mbx, vha, 0x10ba,
-			    "Could not acquire ID for VP[%d].\n", vp_idx);
-			return;
-		}
+			if (qla_ini_mode_enabled(vha))
+				ql_dbg(ql_dbg_mbx, vha, 0x1018,
+				    "FA-WWN portname %016llx (%x)\n",
+				    fc_host_port_name(vha->host),
+				    rptid_entry->vp_status);
 
-		found = 0;
-		spin_lock_irqsave(&ha->vport_slock, flags);
-		list_for_each_entry(vp, &ha->vp_list, list) {
-			if (vp_idx == vp->vp_idx) {
-				found = 1;
-				break;
+			set_bit(REGISTER_FC4_NEEDED, &vha->dpc_flags);
+			set_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags);
+		} else {
+			if (rptid_entry->vp_status != VP_STAT_COMPL &&
+				rptid_entry->vp_status != VP_STAT_ID_CHG) {
+				ql_dbg(ql_dbg_mbx, vha, 0x10ba,
+				    "Could not acquire ID for VP[%d].\n",
+				    rptid_entry->vp_idx);
+				return;
 			}
-		}
-		spin_unlock_irqrestore(&ha->vport_slock, flags);
 
-		if (!found)
-			return;
+			found = 0;
+			spin_lock_irqsave(&ha->vport_slock, flags);
+			list_for_each_entry(vp, &ha->vp_list, list) {
+				if (rptid_entry->vp_idx == vp->vp_idx) {
+					found = 1;
+					break;
+				}
+			}
+			spin_unlock_irqrestore(&ha->vport_slock, flags);
 
-		vp->d_id.b.domain = rptid_entry->port_id[2];
-		vp->d_id.b.area =  rptid_entry->port_id[1];
-		vp->d_id.b.al_pa = rptid_entry->port_id[0];
+			if (!found)
+				return;
 
-		/*
-		 * Cannot configure here as we are still sitting on the
-		 * response queue. Handle it in dpc context.
-		 */
-		set_bit(VP_IDX_ACQUIRED, &vp->vp_flags);
+			vp->d_id.b.domain = rptid_entry->port_id[2];
+			vp->d_id.b.area =  rptid_entry->port_id[1];
+			vp->d_id.b.al_pa = rptid_entry->port_id[0];
+			spin_lock_irqsave(&ha->vport_slock, flags);
+			qlt_update_vp_map(vp, SET_AL_PA);
+			spin_unlock_irqrestore(&ha->vport_slock, flags);
 
-reg_needed:
-		set_bit(REGISTER_FC4_NEEDED, &vp->dpc_flags);
-		set_bit(REGISTER_FDMI_NEEDED, &vp->dpc_flags);
+			/*
+			 * Cannot configure here as we are still sitting on the
+			 * response queue. Handle it in dpc context.
+			 */
+			set_bit(VP_IDX_ACQUIRED, &vp->vp_flags);
+			set_bit(REGISTER_FC4_NEEDED, &vp->dpc_flags);
+			set_bit(REGISTER_FDMI_NEEDED, &vp->dpc_flags);
+		}
 		set_bit(VP_DPC_NEEDED, &vha->dpc_flags);
 		qla2xxx_wake_dpc(vha);
+	} else if (rptid_entry->format == 2) {
+		ql_dbg(ql_dbg_async, vha, 0xffff,
+		    "RIDA: format 2/N2N Primary port id %02x%02x%02x.\n",
+		    rptid_entry->port_id[2], rptid_entry->port_id[1],
+		    rptid_entry->port_id[0]);
+
+		ql_dbg(ql_dbg_async, vha, 0xffff,
+		    "N2N: Remote WWPN %8phC.\n",
+		    rptid_entry->u.f2.port_name);
+
+		/* N2N.  direct connect */
+		vha->d_id.b.domain = rptid_entry->port_id[2];
+		vha->d_id.b.area = rptid_entry->port_id[1];
+		vha->d_id.b.al_pa = rptid_entry->port_id[0];
+
+		spin_lock_irqsave(&ha->vport_slock, flags);
+		qlt_update_vp_map(vha, SET_AL_PA);
+		spin_unlock_irqrestore(&ha->vport_slock, flags);
 	}
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 9c4699623410..bdaa238ca0ab 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -237,6 +237,13 @@ MODULE_PARM_DESC(ql2xfwholdabts,
 		"0 (Default) Do not set fw option. "
 		"1 - Set fw option to hold ABTS.");
 
+int ql2xmvasynctoatio = 1;
+module_param(ql2xmvasynctoatio, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(ql2xmvasynctoatio,
+		"Move PUREX, ABTS RX and RIDA IOCBs to ATIOQ"
+		"0 (Default). Do not move IOCBs"
+		"1 - Move IOCBs.");
+
 /*
  * SCSI host template entry points
  */
@@ -2932,18 +2939,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto probe_init_failed;
 
-	base_vha->gnl.size = (ha->max_loop_id + 1) *
-		sizeof(struct get_name_list_extended);
-	base_vha->gnl.l = dma_alloc_coherent(&ha->pdev->dev,
-		base_vha->gnl.size, &base_vha->gnl.ldma, GFP_KERNEL);
-	INIT_LIST_HEAD(&base_vha->gnl.fcports);
-
-	if (base_vha->gnl.l == NULL) {
-		ql_log(ql_log_fatal, base_vha, 0xffff,
-			"Alloc failed for name list.\n");
-		goto probe_init_failed;
-	}
-
 	/* Alloc arrays of request and response ring ptrs */
 	if (!qla2x00_alloc_queues(ha, req, rsp)) {
 		ql_log(ql_log_fatal, base_vha, 0x003d,
@@ -4250,10 +4245,10 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	struct scsi_qla_host *vha = NULL;
 
 	host = scsi_host_alloc(sht, sizeof(scsi_qla_host_t));
-	if (host == NULL) {
+	if (!host) {
 		ql_log_pci(ql_log_fatal, ha->pdev, 0x0107,
 		    "Failed to allocate host from the scsi layer, aborting.\n");
-		goto fail;
+		return NULL;
 	}
 
 	/* Clear our data area */
@@ -4272,11 +4267,23 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	INIT_LIST_HEAD(&vha->logo_list);
 	INIT_LIST_HEAD(&vha->plogi_ack_list);
 	INIT_LIST_HEAD(&vha->qp_list);
+	INIT_LIST_HEAD(&vha->gnl.fcports);
 
 	spin_lock_init(&vha->work_lock);
 	spin_lock_init(&vha->cmd_list_lock);
 	init_waitqueue_head(&vha->fcport_waitQ);
 
+	vha->gnl.size =
+	    sizeof(struct get_name_list_extended[ha->max_loop_id+1]);
+	vha->gnl.l = dma_alloc_coherent(&ha->pdev->dev,
+	    vha->gnl.size, &vha->gnl.ldma, GFP_KERNEL);
+	if (!vha->gnl.l) {
+		ql_log(ql_log_fatal, vha, 0xffff,
+		    "Alloc failed for name list.\n");
+		scsi_remove_host(vha->host);
+		return NULL;
+	}
+
 	sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no);
 	ql_dbg(ql_dbg_init, vha, 0x0041,
 	    "Allocated the host=%p hw=%p vha=%p dev_name=%s",
@@ -4284,9 +4291,6 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	    dev_name(&(ha->pdev->dev)));
 
 	return vha;
-
-fail:
-	return vha;
 }
 
 struct qla_work_evt *
@@ -5512,16 +5516,6 @@ qla2x00_do_dpc(void *data)
 			qla2x00_update_fcports(base_vha);
 		}
 
-		if (test_bit(SCR_PENDING, &base_vha->dpc_flags)) {
-			int ret;
-			ret = qla2x00_send_change_request(base_vha, 0x3, 0);
-			if (ret != QLA_SUCCESS)
-				ql_log(ql_log_warn, base_vha, 0x121,
-				    "Failed to enable receiving of RSCN "
-				    "requests: 0x%x.\n", ret);
-			clear_bit(SCR_PENDING, &base_vha->dpc_flags);
-		}
-
 		if (IS_QLAFX00(ha))
 			goto loop_resync_check;
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 6571869c676a..1cd3734292f9 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -224,6 +224,105 @@ static inline void qlt_decr_num_pend_cmds(struct scsi_qla_host *vha)
 	spin_unlock_irqrestore(&vha->hw->tgt.q_full_lock, flags);
 }
 
+
+static void qlt_queue_unknown_atio(scsi_qla_host_t *vha,
+	struct atio_from_isp *atio,	uint8_t ha_locked)
+{
+	struct qla_tgt_sess_op *u;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+	unsigned long flags;
+
+	if (tgt->tgt_stop) {
+		ql_dbg(ql_dbg_async, vha, 0xffff,
+			   "qla_target(%d): dropping unknown ATIO_TYPE7, "
+			   "because tgt is being stopped", vha->vp_idx);
+		goto out_term;
+	}
+
+	u = kzalloc(sizeof(*u), GFP_ATOMIC);
+	if (u == NULL) {
+		ql_dbg(ql_dbg_async, vha, 0xffff,
+		    "Alloc of struct unknown_atio (size %zd) failed", sizeof(*u));
+		/* It should be harmless and on the next retry should work well */
+		goto out_term;
+	}
+
+	u->vha = vha;
+	memcpy(&u->atio, atio, sizeof(*atio));
+	INIT_LIST_HEAD(&u->cmd_list);
+
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
+	list_add_tail(&u->cmd_list, &vha->unknown_atio_list);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
+
+	schedule_delayed_work(&vha->unknown_atio_work, 1);
+
+out:
+	return;
+
+out_term:
+	qlt_send_term_exchange(vha, NULL, atio, ha_locked, 0);
+	goto out;
+}
+
+static void qlt_try_to_dequeue_unknown_atios(struct scsi_qla_host *vha,
+	uint8_t ha_locked)
+{
+	struct qla_tgt_sess_op *u, *t;
+	scsi_qla_host_t *host;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+	unsigned long flags;
+	uint8_t queued = 0;
+
+	list_for_each_entry_safe(u, t, &vha->unknown_atio_list, cmd_list) {
+		if (u->aborted) {
+			ql_dbg(ql_dbg_async, vha, 0xffff,
+			    "Freeing unknown %s %p, because of Abort",
+			    "ATIO_TYPE7", u);
+			qlt_send_term_exchange(vha, NULL, &u->atio,
+			    ha_locked, 0);
+			goto abort;
+		}
+
+		host = qlt_find_host_by_d_id(vha, u->atio.u.isp24.fcp_hdr.d_id);
+		if (host != NULL) {
+			ql_dbg(ql_dbg_async, vha, 0xffff,
+				"Requeuing unknown ATIO_TYPE7 %p", u);
+			qlt_24xx_atio_pkt(host, &u->atio, ha_locked);
+		} else if (tgt->tgt_stop) {
+			ql_dbg(ql_dbg_async, vha, 0xffff,
+				"Freeing unknown %s %p, because tgt is being stopped",
+				"ATIO_TYPE7", u);
+			qlt_send_term_exchange(vha, NULL, &u->atio,
+			    ha_locked, 0);
+		} else {
+			ql_dbg(ql_dbg_async, vha, 0xffff,
+				"u %p, vha %p, host %p, sched again..", u,
+				vha, host);
+			if (!queued) {
+				queued = 1;
+				schedule_delayed_work(&vha->unknown_atio_work,
+				    1);
+			}
+			continue;
+		}
+
+abort:
+		spin_lock_irqsave(&vha->cmd_list_lock, flags);
+		list_del(&u->cmd_list);
+		spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
+		kfree(u);
+	}
+}
+
+void qlt_unknown_atio_work_fn(struct work_struct *work)
+{
+	struct scsi_qla_host *vha = container_of(to_delayed_work(work),
+	    struct scsi_qla_host, unknown_atio_work);
+
+	qlt_try_to_dequeue_unknown_atios(vha, 0);
+}
+
 static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio, uint8_t ha_locked)
 {
@@ -244,8 +343,14 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
 			    atio->u.isp24.fcp_hdr.d_id[0],
 			    atio->u.isp24.fcp_hdr.d_id[1],
 			    atio->u.isp24.fcp_hdr.d_id[2]);
+
+
+			qlt_queue_unknown_atio(vha, atio, ha_locked);
 			break;
 		}
+		if (unlikely(!list_empty(&vha->unknown_atio_list)))
+			qlt_try_to_dequeue_unknown_atios(vha, ha_locked);
+
 		qlt_24xx_atio_pkt(host, atio, ha_locked);
 		break;
 	}
@@ -273,6 +378,31 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
 		break;
 	}
 
+	case VP_RPT_ID_IOCB_TYPE:
+		qla24xx_report_id_acquisition(vha,
+			(struct vp_rpt_id_entry_24xx *)atio);
+		break;
+
+	case ABTS_RECV_24XX:
+	{
+		struct abts_recv_from_24xx *entry =
+			(struct abts_recv_from_24xx *)atio;
+		struct scsi_qla_host *host = qlt_find_host_by_vp_idx(vha,
+			entry->vp_index);
+		if (unlikely(!host)) {
+			ql_dbg(ql_dbg_tgt, vha, 0xffff,
+			    "qla_target(%d): Response pkt (ABTS_RECV_24XX) "
+			    "received, with unknown vp_index %d\n",
+			    vha->vp_idx, entry->vp_index);
+			break;
+		}
+		qlt_response_pkt(host, (response_t *)atio);
+		break;
+
+	}
+
+	/* case PUREX_IOCB_TYPE: ql2xmvasynctoatio */
+
 	default:
 		ql_dbg(ql_dbg_tgt, vha, 0xe040,
 		    "qla_target(%d): Received unknown ATIO atio "
@@ -791,6 +921,7 @@ static void qlt_free_session_done(struct work_struct *work)
 	unsigned long flags;
 	bool logout_started = false;
 	struct event_arg ea;
+	scsi_qla_host_t *base_vha;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084,
 		"%s: se_sess %p / sess %p from port %8phC loop_id %#04x"
@@ -802,23 +933,25 @@ static void qlt_free_session_done(struct work_struct *work)
 
 
 	if (!IS_SW_RESV_ADDR(sess->d_id)) {
-	if (sess->send_els_logo) {
-		qlt_port_logo_t logo;
-		logo.id = sess->d_id;
-		logo.cmd_count = 0;
-		qlt_send_first_logo(vha, &logo);
-	}
+		if (sess->send_els_logo) {
+			qlt_port_logo_t logo;
 
-	if (sess->logout_on_delete) {
-		int rc;
-		rc = qla2x00_post_async_logout_work(vha, sess, NULL);
-		if (rc != QLA_SUCCESS)
-			ql_log(ql_log_warn, vha, 0xf085,
-			       "Schedule logo failed sess %p rc %d\n",
-			       sess, rc);
-		else
-			logout_started = true;
-	}
+			logo.id = sess->d_id;
+			logo.cmd_count = 0;
+			qlt_send_first_logo(vha, &logo);
+		}
+
+		if (sess->logout_on_delete) {
+			int rc;
+
+			rc = qla2x00_post_async_logout_work(vha, sess, NULL);
+			if (rc != QLA_SUCCESS)
+				ql_log(ql_log_warn, vha, 0xf085,
+				    "Schedule logo failed sess %p rc %d\n",
+				    sess, rc);
+			else
+				logout_started = true;
+		}
 	}
 
 	/*
@@ -841,8 +974,13 @@ static void qlt_free_session_done(struct work_struct *work)
 		}
 
 		ql_dbg(ql_dbg_disc, vha, 0xf087,
-			"%s: sess %p logout completed\n",
-			__func__, sess);
+		    "%s: sess %p logout completed\n",__func__, sess);
+	}
+
+	if (sess->logo_ack_needed) {
+		sess->logo_ack_needed = 0;
+		qla24xx_async_notify_ack(vha, sess,
+			(struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO);
 	}
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
@@ -917,6 +1055,10 @@ static void qlt_free_session_done(struct work_struct *work)
 	if (vha->fcport_count == 0)
 		wake_up_all(&vha->fcport_waitQ);
 
+	base_vha = pci_get_drvdata(ha->pdev);
+	if (test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags))
+		return;
+
 	if (!tgt || !tgt->tgt_stop) {
 		memset(&ea, 0, sizeof(ea));
 		ea.event = FCME_DELETE_DONE;
@@ -1602,6 +1744,14 @@ static int abort_cmd_for_tag(struct scsi_qla_host *vha, uint32_t tag)
 		}
 	}
 
+	list_for_each_entry(op, &vha->unknown_atio_list, cmd_list) {
+		if (tag == op->atio.u.isp24.exchange_addr) {
+			op->aborted = true;
+			spin_unlock(&vha->cmd_list_lock);
+			return 1;
+		}
+	}
+
 	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
 		if (tag == cmd->atio.u.isp24.exchange_addr) {
 			cmd->aborted = 1;
@@ -1638,6 +1788,18 @@ static void abort_cmds_for_lun(struct scsi_qla_host *vha,
 		if (op_key == key && op_lun == lun)
 			op->aborted = true;
 	}
+
+	list_for_each_entry(op, &vha->unknown_atio_list, cmd_list) {
+		uint32_t op_key;
+		u64 op_lun;
+
+		op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		op_lun = scsilun_to_int(
+			(struct scsi_lun *)&op->atio.u.isp24.fcp_cmnd.lun);
+		if (op_key == key && op_lun == lun)
+			op->aborted = true;
+	}
+
 	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
 		uint32_t cmd_key;
 		uint32_t cmd_lun;
@@ -1880,7 +2042,11 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 
 	if (mcmd->flags == QLA24XX_MGMT_SEND_NACK) {
 		if (mcmd->orig_iocb.imm_ntfy.u.isp24.status_subcode ==
-		    ELS_LOGO) {
+		    ELS_LOGO ||
+		    mcmd->orig_iocb.imm_ntfy.u.isp24.status_subcode ==
+		    ELS_PRLO ||
+		    mcmd->orig_iocb.imm_ntfy.u.isp24.status_subcode ==
+		    ELS_TPRLO) {
 			ql_dbg(ql_dbg_disc, vha, 0xffff,
 			    "TM response logo %phC status %#x state %#x",
 			    mcmd->sess->port_name, mcmd->fc_tm_rsp,
@@ -4252,11 +4418,21 @@ static int abort_cmds_for_s_id(struct scsi_qla_host *vha, port_id_t *s_id)
 	spin_lock(&vha->cmd_list_lock);
 	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
 		uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+
 		if (op_key == key) {
 			op->aborted = true;
 			count++;
 		}
 	}
+
+	list_for_each_entry(op, &vha->unknown_atio_list, cmd_list) {
+		uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		if (op_key == key) {
+			op->aborted = true;
+			count++;
+		}
+	}
+
 	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
 		uint32_t cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id);
 		if (cmd_key == key) {
@@ -4463,6 +4639,16 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		}
 		break;
 
+
+	case ELS_TPRLO:
+		if (le16_to_cpu(iocb->u.isp24.flags) &
+			NOTIFY24XX_FLAGS_GLOBAL_TPRLO) {
+			loop_id = 0xFFFF;
+			qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS);
+			res = 1;
+			break;
+		}
+		/* drop through */
 	case ELS_LOGO:
 	case ELS_PRLO:
 		spin_lock_irqsave(&ha->tgt.sess_lock, flags);
@@ -4472,7 +4658,6 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		if (sess) {
 			sess->login_gen++;
 			sess->fw_login_state = DSC_LS_LOGO_PEND;
-			sess->logout_on_delete = 0;
 			sess->logo_ack_needed = 1;
 			memcpy(sess->iocb, iocb, IOCB_SIZE);
 		}
@@ -4483,12 +4668,14 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		    "%s: logo %llx res %d sess %p ",
 		    __func__, wwn, res, sess);
 		if (res == 0) {
-			/* cmd went up to ULP. look for qlt_xmit_tm_rsp()
-			   for LOGO_ACK */
+			/*
+			 * cmd went upper layer, look for qlt_xmit_tm_rsp()
+			 * for LOGO_ACK & sess delete
+			 */
 			BUG_ON(!sess);
 			res = 0;
 		} else {
-			/* cmd did not go upstair. */
+			/* cmd did not go to upper layer. */
 			if (sess) {
 				qlt_schedule_sess_for_deletion_lock(sess);
 				res = 0;
@@ -6407,6 +6594,11 @@ qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha)
 
 	mutex_init(&base_vha->vha_tgt.tgt_mutex);
 	mutex_init(&base_vha->vha_tgt.tgt_host_action_mutex);
+
+	INIT_LIST_HEAD(&base_vha->unknown_atio_list);
+	INIT_DELAYED_WORK(&base_vha->unknown_atio_work,
+	    qlt_unknown_atio_work_fn);
+
 	qlt_clear_mode(base_vha);
 }
 
-- 
GitLab


From 25ff6af10562cfe30dd29452a8fc04ec022d4f18 Mon Sep 17 00:00:00 2001
From: Joe Carnuccio <joe.carnuccio@cavium.com>
Date: Thu, 19 Jan 2017 22:28:04 -0800
Subject: [PATCH 071/898] qla2xxx: Simplify usage of SRB structure in driver

This patch simplifies SRB structure usage in driver.

- Simplify sp->done() and sp->free() interfaces.
- Remove sp->fcport->vha to use vha pointer from sp.
- Use sp->vha context in qla2x00_rel_sp().

Signed-off-by: Joe Carnuccio <joe.carnuccio@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_bsg.c    |  23 +++----
 drivers/scsi/qla2xxx/qla_def.h    |   7 ++-
 drivers/scsi/qla2xxx/qla_gbl.h    |  14 ++---
 drivers/scsi/qla2xxx/qla_gs.c     |  32 +++++-----
 drivers/scsi/qla2xxx/qla_init.c   | 100 +++++++++++++++---------------
 drivers/scsi/qla2xxx/qla_inline.h |  13 ++--
 drivers/scsi/qla2xxx/qla_iocb.c   |  96 ++++++++++++++--------------
 drivers/scsi/qla2xxx/qla_isr.c    |  36 +++++------
 drivers/scsi/qla2xxx/qla_mr.c     |  48 +++++++-------
 drivers/scsi/qla2xxx/qla_os.c     |  35 +++++------
 drivers/scsi/qla2xxx/qla_target.c |   8 +--
 11 files changed, 201 insertions(+), 211 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 1bf8061ff803..975e7a117532 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -13,28 +13,25 @@
 
 /* BSG support for ELS/CT pass through */
 void
-qla2x00_bsg_job_done(void *data, void *ptr, int res)
+qla2x00_bsg_job_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
-	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
+	srb_t *sp = ptr;
 	struct bsg_job *bsg_job = sp->u.bsg_job;
 	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
 
 	bsg_reply->result = res;
 	bsg_job_done(bsg_job, bsg_reply->result,
 		       bsg_reply->reply_payload_rcv_len);
-	sp->free(vha, sp);
+	sp->free(sp);
 }
 
 void
-qla2x00_bsg_sp_free(void *data, void *ptr)
+qla2x00_bsg_sp_free(void *ptr)
 {
-	srb_t *sp = (srb_t *)ptr;
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	srb_t *sp = ptr;
+	struct qla_hw_data *ha = sp->vha->hw;
 	struct bsg_job *bsg_job = sp->u.bsg_job;
 	struct fc_bsg_request *bsg_request = bsg_job->request;
-
-	struct qla_hw_data *ha = vha->hw;
 	struct qla_mt_iocb_rqst_fx00 *piocb_rqst;
 
 	if (sp->type == SRB_FXIOCB_BCMD) {
@@ -62,7 +59,7 @@ qla2x00_bsg_sp_free(void *data, void *ptr)
 	    sp->type == SRB_FXIOCB_BCMD ||
 	    sp->type == SRB_ELS_CMD_HST)
 		kfree(sp->fcport);
-	qla2x00_rel_sp(vha, sp);
+	qla2x00_rel_sp(sp);
 }
 
 int
@@ -394,7 +391,7 @@ qla2x00_process_els(struct bsg_job *bsg_job)
 	if (rval != QLA_SUCCESS) {
 		ql_log(ql_log_warn, vha, 0x700e,
 		    "qla2x00_start_sp failed = %d\n", rval);
-		qla2x00_rel_sp(vha, sp);
+		qla2x00_rel_sp(sp);
 		rval = -EIO;
 		goto done_unmap_sg;
 	}
@@ -542,7 +539,7 @@ qla2x00_process_ct(struct bsg_job *bsg_job)
 	if (rval != QLA_SUCCESS) {
 		ql_log(ql_log_warn, vha, 0x7017,
 		    "qla2x00_start_sp failed=%d.\n", rval);
-		qla2x00_rel_sp(vha, sp);
+		qla2x00_rel_sp(sp);
 		rval = -EIO;
 		goto done_free_fcport;
 	}
@@ -2578,6 +2575,6 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
 
 done:
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-	sp->free(vha, sp);
+	sp->free(sp);
 	return 0;
 }
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 3881790e80da..ac37e91aee20 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -433,7 +433,7 @@ struct srb_iocb {
 typedef struct srb {
 	atomic_t ref_count;
 	struct fc_port *fcport;
-	void *vha;
+	struct scsi_qla_host *vha;
 	uint32_t handle;
 	uint16_t flags;
 	uint16_t type;
@@ -447,8 +447,8 @@ typedef struct srb {
 		struct bsg_job *bsg_job;
 		struct srb_cmd scmd;
 	} u;
-	void (*done)(void *, void *, int);
-	void (*free)(void *, void *);
+	void (*done)(void *, int);
+	void (*free)(void *);
 } srb_t;
 
 #define GET_CMD_SP(sp) (sp->u.scmd.cmd)
@@ -3224,6 +3224,7 @@ struct qla_qpair {
 	struct qla_hw_data *hw;
 	struct work_struct q_work;
 	struct list_head qp_list_elem; /* vha->qp_list */
+	struct scsi_qla_host *vha;
 };
 
 /* Place holder for FW buffer parameters */
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index e0914575aab3..b3d6441d1d90 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -186,9 +186,9 @@ extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32);
 
 extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32);
 extern void qla2x00_disable_board_on_pci_error(struct work_struct *);
-extern void qla2x00_sp_compl(void *, void *, int);
-extern void qla2xxx_qpair_sp_free_dma(void *, void *);
-extern void qla2xxx_qpair_sp_compl(void *, void *, int);
+extern void qla2x00_sp_compl(void *, int);
+extern void qla2xxx_qpair_sp_free_dma(void *);
+extern void qla2xxx_qpair_sp_compl(void *, int);
 extern int qla24xx_post_upd_fcport_work(struct scsi_qla_host *, fc_port_t *);
 void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *,
 	uint16_t *);
@@ -215,7 +215,7 @@ extern void qla2x00_do_dpc_all_vps(scsi_qla_host_t *);
 extern int qla24xx_vport_create_req_sanity_check(struct fc_vport *);
 extern scsi_qla_host_t * qla24xx_create_vhost(struct fc_vport *);
 
-extern void qla2x00_sp_free_dma(void *, void *);
+extern void qla2x00_sp_free_dma(void *);
 extern char *qla2x00_get_fw_version_str(struct scsi_qla_host *, char *);
 
 extern void qla2x00_mark_device_lost(scsi_qla_host_t *, fc_port_t *, int, int);
@@ -733,10 +733,10 @@ extern int qla82xx_restart_isp(scsi_qla_host_t *);
 
 /* IOCB related functions */
 extern int qla82xx_start_scsi(srb_t *);
-extern void qla2x00_sp_free(void *, void *);
+extern void qla2x00_sp_free(void *);
 extern void qla2x00_sp_timeout(unsigned long);
-extern void qla2x00_bsg_job_done(void *, void *, int);
-extern void qla2x00_bsg_sp_free(void *, void *);
+extern void qla2x00_bsg_job_done(void *, int);
+extern void qla2x00_bsg_sp_free(void *);
 extern void qla2x00_start_iocbs(struct scsi_qla_host *, struct req_que *);
 
 /* Interrupt related */
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index d1074fb0fff8..6d500fd06768 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -2822,10 +2822,10 @@ void qla24xx_handle_gidpn_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	}
 } /* gidpn_event */
 
-static void qla2x00_async_gidpn_sp_done(void *v, void *s, int res)
+static void qla2x00_async_gidpn_sp_done(void *s, int res)
 {
-	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
-	struct srb *sp = (struct srb *)s;
+	struct srb *sp = s;
+	struct scsi_qla_host *vha = sp->vha;
 	fc_port_t *fcport = sp->fcport;
 	u8 *id = fcport->ct_desc.ct_sns->p.rsp.rsp.gid_pn.port_id;
 	struct event_arg ea;
@@ -2847,7 +2847,7 @@ static void qla2x00_async_gidpn_sp_done(void *v, void *s, int res)
 
 	qla2x00_fcport_event_handler(vha, &ea);
 
-	sp->free(vha, sp);
+	sp->free(sp);
 }
 
 int qla24xx_async_gidpn(scsi_qla_host_t *vha, fc_port_t *fcport)
@@ -2905,7 +2905,7 @@ int qla24xx_async_gidpn(scsi_qla_host_t *vha, fc_port_t *fcport)
 	return rval;
 
 done_free_sp:
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
@@ -2941,11 +2941,11 @@ int qla24xx_post_gpsc_work(struct scsi_qla_host *vha, fc_port_t *fcport)
 	return qla2x00_post_work(vha, e);
 }
 
-static void qla24xx_async_gpsc_sp_done(void *v, void *s, int res)
+static void qla24xx_async_gpsc_sp_done(void *s, int res)
 {
-	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
+	struct srb *sp = s;
+	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct srb *sp = (struct srb *)s;
 	fc_port_t *fcport = sp->fcport;
 	struct ct_sns_rsp       *ct_rsp;
 	struct event_arg ea;
@@ -3011,7 +3011,7 @@ static void qla24xx_async_gpsc_sp_done(void *v, void *s, int res)
 	ea.fcport = fcport;
 	qla2x00_fcport_event_handler(vha, &ea);
 
-	sp->free(vha, sp);
+	sp->free(sp);
 }
 
 int qla24xx_async_gpsc(scsi_qla_host_t *vha, fc_port_t *fcport)
@@ -3066,7 +3066,7 @@ int qla24xx_async_gpsc(scsi_qla_host_t *vha, fc_port_t *fcport)
 	return rval;
 
 done_free_sp:
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
@@ -3104,7 +3104,7 @@ void qla24xx_async_gpnid_done(scsi_qla_host_t *vha, srb_t *sp)
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
 	}
 
-	sp->free(vha, sp);
+	sp->free(sp);
 }
 
 void qla24xx_handle_gpnid_event(scsi_qla_host_t *vha, struct event_arg *ea)
@@ -3138,10 +3138,10 @@ void qla24xx_handle_gpnid_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	}
 }
 
-static void qla2x00_async_gpnid_sp_done(void *v, void *s, int res)
+static void qla2x00_async_gpnid_sp_done(void *s, int res)
 {
-	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
-	struct srb *sp = (struct srb *)s;
+	struct srb *sp = s;
+	struct scsi_qla_host *vha = sp->vha;
 	struct ct_sns_req *ct_req =
 	    (struct ct_sns_req *)sp->u.iocb_cmd.u.ctarg.req;
 	struct ct_sns_rsp *ct_rsp =
@@ -3183,7 +3183,7 @@ static void qla2x00_async_gpnid_sp_done(void *v, void *s, int res)
 			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
 		}
 
-		sp->free(vha, sp);
+		sp->free(sp);
 		return;
 	}
 
@@ -3272,7 +3272,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id)
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
 	}
 
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	return rval;
 }
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 68430934fa8d..f65431480833 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -47,29 +47,27 @@ qla2x00_sp_timeout(unsigned long __data)
 {
 	srb_t *sp = (srb_t *)__data;
 	struct srb_iocb *iocb;
-	scsi_qla_host_t *vha = (scsi_qla_host_t *)sp->vha;
-	struct qla_hw_data *ha = vha->hw;
+	scsi_qla_host_t *vha = sp->vha;
 	struct req_que *req;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	req = ha->req_q_map[0];
+	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
+	req = vha->hw->req_q_map[0];
 	req->outstanding_cmds[sp->handle] = NULL;
 	iocb = &sp->u.iocb_cmd;
 	iocb->timeout(sp);
-	sp->free(vha, sp);
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+	sp->free(sp);
+	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 }
 
 void
-qla2x00_sp_free(void *data, void *ptr)
+qla2x00_sp_free(void *ptr)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	struct srb_iocb *iocb = &sp->u.iocb_cmd;
-	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
 
 	del_timer(&iocb->timer);
-	qla2x00_rel_sp(vha, sp);
+	qla2x00_rel_sp(sp);
 }
 
 /* Asynchronous Login/Logout Routines -------------------------------------- */
@@ -97,7 +95,7 @@ qla2x00_get_async_timeout(struct scsi_qla_host *vha)
 void
 qla2x00_async_iocb_timeout(void *data)
 {
-	srb_t *sp = (srb_t *)data;
+	srb_t *sp = data;
 	fc_port_t *fcport = sp->fcport;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	struct event_arg ea;
@@ -130,22 +128,21 @@ qla2x00_async_iocb_timeout(void *data)
 	case SRB_NACK_PLOGI:
 	case SRB_NACK_PRLI:
 	case SRB_NACK_LOGO:
-		sp->done(sp->vha, sp, QLA_FUNCTION_TIMEOUT);
+		sp->done(sp, QLA_FUNCTION_TIMEOUT);
 		break;
 	}
 }
 
 static void
-qla2x00_async_login_sp_done(void *data, void *ptr, int res)
+qla2x00_async_login_sp_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
+	struct scsi_qla_host *vha = sp->vha;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
-	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
 	struct event_arg ea;
 
 	ql_dbg(ql_dbg_disc, vha, 0xffff,
-		"%s %8phC res %d \n",
-		   __func__, sp->fcport->port_name, res);
+	    "%s %8phC res %d \n", __func__, sp->fcport->port_name, res);
 
 	sp->fcport->flags &= ~FCF_ASYNC_SENT;
 	if (!test_bit(UNLOADING, &vha->dpc_flags)) {
@@ -160,7 +157,7 @@ qla2x00_async_login_sp_done(void *data, void *ptr, int res)
 		qla2x00_fcport_event_handler(vha, &ea);
 	}
 
-	sp->free(sp->fcport->vha, sp);
+	sp->free(sp);
 }
 
 int
@@ -212,24 +209,23 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 	return rval;
 
 done_free_sp:
-	sp->free(fcport->vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
 }
 
 static void
-qla2x00_async_logout_sp_done(void *data, void *ptr, int res)
+qla2x00_async_logout_sp_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
-	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
 
 	sp->fcport->flags &= ~FCF_ASYNC_SENT;
-	if (!test_bit(UNLOADING, &vha->dpc_flags))
-		qla2x00_post_async_logout_done_work(sp->fcport->vha, sp->fcport,
+	if (!test_bit(UNLOADING, &sp->vha->dpc_flags))
+		qla2x00_post_async_logout_done_work(sp->vha, sp->fcport,
 		    lio->u.logio.data);
-	sp->free(sp->fcport->vha, sp);
+	sp->free(sp);
 }
 
 int
@@ -264,23 +260,23 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport)
 	return rval;
 
 done_free_sp:
-	sp->free(fcport->vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
 }
 
 static void
-qla2x00_async_adisc_sp_done(void *data, void *ptr, int res)
+qla2x00_async_adisc_sp_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
+	struct scsi_qla_host *vha = sp->vha;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
-	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
 
 	if (!test_bit(UNLOADING, &vha->dpc_flags))
-		qla2x00_post_async_adisc_done_work(sp->fcport->vha, sp->fcport,
+		qla2x00_post_async_adisc_done_work(sp->vha, sp->fcport,
 		    lio->u.logio.data);
-	sp->free(sp->fcport->vha, sp);
+	sp->free(sp);
 }
 
 int
@@ -317,7 +313,7 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport,
 	return rval;
 
 done_free_sp:
-	sp->free(fcport->vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
@@ -479,10 +475,10 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 } /* gnl_event */
 
 static void
-qla24xx_async_gnl_sp_done(void *v, void *s, int res)
+qla24xx_async_gnl_sp_done(void *s, int res)
 {
-	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
-	struct srb *sp = (struct srb *)s;
+	struct srb *sp = s;
+	struct scsi_qla_host *vha = sp->vha;
 	unsigned long flags;
 	struct fc_port *fcport = NULL, *tf;
 	u16 i, n = 0, loop_id;
@@ -541,7 +537,7 @@ qla24xx_async_gnl_sp_done(void *v, void *s, int res)
 
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
-	sp->free(vha, sp);
+	sp->free(sp);
 }
 
 int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
@@ -609,7 +605,7 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
 	return rval;
 
 done_free_sp:
-	sp->free(fcport->vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
@@ -628,10 +624,10 @@ int qla24xx_post_gnl_work(struct scsi_qla_host *vha, fc_port_t *fcport)
 }
 
 static
-void qla24xx_async_gpdb_sp_done(void *v, void *s, int res)
+void qla24xx_async_gpdb_sp_done(void *s, int res)
 {
-	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
-	struct srb *sp = (struct srb *)s;
+	struct srb *sp = s;
+	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
 	uint64_t zero = 0;
 	struct port_database_24xx *pd;
@@ -708,7 +704,7 @@ void qla24xx_async_gpdb_sp_done(void *v, void *s, int res)
 	dma_pool_free(ha->s_dma_pool, sp->u.iocb_cmd.u.mbx.in,
 		sp->u.iocb_cmd.u.mbx.in_dma);
 
-	sp->free(vha, sp);
+	sp->free(sp);
 }
 
 static int qla24xx_post_gpdb_work(struct scsi_qla_host *vha, fc_port_t *fcport,
@@ -790,7 +786,7 @@ int qla24xx_async_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport, u8 opt)
 	if (pd)
 		dma_pool_free(ha->s_dma_pool, pd, pd_dma);
 
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	qla24xx_post_gpdb_work(vha, fcport, opt);
@@ -1168,7 +1164,7 @@ void qla2x00_fcport_event_handler(scsi_qla_host_t *vha, struct event_arg *ea)
 static void
 qla2x00_tmf_iocb_timeout(void *data)
 {
-	srb_t *sp = (srb_t *)data;
+	srb_t *sp = data;
 	struct srb_iocb *tmf = &sp->u.iocb_cmd;
 
 	tmf->u.tmf.comp_status = CS_TIMEOUT;
@@ -1176,10 +1172,11 @@ qla2x00_tmf_iocb_timeout(void *data)
 }
 
 static void
-qla2x00_tmf_sp_done(void *data, void *ptr, int res)
+qla2x00_tmf_sp_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	struct srb_iocb *tmf = &sp->u.iocb_cmd;
+
 	complete(&tmf->u.tmf.comp);
 }
 
@@ -1237,7 +1234,7 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
 	}
 
 done_free_sp:
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	return rval;
 }
@@ -1245,7 +1242,7 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun,
 static void
 qla24xx_abort_iocb_timeout(void *data)
 {
-	srb_t *sp = (srb_t *)data;
+	srb_t *sp = data;
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
 	abt->u.abt.comp_status = CS_TIMEOUT;
@@ -1253,9 +1250,9 @@ qla24xx_abort_iocb_timeout(void *data)
 }
 
 static void
-qla24xx_abort_sp_done(void *data, void *ptr, int res)
+qla24xx_abort_sp_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
 	complete(&abt->u.abt.comp);
@@ -1264,7 +1261,7 @@ qla24xx_abort_sp_done(void *data, void *ptr, int res)
 static int
 qla24xx_async_abort_cmd(srb_t *cmd_sp)
 {
-	scsi_qla_host_t *vha = cmd_sp->fcport->vha;
+	scsi_qla_host_t *vha = cmd_sp->vha;
 	fc_port_t *fcport = cmd_sp->fcport;
 	struct srb_iocb *abt_iocb;
 	srb_t *sp;
@@ -1297,7 +1294,7 @@ qla24xx_async_abort_cmd(srb_t *cmd_sp)
 	    QLA_SUCCESS : QLA_FUNCTION_FAILED;
 
 done_free_sp:
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	return rval;
 }
@@ -7564,6 +7561,7 @@ struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, int v
 		memset(qpair, 0, sizeof(struct qla_qpair));
 
 		qpair->hw = vha->hw;
+		qpair->vha = vha;
 
 		/* Assign available que pair id */
 		mutex_lock(&ha->mq_lock);
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 647828b9e622..66df6cec59da 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -232,6 +232,7 @@ qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag)
 	memset(sp, 0, sizeof(*sp));
 	sp->fcport = fcport;
 	sp->iocbs = 1;
+	sp->vha = qpair->vha;
 done:
 	if (!sp)
 		QLA_QPAIR_MARK_NOT_BUSY(qpair);
@@ -249,14 +250,13 @@ static inline srb_t *
 qla2x00_get_sp(scsi_qla_host_t *vha, fc_port_t *fcport, gfp_t flag)
 {
 	srb_t *sp = NULL;
-	struct qla_hw_data *ha = vha->hw;
 	uint8_t bail;
 
 	QLA_VHA_MARK_BUSY(vha, bail);
 	if (unlikely(bail))
 		return NULL;
 
-	sp = mempool_alloc(ha->srb_mempool, flag);
+	sp = mempool_alloc(vha->hw->srb_mempool, flag);
 	if (!sp)
 		goto done;
 
@@ -271,10 +271,10 @@ qla2x00_get_sp(scsi_qla_host_t *vha, fc_port_t *fcport, gfp_t flag)
 }
 
 static inline void
-qla2x00_rel_sp(scsi_qla_host_t *vha, srb_t *sp)
+qla2x00_rel_sp(srb_t *sp)
 {
-	mempool_free(sp, vha->hw->srb_mempool);
-	QLA_VHA_MARK_NOT_BUSY(vha);
+	QLA_VHA_MARK_NOT_BUSY(sp->vha);
+	mempool_free(sp, sp->vha->hw->srb_mempool);
 }
 
 static inline void
@@ -286,8 +286,7 @@ qla2x00_init_timer(srb_t *sp, unsigned long tmo)
 	sp->u.iocb_cmd.timer.function = qla2x00_sp_timeout;
 	add_timer(&sp->u.iocb_cmd.timer);
 	sp->free = qla2x00_sp_free;
-	if ((IS_QLAFX00(((scsi_qla_host_t *)sp->vha)->hw)) &&
-	    (sp->type == SRB_FXIOCB_DCMD))
+	if (IS_QLAFX00(sp->vha->hw) && (sp->type == SRB_FXIOCB_DCMD))
 		init_completion(&sp->u.iocb_cmd.u.fxiocb.fxiocb_comp);
 	if (sp->type == SRB_ELS_DCMD)
 		init_completion(&sp->u.iocb_cmd.u.els_logo.comp);
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 33d3d90c089b..535079280288 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -23,7 +23,7 @@ qla2x00_get_cmd_direction(srb_t *sp)
 {
 	uint16_t cflags;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 
 	cflags = 0;
 
@@ -210,7 +210,7 @@ void qla2x00_build_scsi_iocbs_32(srb_t *sp, cmd_entry_t *cmd_pkt,
 		return;
 	}
 
-	vha = sp->fcport->vha;
+	vha = sp->vha;
 	cmd_pkt->control_flags |= cpu_to_le16(qla2x00_get_cmd_direction(sp));
 
 	/* Three DSDs are available in the Command Type 2 IOCB */
@@ -267,7 +267,7 @@ void qla2x00_build_scsi_iocbs_64(srb_t *sp, cmd_entry_t *cmd_pkt,
 		return;
 	}
 
-	vha = sp->fcport->vha;
+	vha = sp->vha;
 	cmd_pkt->control_flags |= cpu_to_le16(qla2x00_get_cmd_direction(sp));
 
 	/* Two DSDs are available in the Command Type 3 IOCB */
@@ -324,7 +324,7 @@ qla2x00_start_scsi(srb_t *sp)
 	struct rsp_que *rsp;
 
 	/* Setup device pointers. */
-	vha = sp->fcport->vha;
+	vha = sp->vha;
 	ha = vha->hw;
 	reg = &ha->iobase->isp;
 	cmd = GET_CMD_SP(sp);
@@ -601,7 +601,7 @@ qla24xx_build_scsi_type_6_iocbs(srb_t *sp, struct cmd_type_6 *cmd_pkt,
 		return 0;
 	}
 
-	vha = sp->fcport->vha;
+	vha = sp->vha;
 	ha = vha->hw;
 
 	/* Set transfer direction */
@@ -716,7 +716,7 @@ qla24xx_build_scsi_iocbs(srb_t *sp, struct cmd_type_7 *cmd_pkt,
 		return;
 	}
 
-	vha = sp->fcport->vha;
+	vha = sp->vha;
 
 	/* Set transfer direction */
 	if (cmd->sc_data_direction == DMA_TO_DEVICE) {
@@ -1108,7 +1108,7 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
 	if (sp) {
 		cmd = GET_CMD_SP(sp);
 		sgl = scsi_prot_sglist(cmd);
-		vha = sp->fcport->vha;
+		vha = sp->vha;
 	} else if (tc) {
 		vha = tc->vha;
 		sgl = tc->prot_sg;
@@ -1215,7 +1215,7 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
 	/* Update entry type to indicate Command Type CRC_2 IOCB */
 	*((uint32_t *)(&cmd_pkt->entry_type)) = cpu_to_le32(COMMAND_TYPE_CRC_2);
 
-	vha = sp->fcport->vha;
+	vha = sp->vha;
 	ha = vha->hw;
 
 	/* No data transfer */
@@ -1225,7 +1225,7 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
 		return QLA_SUCCESS;
 	}
 
-	cmd_pkt->vp_index = sp->fcport->vha->vp_idx;
+	cmd_pkt->vp_index = sp->vha->vp_idx;
 
 	/* Set transfer direction */
 	if (cmd->sc_data_direction == DMA_TO_DEVICE) {
@@ -1415,7 +1415,7 @@ qla24xx_start_scsi(srb_t *sp)
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
 
 	/* Setup device pointers. */
@@ -1492,7 +1492,7 @@ qla24xx_start_scsi(srb_t *sp)
 	cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
 	cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
 	cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
-	cmd_pkt->vp_index = sp->fcport->vha->vp_idx;
+	cmd_pkt->vp_index = sp->vha->vp_idx;
 
 	int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
 	host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
@@ -1564,7 +1564,7 @@ qla24xx_dif_start_scsi(srb_t *sp)
 	struct req_que		*req = NULL;
 	struct rsp_que		*rsp = NULL;
 	struct scsi_cmnd	*cmd = GET_CMD_SP(sp);
-	struct scsi_qla_host	*vha = sp->fcport->vha;
+	struct scsi_qla_host	*vha = sp->vha;
 	struct qla_hw_data	*ha = vha->hw;
 	struct cmd_type_crc_2	*cmd_pkt;
 	uint32_t		status = 0;
@@ -2214,13 +2214,13 @@ qla24xx_login_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
 	logio->port_id[2] = sp->fcport->d_id.b.domain;
-	logio->vp_index = sp->fcport->vha->vp_idx;
+	logio->vp_index = sp->vha->vp_idx;
 }
 
 static void
 qla2x00_login_iocb(srb_t *sp, struct mbx_entry *mbx)
 {
-	struct qla_hw_data *ha = sp->fcport->vha->hw;
+	struct qla_hw_data *ha = sp->vha->hw;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	uint16_t opts;
 
@@ -2238,7 +2238,7 @@ qla2x00_login_iocb(srb_t *sp, struct mbx_entry *mbx)
 	mbx->mb2 = cpu_to_le16(sp->fcport->d_id.b.domain);
 	mbx->mb3 = cpu_to_le16(sp->fcport->d_id.b.area << 8 |
 	    sp->fcport->d_id.b.al_pa);
-	mbx->mb9 = cpu_to_le16(sp->fcport->vha->vp_idx);
+	mbx->mb9 = cpu_to_le16(sp->vha->vp_idx);
 }
 
 static void
@@ -2254,13 +2254,13 @@ qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
 	logio->port_id[2] = sp->fcport->d_id.b.domain;
-	logio->vp_index = sp->fcport->vha->vp_idx;
+	logio->vp_index = sp->vha->vp_idx;
 }
 
 static void
 qla2x00_logout_iocb(srb_t *sp, struct mbx_entry *mbx)
 {
-	struct qla_hw_data *ha = sp->fcport->vha->hw;
+	struct qla_hw_data *ha = sp->vha->hw;
 
 	mbx->entry_type = MBX_IOCB_TYPE;
 	SET_TARGET_ID(ha, mbx->loop_id, sp->fcport->loop_id);
@@ -2271,7 +2271,7 @@ qla2x00_logout_iocb(srb_t *sp, struct mbx_entry *mbx)
 	mbx->mb2 = cpu_to_le16(sp->fcport->d_id.b.domain);
 	mbx->mb3 = cpu_to_le16(sp->fcport->d_id.b.area << 8 |
 	    sp->fcport->d_id.b.al_pa);
-	mbx->mb9 = cpu_to_le16(sp->fcport->vha->vp_idx);
+	mbx->mb9 = cpu_to_le16(sp->vha->vp_idx);
 	/* Implicit: mbx->mbx10 = 0. */
 }
 
@@ -2281,13 +2281,13 @@ qla24xx_adisc_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
 	logio->control_flags = cpu_to_le16(LCF_COMMAND_ADISC);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
-	logio->vp_index = sp->fcport->vha->vp_idx;
+	logio->vp_index = sp->vha->vp_idx;
 }
 
 static void
 qla2x00_adisc_iocb(srb_t *sp, struct mbx_entry *mbx)
 {
-	struct qla_hw_data *ha = sp->fcport->vha->hw;
+	struct qla_hw_data *ha = sp->vha->hw;
 
 	mbx->entry_type = MBX_IOCB_TYPE;
 	SET_TARGET_ID(ha, mbx->loop_id, sp->fcport->loop_id);
@@ -2302,7 +2302,7 @@ qla2x00_adisc_iocb(srb_t *sp, struct mbx_entry *mbx)
 	mbx->mb3 = cpu_to_le16(LSW(ha->async_pd_dma));
 	mbx->mb6 = cpu_to_le16(MSW(MSD(ha->async_pd_dma)));
 	mbx->mb7 = cpu_to_le16(LSW(MSD(ha->async_pd_dma)));
-	mbx->mb9 = cpu_to_le16(sp->fcport->vha->vp_idx);
+	mbx->mb9 = cpu_to_le16(sp->vha->vp_idx);
 }
 
 static void
@@ -2338,32 +2338,30 @@ qla24xx_tm_iocb(srb_t *sp, struct tsk_mgmt_entry *tsk)
 }
 
 static void
-qla2x00_els_dcmd_sp_free(void *ptr, void *data)
+qla2x00_els_dcmd_sp_free(void *data)
 {
-	struct scsi_qla_host *vha = (scsi_qla_host_t *)ptr;
-	struct qla_hw_data *ha = vha->hw;
-	srb_t *sp = (srb_t *)data;
+	srb_t *sp = data;
 	struct srb_iocb *elsio = &sp->u.iocb_cmd;
 
 	kfree(sp->fcport);
 
 	if (elsio->u.els_logo.els_logo_pyld)
-		dma_free_coherent(&ha->pdev->dev, DMA_POOL_SIZE,
+		dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
 		    elsio->u.els_logo.els_logo_pyld,
 		    elsio->u.els_logo.els_logo_pyld_dma);
 
 	del_timer(&elsio->timer);
-	qla2x00_rel_sp(vha, sp);
+	qla2x00_rel_sp(sp);
 }
 
 static void
 qla2x00_els_dcmd_iocb_timeout(void *data)
 {
-	srb_t *sp = (srb_t *)data;
-	struct srb_iocb *lio = &sp->u.iocb_cmd;
+	srb_t *sp = data;
 	fc_port_t *fcport = sp->fcport;
-	struct scsi_qla_host *vha = fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
+	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	unsigned long flags = 0;
 
 	ql_dbg(ql_dbg_io, vha, 0x3069,
@@ -2386,12 +2384,12 @@ qla2x00_els_dcmd_iocb_timeout(void *data)
 }
 
 static void
-qla2x00_els_dcmd_sp_done(void *data, void *ptr, int res)
+qla2x00_els_dcmd_sp_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	fc_port_t *fcport = sp->fcport;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
-	struct scsi_qla_host *vha = fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 
 	ql_dbg(ql_dbg_io, vha, 0x3072,
 	    "%s hdl=%x, portid=%02x%02x%02x done\n",
@@ -2449,7 +2447,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 			    GFP_KERNEL);
 
 	if (!elsio->u.els_logo.els_logo_pyld) {
-		sp->free(vha, sp);
+		sp->free(sp);
 		return QLA_FUNCTION_FAILED;
 	}
 
@@ -2468,7 +2466,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
-		sp->free(vha, sp);
+		sp->free(sp);
 		return QLA_FUNCTION_FAILED;
 	}
 
@@ -2479,14 +2477,14 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 
 	wait_for_completion(&elsio->u.els_logo.comp);
 
-	sp->free(vha, sp);
+	sp->free(sp);
 	return rval;
 }
 
 static void
 qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 {
-	scsi_qla_host_t *vha = sp->fcport->vha;
+	scsi_qla_host_t *vha = sp->vha;
 	struct srb_iocb *elsio = &sp->u.iocb_cmd;
 
 	els_iocb->entry_type = ELS_IOCB_TYPE;
@@ -2518,7 +2516,7 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 	els_iocb->rx_address[1] = 0;
 	els_iocb->rx_len = 0;
 
-	sp->fcport->vha->qla_stats.control_requests++;
+	sp->vha->qla_stats.control_requests++;
 }
 
 static void
@@ -2534,7 +2532,7 @@ qla24xx_els_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
         els_iocb->handle = sp->handle;
         els_iocb->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	els_iocb->tx_dsd_count = cpu_to_le16(bsg_job->request_payload.sg_cnt);
-	els_iocb->vp_index = sp->fcport->vha->vp_idx;
+	els_iocb->vp_index = sp->vha->vp_idx;
         els_iocb->sof_type = EST_SOFI3;
 	els_iocb->rx_dsd_count = cpu_to_le16(bsg_job->reply_payload.sg_cnt);
 
@@ -2565,7 +2563,7 @@ qla24xx_els_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
         els_iocb->rx_len = cpu_to_le32(sg_dma_len
             (bsg_job->reply_payload.sg_list));
 
-	sp->fcport->vha->qla_stats.control_requests++;
+	sp->vha->qla_stats.control_requests++;
 }
 
 static void
@@ -2576,7 +2574,7 @@ qla2x00_ct_iocb(srb_t *sp, ms_iocb_entry_t *ct_iocb)
 	struct scatterlist *sg;
 	int index;
 	uint16_t tot_dsds;
-	scsi_qla_host_t *vha = sp->fcport->vha;
+	scsi_qla_host_t *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct bsg_job *bsg_job = sp->u.bsg_job;
 	int loop_iterartion = 0;
@@ -2642,7 +2640,7 @@ qla2x00_ct_iocb(srb_t *sp, ms_iocb_entry_t *ct_iocb)
 	}
 	ct_iocb->entry_count = entry_count;
 
-	sp->fcport->vha->qla_stats.control_requests++;
+	sp->vha->qla_stats.control_requests++;
 }
 
 static void
@@ -2653,7 +2651,7 @@ qla24xx_ct_iocb(srb_t *sp, struct ct_entry_24xx *ct_iocb)
 	struct scatterlist *sg;
 	int index;
 	uint16_t tot_dsds;
-        scsi_qla_host_t *vha = sp->fcport->vha;
+	scsi_qla_host_t *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct bsg_job *bsg_job = sp->u.bsg_job;
 	int loop_iterartion = 0;
@@ -2665,7 +2663,7 @@ qla24xx_ct_iocb(srb_t *sp, struct ct_entry_24xx *ct_iocb)
         ct_iocb->handle = sp->handle;
 
 	ct_iocb->nport_handle = cpu_to_le16(sp->fcport->loop_id);
-	ct_iocb->vp_index = sp->fcport->vha->vp_idx;
+	ct_iocb->vp_index = sp->vha->vp_idx;
 	ct_iocb->comp_status = cpu_to_le16(0);
 
 	ct_iocb->cmd_dsd_count =
@@ -2739,7 +2737,7 @@ qla82xx_start_scsi(srb_t *sp)
 	uint32_t *fcp_dl;
 	uint8_t additional_cdb_len;
 	struct ct6_dsd *ctx;
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
@@ -2901,7 +2899,7 @@ qla82xx_start_scsi(srb_t *sp)
 		cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
 		cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
 		cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
-		cmd_pkt->vp_index = sp->fcport->vha->vp_idx;
+		cmd_pkt->vp_index = sp->vha->vp_idx;
 
 		/* Build IOCB segments */
 		if (qla24xx_build_scsi_type_6_iocbs(sp, cmd_pkt, tot_dsds))
@@ -2974,7 +2972,7 @@ qla82xx_start_scsi(srb_t *sp)
 		cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
 		cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
 		cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
-		cmd_pkt->vp_index = sp->fcport->vha->vp_idx;
+		cmd_pkt->vp_index = sp->vha->vp_idx;
 
 		int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
 		host_to_fcp_swap((uint8_t *)&cmd_pkt->lun,
@@ -3060,7 +3058,7 @@ static void
 qla24xx_abort_iocb(srb_t *sp, struct abort_entry_24xx *abt_iocb)
 {
 	struct srb_iocb *aio = &sp->u.iocb_cmd;
-	scsi_qla_host_t *vha = sp->fcport->vha;
+	scsi_qla_host_t *vha = sp->vha;
 	struct req_que *req = vha->req;
 
 	memset(abt_iocb, 0, sizeof(struct abort_entry_24xx));
@@ -3132,7 +3130,7 @@ int
 qla2x00_start_sp(srb_t *sp)
 {
 	int rval;
-	scsi_qla_host_t *vha = (scsi_qla_host_t *)sp->vha;
+	scsi_qla_host_t *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
 	void *pkt;
 	unsigned long flags;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index d9577db7ddbb..914cc5a66b34 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1241,7 +1241,7 @@ qla2x00_process_completed_request(struct scsi_qla_host *vha,
 		req->outstanding_cmds[index] = NULL;
 
 		/* Save ISP completion status */
-		sp->done(vha, sp, DID_OK << 16);
+		sp->done(sp, DID_OK << 16);
 	} else {
 		ql_log(ql_log_warn, vha, 0x3016, "Invalid SCSI SRB.\n");
 
@@ -1373,7 +1373,7 @@ qla2x00_mbx_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 	    le16_to_cpu(mbx->mb7));
 
 logio_done:
-	sp->done(vha, sp, 0);
+	sp->done(sp, 0);
 }
 
 static void
@@ -1398,7 +1398,7 @@ qla24xx_mbx_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 
 	res = (si->u.mbx.in_mb[0] & MBS_MASK);
 
-	sp->done(vha, sp, res);
+	sp->done(sp, res);
 }
 
 static void
@@ -1416,7 +1416,7 @@ qla24xxx_nack_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 	if (pkt->u.isp2x.status != cpu_to_le16(NOTIFY_ACK_SUCCESS))
 		res = QLA_FUNCTION_FAILED;
 
-	sp->done(vha, sp, res);
+	sp->done(sp, res);
 }
 
 static void
@@ -1488,7 +1488,7 @@ qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	     break;
 	}
 
-	sp->done(vha, sp, res);
+	sp->done(sp, res);
 }
 
 static void
@@ -1524,7 +1524,7 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 		type = "Driver ELS logo";
 		ql_dbg(ql_dbg_user, vha, 0x5047,
 		    "Completing %s: (%p) type=%d.\n", type, sp, sp->type);
-		sp->done(vha, sp, 0);
+		sp->done(sp, 0);
 		return;
 	case SRB_CT_PTHRU_CMD:
 		/* borrowing sts_entry_24xx.comp_status.
@@ -1533,7 +1533,7 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 		res = qla2x00_chk_ms_status(vha, (ms_iocb_entry_t *)pkt,
 			(struct ct_sns_rsp *)sp->u.iocb_cmd.u.ctarg.rsp,
 			sp->name);
-		sp->done(vha, sp, res);
+		sp->done(sp, res);
 		return;
 	default:
 		ql_dbg(ql_dbg_user, vha, 0x503e,
@@ -1589,7 +1589,7 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 		bsg_job->reply_len = 0;
 	}
 
-	sp->done(vha, sp, res);
+	sp->done(sp, res);
 }
 
 static void
@@ -1701,7 +1701,7 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
 	    le32_to_cpu(logio->io_parameter[1]));
 
 logio_done:
-	sp->done(vha, sp, 0);
+	sp->done(sp, 0);
 }
 
 static void
@@ -1751,7 +1751,7 @@ qla24xx_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, void *tsk)
 		ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x5055,
 		    (uint8_t *)sts, sizeof(*sts));
 
-	sp->done(vha, sp, 0);
+	sp->done(sp, 0);
 }
 
 /**
@@ -1839,7 +1839,7 @@ static inline void
 qla2x00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len,
 		     uint32_t sense_len, struct rsp_que *rsp, int res)
 {
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 	struct scsi_cmnd *cp = GET_CMD_SP(sp);
 	uint32_t track_sense_len;
 
@@ -1867,7 +1867,7 @@ qla2x00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len,
 	if (sense_len) {
 		ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x301c,
 		    "Check condition Sense data, nexus%ld:%d:%llu cmd=%p.\n",
-		    sp->fcport->vha->host_no, cp->device->id, cp->device->lun,
+		    sp->vha->host_no, cp->device->id, cp->device->lun,
 		    cp);
 		ql_dump_buffer(ql_dbg_io + ql_dbg_buffer, vha, 0x302b,
 		    cp->sense_buffer, sense_len);
@@ -1889,7 +1889,7 @@ struct scsi_dif_tuple {
 static inline int
 qla2x00_handle_dif_error(srb_t *sp, struct sts_entry_24xx *sts24)
 {
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 	uint8_t		*ap = &sts24->data[12];
 	uint8_t		*ep = &sts24->data[20];
@@ -2154,7 +2154,7 @@ qla25xx_process_bidir_status_iocb(scsi_qla_host_t *vha, void *pkt,
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
 	/* Always return DID_OK, bsg will send the vendor specific response
 	 * in this case only */
-	sp->done(vha, sp, (DID_OK << 6));
+	sp->done(sp, DID_OK << 6);
 
 }
 
@@ -2527,7 +2527,7 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 		    resid_len, fw_resid_len, sp, cp);
 
 	if (rsp->status_srb == NULL)
-		sp->done(vha, sp, res);
+		sp->done(sp, res);
 }
 
 /**
@@ -2584,7 +2584,7 @@ qla2x00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt)
 	/* Place command on done queue. */
 	if (sense_len == 0) {
 		rsp->status_srb = NULL;
-		sp->done(vha, sp, cp->result);
+		sp->done(sp, cp->result);
 	}
 }
 
@@ -2620,7 +2620,7 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt)
 
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (sp) {
-		sp->done(vha, sp, res);
+		sp->done(sp, res);
 		return;
 	}
 fatal:
@@ -2678,7 +2678,7 @@ qla24xx_abort_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 
 	abt = &sp->u.iocb_cmd;
 	abt->u.abt.comp_status = le32_to_cpu(pkt->nport_handle);
-	sp->done(vha, sp, 0);
+	sp->done(sp, 0);
 }
 
 /**
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index d38bc6452abd..945b6320e7d7 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -1789,16 +1789,16 @@ qlafx00_update_host_attr(scsi_qla_host_t *vha, struct port_info_data *pinfo)
 static void
 qla2x00_fxdisc_iocb_timeout(void *data)
 {
-	srb_t *sp = (srb_t *)data;
+	srb_t *sp = data;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 
 	complete(&lio->u.fxiocb.fxiocb_comp);
 }
 
 static void
-qla2x00_fxdisc_sp_done(void *data, void *ptr, int res)
+qla2x00_fxdisc_sp_done(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 
 	complete(&lio->u.fxiocb.fxiocb_comp);
@@ -1999,7 +1999,7 @@ qlafx00_fx_disc(scsi_qla_host_t *vha, fc_port_t *fcport, uint16_t fx_type)
 		dma_free_coherent(&ha->pdev->dev, fdisc->u.fxiocb.req_len,
 		    fdisc->u.fxiocb.req_addr, fdisc->u.fxiocb.req_dma_handle);
 done_free_sp:
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	return rval;
 }
@@ -2127,7 +2127,7 @@ static inline void
 qlafx00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len,
 		     uint32_t sense_len, struct rsp_que *rsp, int res)
 {
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 	struct scsi_cmnd *cp = GET_CMD_SP(sp);
 	uint32_t track_sense_len;
 
@@ -2162,7 +2162,7 @@ qlafx00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len,
 	if (sense_len) {
 		ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3039,
 		    "Check condition Sense data, nexus%ld:%d:%llu cmd=%p.\n",
-		    sp->fcport->vha->host_no, cp->device->id, cp->device->lun,
+		    sp->vha->host_no, cp->device->id, cp->device->lun,
 		    cp);
 		ql_dump_buffer(ql_dbg_io + ql_dbg_buffer, vha, 0x3049,
 		    cp->sense_buffer, sense_len);
@@ -2181,7 +2181,7 @@ qlafx00_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 	    (sstatus & cpu_to_le16((uint16_t)SS_RESPONSE_INFO_LEN_VALID)))
 		cpstatus = cpu_to_le16((uint16_t)CS_INCOMPLETE);
 	tmf->u.tmf.comp_status = cpstatus;
-	sp->done(vha, sp, 0);
+	sp->done(sp, 0);
 }
 
 static void
@@ -2198,7 +2198,7 @@ qlafx00_abort_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 
 	abt = &sp->u.iocb_cmd;
 	abt->u.abt.comp_status = pkt->tgt_id_sts;
-	sp->done(vha, sp, 0);
+	sp->done(sp, 0);
 }
 
 static void
@@ -2264,7 +2264,7 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req,
 		bsg_reply->reply_payload_rcv_len =
 		    bsg_job->reply_payload.payload_len;
 	}
-	sp->done(vha, sp, res);
+	sp->done(sp, res);
 }
 
 /**
@@ -2537,7 +2537,7 @@ qlafx00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 		    par_sense_len, rsp_info_len);
 
 	if (rsp->status_srb == NULL)
-		sp->done(vha, sp, res);
+		sp->done(sp, res);
 }
 
 /**
@@ -2614,7 +2614,7 @@ qlafx00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt)
 	/* Place command on done queue. */
 	if (sense_len == 0) {
 		rsp->status_srb = NULL;
-		sp->done(vha, sp, cp->result);
+		sp->done(sp, cp->result);
 	}
 }
 
@@ -2695,7 +2695,7 @@ qlafx00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp,
 
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (sp) {
-		sp->done(vha, sp, res);
+		sp->done(sp, res);
 		return;
 	}
 
@@ -2997,7 +2997,7 @@ qlafx00_build_scsi_iocbs(srb_t *sp, struct cmd_type_7_fx00 *cmd_pkt,
 	cont_a64_entry_t lcont_pkt;
 	cont_a64_entry_t *cont_pkt;
 
-	vha = sp->fcport->vha;
+	vha = sp->vha;
 	req = vha->req;
 
 	cmd = GET_CMD_SP(sp);
@@ -3081,7 +3081,7 @@ qlafx00_start_scsi(srb_t *sp)
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
-	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct cmd_type_7_fx00 *cmd_pkt;
 	struct cmd_type_7_fx00 lcmd_pkt;
@@ -3205,7 +3205,7 @@ void
 qlafx00_tm_iocb(srb_t *sp, struct tsk_mgmt_entry_fx00 *ptm_iocb)
 {
 	struct srb_iocb *fxio = &sp->u.iocb_cmd;
-	scsi_qla_host_t *vha = sp->fcport->vha;
+	scsi_qla_host_t *vha = sp->vha;
 	struct req_que *req = vha->req;
 	struct tsk_mgmt_entry_fx00 tm_iocb;
 	struct scsi_lun llun;
@@ -3232,7 +3232,7 @@ void
 qlafx00_abort_iocb(srb_t *sp, struct abort_iocb_entry_fx00 *pabt_iocb)
 {
 	struct srb_iocb *fxio = &sp->u.iocb_cmd;
-	scsi_qla_host_t *vha = sp->fcport->vha;
+	scsi_qla_host_t *vha = sp->vha;
 	struct req_que *req = vha->req;
 	struct abort_iocb_entry_fx00 abt_iocb;
 
@@ -3346,8 +3346,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 					    REQUEST_ENTRY_SIZE);
 					cont_pkt =
 					    qlafx00_prep_cont_type1_iocb(
-						sp->fcport->vha->req,
-						&lcont_pkt);
+						sp->vha->req, &lcont_pkt);
 					cur_dsd = (__le32 *)
 					    lcont_pkt.dseg_0_address;
 					avail_dsds = 5;
@@ -3368,7 +3367,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 					    &lcont_pkt, REQUEST_ENTRY_SIZE);
 					ql_dump_buffer(
 					    ql_dbg_user + ql_dbg_verbose,
-					    sp->fcport->vha, 0x3042,
+					    sp->vha, 0x3042,
 					    (uint8_t *)&lcont_pkt,
 					     REQUEST_ENTRY_SIZE);
 				}
@@ -3377,7 +3376,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 				memcpy_toio((void __iomem *)cont_pkt,
 				    &lcont_pkt, REQUEST_ENTRY_SIZE);
 				ql_dump_buffer(ql_dbg_user + ql_dbg_verbose,
-				    sp->fcport->vha, 0x3043,
+				    sp->vha, 0x3043,
 				    (uint8_t *)&lcont_pkt, REQUEST_ENTRY_SIZE);
 			}
 		}
@@ -3409,8 +3408,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 					    REQUEST_ENTRY_SIZE);
 					cont_pkt =
 					    qlafx00_prep_cont_type1_iocb(
-						sp->fcport->vha->req,
-						&lcont_pkt);
+						sp->vha->req, &lcont_pkt);
 					cur_dsd = (__le32 *)
 					    lcont_pkt.dseg_0_address;
 					avail_dsds = 5;
@@ -3431,7 +3429,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 					    REQUEST_ENTRY_SIZE);
 					ql_dump_buffer(
 					    ql_dbg_user + ql_dbg_verbose,
-					    sp->fcport->vha, 0x3045,
+					    sp->vha, 0x3045,
 					    (uint8_t *)&lcont_pkt,
 					    REQUEST_ENTRY_SIZE);
 				}
@@ -3440,7 +3438,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 				memcpy_toio((void __iomem *)cont_pkt,
 				    &lcont_pkt, REQUEST_ENTRY_SIZE);
 				ql_dump_buffer(ql_dbg_user + ql_dbg_verbose,
-				    sp->fcport->vha, 0x3046,
+				    sp->vha, 0x3046,
 				    (uint8_t *)&lcont_pkt, REQUEST_ENTRY_SIZE);
 			}
 		}
@@ -3452,7 +3450,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 	}
 
 	ql_dump_buffer(ql_dbg_user + ql_dbg_verbose,
-	    sp->fcport->vha, 0x3047,
+	    sp->vha, 0x3047,
 	    (uint8_t *)&fx_iocb, sizeof(struct fxdisc_entry_fx00));
 
 	memcpy_toio((void __iomem *)pfxiocb, &fx_iocb,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index bdaa238ca0ab..191aa94dc2f1 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -613,11 +613,11 @@ qla24xx_fw_version_str(struct scsi_qla_host *vha, char *str, size_t size)
 }
 
 void
-qla2x00_sp_free_dma(void *vha, void *ptr)
+qla2x00_sp_free_dma(void *ptr)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
+	struct qla_hw_data *ha = sp->vha->hw;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
-	struct qla_hw_data *ha = sp->fcport->vha->hw;
 	void *ctx = GET_CMD_CTX_SP(sp);
 
 	if (sp->flags & SRB_DMA_VALID) {
@@ -656,20 +656,19 @@ qla2x00_sp_free_dma(void *vha, void *ptr)
 	}
 
 	CMD_SP(cmd) = NULL;
-	qla2x00_rel_sp(sp->fcport->vha, sp);
+	qla2x00_rel_sp(sp);
 }
 
 void
-qla2x00_sp_compl(void *data, void *ptr, int res)
+qla2x00_sp_compl(void *ptr, int res)
 {
-	struct qla_hw_data *ha = (struct qla_hw_data *)data;
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 
 	cmd->result = res;
 
 	if (atomic_read(&sp->ref_count) == 0) {
-		ql_dbg(ql_dbg_io, sp->fcport->vha, 0x3015,
+		ql_dbg(ql_dbg_io, sp->vha, 0x3015,
 		    "SP reference-count to ZERO -- sp=%p cmd=%p.\n",
 		    sp, GET_CMD_SP(sp));
 		if (ql2xextended_error_logging & ql_dbg_io)
@@ -679,12 +678,12 @@ qla2x00_sp_compl(void *data, void *ptr, int res)
 	if (!atomic_dec_and_test(&sp->ref_count))
 		return;
 
-	qla2x00_sp_free_dma(ha, sp);
+	qla2x00_sp_free_dma(sp);
 	cmd->scsi_done(cmd);
 }
 
 void
-qla2xxx_qpair_sp_free_dma(void *vha, void *ptr)
+qla2xxx_qpair_sp_free_dma(void *ptr)
 {
 	srb_t *sp = (srb_t *)ptr;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
@@ -730,9 +729,9 @@ qla2xxx_qpair_sp_free_dma(void *vha, void *ptr)
 }
 
 void
-qla2xxx_qpair_sp_compl(void *data, void *ptr, int res)
+qla2xxx_qpair_sp_compl(void *ptr, int res)
 {
-	srb_t *sp = (srb_t *)ptr;
+	srb_t *sp = ptr;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 
 	cmd->result = res;
@@ -748,7 +747,7 @@ qla2xxx_qpair_sp_compl(void *data, void *ptr, int res)
 	if (!atomic_dec_and_test(&sp->ref_count))
 		return;
 
-	qla2xxx_qpair_sp_free_dma(sp->fcport->vha, sp);
+	qla2xxx_qpair_sp_free_dma(sp);
 	cmd->scsi_done(cmd);
 }
 
@@ -869,7 +868,7 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	return 0;
 
 qc24_host_busy_free_sp:
-	qla2x00_sp_free_dma(ha, sp);
+	qla2x00_sp_free_dma(sp);
 
 qc24_host_busy:
 	return SCSI_MLQUEUE_HOST_BUSY;
@@ -958,7 +957,7 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd,
 	return 0;
 
 qc24_host_busy_free_sp:
-	qla2xxx_qpair_sp_free_dma(vha, sp);
+	qla2xxx_qpair_sp_free_dma(sp);
 
 qc24_host_busy:
 	return SCSI_MLQUEUE_HOST_BUSY;
@@ -1238,7 +1237,7 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 	}
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	sp->done(vha, sp, 0);
+	sp->done(sp, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	/* Did the command return during mailbox execution? */
@@ -1283,7 +1282,7 @@ qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t,
 			continue;
 		if (sp->type != SRB_SCSI_CMD)
 			continue;
-		if (vha->vp_idx != sp->fcport->vha->vp_idx)
+		if (vha->vp_idx != sp->vha->vp_idx)
 			continue;
 		match = 0;
 		cmd = GET_CMD_SP(sp);
@@ -1663,7 +1662,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 					spin_lock_irqsave(&ha->hardware_lock, flags);
 				}
 				req->outstanding_cmds[cnt] = NULL;
-				sp->done(vha, sp, res);
+				sp->done(sp, res);
 			}
 		}
 	}
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 1cd3734292f9..45f5077684f0 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -535,10 +535,10 @@ static int qla24xx_post_nack_work(struct scsi_qla_host *vha, fc_port_t *fcport,
 }
 
 static
-void qla2x00_async_nack_sp_done(void *v, void *s, int res)
+void qla2x00_async_nack_sp_done(void *s, int res)
 {
-	struct scsi_qla_host *vha = (struct scsi_qla_host *)v;
 	struct srb *sp = (struct srb *)s;
+	struct scsi_qla_host *vha = sp->vha;
 	unsigned long flags;
 
 	ql_dbg(ql_dbg_disc, vha, 0xffff,
@@ -595,7 +595,7 @@ void qla2x00_async_nack_sp_done(void *v, void *s, int res)
 	}
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
-	sp->free(vha, sp);
+	sp->free(sp);
 }
 
 int qla24xx_async_notify_ack(scsi_qla_host_t *vha, fc_port_t *fcport,
@@ -645,7 +645,7 @@ int qla24xx_async_notify_ack(scsi_qla_host_t *vha, fc_port_t *fcport,
 	return rval;
 
 done_free_sp:
-	sp->free(vha, sp);
+	sp->free(sp);
 done:
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	return rval;
-- 
GitLab


From 2fdbc65eae3989b566047b2ce21d66f52fe6bf69 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 20 Jan 2017 13:31:13 -0800
Subject: [PATCH 072/898] qla2xxx: Avoid using variable-length arrays

This patch does not change any functionality but avoids that sparse
complains about using variable-length arrays.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Acked-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Cc: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_os.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 191aa94dc2f1..4f5965281395 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4272,8 +4272,8 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	spin_lock_init(&vha->cmd_list_lock);
 	init_waitqueue_head(&vha->fcport_waitQ);
 
-	vha->gnl.size =
-	    sizeof(struct get_name_list_extended[ha->max_loop_id+1]);
+	vha->gnl.size = sizeof(struct get_name_list_extended) *
+			(ha->max_loop_id + 1);
 	vha->gnl.l = dma_alloc_coherent(&ha->pdev->dev,
 	    vha->gnl.size, &vha->gnl.ldma, GFP_KERNEL);
 	if (!vha->gnl.l) {
-- 
GitLab


From 5cadafb236dffd8aa4772b32bf848af9128faedc Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 13 Jan 2017 10:41:52 -0800
Subject: [PATCH 073/898] target/cxgbit: Fix endianness annotations

This patch does not change any functionality but avoids that sparse
complains about endianness.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Acked-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h |  2 +-
 drivers/target/iscsi/cxgbit/cxgbit_cm.c            | 11 ++++++-----
 drivers/target/iscsi/cxgbit/cxgbit_main.c          |  2 +-
 drivers/target/iscsi/cxgbit/cxgbit_target.c        |  2 +-
 4 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h
index e995a1a3840a..a91ad766cef0 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h
@@ -59,7 +59,7 @@ struct cxgbi_pagepod_hdr {
 #define PPOD_PAGES_MAX			4
 struct cxgbi_pagepod {
 	struct cxgbi_pagepod_hdr hdr;
-	u64 addr[PPOD_PAGES_MAX + 1];
+	__be64 addr[PPOD_PAGES_MAX + 1];
 };
 
 /* ddp tag format
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
index 2fb1bf1a26c5..35aaa36e9af5 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -1726,7 +1726,7 @@ static bool cxgbit_credit_err(const struct cxgbit_sock *csk)
 	}
 
 	while (skb) {
-		credit += skb->csum;
+		credit += (__force u32)skb->csum;
 		skb = cxgbit_skcb_tx_wr_next(skb);
 	}
 
@@ -1753,6 +1753,7 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb)
 
 	while (credits) {
 		struct sk_buff *p = cxgbit_sock_peek_wr(csk);
+		const u32 csum = (__force u32)p->csum;
 
 		if (unlikely(!p)) {
 			pr_err("csk 0x%p,%u, cr %u,%u+%u, empty.\n",
@@ -1761,17 +1762,17 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb)
 			break;
 		}
 
-		if (unlikely(credits < p->csum)) {
+		if (unlikely(credits < csum)) {
 			pr_warn("csk 0x%p,%u, cr %u,%u+%u, < %u.\n",
 				csk,  csk->tid,
 				credits, csk->wr_cred, csk->wr_una_cred,
-				p->csum);
-			p->csum -= credits;
+				csum);
+			p->csum = (__force __wsum)(csum - credits);
 			break;
 		}
 
 		cxgbit_sock_dequeue_wr(csk);
-		credits -= p->csum;
+		credits -= csum;
 		kfree_skb(p);
 	}
 
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c
index 96eedfc49c94..6531aaac2b96 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_main.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c
@@ -454,7 +454,7 @@ cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp,
 		if (unlikely(op != *(u8 *)gl->va)) {
 			pr_info("? FL 0x%p,RSS%#llx,FL %#llx,len %u.\n",
 				gl->va, be64_to_cpu(*rsp),
-				be64_to_cpu(*(u64 *)gl->va),
+				get_unaligned_be64(gl->va),
 				gl->tot_len);
 			return 0;
 		}
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
index 8bcb9b71f764..e183e0bdd3bf 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_target.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -243,7 +243,7 @@ void cxgbit_push_tx_frames(struct cxgbit_sock *csk)
 		}
 		__skb_unlink(skb, &csk->txq);
 		set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
-		skb->csum = credits_needed + flowclen16;
+		skb->csum = (__force __wsum)(credits_needed + flowclen16);
 		csk->wr_cred -= credits_needed;
 		csk->wr_una_cred += credits_needed;
 
-- 
GitLab


From bdec5188745c4f03ecbc5b88bc2c3f76acb435ae Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Tue, 24 Jan 2017 17:07:02 +0530
Subject: [PATCH 074/898] target/cxgbit: Use T6 specific macro to set the force
 bit

For T6 adapters use T6 specific macro to set the force bit.

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 4 ++++
 drivers/target/iscsi/cxgbit/cxgbit_target.c | 4 +++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index a267173f5997..21fc2fe1fc10 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -1349,6 +1349,10 @@ struct cpl_tx_data {
 #define TX_FORCE_S	13
 #define TX_FORCE_V(x)	((x) << TX_FORCE_S)
 
+#define T6_TX_FORCE_S		20
+#define T6_TX_FORCE_V(x)	((x) << T6_TX_FORCE_S)
+#define T6_TX_FORCE_F		T6_TX_FORCE_V(1U)
+
 enum {
 	ULP_TX_MEM_READ = 2,
 	ULP_TX_MEM_WRITE = 3,
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
index e183e0bdd3bf..8ae399dfe84f 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_target.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -162,12 +162,14 @@ cxgbit_tx_data_wr(struct cxgbit_sock *csk, struct sk_buff *skb, u32 dlen,
 		  u32 len, u32 credits, u32 compl)
 {
 	struct fw_ofld_tx_data_wr *req;
+	const struct cxgb4_lld_info *lldi = &csk->com.cdev->lldi;
 	u32 submode = cxgbit_skcb_submode(skb);
 	u32 wr_ulp_mode = 0;
 	u32 hdr_size = sizeof(*req);
 	u32 opcode = FW_OFLD_TX_DATA_WR;
 	u32 immlen = 0;
-	u32 force = TX_FORCE_V(!submode);
+	u32 force = is_t5(lldi->adapter_type) ? TX_FORCE_V(!submode) :
+		    T6_TX_FORCE_F;
 
 	if (cxgbit_skcb_flags(skb) & SKCBF_TX_ISO) {
 		opcode = FW_ISCSI_TX_DATA_WR;
-- 
GitLab


From 664a722b4f1bab63fee0193459036d1a95e19e99 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Wed, 4 Jan 2017 08:13:34 +0100
Subject: [PATCH 075/898] target/tcm_fc: Remove a set-but-not-used variable

This was detected by building with W=1.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jth@kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/tcm_fc/tfc_cmd.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 9af7842b8178..ec372860106f 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -83,14 +83,12 @@ void ft_dump_cmd(struct ft_cmd *cmd, const char *caller)
 static void ft_free_cmd(struct ft_cmd *cmd)
 {
 	struct fc_frame *fp;
-	struct fc_lport *lport;
 	struct ft_sess *sess;
 
 	if (!cmd)
 		return;
 	sess = cmd->sess;
 	fp = cmd->req_frame;
-	lport = fr_dev(fp);
 	if (fr_seq(fp))
 		fc_seq_release(fr_seq(fp));
 	fc_frame_free(fp);
-- 
GitLab


From 1efaa949396b5d9e8d1e6edef7e97e9ce1a97319 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 23 Dec 2016 12:45:27 +0100
Subject: [PATCH 076/898] target/iscsi: Fix indentation in
 iscsi_target_start_negotiation()

This patch avoids that smatch complains about inconsistent
indentation in iscsi_target_start_negotiation().

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target_nego.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 46388c9e08da..5269e9ef031c 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -1249,16 +1249,16 @@ int iscsi_target_start_negotiation(
 {
 	int ret;
 
-       if (conn->sock) {
-               struct sock *sk = conn->sock->sk;
+	if (conn->sock) {
+		struct sock *sk = conn->sock->sk;
 
-               write_lock_bh(&sk->sk_callback_lock);
-               set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
-               write_unlock_bh(&sk->sk_callback_lock);
-       }
+		write_lock_bh(&sk->sk_callback_lock);
+		set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
+		write_unlock_bh(&sk->sk_callback_lock);
+	}
 
-       ret = iscsi_target_do_login(conn, login);
-       if (ret < 0) {
+	ret = iscsi_target_do_login(conn, login);
+	if (ret < 0) {
 		cancel_delayed_work_sync(&conn->login_work);
 		cancel_delayed_work_sync(&conn->login_cleanup_work);
 		iscsi_target_restore_sock_callbacks(conn);
-- 
GitLab


From 0d5efb8a3c62c598d092bedb579debacd3f746eb Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 23 Dec 2016 14:37:52 +0100
Subject: [PATCH 077/898] target/iscsi: Fix spelling of "perform"

Change two occurrences of "preform" into "perform".

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target.c       | 2 +-
 drivers/target/iscsi/iscsi_target_login.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index da2c73a255de..3b770fddcb3b 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1545,7 +1545,7 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf,
 		}
 	}
 	/*
-	 * Preform DataSN, DataSequenceInOrder, DataPDUInOrder, and
+	 * Perform DataSN, DataSequenceInOrder, DataPDUInOrder, and
 	 * within-command recovery checks before receiving the payload.
 	 */
 	rc = iscsit_check_pre_dataout(cmd, buf);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 450f51deb2a2..303cb6574a93 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -222,7 +222,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
 		return 0;
 
 	pr_debug("%s iSCSI Session SID %u is still active for %s,"
-		" preforming session reinstatement.\n", (sessiontype) ?
+		" performing session reinstatement.\n", (sessiontype) ?
 		"Discovery" : "Normal", sess->sid,
 		sess->sess_ops->InitiatorName);
 
-- 
GitLab


From 53c561dca9fd66330fe63d8a03ef859407e2cd91 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 23 Dec 2016 14:40:24 +0100
Subject: [PATCH 078/898] target/iscsi: Fix spelling of "reallegiance"

Fix the spelling of this word in a function name, messages and
source code comments.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target.c      | 4 ++--
 drivers/target/iscsi/iscsi_target_erl2.c | 6 +++---
 drivers/target/iscsi/iscsi_target_erl2.h | 2 +-
 drivers/target/iscsi/iscsi_target_tmr.c  | 4 ++--
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 3b770fddcb3b..e11f8d0f1fa3 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4136,7 +4136,7 @@ int iscsit_close_connection(
 	/*
 	 * During Connection recovery drop unacknowledged out of order
 	 * commands for this connection, and prepare the other commands
-	 * for realligence.
+	 * for reallegiance.
 	 *
 	 * During normal operation clear the out of order commands (but
 	 * do not free the struct iscsi_ooo_cmdsn's) and release all
@@ -4144,7 +4144,7 @@ int iscsit_close_connection(
 	 */
 	if (atomic_read(&conn->connection_recovery)) {
 		iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(conn);
-		iscsit_prepare_cmds_for_realligance(conn);
+		iscsit_prepare_cmds_for_reallegiance(conn);
 	} else {
 		iscsit_clear_ooo_cmdsns_for_conn(conn);
 		iscsit_release_commands_from_conn(conn);
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index faf9ae014b30..8df9c90f3db3 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -312,7 +312,7 @@ int iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(struct iscsi_conn *conn)
 	return 0;
 }
 
-int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn)
+int iscsit_prepare_cmds_for_reallegiance(struct iscsi_conn *conn)
 {
 	u32 cmd_count = 0;
 	struct iscsi_cmd *cmd, *cmd_tmp;
@@ -347,7 +347,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn)
 
 		if ((cmd->iscsi_opcode != ISCSI_OP_SCSI_CMD) &&
 		    (cmd->iscsi_opcode != ISCSI_OP_NOOP_OUT)) {
-			pr_debug("Not performing realligence on"
+			pr_debug("Not performing reallegiance on"
 				" Opcode: 0x%02x, ITT: 0x%08x, CmdSN: 0x%08x,"
 				" CID: %hu\n", cmd->iscsi_opcode,
 				cmd->init_task_tag, cmd->cmd_sn, conn->cid);
@@ -382,7 +382,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn)
 		cmd_count++;
 		pr_debug("Preparing Opcode: 0x%02x, ITT: 0x%08x,"
 			" CmdSN: 0x%08x, StatSN: 0x%08x, CID: %hu for"
-			" realligence.\n", cmd->iscsi_opcode,
+			" reallegiance.\n", cmd->iscsi_opcode,
 			cmd->init_task_tag, cmd->cmd_sn, cmd->stat_sn,
 			conn->cid);
 
diff --git a/drivers/target/iscsi/iscsi_target_erl2.h b/drivers/target/iscsi/iscsi_target_erl2.h
index 7965f1e86506..634d01e13652 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.h
+++ b/drivers/target/iscsi/iscsi_target_erl2.h
@@ -19,7 +19,7 @@ extern int iscsit_remove_cmd_from_connection_recovery(struct iscsi_cmd *,
 			struct iscsi_session *);
 extern void iscsit_discard_cr_cmds_by_expstatsn(struct iscsi_conn_recovery *, u32);
 extern int iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(struct iscsi_conn *);
-extern int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *);
+extern int iscsit_prepare_cmds_for_reallegiance(struct iscsi_conn *);
 extern int iscsit_connection_recovery_transport_reset(struct iscsi_conn *);
 
 #endif /*** ISCSI_TARGET_ERL2_H ***/
diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c
index 3d637055c36f..cb231c907d51 100644
--- a/drivers/target/iscsi/iscsi_target_tmr.c
+++ b/drivers/target/iscsi/iscsi_target_tmr.c
@@ -440,14 +440,14 @@ static int iscsit_task_reassign_complete(
 		break;
 	default:
 		 pr_err("Illegal iSCSI Opcode 0x%02x during"
-			" command realligence\n", cmd->iscsi_opcode);
+			" command reallegiance\n", cmd->iscsi_opcode);
 		return -1;
 	}
 
 	if (ret != 0)
 		return ret;
 
-	pr_debug("Completed connection realligence for Opcode: 0x%02x,"
+	pr_debug("Completed connection reallegiance for Opcode: 0x%02x,"
 		" ITT: 0x%08x to CID: %hu.\n", cmd->iscsi_opcode,
 			cmd->init_task_tag, conn->cid);
 
-- 
GitLab


From e381fe9e89909ced3d878b8c3c3a9b344c02cbdc Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 6 Jan 2017 11:32:08 +0100
Subject: [PATCH 079/898] target/iscsi: Introduce a helper function for TMF
 translation

This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target.c | 48 ++++++++++++++---------------
 include/target/target_core_base.h   |  1 +
 2 files changed, 25 insertions(+), 24 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index e11f8d0f1fa3..d16729fa1f67 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1920,6 +1920,28 @@ static int iscsit_handle_nop_out(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	return ret;
 }
 
+static enum tcm_tmreq_table iscsit_convert_tmf(u8 iscsi_tmf)
+{
+	switch (iscsi_tmf) {
+	case ISCSI_TM_FUNC_ABORT_TASK:
+		return TMR_ABORT_TASK;
+	case ISCSI_TM_FUNC_ABORT_TASK_SET:
+		return TMR_ABORT_TASK_SET;
+	case ISCSI_TM_FUNC_CLEAR_ACA:
+		return TMR_CLEAR_ACA;
+	case ISCSI_TM_FUNC_CLEAR_TASK_SET:
+		return TMR_CLEAR_TASK_SET;
+	case ISCSI_TM_FUNC_LOGICAL_UNIT_RESET:
+		return TMR_LUN_RESET;
+	case ISCSI_TM_FUNC_TARGET_WARM_RESET:
+		return TMR_TARGET_WARM_RESET;
+	case ISCSI_TM_FUNC_TARGET_COLD_RESET:
+		return TMR_TARGET_COLD_RESET;
+	default:
+		return TMR_UNKNOWN;
+	}
+}
+
 int
 iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 			   unsigned char *buf)
@@ -1985,30 +2007,8 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 
 		target_get_sess_cmd(&cmd->se_cmd, true);
 		sess_ref = true;
-
-		switch (function) {
-		case ISCSI_TM_FUNC_ABORT_TASK:
-			tcm_function = TMR_ABORT_TASK;
-			break;
-		case ISCSI_TM_FUNC_ABORT_TASK_SET:
-			tcm_function = TMR_ABORT_TASK_SET;
-			break;
-		case ISCSI_TM_FUNC_CLEAR_ACA:
-			tcm_function = TMR_CLEAR_ACA;
-			break;
-		case ISCSI_TM_FUNC_CLEAR_TASK_SET:
-			tcm_function = TMR_CLEAR_TASK_SET;
-			break;
-		case ISCSI_TM_FUNC_LOGICAL_UNIT_RESET:
-			tcm_function = TMR_LUN_RESET;
-			break;
-		case ISCSI_TM_FUNC_TARGET_WARM_RESET:
-			tcm_function = TMR_TARGET_WARM_RESET;
-			break;
-		case ISCSI_TM_FUNC_TARGET_COLD_RESET:
-			tcm_function = TMR_TARGET_COLD_RESET;
-			break;
-		default:
+		tcm_function = iscsit_convert_tmf(function);
+		if (tcm_function == TMR_UNKNOWN) {
 			pr_err("Unknown iSCSI TMR Function:"
 			       " 0x%02x\n", function);
 			return iscsit_add_reject_cmd(cmd,
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index da854fb4530f..92d5628775c2 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -197,6 +197,7 @@ enum tcm_tmreq_table {
 	TMR_LUN_RESET		= 5,
 	TMR_TARGET_WARM_RESET	= 6,
 	TMR_TARGET_COLD_RESET	= 7,
+	TMR_UNKNOWN		= 0xff,
 };
 
 /* fabric independent task management response values */
-- 
GitLab


From 59b6986dbfcdab96a971f9663221849de79a7556 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Thu, 5 Jan 2017 12:39:57 +0100
Subject: [PATCH 080/898] target/iscsi: Fix iSCSI task reassignment handling

Allocate a task management request structure for all task management
requests, including task reassignment. This change avoids that the
se_tmr->response assignment dereferences an uninitialized se_tmr
pointer.

Reported-by: Moshe David <mdavid@infinidat.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Moshe David <mdavid@infinidat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index d16729fa1f67..b4f1d1cbe521 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1951,7 +1951,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	struct iscsi_tm *hdr;
 	int out_of_order_cmdsn = 0, ret;
 	bool sess_ref = false;
-	u8 function;
+	u8 function, tcm_function = TMR_UNKNOWN;
 
 	hdr			= (struct iscsi_tm *) buf;
 	hdr->flags &= ~ISCSI_FLAG_CMD_FINAL;
@@ -1997,10 +1997,6 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	 * LIO-Target $FABRIC_MOD
 	 */
 	if (function != ISCSI_TM_FUNC_TASK_REASSIGN) {
-
-		u8 tcm_function;
-		int ret;
-
 		transport_init_se_cmd(&cmd->se_cmd, &iscsi_ops,
 				      conn->sess->se_sess, 0, DMA_NONE,
 				      TCM_SIMPLE_TAG, cmd->sense_buffer + 2);
@@ -2014,15 +2010,14 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 			return iscsit_add_reject_cmd(cmd,
 				ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
 		}
-
-		ret = core_tmr_alloc_req(&cmd->se_cmd, cmd->tmr_req,
-					 tcm_function, GFP_KERNEL);
-		if (ret < 0)
-			return iscsit_add_reject_cmd(cmd,
+	}
+	ret = core_tmr_alloc_req(&cmd->se_cmd, cmd->tmr_req, tcm_function,
+				 GFP_KERNEL);
+	if (ret < 0)
+		return iscsit_add_reject_cmd(cmd,
 				ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
 
-		cmd->tmr_req->se_tmr_req = cmd->se_cmd.se_tmr_req;
-	}
+	cmd->tmr_req->se_tmr_req = cmd->se_cmd.se_tmr_req;
 
 	cmd->iscsi_opcode	= ISCSI_OP_SCSI_TMFUNC;
 	cmd->i_state		= ISTATE_SEND_TASKMGTRSP;
-- 
GitLab


From 4f4c6c3ddb15af396cd8cf81b487b59261199ee9 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 23 Dec 2016 13:23:45 +0100
Subject: [PATCH 081/898] target: Remove se_tmr_req.tmr_lun

Member tmr_lun of se_tmr_req is set but not used. Hence remove it.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Cc: Giridhar Malavali <giridhar.malavali@cavium.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c | 1 -
 include/target/target_core_base.h   | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 26929c44d703..cb7047d66afc 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -163,7 +163,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, unpacked_lun);
 	if (deve) {
-		se_tmr->tmr_lun = rcu_dereference(deve->se_lun);
 		se_cmd->se_lun = rcu_dereference(deve->se_lun);
 		se_lun = rcu_dereference(deve->se_lun);
 		se_cmd->pr_res_key = deve->pr_res_key;
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 92d5628775c2..c8b06e226f2e 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -398,7 +398,6 @@ struct se_tmr_req {
 	void 			*fabric_tmr_ptr;
 	struct se_cmd		*task_cmd;
 	struct se_device	*tmr_dev;
-	struct se_lun		*tmr_lun;
 	struct list_head	tmr_list;
 };
 
-- 
GitLab


From 3a1e7ca64f2dae69536054c42b7b90e480db1045 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 23 Dec 2016 13:47:38 +0100
Subject: [PATCH 082/898] target: Make core_tmr_abort_task() consider all
 commands

It is possible that two commands with the same tag are present on
sess_cmd_list because commands are removed from sess_cmd_list after
a response has been sent to the initiator. Hence continue searching
through sess_cmd_list even if a matching tag has already been found.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Himanshu Madhani <himanshu.madhani@cavium.com>
Cc: Giridhar Malavali <giridhar.malavali@cavium.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_tmr.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 4f229e711e1c..311dc3c2f1dc 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -175,10 +175,9 @@ void core_tmr_abort_task(
 		printk("ABORT_TASK: Found referenced %s task_tag: %llu\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
-		if (!__target_check_io_state(se_cmd, se_sess, 0)) {
-			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-			goto out;
-		}
+		if (!__target_check_io_state(se_cmd, se_sess, 0))
+			continue;
+
 		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
@@ -195,7 +194,6 @@ void core_tmr_abort_task(
 	}
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
-out:
 	printk("ABORT_TASK: Sending TMR_TASK_DOES_NOT_EXIST for ref_tag: %lld\n",
 			tmr->ref_task_tag);
 	tmr->response = TMR_TASK_DOES_NOT_EXIST;
-- 
GitLab


From 2d4760ee4720d5f0eeda770ce248244166676283 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 10 Jan 2017 10:03:28 -0800
Subject: [PATCH 083/898] target: Correct transport_wait_for_tasks()
 documentation

transport_wait_for_tasks() not only waits for command completion
but also sets CMD_T_STOP. Additionally, this function is not only
called by frontend drivers but also by the target core. Update
the transport_wait_for_tasks() documentation to reflect this.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 437591bc7c08..62a50ea52a49 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2765,11 +2765,8 @@ __transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
 }
 
 /**
- * transport_wait_for_tasks - wait for completion to occur
- * @cmd:	command to wait
- *
- * Called from frontend fabric context to wait for storage engine
- * to pause and/or release frontend generated struct se_cmd.
+ * transport_wait_for_tasks - set CMD_T_STOP and wait for t_transport_stop_comp
+ * @cmd: command to wait on
  */
 bool transport_wait_for_tasks(struct se_cmd *cmd)
 {
-- 
GitLab


From a5eb307f37d1e9909284b6f0a8f72bf55423c137 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Mon, 9 Jan 2017 10:14:54 -0800
Subject: [PATCH 084/898] target: Stop execution if CMD_T_STOP has been set

Stop execution if CMD_T_STOP has been set for a command just after
the command has been added to the device command list and before
.write_pending() is called. The following sequence can trigger this:
- transport_handle_cdb_direct() gets called. This function namely
  sets CMD_T_ACTIVE before it calls transport_generic_new_cmd().
- __transport_wait_for_tasks() is called concurrently. This function
  sets CMD_T_STOP for all active commands that have not been aborted.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 62a50ea52a49..2d867af1961f 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2452,7 +2452,8 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 		target_execute_cmd(cmd);
 		return 0;
 	}
-	transport_cmd_check_stop(cmd, false, true);
+	if (transport_cmd_check_stop(cmd, false, true))
+		return 0;
 
 	ret = cmd->se_tfo->write_pending(cmd);
 	if (ret == -EAGAIN || ret == -ENOMEM)
-- 
GitLab


From 580ab13ac445a2bb717bee995d8639ec6836f78c Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Sun, 27 Dec 2015 13:48:09 +0100
Subject: [PATCH 085/898] target: Remove an overly chatty debug message

Enabling dynamic debug for the target_core_mod kernel module
causes the system log to be spammed with the "Incremented ..."
message. Hence remove it.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 2d867af1961f..738ab107ec12 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1979,8 +1979,6 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 	if (cmd->sam_task_attr == TCM_SIMPLE_TAG) {
 		atomic_dec_mb(&dev->simple_cmds);
 		dev->dev_cur_ordered_id++;
-		pr_debug("Incremented dev->dev_cur_ordered_id: %u for SIMPLE\n",
-			 dev->dev_cur_ordered_id);
 	} else if (cmd->sam_task_attr == TCM_HEAD_TAG) {
 		dev->dev_cur_ordered_id++;
 		pr_debug("Incremented dev_cur_ordered_id: %u for HEAD_OF_QUEUE\n",
-- 
GitLab


From b1a2ecdad72e0a4f0ebdbaff580b5330ebcf68c3 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Wed, 1 Feb 2017 16:58:35 -0800
Subject: [PATCH 086/898] target: Inline transport_cmd_check_stop()

The function transport_cmd_check_stop() has two callers. These callers
invoke this function as follows:
* transport_cmd_check_stop(cmd, true, false)
* transport_cmd_check_stop(cmd, false, true)
Hence inline this function into its callers.

This patch does not change any functionality but improves source
code readability.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 68 +++++++++++++-------------
 include/target/target_core_fabric.h    |  2 +-
 2 files changed, 34 insertions(+), 36 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 738ab107ec12..6f66a2d890b8 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -604,24 +604,18 @@ static void target_remove_from_state_list(struct se_cmd *cmd)
 	spin_unlock_irqrestore(&dev->execute_task_lock, flags);
 }
 
-static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
-				    bool write_pending)
+static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
 {
 	unsigned long flags;
 
-	if (remove_from_lists) {
-		target_remove_from_state_list(cmd);
+	target_remove_from_state_list(cmd);
 
-		/*
-		 * Clear struct se_cmd->se_lun before the handoff to FE.
-		 */
-		cmd->se_lun = NULL;
-	}
+	/*
+	 * Clear struct se_cmd->se_lun before the handoff to FE.
+	 */
+	cmd->se_lun = NULL;
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if (write_pending)
-		cmd->t_state = TRANSPORT_WRITE_PENDING;
-
 	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
@@ -635,31 +629,18 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 		complete_all(&cmd->t_transport_stop_comp);
 		return 1;
 	}
-
 	cmd->transport_state &= ~CMD_T_ACTIVE;
-	if (remove_from_lists) {
-		/*
-		 * Some fabric modules like tcm_loop can release
-		 * their internally allocated I/O reference now and
-		 * struct se_cmd now.
-		 *
-		 * Fabric modules are expected to return '1' here if the
-		 * se_cmd being passed is released at this point,
-		 * or zero if not being released.
-		 */
-		if (cmd->se_tfo->check_stop_free != NULL) {
-			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-			return cmd->se_tfo->check_stop_free(cmd);
-		}
-	}
-
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-	return 0;
-}
 
-static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
-{
-	return transport_cmd_check_stop(cmd, true, false);
+	/*
+	 * Some fabric modules like tcm_loop can release their internally
+	 * allocated I/O reference and struct se_cmd now.
+	 *
+	 * Fabric modules are expected to return '1' here if the se_cmd being
+	 * passed is released at this point, or zero if not being released.
+	 */
+	return cmd->se_tfo->check_stop_free ? cmd->se_tfo->check_stop_free(cmd)
+		: 0;
 }
 
 static void transport_lun_remove_cmd(struct se_cmd *cmd)
@@ -2385,6 +2366,7 @@ EXPORT_SYMBOL(target_alloc_sgl);
 sense_reason_t
 transport_generic_new_cmd(struct se_cmd *cmd)
 {
+	unsigned long flags;
 	int ret = 0;
 	bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB);
 
@@ -2450,8 +2432,24 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 		target_execute_cmd(cmd);
 		return 0;
 	}
-	if (transport_cmd_check_stop(cmd, false, true))
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	cmd->t_state = TRANSPORT_WRITE_PENDING;
+	/*
+	 * Determine if frontend context caller is requesting the stopping of
+	 * this command for frontend exceptions.
+	 */
+	if (cmd->transport_state & CMD_T_STOP) {
+		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n",
+			 __func__, __LINE__, cmd->tag);
+
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
+		complete_all(&cmd->t_transport_stop_comp);
 		return 0;
+	}
+	cmd->transport_state &= ~CMD_T_ACTIVE;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
 	ret = cmd->se_tfo->write_pending(cmd);
 	if (ret == -EAGAIN || ret == -ENOMEM)
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 358041bad1da..d7dd1427fe0d 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -47,7 +47,7 @@ struct target_core_fabric_ops {
 	u32 (*tpg_get_inst_index)(struct se_portal_group *);
 	/*
 	 * Optional to release struct se_cmd and fabric dependent allocated
-	 * I/O descriptor in transport_cmd_check_stop().
+	 * I/O descriptor after command execution has finished.
 	 *
 	 * Returning 1 will signal a descriptor has been released.
 	 * Returning 0 will signal a descriptor has not been released.
-- 
GitLab


From 6b6427b6fd90ba1ff13e540bf7276f30a3e6f74f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 7 Feb 2017 12:19:16 -0800
Subject: [PATCH 087/898] target: Move session check from target_put_sess_cmd()
 into target_release_cmd_kref()

This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 39 +++++++++++++-------------
 1 file changed, 19 insertions(+), 20 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 6f66a2d890b8..e949db12c4d8 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2592,39 +2592,38 @@ static void target_release_cmd_kref(struct kref *kref)
 	unsigned long flags;
 	bool fabric_stop;
 
-	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
+	if (se_sess) {
+		spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 
-	spin_lock(&se_cmd->t_state_lock);
-	fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) &&
-		      (se_cmd->transport_state & CMD_T_ABORTED);
-	spin_unlock(&se_cmd->t_state_lock);
+		spin_lock(&se_cmd->t_state_lock);
+		fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) &&
+			      (se_cmd->transport_state & CMD_T_ABORTED);
+		spin_unlock(&se_cmd->t_state_lock);
 
-	if (se_cmd->cmd_wait_set || fabric_stop) {
+		if (se_cmd->cmd_wait_set || fabric_stop) {
+			list_del_init(&se_cmd->se_cmd_list);
+			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+			target_free_cmd_mem(se_cmd);
+			complete(&se_cmd->cmd_wait_comp);
+			return;
+		}
 		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-		target_free_cmd_mem(se_cmd);
-		complete(&se_cmd->cmd_wait_comp);
-		return;
 	}
-	list_del_init(&se_cmd->se_cmd_list);
-	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 	target_free_cmd_mem(se_cmd);
 	se_cmd->se_tfo->release_cmd(se_cmd);
 }
 
-/* target_put_sess_cmd - Check for active I/O shutdown via kref_put
- * @se_cmd:	command descriptor to drop
+/**
+ * target_put_sess_cmd - decrease the command reference count
+ * @se_cmd:	command to drop a reference from
+ *
+ * Returns 1 if and only if this target_put_sess_cmd() call caused the
+ * refcount to drop to zero. Returns zero otherwise.
  */
 int target_put_sess_cmd(struct se_cmd *se_cmd)
 {
-	struct se_session *se_sess = se_cmd->se_sess;
-
-	if (!se_sess) {
-		target_free_cmd_mem(se_cmd);
-		se_cmd->se_tfo->release_cmd(se_cmd);
-		return 1;
-	}
 	return kref_put(&se_cmd->cmd_kref, target_release_cmd_kref);
 }
 EXPORT_SYMBOL(target_put_sess_cmd);
-- 
GitLab


From fd5e64def9170392fdf258d1eee5966433ee3d45 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 3 Jan 2017 10:44:11 +0100
Subject: [PATCH 088/898] target: Remove command flag CMD_T_BUSY

The patch that reworks task management function handling guarantees
that target_remove_from_state_list() is always called with CMD_T_BUSY
cleared. Since that function is the only function that tests that flag
this means that that flag is now superfluous. Hence remove that flag.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Andy Grover <agrover@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_sbc.c       |  2 +-
 drivers/target/target_core_transport.c | 12 ++++--------
 include/target/target_core_base.h      |  1 -
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index df7b6e95c019..68d8aef7ab78 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -604,7 +604,7 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool succes
 
 	spin_lock_irq(&cmd->t_state_lock);
 	cmd->t_state = TRANSPORT_PROCESSING;
-	cmd->transport_state |= CMD_T_ACTIVE|CMD_T_BUSY|CMD_T_SENT;
+	cmd->transport_state |= CMD_T_ACTIVE | CMD_T_SENT;
 	spin_unlock_irq(&cmd->t_state_lock);
 
 	__target_execute_cmd(cmd, false);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index e949db12c4d8..012ed95c3f40 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -593,9 +593,6 @@ static void target_remove_from_state_list(struct se_cmd *cmd)
 	if (!dev)
 		return;
 
-	if (cmd->transport_state & CMD_T_BUSY)
-		return;
-
 	spin_lock_irqsave(&dev->execute_task_lock, flags);
 	if (cmd->state_active) {
 		list_del(&cmd->state_list);
@@ -714,7 +711,6 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	cmd->transport_state &= ~CMD_T_BUSY;
 
 	if (dev && dev->transport->transport_complete) {
 		dev->transport->transport_complete(cmd,
@@ -1782,7 +1778,7 @@ void __target_execute_cmd(struct se_cmd *cmd, bool do_checks)
 		return;
 err:
 	spin_lock_irq(&cmd->t_state_lock);
-	cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
+	cmd->transport_state &= ~CMD_T_SENT;
 	spin_unlock_irq(&cmd->t_state_lock);
 
 	transport_generic_request_failure(cmd, ret);
@@ -1810,7 +1806,7 @@ static int target_write_prot_action(struct se_cmd *cmd)
 					     sectors, 0, cmd->t_prot_sg, 0);
 		if (unlikely(cmd->pi_err)) {
 			spin_lock_irq(&cmd->t_state_lock);
-			cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
+			cmd->transport_state &= ~CMD_T_SENT;
 			spin_unlock_irq(&cmd->t_state_lock);
 			transport_generic_request_failure(cmd, cmd->pi_err);
 			return -1;
@@ -1899,7 +1895,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 	}
 
 	cmd->t_state = TRANSPORT_PROCESSING;
-	cmd->transport_state |= CMD_T_ACTIVE|CMD_T_BUSY|CMD_T_SENT;
+	cmd->transport_state |= CMD_T_ACTIVE | CMD_T_SENT;
 	spin_unlock_irq(&cmd->t_state_lock);
 
 	if (target_write_prot_action(cmd))
@@ -1907,7 +1903,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 
 	if (target_handle_task_attr(cmd)) {
 		spin_lock_irq(&cmd->t_state_lock);
-		cmd->transport_state &= ~(CMD_T_BUSY | CMD_T_SENT);
+		cmd->transport_state &= ~CMD_T_SENT;
 		spin_unlock_irq(&cmd->t_state_lock);
 		return;
 	}
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c8b06e226f2e..7b350fd60cdb 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -489,7 +489,6 @@ struct se_cmd {
 #define CMD_T_SENT		(1 << 4)
 #define CMD_T_STOP		(1 << 5)
 #define CMD_T_DEV_ACTIVE	(1 << 7)
-#define CMD_T_BUSY		(1 << 9)
 #define CMD_T_TAS		(1 << 10)
 #define CMD_T_FABRIC_STOP	(1 << 11)
 	spinlock_t		t_state_lock;
-- 
GitLab


From b2c9652eba6c11787b5f6cfa53aaea752f58809e Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Fri, 5 Jun 2015 16:17:51 -0700
Subject: [PATCH 089/898] target: Remove command flag CMD_T_DEV_ACTIVE

The code that tests the CMD_T_DEV_ACTIVE flag has been removed. Hence
also remove the flag itself.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Andy Grover <agrover@redhat.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 1 -
 include/target/target_core_base.h      | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 012ed95c3f40..22190003534d 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1223,7 +1223,6 @@ void transport_init_se_cmd(
 	init_completion(&cmd->cmd_wait_comp);
 	spin_lock_init(&cmd->t_state_lock);
 	kref_init(&cmd->cmd_kref);
-	cmd->transport_state = CMD_T_DEV_ACTIVE;
 
 	cmd->se_tfo = tfo;
 	cmd->se_sess = se_sess;
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 7b350fd60cdb..d7336f3c6b60 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -488,7 +488,6 @@ struct se_cmd {
 #define CMD_T_COMPLETE		(1 << 2)
 #define CMD_T_SENT		(1 << 4)
 #define CMD_T_STOP		(1 << 5)
-#define CMD_T_DEV_ACTIVE	(1 << 7)
 #define CMD_T_TAS		(1 << 10)
 #define CMD_T_FABRIC_STOP	(1 << 11)
 	spinlock_t		t_state_lock;
-- 
GitLab


From ca8d8e03b4c9ad447d1e882cc8014e538f653018 Mon Sep 17 00:00:00 2001
From: William Breathitt Gray <vilhelm.gray@gmail.com>
Date: Thu, 9 Feb 2017 10:03:41 -0500
Subject: [PATCH 090/898] iio: 104-quad-8: Fix off-by-one error when addressing
 flag register

The flag register is offset by 1 from the respective channel data
register. This patch fixes an off-by-one error when attempting to read a
channel flag register where the base address was not properly offset.

Fixes: 28e5d3bb0325 ("iio: 104-quad-8: Add IIO support for the ACCES 104-QUAD-8")
Signed-off-by: William Breathitt Gray <vilhelm.gray@gmail.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/counter/104-quad-8.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/counter/104-quad-8.c b/drivers/iio/counter/104-quad-8.c
index a5913e97945e..f9b8fc9ae13f 100644
--- a/drivers/iio/counter/104-quad-8.c
+++ b/drivers/iio/counter/104-quad-8.c
@@ -76,7 +76,7 @@ static int quad8_read_raw(struct iio_dev *indio_dev,
 			return IIO_VAL_INT;
 		}
 
-		flags = inb(base_offset);
+		flags = inb(base_offset + 1);
 		borrow = flags & BIT(0);
 		carry = !!(flags & BIT(1));
 
-- 
GitLab


From 7e91c7df29b5e196de3dc6f086c8937973bd0b88 Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Tue, 7 Feb 2017 19:58:02 +0200
Subject: [PATCH 091/898] swiotlb-xen: implement xen_swiotlb_dma_mmap callback

This function creates userspace mapping for the DMA-coherent memory.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Oleksandr Dmytryshyn <oleksandr.dmytryshyn@globallogic.com>
Signed-off-by: Andrii Anisov <andrii_anisov@epam.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad@kernel.org>
---
 arch/arm/xen/mm.c         |  1 +
 drivers/xen/swiotlb-xen.c | 19 +++++++++++++++++++
 include/xen/swiotlb-xen.h |  5 +++++
 3 files changed, 25 insertions(+)

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index bd62d94f8ac5..cd1684e4e864 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -198,6 +198,7 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
 	.unmap_page = xen_swiotlb_unmap_page,
 	.dma_supported = xen_swiotlb_dma_supported,
 	.set_dma_mask = xen_swiotlb_set_dma_mask,
+	.mmap = xen_swiotlb_dma_mmap,
 };
 
 int __init xen_mm_init(void)
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f905d6eeb048..c7f61fc0572a 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -680,3 +680,22 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+	if (__generic_dma_ops(dev)->mmap)
+		return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr,
+						    dma_addr, size, attrs);
+#endif
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index a0083be5d529..a315c876aaa9 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -55,4 +55,9 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
 
 extern int
 xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
+
+extern int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs);
 #endif /* __LINUX_SWIOTLB_XEN_H */
-- 
GitLab


From 69369f52d28a34c84acb6f2a8a585e743441566a Mon Sep 17 00:00:00 2001
From: Andrii Anisov <andrii_anisov@epam.com>
Date: Tue, 7 Feb 2017 19:58:03 +0200
Subject: [PATCH 092/898] swiotlb-xen: implement xen_swiotlb_get_sgtable
 callback

Signed-off-by: Andrii Anisov <andrii_anisov@epam.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Konrad Rzeszutek Wilk <konrad@kernel.org>
---
 arch/arm/xen/mm.c         |  1 +
 drivers/xen/swiotlb-xen.c | 28 ++++++++++++++++++++++++++++
 include/xen/swiotlb-xen.h |  6 ++++++
 3 files changed, 35 insertions(+)

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index cd1684e4e864..76ea48a614e1 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -199,6 +199,7 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
 	.dma_supported = xen_swiotlb_dma_supported,
 	.set_dma_mask = xen_swiotlb_set_dma_mask,
 	.mmap = xen_swiotlb_dma_mmap,
+	.get_sgtable = xen_swiotlb_get_sgtable,
 };
 
 int __init xen_mm_init(void)
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index c7f61fc0572a..23e30b4e1fb6 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -699,3 +699,31 @@ xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);
+
+/*
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t handle, size_t size,
+			unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+	if (__generic_dma_ops(dev)->get_sgtable) {
+#if 0
+	/*
+	 * This check verifies that the page belongs to the current domain and
+	 * is not one mapped from another domain.
+	 * This check is for debug only, and should not go to production build
+	 */
+		unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
+		BUG_ON (!page_is_ram(bfn));
+#endif
+		return __generic_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
+							   handle, size, attrs);
+	}
+#endif
+	return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_get_sgtable);
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index a315c876aaa9..1f6d78f044b6 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -2,6 +2,7 @@
 #define __LINUX_SWIOTLB_XEN_H
 
 #include <linux/dma-direction.h>
+#include <linux/scatterlist.h>
 #include <linux/swiotlb.h>
 
 extern int xen_swiotlb_init(int verbose, bool early);
@@ -60,4 +61,9 @@ extern int
 xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		     unsigned long attrs);
+
+extern int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t handle, size_t size,
+			unsigned long attrs);
 #endif /* __LINUX_SWIOTLB_XEN_H */
-- 
GitLab


From f655e67ac8d797425abb0404d0878758f3f71c1a Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Thu, 16 Feb 2017 14:10:01 +0800
Subject: [PATCH 093/898] drm/i915/gvt: Fix check error on opregion.c

As we switched to memremap for opregion, shouldn't use any __iomem
for that, and move to use memcpy instead.

This fixed static check errors for:

  CHECK   drivers/gpu/drm/i915//gvt/opregion.c
  drivers/gpu/drm/i915//gvt/opregion.c:142:31: warning: incorrect type in argument 1 (different address spaces)
  drivers/gpu/drm/i915//gvt/opregion.c:142:31:    expected void *addr
  drivers/gpu/drm/i915//gvt/opregion.c:142:31:    got void [noderef] <asn:2>*opregion_va
  drivers/gpu/drm/i915//gvt/opregion.c:160:35: warning: incorrect type in assignment (different address spaces)
  drivers/gpu/drm/i915//gvt/opregion.c:160:35:    expected void [noderef] <asn:2>*opregion_va
  drivers/gpu/drm/i915//gvt/opregion.c:160:35:    got void *

Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gvt.h      | 2 +-
 drivers/gpu/drm/i915/gvt/opregion.c | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index e227caf5859e..5ee660077b0c 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -203,7 +203,7 @@ struct intel_gvt_firmware {
 };
 
 struct intel_gvt_opregion {
-	void __iomem *opregion_va;
+	void *opregion_va;
 	u32 opregion_pa;
 };
 
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index d9fb41ab7119..5d1caf9daba9 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -27,7 +27,6 @@
 
 static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa)
 {
-	void __iomem *host_va = vgpu->gvt->opregion.opregion_va;
 	u8 *buf;
 	int i;
 
@@ -43,8 +42,8 @@ static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa)
 	if (!vgpu_opregion(vgpu)->va)
 		return -ENOMEM;
 
-	memcpy_fromio(vgpu_opregion(vgpu)->va, host_va,
-			INTEL_GVT_OPREGION_SIZE);
+	memcpy(vgpu_opregion(vgpu)->va, vgpu->gvt->opregion.opregion_va,
+	       INTEL_GVT_OPREGION_SIZE);
 
 	for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++)
 		vgpu_opregion(vgpu)->gfn[i] = (gpa >> PAGE_SHIFT) + i;
-- 
GitLab


From fd64be636708d808852c4c8c1efce0a0a51c24c5 Mon Sep 17 00:00:00 2001
From: Min He <min.he@intel.com>
Date: Fri, 17 Feb 2017 15:02:36 +0800
Subject: [PATCH 094/898] drm/i915/gvt: introduced failsafe mode into vgpu

New failsafe mode is introduced, when we detect guest not supporting
GVT-g.
In failsafe mode, we will ignore all the MMIO and cfg space read/write
from guest.

This patch can fix the issue that when guest kernel or graphics driver
version is too low, there will be a lot of kernel traces in host.

V5: rebased onto latest gvt-staging
V4: changed coding style by Zhenyu and Ping's advice
V3: modified coding style and error messages according to Zhenyu's comment
V2: 1) implemented MMIO/GTT/WP pages read/write logic; 2) used a unified
function to enter failsafe mode

Signed-off-by: Min He <min.he@intel.com>
Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/cfg_space.c |  3 ++
 drivers/gpu/drm/i915/gvt/gvt.h       |  6 +++
 drivers/gpu/drm/i915/gvt/handlers.c  | 36 ++++++++++++++++
 drivers/gpu/drm/i915/gvt/mmio.c      | 62 ++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/gvt/vgpu.c      |  6 ++-
 5 files changed, 112 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 4a6a2ed65732..a77e050b85a3 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -237,6 +237,9 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset,
 {
 	int ret;
 
+	if (vgpu->failsafe)
+		return 0;
+
 	if (WARN_ON(bytes > 4))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 5ee660077b0c..48ef0771d772 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -143,6 +143,8 @@ struct intel_vgpu {
 	int id;
 	unsigned long handle; /* vGPU handle used by hypervisor MPT modules */
 	bool active;
+	bool pv_notified;
+	bool failsafe;
 	bool resetting;
 	void *sched_data;
 
@@ -449,6 +451,10 @@ struct intel_gvt_ops {
 };
 
 
+enum {
+	GVT_FAILSAFE_UNSUPPORTED_GUEST,
+};
+
 #include "mpt.h"
 
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 1d450627ff65..6f098bb110bd 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -150,10 +150,34 @@ static int render_mmio_to_ring_id(struct intel_gvt *gvt, unsigned int reg)
 #define fence_num_to_offset(num) \
 	(num * 8 + i915_mmio_reg_offset(FENCE_REG_GEN6_LO(0)))
 
+
+static void enter_failsafe_mode(struct intel_vgpu *vgpu, int reason)
+{
+	switch (reason) {
+	case GVT_FAILSAFE_UNSUPPORTED_GUEST:
+		pr_err("Detected your guest driver doesn't support GVT-g.\n");
+		break;
+	default:
+		break;
+	}
+	pr_err("Now vgpu %d will enter failsafe mode.\n", vgpu->id);
+	vgpu->failsafe = true;
+}
+
 static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 		unsigned int fence_num, void *p_data, unsigned int bytes)
 {
 	if (fence_num >= vgpu_fence_sz(vgpu)) {
+
+		/* When guest access oob fence regs without access
+		 * pv_info first, we treat guest not supporting GVT,
+		 * and we will let vgpu enter failsafe mode.
+		 */
+		if (!vgpu->pv_notified) {
+			enter_failsafe_mode(vgpu,
+					GVT_FAILSAFE_UNSUPPORTED_GUEST);
+			return -EINVAL;
+		}
 		gvt_err("vgpu%d: found oob fence register access\n",
 				vgpu->id);
 		gvt_err("vgpu%d: total fence num %d access fence num %d\n",
@@ -1001,6 +1025,7 @@ static int pvinfo_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 	if (invalid_read)
 		gvt_err("invalid pvinfo read: [%x:%x] = %x\n",
 				offset, bytes, *(u32 *)p_data);
+	vgpu->pv_notified = true;
 	return 0;
 }
 
@@ -1318,6 +1343,17 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	bool enable_execlist;
 
 	write_vreg(vgpu, offset, p_data, bytes);
+
+	/* when PPGTT mode enabled, we will check if guest has called
+	 * pvinfo, if not, we will treat this guest as non-gvtg-aware
+	 * guest, and stop emulating its cfg space, mmio, gtt, etc.
+	 */
+	if (((data & _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)) ||
+			(data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)))
+			&& !vgpu->pv_notified) {
+		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
+		return 0;
+	}
 	if ((data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE))
 			|| (data & _MASKED_BIT_DISABLE(GFX_RUN_LIST_ENABLE))) {
 		enable_execlist = !!(data & GFX_RUN_LIST_ENABLE);
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 4df078bc5d04..b2d72dad1537 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -57,6 +57,58 @@ int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa)
 	(reg >= gvt->device_info.gtt_start_offset \
 	 && reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt))
 
+static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
+		void *p_data, unsigned int bytes, bool read)
+{
+	struct intel_gvt *gvt = NULL;
+	void *pt = NULL;
+	unsigned int offset = 0;
+
+	if (!vgpu || !p_data)
+		return;
+
+	gvt = vgpu->gvt;
+	mutex_lock(&gvt->lock);
+	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
+	if (reg_is_mmio(gvt, offset)) {
+		if (read)
+			intel_vgpu_default_mmio_read(vgpu, offset, p_data,
+					bytes);
+		else
+			intel_vgpu_default_mmio_write(vgpu, offset, p_data,
+					bytes);
+	} else if (reg_is_gtt(gvt, offset) &&
+			vgpu->gtt.ggtt_mm->virtual_page_table) {
+		offset -= gvt->device_info.gtt_start_offset;
+		pt = vgpu->gtt.ggtt_mm->virtual_page_table + offset;
+		if (read)
+			memcpy(p_data, pt, bytes);
+		else
+			memcpy(pt, p_data, bytes);
+
+	} else if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
+		struct intel_vgpu_guest_page *gp;
+
+		/* Since we enter the failsafe mode early during guest boot,
+		 * guest may not have chance to set up its ppgtt table, so
+		 * there should not be any wp pages for guest. Keep the wp
+		 * related code here in case we need to handle it in furture.
+		 */
+		gp = intel_vgpu_find_guest_page(vgpu, pa >> PAGE_SHIFT);
+		if (gp) {
+			/* remove write protection to prevent furture traps */
+			intel_vgpu_clean_guest_page(vgpu, gp);
+			if (read)
+				intel_gvt_hypervisor_read_gpa(vgpu, pa,
+						p_data, bytes);
+			else
+				intel_gvt_hypervisor_write_gpa(vgpu, pa,
+						p_data, bytes);
+		}
+	}
+	mutex_unlock(&gvt->lock);
+}
+
 /**
  * intel_vgpu_emulate_mmio_read - emulate MMIO read
  * @vgpu: a vGPU
@@ -75,6 +127,11 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 	unsigned int offset = 0;
 	int ret = -EINVAL;
 
+
+	if (vgpu->failsafe) {
+		failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, true);
+		return 0;
+	}
 	mutex_lock(&gvt->lock);
 
 	if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
@@ -188,6 +245,11 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 	u32 old_vreg = 0, old_sreg = 0;
 	int ret = -EINVAL;
 
+	if (vgpu->failsafe) {
+		failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, false);
+		return 0;
+	}
+
 	mutex_lock(&gvt->lock);
 
 	if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 95a97aa0051e..dcfcce1dc00e 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -387,8 +387,12 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 		populate_pvinfo_page(vgpu);
 		intel_vgpu_reset_display(vgpu);
 
-		if (dmlr)
+		if (dmlr) {
 			intel_vgpu_reset_cfg_space(vgpu);
+			/* only reset the failsafe mode when dmlr reset */
+			vgpu->failsafe = false;
+			vgpu->pv_notified = false;
+		}
 	}
 
 	vgpu->resetting = false;
-- 
GitLab


From d1be371d4f4c12d11023c9fc795e5d460d960680 Mon Sep 17 00:00:00 2001
From: "Zhao, Xinda" <xinda.zhao@intel.com>
Date: Fri, 17 Feb 2017 14:38:33 +0800
Subject: [PATCH 095/898] drm/i915/gvt: handle fence reg access during GPU
 reset

Lots of reduntant log info will be printed out during GPU reset,
including accessing untracked mmio register and fence register,
variable disable_warn_untrack is added previously to handle the
situation, but the accessing of fence register is ignored in the
previously patch, so add it back.

Besides, set the variable disable_warn_untrack to the defalut value
after GPU reset is finished.

Signed-off-by: Zhao, Xinda <xinda.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 15 +++++++++------
 drivers/gpu/drm/i915/gvt/mmio.c     |  2 ++
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 6f098bb110bd..fd7e789a72c3 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -173,16 +173,19 @@ static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 		 * pv_info first, we treat guest not supporting GVT,
 		 * and we will let vgpu enter failsafe mode.
 		 */
-		if (!vgpu->pv_notified) {
+		if (!vgpu->pv_notified)
 			enter_failsafe_mode(vgpu,
 					GVT_FAILSAFE_UNSUPPORTED_GUEST);
-			return -EINVAL;
+
+		if (!vgpu->mmio.disable_warn_untrack) {
+			gvt_err("vgpu%d: found oob fence register access\n",
+					vgpu->id);
+			gvt_err("vgpu%d: total fence %d, access fence %d\n",
+					vgpu->id, vgpu_fence_sz(vgpu),
+					fence_num);
 		}
-		gvt_err("vgpu%d: found oob fence register access\n",
-				vgpu->id);
-		gvt_err("vgpu%d: total fence num %d access fence num %d\n",
-				vgpu->id, vgpu_fence_sz(vgpu), fence_num);
 		memset(p_data, 0, bytes);
+		return -EINVAL;
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index b2d72dad1537..99abb01fa9eb 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -384,6 +384,8 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu)
 
 	/* set the bit 0:2(Core C-State ) to C0 */
 	vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
+
+	vgpu->mmio.disable_warn_untrack = false;
 }
 
 /**
-- 
GitLab


From b8826e506ee58873725ec3a25a2a27fefd762574 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 18 Feb 2017 22:07:24 -0500
Subject: [PATCH 096/898] selftest for default_file_splice_read() infoleak

bug fixed in commit b9dc6f65bc5e ("fix a fencepost error in pipe_advance()")

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 tools/testing/selftests/Makefile                          | 1 +
 tools/testing/selftests/splice/Makefile                   | 8 ++++++++
 tools/testing/selftests/splice/default_file_splice_read.c | 8 ++++++++
 .../testing/selftests/splice/default_file_splice_read.sh  | 7 +++++++
 4 files changed, 24 insertions(+)
 create mode 100644 tools/testing/selftests/splice/Makefile
 create mode 100644 tools/testing/selftests/splice/default_file_splice_read.c
 create mode 100755 tools/testing/selftests/splice/default_file_splice_read.sh

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 71b05891a6a1..0e72f1d03c9e 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -24,6 +24,7 @@ TARGETS += ptrace
 TARGETS += seccomp
 TARGETS += sigaltstack
 TARGETS += size
+TARGETS += splice
 TARGETS += static_keys
 TARGETS += sync
 TARGETS += sysctl
diff --git a/tools/testing/selftests/splice/Makefile b/tools/testing/selftests/splice/Makefile
new file mode 100644
index 000000000000..de51f439d4a6
--- /dev/null
+++ b/tools/testing/selftests/splice/Makefile
@@ -0,0 +1,8 @@
+TEST_PROGS := default_file_splice_read.sh
+EXTRA := default_file_splice_read
+all: $(TEST_PROGS) $(EXTRA)
+
+include ../lib.mk
+
+clean:
+	rm -fr $(TEST_PROGS) $(EXTRA)
diff --git a/tools/testing/selftests/splice/default_file_splice_read.c b/tools/testing/selftests/splice/default_file_splice_read.c
new file mode 100644
index 000000000000..01dd6091554c
--- /dev/null
+++ b/tools/testing/selftests/splice/default_file_splice_read.c
@@ -0,0 +1,8 @@
+#define _GNU_SOURCE
+#include <fcntl.h>
+
+int main(int argc, char **argv)
+{
+        splice(0, 0, 1, 0, 1<<30, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/splice/default_file_splice_read.sh b/tools/testing/selftests/splice/default_file_splice_read.sh
new file mode 100755
index 000000000000..1ea2adeabc94
--- /dev/null
+++ b/tools/testing/selftests/splice/default_file_splice_read.sh
@@ -0,0 +1,7 @@
+#!/bin/sh
+n=`./default_file_splice_read </dev/null | wc -c`
+
+test "$n" = 0 && exit 0
+
+echo "default_file_splice_read broken: leaked $n"
+exit 1
-- 
GitLab


From eec11535ca3d3e2daa2c8f59fa8ce1963db98abd Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 18 Jan 2017 14:13:20 +0300
Subject: [PATCH 097/898] hfs: fix hfs_readdir()

I was looking through static analysis warnings and there is a bug here
that goes all the way back to the start of git.  Basically we're copying
the pointer and nearby garbage instead of the data the fd.key pointer is
pointing to.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Vyacheslav Dubeyko <slava@dubeyko.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/hfs/dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 5de5c48b418d..75b254280ff6 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -169,7 +169,7 @@ static int hfs_readdir(struct file *file, struct dir_context *ctx)
 	 * Can be done after the list insertion; exclusion with
 	 * hfs_delete_cat() is provided by directory lock.
 	 */
-	memcpy(&rd->key, &fd.key, sizeof(struct hfs_cat_key));
+	memcpy(&rd->key, &fd.key->cat, sizeof(struct hfs_cat_key));
 out:
 	hfs_find_exit(&fd);
 	return err;
-- 
GitLab


From 9a584bf9bf0a1c608f5ed5f5e63b074bbc81a322 Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Fri, 13 Jan 2017 20:53:21 +0530
Subject: [PATCH 098/898] target/iscsi: split iscsit_check_dataout_hdr()

Split iscsit_check_dataout_hdr() into two functions
1. __iscsit_check_dataout_hdr() - This function
   validates data out hdr.
2. iscsit_check_dataout_hdr() - This function finds
   iSCSI cmd using iscsit_find_cmd_from_itt_or_dump(),
   then it calls __iscsit_check_dataout_hdr() to
   validate iSCSI hdr.

This split is required to support Chelsio T6 iSCSI
DDP completion feature. T6 adapters reduce number of
completions to host by generating single completion
for all directly placed(DDP) iSCSI pdus in a sequence,
DDP completion contains iSCSI hdr of the last pdu in a
sequence.

On receiving DDP completion cxgbit driver will first
find iSCSI cmd using iscsit_find_cmd_from_itt_or_dump()
then updates cmd->write_data_done, cmd->next_burst_len,
cmd->data_sn and calls  __iscsit_check_dataout_hdr()
to validate iSCSI hdr.

(Move XRDSL check ahead of itt lookup / dump - nab)

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target.c      | 65 +++++++++++++++---------
 drivers/target/iscsi/iscsi_target_util.c |  1 +
 include/target/iscsi/iscsi_transport.h   | 11 +++-
 3 files changed, 50 insertions(+), 27 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index b4f1d1cbe521..2285988c209b 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1431,36 +1431,17 @@ static void iscsit_do_crypto_hash_buf(
 }
 
 int
-iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf,
-			  struct iscsi_cmd **out_cmd)
+__iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf,
+			   struct iscsi_cmd *cmd, u32 payload_length,
+			   bool *success)
 {
-	struct iscsi_data *hdr = (struct iscsi_data *)buf;
-	struct iscsi_cmd *cmd = NULL;
+	struct iscsi_data *hdr = buf;
 	struct se_cmd *se_cmd;
-	u32 payload_length = ntoh24(hdr->dlength);
 	int rc;
 
-	if (!payload_length) {
-		pr_warn("DataOUT payload is ZERO, ignoring.\n");
-		return 0;
-	}
-
 	/* iSCSI write */
 	atomic_long_add(payload_length, &conn->sess->rx_data_octets);
 
-	if (payload_length > conn->conn_ops->MaxXmitDataSegmentLength) {
-		pr_err("DataSegmentLength: %u is greater than"
-			" MaxXmitDataSegmentLength: %u\n", payload_length,
-			conn->conn_ops->MaxXmitDataSegmentLength);
-		return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
-					 buf);
-	}
-
-	cmd = iscsit_find_cmd_from_itt_or_dump(conn, hdr->itt,
-			payload_length);
-	if (!cmd)
-		return 0;
-
 	pr_debug("Got DataOut ITT: 0x%08x, TTT: 0x%08x,"
 		" DataSN: 0x%08x, Offset: %u, Length: %u, CID: %hu\n",
 		hdr->itt, hdr->ttt, hdr->datasn, ntohl(hdr->offset),
@@ -1553,10 +1534,44 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf,
 		return 0;
 	else if (rc == DATAOUT_CANNOT_RECOVER)
 		return -1;
-
-	*out_cmd = cmd;
+	*success = true;
 	return 0;
 }
+EXPORT_SYMBOL(__iscsit_check_dataout_hdr);
+
+int
+iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf,
+			 struct iscsi_cmd **out_cmd)
+{
+	struct iscsi_data *hdr = buf;
+	struct iscsi_cmd *cmd;
+	u32 payload_length = ntoh24(hdr->dlength);
+	int rc;
+	bool success = false;
+
+	if (!payload_length) {
+		pr_warn_ratelimited("DataOUT payload is ZERO, ignoring.\n");
+		return 0;
+	}
+
+	if (payload_length > conn->conn_ops->MaxXmitDataSegmentLength) {
+		pr_err_ratelimited("DataSegmentLength: %u is greater than"
+			" MaxXmitDataSegmentLength: %u\n", payload_length,
+			conn->conn_ops->MaxXmitDataSegmentLength);
+		return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, buf);
+	}
+
+	cmd = iscsit_find_cmd_from_itt_or_dump(conn, hdr->itt, payload_length);
+	if (!cmd)
+		return 0;
+
+	rc = __iscsit_check_dataout_hdr(conn, buf, cmd, payload_length, &success);
+
+	if (success)
+		*out_cmd = cmd;
+
+	return rc;
+}
 EXPORT_SYMBOL(iscsit_check_dataout_hdr);
 
 static int
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index b5a1b4ccba12..f46eadffec07 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -417,6 +417,7 @@ struct iscsi_cmd *iscsit_find_cmd_from_itt_or_dump(
 
 	return NULL;
 }
+EXPORT_SYMBOL(iscsit_find_cmd_from_itt_or_dump);
 
 struct iscsi_cmd *iscsit_find_cmd_from_ttt(
 	struct iscsi_conn *conn,
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index 1277e9ba0318..ff1a4f4cd66d 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -55,8 +55,12 @@ extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *,
 extern void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *);
 extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *,
 				struct iscsi_scsi_req *);
-extern int iscsit_check_dataout_hdr(struct iscsi_conn *, unsigned char *,
-				struct iscsi_cmd **);
+extern int
+__iscsit_check_dataout_hdr(struct iscsi_conn *, void *,
+			   struct iscsi_cmd *, u32, bool *);
+extern int
+iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf,
+			 struct iscsi_cmd **out_cmd);
 extern int iscsit_check_dataout_payload(struct iscsi_cmd *, struct iscsi_data *,
 				bool);
 extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsi_cmd *,
@@ -125,6 +129,9 @@ extern void iscsit_release_cmd(struct iscsi_cmd *);
 extern void iscsit_free_cmd(struct iscsi_cmd *, bool);
 extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *,
 					      struct iscsi_conn *, u8);
+extern struct iscsi_cmd *
+iscsit_find_cmd_from_itt_or_dump(struct iscsi_conn *conn,
+				 itt_t init_task_tag, u32 length);
 
 /*
  * From iscsi_target_nego.c
-- 
GitLab


From 3da1110fd1ac3e11208f12c966c6de7a2c306b9d Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Fri, 13 Jan 2017 20:53:22 +0530
Subject: [PATCH 099/898] target/cxgbit: use cxgb4_tp_smt_idx() to get smt idx

cxgb4_tp_smt_idx() returns smt idx for T4,T5,T6 adapters.

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/cxgbit/cxgbit_cm.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
index 35aaa36e9af5..845a7de39b9c 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -872,7 +872,8 @@ cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip,
 			goto out;
 		csk->mtu = ndev->mtu;
 		csk->tx_chan = cxgb4_port_chan(ndev);
-		csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1;
+		csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi.adapter_type,
+						 cxgb4_port_viid(ndev));
 		step = cdev->lldi.ntxq /
 			cdev->lldi.nchan;
 		csk->txq_idx = cxgb4_port_idx(ndev) * step;
@@ -907,7 +908,8 @@ cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip,
 		port_id = cxgb4_port_idx(ndev);
 		csk->mtu = dst_mtu(dst);
 		csk->tx_chan = cxgb4_port_chan(ndev);
-		csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1;
+		csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi.adapter_type,
+						 cxgb4_port_viid(ndev));
 		step = cdev->lldi.ntxq /
 			cdev->lldi.nports;
 		csk->txq_idx = (port_id * step) +
-- 
GitLab


From d88b504e413e7d1471562ff9c3311dbf983e0291 Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Fri, 13 Jan 2017 20:53:23 +0530
Subject: [PATCH 100/898] target/cxgbit: Use T6 specific macros to get ETH/IP
 hdr len

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/cxgbit/cxgbit_cm.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
index 845a7de39b9c..b26c85a65b80 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -1068,6 +1068,7 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req)
 	struct sk_buff *skb;
 	const struct tcphdr *tcph;
 	struct cpl_t5_pass_accept_rpl *rpl5;
+	struct cxgb4_lld_info *lldi = &csk->com.cdev->lldi;
 	unsigned int len = roundup(sizeof(*rpl5), 16);
 	unsigned int mtu_idx;
 	u64 opt0;
@@ -1121,8 +1122,13 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req)
 		opt2 |= WND_SCALE_EN_F;
 
 	hlen = ntohl(req->hdr_len);
-	tcph = (const void *)(req + 1) + ETH_HDR_LEN_G(hlen) +
-		IP_HDR_LEN_G(hlen);
+
+	if (is_t5(lldi->adapter_type))
+		tcph = (struct tcphdr *)((u8 *)(req + 1) +
+		       ETH_HDR_LEN_G(hlen) + IP_HDR_LEN_G(hlen));
+	else
+		tcph = (struct tcphdr *)((u8 *)(req + 1) +
+		       T6_ETH_HDR_LEN_G(hlen) + T6_IP_HDR_LEN_G(hlen));
 
 	if (tcph->ece && tcph->cwr)
 		opt2 |= CCTRL_ECN_V(1);
-- 
GitLab


From 5248788ec300f7ee738502bfc466dbb9b625247e Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Fri, 13 Jan 2017 20:53:24 +0530
Subject: [PATCH 101/898] target/cxgbit: Enable DDP for T6 only if data
 sequence and pdu are in order

Enable DDP for T6 only if DataSequenceInOrder=YES and
DataPDUInOrder=YES to ensure inorder delivery of iSCSI pdus.

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/cxgbit/cxgbit_target.c | 86 +++++++++++++++------
 1 file changed, 61 insertions(+), 25 deletions(-)

diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
index 8ae399dfe84f..4780fae2a1d1 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_target.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -653,26 +653,6 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk)
 	u32 max_npdu, max_iso_npdu;
 
 	if (conn->login->leading_connection) {
-		param = iscsi_find_param_from_key(DATASEQUENCEINORDER,
-						  conn->param_list);
-		if (!param) {
-			pr_err("param not found key %s\n", DATASEQUENCEINORDER);
-			return -1;
-		}
-
-		if (strcmp(param->value, YES))
-			return 0;
-
-		param = iscsi_find_param_from_key(DATAPDUINORDER,
-						  conn->param_list);
-		if (!param) {
-			pr_err("param not found key %s\n", DATAPDUINORDER);
-			return -1;
-		}
-
-		if (strcmp(param->value, YES))
-			return 0;
-
 		param = iscsi_find_param_from_key(MAXBURSTLENGTH,
 						  conn->param_list);
 		if (!param) {
@@ -683,11 +663,6 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk)
 		if (kstrtou32(param->value, 0, &mbl) < 0)
 			return -1;
 	} else {
-		if (!conn->sess->sess_ops->DataSequenceInOrder)
-			return 0;
-		if (!conn->sess->sess_ops->DataPDUInOrder)
-			return 0;
-
 		mbl = conn->sess->sess_ops->MaxBurstLength;
 	}
 
@@ -706,6 +681,53 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk)
 	return 0;
 }
 
+/*
+ * cxgbit_seq_pdu_inorder()
+ * @csk: pointer to cxgbit socket structure
+ *
+ * This function checks whether data sequence and data
+ * pdu are in order.
+ *
+ * Return: returns -1 on error, 0 if data sequence and
+ * data pdu are in order, 1 if data sequence or data pdu
+ * is not in order.
+ */
+static int cxgbit_seq_pdu_inorder(struct cxgbit_sock *csk)
+{
+	struct iscsi_conn *conn = csk->conn;
+	struct iscsi_param *param;
+
+	if (conn->login->leading_connection) {
+		param = iscsi_find_param_from_key(DATASEQUENCEINORDER,
+						  conn->param_list);
+		if (!param) {
+			pr_err("param not found key %s\n", DATASEQUENCEINORDER);
+			return -1;
+		}
+
+		if (strcmp(param->value, YES))
+			return 1;
+
+		param = iscsi_find_param_from_key(DATAPDUINORDER,
+						  conn->param_list);
+		if (!param) {
+			pr_err("param not found key %s\n", DATAPDUINORDER);
+			return -1;
+		}
+
+		if (strcmp(param->value, YES))
+			return 1;
+
+	} else {
+		if (!conn->sess->sess_ops->DataSequenceInOrder)
+			return 1;
+		if (!conn->sess->sess_ops->DataPDUInOrder)
+			return 1;
+	}
+
+	return 0;
+}
+
 static int cxgbit_set_params(struct iscsi_conn *conn)
 {
 	struct cxgbit_sock *csk = conn->context;
@@ -732,11 +754,24 @@ static int cxgbit_set_params(struct iscsi_conn *conn)
 	}
 
 	if (!erl) {
+		int ret;
+
+		ret = cxgbit_seq_pdu_inorder(csk);
+		if (ret < 0) {
+			return -1;
+		} else if (ret > 0) {
+			if (is_t5(cdev->lldi.adapter_type))
+				goto enable_ddp;
+			else
+				goto enable_digest;
+		}
+
 		if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) {
 			if (cxgbit_set_iso_npdu(csk))
 				return -1;
 		}
 
+enable_ddp:
 		if (test_bit(CDEV_DDP_ENABLE, &cdev->flags)) {
 			if (cxgbit_setup_conn_pgidx(csk,
 						    ppm->tformat.pgsz_idx_dflt))
@@ -745,6 +780,7 @@ static int cxgbit_set_params(struct iscsi_conn *conn)
 		}
 	}
 
+enable_digest:
 	if (cxgbit_set_digest(csk))
 		return -1;
 
-- 
GitLab


From 79e57cfe00f40d509e2d007a5662db26cdbc74db Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Fri, 13 Jan 2017 20:53:25 +0530
Subject: [PATCH 102/898] target/cxgbit: add T6 iSCSI DDP completion feature

Chelsio T6 adapters reduce number of completion
to host by generating single completion for all
directly placed(DDP) iSCSI pdus in a sequence,
completion contains iSCSI hdr of the last pdu
in a sequence.

On receiving DDP completion cxgbit driver finds
iSCSI cmd using iscsit_find_cmd_from_itt_or_dump(),
then updates cmd->write_data_done, cmd->next_burst_len,
cmd->data_sn and calls __iscsit_check_dataout_hdr()
to validate iSCSI hdr.

(Update __iscsit_check_dataout_hdr parameter usage - nab)

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/cxgbit/cxgbit_cm.c     |  3 +
 drivers/target/iscsi/cxgbit/cxgbit_lro.h    |  5 +-
 drivers/target/iscsi/cxgbit/cxgbit_main.c   | 67 ++++++++++++-----
 drivers/target/iscsi/cxgbit/cxgbit_target.c | 81 +++++++++++++++------
 4 files changed, 113 insertions(+), 43 deletions(-)

diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
index b26c85a65b80..37a05185dcbe 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -1114,6 +1114,9 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req)
 	opt2 = RX_CHANNEL_V(0) |
 		RSS_QUEUE_VALID_F | RSS_QUEUE_V(csk->rss_qid);
 
+	if (!is_t5(lldi->adapter_type))
+		opt2 |= RX_FC_DISABLE_F;
+
 	if (req->tcpopt.tstamp)
 		opt2 |= TSTAMPS_EN_F;
 	if (req->tcpopt.sack)
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_lro.h b/drivers/target/iscsi/cxgbit/cxgbit_lro.h
index 28c11bd1b930..dcaed3a1d23f 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_lro.h
+++ b/drivers/target/iscsi/cxgbit/cxgbit_lro.h
@@ -31,8 +31,9 @@ enum cxgbit_pducb_flags {
 	PDUCBF_RX_DATA		= (1 << 1), /* received pdu payload */
 	PDUCBF_RX_STATUS	= (1 << 2), /* received ddp status */
 	PDUCBF_RX_DATA_DDPD	= (1 << 3), /* pdu payload ddp'd */
-	PDUCBF_RX_HCRC_ERR	= (1 << 4), /* header digest error */
-	PDUCBF_RX_DCRC_ERR	= (1 << 5), /* data digest error */
+	PDUCBF_RX_DDP_CMP	= (1 << 4), /* ddp completion */
+	PDUCBF_RX_HCRC_ERR	= (1 << 5), /* header digest error */
+	PDUCBF_RX_DCRC_ERR	= (1 << 6), /* data digest error */
 };
 
 struct cxgbit_lro_pdu_cb {
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c
index 6531aaac2b96..4fd775ace541 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_main.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c
@@ -165,29 +165,24 @@ static int cxgbit_uld_state_change(void *handle, enum cxgb4_state state)
 }
 
 static void
-cxgbit_proc_ddp_status(unsigned int tid, struct cpl_rx_data_ddp *cpl,
-		       struct cxgbit_lro_pdu_cb *pdu_cb)
+cxgbit_process_ddpvld(struct cxgbit_sock *csk, struct cxgbit_lro_pdu_cb *pdu_cb,
+		      u32 ddpvld)
 {
-	unsigned int status = ntohl(cpl->ddpvld);
 
-	pdu_cb->flags |= PDUCBF_RX_STATUS;
-	pdu_cb->ddigest = ntohl(cpl->ulp_crc);
-	pdu_cb->pdulen = ntohs(cpl->len);
-
-	if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT)) {
-		pr_info("tid 0x%x, status 0x%x, hcrc bad.\n", tid, status);
+	if (ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT)) {
+		pr_info("tid 0x%x, status 0x%x, hcrc bad.\n", csk->tid, ddpvld);
 		pdu_cb->flags |= PDUCBF_RX_HCRC_ERR;
 	}
 
-	if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT)) {
-		pr_info("tid 0x%x, status 0x%x, dcrc bad.\n", tid, status);
+	if (ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT)) {
+		pr_info("tid 0x%x, status 0x%x, dcrc bad.\n", csk->tid, ddpvld);
 		pdu_cb->flags |= PDUCBF_RX_DCRC_ERR;
 	}
 
-	if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT))
-		pr_info("tid 0x%x, status 0x%x, pad bad.\n", tid, status);
+	if (ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT))
+		pr_info("tid 0x%x, status 0x%x, pad bad.\n", csk->tid, ddpvld);
 
-	if ((status & (1 << CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT)) &&
+	if ((ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT)) &&
 	    (!(pdu_cb->flags & PDUCBF_RX_DATA))) {
 		pdu_cb->flags |= PDUCBF_RX_DATA_DDPD;
 	}
@@ -201,13 +196,17 @@ cxgbit_lro_add_packet_rsp(struct sk_buff *skb, u8 op, const __be64 *rsp)
 						lro_cb->pdu_idx);
 	struct cpl_rx_iscsi_ddp *cpl = (struct cpl_rx_iscsi_ddp *)(rsp + 1);
 
-	cxgbit_proc_ddp_status(lro_cb->csk->tid, cpl, pdu_cb);
+	cxgbit_process_ddpvld(lro_cb->csk, pdu_cb, be32_to_cpu(cpl->ddpvld));
+
+	pdu_cb->flags |= PDUCBF_RX_STATUS;
+	pdu_cb->ddigest = ntohl(cpl->ulp_crc);
+	pdu_cb->pdulen = ntohs(cpl->len);
 
 	if (pdu_cb->flags & PDUCBF_RX_HDR)
 		pdu_cb->complete = true;
 
-	lro_cb->complete = true;
 	lro_cb->pdu_totallen += pdu_cb->pdulen;
+	lro_cb->complete = true;
 	lro_cb->pdu_idx++;
 }
 
@@ -257,7 +256,7 @@ cxgbit_lro_add_packet_gl(struct sk_buff *skb, u8 op, const struct pkt_gl *gl)
 			cxgbit_skcb_flags(skb) = 0;
 
 		lro_cb->complete = false;
-	} else {
+	} else if (op == CPL_ISCSI_DATA) {
 		struct cpl_iscsi_data *cpl = (struct cpl_iscsi_data *)gl->va;
 
 		offset = sizeof(struct cpl_iscsi_data);
@@ -267,6 +266,36 @@ cxgbit_lro_add_packet_gl(struct sk_buff *skb, u8 op, const struct pkt_gl *gl)
 		pdu_cb->doffset = lro_cb->offset;
 		pdu_cb->nr_dfrags = gl->nfrags;
 		pdu_cb->dfrag_idx = skb_shinfo(skb)->nr_frags;
+		lro_cb->complete = false;
+	} else {
+		struct cpl_rx_iscsi_cmp *cpl;
+
+		cpl = (struct cpl_rx_iscsi_cmp *)gl->va;
+		offset = sizeof(struct cpl_rx_iscsi_cmp);
+		pdu_cb->flags |= (PDUCBF_RX_HDR | PDUCBF_RX_STATUS);
+		len = be16_to_cpu(cpl->len);
+		pdu_cb->hdr = gl->va + offset;
+		pdu_cb->hlen = len;
+		pdu_cb->hfrag_idx = skb_shinfo(skb)->nr_frags;
+		pdu_cb->ddigest = be32_to_cpu(cpl->ulp_crc);
+		pdu_cb->pdulen = ntohs(cpl->len);
+
+		if (unlikely(gl->nfrags > 1))
+			cxgbit_skcb_flags(skb) = 0;
+
+		cxgbit_process_ddpvld(lro_cb->csk, pdu_cb,
+				      be32_to_cpu(cpl->ddpvld));
+
+		if (pdu_cb->flags & PDUCBF_RX_DATA_DDPD) {
+			pdu_cb->flags |= PDUCBF_RX_DDP_CMP;
+			pdu_cb->complete = true;
+		} else if (pdu_cb->flags & PDUCBF_RX_DATA) {
+			pdu_cb->complete = true;
+		}
+
+		lro_cb->pdu_totallen += pdu_cb->hlen + pdu_cb->dlen;
+		lro_cb->complete = true;
+		lro_cb->pdu_idx++;
 	}
 
 	cxgbit_copy_frags(skb, gl, offset);
@@ -413,6 +442,7 @@ cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp,
 	switch (op) {
 	case CPL_ISCSI_HDR:
 	case CPL_ISCSI_DATA:
+	case CPL_RX_ISCSI_CMP:
 	case CPL_RX_ISCSI_DDP:
 	case CPL_FW4_ACK:
 		lro_flush = false;
@@ -459,7 +489,8 @@ cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp,
 			return 0;
 		}
 
-		if (op == CPL_ISCSI_HDR || op == CPL_ISCSI_DATA) {
+		if ((op == CPL_ISCSI_HDR) || (op == CPL_ISCSI_DATA) ||
+		    (op == CPL_RX_ISCSI_CMP)) {
 			if (!cxgbit_lro_receive(csk, op, rsp, gl, lro_mgr,
 						napi))
 				return 0;
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
index 4780fae2a1d1..2714e5901d18 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_target.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -1021,11 +1021,36 @@ static int cxgbit_handle_iscsi_dataout(struct cxgbit_sock *csk)
 	int rc, sg_nents, sg_off;
 	bool dcrc_err = false;
 
-	rc = iscsit_check_dataout_hdr(conn, (unsigned char *)hdr, &cmd);
-	if (rc < 0)
-		return rc;
-	else if (!cmd)
-		return 0;
+	if (pdu_cb->flags & PDUCBF_RX_DDP_CMP) {
+		u32 offset = be32_to_cpu(hdr->offset);
+		u32 ddp_data_len;
+		u32 payload_length = ntoh24(hdr->dlength);
+		bool success = false;
+
+		cmd = iscsit_find_cmd_from_itt_or_dump(conn, hdr->itt, 0);
+		if (!cmd)
+			return 0;
+
+		ddp_data_len = offset - cmd->write_data_done;
+		atomic_long_add(ddp_data_len, &conn->sess->rx_data_octets);
+
+		cmd->write_data_done = offset;
+		cmd->next_burst_len = ddp_data_len;
+		cmd->data_sn = be32_to_cpu(hdr->datasn);
+
+		rc = __iscsit_check_dataout_hdr(conn, (unsigned char *)hdr,
+						cmd, payload_length, &success);
+		if (rc < 0)
+			return rc;
+		else if (!success)
+			return 0;
+	} else {
+		rc = iscsit_check_dataout_hdr(conn, (unsigned char *)hdr, &cmd);
+		if (rc < 0)
+			return rc;
+		else if (!cmd)
+			return 0;
+	}
 
 	if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) {
 		pr_err("ITT: 0x%08x, Offset: %u, Length: %u,"
@@ -1389,6 +1414,9 @@ static void cxgbit_lro_hskb_reset(struct cxgbit_sock *csk)
 	for (i = 0; i < ssi->nr_frags; i++)
 		put_page(skb_frag_page(&ssi->frags[i]));
 	ssi->nr_frags = 0;
+	skb->data_len = 0;
+	skb->truesize -= skb->len;
+	skb->len = 0;
 }
 
 static void
@@ -1402,39 +1430,42 @@ cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx)
 	unsigned int len = 0;
 
 	if (pdu_cb->flags & PDUCBF_RX_HDR) {
-		hpdu_cb->flags = pdu_cb->flags;
+		u8 hfrag_idx = hssi->nr_frags;
+
+		hpdu_cb->flags |= pdu_cb->flags;
 		hpdu_cb->seq = pdu_cb->seq;
 		hpdu_cb->hdr = pdu_cb->hdr;
 		hpdu_cb->hlen = pdu_cb->hlen;
 
-		memcpy(&hssi->frags[0], &ssi->frags[pdu_cb->hfrag_idx],
+		memcpy(&hssi->frags[hfrag_idx], &ssi->frags[pdu_cb->hfrag_idx],
 		       sizeof(skb_frag_t));
 
-		get_page(skb_frag_page(&hssi->frags[0]));
-		hssi->nr_frags = 1;
-		hpdu_cb->frags = 1;
-		hpdu_cb->hfrag_idx = 0;
+		get_page(skb_frag_page(&hssi->frags[hfrag_idx]));
+		hssi->nr_frags++;
+		hpdu_cb->frags++;
+		hpdu_cb->hfrag_idx = hfrag_idx;
 
-		len = hssi->frags[0].size;
-		hskb->len = len;
-		hskb->data_len = len;
-		hskb->truesize = len;
+		len = hssi->frags[hfrag_idx].size;
+		hskb->len += len;
+		hskb->data_len += len;
+		hskb->truesize += len;
 	}
 
 	if (pdu_cb->flags & PDUCBF_RX_DATA) {
-		u8 hfrag_idx = 1, i;
+		u8 dfrag_idx = hssi->nr_frags, i;
 
 		hpdu_cb->flags |= pdu_cb->flags;
+		hpdu_cb->dfrag_idx = dfrag_idx;
 
 		len = 0;
-		for (i = 0; i < pdu_cb->nr_dfrags; hfrag_idx++, i++) {
-			memcpy(&hssi->frags[hfrag_idx],
+		for (i = 0; i < pdu_cb->nr_dfrags; dfrag_idx++, i++) {
+			memcpy(&hssi->frags[dfrag_idx],
 			       &ssi->frags[pdu_cb->dfrag_idx + i],
 			       sizeof(skb_frag_t));
 
-			get_page(skb_frag_page(&hssi->frags[hfrag_idx]));
+			get_page(skb_frag_page(&hssi->frags[dfrag_idx]));
 
-			len += hssi->frags[hfrag_idx].size;
+			len += hssi->frags[dfrag_idx].size;
 
 			hssi->nr_frags++;
 			hpdu_cb->frags++;
@@ -1443,7 +1474,6 @@ cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx)
 		hpdu_cb->dlen = pdu_cb->dlen;
 		hpdu_cb->doffset = hpdu_cb->hlen;
 		hpdu_cb->nr_dfrags = pdu_cb->nr_dfrags;
-		hpdu_cb->dfrag_idx = 1;
 		hskb->len += len;
 		hskb->data_len += len;
 		hskb->truesize += len;
@@ -1528,10 +1558,15 @@ static int cxgbit_rx_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
 
 static int cxgbit_rx_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
 {
+	struct cxgb4_lld_info *lldi = &csk->com.cdev->lldi;
 	int ret = -1;
 
-	if (likely(cxgbit_skcb_flags(skb) & SKCBF_RX_LRO))
-		ret = cxgbit_rx_lro_skb(csk, skb);
+	if (likely(cxgbit_skcb_flags(skb) & SKCBF_RX_LRO)) {
+		if (is_t5(lldi->adapter_type))
+			ret = cxgbit_rx_lro_skb(csk, skb);
+		else
+			ret = cxgbit_process_lro_skb(csk, skb);
+	}
 
 	__kfree_skb(skb);
 	return ret;
-- 
GitLab


From 4d65491c269729a1e3b375c45e73213f49103d33 Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Fri, 20 Jan 2017 16:44:33 +0530
Subject: [PATCH 103/898] target/iscsi: Fix unsolicited data seq_end_offset
 calculation

In case of unsolicited data for the first sequence
seq_end_offset must be set to minimum of total data length
and FirstBurstLength, so do not add cmd->write_data_done
to the min of total data length and FirstBurstLength.

This patch avoids that with ImmediateData=Yes, InitialR2T=No,
MaxXmitDataSegmentLength < FirstBurstLength that a WRITE command
with IO size above FirstBurstLength triggers sequence error
messages, for example

Set following parameters on target (linux-4.8.12)
ImmediateData = Yes
InitialR2T = No
MaxXmitDataSegmentLength = 8k
FirstBurstLength = 64k

Log in from Open iSCSI initiator and execute
dd if=/dev/zero of=/dev/sdb bs=128k count=1 oflag=direct

Error messages on target
Command ITT: 0x00000035 with Offset: 65536, Length: 8192 outside
of Sequence 73728:131072 while DataSequenceInOrder=Yes.
Command ITT: 0x00000035, received DataSN: 0x00000001 higher than
expected 0x00000000.
Unable to perform within-command recovery while ERL=0.

Signed-off-by: Varun Prakash <varun@chelsio.com>
[ bvanassche: Use min() instead of open-coding it / edited patch description ]
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target_erl0.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index b54e72c7ab0f..a8bcbc43b047 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -44,10 +44,8 @@ void iscsit_set_dataout_sequence_values(
 	 */
 	if (cmd->unsolicited_data) {
 		cmd->seq_start_offset = cmd->write_data_done;
-		cmd->seq_end_offset = (cmd->write_data_done +
-			((cmd->se_cmd.data_length >
-			  conn->sess->sess_ops->FirstBurstLength) ?
-			 conn->sess->sess_ops->FirstBurstLength : cmd->se_cmd.data_length));
+		cmd->seq_end_offset = min(cmd->se_cmd.data_length,
+					conn->sess->sess_ops->FirstBurstLength);
 		return;
 	}
 
-- 
GitLab


From 6cb3216a7863fd13fb125f0867fce55c2bbd8c8e Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Mon, 13 Feb 2017 12:18:29 -0800
Subject: [PATCH 104/898] qla2xxx: Fix a warning reported by the "smatch"
 static checker

Fix the following warning reported by the "smatch" static checker:

drivers/scsi/qla2xxx/qla_init.c:3910 qla2x00_alloc_fcport()
warn: use 'flags' here instead of GFP_XXX?

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/scsi/qla2xxx/qla_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index f65431480833..ac579fc5f202 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -3909,7 +3909,7 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags)
 
 	fcport->ct_desc.ct_sns = dma_alloc_coherent(&vha->hw->pdev->dev,
 		sizeof(struct ct_sns_pkt), &fcport->ct_desc.ct_sns_dma,
-			GFP_ATOMIC);
+		flags);
 	fcport->disc_state = DSC_DELETED;
 	fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
 	fcport->deleted = QLA_SESS_DELETED;
-- 
GitLab


From 0ab8ac6f504d61b59856bd34e62bbfd60edd2bb0 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 13 Jan 2017 04:47:48 -0600
Subject: [PATCH 105/898] target: export protocol identifier

I think the transport statistics device file was supposed
to show scsiTransportProtocolType. It instead shows the
fabric name which is normally closer to the driver name.

I was thinking I cannot change from fabric name to protocol
type name incase people are expecting the driver name, so
this patch adds another file proto_id that exports the SCSI
protocol identifier ID.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_stat.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index 1a39033d2bff..be380e4acfcd 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -795,16 +795,34 @@ static ssize_t target_stat_transport_dev_name_show(struct config_item *item,
 	return ret;
 }
 
+static ssize_t target_stat_transport_proto_id_show(struct config_item *item,
+		char *page)
+{
+	struct se_lun *lun = to_transport_stat(item);
+	struct se_device *dev;
+	struct se_portal_group *tpg = lun->lun_tpg;
+	ssize_t ret = -ENODEV;
+
+	rcu_read_lock();
+	dev = rcu_dereference(lun->lun_se_dev);
+	if (dev)
+		ret = snprintf(page, PAGE_SIZE, "%u\n", tpg->proto_id);
+	rcu_read_unlock();
+	return ret;
+}
+
 CONFIGFS_ATTR_RO(target_stat_transport_, inst);
 CONFIGFS_ATTR_RO(target_stat_transport_, device);
 CONFIGFS_ATTR_RO(target_stat_transport_, indx);
 CONFIGFS_ATTR_RO(target_stat_transport_, dev_name);
+CONFIGFS_ATTR_RO(target_stat_transport_, proto_id);
 
 static struct configfs_attribute *target_stat_scsi_transport_attrs[] = {
 	&target_stat_transport_attr_inst,
 	&target_stat_transport_attr_device,
 	&target_stat_transport_attr_indx,
 	&target_stat_transport_attr_dev_name,
+	&target_stat_transport_attr_proto_id,
 	NULL,
 };
 
-- 
GitLab


From 762b6f00a995863afa274d6b5ffa3880dac1714b Mon Sep 17 00:00:00 2001
From: "Dmitry V. Levin" <ldv@altlinux.org>
Date: Wed, 15 Feb 2017 23:04:54 +0300
Subject: [PATCH 106/898] uapi: fix linux/target_core_user.h userspace
 compilation errors

Consistently use types from linux/types.h to fix the following
linux/target_core_user.h userspace compilation errors:

/usr/include/linux/target_core_user.h:108:4: error: unknown type name 'uint32_t'
    uint32_t iov_cnt;
/usr/include/linux/target_core_user.h:109:4: error: unknown type name 'uint32_t'
    uint32_t iov_bidi_cnt;
/usr/include/linux/target_core_user.h:110:4: error: unknown type name 'uint32_t'
    uint32_t iov_dif_cnt;
/usr/include/linux/target_core_user.h:111:4: error: unknown type name 'uint64_t'
    uint64_t cdb_off;
/usr/include/linux/target_core_user.h:112:4: error: unknown type name 'uint64_t'
    uint64_t __pad1;
/usr/include/linux/target_core_user.h:113:4: error: unknown type name 'uint64_t'
    uint64_t __pad2;
/usr/include/linux/target_core_user.h:117:4: error: unknown type name 'uint8_t'
    uint8_t scsi_status;
/usr/include/linux/target_core_user.h:118:4: error: unknown type name 'uint8_t'
    uint8_t __pad1;
/usr/include/linux/target_core_user.h:119:4: error: unknown type name 'uint16_t'
    uint16_t __pad2;
/usr/include/linux/target_core_user.h:120:4: error: unknown type name 'uint32_t'
    uint32_t __pad3;

Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 include/uapi/linux/target_core_user.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index c506cddb8165..af17b4154ef6 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -105,26 +105,26 @@ struct tcmu_cmd_entry {
 
 	union {
 		struct {
-			uint32_t iov_cnt;
-			uint32_t iov_bidi_cnt;
-			uint32_t iov_dif_cnt;
-			uint64_t cdb_off;
-			uint64_t __pad1;
-			uint64_t __pad2;
+			__u32 iov_cnt;
+			__u32 iov_bidi_cnt;
+			__u32 iov_dif_cnt;
+			__u64 cdb_off;
+			__u64 __pad1;
+			__u64 __pad2;
 			struct iovec iov[0];
 		} req;
 		struct {
-			uint8_t scsi_status;
-			uint8_t __pad1;
-			uint16_t __pad2;
-			uint32_t __pad3;
+			__u8 scsi_status;
+			__u8 __pad1;
+			__u16 __pad2;
+			__u32 __pad3;
 			char sense_buffer[TCMU_SENSE_BUFFERSIZE];
 		} rsp;
 	};
 
 } __packed;
 
-#define TCMU_OP_ALIGN_SIZE sizeof(uint64_t)
+#define TCMU_OP_ALIGN_SIZE sizeof(__u64)
 
 enum tcmu_genl_cmd {
 	TCMU_CMD_UNSPEC,
-- 
GitLab


From 7687a7a4435f4b32d8e775a7b6b25aea3a25d25a Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 20 Feb 2017 16:51:23 +0100
Subject: [PATCH 107/898] vfs: extract common parts of
 {compat_,}do_readv_writev()

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/read_write.c | 80 ++++++++++++++++++-------------------------------
 1 file changed, 29 insertions(+), 51 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 820a3f06c46a..12a216021f87 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -834,25 +834,15 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 	return ret;
 }
 
-static ssize_t do_readv_writev(int type, struct file *file,
-			       const struct iovec __user * uvector,
-			       unsigned long nr_segs, loff_t *pos,
-			       int flags)
+static ssize_t __do_readv_writev(int type, struct file *file,
+				 struct iov_iter *iter, loff_t *pos, int flags)
 {
 	size_t tot_len;
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
+	ssize_t ret = 0;
 	io_fn_t fn;
 	iter_fn_t iter_fn;
 
-	ret = import_iovec(type, uvector, nr_segs,
-			   ARRAY_SIZE(iovstack), &iov, &iter);
-	if (ret < 0)
-		return ret;
-
-	tot_len = iov_iter_count(&iter);
+	tot_len = iov_iter_count(iter);
 	if (!tot_len)
 		goto out;
 	ret = rw_verify_area(type, file, pos, tot_len);
@@ -869,15 +859,14 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
+		ret = do_iter_readv_writev(file, iter, pos, iter_fn, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
+		ret = do_loop_readv_writev(file, iter, pos, fn, flags);
 
 	if (type != READ)
 		file_end_write(file);
 
 out:
-	kfree(iov);
 	if ((ret + (type == READ)) > 0) {
 		if (type == READ)
 			fsnotify_access(file);
@@ -887,6 +876,27 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	return ret;
 }
 
+static ssize_t do_readv_writev(int type, struct file *file,
+			       const struct iovec __user *uvector,
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	ret = import_iovec(type, uvector, nr_segs,
+			   ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret < 0)
+		return ret;
+
+	ret = __do_readv_writev(type, file, &iter, pos, flags);
+	kfree(iov);
+
+	return ret;
+}
+
 ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 		  unsigned long vlen, loff_t *pos, int flags)
 {
@@ -1064,51 +1074,19 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 			       unsigned long nr_segs, loff_t *pos,
 			       int flags)
 {
-	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
 	ssize_t ret;
-	io_fn_t fn;
-	iter_fn_t iter_fn;
 
 	ret = compat_import_iovec(type, uvector, nr_segs,
 				  UIO_FASTIOV, &iov, &iter);
 	if (ret < 0)
 		return ret;
 
-	tot_len = iov_iter_count(&iter);
-	if (!tot_len)
-		goto out;
-	ret = rw_verify_area(type, file, pos, tot_len);
-	if (ret < 0)
-		goto out;
-
-	if (type == READ) {
-		fn = file->f_op->read;
-		iter_fn = file->f_op->read_iter;
-	} else {
-		fn = (io_fn_t)file->f_op->write;
-		iter_fn = file->f_op->write_iter;
-		file_start_write(file);
-	}
-
-	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
-	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
-
-	if (type != READ)
-		file_end_write(file);
-
-out:
+	ret = __do_readv_writev(type, file, &iter, pos, flags);
 	kfree(iov);
-	if ((ret + (type == READ)) > 0) {
-		if (type == READ)
-			fsnotify_access(file);
-		else
-			fsnotify_modify(file);
-	}
+
 	return ret;
 }
 
-- 
GitLab


From 0f78d06ac1e9b470cbd8f913ee1688c8b2c8feb3 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 20 Feb 2017 16:51:23 +0100
Subject: [PATCH 108/898] vfs: pass type instead of fn to
 do_{loop,iter}_readv_writev()

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/read_write.c | 37 ++++++++++++++++++-------------------
 1 file changed, 18 insertions(+), 19 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 12a216021f87..198614f757fa 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -23,9 +23,6 @@
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 
-typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
-typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *);
-
 const struct file_operations generic_ro_fops = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
@@ -675,7 +672,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 EXPORT_SYMBOL(iov_shorten);
 
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, iter_fn_t fn, int flags)
+		loff_t *ppos, int type, int flags)
 {
 	struct kiocb kiocb;
 	ssize_t ret;
@@ -692,7 +689,10 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 		kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
 	kiocb.ki_pos = *ppos;
 
-	ret = fn(&kiocb, iter);
+	if (type == READ)
+		ret = filp->f_op->read_iter(&kiocb, iter);
+	else
+		ret = filp->f_op->write_iter(&kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
@@ -700,7 +700,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 
 /* Do it by hand, with file-ops */
 static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, io_fn_t fn, int flags)
+		loff_t *ppos, int type, int flags)
 {
 	ssize_t ret = 0;
 
@@ -711,7 +711,13 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
 
-		nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos);
+		if (type == READ) {
+			nr = filp->f_op->read(filp, iovec.iov_base,
+					      iovec.iov_len, ppos);
+		} else {
+			nr = filp->f_op->write(filp, iovec.iov_base,
+					       iovec.iov_len, ppos);
+		}
 
 		if (nr < 0) {
 			if (!ret)
@@ -839,8 +845,6 @@ static ssize_t __do_readv_writev(int type, struct file *file,
 {
 	size_t tot_len;
 	ssize_t ret = 0;
-	io_fn_t fn;
-	iter_fn_t iter_fn;
 
 	tot_len = iov_iter_count(iter);
 	if (!tot_len)
@@ -849,19 +853,14 @@ static ssize_t __do_readv_writev(int type, struct file *file,
 	if (ret < 0)
 		goto out;
 
-	if (type == READ) {
-		fn = file->f_op->read;
-		iter_fn = file->f_op->read_iter;
-	} else {
-		fn = (io_fn_t)file->f_op->write;
-		iter_fn = file->f_op->write_iter;
+	if (type != READ)
 		file_start_write(file);
-	}
 
-	if (iter_fn)
-		ret = do_iter_readv_writev(file, iter, pos, iter_fn, flags);
+	if ((type == READ && file->f_op->read_iter) ||
+	    (type == WRITE && file->f_op->write_iter))
+		ret = do_iter_readv_writev(file, iter, pos, type, flags);
 	else
-		ret = do_loop_readv_writev(file, iter, pos, fn, flags);
+		ret = do_loop_readv_writev(file, iter, pos, type, flags);
 
 	if (type != READ)
 		file_end_write(file);
-- 
GitLab


From bb7462b6fd64e40809a857223bf7f0e628969f87 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 20 Feb 2017 16:51:23 +0100
Subject: [PATCH 109/898] vfs: use helpers for calling
 f_op->{read,write}_iter()

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 drivers/block/loop.c |  4 ++--
 fs/aio.c             |  4 ++--
 fs/read_write.c      | 12 ++++++------
 fs/splice.c          |  2 +-
 include/linux/fs.h   | 12 ++++++++++++
 5 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f347285c67ec..2cf2903a0715 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -501,9 +501,9 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	cmd->iocb.ki_flags = IOCB_DIRECT;
 
 	if (rw == WRITE)
-		ret = file->f_op->write_iter(&cmd->iocb, &iter);
+		ret = call_write_iter(file, &cmd->iocb, &iter);
 	else
-		ret = file->f_op->read_iter(&cmd->iocb, &iter);
+		ret = call_read_iter(file, &cmd->iocb, &iter);
 
 	if (ret != -EIOCBQUEUED)
 		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
diff --git a/fs/aio.c b/fs/aio.c
index 4ab67e8cb776..9f4a9a2e7ae4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1494,7 +1494,7 @@ static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
 		return ret;
 	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret)
-		ret = aio_ret(req, file->f_op->read_iter(req, &iter));
+		ret = aio_ret(req, call_read_iter(file, req, &iter));
 	kfree(iovec);
 	return ret;
 }
@@ -1519,7 +1519,7 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 	if (!ret) {
 		req->ki_flags |= IOCB_WRITE;
 		file_start_write(file);
-		ret = aio_ret(req, file->f_op->write_iter(req, &iter));
+		ret = aio_ret(req, call_write_iter(file, req, &iter));
 		/*
 		 * We release freeze protection in aio_complete().  Fool lockdep
 		 * by telling it the lock got released so that it doesn't
diff --git a/fs/read_write.c b/fs/read_write.c
index 198614f757fa..f2ed9fdc98fd 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -367,7 +367,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos)
 	kiocb.ki_pos = *ppos;
 
 	iter->type |= READ;
-	ret = file->f_op->read_iter(&kiocb, iter);
+	ret = call_read_iter(file, &kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
@@ -387,7 +387,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
 	kiocb.ki_pos = *ppos;
 
 	iter->type |= WRITE;
-	ret = file->f_op->write_iter(&kiocb, iter);
+	ret = call_write_iter(file, &kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
@@ -436,7 +436,7 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	kiocb.ki_pos = *ppos;
 	iov_iter_init(&iter, READ, &iov, 1, len);
 
-	ret = filp->f_op->read_iter(&kiocb, &iter);
+	ret = call_read_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
@@ -493,7 +493,7 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 	kiocb.ki_pos = *ppos;
 	iov_iter_init(&iter, WRITE, &iov, 1, len);
 
-	ret = filp->f_op->write_iter(&kiocb, &iter);
+	ret = call_write_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
@@ -690,9 +690,9 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 	kiocb.ki_pos = *ppos;
 
 	if (type == READ)
-		ret = filp->f_op->read_iter(&kiocb, iter);
+		ret = call_read_iter(filp, &kiocb, iter);
 	else
-		ret = filp->f_op->write_iter(&kiocb, iter);
+		ret = call_write_iter(filp, &kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
diff --git a/fs/splice.c b/fs/splice.c
index 873d83104e79..6518f058bd7f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -306,7 +306,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 	idx = to.idx;
 	init_sync_kiocb(&kiocb, in);
 	kiocb.ki_pos = *ppos;
-	ret = in->f_op->read_iter(&kiocb, &to);
+	ret = call_read_iter(in, &kiocb, &to);
 	if (ret > 0) {
 		*ppos = kiocb.ki_pos;
 		file_accessed(in);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 78c81e6f5d76..a3145cdff8f2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1715,6 +1715,18 @@ struct inode_operations {
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 } ____cacheline_aligned;
 
+static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
+				     struct iov_iter *iter)
+{
+	return file->f_op->read_iter(kio, iter);
+}
+
+static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
+				      struct iov_iter *iter)
+{
+	return file->f_op->write_iter(kio, iter);
+}
+
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,
-- 
GitLab


From f74ac01520c9f6d89bbc3c6931a72f757b742f86 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 20 Feb 2017 16:51:23 +0100
Subject: [PATCH 110/898] mm: use helper for calling f_op->mmap()

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 drivers/gpu/drm/i915/i915_gem_dmabuf.c | 2 +-
 drivers/gpu/drm/vgem/vgem_drv.c        | 2 +-
 fs/coda/file.c                         | 2 +-
 include/linux/fs.h                     | 5 +++++
 ipc/shm.c                              | 2 +-
 mm/mmap.c                              | 2 +-
 mm/nommu.c                             | 4 ++--
 7 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 5e38299b5df6..84fc9f001576 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -141,7 +141,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 	if (!obj->base.filp)
 		return -ENODEV;
 
-	ret = obj->base.filp->f_op->mmap(obj->base.filp, vma);
+	ret = call_mmap(obj->base.filp, vma);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 477e07f0ecb6..9f7e222b3e89 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -287,7 +287,7 @@ static int vgem_prime_mmap(struct drm_gem_object *obj,
 	if (!obj->filp)
 		return -ENODEV;
 
-	ret = obj->filp->f_op->mmap(obj->filp, vma);
+	ret = call_mmap(obj->filp, vma);
 	if (ret)
 		return ret;
 
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 6e0154eb6fcc..9d956cd6d46f 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -96,7 +96,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	cfi->cfi_mapcount++;
 	spin_unlock(&cii->c_lock);
 
-	return host_file->f_op->mmap(host_file, vma);
+	return call_mmap(host_file, vma);
 }
 
 int coda_open(struct inode *coda_inode, struct file *coda_file)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a3145cdff8f2..93691b59e476 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1727,6 +1727,11 @@ static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
 	return file->f_op->write_iter(kio, iter);
 }
 
+static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	return file->f_op->mmap(file, vma);
+}
+
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,
diff --git a/ipc/shm.c b/ipc/shm.c
index 81203e8ba013..4329fe3ef594 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -423,7 +423,7 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	if (ret)
 		return ret;
 
-	ret = sfd->file->f_op->mmap(sfd->file, vma);
+	ret = call_mmap(sfd->file, vma);
 	if (ret) {
 		shm_close(vma);
 		return ret;
diff --git a/mm/mmap.c b/mm/mmap.c
index dc4291dcc99b..3714aa4e6f81 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1668,7 +1668,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		 * new file must not have been exposed to user-space, yet.
 		 */
 		vma->vm_file = get_file(file);
-		error = file->f_op->mmap(file, vma);
+		error = call_mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 24f9f5f39145..e366354f777d 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1084,7 +1084,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma)
 {
 	int ret;
 
-	ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
+	ret = call_mmap(vma->vm_file, vma);
 	if (ret == 0) {
 		vma->vm_region->vm_top = vma->vm_region->vm_end;
 		return 0;
@@ -1115,7 +1115,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 	 * - VM_MAYSHARE will be set if it may attempt to share
 	 */
 	if (capabilities & NOMMU_MAP_DIRECT) {
-		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
+		ret = call_mmap(vma->vm_file, vma);
 		if (ret == 0) {
 			/* shouldn't return success if we're not sharing */
 			BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
-- 
GitLab


From 0eb8af4916a540c362a2950e5ab54eca32eb7d58 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 20 Feb 2017 16:51:23 +0100
Subject: [PATCH 111/898] vfs: use helper for calling f_op->fsync()

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/sync.c          | 2 +-
 include/linux/fs.h | 6 ++++++
 ipc/shm.c          | 2 +-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/sync.c b/fs/sync.c
index 2a54c1f22035..11ba023434b1 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -192,7 +192,7 @@ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync)
 		spin_unlock(&inode->i_lock);
 		mark_inode_dirty_sync(inode);
 	}
-	return file->f_op->fsync(file, start, end, datasync);
+	return call_fsync(file, start, end, datasync);
 }
 EXPORT_SYMBOL(vfs_fsync_range);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 93691b59e476..72a33007ec24 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1732,6 +1732,12 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
 	return file->f_op->mmap(file, vma);
 }
 
+static inline int call_fsync(struct file *file, loff_t start, loff_t end,
+			     int datasync)
+{
+	return file->f_op->fsync(file, start, end, datasync);
+}
+
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,
diff --git a/ipc/shm.c b/ipc/shm.c
index 4329fe3ef594..258aff2e03bb 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -452,7 +452,7 @@ static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	if (!sfd->file->f_op->fsync)
 		return -EINVAL;
-	return sfd->file->f_op->fsync(sfd->file, start, end, datasync);
+	return call_fsync(sfd->file, start, end, datasync);
 }
 
 static long shm_fallocate(struct file *file, int mode, loff_t offset,
-- 
GitLab


From e3b88ee95b4e4bf3e9729a4695d695b9c7c296c8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 14 Feb 2017 16:25:45 -0800
Subject: [PATCH 112/898] target: Fix handling of aborted failed commands

If a target driver (e.g. tcm_qla2xxx) calls
transport_generic_request_failure() to report that receiving data
has failed and that SCSI command has already been aborted by the
initiator, ensure that the SCSI status ABORTED is sent back to the
initiator instead of the sense code provided by the target driver.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 22190003534d..efb9e6f38201 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1647,6 +1647,9 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 {
 	int ret = 0, post_ret = 0;
 
+	if (transport_check_aborted_status(cmd, 1))
+		return;
+
 	pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08llx"
 		" CDB: 0x%02x\n", cmd, cmd->tag, cmd->t_task_cdb[0]);
 	pr_debug("-----[ i_state: %d t_state: %d sense_reason: %d\n",
-- 
GitLab


From 51ec502a32665fed66c7f03799ede4023b212536 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue, 14 Feb 2017 16:25:54 -0800
Subject: [PATCH 113/898] target: Delete tmr from list before processing

This patch does an explicit list_del_init(tmr->tmr_list) in
core_tmr_drain_tmr_list() before starting processing of
outstanding TMRs to abort, instead of explicitly checking
which TMR descriptor matches the caller.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_tmr.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 311dc3c2f1dc..a806d9bca3d2 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -215,13 +215,8 @@ static void core_tmr_drain_tmr_list(
 	 * LUN_RESET tmr..
 	 */
 	spin_lock_irqsave(&dev->se_tmr_lock, flags);
+	list_del_init(&tmr->tmr_list);
 	list_for_each_entry_safe(tmr_p, tmr_pp, &dev->dev_tmr_list, tmr_list) {
-		/*
-		 * Allow the received TMR to return with FUNCTION_COMPLETE.
-		 */
-		if (tmr_p == tmr)
-			continue;
-
 		cmd = tmr_p->task_cmd;
 		if (!cmd) {
 			pr_err("Unable to locate struct se_cmd for TMR\n");
-- 
GitLab


From 7e6a69ee954caf8dd8c98f70c8ee894c8ebfdcf0 Mon Sep 17 00:00:00 2001
From: Mike Leach <mike.leach@linaro.org>
Date: Fri, 17 Feb 2017 19:13:10 +0000
Subject: [PATCH 114/898] arm64: dts: juno: update definition for programmable
 replicator

Juno platforms have a programmable replicator splitting the trace output
to TPIU and ETR. Currently this is not being programmed as it is being
treated as a none-programmable replicator - which is the default
operational mode for these devices. The TPIU in the system is enabled by
default, and this combination is causing back-pressure in the trace
system resulting in overflows at the source.

Replaces the existing definition with one that defines the programmable
replicator, using the "qcom,coresight-replicator1x" driver that provides
the correct functionality for CoreSight programmable replicators.

Reviewed-and-Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 arch/arm64/boot/dts/arm/juno-base.dtsi | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index 9d799d938d2f..df539e865b90 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -372,12 +372,13 @@
 		};
 	};
 
-	coresight-replicator {
-		/*
-		 * Non-configurable replicators don't show up on the
-		 * AMBA bus.  As such no need to add "arm,primecell".
-		 */
-		compatible = "arm,coresight-replicator";
+	replicator@20120000 {
+		compatible = "qcom,coresight-replicator1x", "arm,primecell";
+		reg = <0 0x20120000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
 
 		ports {
 			#address-cells = <1>;
-- 
GitLab


From 248e23b50e2da0753f3b5faa068939cbe9f8a75a Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 12 Feb 2017 11:26:33 +0100
Subject: [PATCH 115/898] batman-adv: Fix double free during fragment merge
 error

The function batadv_frag_skb_buffer was supposed not to consume the skbuff
on errors. This was followed in the helper function
batadv_frag_insert_packet when the skb would potentially be inserted in the
fragment queue. But it could happen that the next helper function
batadv_frag_merge_packets would try to merge the fragments and fail. This
results in a kfree_skb of all the enqueued fragments (including the just
inserted one). batadv_recv_frag_packet would detect the error in
batadv_frag_skb_buffer and try to free the skb again.

The behavior of batadv_frag_skb_buffer (and its helper
batadv_frag_insert_packet) must therefore be changed to always consume the
skbuff to have a common behavior and avoid the double kfree_skb.

Fixes: 610bfc6bc99b ("batman-adv: Receive fragmented packets and merge")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/fragmentation.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 0854ebd8613e..31e97e9aee0d 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -239,8 +239,10 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
 	spin_unlock_bh(&chain->lock);
 
 err:
-	if (!ret)
+	if (!ret) {
 		kfree(frag_entry_new);
+		kfree_skb(skb);
+	}
 
 	return ret;
 }
@@ -313,7 +315,7 @@ batadv_frag_merge_packets(struct hlist_head *chain)
  *
  * There are three possible outcomes: 1) Packet is merged: Return true and
  * set *skb to merged packet; 2) Packet is buffered: Return true and set *skb
- * to NULL; 3) Error: Return false and leave skb as is.
+ * to NULL; 3) Error: Return false and free skb.
  *
  * Return: true when packet is merged or buffered, false when skb is not not
  * used.
@@ -338,9 +340,9 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb,
 		goto out_err;
 
 out:
-	*skb = skb_out;
 	ret = true;
 out_err:
+	*skb = skb_out;
 	return ret;
 }
 
-- 
GitLab


From 51c6b429c0c95e67edd1cb0b548c5cf6a6604763 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Mon, 13 Feb 2017 20:44:31 +0100
Subject: [PATCH 116/898] batman-adv: Fix transmission of final, 16th fragment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Trying to split and transmit a unicast packet in 16 parts will fail for
the final fragment: After having sent the 15th one with a frag_packet.no
index of 14, we will increase the the index to 15 - and return with an
error code immediately, even though one more fragment is due for
transmission and allowed.

Fixing this issue by moving the check before incrementing the index.

While at it, adding an unlikely(), because the check is actually more of
an assertion.

Fixes: ee75ed88879a ("batman-adv: Fragment and send skbs larger than mtu")
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/fragmentation.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 31e97e9aee0d..11149e5be4e0 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -501,6 +501,12 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 
 	/* Eat and send fragments from the tail of skb */
 	while (skb->len > max_fragment_size) {
+		/* The initial check in this function should cover this case */
+		if (unlikely(frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1)) {
+			ret = -EINVAL;
+			goto put_primary_if;
+		}
+
 		skb_fragment = batadv_frag_create(skb, &frag_header, mtu);
 		if (!skb_fragment) {
 			ret = -ENOMEM;
@@ -517,12 +523,6 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 		}
 
 		frag_header.no++;
-
-		/* The initial check in this function should cover this case */
-		if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) {
-			ret = -EINVAL;
-			goto put_primary_if;
-		}
 	}
 
 	/* Make room for the fragment header. */
-- 
GitLab


From c74fd80f2f41d05f350bb478151021f88551afe8 Mon Sep 17 00:00:00 2001
From: Dan Streetman <ddstreet@ieee.org>
Date: Fri, 13 Jan 2017 15:07:51 -0500
Subject: [PATCH 117/898] xen: do not re-use pirq number cached in pci device
 msi msg data

Revert the main part of commit:
af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests")

That commit introduced reading the pci device's msi message data to see
if a pirq was previously configured for the device's msi/msix, and re-use
that pirq.  At the time, that was the correct behavior.  However, a
later change to Qemu caused it to call into the Xen hypervisor to unmap
all pirqs for a pci device, when the pci device disables its MSI/MSIX
vectors; specifically the Qemu commit:
c976437c7dba9c7444fb41df45468968aaa326ad
("qemu-xen: free all the pirqs for msi/msix when driver unload")

Once Qemu added this pirq unmapping, it was no longer correct for the
kernel to re-use the pirq number cached in the pci device msi message
data.  All Qemu releases since 2.1.0 contain the patch that unmaps the
pirqs when the pci device disables its MSI/MSIX vectors.

This bug is causing failures to initialize multiple NVMe controllers
under Xen, because the NVMe driver sets up a single MSIX vector for
each controller (concurrently), and then after using that to talk to
the controller for some configuration data, it disables the single MSIX
vector and re-configures all the MSIX vectors it needs.  So the MSIX
setup code tries to re-use the cached pirq from the first vector
for each controller, but the hypervisor has already given away that
pirq to another controller, and its initialization fails.

This is discussed in more detail at:
https://lists.xen.org/archives/html/xen-devel/2017-01/msg00447.html

Fixes: af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests")
Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/pci/xen.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index e1fb269c87af..292ab0364a89 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		return 1;
 
 	for_each_pci_msi_entry(msidesc, dev) {
-		__pci_read_msi_msg(msidesc, &msg);
-		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
-			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
-		if (msg.data != XEN_PIRQ_MSI_DATA ||
-		    xen_irq_from_pirq(pirq) < 0) {
-			pirq = xen_allocate_pirq_msi(dev, msidesc);
-			if (pirq < 0) {
-				irq = -ENODEV;
-				goto error;
-			}
-			xen_msi_compose_msg(dev, pirq, &msg);
-			__pci_write_msi_msg(msidesc, &msg);
-			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
-		} else {
-			dev_dbg(&dev->dev,
-				"xen: msi already bound to pirq=%d\n", pirq);
+		pirq = xen_allocate_pirq_msi(dev, msidesc);
+		if (pirq < 0) {
+			irq = -ENODEV;
+			goto error;
 		}
+		xen_msi_compose_msg(dev, pirq, &msg);
+		__pci_write_msi_msg(msidesc, &msg);
+		dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
 					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
-- 
GitLab


From 2e38bea99a80eab408adee27f873a188d57b76cb Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 22 Feb 2017 20:08:25 +0100
Subject: [PATCH 118/898] fuse: add missing FR_FORCE

fuse_file_put() was missing the "force" flag for the RELEASE request when
sending synchronously (fuseblk).

If this flag is not set, then a sync request may be interrupted before it
is dequeued by the userspace filesystem.  In this case the OPEN won't be
balanced with a RELEASE.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 5a18ec176c93 ("fuse: fix hang of single threaded fuseblk filesystem")
Cc: <stable@vger.kernel.org> # v2.6.38+
---
 fs/fuse/file.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 2401c5dabb2a..5ec5870e423a 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -100,6 +100,7 @@ static void fuse_file_put(struct fuse_file *ff, bool sync)
 			iput(req->misc.release.inode);
 			fuse_put_request(ff->fc, req);
 		} else if (sync) {
+			__set_bit(FR_FORCE, &req->flags);
 			__clear_bit(FR_BACKGROUND, &req->flags);
 			fuse_request_send(ff->fc, req);
 			iput(req->misc.release.inode);
-- 
GitLab


From 267d84449f52349ee252db684ed95ede18e51744 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 22 Feb 2017 20:08:25 +0100
Subject: [PATCH 119/898] fuse: cleanup fuse_file refcounting

struct fuse_file is stored in file->private_data.  Make this always be a
counting reference for consistency.

This also allows fuse_sync_release() to call fuse_file_put() instead of
partially duplicating its functionality.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dir.c    |  2 +-
 fs/fuse/file.c   | 18 +++++++++---------
 fs/fuse/fuse_i.h |  1 -
 3 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 811fd8929a18..e816166ce42f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -473,7 +473,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	if (err) {
 		fuse_sync_release(ff, flags);
 	} else {
-		file->private_data = fuse_file_get(ff);
+		file->private_data = ff;
 		fuse_finish_open(inode, file);
 	}
 	return err;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5ec5870e423a..a5f79c59fe1e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -58,7 +58,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc)
 	}
 
 	INIT_LIST_HEAD(&ff->write_entry);
-	atomic_set(&ff->count, 0);
+	atomic_set(&ff->count, 1);
 	RB_CLEAR_NODE(&ff->polled_node);
 	init_waitqueue_head(&ff->poll_wait);
 
@@ -75,7 +75,7 @@ void fuse_file_free(struct fuse_file *ff)
 	kfree(ff);
 }
 
-struct fuse_file *fuse_file_get(struct fuse_file *ff)
+static struct fuse_file *fuse_file_get(struct fuse_file *ff)
 {
 	atomic_inc(&ff->count);
 	return ff;
@@ -147,7 +147,7 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 		ff->open_flags &= ~FOPEN_DIRECT_IO;
 
 	ff->nodeid = nodeid;
-	file->private_data = fuse_file_get(ff);
+	file->private_data = ff;
 
 	return 0;
 }
@@ -298,13 +298,13 @@ static int fuse_release(struct inode *inode, struct file *file)
 
 void fuse_sync_release(struct fuse_file *ff, int flags)
 {
-	WARN_ON(atomic_read(&ff->count) > 1);
+	WARN_ON(atomic_read(&ff->count) != 1);
 	fuse_prepare_release(ff, flags, FUSE_RELEASE);
-	__set_bit(FR_FORCE, &ff->reserved_req->flags);
-	__clear_bit(FR_BACKGROUND, &ff->reserved_req->flags);
-	fuse_request_send(ff->fc, ff->reserved_req);
-	fuse_put_request(ff->fc, ff->reserved_req);
-	kfree(ff);
+	/*
+	 * iput(NULL) is a no-op and since the refcount is 1 and everything's
+	 * synchronous, we are fine with not doing igrab() here"
+	 */
+	fuse_file_put(ff, true);
 }
 EXPORT_SYMBOL_GPL(fuse_sync_release);
 
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 91307940c8ac..83f797271aef 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -732,7 +732,6 @@ void fuse_read_fill(struct fuse_req *req, struct file *file,
 int fuse_open_common(struct inode *inode, struct file *file, bool isdir);
 
 struct fuse_file *fuse_file_alloc(struct fuse_conn *fc);
-struct fuse_file *fuse_file_get(struct fuse_file *ff);
 void fuse_file_free(struct fuse_file *ff);
 void fuse_finish_open(struct inode *inode, struct file *file);
 
-- 
GitLab


From 9a87ad3da905239413477ac0698734afc5cc30bd Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 22 Feb 2017 20:08:25 +0100
Subject: [PATCH 120/898] fuse: release: private_data cannot be NULL

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a5f79c59fe1e..7069ea232049 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -246,14 +246,9 @@ static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode)
 
 void fuse_release_common(struct file *file, int opcode)
 {
-	struct fuse_file *ff;
-	struct fuse_req *req;
-
-	ff = file->private_data;
-	if (unlikely(!ff))
-		return;
+	struct fuse_file *ff = file->private_data;
+	struct fuse_req *req = ff->reserved_req;
 
-	req = ff->reserved_req;
 	fuse_prepare_release(ff, file->f_flags, opcode);
 
 	if (ff->flock) {
-- 
GitLab


From 1c68856e6ea8abd714415e52ef88943c022e24f0 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:10 -0800
Subject: [PATCH 121/898] scsi: aacraid: Fix camel case

Replaced camel case with snake case for init supported options.

Suggested-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/aachba.c  | 53 +++++++++---------
 drivers/scsi/aacraid/aacraid.h | 98 +++++++++++++++++-----------------
 drivers/scsi/aacraid/commsup.c |  6 +--
 drivers/scsi/aacraid/linit.c   | 32 +++++------
 drivers/scsi/aacraid/rx.c      |  2 +-
 drivers/scsi/aacraid/src.c     |  2 +-
 6 files changed, 100 insertions(+), 93 deletions(-)

diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 907f1e80665b..98d4ffd798c5 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -483,7 +483,7 @@ int aac_get_containers(struct aac_dev *dev)
 	if (status >= 0) {
 		dresp = (struct aac_get_container_count_resp *)fib_data(fibptr);
 		maximum_num_containers = le32_to_cpu(dresp->ContainerSwitchEntries);
-		if (fibptr->dev->supplement_adapter_info.SupportedOptions2 &
+		if (fibptr->dev->supplement_adapter_info.supported_options2 &
 		    AAC_OPTION_SUPPORTED_240_VOLUMES) {
 			maximum_num_containers =
 				le32_to_cpu(dresp->MaxSimpleVolumes);
@@ -639,13 +639,16 @@ static void _aac_probe_container2(void * context, struct fib * fibptr)
 	fsa_dev_ptr = fibptr->dev->fsa_dev;
 	if (fsa_dev_ptr) {
 		struct aac_mount * dresp = (struct aac_mount *) fib_data(fibptr);
+		__le32 sup_options2;
+
 		fsa_dev_ptr += scmd_id(scsicmd);
+		sup_options2 =
+			fibptr->dev->supplement_adapter_info.supported_options2;
 
 		if ((le32_to_cpu(dresp->status) == ST_OK) &&
 		    (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE) &&
 		    (le32_to_cpu(dresp->mnt[0].state) != FSCS_HIDDEN)) {
-			if (!(fibptr->dev->supplement_adapter_info.SupportedOptions2 &
-			    AAC_OPTION_VARIABLE_BLOCK_SIZE)) {
+			if (!(sup_options2 & AAC_OPTION_VARIABLE_BLOCK_SIZE)) {
 				dresp->mnt[0].fileinfo.bdevinfo.block_size = 0x200;
 				fsa_dev_ptr->block_size = 0x200;
 			} else {
@@ -688,7 +691,7 @@ static void _aac_probe_container1(void * context, struct fib * fibptr)
 	int status;
 
 	dresp = (struct aac_mount *) fib_data(fibptr);
-	if (!(fibptr->dev->supplement_adapter_info.SupportedOptions2 &
+	if (!(fibptr->dev->supplement_adapter_info.supported_options2 &
 	    AAC_OPTION_VARIABLE_BLOCK_SIZE))
 		dresp->mnt[0].capacityhigh = 0;
 	if ((le32_to_cpu(dresp->status) != ST_OK) ||
@@ -705,7 +708,7 @@ static void _aac_probe_container1(void * context, struct fib * fibptr)
 
 	dinfo = (struct aac_query_mount *)fib_data(fibptr);
 
-	if (fibptr->dev->supplement_adapter_info.SupportedOptions2 &
+	if (fibptr->dev->supplement_adapter_info.supported_options2 &
 	    AAC_OPTION_VARIABLE_BLOCK_SIZE)
 		dinfo->command = cpu_to_le32(VM_NameServeAllBlk);
 	else
@@ -745,7 +748,7 @@ static int _aac_probe_container(struct scsi_cmnd * scsicmd, int (*callback)(stru
 
 		dinfo = (struct aac_query_mount *)fib_data(fibptr);
 
-		if (fibptr->dev->supplement_adapter_info.SupportedOptions2 &
+		if (fibptr->dev->supplement_adapter_info.supported_options2 &
 		    AAC_OPTION_VARIABLE_BLOCK_SIZE)
 			dinfo->command = cpu_to_le32(VM_NameServeAllBlk);
 		else
@@ -896,12 +899,14 @@ char * get_container_type(unsigned tindex)
 static void setinqstr(struct aac_dev *dev, void *data, int tindex)
 {
 	struct scsi_inq *str;
+	struct aac_supplement_adapter_info *sup_adap_info;
 
+	sup_adap_info = &dev->supplement_adapter_info;
 	str = (struct scsi_inq *)(data); /* cast data to scsi inq block */
 	memset(str, ' ', sizeof(*str));
 
-	if (dev->supplement_adapter_info.AdapterTypeText[0]) {
-		char * cp = dev->supplement_adapter_info.AdapterTypeText;
+	if (sup_adap_info->adapter_type_text[0]) {
+		char *cp = sup_adap_info->adapter_type_text;
 		int c;
 		if ((cp[0] == 'A') && (cp[1] == 'O') && (cp[2] == 'C'))
 			inqstrcpy("SMC", str->vid);
@@ -911,8 +916,7 @@ static void setinqstr(struct aac_dev *dev, void *data, int tindex)
 				++cp;
 			c = *cp;
 			*cp = '\0';
-			inqstrcpy (dev->supplement_adapter_info.AdapterTypeText,
-				   str->vid);
+			inqstrcpy(sup_adap_info->adapter_type_text, str->vid);
 			*cp = c;
 			while (*cp && *cp != ' ')
 				++cp;
@@ -1675,8 +1679,8 @@ int aac_issue_bmic_identify(struct aac_dev *dev, u32 bus, u32 target)
 	if (!identify_resp)
 		goto fib_free_ptr;
 
-	vbus = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceBus);
-	vid = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceTarget);
+	vbus = (u32)le16_to_cpu(dev->supplement_adapter_info.virt_device_bus);
+	vid = (u32)le16_to_cpu(dev->supplement_adapter_info.virt_device_target);
 
 	aac_fib_init(fibptr);
 
@@ -1815,9 +1819,9 @@ int aac_report_phys_luns(struct aac_dev *dev, struct fib *fibptr, int rescan)
 	}
 
 	vbus = (u32) le16_to_cpu(
-			dev->supplement_adapter_info.VirtDeviceBus);
+			dev->supplement_adapter_info.virt_device_bus);
 	vid = (u32) le16_to_cpu(
-			dev->supplement_adapter_info.VirtDeviceTarget);
+			dev->supplement_adapter_info.virt_device_target);
 
 	aac_fib_init(fibptr);
 
@@ -1893,7 +1897,7 @@ int aac_get_adapter_info(struct aac_dev* dev)
 	}
 	memcpy(&dev->adapter_info, info, sizeof(*info));
 
-	dev->supplement_adapter_info.VirtDeviceBus = 0xffff;
+	dev->supplement_adapter_info.virt_device_bus = 0xffff;
 	if (dev->adapter_info.options & AAC_OPT_SUPPLEMENT_ADAPTER_INFO) {
 		struct aac_supplement_adapter_info * sinfo;
 
@@ -1961,7 +1965,7 @@ int aac_get_adapter_info(struct aac_dev* dev)
 	}
 
 	if (!dev->sync_mode && dev->sa_firmware &&
-			dev->supplement_adapter_info.VirtDeviceBus != 0xffff) {
+		dev->supplement_adapter_info.virt_device_bus != 0xffff) {
 		/* Thor SA Firmware -> CISS_REPORT_PHYSICAL_LUNS */
 		rcode = aac_report_phys_luns(dev, fibptr, AAC_INIT);
 	}
@@ -1976,8 +1980,8 @@ int aac_get_adapter_info(struct aac_dev* dev)
 			(tmp>>16)&0xff,
 			tmp&0xff,
 			le32_to_cpu(dev->adapter_info.kernelbuild),
-			(int)sizeof(dev->supplement_adapter_info.BuildDate),
-			dev->supplement_adapter_info.BuildDate);
+			(int)sizeof(dev->supplement_adapter_info.build_date),
+			dev->supplement_adapter_info.build_date);
 		tmp = le32_to_cpu(dev->adapter_info.monitorrev);
 		printk(KERN_INFO "%s%d: monitor %d.%d-%d[%d]\n",
 			dev->name, dev->id,
@@ -1993,14 +1997,15 @@ int aac_get_adapter_info(struct aac_dev* dev)
 		  shost_to_class(dev->scsi_host_ptr), buffer))
 			printk(KERN_INFO "%s%d: serial %s",
 			  dev->name, dev->id, buffer);
-		if (dev->supplement_adapter_info.VpdInfo.Tsid[0]) {
+		if (dev->supplement_adapter_info.vpd_info.tsid[0]) {
 			printk(KERN_INFO "%s%d: TSID %.*s\n",
 			  dev->name, dev->id,
-			  (int)sizeof(dev->supplement_adapter_info.VpdInfo.Tsid),
-			  dev->supplement_adapter_info.VpdInfo.Tsid);
+			  (int)sizeof(dev->supplement_adapter_info
+							.vpd_info.tsid),
+				dev->supplement_adapter_info.vpd_info.tsid);
 		}
 		if (!aac_check_reset || ((aac_check_reset == 1) &&
-		  (dev->supplement_adapter_info.SupportedOptions2 &
+		  (dev->supplement_adapter_info.supported_options2 &
 		  AAC_OPTION_IGNORE_RESET))) {
 			printk(KERN_INFO "%s%d: Reset Adapter Ignored\n",
 			  dev->name, dev->id);
@@ -2008,7 +2013,7 @@ int aac_get_adapter_info(struct aac_dev* dev)
 	}
 
 	dev->cache_protected = 0;
-	dev->jbod = ((dev->supplement_adapter_info.FeatureBits &
+	dev->jbod = ((dev->supplement_adapter_info.feature_bits &
 		AAC_FEATURE_JBOD) != 0);
 	dev->nondasd_support = 0;
 	dev->raid_scsi_mode = 0;
@@ -2631,7 +2636,7 @@ static int aac_start_stop(struct scsi_cmnd *scsicmd)
 	struct scsi_device *sdev = scsicmd->device;
 	struct aac_dev *aac = (struct aac_dev *)sdev->host->hostdata;
 
-	if (!(aac->supplement_adapter_info.SupportedOptions2 &
+	if (!(aac->supplement_adapter_info.supported_options2 &
 	      AAC_OPTION_POWER_MANAGEMENT)) {
 		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
 				  SAM_STAT_GOOD;
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index f2344971e3cb..b5a2c87f289b 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1380,57 +1380,57 @@ struct aac_adapter_info
 
 struct aac_supplement_adapter_info
 {
-	u8	AdapterTypeText[17+1];
-	u8	Pad[2];
-	__le32	FlashMemoryByteSize;
-	__le32	FlashImageId;
-	__le32	MaxNumberPorts;
-	__le32	Version;
-	__le32	FeatureBits;
-	u8	SlotNumber;
-	u8	ReservedPad0[3];
-	u8	BuildDate[12];
-	__le32	CurrentNumberPorts;
+	u8	adapter_type_text[17+1];
+	u8	pad[2];
+	__le32	flash_memory_byte_size;
+	__le32	flash_image_id;
+	__le32	max_number_ports;
+	__le32	version;
+	__le32	feature_bits;
+	u8	slot_number;
+	u8	reserved_pad0[3];
+	u8	build_date[12];
+	__le32	current_number_ports;
 	struct {
-		u8	AssemblyPn[8];
-		u8	FruPn[8];
-		u8	BatteryFruPn[8];
-		u8	EcVersionString[8];
-		u8	Tsid[12];
-	}	VpdInfo;
-	__le32	FlashFirmwareRevision;
-	__le32	FlashFirmwareBuild;
-	__le32	RaidTypeMorphOptions;
-	__le32	FlashFirmwareBootRevision;
-	__le32	FlashFirmwareBootBuild;
-	u8	MfgPcbaSerialNo[12];
-	u8	MfgWWNName[8];
-	__le32	SupportedOptions2;
-	__le32	StructExpansion;
+		u8	assembly_pn[8];
+		u8	fru_pn[8];
+		u8	battery_fru_pn[8];
+		u8	ec_version_string[8];
+		u8	tsid[12];
+	}	vpd_info;
+	__le32	flash_firmware_revision;
+	__le32	flash_firmware_build;
+	__le32	raid_type_morph_options;
+	__le32	flash_firmware_boot_revision;
+	__le32	flash_firmware_boot_build;
+	u8	mfg_pcba_serial_no[12];
+	u8	mfg_wwn_name[8];
+	__le32	supported_options2;
+	__le32	struct_expansion;
 	/* StructExpansion == 1 */
-	__le32	FeatureBits3;
-	__le32	SupportedPerformanceModes;
-	u8	HostBusType;		/* uses HOST_BUS_TYPE_xxx defines */
-	u8	HostBusWidth;		/* actual width in bits or links */
-	u16	HostBusSpeed;		/* actual bus speed/link rate in MHz */
-	u8	MaxRRCDrives;		/* max. number of ITP-RRC drives/pool */
-	u8	MaxDiskXtasks;		/* max. possible num of DiskX Tasks */
-
-	u8	CpldVerLoaded;
-	u8	CpldVerInFlash;
-
-	__le64	MaxRRCCapacity;
-	__le32	CompiledMaxHistLogLevel;
-	u8	CustomBoardName[12];
-	u16	SupportedCntlrMode;	/* identify supported controller mode */
-	u16	ReservedForFuture16;
-	__le32	SupportedOptions3;	/* reserved for future options */
-
-	__le16	VirtDeviceBus;		/* virt. SCSI device for Thor */
-	__le16	VirtDeviceTarget;
-	__le16	VirtDeviceLUN;
-	__le16	Unused;
-	__le32	ReservedForFutureGrowth[68];
+	__le32	feature_bits3;
+	__le32	supported_performance_modes;
+	u8	host_bus_type;		/* uses HOST_BUS_TYPE_xxx defines */
+	u8	host_bus_width;		/* actual width in bits or links */
+	u16	host_bus_speed;		/* actual bus speed/link rate in MHz */
+	u8	max_rrc_drives;		/* max. number of ITP-RRC drives/pool */
+	u8	max_disk_xtasks;	/* max. possible num of DiskX Tasks */
+
+	u8	cpld_ver_loaded;
+	u8	cpld_ver_in_flash;
+
+	__le64	max_rrc_capacity;
+	__le32	compiled_max_hist_log_level;
+	u8	custom_board_name[12];
+	u16	supported_cntlr_mode;	/* identify supported controller mode */
+	u16	reserved_for_future16;
+	__le32	supported_options3;	/* reserved for future options */
+
+	__le16	virt_device_bus;		/* virt. SCSI device for Thor */
+	__le16	virt_device_target;
+	__le16	virt_device_lun;
+	__le16	unused;
+	__le32	reserved_for_future_growth[68];
 
 };
 #define AAC_FEATURE_FALCON	cpu_to_le32(0x00000010)
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 969727b67cdd..56090f5be6c5 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1815,7 +1815,7 @@ int aac_check_health(struct aac_dev * aac)
 	printk(KERN_ERR "%s: Host adapter BLINK LED 0x%x\n", aac->name, BlinkLED);
 
 	if (!aac_check_reset || ((aac_check_reset == 1) &&
-		(aac->supplement_adapter_info.SupportedOptions2 &
+		(aac->supplement_adapter_info.supported_options2 &
 			AAC_OPTION_IGNORE_RESET)))
 		goto out;
 	host = aac->scsi_host_ptr;
@@ -2264,8 +2264,8 @@ static int aac_send_wellness_command(struct aac_dev *dev, char *wellness_str,
 
 	aac_fib_init(fibptr);
 
-	vbus = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceBus);
-	vid = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceTarget);
+	vbus = (u32)le16_to_cpu(dev->supplement_adapter_info.virt_device_bus);
+	vid = (u32)le16_to_cpu(dev->supplement_adapter_info.virt_device_target);
 
 	srbcmd = (struct aac_srb *)fib_data(fibptr);
 
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 137d22d3a005..ab4f1e7870b9 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -891,13 +891,13 @@ static int aac_eh_reset(struct scsi_cmnd* cmd)
 		 * Adapters that support a register, instead of a commanded,
 		 * reset.
 		 */
-		if (((aac->supplement_adapter_info.SupportedOptions2 &
+		if (((aac->supplement_adapter_info.supported_options2 &
 			  AAC_OPTION_MU_RESET) ||
-			  (aac->supplement_adapter_info.SupportedOptions2 &
+			  (aac->supplement_adapter_info.supported_options2 &
 			  AAC_OPTION_DOORBELL_RESET)) &&
 			  aac_check_reset &&
 			  ((aac_check_reset != 1) ||
-			   !(aac->supplement_adapter_info.SupportedOptions2 &
+			   !(aac->supplement_adapter_info.supported_options2 &
 			    AAC_OPTION_IGNORE_RESET))) {
 			/* Bypass wait for command quiesce */
 			aac_reset_adapter(aac, 2, IOP_HWSOFT_RESET);
@@ -1029,8 +1029,8 @@ static ssize_t aac_show_model(struct device *device,
 	struct aac_dev *dev = (struct aac_dev*)class_to_shost(device)->hostdata;
 	int len;
 
-	if (dev->supplement_adapter_info.AdapterTypeText[0]) {
-		char * cp = dev->supplement_adapter_info.AdapterTypeText;
+	if (dev->supplement_adapter_info.adapter_type_text[0]) {
+		char *cp = dev->supplement_adapter_info.adapter_type_text;
 		while (*cp && *cp != ' ')
 			++cp;
 		while (*cp == ' ')
@@ -1046,18 +1046,20 @@ static ssize_t aac_show_vendor(struct device *device,
 			       struct device_attribute *attr, char *buf)
 {
 	struct aac_dev *dev = (struct aac_dev*)class_to_shost(device)->hostdata;
+	struct aac_supplement_adapter_info *sup_adap_info;
 	int len;
 
-	if (dev->supplement_adapter_info.AdapterTypeText[0]) {
-		char * cp = dev->supplement_adapter_info.AdapterTypeText;
+	sup_adap_info = &dev->supplement_adapter_info;
+	if (sup_adap_info->adapter_type_text[0]) {
+		char *cp = sup_adap_info->adapter_type_text;
 		while (*cp && *cp != ' ')
 			++cp;
 		len = snprintf(buf, PAGE_SIZE, "%.*s\n",
-		  (int)(cp - (char *)dev->supplement_adapter_info.AdapterTypeText),
-		  dev->supplement_adapter_info.AdapterTypeText);
+			(int)(cp - (char *)sup_adap_info->adapter_type_text),
+					sup_adap_info->adapter_type_text);
 	} else
 		len = snprintf(buf, PAGE_SIZE, "%s\n",
-		  aac_drivers[dev->cardtype].vname);
+			aac_drivers[dev->cardtype].vname);
 	return len;
 }
 
@@ -1078,7 +1080,7 @@ static ssize_t aac_show_flags(struct device *cdev,
 				"SAI_READ_CAPACITY_16\n");
 	if (dev->jbod)
 		len += snprintf(buf + len, PAGE_SIZE - len, "SUPPORTED_JBOD\n");
-	if (dev->supplement_adapter_info.SupportedOptions2 &
+	if (dev->supplement_adapter_info.supported_options2 &
 		AAC_OPTION_POWER_MANAGEMENT)
 		len += snprintf(buf + len, PAGE_SIZE - len,
 				"SUPPORTED_POWER_MANAGEMENT\n");
@@ -1139,12 +1141,12 @@ static ssize_t aac_show_serial_number(struct device *device,
 		len = snprintf(buf, 16, "%06X\n",
 		  le32_to_cpu(dev->adapter_info.serial[0]));
 	if (len &&
-	  !memcmp(&dev->supplement_adapter_info.MfgPcbaSerialNo[
-	    sizeof(dev->supplement_adapter_info.MfgPcbaSerialNo)-len],
+	  !memcmp(&dev->supplement_adapter_info.mfg_pcba_serial_no[
+	    sizeof(dev->supplement_adapter_info.mfg_pcba_serial_no)-len],
 	  buf, len-1))
 		len = snprintf(buf, 16, "%.*s\n",
-		  (int)sizeof(dev->supplement_adapter_info.MfgPcbaSerialNo),
-		  dev->supplement_adapter_info.MfgPcbaSerialNo);
+		  (int)sizeof(dev->supplement_adapter_info.mfg_pcba_serial_no),
+		  dev->supplement_adapter_info.mfg_pcba_serial_no);
 
 	return min(len, 16);
 }
diff --git a/drivers/scsi/aacraid/rx.c b/drivers/scsi/aacraid/rx.c
index 0e69a80c3275..5d19c31e3bba 100644
--- a/drivers/scsi/aacraid/rx.c
+++ b/drivers/scsi/aacraid/rx.c
@@ -475,7 +475,7 @@ static int aac_rx_restart_adapter(struct aac_dev *dev, int bled, u8 reset_type)
 {
 	u32 var = 0;
 
-	if (!(dev->supplement_adapter_info.SupportedOptions2 &
+	if (!(dev->supplement_adapter_info.supported_options2 &
 	  AAC_OPTION_MU_RESET) || (bled >= 0) || (bled == -2)) {
 		if (bled)
 			printk(KERN_ERR "%s%d: adapter kernel panic'd %x.\n",
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 8e4e2ddbafd7..c17b0603749c 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -684,7 +684,7 @@ static void aac_send_iop_reset(struct aac_dev *dev, int bled)
 
 	aac_set_intx_mode(dev);
 
-	if (!bled && (dev->supplement_adapter_info.SupportedOptions2 &
+	if (!bled && (dev->supplement_adapter_info.supported_options2 &
 	    AAC_OPTION_DOORBELL_RESET)) {
 		src_writel(dev, MUnit.IDR, reset_mask);
 	} else {
-- 
GitLab


From f3ef4a74dc3712ef0ce60d652aa87b1ba70cb2a4 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:11 -0800
Subject: [PATCH 122/898] scsi: aacraid: Use correct channel number for raw srb

The channel being used for raw srb commands is retrieved from the utility
sent fibs and is converted into physical channel id. The driver does not
need to to do this since the management utility sends the correct channel
id in the first place and in addition the driver sets inaccurate
information in the cmd sent to the firmware and gets an invalid response.

Fixed by using channel id from srb command.

Cc: stable@vger.kernel.org
Fixes: 423400e64d377c0 ("scsi: aacraid: Include HBA direct interface")
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commctrl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 614842a9eb07..f6afd50579c0 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -580,7 +580,7 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 		goto cleanup;
 	}
 
-	chn = aac_logical_to_phys(user_srbcmd->channel);
+	chn = user_srbcmd->channel;
 	if (chn < AAC_MAX_BUSES && user_srbcmd->id < AAC_MAX_TARGETS &&
 		dev->hba_map[chn][user_srbcmd->id].devtype ==
 		AAC_DEVTYPE_NATIVE_RAW) {
-- 
GitLab


From 16ae9dd35d374182ce955063100fce66a9974e74 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:12 -0800
Subject: [PATCH 123/898] scsi: aacraid: Fix for excessive prints on EEH

This issue showed up on a kdump debug(single CPU on powerkvm), when EEH
errors rendered the adapter unusable. The driver correctly detected the
issue and attempted to restart the controller, in doing so the driver
attempted to read the status registers of the controller. This triggered
additional eeh errors which continued for a good 6 minutes.

Fixed by returning without waiting when EEH error is reported.

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 39 +++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 56090f5be6c5..a8dd4b51b086 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -461,6 +461,35 @@ int aac_queue_get(struct aac_dev * dev, u32 * index, u32 qid, struct hw_fib * hw
 	return 0;
 }
 
+#ifdef CONFIG_EEH
+static inline int aac_check_eeh_failure(struct aac_dev *dev)
+{
+	/* Check for an EEH failure for the given
+	 * device node. Function eeh_dev_check_failure()
+	 * returns 0 if there has not been an EEH error
+	 * otherwise returns a non-zero value.
+	 *
+	 * Need to be called before any PCI operation,
+	 * i.e.,before aac_adapter_check_health()
+	 */
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev->pdev);
+
+	if (eeh_dev_check_failure(edev)) {
+		/* The EEH mechanisms will handle this
+		 * error and reset the device if
+		 * necessary.
+		 */
+		return 1;
+	}
+	return 0;
+}
+#else
+static inline int aac_check_eeh_failure(struct aac_dev *dev)
+{
+	return 0;
+}
+#endif
+
 /*
  *	Define the highest level of host to adapter communication routines.
  *	These routines will support host to adapter FS commuication. These
@@ -496,7 +525,6 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 	unsigned long mflags = 0;
 	unsigned long sflags = 0;
 
-
 	if (!(hw_fib->header.XferState & cpu_to_le32(HostOwned)))
 		return -EBUSY;
 	/*
@@ -662,6 +690,10 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 					}
 					return -ETIMEDOUT;
 				}
+
+				if (aac_check_eeh_failure(dev))
+					return -EFAULT;
+
 				if ((blink = aac_adapter_check_health(dev)) > 0) {
 					if (wait == -1) {
 	        				printk(KERN_ERR "aacraid: aac_fib_send: adapter blinkLED 0x%x.\n"
@@ -755,7 +787,12 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
 	FIB_COUNTER_INCREMENT(aac_config.NativeSent);
 
 	if (wait) {
+
 		spin_unlock_irqrestore(&fibptr->event_lock, flags);
+
+		if (aac_check_eeh_failure(dev))
+			return -EFAULT;
+
 		/* Only set for first known interruptable command */
 		if (down_interruptible(&fibptr->event_wait)) {
 			fibptr->done = 2;
-- 
GitLab


From a0c6143e95c5b9e1f2d83e005e4e86ed3dc6096f Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:13 -0800
Subject: [PATCH 124/898] scsi: aacraid: Prevent E3 lockup when deleting units

Arrconf management utility at times sends fibs with AdapterProcessed set
in its fibs. This causes the controller to panic and lockup.

Fixed by failing the commands that have AdapterProcessed set in its flag.

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index a8dd4b51b086..e221321d97d2 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -527,6 +527,10 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 
 	if (!(hw_fib->header.XferState & cpu_to_le32(HostOwned)))
 		return -EBUSY;
+
+	if (hw_fib->header.XferState & cpu_to_le32(AdapterProcessed))
+		return -EINVAL;
+
 	/*
 	 *	There are 5 cases with the wait and response requested flags.
 	 *	The only invalid cases are if the caller requests to wait and
-- 
GitLab


From 1bff5abca65d4b9761fcc992ab6288243220003d Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:14 -0800
Subject: [PATCH 125/898] scsi: aacraid: Fix memory leak in fib init path

aac_fib_map_free frees misaligned fib dma memory, additionally it does not
free up the whole memory.

Fixed by changing the  code to free up the correct and full memory
allocation.

Cc: stable@vger.kernel.org
Fixes: e8b12f0fb835223 ([SCSI] aacraid: Add new code for PMC-Sierra's SRC based controller family)
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 36 ++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index e221321d97d2..c10954b3cd46 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -95,12 +95,20 @@ static int fib_map_alloc(struct aac_dev *dev)
 
 void aac_fib_map_free(struct aac_dev *dev)
 {
-	if (dev->hw_fib_va && dev->max_cmd_size) {
-		pci_free_consistent(dev->pdev,
-		(dev->max_cmd_size *
-		(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB)),
-		dev->hw_fib_va, dev->hw_fib_pa);
-	}
+	size_t alloc_size;
+	size_t fib_size;
+	int num_fibs;
+
+	if(!dev->hw_fib_va || !dev->max_cmd_size)
+		return;
+
+	num_fibs = dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB;
+	fib_size = dev->max_fib_size + sizeof(struct aac_fib_xporthdr);
+	alloc_size = fib_size * num_fibs + ALIGN32 - 1;
+
+	pci_free_consistent(dev->pdev, alloc_size, dev->hw_fib_va,
+							dev->hw_fib_pa);
+
 	dev->hw_fib_va = NULL;
 	dev->hw_fib_pa = 0;
 }
@@ -153,22 +161,20 @@ int aac_fib_setup(struct aac_dev * dev)
 	if (i<0)
 		return -ENOMEM;
 
-	/* 32 byte alignment for PMC */
-	hw_fib_pa = (dev->hw_fib_pa + (ALIGN32 - 1)) & ~(ALIGN32 - 1);
-	dev->hw_fib_va = (struct hw_fib *)((unsigned char *)dev->hw_fib_va +
-		(hw_fib_pa - dev->hw_fib_pa));
-	dev->hw_fib_pa = hw_fib_pa;
 	memset(dev->hw_fib_va, 0,
 		(dev->max_cmd_size + sizeof(struct aac_fib_xporthdr)) *
 		(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB));
 
+	/* 32 byte alignment for PMC */
+	hw_fib_pa = (dev->hw_fib_pa + (ALIGN32 - 1)) & ~(ALIGN32 - 1);
+	hw_fib    = (struct hw_fib *)((unsigned char *)dev->hw_fib_va +
+					(hw_fib_pa - dev->hw_fib_pa));
+
 	/* add Xport header */
-	dev->hw_fib_va = (struct hw_fib *)((unsigned char *)dev->hw_fib_va +
+	hw_fib = (struct hw_fib *)((unsigned char *)hw_fib +
 		sizeof(struct aac_fib_xporthdr));
-	dev->hw_fib_pa += sizeof(struct aac_fib_xporthdr);
+	hw_fib_pa += sizeof(struct aac_fib_xporthdr);
 
-	hw_fib = dev->hw_fib_va;
-	hw_fib_pa = dev->hw_fib_pa;
 	/*
 	 *	Initialise the fibs
 	 */
-- 
GitLab


From 30202e067a81754cb78cb823b7ce7e7cddd040e2 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:15 -0800
Subject: [PATCH 126/898] scsi: aacraid: Added sysfs for driver version

Added support to retrieve driver version from a new sysfs variable called
driver_version. It makes it easier for the user to figure out the driver
version that is currently running.

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/linit.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index ab4f1e7870b9..df027847f208 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -1131,6 +1131,13 @@ static ssize_t aac_show_bios_version(struct device *device,
 	return len;
 }
 
+static ssize_t aac_show_driver_version(struct device *device,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%s\n", aac_driver_version);
+}
+
 static ssize_t aac_show_serial_number(struct device *device,
 			       struct device_attribute *attr, char *buf)
 {
@@ -1241,6 +1248,13 @@ static struct device_attribute aac_bios_version = {
 	},
 	.show = aac_show_bios_version,
 };
+static struct device_attribute aac_lld_version = {
+	.attr = {
+		.name = "driver_version",
+		.mode = 0444,
+	},
+	.show = aac_show_driver_version,
+};
 static struct device_attribute aac_serial_number = {
 	.attr = {
 		.name = "serial_number",
@@ -1278,6 +1292,7 @@ static struct device_attribute *aac_attrs[] = {
 	&aac_kernel_version,
 	&aac_monitor_version,
 	&aac_bios_version,
+	&aac_lld_version,
 	&aac_serial_number,
 	&aac_max_channel,
 	&aac_max_id,
-- 
GitLab


From a7e2c642844cfefd570cb54a8d9fe7b85605311b Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:16 -0800
Subject: [PATCH 127/898] scsi: aacraid: Fix sync fibs time out on controller
 reset

After controller shutdown, all sync fibs time out due to not knowing
about the switch to INT-x mode

Fixed by replacing aac_src_access_devreg() to aac_set_intx_mode() call.

Cc: stable@vger.kernel.org
Fixes: 495c021767bd78c998 (aacraid: MSI-x support)
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/aacraid.h  | 1 +
 drivers/scsi/aacraid/comminit.c | 2 +-
 drivers/scsi/aacraid/src.c      | 2 +-
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index b5a2c87f289b..9281e7295480 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -2639,6 +2639,7 @@ void aac_hba_callback(void *context, struct fib *fibptr);
 #define fib_data(fibctx) ((void *)(fibctx)->hw_fib_va->data)
 struct aac_dev *aac_init_adapter(struct aac_dev *dev);
 void aac_src_access_devreg(struct aac_dev *dev, int mode);
+void aac_set_intx_mode(struct aac_dev *dev);
 int aac_get_config_status(struct aac_dev *dev, int commit_flag);
 int aac_get_containers(struct aac_dev *dev);
 int aac_scsi_cmd(struct scsi_cmnd *cmd);
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 40bfc57b6849..35607005f7e1 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -330,7 +330,7 @@ int aac_send_shutdown(struct aac_dev * dev)
 	     dev->pdev->device == PMC_DEVICE_S8 ||
 	     dev->pdev->device == PMC_DEVICE_S9) &&
 	     dev->msi_enabled)
-		aac_src_access_devreg(dev, AAC_ENABLE_INTX);
+		aac_set_intx_mode(dev);
 	return status;
 }
 
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index c17b0603749c..b23c818adbf6 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -657,7 +657,7 @@ static int aac_srcv_ioremap(struct aac_dev *dev, u32 size)
 	return 0;
 }
 
-static void aac_set_intx_mode(struct aac_dev *dev)
+void aac_set_intx_mode(struct aac_dev *dev)
 {
 	if (dev->msi_enabled) {
 		aac_src_access_devreg(dev, AAC_ENABLE_INTX);
-- 
GitLab


From 849ac6a591bf7b5777fdb6ce65030f32a7c73e1a Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:17 -0800
Subject: [PATCH 128/898] scsi: aacraid: Skip wellness sync on controller
 failure

aac_command_thread checks on the health of controller periodically,
using aac_check_health. If the status is an error state KERNEL_PANIC or
anything else. The driver will attempt to restart the adapter, but the
response is not checked in aac_command_thread. This allows the periodic
sync to go thru and lead the driver to a hung state.

Fixed by terminating the periodic loop(intended per original design),
if the controller is not restored to a healthy state.

Cc: stable@vger.kernel.org
Fixes: 3d77d8404478353358 (scsi: aacraid: Added support for periodic wellness sync)
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index c10954b3cd46..eb4d8cfc3194 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -2481,7 +2481,7 @@ int aac_command_thread(void *data)
 
 			/* Don't even try to talk to adapter if its sick */
 			ret = aac_check_health(dev);
-			if (!dev->queues)
+			if (ret || !dev->queues)
 				break;
 			next_check_jiffies = jiffies
 					   + ((long)(unsigned)check_interval)
-- 
GitLab


From a2d0321dd532901ea64118ed5a752fa6e447d1da Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:18 -0800
Subject: [PATCH 129/898] scsi: aacraid: Reload offlined drives after
 controller reset

During the IOP reset stress testing, it was found that the drives can be
marked offline when the adapter controller crashes and IO's are running
in parallel. When the controller  does come back from the reset, the drive
that is marked offline is not exposed.

Fixed by removing and adding drives that are marked offline. In addition
invoke a scsi host bus rescan to capture any additional configuration
changes.

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index eb4d8cfc3194..1f716c01708b 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1637,11 +1637,29 @@ static int _aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 		command->SCp.phase = AAC_OWNER_ERROR_HANDLER;
 		command->scsi_done(command);
 	}
+	/*
+	 * Any Device that was already marked offline needs to be cleaned up
+	 */
+	__shost_for_each_device(dev, host) {
+		if (!scsi_device_online(dev)) {
+			sdev_printk(KERN_INFO, dev, "Removing offline device\n");
+			scsi_remove_device(dev);
+			scsi_device_put(dev);
+		}
+	}
 	retval = 0;
 
 out:
 	aac->in_reset = 0;
 	scsi_unblock_requests(host);
+	/*
+	 * Issue bus rescan to catch any configuration that might have
+	 * occurred
+	 */
+	if (!retval) {
+		dev_info(&aac->pdev->dev, "Issuing bus rescan\n");
+		scsi_scan_host(host);
+	}
 	if (jafo) {
 		spin_lock_irq(host->host_lock);
 	}
-- 
GitLab


From 11da1b7c4856de05e00f50f54efe2f5349214d5b Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:19 -0800
Subject: [PATCH 130/898] scsi: aacraid: Decrease adapter health check interval

Currently driver checks the health status of the adapter once every 24
hours. When that happens the driver becomes dependent on the kernel to
figure out if the  adapter is misbehaving. This might take some time
(when the adapter is idle). The driver currently has support to
restart/recover the controller when it fails, and decreasing the time
interval will help.

Fixed by decreasing check interval from 24 hours to 1 minute

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/aachba.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 98d4ffd798c5..3ede50f25f46 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -311,7 +311,7 @@ module_param(update_interval, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(update_interval, "Interval in seconds between time sync"
 	" updates issued to adapter.");
 
-int check_interval = 24 * 60 * 60;
+int check_interval = 60;
 module_param(check_interval, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(check_interval, "Interval in seconds between adapter health"
 	" checks.");
-- 
GitLab


From 146aa1786d4978795cab5347d810e00236dea1c3 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:20 -0800
Subject: [PATCH 131/898] scsi: aacraid: Skip IOP reset on controller
 panic(SMART Family)

When the SMART family of controller panic (KERNEL_PANIC) , they do not
honor IOP resets. So better to skip it and directly perform a IWBR reset.

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/src.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index b23c818adbf6..9b11e1a6cc75 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -714,6 +714,12 @@ static int aac_src_restart_adapter(struct aac_dev *dev, int bled, u8 reset_type)
 		pr_err("%s%d: adapter kernel panic'd %x.\n",
 				dev->name, dev->id, bled);
 
+	/*
+	 * When there is a BlinkLED, IOP_RESET has not effect
+	 */
+	if (bled >= 2 && dev->sa_firmware && reset_type & HW_IOP_RESET)
+		reset_type &= ~HW_IOP_RESET;
+
 	dev->a_ops.adapter_enable_int = aac_src_disable_interrupt;
 
 	switch (reset_type) {
-- 
GitLab


From c421530bf848604e97d0785a03b3fe2c62775083 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:21 -0800
Subject: [PATCH 132/898] scsi: aacraid: Reorder Adapter status check

The driver currently checks the SELF_TEST_FAILED first and then
KERNEL_PANIC next. Under error conditions(boot code failure) both
SELF_TEST_FAILED and KERNEL_PANIC can be set at the same time.

The driver has the capability to reset the controller on an KERNEL_PANIC,
but not on SELF_TEST_FAILED.

Fixed by first checking KERNEL_PANIC and then the others.

Cc: stable@vger.kernel.org
Fixes: e8b12f0fb835223752 ([SCSI] aacraid: Add new code for PMC-Sierra's SRC base controller family)
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/src.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 9b11e1a6cc75..71aaabde6b57 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -436,17 +436,24 @@ static int aac_src_check_health(struct aac_dev *dev)
 {
 	u32 status = src_readl(dev, MUnit.OMR);
 
+	/*
+	 *	Check to see if the board panic'd.
+	 */
+	if (unlikely(status & KERNEL_PANIC))
+		goto err_blink;
+
 	/*
 	 *	Check to see if the board failed any self tests.
 	 */
 	if (unlikely(status & SELF_TEST_FAILED))
-		return -1;
+		goto err_out;
 
 	/*
-	 *	Check to see if the board panic'd.
+	 *	Check to see if the board failed any self tests.
 	 */
-	if (unlikely(status & KERNEL_PANIC))
-		return (status >> 16) & 0xFF;
+	if (unlikely(status & MONITOR_PANIC))
+		goto err_out;
+
 	/*
 	 *	Wait for the adapter to be up and running.
 	 */
@@ -456,6 +463,12 @@ static int aac_src_check_health(struct aac_dev *dev)
 	 *	Everything is OK
 	 */
 	return 0;
+
+err_out:
+	return -1;
+
+err_blink:
+	return (status > 16) & 0xFF;
 }
 
 static inline u32 aac_get_vector(struct aac_dev *dev)
-- 
GitLab


From 09624645e1e85df8d68b04de6e0607d696268333 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:22 -0800
Subject: [PATCH 133/898] scsi: aacraid: Save adapter fib log before an IOP
 reset

Currently  the adapter firmware does not save outstanding I/O's log
information  when an IOP reset is triggered. This is problematic when
trying to root cause and debug issues.

Fixed by adding sync command to trigger I/O log file save in the adapter
firmware before issuing an IOP reset.

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/aachba.c  |  4 ++++
 drivers/scsi/aacraid/aacraid.h |  6 ++++++
 drivers/scsi/aacraid/src.c     | 17 +++++++++++++++++
 3 files changed, 27 insertions(+)

diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 3ede50f25f46..e3e93def722b 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -294,6 +294,10 @@ MODULE_PARM_DESC(aif_timeout, "The duration of time in seconds to wait for"
 	"deregistering them. This is typically adjusted for heavily burdened"
 	" systems.");
 
+int aac_fib_dump;
+module_param(aac_fib_dump, int, 0644);
+MODULE_PARM_DESC(aac_fib_dump, "Dump controller fibs prior to IOP_RESET 0=off, 1=on");
+
 int numacb = -1;
 module_param(numacb, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(numacb, "Request a limit to the number of adapter control"
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 9281e7295480..622fd69b35cc 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1444,6 +1444,10 @@ struct aac_supplement_adapter_info
 #define AAC_OPTION_VARIABLE_BLOCK_SIZE	cpu_to_le32(0x00040000)
 /* 240 simple volume support */
 #define AAC_OPTION_SUPPORTED_240_VOLUMES cpu_to_le32(0x10000000)
+/*
+ * Supports FIB dump sync command send prior to IOP_RESET
+ */
+#define AAC_OPTION_SUPPORTED3_IOP_RESET_FIB_DUMP	cpu_to_le32(0x00004000)
 #define AAC_SIS_VERSION_V3	3
 #define AAC_SIS_SLOT_UNKNOWN	0xFF
 
@@ -2483,6 +2487,7 @@ struct aac_hba_info {
 #define GET_DRIVER_BUFFER_PROPERTIES	0x00000023
 #define RCV_TEMP_READINGS		0x00000025
 #define GET_COMM_PREFERRED_SETTINGS	0x00000026
+#define IOP_RESET_FW_FIB_DUMP		0x00000034
 #define IOP_RESET			0x00001000
 #define IOP_RESET_ALWAYS		0x00001001
 #define RE_INIT_ADAPTER			0x000000ee
@@ -2686,4 +2691,5 @@ extern int aac_commit;
 extern int update_interval;
 extern int check_interval;
 extern int aac_check_reset;
+extern int aac_fib_dump;
 #endif
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 71aaabde6b57..2e5338dec621 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -679,10 +679,27 @@ void aac_set_intx_mode(struct aac_dev *dev)
 	}
 }
 
+static void aac_dump_fw_fib_iop_reset(struct aac_dev *dev)
+{
+	__le32 supported_options3;
+
+	if (!aac_fib_dump)
+		return;
+
+	supported_options3  = dev->supplement_adapter_info.supported_options3;
+	if (!(supported_options3 & AAC_OPTION_SUPPORTED3_IOP_RESET_FIB_DUMP))
+		return;
+
+	aac_adapter_sync_cmd(dev, IOP_RESET_FW_FIB_DUMP,
+			0, 0, 0,  0, 0, 0, NULL, NULL, NULL, NULL, NULL);
+}
+
 static void aac_send_iop_reset(struct aac_dev *dev, int bled)
 {
 	u32 var, reset_mask;
 
+	aac_dump_fw_fib_iop_reset(dev);
+
 	bled = aac_adapter_sync_cmd(dev, IOP_RESET_ALWAYS,
 				    0, 0, 0, 0, 0, 0, &var,
 				    &reset_mask, NULL, NULL, NULL);
-- 
GitLab


From d844752e1801099f92c178845f56412861a2b4af Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:23 -0800
Subject: [PATCH 134/898] scsi: aacraid: Fix a potential spinlock double unlock
 bug

The driver does not unlock the reply  queue spin lock after handling SMART
adapter events. Instead it might attempt to unlock an already unlocked
spin lock.

Fixed by making sure the driver locks the spin lock before freeing it.

Thank you dan for finding this issue out.

Fixes: 6223a39fe6fbbeef (scsi: aacraid: Added support for hotplug)
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 1f716c01708b..a2ea70d8a13a 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -2215,7 +2215,7 @@ static void aac_process_events(struct aac_dev *dev)
 			/* Thor AIF */
 			aac_handle_sa_aif(dev, fib);
 			aac_fib_adapter_complete(fib, (u16)sizeof(u32));
-			continue;
+			goto free_fib;
 		}
 		/*
 		 *	We will process the FIB here or pass it to a
-- 
GitLab


From 0662cc968aceaca34848e63f431e585f4f71f746 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Thu, 16 Feb 2017 12:51:24 -0800
Subject: [PATCH 135/898] scsi: aacraid: Update driver version

Updated driver version to 50792

Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: David Carroll <David.Carroll@microsemi.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/aacraid.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 622fd69b35cc..d036a806f31c 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -97,7 +97,7 @@ enum {
 #define	PMC_GLOBAL_INT_BIT0		0x00000001
 
 #ifndef AAC_DRIVER_BUILD
-# define AAC_DRIVER_BUILD 50740
+# define AAC_DRIVER_BUILD 50792
 # define AAC_DRIVER_BRANCH "-custom"
 #endif
 #define MAXIMUM_NUM_CONTAINERS	32
-- 
GitLab


From ed10858eadd4988260c6bc7d75fc25176342b5a7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 17 Feb 2017 16:03:52 +0100
Subject: [PATCH 136/898] scsi: smartpqi: fix time handling

When we have turned off RTC support, the smartpqi driver fails to build:

ERROR: "rtc_time64_to_tm" [drivers/scsi/smartpqi/smartpqi.ko] undefined!

This is easily avoided by using the generic 'struct tm' based helper rather
than the RTC specific one. While fixing this, I noticed that even though
the driver uses time64_t for storing seconds, it gets them from the
old 32-bit struct timeval. To address this, we can simplify the code
by calling ktime_get_real_seconds() directly.

Fixes: 6c223761eb54 ("smartpqi: initial commit of Microsemi smartpqi driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 11c0dfb3dfa3..657ad15682a3 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -534,8 +534,7 @@ static int pqi_write_current_time_to_host_wellness(
 	size_t buffer_length;
 	time64_t local_time;
 	unsigned int year;
-	struct timeval time;
-	struct rtc_time tm;
+	struct tm tm;
 
 	buffer_length = sizeof(*buffer);
 
@@ -552,9 +551,8 @@ static int pqi_write_current_time_to_host_wellness(
 	put_unaligned_le16(sizeof(buffer->time),
 		&buffer->time_length);
 
-	do_gettimeofday(&time);
-	local_time = time.tv_sec - (sys_tz.tz_minuteswest * 60);
-	rtc_time64_to_tm(local_time, &tm);
+	local_time = ktime_get_real_seconds();
+	time64_to_tm(local_time, -sys_tz.tz_minuteswest * 60, &tm);
 	year = tm.tm_year + 1900;
 
 	buffer->time[0] = bin2bcd(tm.tm_hour);
-- 
GitLab


From f22aaec97d889f3fbf89b185309bdc98b8202eda Mon Sep 17 00:00:00 2001
From: Subhash Jadavani <subhashj@codeaurora.org>
Date: Fri, 17 Feb 2017 13:53:41 -0800
Subject: [PATCH 137/898] scsi: ufs-qcom: remove redundant condition check

Dan Carpenter <dan.carpenter@oracle.com> reported this:

The patch 9c46b8676271: "scsi: ufs-qcom: dump additional testbus
registers" from Feb 3, 2017, leads to the following static checker
warning:

    drivers/scsi/ufs/ufs-qcom.c:1531 ufs_qcom_testbus_cfg_is_ok()
    warn: impossible condition
                '(host->testbus.select_minor > 255) => (0-255 > 255)'

drivers/scsi/ufs/ufs-qcom.c
  1517  static bool ufs_qcom_testbus_cfg_is_ok(struct ufs_qcom_host *host)
  1518  {
  1519          if (host->testbus.select_major >= TSTBUS_MAX) {
  1520               dev_err(host->hba->dev,
  1521                 "%s: UFS_CFG1[TEST_BUS_SEL} may not equal 0x%05X\n",
  1522                  __func__, host->testbus.select_major);
  1523                  return false;
  1524          }
  1525
  1526          /*
  1527           * Not performing check for each individual select_major
  1528           * mappings of select_minor, since there is no harm in
  1529           * configuring a non-existent select_minor
  1530           */
  1531          if (host->testbus.select_minor > 0xFF) {
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

It might make sense to keep this check.  I don't know.  But it's
confusing that 0xFF is a magic number.  Better to make it a define.

  1532                  dev_err(host->hba->dev,
  1533                       "%s: 0x%05X is not a legal testbus option\n",
  1534                        __func__, host->testbus.select_minor);
  1535                  return false;
  1536          }
  1537
  1538          return true;
  1539  }
---

As data type of "select_minor" is u8, above check is redundant. This
change removes it.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Subhash Jadavani <subhashj@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufs-qcom.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index ce5d023c1c91..c87d770b519a 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -1523,18 +1523,6 @@ static bool ufs_qcom_testbus_cfg_is_ok(struct ufs_qcom_host *host)
 		return false;
 	}
 
-	/*
-	 * Not performing check for each individual select_major
-	 * mappings of select_minor, since there is no harm in
-	 * configuring a non-existent select_minor
-	 */
-	if (host->testbus.select_minor > 0xFF) {
-		dev_err(host->hba->dev,
-			"%s: 0x%05X is not a legal testbus option\n",
-			__func__, host->testbus.select_minor);
-		return false;
-	}
-
 	return true;
 }
 
-- 
GitLab


From 857de6e00778738dc3d61f75acbac35bdc48e533 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 17 Feb 2017 09:02:45 +0100
Subject: [PATCH 138/898] scsi: use 'scsi_device_from_queue()' for scsi_dh

The device handler needs to check if a given queue belongs to a scsi
device; only then does it make sense to attach a device handler.

[mkp: dropped flags]

Cc: <stable@vger.kernel.org>
Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_dh.c     | 22 ++++------------------
 drivers/scsi/scsi_lib.c    | 23 +++++++++++++++++++++++
 include/scsi/scsi_device.h |  1 +
 3 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c
index b8d3b97b217a..84addee05be6 100644
--- a/drivers/scsi/scsi_dh.c
+++ b/drivers/scsi/scsi_dh.c
@@ -219,20 +219,6 @@ int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh)
 }
 EXPORT_SYMBOL_GPL(scsi_unregister_device_handler);
 
-static struct scsi_device *get_sdev_from_queue(struct request_queue *q)
-{
-	struct scsi_device *sdev;
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	sdev = q->queuedata;
-	if (!sdev || !get_device(&sdev->sdev_gendev))
-		sdev = NULL;
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
-	return sdev;
-}
-
 /*
  * scsi_dh_activate - activate the path associated with the scsi_device
  *      corresponding to the given request queue.
@@ -251,7 +237,7 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data)
 	struct scsi_device *sdev;
 	int err = SCSI_DH_NOSYS;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev) {
 		if (fn)
 			fn(data, err);
@@ -298,7 +284,7 @@ int scsi_dh_set_params(struct request_queue *q, const char *params)
 	struct scsi_device *sdev;
 	int err = -SCSI_DH_NOSYS;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev)
 		return err;
 
@@ -321,7 +307,7 @@ int scsi_dh_attach(struct request_queue *q, const char *name)
 	struct scsi_device_handler *scsi_dh;
 	int err = 0;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev)
 		return -ENODEV;
 
@@ -359,7 +345,7 @@ const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp)
 	struct scsi_device *sdev;
 	const char *handler_name = NULL;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev)
 		return NULL;
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 912fbc3b4543..39b2d727f033 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2231,6 +2231,29 @@ void scsi_mq_destroy_tags(struct Scsi_Host *shost)
 	blk_mq_free_tag_set(&shost->tag_set);
 }
 
+/**
+ * scsi_device_from_queue - return sdev associated with a request_queue
+ * @q: The request queue to return the sdev from
+ *
+ * Return the sdev associated with a request queue or NULL if the
+ * request_queue does not reference a SCSI device.
+ */
+struct scsi_device *scsi_device_from_queue(struct request_queue *q)
+{
+	struct scsi_device *sdev = NULL;
+
+	if (q->mq_ops) {
+		if (q->mq_ops == &scsi_mq_ops)
+			sdev = q->queuedata;
+	} else if (q->request_fn == scsi_request_fn)
+		sdev = q->queuedata;
+	if (!sdev || !get_device(&sdev->sdev_gendev))
+		sdev = NULL;
+
+	return sdev;
+}
+EXPORT_SYMBOL_GPL(scsi_device_from_queue);
+
 /*
  * Function:    scsi_block_requests()
  *
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 8990e580b278..be41c76ddd48 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -315,6 +315,7 @@ extern void scsi_remove_device(struct scsi_device *);
 extern int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh);
 void scsi_attach_vpd(struct scsi_device *sdev);
 
+extern struct scsi_device *scsi_device_from_queue(struct request_queue *q);
 extern int scsi_device_get(struct scsi_device *);
 extern void scsi_device_put(struct scsi_device *);
 extern struct scsi_device *scsi_device_lookup(struct Scsi_Host *,
-- 
GitLab


From 943445200b049d5179b95297e5372d399c8ab0e2 Mon Sep 17 00:00:00 2001
From: "Matthew R. Ochs" <mrochs@linux.vnet.ibm.com>
Date: Thu, 16 Feb 2017 21:39:32 -0600
Subject: [PATCH 139/898] scsi: cxlflash: Enable PCI device ID for future IBM
 CXL Flash AFU

Add support for a future IBM Coherent Accelerator (CXL) flash AFU with
an ID of 0x0624.

Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com>
Signed-off-by: Uma Krishnan <ukrishn@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/cxlflash/main.c | 4 ++++
 drivers/scsi/cxlflash/main.h | 1 +
 2 files changed, 5 insertions(+)

diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 7069639e92bc..3061d8045382 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -2259,6 +2259,8 @@ static struct dev_dependent_vals dev_corsa_vals = { CXLFLASH_MAX_SECTORS,
 					0ULL };
 static struct dev_dependent_vals dev_flash_gt_vals = { CXLFLASH_MAX_SECTORS,
 					CXLFLASH_NOTIFY_SHUTDOWN };
+static struct dev_dependent_vals dev_briard_vals = { CXLFLASH_MAX_SECTORS,
+					CXLFLASH_NOTIFY_SHUTDOWN };
 
 /*
  * PCI device binding table
@@ -2268,6 +2270,8 @@ static struct pci_device_id cxlflash_pci_table[] = {
 	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_corsa_vals},
 	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_FLASH_GT,
 	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_flash_gt_vals},
+	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_BRIARD,
+	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_briard_vals},
 	{}
 };
 
diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h
index e43545c86bcf..0be2261e6312 100644
--- a/drivers/scsi/cxlflash/main.h
+++ b/drivers/scsi/cxlflash/main.h
@@ -25,6 +25,7 @@
 
 #define PCI_DEVICE_ID_IBM_CORSA		0x04F0
 #define PCI_DEVICE_ID_IBM_FLASH_GT	0x0600
+#define PCI_DEVICE_ID_IBM_BRIARD	0x0624
 
 /* Since there is only one target, make it 0 */
 #define CXLFLASH_TARGET		0
-- 
GitLab


From 8ea73db486cda442f0671f4bc9c03a76be398a28 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:25 -0800
Subject: [PATCH 140/898] scsi: lpfc: Correct WQ creation for pagesize

Correct WQ creation for pagesize

The driver was calculating the adapter command pagesize indicator from
the system pagesize. However, the buffers the driver allocates are only
one size (SLI4_PAGE_SIZE), so no calculation was necessary.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_hw4.h | 2 ++
 drivers/scsi/lpfc/lpfc_sli.c | 9 +++++----
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 5646699b0516..964a1fdb076b 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1186,6 +1186,7 @@ struct lpfc_mbx_wq_create {
 #define lpfc_mbx_wq_create_page_size_SHIFT	0
 #define lpfc_mbx_wq_create_page_size_MASK	0x000000FF
 #define lpfc_mbx_wq_create_page_size_WORD	word1
+#define LPFC_WQ_PAGE_SIZE_4096	0x1
 #define lpfc_mbx_wq_create_wqe_size_SHIFT	8
 #define lpfc_mbx_wq_create_wqe_size_MASK	0x0000000F
 #define lpfc_mbx_wq_create_wqe_size_WORD	word1
@@ -1257,6 +1258,7 @@ struct rq_context {
 #define lpfc_rq_context_page_size_SHIFT	0		/* Version 1 Only */
 #define lpfc_rq_context_page_size_MASK	0x000000FF
 #define lpfc_rq_context_page_size_WORD	word0
+#define	LPFC_RQ_PAGE_SIZE_4096	0x1
 	uint32_t reserved1;
 	uint32_t word2;
 #define lpfc_rq_context_cq_id_SHIFT	16
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index d977a472f89f..586984dce3a4 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -13722,7 +13722,7 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 			       LPFC_WQ_WQE_SIZE_128);
 			bf_set(lpfc_mbx_wq_create_page_size,
 			       &wq_create->u.request_1,
-			       (PAGE_SIZE/SLI4_PAGE_SIZE));
+			       LPFC_WQ_PAGE_SIZE_4096);
 			page = wq_create->u.request_1.page;
 			break;
 		}
@@ -13748,8 +13748,9 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 			       LPFC_WQ_WQE_SIZE_128);
 			break;
 		}
-		bf_set(lpfc_mbx_wq_create_page_size, &wq_create->u.request_1,
-		       (PAGE_SIZE/SLI4_PAGE_SIZE));
+		bf_set(lpfc_mbx_wq_create_page_size,
+		       &wq_create->u.request_1,
+		       LPFC_WQ_PAGE_SIZE_4096);
 		page = wq_create->u.request_1.page;
 		break;
 	default:
@@ -13935,7 +13936,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 		       LPFC_RQE_SIZE_8);
 		bf_set(lpfc_rq_context_page_size,
 		       &rq_create->u.request.context,
-		       (PAGE_SIZE/SLI4_PAGE_SIZE));
+		       LPFC_RQ_PAGE_SIZE_4096);
 	} else {
 		switch (hrq->entry_count) {
 		default:
-- 
GitLab


From 45ffac1976c580ac20d926257b2f6320ce1b210f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 12 Feb 2017 13:52:26 -0800
Subject: [PATCH 141/898] scsi: lpfc: use pci_irq_alloc_vectors and
 pci_irq_free_vectors

This avoids having to store the msix_entries array and simpliefies the
shutdown and cleanup path a lot.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h      |   2 -
 drivers/scsi/lpfc/lpfc_init.c | 240 ++++++++--------------------------
 drivers/scsi/lpfc/lpfc_sli4.h |   1 -
 3 files changed, 54 insertions(+), 189 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 6593b073c524..64022d79117b 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -878,8 +878,6 @@ struct lpfc_hba {
 	enum intr_type_t intr_type;
 	uint32_t intr_mode;
 #define LPFC_INTR_ERROR	0xFFFFFFFF
-	struct msix_entry msix_entries[LPFC_MSIX_VECTORS];
-
 	struct list_head port_list;
 	struct lpfc_vport *pport;	/* physical lpfc_vport pointer */
 	uint16_t max_vpi;		/* Maximum virtual nports */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 64717c171b15..8cffad192f17 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -5509,17 +5509,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		goto out_free_fcf_rr_bmask;
 	}
 
-	phba->sli4_hba.msix_entries = kzalloc((sizeof(struct msix_entry) *
-				  (fof_vectors +
-				   phba->cfg_fcp_io_channel)), GFP_KERNEL);
-	if (!phba->sli4_hba.msix_entries) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"2573 Failed allocate memory for msi-x "
-				"interrupt vector entries\n");
-		rc = -ENOMEM;
-		goto out_free_fcp_eq_hdl;
-	}
-
 	phba->sli4_hba.cpu_map = kzalloc((sizeof(struct lpfc_vector_map_info) *
 					 phba->sli4_hba.num_present_cpu),
 					 GFP_KERNEL);
@@ -5528,7 +5517,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 				"3327 Failed allocate memory for msi-x "
 				"interrupt vector mapping\n");
 		rc = -ENOMEM;
-		goto out_free_msix;
+		goto out_free_fcp_eq_hdl;
 	}
 	if (lpfc_used_cpu == NULL) {
 		lpfc_used_cpu = kzalloc((sizeof(uint16_t) * lpfc_present_cpu),
@@ -5539,7 +5528,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 					"interrupt vector mapping\n");
 			kfree(phba->sli4_hba.cpu_map);
 			rc = -ENOMEM;
-			goto out_free_msix;
+			goto out_free_fcp_eq_hdl;
 		}
 		for (i = 0; i < lpfc_present_cpu; i++)
 			lpfc_used_cpu[i] = LPFC_VECTOR_MAP_EMPTY;
@@ -5574,8 +5563,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	return 0;
 
-out_free_msix:
-	kfree(phba->sli4_hba.msix_entries);
 out_free_fcp_eq_hdl:
 	kfree(phba->sli4_hba.fcp_eq_hdl);
 out_free_fcf_rr_bmask:
@@ -5611,9 +5598,6 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	phba->sli4_hba.num_online_cpu = 0;
 	phba->sli4_hba.curr_disp_cpu = 0;
 
-	/* Free memory allocated for msi-x interrupt vector entries */
-	kfree(phba->sli4_hba.msix_entries);
-
 	/* Free memory allocated for fast-path work queue handles */
 	kfree(phba->sli4_hba.fcp_eq_hdl);
 
@@ -8484,16 +8468,7 @@ lpfc_sli4_pci_mem_unset(struct lpfc_hba *phba)
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine is invoked to enable the MSI-X interrupt vectors to device
- * with SLI-3 interface specs. The kernel function pci_enable_msix_exact()
- * is called to enable the MSI-X vectors. Note that pci_enable_msix_exact(),
- * once invoked, enables either all or nothing, depending on the current
- * availability of PCI vector resources. The device driver is responsible
- * for calling the individual request_irq() to register each MSI-X vector
- * with a interrupt handler, which is done in this function. Note that
- * later when device is unloading, the driver should always call free_irq()
- * on all MSI-X vectors it has done request_irq() on before calling
- * pci_disable_msix(). Failure to do so results in a BUG_ON() and a device
- * will be left with MSI-X enabled and leaks its vectors.
+ * with SLI-3 interface specs.
  *
  * Return codes
  *   0 - successful
@@ -8502,33 +8477,24 @@ lpfc_sli4_pci_mem_unset(struct lpfc_hba *phba)
 static int
 lpfc_sli_enable_msix(struct lpfc_hba *phba)
 {
-	int rc, i;
+	int rc;
 	LPFC_MBOXQ_t *pmb;
 
 	/* Set up MSI-X multi-message vectors */
-	for (i = 0; i < LPFC_MSIX_VECTORS; i++)
-		phba->msix_entries[i].entry = i;
-
-	/* Configure MSI-X capability structure */
-	rc = pci_enable_msix_exact(phba->pcidev, phba->msix_entries,
-				   LPFC_MSIX_VECTORS);
-	if (rc) {
+	rc = pci_alloc_irq_vectors(phba->pcidev,
+			LPFC_MSIX_VECTORS, LPFC_MSIX_VECTORS, PCI_IRQ_MSIX);
+	if (rc < 0) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0420 PCI enable MSI-X failed (%d)\n", rc);
 		goto vec_fail_out;
 	}
-	for (i = 0; i < LPFC_MSIX_VECTORS; i++)
-		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"0477 MSI-X entry[%d]: vector=x%x "
-				"message=%d\n", i,
-				phba->msix_entries[i].vector,
-				phba->msix_entries[i].entry);
+
 	/*
 	 * Assign MSI-X vectors to interrupt handlers
 	 */
 
 	/* vector-0 is associated to slow-path handler */
-	rc = request_irq(phba->msix_entries[0].vector,
+	rc = request_irq(pci_irq_vector(phba->pcidev, 0),
 			 &lpfc_sli_sp_intr_handler, 0,
 			 LPFC_SP_DRIVER_HANDLER_NAME, phba);
 	if (rc) {
@@ -8539,7 +8505,7 @@ lpfc_sli_enable_msix(struct lpfc_hba *phba)
 	}
 
 	/* vector-1 is associated to fast-path handler */
-	rc = request_irq(phba->msix_entries[1].vector,
+	rc = request_irq(pci_irq_vector(phba->pcidev, 1),
 			 &lpfc_sli_fp_intr_handler, 0,
 			 LPFC_FP_DRIVER_HANDLER_NAME, phba);
 
@@ -8584,41 +8550,20 @@ lpfc_sli_enable_msix(struct lpfc_hba *phba)
 
 mem_fail_out:
 	/* free the irq already requested */
-	free_irq(phba->msix_entries[1].vector, phba);
+	free_irq(pci_irq_vector(phba->pcidev, 1), phba);
 
 irq_fail_out:
 	/* free the irq already requested */
-	free_irq(phba->msix_entries[0].vector, phba);
+	free_irq(pci_irq_vector(phba->pcidev, 0), phba);
 
 msi_fail_out:
 	/* Unconfigure MSI-X capability structure */
-	pci_disable_msix(phba->pcidev);
+	pci_free_irq_vectors(phba->pcidev);
 
 vec_fail_out:
 	return rc;
 }
 
-/**
- * lpfc_sli_disable_msix - Disable MSI-X interrupt mode on SLI-3 device.
- * @phba: pointer to lpfc hba data structure.
- *
- * This routine is invoked to release the MSI-X vectors and then disable the
- * MSI-X interrupt mode to device with SLI-3 interface spec.
- **/
-static void
-lpfc_sli_disable_msix(struct lpfc_hba *phba)
-{
-	int i;
-
-	/* Free up MSI-X multi-message vectors */
-	for (i = 0; i < LPFC_MSIX_VECTORS; i++)
-		free_irq(phba->msix_entries[i].vector, phba);
-	/* Disable MSI-X */
-	pci_disable_msix(phba->pcidev);
-
-	return;
-}
-
 /**
  * lpfc_sli_enable_msi - Enable MSI interrupt mode on SLI-3 device.
  * @phba: pointer to lpfc hba data structure.
@@ -8658,24 +8603,6 @@ lpfc_sli_enable_msi(struct lpfc_hba *phba)
 	return rc;
 }
 
-/**
- * lpfc_sli_disable_msi - Disable MSI interrupt mode to SLI-3 device.
- * @phba: pointer to lpfc hba data structure.
- *
- * This routine is invoked to disable the MSI interrupt mode to device with
- * SLI-3 interface spec. The driver calls free_irq() on MSI vector it has
- * done request_irq() on before calling pci_disable_msi(). Failure to do so
- * results in a BUG_ON() and a device will be left with MSI enabled and leaks
- * its vector.
- */
-static void
-lpfc_sli_disable_msi(struct lpfc_hba *phba)
-{
-	free_irq(phba->pcidev->irq, phba);
-	pci_disable_msi(phba->pcidev);
-	return;
-}
-
 /**
  * lpfc_sli_enable_intr - Enable device interrupt to SLI-3 device.
  * @phba: pointer to lpfc hba data structure.
@@ -8747,19 +8674,20 @@ lpfc_sli_enable_intr(struct lpfc_hba *phba, uint32_t cfg_mode)
 static void
 lpfc_sli_disable_intr(struct lpfc_hba *phba)
 {
-	/* Disable the currently initialized interrupt mode */
+	int nr_irqs, i;
+
 	if (phba->intr_type == MSIX)
-		lpfc_sli_disable_msix(phba);
-	else if (phba->intr_type == MSI)
-		lpfc_sli_disable_msi(phba);
-	else if (phba->intr_type == INTx)
-		free_irq(phba->pcidev->irq, phba);
+		nr_irqs = LPFC_MSIX_VECTORS;
+	else
+		nr_irqs = 1;
+
+	for (i = 0; i < nr_irqs; i++)
+		free_irq(pci_irq_vector(phba->pcidev, i), phba);
+	pci_free_irq_vectors(phba->pcidev);
 
 	/* Reset interrupt management states */
 	phba->intr_type = NONE;
 	phba->sli.slistat.sli_intr = 0;
-
-	return;
 }
 
 /**
@@ -8915,7 +8843,7 @@ lpfc_sli4_set_affinity(struct lpfc_hba *phba, int vectors)
 			lpfc_used_cpu[cpu] = phys_id;
 
 		/* Associate vector with selected CPU */
-		cpup->irq = phba->sli4_hba.msix_entries[idx].vector;
+		cpup->irq = pci_irq_vector(phba->pcidev, idx);
 
 		/* Associate IO channel with selected CPU */
 		cpup->channel_id = idx;
@@ -8925,14 +8853,14 @@ lpfc_sli4_set_affinity(struct lpfc_hba *phba, int vectors)
 			first_cpu = cpu;
 
 		/* Now affinitize to the selected CPU */
-		i = irq_set_affinity_hint(phba->sli4_hba.msix_entries[idx].
-					  vector, get_cpu_mask(cpu));
+		i = irq_set_affinity_hint(pci_irq_vector(phba->pcidev, idx),
+					  get_cpu_mask(cpu));
 
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"3330 Set Affinity: CPU %d channel %d "
 				"irq %d (%x)\n",
 				cpu, cpup->channel_id,
-				phba->sli4_hba.msix_entries[idx].vector, i);
+				pci_irq_vector(phba->pcidev, idx), i);
 
 		/* Spread vector mapping across multple physical CPU nodes */
 		phys_id++;
@@ -9047,14 +8975,7 @@ lpfc_sli4_set_affinity(struct lpfc_hba *phba, int vectors)
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine is invoked to enable the MSI-X interrupt vectors to device
- * with SLI-4 interface spec. The kernel function pci_enable_msix_range()
- * is called to enable the MSI-X vectors. The device driver is responsible
- * for calling the individual request_irq() to register each MSI-X vector
- * with a interrupt handler, which is done in this function. Note that
- * later when device is unloading, the driver should always call free_irq()
- * on all MSI-X vectors it has done request_irq() on before calling
- * pci_disable_msix(). Failure to do so results in a BUG_ON() and a device
- * will be left with MSI-X enabled and leaks its vectors.
+ * with SLI-4 interface spec.
  *
  * Return codes
  * 0 - successful
@@ -9066,17 +8987,11 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 	int vectors, rc, index;
 
 	/* Set up MSI-X multi-message vectors */
-	for (index = 0; index < phba->cfg_fcp_io_channel; index++)
-		phba->sli4_hba.msix_entries[index].entry = index;
-
-	/* Configure MSI-X capability structure */
 	vectors = phba->cfg_fcp_io_channel;
-	if (phba->cfg_fof) {
-		phba->sli4_hba.msix_entries[index].entry = index;
+	if (phba->cfg_fof)
 		vectors++;
-	}
-	rc = pci_enable_msix_range(phba->pcidev, phba->sli4_hba.msix_entries,
-				   2, vectors);
+
+	rc = pci_alloc_irq_vectors(phba->pcidev, 2, vectors, PCI_IRQ_MSIX);
 	if (rc < 0) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0484 PCI enable MSI-X failed (%d)\n", rc);
@@ -9084,14 +8999,6 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 	}
 	vectors = rc;
 
-	/* Log MSI-X vector assignment */
-	for (index = 0; index < vectors; index++)
-		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"0489 MSI-X entry[%d]: vector=x%x "
-				"message=%d\n", index,
-				phba->sli4_hba.msix_entries[index].vector,
-				phba->sli4_hba.msix_entries[index].entry);
-
 	/* Assign MSI-X vectors to interrupt handlers */
 	for (index = 0; index < vectors; index++) {
 		memset(&phba->sli4_hba.handler_name[index], 0, 16);
@@ -9103,14 +9010,12 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 		phba->sli4_hba.fcp_eq_hdl[index].phba = phba;
 		atomic_set(&phba->sli4_hba.fcp_eq_hdl[index].fcp_eq_in_use, 1);
 		if (phba->cfg_fof && (index == (vectors - 1)))
-			rc = request_irq(
-				phba->sli4_hba.msix_entries[index].vector,
+			rc = request_irq(pci_irq_vector(phba->pcidev, index),
 				 &lpfc_sli4_fof_intr_handler, 0,
 				 (char *)&phba->sli4_hba.handler_name[index],
 				 &phba->sli4_hba.fcp_eq_hdl[index]);
 		else
-			rc = request_irq(
-				phba->sli4_hba.msix_entries[index].vector,
+			rc = request_irq(pci_irq_vector(phba->pcidev, index),
 				 &lpfc_sli4_hba_intr_handler, 0,
 				 (char *)&phba->sli4_hba.handler_name[index],
 				 &phba->sli4_hba.fcp_eq_hdl[index]);
@@ -9140,48 +9045,19 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 cfg_fail_out:
 	/* free the irq already requested */
 	for (--index; index >= 0; index--) {
-		irq_set_affinity_hint(phba->sli4_hba.msix_entries[index].
-					  vector, NULL);
-		free_irq(phba->sli4_hba.msix_entries[index].vector,
-			 &phba->sli4_hba.fcp_eq_hdl[index]);
+		int irq = pci_irq_vector(phba->pcidev, index);
+
+		irq_set_affinity_hint(irq, NULL);
+		free_irq(irq, &phba->sli4_hba.fcp_eq_hdl[index]);
 	}
 
 	/* Unconfigure MSI-X capability structure */
-	pci_disable_msix(phba->pcidev);
+	pci_free_irq_vectors(phba->pcidev);
 
 vec_fail_out:
 	return rc;
 }
 
-/**
- * lpfc_sli4_disable_msix - Disable MSI-X interrupt mode to SLI-4 device
- * @phba: pointer to lpfc hba data structure.
- *
- * This routine is invoked to release the MSI-X vectors and then disable the
- * MSI-X interrupt mode to device with SLI-4 interface spec.
- **/
-static void
-lpfc_sli4_disable_msix(struct lpfc_hba *phba)
-{
-	int index;
-
-	/* Free up MSI-X multi-message vectors */
-	for (index = 0; index < phba->cfg_fcp_io_channel; index++) {
-		irq_set_affinity_hint(phba->sli4_hba.msix_entries[index].
-					  vector, NULL);
-		free_irq(phba->sli4_hba.msix_entries[index].vector,
-			 &phba->sli4_hba.fcp_eq_hdl[index]);
-	}
-	if (phba->cfg_fof) {
-		free_irq(phba->sli4_hba.msix_entries[index].vector,
-			 &phba->sli4_hba.fcp_eq_hdl[index]);
-	}
-	/* Disable MSI-X */
-	pci_disable_msix(phba->pcidev);
-
-	return;
-}
-
 /**
  * lpfc_sli4_enable_msi - Enable MSI interrupt mode to SLI-4 device
  * @phba: pointer to lpfc hba data structure.
@@ -9232,24 +9108,6 @@ lpfc_sli4_enable_msi(struct lpfc_hba *phba)
 	return 0;
 }
 
-/**
- * lpfc_sli4_disable_msi - Disable MSI interrupt mode to SLI-4 device
- * @phba: pointer to lpfc hba data structure.
- *
- * This routine is invoked to disable the MSI interrupt mode to device with
- * SLI-4 interface spec. The driver calls free_irq() on MSI vector it has
- * done request_irq() on before calling pci_disable_msi(). Failure to do so
- * results in a BUG_ON() and a device will be left with MSI enabled and leaks
- * its vector.
- **/
-static void
-lpfc_sli4_disable_msi(struct lpfc_hba *phba)
-{
-	free_irq(phba->pcidev->irq, phba);
-	pci_disable_msi(phba->pcidev);
-	return;
-}
-
 /**
  * lpfc_sli4_enable_intr - Enable device interrupt to SLI-4 device
  * @phba: pointer to lpfc hba data structure.
@@ -9335,18 +9193,28 @@ static void
 lpfc_sli4_disable_intr(struct lpfc_hba *phba)
 {
 	/* Disable the currently initialized interrupt mode */
-	if (phba->intr_type == MSIX)
-		lpfc_sli4_disable_msix(phba);
-	else if (phba->intr_type == MSI)
-		lpfc_sli4_disable_msi(phba);
-	else if (phba->intr_type == INTx)
+	if (phba->intr_type == MSIX) {
+		int index;
+
+		/* Free up MSI-X multi-message vectors */
+		for (index = 0; index < phba->cfg_fcp_io_channel; index++) {
+			int irq = pci_irq_vector(phba->pcidev, index);
+
+			irq_set_affinity_hint(irq, NULL);
+			free_irq(irq, &phba->sli4_hba.fcp_eq_hdl[index]);
+		}
+
+		if (phba->cfg_fof)
+			free_irq(pci_irq_vector(phba->pcidev, index), phba);
+	} else {
 		free_irq(phba->pcidev->irq, phba);
+	}
+
+	pci_free_irq_vectors(phba->pcidev);
 
 	/* Reset interrupt management states */
 	phba->intr_type = NONE;
 	phba->sli.slistat.sli_intr = 0;
-
-	return;
 }
 
 /**
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 0b88b5703e0f..dfbb25e5c5b6 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -515,7 +515,6 @@ struct lpfc_sli4_hba {
 	uint32_t ue_to_rp;
 	struct lpfc_register sli_intf;
 	struct lpfc_pc_sli4_params pc_sli4_params;
-	struct msix_entry *msix_entries;
 	uint8_t handler_name[LPFC_SLI4_HANDLER_CNT][LPFC_SLI4_HANDLER_NAME_SZ];
 	struct lpfc_fcp_eq_hdl *fcp_eq_hdl; /* FCP per-WQ handle */
 
-- 
GitLab


From 2ea259eead133026ac6a3fbfa040cc58a96cae44 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:27 -0800
Subject: [PATCH 142/898] scsi: lpfc: minor code cleanups

This contains code cleanups that were in the prior patch set.
This allows better review of real changes later.

minor code cleanups:
 fix indentation, punctuation, line length
 addition/reduction of whitespace
 remove unneeded parens, braces
 lpfc_debugfs_nodelist_data: print as u64 rather than byte by byte
 covert printk(KERN_ERR to pr_err
 small print string deltas
 use num_present_cpus() rather than count them
 comment updates
 rctl/type names moved to module variable, not on stack

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_attr.c    |  8 ++--
 drivers/scsi/lpfc/lpfc_bsg.c     |  2 +-
 drivers/scsi/lpfc/lpfc_debugfs.c | 81 +++++++++++++++-----------------
 drivers/scsi/lpfc/lpfc_hbadisc.c |  7 ++-
 drivers/scsi/lpfc/lpfc_init.c    | 19 ++++----
 drivers/scsi/lpfc/lpfc_scsi.c    |  3 +-
 drivers/scsi/lpfc/lpfc_scsi.h    | 12 ++---
 drivers/scsi/lpfc/lpfc_sli.c     | 48 ++++++++++---------
 drivers/scsi/lpfc/lpfc_sli.h     |  6 +--
 drivers/scsi/lpfc/lpfc_vport.c   |  1 +
 10 files changed, 98 insertions(+), 89 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 50cf402dea29..ce41dea47682 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -50,9 +50,9 @@
 #include "lpfc_vport.h"
 #include "lpfc_attr.h"
 
-#define LPFC_DEF_DEVLOSS_TMO 30
-#define LPFC_MIN_DEVLOSS_TMO 1
-#define LPFC_MAX_DEVLOSS_TMO 255
+#define LPFC_DEF_DEVLOSS_TMO	30
+#define LPFC_MIN_DEVLOSS_TMO	1
+#define LPFC_MAX_DEVLOSS_TMO	255
 
 /*
  * Write key size should be multiple of 4. If write key is changed
@@ -5769,10 +5769,12 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	lpfc_fcp_io_channel_init(phba, lpfc_fcp_io_channel);
 	lpfc_enable_hba_reset_init(phba, lpfc_enable_hba_reset);
 	lpfc_enable_hba_heartbeat_init(phba, lpfc_enable_hba_heartbeat);
+
 	lpfc_EnableXLane_init(phba, lpfc_EnableXLane);
 	if (phba->sli_rev != LPFC_SLI_REV4)
 		phba->cfg_EnableXLane = 0;
 	lpfc_XLanePriority_init(phba, lpfc_XLanePriority);
+
 	memset(phba->cfg_oas_tgt_wwpn, 0, (8 * sizeof(uint8_t)));
 	memset(phba->cfg_oas_vpt_wwpn, 0, (8 * sizeof(uint8_t)));
 	phba->cfg_oas_lun_state = 0;
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 7dca4d6a8883..1ee131f124b9 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2703,7 +2703,7 @@ static int lpfcdiag_loop_get_xri(struct lpfc_hba *phba, uint16_t rpi,
  * lpfc_bsg_dma_page_alloc - allocate a bsg mbox page sized dma buffers
  * @phba: Pointer to HBA context object
  *
- * This function allocates BSG_MBOX_SIZE (4KB) page size dma buffer and.
+ * This function allocates BSG_MBOX_SIZE (4KB) page size dma buffer and
  * returns the pointer to the buffer.
  **/
 static struct lpfc_dmabuf *
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index caa7a7b0ec53..f26eba713c53 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -531,7 +531,7 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 	int cnt;
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 	struct lpfc_nodelist *ndlp;
-	unsigned char *statep, *name;
+	unsigned char *statep;
 
 	cnt = (LPFC_NODELIST_SIZE / LPFC_NODELIST_ENTRY_SIZE);
 
@@ -574,36 +574,32 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 		default:
 			statep = "UNKNOWN";
 		}
-		len +=  snprintf(buf+len, size-len, "%s DID:x%06x ",
-			statep, ndlp->nlp_DID);
-		name = (unsigned char *)&ndlp->nlp_portname;
-		len +=  snprintf(buf+len, size-len,
-			"WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x ",
-			*name, *(name+1), *(name+2), *(name+3),
-			*(name+4), *(name+5), *(name+6), *(name+7));
-		name = (unsigned char *)&ndlp->nlp_nodename;
-		len +=  snprintf(buf+len, size-len,
-			"WWNN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x ",
-			*name, *(name+1), *(name+2), *(name+3),
-			*(name+4), *(name+5), *(name+6), *(name+7));
+		len += snprintf(buf+len, size-len, "%s DID:x%06x ",
+				statep, ndlp->nlp_DID);
+		len += snprintf(buf+len, size-len,
+				"WWPN x%llx ",
+				wwn_to_u64(ndlp->nlp_portname.u.wwn));
+		len += snprintf(buf+len, size-len,
+				"WWNN x%llx ",
+				wwn_to_u64(ndlp->nlp_nodename.u.wwn));
 		if (ndlp->nlp_flag & NLP_RPI_REGISTERED)
-			len +=  snprintf(buf+len, size-len, "RPI:%03d ",
-				ndlp->nlp_rpi);
+			len += snprintf(buf+len, size-len, "RPI:%03d ",
+					ndlp->nlp_rpi);
 		else
-			len +=  snprintf(buf+len, size-len, "RPI:none ");
+			len += snprintf(buf+len, size-len, "RPI:none ");
 		len +=  snprintf(buf+len, size-len, "flag:x%08x ",
 			ndlp->nlp_flag);
 		if (!ndlp->nlp_type)
-			len +=  snprintf(buf+len, size-len, "UNKNOWN_TYPE ");
+			len += snprintf(buf+len, size-len, "UNKNOWN_TYPE ");
 		if (ndlp->nlp_type & NLP_FC_NODE)
-			len +=  snprintf(buf+len, size-len, "FC_NODE ");
+			len += snprintf(buf+len, size-len, "FC_NODE ");
 		if (ndlp->nlp_type & NLP_FABRIC)
-			len +=  snprintf(buf+len, size-len, "FABRIC ");
+			len += snprintf(buf+len, size-len, "FABRIC ");
 		if (ndlp->nlp_type & NLP_FCP_TARGET)
-			len +=  snprintf(buf+len, size-len, "FCP_TGT sid:%d ",
+			len += snprintf(buf+len, size-len, "FCP_TGT sid:%d ",
 				ndlp->nlp_sid);
 		if (ndlp->nlp_type & NLP_FCP_INITIATOR)
-			len +=  snprintf(buf+len, size-len, "FCP_INITIATOR ");
+			len += snprintf(buf+len, size-len, "FCP_INITIATOR ");
 		len += snprintf(buf+len, size-len, "usgmap:%x ",
 			ndlp->nlp_usg_map);
 		len += snprintf(buf+len, size-len, "refcnt:%x",
@@ -611,8 +607,10 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 		len +=  snprintf(buf+len, size-len, "\n");
 	}
 	spin_unlock_irq(shost->host_lock);
+
 	return len;
 }
+
 #endif
 
 /**
@@ -938,7 +936,7 @@ lpfc_debugfs_dumpData_open(struct inode *inode, struct file *file)
 		goto out;
 
 	/* Round to page boundary */
-	printk(KERN_ERR "9059 BLKGRD:  %s: _dump_buf_data=0x%p\n",
+	pr_err("9059 BLKGRD:  %s: _dump_buf_data=0x%p\n",
 			__func__, _dump_buf_data);
 	debug->buffer = _dump_buf_data;
 	if (!debug->buffer) {
@@ -968,8 +966,8 @@ lpfc_debugfs_dumpDif_open(struct inode *inode, struct file *file)
 		goto out;
 
 	/* Round to page boundary */
-	printk(KERN_ERR	"9060 BLKGRD: %s: _dump_buf_dif=0x%p file=%pD\n",
-		__func__, _dump_buf_dif, file);
+	pr_err("9060 BLKGRD: %s: _dump_buf_dif=0x%p file=%pD\n",
+			__func__, _dump_buf_dif, file);
 	debug->buffer = _dump_buf_dif;
 	if (!debug->buffer) {
 		kfree(debug);
@@ -3853,7 +3851,7 @@ lpfc_idiag_mbxacc_dump_bsg_mbox(struct lpfc_hba *phba, enum nemb_type nemb_tp,
 	if ((mbox_tp == mbox_rd) && (dma_tp == dma_mbox)) {
 		if (*mbx_dump_map & LPFC_BSG_DMP_MBX_RD_MBX) {
 			do_dump |= LPFC_BSG_DMP_MBX_RD_MBX;
-			printk(KERN_ERR "\nRead mbox command (x%x), "
+			pr_err("\nRead mbox command (x%x), "
 			       "nemb:0x%x, extbuf_cnt:%d:\n",
 			       sta_tp, nemb_tp, ext_buf);
 		}
@@ -3861,7 +3859,7 @@ lpfc_idiag_mbxacc_dump_bsg_mbox(struct lpfc_hba *phba, enum nemb_type nemb_tp,
 	if ((mbox_tp == mbox_rd) && (dma_tp == dma_ebuf)) {
 		if (*mbx_dump_map & LPFC_BSG_DMP_MBX_RD_BUF) {
 			do_dump |= LPFC_BSG_DMP_MBX_RD_BUF;
-			printk(KERN_ERR "\nRead mbox buffer (x%x), "
+			pr_err("\nRead mbox buffer (x%x), "
 			       "nemb:0x%x, extbuf_seq:%d:\n",
 			       sta_tp, nemb_tp, ext_buf);
 		}
@@ -3869,7 +3867,7 @@ lpfc_idiag_mbxacc_dump_bsg_mbox(struct lpfc_hba *phba, enum nemb_type nemb_tp,
 	if ((mbox_tp == mbox_wr) && (dma_tp == dma_mbox)) {
 		if (*mbx_dump_map & LPFC_BSG_DMP_MBX_WR_MBX) {
 			do_dump |= LPFC_BSG_DMP_MBX_WR_MBX;
-			printk(KERN_ERR "\nWrite mbox command (x%x), "
+			pr_err("\nWrite mbox command (x%x), "
 			       "nemb:0x%x, extbuf_cnt:%d:\n",
 			       sta_tp, nemb_tp, ext_buf);
 		}
@@ -3877,7 +3875,7 @@ lpfc_idiag_mbxacc_dump_bsg_mbox(struct lpfc_hba *phba, enum nemb_type nemb_tp,
 	if ((mbox_tp == mbox_wr) && (dma_tp == dma_ebuf)) {
 		if (*mbx_dump_map & LPFC_BSG_DMP_MBX_WR_BUF) {
 			do_dump |= LPFC_BSG_DMP_MBX_WR_BUF;
-			printk(KERN_ERR "\nWrite mbox buffer (x%x), "
+			pr_err("\nWrite mbox buffer (x%x), "
 			       "nemb:0x%x, extbuf_seq:%d:\n",
 			       sta_tp, nemb_tp, ext_buf);
 		}
@@ -3889,7 +3887,7 @@ lpfc_idiag_mbxacc_dump_bsg_mbox(struct lpfc_hba *phba, enum nemb_type nemb_tp,
 		for (i = 0; i < *mbx_word_cnt; i++) {
 			if (!(i % 8)) {
 				if (i != 0)
-					printk(KERN_ERR "%s\n", line_buf);
+					pr_err("%s\n", line_buf);
 				len = 0;
 				len += snprintf(line_buf+len,
 						LPFC_MBX_ACC_LBUF_SZ-len,
@@ -3900,7 +3898,7 @@ lpfc_idiag_mbxacc_dump_bsg_mbox(struct lpfc_hba *phba, enum nemb_type nemb_tp,
 			pword++;
 		}
 		if ((i - 1) % 8)
-			printk(KERN_ERR "%s\n", line_buf);
+			pr_err("%s\n", line_buf);
 		(*mbx_dump_cnt)--;
 	}
 
@@ -3949,13 +3947,13 @@ lpfc_idiag_mbxacc_dump_issue_mbox(struct lpfc_hba *phba, MAILBOX_t *pmbox)
 
 	/* dump buffer content */
 	if (*mbx_dump_map & LPFC_MBX_DMP_MBX_WORD) {
-		printk(KERN_ERR "Mailbox command:0x%x dump by word:\n",
+		pr_err("Mailbox command:0x%x dump by word:\n",
 		       pmbox->mbxCommand);
 		pword = (uint32_t *)pmbox;
 		for (i = 0; i < *mbx_word_cnt; i++) {
 			if (!(i % 8)) {
 				if (i != 0)
-					printk(KERN_ERR "%s\n", line_buf);
+					pr_err("%s\n", line_buf);
 				len = 0;
 				memset(line_buf, 0, LPFC_MBX_ACC_LBUF_SZ);
 				len += snprintf(line_buf+len,
@@ -3968,17 +3966,17 @@ lpfc_idiag_mbxacc_dump_issue_mbox(struct lpfc_hba *phba, MAILBOX_t *pmbox)
 			pword++;
 		}
 		if ((i - 1) % 8)
-			printk(KERN_ERR "%s\n", line_buf);
-		printk(KERN_ERR "\n");
+			pr_err("%s\n", line_buf);
+		pr_err("\n");
 	}
 	if (*mbx_dump_map & LPFC_MBX_DMP_MBX_BYTE) {
-		printk(KERN_ERR "Mailbox command:0x%x dump by byte:\n",
+		pr_err("Mailbox command:0x%x dump by byte:\n",
 		       pmbox->mbxCommand);
 		pbyte = (uint8_t *)pmbox;
 		for (i = 0; i < *mbx_word_cnt; i++) {
 			if (!(i % 8)) {
 				if (i != 0)
-					printk(KERN_ERR "%s\n", line_buf);
+					pr_err("%s\n", line_buf);
 				len = 0;
 				memset(line_buf, 0, LPFC_MBX_ACC_LBUF_SZ);
 				len += snprintf(line_buf+len,
@@ -3996,8 +3994,8 @@ lpfc_idiag_mbxacc_dump_issue_mbox(struct lpfc_hba *phba, MAILBOX_t *pmbox)
 					LPFC_MBX_ACC_LBUF_SZ-len, " ");
 		}
 		if ((i - 1) % 8)
-			printk(KERN_ERR "%s\n", line_buf);
-		printk(KERN_ERR "\n");
+			pr_err("%s\n", line_buf);
+		pr_err("\n");
 	}
 	(*mbx_dump_cnt)--;
 
@@ -4240,8 +4238,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 					i++;
 				}
 				lpfc_debugfs_max_slow_ring_trc = (1 << i);
-				printk(KERN_ERR
-				       "lpfc_debugfs_max_disc_trc changed to "
+				pr_err("lpfc_debugfs_max_disc_trc changed to "
 				       "%d\n", lpfc_debugfs_max_disc_trc);
 			}
 		}
@@ -4273,6 +4270,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 				(sizeof(struct lpfc_debugfs_trc) *
 				lpfc_debugfs_max_slow_ring_trc));
 		}
+
 	}
 
 	snprintf(name, sizeof(name), "vport%d", vport->vpi);
@@ -4298,8 +4296,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 				i++;
 			}
 			lpfc_debugfs_max_disc_trc = (1 << i);
-			printk(KERN_ERR
-			       "lpfc_debugfs_max_disc_trc changed to %d\n",
+			pr_err("lpfc_debugfs_max_disc_trc changed to %d\n",
 			       lpfc_debugfs_max_disc_trc);
 		}
 	}
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 82047070cdc9..92627df35a58 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -3972,12 +3972,13 @@ static void
 lpfc_unregister_remote_port(struct lpfc_nodelist *ndlp)
 {
 	struct fc_rport *rport = ndlp->rport;
+	struct lpfc_vport *vport = ndlp->vport;
 
-	lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_RPORT,
+	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
 		"rport delete:    did:x%x flg:x%x type x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type);
 
-	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
 			 "3184 rport unregister x%06x, rport %p\n",
 			 ndlp->nlp_DID, rport);
 
@@ -4424,8 +4425,6 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 		if (icmd->ulpContext == (volatile ushort)ndlp->nlp_rpi) {
 			return 1;
 		}
-	} else if (pring->ringno == psli->next_ring) {
-
 	}
 	return 0;
 }
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 8cffad192f17..ec23388ac4f5 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -4272,13 +4272,13 @@ lpfc_sli4_async_sli_evt(struct lpfc_hba *phba, struct lpfc_acqe_sli *acqe_sli)
 			sprintf(message, "Unqualified optics - Replace with "
 				"Avago optics for Warranty and Technical "
 				"Support - Link is%s operational",
-				(operational) ? "" : " not");
+				(operational) ? " not" : "");
 			break;
 		case LPFC_SLI_EVENT_STATUS_UNCERTIFIED:
 			sprintf(message, "Uncertified optics - Replace with "
 				"Avago-certified optics to enable link "
 				"operation - Link is%s operational",
-				(operational) ? "" : " not");
+				(operational) ? " not" : "");
 			break;
 		default:
 			/* firmware is reporting a status we don't know about */
@@ -6207,6 +6207,7 @@ lpfc_create_shost(struct lpfc_hba *phba)
 
 	shost = lpfc_shost_from_vport(vport);
 	phba->pport = vport;
+
 	lpfc_debugfs_initialize(vport);
 	/* Put reference to SCSI host to driver's device private data */
 	pci_set_drvdata(phba->pcidev, shost);
@@ -6993,7 +6994,7 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 				"VPI(B:%d M:%d) "
 				"VFI(B:%d M:%d) "
 				"RPI(B:%d M:%d) "
-				"FCFI(Count:%d)\n",
+				"FCFI:%d EQ:%d CQ:%d WQ:%d RQ:%d\n",
 				phba->sli4_hba.extents_in_use,
 				phba->sli4_hba.max_cfg_param.xri_base,
 				phba->sli4_hba.max_cfg_param.max_xri,
@@ -7003,7 +7004,12 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 				phba->sli4_hba.max_cfg_param.max_vfi,
 				phba->sli4_hba.max_cfg_param.rpi_base,
 				phba->sli4_hba.max_cfg_param.max_rpi,
-				phba->sli4_hba.max_cfg_param.max_fcfi);
+				phba->sli4_hba.max_cfg_param.max_fcfi,
+				phba->sli4_hba.max_cfg_param.max_eq,
+				phba->sli4_hba.max_cfg_param.max_cq,
+				phba->sli4_hba.max_cfg_param.max_wq,
+				phba->sli4_hba.max_cfg_param.max_rq);
+
 	}
 
 	if (rc)
@@ -11344,7 +11350,6 @@ static struct miscdevice lpfc_mgmt_dev = {
 static int __init
 lpfc_init(void)
 {
-	int cpu;
 	int error = 0;
 
 	printk(LPFC_MODULE_DESC "\n");
@@ -11370,9 +11375,7 @@ lpfc_init(void)
 
 	/* Initialize in case vector mapping is needed */
 	lpfc_used_cpu = NULL;
-	lpfc_present_cpu = 0;
-	for_each_present_cpu(cpu)
-		lpfc_present_cpu++;
+	lpfc_present_cpu = num_present_cpus();
 
 	error = pci_register_driver(&lpfc_driver);
 	if (error) {
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 1180a22beb43..bd7b75dbb97e 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3894,7 +3894,7 @@ int lpfc_sli4_scmd_to_wqidx_distr(struct lpfc_hba *phba,
 		}
 	}
 	chann = atomic_add_return(1, &phba->fcp_qidx);
-	chann = (chann % phba->cfg_fcp_io_channel);
+	chann = chann % phba->cfg_fcp_io_channel;
 	return chann;
 }
 
@@ -3967,6 +3967,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 		lpfc_cmd->prot_data_segment = NULL;
 	}
 #endif
+
 	if (pnode && NLP_CHK_NODE_ACT(pnode))
 		atomic_dec(&pnode->cmd_pending);
 
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index 8cb80dabada8..4d7062258cf8 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -178,13 +178,13 @@ struct lpfc_scsi_buf {
 #endif
 };
 
-#define LPFC_SCSI_DMA_EXT_SIZE 264
-#define LPFC_BPL_SIZE          1024
-#define MDAC_DIRECT_CMD                  0x22
+#define LPFC_SCSI_DMA_EXT_SIZE	264
+#define LPFC_BPL_SIZE		1024
+#define MDAC_DIRECT_CMD		0x22
 
-#define FIND_FIRST_OAS_LUN		 0
-#define NO_MORE_OAS_LUN			-1
-#define NOT_OAS_ENABLED_LUN		NO_MORE_OAS_LUN
+#define FIND_FIRST_OAS_LUN	0
+#define NO_MORE_OAS_LUN		-1
+#define NOT_OAS_ENABLED_LUN	NO_MORE_OAS_LUN
 
 int lpfc_sli4_scmd_to_wqidx_distr(struct lpfc_hba *phba,
 				  struct lpfc_scsi_buf *lpfc_cmd);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 586984dce3a4..19543142c94c 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -271,10 +271,11 @@ lpfc_sli4_eq_get(struct lpfc_queue *q)
 	/*
 	 * insert barrier for instruction interlock : data from the hardware
 	 * must have the valid bit checked before it can be copied and acted
-	 * upon. Given what was seen in lpfc_sli4_cq_get() of speculative
-	 * instructions allowing action on content before valid bit checked,
-	 * add barrier here as well. May not be needed as "content" is a
-	 * single 32-bit entity here (vs multi word structure for cq's).
+	 * upon. Speculative instructions were allowing a bcopy at the start
+	 * of lpfc_sli4_fp_handle_wcqe(), which is called immediately
+	 * after our return, to copy data before the valid bit check above
+	 * was done. As such, some of the copied data was stale. The barrier
+	 * ensures the check is before any data is copied.
 	 */
 	mb();
 	return eqe;
@@ -386,11 +387,10 @@ lpfc_sli4_cq_get(struct lpfc_queue *q)
 	/*
 	 * insert barrier for instruction interlock : data from the hardware
 	 * must have the valid bit checked before it can be copied and acted
-	 * upon. Speculative instructions were allowing a bcopy at the start
-	 * of lpfc_sli4_fp_handle_wcqe(), which is called immediately
-	 * after our return, to copy data before the valid bit check above
-	 * was done. As such, some of the copied data was stale. The barrier
-	 * ensures the check is before any data is copied.
+	 * upon. Given what was seen in lpfc_sli4_cq_get() of speculative
+	 * instructions allowing action on content before valid bit checked,
+	 * add barrier here as well. May not be needed as "content" is a
+	 * single 32-bit entity here (vs multi word structure for cq's).
 	 */
 	mb();
 	return cqe;
@@ -7368,7 +7368,8 @@ lpfc_sli_issue_mbox_s3(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmbox,
 
 		if (psli->sli_flag & LPFC_SLI_ACTIVE) {
 			/* copy results back to user */
-			lpfc_sli_pcimem_bcopy(phba->mbox, mbx, MAILBOX_CMD_SIZE);
+			lpfc_sli_pcimem_bcopy(phba->mbox, mbx,
+						MAILBOX_CMD_SIZE);
 			/* Copy the mailbox extension data */
 			if (pmbox->out_ext_byte_len && pmbox->context2) {
 				lpfc_sli_pcimem_bcopy(phba->mbox_ext,
@@ -7378,7 +7379,7 @@ lpfc_sli_issue_mbox_s3(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmbox,
 		} else {
 			/* First copy command data */
 			lpfc_memcpy_from_slim(mbx, phba->MBslimaddr,
-							MAILBOX_CMD_SIZE);
+						MAILBOX_CMD_SIZE);
 			/* Copy the mailbox extension data */
 			if (pmbox->out_ext_byte_len && pmbox->context2) {
 				lpfc_memcpy_from_slim(pmbox->context2,
@@ -8906,10 +8907,10 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 				}
 			}
 		}
-	} else if (piocb->iocb_flag &  LPFC_IO_FCP) {
+	} else if (piocb->iocb_flag &  LPFC_IO_FCP)
 		/* These IO's already have an XRI and a mapped sgl. */
 		sglq = NULL;
-	} else {
+	else {
 		/*
 		 * This is a continuation of a commandi,(CX) so this
 		 * sglq is on the active list
@@ -13359,8 +13360,10 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	switch (cq->entry_count) {
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-				"0361 Unsupported CQ count. (%d)\n",
-				cq->entry_count);
+				"0361 Unsupported CQ count: "
+				"entry cnt %d sz %d pg cnt %d repost %d\n",
+				cq->entry_count, cq->entry_size,
+				cq->page_count, cq->entry_repost);
 		if (cq->entry_count < 256) {
 			status = -EINVAL;
 			goto out;
@@ -14824,6 +14827,9 @@ lpfc_sli4_post_scsi_sgl_block(struct lpfc_hba *phba,
 	return rc;
 }
 
+static char *lpfc_rctl_names[] = FC_RCTL_NAMES_INIT;
+static char *lpfc_type_names[] = FC_TYPE_NAMES_INIT;
+
 /**
  * lpfc_fc_frame_check - Check that this frame is a valid frame to handle
  * @phba: pointer to lpfc_hba struct that the frame was received on
@@ -14838,8 +14844,6 @@ static int
 lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 {
 	/*  make rctl_names static to save stack space */
-	static char *rctl_names[] = FC_RCTL_NAMES_INIT;
-	char *type_names[] = FC_TYPE_NAMES_INIT;
 	struct fc_vft_header *fc_vft_hdr;
 	uint32_t *header = (uint32_t *) fc_hdr;
 
@@ -14894,8 +14898,8 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
 			"2538 Received frame rctl:%s (x%x), type:%s (x%x), "
 			"frame Data:%08x %08x %08x %08x %08x %08x %08x\n",
-			rctl_names[fc_hdr->fh_r_ctl], fc_hdr->fh_r_ctl,
-			type_names[fc_hdr->fh_type], fc_hdr->fh_type,
+			lpfc_rctl_names[fc_hdr->fh_r_ctl], fc_hdr->fh_r_ctl,
+			lpfc_type_names[fc_hdr->fh_type], fc_hdr->fh_type,
 			be32_to_cpu(header[0]), be32_to_cpu(header[1]),
 			be32_to_cpu(header[2]), be32_to_cpu(header[3]),
 			be32_to_cpu(header[4]), be32_to_cpu(header[5]),
@@ -14904,8 +14908,8 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 drop:
 	lpfc_printf_log(phba, KERN_WARNING, LOG_ELS,
 			"2539 Dropped frame rctl:%s type:%s\n",
-			rctl_names[fc_hdr->fh_r_ctl],
-			type_names[fc_hdr->fh_type]);
+			lpfc_rctl_names[fc_hdr->fh_r_ctl],
+			lpfc_type_names[fc_hdr->fh_type]);
 	return 1;
 }
 
@@ -15726,11 +15730,13 @@ lpfc_sli4_handle_received_buffer(struct lpfc_hba *phba,
 
 	/* Process each received buffer */
 	fc_hdr = (struct fc_frame_header *)dmabuf->hbuf.virt;
+
 	/* check to see if this a valid type of frame */
 	if (lpfc_fc_frame_check(phba, fc_hdr)) {
 		lpfc_in_buf_free(phba, &dmabuf->dbuf);
 		return;
 	}
+
 	if ((bf_get(lpfc_cqe_code,
 		    &dmabuf->cq_event.cqe.rcqe_cmpl) == CQE_CODE_RECEIVE_V1))
 		fcfi = bf_get(lpfc_rcqe_fcf_id_v1,
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 74227a28bd56..3fad5657514b 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -97,11 +97,11 @@ struct lpfc_iocbq {
 		struct lpfc_node_rrq *rrq;
 	} context_un;
 
-	void (*fabric_iocb_cmpl) (struct lpfc_hba *, struct lpfc_iocbq *,
+	void (*fabric_iocb_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
 			   struct lpfc_iocbq *);
-	void (*wait_iocb_cmpl) (struct lpfc_hba *, struct lpfc_iocbq *,
+	void (*wait_iocb_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
 			   struct lpfc_iocbq *);
-	void (*iocb_cmpl) (struct lpfc_hba *, struct lpfc_iocbq *,
+	void (*iocb_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
 			   struct lpfc_iocbq *);
 };
 
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index e18bbc66e83b..5bbe6af148dd 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -33,6 +33,7 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport_fc.h>
+
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
 #include "lpfc_sli.h"
-- 
GitLab


From 07bcd98efba2edd2bd2230e24f6a46a09991e2a4 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:28 -0800
Subject: [PATCH 143/898] scsi: lpfc: refactor debugfs queue prints

Create common wq, cq, eq, rq print functions

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h         |   1 +
 drivers/scsi/lpfc/lpfc_debugfs.c | 564 +++++++++++++------------------
 2 files changed, 228 insertions(+), 337 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 64022d79117b..8e0d6f43878d 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -948,6 +948,7 @@ struct lpfc_hba {
 	struct dentry *idiag_ctl_acc;
 	struct dentry *idiag_mbx_acc;
 	struct dentry *idiag_ext_acc;
+	uint8_t lpfc_idiag_last_eq;
 #endif
 
 	/* Used for deferred freeing of ELS data buffers */
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index f26eba713c53..866361d4d637 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1972,6 +1972,155 @@ lpfc_idiag_baracc_write(struct file *file, const char __user *buf,
 	return -EINVAL;
 }
 
+static int
+__lpfc_idiag_print_wq(struct lpfc_queue *qp, char *wqtype,
+			char *pbuffer, int len)
+{
+	if (!qp)
+		return len;
+
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\t\t%s WQ info: ", wqtype);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"AssocCQID[%04d]: WQ-STAT[oflow:x%x posted:x%llx]\n",
+			qp->assoc_qid, qp->q_cnt_1,
+			(unsigned long long)qp->q_cnt_4);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\t\tWQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
+			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			qp->queue_id, qp->entry_count,
+			qp->entry_size, qp->host_index,
+			qp->hba_index);
+	len +=  snprintf(pbuffer + len,
+			LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
+	return len;
+}
+
+static int
+lpfc_idiag_wqs_for_cq(struct lpfc_hba *phba, char *wqtype, char *pbuffer,
+		int *len, int max_cnt, int cq_id)
+{
+	struct lpfc_queue *qp;
+	int qidx;
+
+	for (qidx = 0; qidx < phba->cfg_fcp_io_channel; qidx++) {
+		qp = phba->sli4_hba.fcp_wq[qidx];
+		if (qp->assoc_qid != cq_id)
+			continue;
+		*len = __lpfc_idiag_print_wq(qp, wqtype, pbuffer, *len);
+		if (*len >= max_cnt)
+			return 1;
+	}
+	return 0;
+}
+
+static int
+__lpfc_idiag_print_cq(struct lpfc_queue *qp, char *cqtype,
+			char *pbuffer, int len)
+{
+	if (!qp)
+		return len;
+
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\t%s CQ info: ", cqtype);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"AssocEQID[%02d]: CQ STAT[max:x%x relw:x%x "
+			"xabt:x%x wq:x%llx]\n",
+			qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
+			qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\tCQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
+			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			qp->queue_id, qp->entry_count,
+			qp->entry_size, qp->host_index,
+			qp->hba_index);
+
+	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
+
+	return len;
+}
+
+static int
+__lpfc_idiag_print_rqpair(struct lpfc_queue *qp, struct lpfc_queue *datqp,
+			char *rqtype, char *pbuffer, int len)
+{
+	if (!qp || !datqp)
+		return len;
+
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\t\t%s RQ info: ", rqtype);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"AssocCQID[%02d]: RQ-STAT[nopost:x%x nobuf:x%x "
+			"trunc:x%x rcv:x%llx]\n",
+			qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
+			qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\t\tHQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
+			"HOST-IDX[%04d], PORT-IDX[%04d]\n",
+			qp->queue_id, qp->entry_count, qp->entry_size,
+			qp->host_index, qp->hba_index);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\t\tDQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
+			"HOST-IDX[%04d], PORT-IDX[%04d]\n",
+			datqp->queue_id, datqp->entry_count,
+			datqp->entry_size, datqp->host_index,
+			datqp->hba_index);
+	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
+
+	return len;
+}
+
+static int
+lpfc_idiag_cqs_for_eq(struct lpfc_hba *phba, char *pbuffer,
+		int *len, int max_cnt, int eq_id)
+{
+	struct lpfc_queue *qp;
+	int qidx, rc;
+
+	for (qidx = 0; qidx < phba->cfg_fcp_io_channel; qidx++) {
+		qp = phba->sli4_hba.fcp_cq[qidx];
+		if (qp->assoc_qid != eq_id)
+			continue;
+
+		*len = __lpfc_idiag_print_cq(qp, "FCP", pbuffer, *len);
+
+		/* Reset max counter */
+		qp->CQ_max_cqe = 0;
+
+		if (*len >= max_cnt)
+			return 1;
+
+		rc = lpfc_idiag_wqs_for_cq(phba, "FCP", pbuffer, len,
+				max_cnt, qp->queue_id);
+		if (rc)
+			return 1;
+	}
+
+	return 0;
+}
+
+static int
+__lpfc_idiag_print_eq(struct lpfc_queue *qp, char *eqtype,
+			char *pbuffer, int len)
+{
+	if (!qp)
+		return len;
+
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"\n%s EQ info: EQ-STAT[max:x%x noE:x%x "
+			"bs:x%x proc:x%llx]\n",
+			eqtype, qp->q_cnt_1, qp->q_cnt_2, qp->q_cnt_3,
+			(unsigned long long)qp->q_cnt_4);
+	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+			"EQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
+			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			qp->queue_id, qp->entry_count, qp->entry_size,
+			qp->host_index, qp->hba_index);
+	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
+
+	return len;
+}
+
 /**
  * lpfc_idiag_queinfo_read - idiag debugfs read queue information
  * @file: The file pointer to read from.
@@ -1982,6 +2131,9 @@ lpfc_idiag_baracc_write(struct file *file, const char __user *buf,
  * Description:
  * This routine reads data from the @phba SLI4 PCI function queue information,
  * and copies to user @buf.
+ * This routine only returns 1 EQs worth of information. It remembers the last
+ * EQ read and jumps to the next EQ. Thus subsequent calls to queInfo will
+ * retrieve all EQs allocated for the phba.
  *
  * Returns:
  * This function returns the amount of data that was read (this could be less
@@ -1993,19 +2145,16 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 {
 	struct lpfc_debug *debug = file->private_data;
 	struct lpfc_hba *phba = (struct lpfc_hba *)debug->i_private;
-	int len = 0;
 	char *pbuffer;
-	int x, cnt;
-	int max_cnt;
+	int max_cnt, rc, x, len = 0;
 	struct lpfc_queue *qp = NULL;
 
-
 	if (!debug->buffer)
 		debug->buffer = kmalloc(LPFC_QUE_INFO_GET_BUF_SIZE, GFP_KERNEL);
 	if (!debug->buffer)
 		return 0;
 	pbuffer = debug->buffer;
-	max_cnt = LPFC_QUE_INFO_GET_BUF_SIZE - 128;
+	max_cnt = LPFC_QUE_INFO_GET_BUF_SIZE - 256;
 
 	if (*ppos)
 		return 0;
@@ -2014,374 +2163,115 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 
 	/* Fast-path event queue */
 	if (phba->sli4_hba.hba_eq && phba->cfg_fcp_io_channel) {
-		cnt = phba->cfg_fcp_io_channel;
 
-		for (x = 0; x < cnt; x++) {
+		x = phba->lpfc_idiag_last_eq;
+		if (phba->cfg_fof && (x >= phba->cfg_fcp_io_channel)) {
+			phba->lpfc_idiag_last_eq = 0;
+			goto fof;
+		}
+		phba->lpfc_idiag_last_eq++;
+		if (phba->lpfc_idiag_last_eq >= phba->cfg_fcp_io_channel)
+			if (phba->cfg_fof == 0)
+				phba->lpfc_idiag_last_eq = 0;
 
-			/* Fast-path EQ */
-			qp = phba->sli4_hba.hba_eq[x];
-			if (!qp)
-				goto proc_cq;
+		len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
+					"EQ %d out of %d HBA EQs\n",
+					x, phba->cfg_fcp_io_channel);
 
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\nHBA EQ info: "
-				"EQ-STAT[max:x%x noE:x%x "
-				"bs:x%x proc:x%llx]\n",
-				qp->q_cnt_1, qp->q_cnt_2,
-				qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
-
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"EQID[%02d], "
-				"QE-CNT[%04d], QE-SIZE[%04d], "
-				"HOST-IDX[%04d], PORT-IDX[%04d]",
-				qp->queue_id,
-				qp->entry_count,
-				qp->entry_size,
-				qp->host_index,
-				qp->hba_index);
-
-
-			/* Reset max counter */
-			qp->EQ_max_eqe = 0;
+		/* Fast-path EQ */
+		qp = phba->sli4_hba.hba_eq[x];
+		if (!qp)
+			goto out;
 
-			len +=  snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-			if (len >= max_cnt)
-				goto too_big;
-proc_cq:
-			/* Fast-path FCP CQ */
-			qp = phba->sli4_hba.fcp_cq[x];
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\tFCP CQ info: ");
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"AssocEQID[%02d]: "
-				"CQ STAT[max:x%x relw:x%x "
-				"xabt:x%x wq:x%llx]\n",
-				qp->assoc_qid,
-				qp->q_cnt_1, qp->q_cnt_2,
-				qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\tCQID[%02d], "
-				"QE-CNT[%04d], QE-SIZE[%04d], "
-				"HOST-IDX[%04d], PORT-IDX[%04d]",
-				qp->queue_id, qp->entry_count,
-				qp->entry_size, qp->host_index,
-				qp->hba_index);
+		len = __lpfc_idiag_print_eq(qp, "HBA", pbuffer, len);
 
+		/* Reset max counter */
+		qp->EQ_max_eqe = 0;
 
-			/* Reset max counter */
-			qp->CQ_max_cqe = 0;
+		if (len >= max_cnt)
+			goto too_big;
 
-			len +=  snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-			if (len >= max_cnt)
-				goto too_big;
+		rc = lpfc_idiag_cqs_for_eq(phba, pbuffer, &len,
+			max_cnt, qp->queue_id);
+		if (rc)
+			goto too_big;
 
-			/* Fast-path FCP WQ */
-			qp = phba->sli4_hba.fcp_wq[x];
+		/* Only EQ 0 has slow path CQs configured */
+		if (x)
+			goto out;
 
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\t\tFCP WQ info: ");
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"AssocCQID[%02d]: "
-				"WQ-STAT[oflow:x%x posted:x%llx]\n",
-				qp->assoc_qid,
-				qp->q_cnt_1, (unsigned long long)qp->q_cnt_4);
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\t\tWQID[%02d], "
-				"QE-CNT[%04d], QE-SIZE[%04d], "
-				"HOST-IDX[%04d], PORT-IDX[%04d]",
-				qp->queue_id,
-				qp->entry_count,
-				qp->entry_size,
-				qp->host_index,
-				qp->hba_index);
-
-			len +=  snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-			if (len >= max_cnt)
-				goto too_big;
-
-			if (x)
-				continue;
-
-			/* Only EQ 0 has slow path CQs configured */
-
-			/* Slow-path mailbox CQ */
-			qp = phba->sli4_hba.mbx_cq;
-			if (qp) {
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\tMBX CQ info: ");
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"AssocEQID[%02d]: "
-					"CQ-STAT[mbox:x%x relw:x%x "
-					"xabt:x%x wq:x%llx]\n",
-					qp->assoc_qid,
-					qp->q_cnt_1, qp->q_cnt_2,
-					qp->q_cnt_3,
-					(unsigned long long)qp->q_cnt_4);
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\tCQID[%02d], "
-					"QE-CNT[%04d], QE-SIZE[%04d], "
-					"HOST-IDX[%04d], PORT-IDX[%04d]",
-					qp->queue_id, qp->entry_count,
-					qp->entry_size, qp->host_index,
-					qp->hba_index);
-
-				len +=  snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-				if (len >= max_cnt)
-					goto too_big;
-			}
+		/* Slow-path mailbox CQ */
+		qp = phba->sli4_hba.mbx_cq;
+		len = __lpfc_idiag_print_cq(qp, "MBX", pbuffer, len);
+		if (len >= max_cnt)
+			goto too_big;
 
-			/* Slow-path MBOX MQ */
-			qp = phba->sli4_hba.mbx_wq;
-			if (qp) {
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\t\tMBX MQ info: ");
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"AssocCQID[%02d]:\n",
-					phba->sli4_hba.mbx_wq->assoc_qid);
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\t\tWQID[%02d], "
-					"QE-CNT[%04d], QE-SIZE[%04d], "
-					"HOST-IDX[%04d], PORT-IDX[%04d]",
-					qp->queue_id, qp->entry_count,
-					qp->entry_size, qp->host_index,
-					qp->hba_index);
-
-				len +=  snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-				if (len >= max_cnt)
-					goto too_big;
-			}
+		/* Slow-path MBOX MQ */
+		qp = phba->sli4_hba.mbx_wq;
+		len = __lpfc_idiag_print_wq(qp, "MBX", pbuffer, len);
+		if (len >= max_cnt)
+			goto too_big;
 
-			/* Slow-path ELS response CQ */
-			qp = phba->sli4_hba.els_cq;
-			if (qp) {
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\tELS CQ info: ");
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"AssocEQID[%02d]: "
-					"CQ-STAT[max:x%x relw:x%x "
-					"xabt:x%x wq:x%llx]\n",
-					qp->assoc_qid,
-					qp->q_cnt_1, qp->q_cnt_2,
-					qp->q_cnt_3,
-					(unsigned long long)qp->q_cnt_4);
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\tCQID [%02d], "
-					"QE-CNT[%04d], QE-SIZE[%04d], "
-					"HOST-IDX[%04d], PORT-IDX[%04d]",
-					qp->queue_id, qp->entry_count,
-					qp->entry_size, qp->host_index,
-					qp->hba_index);
-
-				/* Reset max counter */
-				qp->CQ_max_cqe = 0;
-
-				len +=  snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-				if (len >= max_cnt)
-					goto too_big;
-			}
+		/* Slow-path ELS response CQ */
+		qp = phba->sli4_hba.els_cq;
+		len = __lpfc_idiag_print_cq(qp, "ELS", pbuffer, len);
+		/* Reset max counter */
+		if (qp)
+			qp->CQ_max_cqe = 0;
+		if (len >= max_cnt)
+			goto too_big;
 
-			/* Slow-path ELS WQ */
-			qp = phba->sli4_hba.els_wq;
-			if (qp) {
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\t\tELS WQ info: ");
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"AssocCQID[%02d]: "
-					" WQ-STAT[oflow:x%x "
-					"posted:x%llx]\n",
-					qp->assoc_qid,
-					qp->q_cnt_1,
-					(unsigned long long)qp->q_cnt_4);
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\t\tWQID[%02d], "
-					"QE-CNT[%04d], QE-SIZE[%04d], "
-					"HOST-IDX[%04d], PORT-IDX[%04d]",
-					qp->queue_id, qp->entry_count,
-					qp->entry_size, qp->host_index,
-					qp->hba_index);
-
-				len +=  snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-				if (len >= max_cnt)
-					goto too_big;
-			}
+		/* Slow-path ELS WQ */
+		qp = phba->sli4_hba.els_wq;
+		len = __lpfc_idiag_print_wq(qp, "ELS", pbuffer, len);
+		if (len >= max_cnt)
+			goto too_big;
 
-			if (phba->sli4_hba.hdr_rq && phba->sli4_hba.dat_rq) {
-				/* Slow-path RQ header */
-				qp = phba->sli4_hba.hdr_rq;
+		qp = phba->sli4_hba.hdr_rq;
+		len = __lpfc_idiag_print_rqpair(qp, phba->sli4_hba.dat_rq,
+				"RQpair", pbuffer, len);
+		if (len >= max_cnt)
+			goto too_big;
 
-				len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\t\tRQ info: ");
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"AssocCQID[%02d]: "
-					"RQ-STAT[nopost:x%x nobuf:x%x "
-					"trunc:x%x rcv:x%llx]\n",
-					qp->assoc_qid,
-					qp->q_cnt_1, qp->q_cnt_2,
-					qp->q_cnt_3,
-					(unsigned long long)qp->q_cnt_4);
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\t\tHQID[%02d], "
-					"QE-CNT[%04d], QE-SIZE[%04d], "
-					"HOST-IDX[%04d], PORT-IDX[%04d]\n",
-					qp->queue_id,
-					qp->entry_count,
-					qp->entry_size,
-					qp->host_index,
-					qp->hba_index);
-
-				/* Slow-path RQ data */
-				qp = phba->sli4_hba.dat_rq;
-				len += snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len,
-					"\t\tDQID[%02d], "
-					"QE-CNT[%04d], QE-SIZE[%04d], "
-					"HOST-IDX[%04d], PORT-IDX[%04d]\n",
-					qp->queue_id,
-					qp->entry_count,
-					qp->entry_size,
-					qp->host_index,
-					qp->hba_index);
-
-				len +=  snprintf(pbuffer+len,
-					LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-			}
-		}
+		goto out;
 	}
 
+fof:
 	if (phba->cfg_fof) {
 		/* FOF EQ */
 		qp = phba->sli4_hba.fof_eq;
-		if (!qp)
-			goto out;
-
-		len += snprintf(pbuffer+len,
-			LPFC_QUE_INFO_GET_BUF_SIZE-len,
-			"\nFOF EQ info: "
-			"EQ-STAT[max:x%x noE:x%x "
-			"bs:x%x proc:x%llx]\n",
-			qp->q_cnt_1, qp->q_cnt_2,
-			qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
-
-		len += snprintf(pbuffer+len,
-			LPFC_QUE_INFO_GET_BUF_SIZE-len,
-			"EQID[%02d], "
-			"QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]",
-			qp->queue_id,
-			qp->entry_count,
-			qp->entry_size,
-			qp->host_index,
-			qp->hba_index);
+		len = __lpfc_idiag_print_eq(qp, "FOF", pbuffer, len);
 
 		/* Reset max counter */
-		qp->EQ_max_eqe = 0;
+		if (qp)
+			qp->EQ_max_eqe = 0;
 
-		len +=  snprintf(pbuffer+len,
-			LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
 		if (len >= max_cnt)
 			goto too_big;
-	}
-
-	if (phba->cfg_fof) {
 
 		/* OAS CQ */
 		qp = phba->sli4_hba.oas_cq;
-		if (qp) {
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\tOAS CQ info: ");
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"AssocEQID[%02d]: "
-				"CQ STAT[max:x%x relw:x%x "
-				"xabt:x%x wq:x%llx]\n",
-				qp->assoc_qid,
-				qp->q_cnt_1, qp->q_cnt_2,
-				qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\tCQID[%02d], "
-				"QE-CNT[%04d], QE-SIZE[%04d], "
-				"HOST-IDX[%04d], PORT-IDX[%04d]",
-				qp->queue_id, qp->entry_count,
-				qp->entry_size, qp->host_index,
-				qp->hba_index);
-
-			/* Reset max counter */
+		len = __lpfc_idiag_print_cq(qp, "OAS", pbuffer, len);
+		/* Reset max counter */
+		if (qp)
 			qp->CQ_max_cqe = 0;
-
-			len +=  snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-			if (len >= max_cnt)
-				goto too_big;
-		}
+		if (len >= max_cnt)
+			goto too_big;
 
 		/* OAS WQ */
 		qp = phba->sli4_hba.oas_wq;
-		if (qp) {
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\t\tOAS WQ info: ");
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"AssocCQID[%02d]: "
-				"WQ-STAT[oflow:x%x posted:x%llx]\n",
-				qp->assoc_qid,
-				qp->q_cnt_1, (unsigned long long)qp->q_cnt_4);
-			len += snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len,
-				"\t\tWQID[%02d], "
-				"QE-CNT[%04d], QE-SIZE[%04d], "
-				"HOST-IDX[%04d], PORT-IDX[%04d]",
-				qp->queue_id,
-				qp->entry_count,
-				qp->entry_size,
-				qp->host_index,
-				qp->hba_index);
-
-			len +=  snprintf(pbuffer+len,
-				LPFC_QUE_INFO_GET_BUF_SIZE-len, "\n");
-			if (len >= max_cnt)
-				goto too_big;
-		}
+		len = __lpfc_idiag_print_wq(qp, "OAS", pbuffer, len);
+		if (len >= max_cnt)
+			goto too_big;
 	}
-out:
+
 	spin_unlock_irq(&phba->hbalock);
 	return simple_read_from_buffer(buf, nbytes, ppos, pbuffer, len);
 
 too_big:
-	len +=  snprintf(pbuffer+len,
-		LPFC_QUE_INFO_GET_BUF_SIZE-len, "Truncated ...\n");
+	len +=  snprintf(pbuffer + len,
+		LPFC_QUE_INFO_GET_BUF_SIZE - len, "Truncated ...\n");
+out:
 	spin_unlock_irq(&phba->hbalock);
 	return simple_read_from_buffer(buf, nbytes, ppos, pbuffer, len);
 }
-- 
GitLab


From 1d9d5a9879ad493ee7cf75987df1f365c61fefe5 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:29 -0800
Subject: [PATCH 144/898] scsi: lpfc: refactor debugfs queue dump routines

Create common wq, cq, eq, rq dump functions

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_debugfs.c |  22 ++--
 drivers/scsi/lpfc/lpfc_debugfs.h | 214 +++++++++++++------------------
 2 files changed, 101 insertions(+), 135 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 866361d4d637..93ddda16c632 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -4555,31 +4555,31 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 void
 lpfc_debug_dump_all_queues(struct lpfc_hba *phba)
 {
-	int fcp_wqidx;
+	int idx;
 
 	/*
 	 * Dump Work Queues (WQs)
 	 */
-	lpfc_debug_dump_mbx_wq(phba);
-	lpfc_debug_dump_els_wq(phba);
+	lpfc_debug_dump_wq(phba, DUMP_MBX, 0);
+	lpfc_debug_dump_wq(phba, DUMP_ELS, 0);
 
-	for (fcp_wqidx = 0; fcp_wqidx < phba->cfg_fcp_io_channel; fcp_wqidx++)
-		lpfc_debug_dump_fcp_wq(phba, fcp_wqidx);
+	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
+		lpfc_debug_dump_wq(phba, DUMP_FCP, idx);
 
 	lpfc_debug_dump_hdr_rq(phba);
 	lpfc_debug_dump_dat_rq(phba);
 	/*
 	 * Dump Complete Queues (CQs)
 	 */
-	lpfc_debug_dump_mbx_cq(phba);
-	lpfc_debug_dump_els_cq(phba);
+	lpfc_debug_dump_cq(phba, DUMP_MBX, 0);
+	lpfc_debug_dump_cq(phba, DUMP_ELS, 0);
 
-	for (fcp_wqidx = 0; fcp_wqidx < phba->cfg_fcp_io_channel; fcp_wqidx++)
-		lpfc_debug_dump_fcp_cq(phba, fcp_wqidx);
+	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
+		lpfc_debug_dump_cq(phba, DUMP_FCP, idx);
 
 	/*
 	 * Dump Event Queues (EQs)
 	 */
-	for (fcp_wqidx = 0; fcp_wqidx < phba->cfg_fcp_io_channel; fcp_wqidx++)
-		lpfc_debug_dump_hba_eq(phba, fcp_wqidx);
+	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
+		lpfc_debug_dump_hba_eq(phba, idx);
 }
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index 8b2b6a3bfc25..9ae2c4b5fd12 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -42,6 +42,12 @@
 /* hbqinfo output buffer size */
 #define LPFC_HBQINFO_SIZE 8192
 
+enum {
+	DUMP_FCP,
+	DUMP_MBX,
+	DUMP_ELS,
+};
+
 /*
  * For SLI4 iDiag debugfs diagnostics tool
  */
@@ -358,58 +364,97 @@ lpfc_debug_dump_q(struct lpfc_queue *q)
 }
 
 /**
- * lpfc_debug_dump_fcp_wq - dump all entries from a fcp work queue
+ * lpfc_debug_dump_wq - dump all entries from the fcp work queue
  * @phba: Pointer to HBA context object.
- * @fcp_wqidx: Index to a FCP work queue.
+ * @wqidx: Index to a FCP work queue.
  *
- * This function dumps all entries from a FCP work queue specified by the
- * @fcp_wqidx.
+ * This function dumps all entries from a FCP work queue specified
+ * by the wqidx.
  **/
 static inline void
-lpfc_debug_dump_fcp_wq(struct lpfc_hba *phba, int fcp_wqidx)
+lpfc_debug_dump_wq(struct lpfc_hba *phba, int qtype, int wqidx)
 {
-	/* sanity check */
-	if (fcp_wqidx >= phba->cfg_fcp_io_channel)
+	struct lpfc_queue *wq;
+	char *qtypestr;
+
+	if (qtype == DUMP_FCP) {
+		wq = phba->sli4_hba.fcp_wq[wqidx];
+		qtypestr = "FCP";
+	} else if (qtype == DUMP_MBX) {
+		wq = phba->sli4_hba.mbx_wq;
+		qtypestr = "MBX";
+	} else if (qtype == DUMP_ELS) {
+		wq = phba->sli4_hba.els_wq;
+		qtypestr = "ELS";
+	} else
 		return;
 
-	printk(KERN_ERR "FCP WQ: WQ[Idx:%d|Qid:%d]\n",
-		fcp_wqidx, phba->sli4_hba.fcp_wq[fcp_wqidx]->queue_id);
-	lpfc_debug_dump_q(phba->sli4_hba.fcp_wq[fcp_wqidx]);
+	if (qtype == DUMP_FCP)
+		pr_err("%s WQ: WQ[Idx:%d|Qid:%d]\n",
+			qtypestr, wqidx, wq->queue_id);
+	else
+		pr_err("%s WQ: WQ[Qid:%d]\n",
+			qtypestr, wq->queue_id);
+
+	lpfc_debug_dump_q(wq);
 }
 
 /**
- * lpfc_debug_dump_fcp_cq - dump all entries from a fcp work queue's cmpl queue
+ * lpfc_debug_dump_cq - dump all entries from a fcp work queue's
+ * cmpl queue
  * @phba: Pointer to HBA context object.
- * @fcp_wqidx: Index to a FCP work queue.
+ * @wqidx: Index to a FCP work queue.
  *
- * This function dumps all entries from a FCP complete queue which is
- * associated to the FCP work queue specified by the @fcp_wqidx.
+ * This function dumps all entries from a FCP completion queue
+ * which is associated to the work queue specified by the @wqidx.
  **/
 static inline void
-lpfc_debug_dump_fcp_cq(struct lpfc_hba *phba, int fcp_wqidx)
+lpfc_debug_dump_cq(struct lpfc_hba *phba, int qtype, int wqidx)
 {
-	int fcp_cqidx, fcp_cqid;
-
-	/* sanity check */
-	if (fcp_wqidx >= phba->cfg_fcp_io_channel)
+	struct lpfc_queue *wq, *cq, *eq;
+	char *qtypestr;
+	int eqidx;
+
+	/* fcp wq and cq are 1:1, thus same indexes */
+
+	if (qtype == DUMP_FCP) {
+		wq = phba->sli4_hba.fcp_wq[wqidx];
+		cq = phba->sli4_hba.fcp_cq[wqidx];
+		qtypestr = "FCP";
+	} else if (qtype == DUMP_MBX) {
+		wq = phba->sli4_hba.mbx_wq;
+		cq = phba->sli4_hba.mbx_cq;
+		qtypestr = "MBX";
+	} else if (qtype == DUMP_ELS) {
+		wq = phba->sli4_hba.els_wq;
+		cq = phba->sli4_hba.els_cq;
+		qtypestr = "ELS";
+	} else
 		return;
 
-	fcp_cqid = phba->sli4_hba.fcp_wq[fcp_wqidx]->assoc_qid;
-	for (fcp_cqidx = 0; fcp_cqidx < phba->cfg_fcp_io_channel; fcp_cqidx++)
-		if (phba->sli4_hba.fcp_cq[fcp_cqidx]->queue_id == fcp_cqid)
+	for (eqidx = 0; eqidx < phba->cfg_fcp_io_channel; eqidx++) {
+		eq = phba->sli4_hba.hba_eq[eqidx];
+		if (cq->assoc_qid == eq->queue_id)
 			break;
-	if (phba->intr_type == MSIX) {
-		if (fcp_cqidx >= phba->cfg_fcp_io_channel)
-			return;
-	} else {
-		if (fcp_cqidx > 0)
-			return;
+	}
+	if (eqidx == phba->cfg_fcp_io_channel) {
+		pr_err("Couldn't find EQ for CQ. Using EQ[0]\n");
+		eqidx = 0;
+		eq = phba->sli4_hba.hba_eq[0];
 	}
 
-	printk(KERN_ERR "FCP CQ: WQ[Idx:%d|Qid%d]->CQ[Idx%d|Qid%d]:\n",
-		fcp_wqidx, phba->sli4_hba.fcp_wq[fcp_wqidx]->queue_id,
-		fcp_cqidx, fcp_cqid);
-	lpfc_debug_dump_q(phba->sli4_hba.fcp_cq[fcp_cqidx]);
+	if (qtype == DUMP_FCP)
+		pr_err("%s CQ: WQ[Idx:%d|Qid%d]->CQ[Idx%d|Qid%d]"
+			"->EQ[Idx:%d|Qid:%d]:\n",
+			qtypestr, wqidx, wq->queue_id, wqidx, cq->queue_id,
+			eqidx, eq->queue_id);
+	else
+		pr_err("%s CQ: WQ[Qid:%d]->CQ[Qid:%d]"
+			"->EQ[Idx:%d|Qid:%d]:\n",
+			qtypestr, wq->queue_id, cq->queue_id,
+			eqidx, eq->queue_id);
+
+	lpfc_debug_dump_q(cq);
 }
 
 /**
@@ -421,64 +466,15 @@ lpfc_debug_dump_fcp_cq(struct lpfc_hba *phba, int fcp_wqidx)
  * associated to the FCP work queue specified by the @fcp_wqidx.
  **/
 static inline void
-lpfc_debug_dump_hba_eq(struct lpfc_hba *phba, int fcp_wqidx)
+lpfc_debug_dump_hba_eq(struct lpfc_hba *phba, int qidx)
 {
-	struct lpfc_queue *qdesc;
-	int fcp_eqidx, fcp_eqid;
-	int fcp_cqidx, fcp_cqid;
-
-	/* sanity check */
-	if (fcp_wqidx >= phba->cfg_fcp_io_channel)
-		return;
-	fcp_cqid = phba->sli4_hba.fcp_wq[fcp_wqidx]->assoc_qid;
-	for (fcp_cqidx = 0; fcp_cqidx < phba->cfg_fcp_io_channel; fcp_cqidx++)
-		if (phba->sli4_hba.fcp_cq[fcp_cqidx]->queue_id == fcp_cqid)
-			break;
-	if (phba->intr_type == MSIX) {
-		if (fcp_cqidx >= phba->cfg_fcp_io_channel)
-			return;
-	} else {
-		if (fcp_cqidx > 0)
-			return;
-	}
+	struct lpfc_queue *qp;
 
-	fcp_eqidx = fcp_cqidx;
-	fcp_eqid = phba->sli4_hba.hba_eq[fcp_eqidx]->queue_id;
-	qdesc = phba->sli4_hba.hba_eq[fcp_eqidx];
+	qp = phba->sli4_hba.hba_eq[qidx];
 
-	printk(KERN_ERR "FCP EQ: WQ[Idx:%d|Qid:%d]->CQ[Idx:%d|Qid:%d]->"
-		"EQ[Idx:%d|Qid:%d]\n",
-		fcp_wqidx, phba->sli4_hba.fcp_wq[fcp_wqidx]->queue_id,
-		fcp_cqidx, fcp_cqid, fcp_eqidx, fcp_eqid);
-	lpfc_debug_dump_q(qdesc);
-}
+	pr_err("EQ[Idx:%d|Qid:%d]\n", qidx, qp->queue_id);
 
-/**
- * lpfc_debug_dump_els_wq - dump all entries from the els work queue
- * @phba: Pointer to HBA context object.
- *
- * This function dumps all entries from the ELS work queue.
- **/
-static inline void
-lpfc_debug_dump_els_wq(struct lpfc_hba *phba)
-{
-	printk(KERN_ERR "ELS WQ: WQ[Qid:%d]:\n",
-		phba->sli4_hba.els_wq->queue_id);
-	lpfc_debug_dump_q(phba->sli4_hba.els_wq);
-}
-
-/**
- * lpfc_debug_dump_mbx_wq - dump all entries from the mbox work queue
- * @phba: Pointer to HBA context object.
- *
- * This function dumps all entries from the MBOX work queue.
- **/
-static inline void
-lpfc_debug_dump_mbx_wq(struct lpfc_hba *phba)
-{
-	printk(KERN_ERR "MBX WQ: WQ[Qid:%d]\n",
-		phba->sli4_hba.mbx_wq->queue_id);
-	lpfc_debug_dump_q(phba->sli4_hba.mbx_wq);
+	lpfc_debug_dump_q(qp);
 }
 
 /**
@@ -509,36 +505,6 @@ lpfc_debug_dump_hdr_rq(struct lpfc_hba *phba)
 	lpfc_debug_dump_q(phba->sli4_hba.hdr_rq);
 }
 
-/**
- * lpfc_debug_dump_els_cq - dump all entries from the els complete queue
- * @phba: Pointer to HBA context object.
- *
- * This function dumps all entries from the els complete queue.
- **/
-static inline void
-lpfc_debug_dump_els_cq(struct lpfc_hba *phba)
-{
-	printk(KERN_ERR "ELS CQ: WQ[Qid:%d]->CQ[Qid:%d]\n",
-		phba->sli4_hba.els_wq->queue_id,
-		phba->sli4_hba.els_cq->queue_id);
-	lpfc_debug_dump_q(phba->sli4_hba.els_cq);
-}
-
-/**
- * lpfc_debug_dump_mbx_cq - dump all entries from the mbox complete queue
- * @phba: Pointer to HBA context object.
- *
- * This function dumps all entries from the mbox complete queue.
- **/
-static inline void
-lpfc_debug_dump_mbx_cq(struct lpfc_hba *phba)
-{
-	printk(KERN_ERR "MBX CQ: WQ[Qid:%d]->CQ[Qid:%d]\n",
-		phba->sli4_hba.mbx_wq->queue_id,
-		phba->sli4_hba.mbx_cq->queue_id);
-	lpfc_debug_dump_q(phba->sli4_hba.mbx_cq);
-}
-
 /**
  * lpfc_debug_dump_wq_by_id - dump all entries from a work queue by queue id
  * @phba: Pointer to HBA context object.
@@ -556,14 +522,15 @@ lpfc_debug_dump_wq_by_id(struct lpfc_hba *phba, int qid)
 		if (phba->sli4_hba.fcp_wq[wq_idx]->queue_id == qid)
 			break;
 	if (wq_idx < phba->cfg_fcp_io_channel) {
-		printk(KERN_ERR "FCP WQ[Idx:%d|Qid:%d]\n", wq_idx, qid);
+		pr_err("FCP WQ[Idx:%d|Qid:%d]\n", wq_idx, qid);
 		lpfc_debug_dump_q(phba->sli4_hba.fcp_wq[wq_idx]);
 		return;
 	}
 
 	if (phba->sli4_hba.els_wq->queue_id == qid) {
-		printk(KERN_ERR "ELS WQ[Qid:%d]\n", qid);
+		pr_err("ELS WQ[Qid:%d]\n", qid);
 		lpfc_debug_dump_q(phba->sli4_hba.els_wq);
+		return;
 	}
 }
 
@@ -617,27 +584,26 @@ lpfc_debug_dump_rq_by_id(struct lpfc_hba *phba, int qid)
 static inline void
 lpfc_debug_dump_cq_by_id(struct lpfc_hba *phba, int qid)
 {
-	int cq_idx = 0;
+	int cq_idx;
 
-	do {
+	for (cq_idx = 0; cq_idx < phba->cfg_fcp_io_channel; cq_idx++)
 		if (phba->sli4_hba.fcp_cq[cq_idx]->queue_id == qid)
 			break;
-	} while (++cq_idx < phba->cfg_fcp_io_channel);
 
 	if (cq_idx < phba->cfg_fcp_io_channel) {
-		printk(KERN_ERR "FCP CQ[Idx:%d|Qid:%d]\n", cq_idx, qid);
+		pr_err("FCP CQ[Idx:%d|Qid:%d]\n", cq_idx, qid);
 		lpfc_debug_dump_q(phba->sli4_hba.fcp_cq[cq_idx]);
 		return;
 	}
 
 	if (phba->sli4_hba.els_cq->queue_id == qid) {
-		printk(KERN_ERR "ELS CQ[Qid:%d]\n", qid);
+		pr_err("ELS CQ[Qid:%d]\n", qid);
 		lpfc_debug_dump_q(phba->sli4_hba.els_cq);
 		return;
 	}
 
 	if (phba->sli4_hba.mbx_cq->queue_id == qid) {
-		printk(KERN_ERR "MBX CQ[Qid:%d]\n", qid);
+		pr_err("MBX CQ[Qid:%d]\n", qid);
 		lpfc_debug_dump_q(phba->sli4_hba.mbx_cq);
 	}
 }
-- 
GitLab


From 895427bd012ce5814fc9888c7c0ee9de44761833 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:30 -0800
Subject: [PATCH 145/898] scsi: lpfc: NVME Initiator: Base modifications

NVME Initiator: Base modifications

This patch adds base modifications for NVME initiator support.

The base modifications consist of:
- Formal split of SLI3 rings from SLI-4 WQs (sometimes referred to as
  rings as well) as implementation now widely varies between the two.
- Addition of configuration modes:
   SCSI initiator only; NVME initiator only; NVME target only; and
   SCSI and NVME initiator.
   The configuration mode drives overall adapter configuration,
   offloads enabled, and resource splits.
   NVME support is only available on SLI-4 devices and newer fw.
- Implements the following based on configuration mode:
  - Exchange resources are split by protocol; Obviously, if only
     1 mode, then no split occurs. Default is 50/50. module attribute
     allows tuning.
  - Pools and config parameters are separated per-protocol
  - Each protocol has it's own set of queues, but share interrupt
    vectors.
     SCSI:
       SLI3 devices have few queues and the original style of queue
         allocation remains.
       SLI4 devices piggy back on an "io-channel" concept that
         eventually needs to merge with scsi-mq/blk-mq support (it is
	 underway).  For now, the paradigm continues as it existed
	 prior. io channel allocates N msix and N WQs (N=4 default)
	 and either round robins or uses cpu # modulo N for scheduling.
	 A bunch of module parameters allow the configuration to be
	 tuned.
     NVME (initiator):
       Allocates an msix per cpu (or whatever pci_alloc_irq_vectors
         gets)
       Allocates a WQ per cpu, and maps the WQs to msix on a WQ #
         modulo msix vector count basis.
       Module parameters exist to cap/control the config if desired.
  - Each protocol has its own buffer and dma pools.

I apologize for the size of the patch.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>

----
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h           |   80 +-
 drivers/scsi/lpfc/lpfc_attr.c      |  374 ++++-
 drivers/scsi/lpfc/lpfc_bsg.c       |   27 +-
 drivers/scsi/lpfc/lpfc_crtn.h      |   27 +-
 drivers/scsi/lpfc/lpfc_debugfs.c   |  178 ++-
 drivers/scsi/lpfc/lpfc_debugfs.h   |   72 +-
 drivers/scsi/lpfc/lpfc_els.c       |   38 +-
 drivers/scsi/lpfc/lpfc_hbadisc.c   |  157 +-
 drivers/scsi/lpfc/lpfc_hw.h        |    3 +-
 drivers/scsi/lpfc/lpfc_hw4.h       |   63 +-
 drivers/scsi/lpfc/lpfc_init.c      | 2141 +++++++++++++++-------------
 drivers/scsi/lpfc/lpfc_logmsg.h    |    4 +
 drivers/scsi/lpfc/lpfc_mbox.c      |   23 +-
 drivers/scsi/lpfc/lpfc_mem.c       |   62 +-
 drivers/scsi/lpfc/lpfc_nportdisc.c |    7 +-
 drivers/scsi/lpfc/lpfc_nvme.h      |   88 ++
 drivers/scsi/lpfc/lpfc_scsi.c      |  101 +-
 drivers/scsi/lpfc/lpfc_scsi.h      |    6 +
 drivers/scsi/lpfc/lpfc_sli.c       | 1429 ++++++++++++++-----
 drivers/scsi/lpfc/lpfc_sli.h       |   30 +-
 drivers/scsi/lpfc/lpfc_sli4.h      |   75 +-
 drivers/scsi/lpfc/lpfc_vport.c     |    2 +
 22 files changed, 3353 insertions(+), 1634 deletions(-)
 create mode 100644 drivers/scsi/lpfc/lpfc_nvme.h

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 8e0d6f43878d..77ad757ca231 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -20,6 +20,7 @@
  *******************************************************************/
 
 #include <scsi/scsi_host.h>
+#include <linux/ktime.h>
 
 #if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_SCSI_LPFC_DEBUG_FS)
 #define CONFIG_SCSI_LPFC_DEBUG_FS
@@ -53,6 +54,7 @@ struct lpfc_sli2_slim;
 #define LPFC_MAX_SG_SEG_CNT	4096	/* sg element count per scsi cmnd */
 #define LPFC_MAX_SGL_SEG_CNT	512	/* SGL element count per scsi cmnd */
 #define LPFC_MAX_BPL_SEG_CNT	4096	/* BPL element count per scsi cmnd */
+#define LPFC_MIN_NVME_SEG_CNT	254
 
 #define LPFC_MAX_SGE_SIZE       0x80000000 /* Maximum data allowed in a SGE */
 #define LPFC_IOCB_LIST_CNT	2250	/* list of IOCBs for fast-path usage. */
@@ -114,6 +116,13 @@ enum lpfc_polling_flags {
 	DISABLE_FCP_RING_INT    = 0x2
 };
 
+struct perf_prof {
+	uint16_t cmd_cpu[40];
+	uint16_t rsp_cpu[40];
+	uint16_t qh_cpu[40];
+	uint16_t wqidx[40];
+};
+
 /* Provide DMA memory definitions the driver uses per port instance. */
 struct lpfc_dmabuf {
 	struct list_head list;
@@ -131,10 +140,24 @@ struct lpfc_dma_pool {
 struct hbq_dmabuf {
 	struct lpfc_dmabuf hbuf;
 	struct lpfc_dmabuf dbuf;
-	uint32_t size;
+	uint16_t total_size;
+	uint16_t bytes_recv;
 	uint32_t tag;
 	struct lpfc_cq_event cq_event;
 	unsigned long time_stamp;
+	void *context;
+};
+
+struct rqb_dmabuf {
+	struct lpfc_dmabuf hbuf;
+	struct lpfc_dmabuf dbuf;
+	uint16_t total_size;
+	uint16_t bytes_recv;
+	void *context;
+	struct lpfc_iocbq *iocbq;
+	struct lpfc_sglq *sglq;
+	struct lpfc_queue *hrq;	  /* ptr to associated Header RQ */
+	struct lpfc_queue *drq;	  /* ptr to associated Data RQ */
 };
 
 /* Priority bit.  Set value to exceed low water mark in lpfc_mem. */
@@ -442,6 +465,11 @@ struct lpfc_vport {
 	uint16_t fdmi_num_disc;
 	uint32_t fdmi_hba_mask;
 	uint32_t fdmi_port_mask;
+
+	/* There is a single nvme instance per vport. */
+	struct nvme_fc_local_port *localport;
+	uint8_t  nvmei_support; /* driver supports NVME Initiator */
+	uint32_t last_fcp_wqidx;
 };
 
 struct hbq_s {
@@ -459,10 +487,9 @@ struct hbq_s {
 					       struct hbq_dmabuf *);
 };
 
-#define LPFC_MAX_HBQS  4
 /* this matches the position in the lpfc_hbq_defs array */
 #define LPFC_ELS_HBQ	0
-#define LPFC_EXTRA_HBQ	1
+#define LPFC_MAX_HBQS	1
 
 enum hba_temp_state {
 	HBA_NORMAL_TEMP,
@@ -652,6 +679,8 @@ struct lpfc_hba {
 					 * Firmware supports Forced Link Speed
 					 * capability
 					 */
+#define HBA_NVME_IOQ_FLUSH      0x80000 /* NVME IO queues flushed. */
+
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;
 
@@ -700,6 +729,8 @@ struct lpfc_hba {
 	uint8_t  wwpn[8];
 	uint32_t RandomData[7];
 	uint8_t  fcp_embed_io;
+	uint8_t  nvme_support;	/* Firmware supports NVME */
+	uint8_t  nvmet_support;	/* driver supports NVMET */
 	uint8_t  mds_diags_support;
 
 	/* HBA Config Parameters */
@@ -725,6 +756,9 @@ struct lpfc_hba {
 	uint32_t cfg_fcp_imax;
 	uint32_t cfg_fcp_cpu_map;
 	uint32_t cfg_fcp_io_channel;
+	uint32_t cfg_nvme_oas;
+	uint32_t cfg_nvme_io_channel;
+	uint32_t cfg_nvme_enable_fb;
 	uint32_t cfg_total_seg_cnt;
 	uint32_t cfg_sg_seg_cnt;
 	uint32_t cfg_sg_dma_buf_size;
@@ -770,6 +804,12 @@ struct lpfc_hba {
 #define LPFC_FDMI_SUPPORT	1	/* FDMI supported? */
 	uint32_t cfg_enable_SmartSAN;
 	uint32_t cfg_enable_mds_diags;
+	uint32_t cfg_enable_fc4_type;
+	uint32_t cfg_xri_split;
+#define LPFC_ENABLE_FCP  1
+#define LPFC_ENABLE_NVME 2
+#define LPFC_ENABLE_BOTH 3
+	uint32_t io_channel_irqs;	/* number of irqs for io channels */
 	lpfc_vpd_t vpd;		/* vital product data */
 
 	struct pci_dev *pcidev;
@@ -784,11 +824,11 @@ struct lpfc_hba {
 	unsigned long data_flags;
 
 	uint32_t hbq_in_use;		/* HBQs in use flag */
-	struct list_head rb_pend_list;  /* Received buffers to be processed */
 	uint32_t hbq_count;	        /* Count of configured HBQs */
 	struct hbq_s hbqs[LPFC_MAX_HBQS]; /* local copy of hbq indicies  */
 
-	atomic_t fcp_qidx;		/* next work queue to post work to */
+	atomic_t fcp_qidx;         /* next FCP WQ (RR Policy) */
+	atomic_t nvme_qidx;        /* next NVME WQ (RR Policy) */
 
 	phys_addr_t pci_bar0_map;     /* Physical address for PCI BAR0 */
 	phys_addr_t pci_bar1_map;     /* Physical address for PCI BAR1 */
@@ -843,9 +883,17 @@ struct lpfc_hba {
 	/*
 	 * stat  counters
 	 */
-	uint64_t fc4InputRequests;
-	uint64_t fc4OutputRequests;
-	uint64_t fc4ControlRequests;
+	uint64_t fc4ScsiInputRequests;
+	uint64_t fc4ScsiOutputRequests;
+	uint64_t fc4ScsiControlRequests;
+	uint64_t fc4ScsiIoCmpls;
+	uint64_t fc4NvmeInputRequests;
+	uint64_t fc4NvmeOutputRequests;
+	uint64_t fc4NvmeControlRequests;
+	uint64_t fc4NvmeIoCmpls;
+	uint64_t fc4NvmeLsRequests;
+	uint64_t fc4NvmeLsCmpls;
+
 	uint64_t bg_guard_err_cnt;
 	uint64_t bg_apptag_err_cnt;
 	uint64_t bg_reftag_err_cnt;
@@ -856,17 +904,23 @@ struct lpfc_hba {
 	struct list_head lpfc_scsi_buf_list_get;
 	struct list_head lpfc_scsi_buf_list_put;
 	uint32_t total_scsi_bufs;
+	spinlock_t nvme_buf_list_get_lock;  /* NVME buf alloc list lock */
+	spinlock_t nvme_buf_list_put_lock;  /* NVME buf free list lock */
+	struct list_head lpfc_nvme_buf_list_get;
+	struct list_head lpfc_nvme_buf_list_put;
+	uint32_t total_nvme_bufs;
 	struct list_head lpfc_iocb_list;
 	uint32_t total_iocbq_bufs;
 	struct list_head active_rrq_list;
 	spinlock_t hbalock;
 
 	/* pci_mem_pools */
-	struct pci_pool *lpfc_scsi_dma_buf_pool;
+	struct pci_pool *lpfc_sg_dma_buf_pool;
 	struct pci_pool *lpfc_mbuf_pool;
 	struct pci_pool *lpfc_hrb_pool;	/* header receive buffer pool */
 	struct pci_pool *lpfc_drb_pool; /* data receive buffer pool */
 	struct pci_pool *lpfc_hbq_pool;	/* SLI3 hbq buffer pool */
+	struct pci_pool *txrdy_payload_pool;
 	struct lpfc_dma_pool lpfc_mbuf_safety_pool;
 
 	mempool_t *mbox_mem_pool;
@@ -1092,3 +1146,11 @@ lpfc_sli_read_hs(struct lpfc_hba *phba)
 
 	return 0;
 }
+
+static inline struct lpfc_sli_ring *
+lpfc_phba_elsring(struct lpfc_hba *phba)
+{
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		return phba->sli4_hba.els_wq->pring;
+	return &phba->sli.sli3_ring[LPFC_ELS_RING];
+}
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index ce41dea47682..b91b4bb1062d 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -35,14 +35,17 @@
 #include <scsi/scsi_transport_fc.h>
 #include <scsi/fc/fc_fs.h>
 
+#include <linux/nvme-fc-driver.h>
+
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
 #include "lpfc_sli.h"
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_version.h"
 #include "lpfc_compat.h"
@@ -129,6 +132,124 @@ lpfc_enable_fip_show(struct device *dev, struct device_attribute *attr,
 		return snprintf(buf, PAGE_SIZE, "0\n");
 }
 
+static ssize_t
+lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
+		    char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct lpfc_vport *vport = shost_priv(shost);
+	struct lpfc_hba   *phba = vport->phba;
+	struct nvme_fc_local_port *localport;
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_nvme_rport *rport;
+	struct nvme_fc_remote_port *nrport;
+	char *statep;
+	int len = 0;
+
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) {
+		len += snprintf(buf, PAGE_SIZE, "NVME Disabled\n");
+		return len;
+	}
+
+	localport = vport->localport;
+	if (!localport) {
+		len = snprintf(buf, PAGE_SIZE,
+				"NVME Initiator x%llx is not allocated\n",
+				wwn_to_u64(vport->fc_portname.u.wwn));
+		return len;
+	}
+	len = snprintf(buf, PAGE_SIZE, "NVME Initiator Enabled\n");
+
+	spin_lock_irq(shost->host_lock);
+	lport = (struct lpfc_nvme_lport *)localport->private;
+
+	/* Port state is only one of two values for now. */
+	if (localport->port_id)
+		statep = "ONLINE";
+	else
+		statep = "UNKNOWN ";
+
+	len += snprintf(buf + len, PAGE_SIZE - len,
+			"%s%d WWPN x%llx WWNN x%llx DID x%06x %s\n",
+			"NVME LPORT lpfc",
+			phba->brd_no,
+			wwn_to_u64(vport->fc_portname.u.wwn),
+			wwn_to_u64(vport->fc_nodename.u.wwn),
+			localport->port_id, statep);
+
+	list_for_each_entry(rport, &lport->rport_list, list) {
+		/* local short-hand pointer. */
+		nrport = rport->remoteport;
+
+		/* Port state is only one of two values for now. */
+		switch (nrport->port_state) {
+		case FC_OBJSTATE_ONLINE:
+			statep = "ONLINE";
+			break;
+		case FC_OBJSTATE_UNKNOWN:
+			statep = "UNKNOWN ";
+			break;
+		default:
+			statep = "UNSUPPORTED";
+			break;
+		}
+
+		/* Tab in to show lport ownership. */
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"NVME RPORT       ");
+		if (phba->brd_no >= 10)
+			len += snprintf(buf + len, PAGE_SIZE - len, " ");
+
+		len += snprintf(buf + len, PAGE_SIZE - len, "WWPN x%llx ",
+				nrport->port_name);
+		len += snprintf(buf + len, PAGE_SIZE - len, "WWNN x%llx ",
+				nrport->node_name);
+		len += snprintf(buf + len, PAGE_SIZE - len, "DID x%06x ",
+				nrport->port_id);
+
+		switch (nrport->port_role) {
+		case FC_PORT_ROLE_NVME_INITIATOR:
+			len +=  snprintf(buf + len, PAGE_SIZE - len,
+					 "INITIATOR ");
+			break;
+		case FC_PORT_ROLE_NVME_TARGET:
+			len +=  snprintf(buf + len, PAGE_SIZE - len,
+					 "TARGET ");
+			break;
+		case FC_PORT_ROLE_NVME_DISCOVERY:
+			len +=  snprintf(buf + len, PAGE_SIZE - len,
+					 "DISCOVERY ");
+			break;
+		default:
+			len +=  snprintf(buf + len, PAGE_SIZE - len,
+					 "UNKNOWN_ROLE x%x",
+					 nrport->port_role);
+			break;
+		}
+		len +=  snprintf(buf + len, PAGE_SIZE - len, "%s  ", statep);
+		/* Terminate the string. */
+		len +=  snprintf(buf + len, PAGE_SIZE - len, "\n");
+	}
+	spin_unlock_irq(shost->host_lock);
+
+	len += snprintf(buf + len, PAGE_SIZE, "\nNVME Statistics\n");
+	len += snprintf(buf+len, PAGE_SIZE-len,
+			"LS: Xmt %016llx Cmpl %016llx\n",
+			phba->fc4NvmeLsRequests,
+			phba->fc4NvmeLsCmpls);
+
+	len += snprintf(buf+len, PAGE_SIZE-len,
+			"FCP: Rd %016llx Wr %016llx IO %016llx\n",
+			phba->fc4NvmeInputRequests,
+			phba->fc4NvmeOutputRequests,
+			phba->fc4NvmeControlRequests);
+
+	len += snprintf(buf+len, PAGE_SIZE-len,
+			"    Cmpl %016llx\n", phba->fc4NvmeIoCmpls);
+
+	return len;
+}
+
 static ssize_t
 lpfc_bg_info_show(struct device *dev, struct device_attribute *attr,
 		  char *buf)
@@ -675,6 +796,28 @@ lpfc_issue_lip(struct Scsi_Host *shost)
 	return 0;
 }
 
+int
+lpfc_emptyq_wait(struct lpfc_hba *phba, struct list_head *q, spinlock_t *lock)
+{
+	int cnt = 0;
+
+	spin_lock_irq(lock);
+	while (!list_empty(q)) {
+		spin_unlock_irq(lock);
+		msleep(20);
+		if (cnt++ > 250) {  /* 5 secs */
+			lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+					"0466 %s %s\n",
+					"Outstanding IO when ",
+					"bringing Adapter offline\n");
+				return 0;
+		}
+		spin_lock_irq(lock);
+	}
+	spin_unlock_irq(lock);
+	return 1;
+}
+
 /**
  * lpfc_do_offline - Issues a mailbox command to bring the link down
  * @phba: lpfc_hba pointer.
@@ -694,10 +837,10 @@ static int
 lpfc_do_offline(struct lpfc_hba *phba, uint32_t type)
 {
 	struct completion online_compl;
+	struct lpfc_queue *qp = NULL;
 	struct lpfc_sli_ring *pring;
 	struct lpfc_sli *psli;
 	int status = 0;
-	int cnt = 0;
 	int i;
 	int rc;
 
@@ -717,20 +860,24 @@ lpfc_do_offline(struct lpfc_hba *phba, uint32_t type)
 	/* Wait a little for things to settle down, but not
 	 * long enough for dev loss timeout to expire.
 	 */
-	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
-		while (!list_empty(&pring->txcmplq)) {
-			msleep(10);
-			if (cnt++ > 500) {  /* 5 secs */
-				lpfc_printf_log(phba,
-					KERN_WARNING, LOG_INIT,
-					"0466 Outstanding IO when "
-					"bringing Adapter offline\n");
-				break;
-			}
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		for (i = 0; i < psli->num_rings; i++) {
+			pring = &psli->sli3_ring[i];
+			if (!lpfc_emptyq_wait(phba, &pring->txcmplq,
+					      &phba->hbalock))
+				goto out;
+		}
+	} else {
+		list_for_each_entry(qp, &phba->sli4_hba.lpfc_wq_list, wq_list) {
+			pring = qp->pring;
+			if (!pring)
+				continue;
+			if (!lpfc_emptyq_wait(phba, &pring->txcmplq,
+					      &pring->ring_lock))
+				goto out;
 		}
 	}
-
+out:
 	init_completion(&online_compl);
 	rc = lpfc_workq_post_event(phba, &status, &online_compl, type);
 	if (rc == 0)
@@ -1945,6 +2092,7 @@ lpfc_##attr##_store(struct device *dev, struct device_attribute *attr, \
 }
 
 
+static DEVICE_ATTR(nvme_info, 0444, lpfc_nvme_info_show, NULL);
 static DEVICE_ATTR(bg_info, S_IRUGO, lpfc_bg_info_show, NULL);
 static DEVICE_ATTR(bg_guard_err, S_IRUGO, lpfc_bg_guard_err_show, NULL);
 static DEVICE_ATTR(bg_apptag_err, S_IRUGO, lpfc_bg_apptag_err_show, NULL);
@@ -2816,9 +2964,9 @@ lpfc_txq_hw_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct Scsi_Host  *shost = class_to_shost(dev);
 	struct lpfc_hba   *phba = ((struct lpfc_vport *) shost->hostdata)->phba;
+	struct lpfc_sli_ring *pring = lpfc_phba_elsring(phba);
 
-	return snprintf(buf, PAGE_SIZE, "%d\n",
-		phba->sli.ring[LPFC_ELS_RING].txq_max);
+	return snprintf(buf, PAGE_SIZE, "%d\n", pring->txq_max);
 }
 
 static DEVICE_ATTR(txq_hw, S_IRUGO,
@@ -2829,9 +2977,9 @@ lpfc_txcmplq_hw_show(struct device *dev, struct device_attribute *attr,
 {
 	struct Scsi_Host  *shost = class_to_shost(dev);
 	struct lpfc_hba   *phba = ((struct lpfc_vport *) shost->hostdata)->phba;
+	struct lpfc_sli_ring *pring = lpfc_phba_elsring(phba);
 
-	return snprintf(buf, PAGE_SIZE, "%d\n",
-		phba->sli.ring[LPFC_ELS_RING].txcmplq_max);
+	return snprintf(buf, PAGE_SIZE, "%d\n", pring->txcmplq_max);
 }
 
 static DEVICE_ATTR(txcmplq_hw, S_IRUGO,
@@ -3029,6 +3177,31 @@ lpfc_vport_param_store(devloss_tmo)
 static DEVICE_ATTR(lpfc_devloss_tmo, S_IRUGO | S_IWUSR,
 		   lpfc_devloss_tmo_show, lpfc_devloss_tmo_store);
 
+/*
+ * lpfc_enable_fc4_type: Defines what FC4 types are supported.
+ * Supported Values:  1 - register just FCP
+ *                    3 - register both FCP and NVME
+ * Supported values are [1,3]. Default value is 3
+ */
+LPFC_ATTR_R(enable_fc4_type, LPFC_ENABLE_BOTH,
+	    LPFC_ENABLE_FCP, LPFC_ENABLE_BOTH,
+	    "Define fc4 type to register with fabric.");
+
+/*
+ * lpfc_xri_split: Defines the division of XRI resources between SCSI and NVME
+ * This parameter is only used if:
+ *     lpfc_enable_fc4_type is 3 - register both FCP and NVME
+ *
+ * ELS/CT always get 10% of XRIs, up to a maximum of 250
+ * The remaining XRIs get split up based on lpfc_xri_split per port:
+ *
+ * Supported Values are in percentages
+ * the xri_split value is the percentage the SCSI port will get. The remaining
+ * percentage will go to NVME.
+ */
+LPFC_ATTR_R(xri_split, 50, 10, 90,
+	     "Division of XRI resources between SCSI and NVME");
+
 /*
 # lpfc_log_verbose: Only turn this flag on if you are willing to risk being
 # deluged with LOTS of information.
@@ -4143,13 +4316,14 @@ lpfc_fcp_imax_store(struct device *dev, struct device_attribute *attr,
 	/*
 	 * Value range for the HBA is [5000,5000000]
 	 * The value for each EQ depends on how many EQs are configured.
+	 * Allow value == 0
 	 */
-	if (val < LPFC_MIN_IMAX || val > LPFC_MAX_IMAX)
+	if (val && (val < LPFC_MIN_IMAX || val > LPFC_MAX_IMAX))
 		return -EINVAL;
 
 	phba->cfg_fcp_imax = (uint32_t)val;
-	for (i = 0; i < phba->cfg_fcp_io_channel; i += LPFC_MAX_EQ_DELAY)
-		lpfc_modify_fcp_eq_delay(phba, i);
+	for (i = 0; i < phba->io_channel_irqs; i++)
+		lpfc_modify_hba_eq_delay(phba, i);
 
 	return strlen(buf);
 }
@@ -4187,7 +4361,8 @@ lpfc_fcp_imax_init(struct lpfc_hba *phba, int val)
 		return 0;
 	}
 
-	if (val >= LPFC_MIN_IMAX && val <= LPFC_MAX_IMAX) {
+	if ((val >= LPFC_MIN_IMAX && val <= LPFC_MAX_IMAX) ||
+	    (val == 0)) {
 		phba->cfg_fcp_imax = val;
 		return 0;
 	}
@@ -4376,6 +4551,17 @@ LPFC_VPORT_ATTR_RW(use_adisc, 0, 0, 1,
 LPFC_VPORT_ATTR_RW(first_burst_size, 0, 0, 65536,
 		   "First burst size for Targets that support first burst");
 
+/*
+* lpfc_nvme_enable_fb: Enable NVME first burst on I and T functions.
+* For the Initiator (I), enabling this parameter means that an NVME
+* PRLI response with FBA enabled and an FB_SIZE set to a nonzero value
+* will be processed by the initiator for subsequent NVME FCP IO.
+* Parameter supported on physical port only - no NPIV support.
+* Value range is [0,1]. Default value is 0 (disabled).
+*/
+LPFC_ATTR_RW(nvme_enable_fb, 0, 0, 1,
+	     "Enable First Burst feature on I and T functions.");
+
 /*
 # lpfc_max_scsicmpl_time: Use scsi command completion time to control I/O queue
 # depth. Default value is 0. When the value of this parameter is zero the
@@ -4423,17 +4609,25 @@ static DEVICE_ATTR(lpfc_max_scsicmpl_time, S_IRUGO | S_IWUSR,
 LPFC_ATTR_R(ack0, 0, 0, 1, "Enable ACK0 support");
 
 /*
-# lpfc_fcp_io_sched: Determine scheduling algrithmn for issuing FCP cmds
-# range is [0,1]. Default value is 0.
-# For [0], FCP commands are issued to Work Queues ina round robin fashion.
-# For [1], FCP commands are issued to a Work Queue associated with the
-#          current CPU.
-# It would be set to 1 by the driver if it's able to set up cpu affinity
-# for FCP I/Os through Work Queue associated with the current CPU. Otherwise,
-# roundrobin scheduling of FCP I/Os through WQs will be used.
-*/
-LPFC_ATTR_RW(fcp_io_sched, 0, 0, 1, "Determine scheduling algorithm for "
-		"issuing commands [0] - Round Robin, [1] - Current CPU");
+ * lpfc_io_sched: Determine scheduling algrithmn for issuing FCP cmds
+ * range is [0,1]. Default value is 0.
+ * For [0], FCP commands are issued to Work Queues ina round robin fashion.
+ * For [1], FCP commands are issued to a Work Queue associated with the
+ *          current CPU.
+ *
+ * LPFC_FCP_SCHED_ROUND_ROBIN == 0
+ * LPFC_FCP_SCHED_BY_CPU == 1
+ *
+ * The driver dynamically sets this to 1 (BY_CPU) if it's able to set up cpu
+ * affinity for FCP/NVME I/Os through Work Queues associated with the current
+ * CPU. Otherwise, the default 0 (Round Robin) scheduling of FCP/NVME I/Os
+ * through WQs will be used.
+ */
+LPFC_ATTR_RW(fcp_io_sched, LPFC_FCP_SCHED_ROUND_ROBIN,
+	     LPFC_FCP_SCHED_ROUND_ROBIN,
+	     LPFC_FCP_SCHED_BY_CPU,
+	     "Determine scheduling algorithm for "
+	     "issuing commands [0] - Round Robin, [1] - Current CPU");
 
 /*
 # lpfc_fcp2_no_tgt_reset: Determine bus reset behavior
@@ -4560,14 +4754,53 @@ LPFC_ATTR_R(use_msi, 2, 0, 2, "Use Message Signaled Interrupts (1) or "
 	    "MSI-X (2), if possible");
 
 /*
-# lpfc_fcp_io_channel: Set the number of FCP EQ/CQ/WQ IO channels
-#
-# Value range is [1,7]. Default value is 4.
-*/
-LPFC_ATTR_R(fcp_io_channel, LPFC_FCP_IO_CHAN_DEF, LPFC_FCP_IO_CHAN_MIN,
-	    LPFC_FCP_IO_CHAN_MAX,
+ * lpfc_nvme_oas: Use the oas bit when sending NVME IOs
+ *
+ *      0  = NVME OAS disabled
+ *      1  = NVME OAS enabled
+ *
+ * Value range is [0,1]. Default value is 0.
+ */
+LPFC_ATTR_RW(nvme_oas, 0, 0, 1,
+	     "Use OAS bit on NVME IOs");
+
+/*
+ * lpfc_fcp_io_channel: Set the number of FCP IO channels the driver
+ * will advertise it supports to the SCSI layer. This also will map to
+ * the number of WQs the driver will create.
+ *
+ *      0    = Configure the number of io channels to the number of active CPUs.
+ *      1,32 = Manually specify how many io channels to use.
+ *
+ * Value range is [0,32]. Default value is 4.
+ */
+LPFC_ATTR_R(fcp_io_channel,
+	    LPFC_FCP_IO_CHAN_DEF,
+	    LPFC_HBA_IO_CHAN_MIN, LPFC_HBA_IO_CHAN_MAX,
 	    "Set the number of FCP I/O channels");
 
+/*
+ * lpfc_nvme_io_channel: Set the number of IO hardware queues the driver
+ * will advertise it supports to the NVME layer. This also will map to
+ * the number of WQs the driver will create.
+ *
+ * This module parameter is valid when lpfc_enable_fc4_type is set
+ * to support NVME.
+ *
+ * The NVME Layer will try to create this many, plus 1 administrative
+ * hardware queue. The administrative queue will always map to WQ 0
+ * A hardware IO queue maps (qidx) to a specific driver WQ.
+ *
+ *      0    = Configure the number of io channels to the number of active CPUs.
+ *      1,32 = Manually specify how many io channels to use.
+ *
+ * Value range is [0,32]. Default value is 0.
+ */
+LPFC_ATTR_R(nvme_io_channel,
+	    LPFC_NVME_IO_CHAN_DEF,
+	    LPFC_HBA_IO_CHAN_MIN, LPFC_HBA_IO_CHAN_MAX,
+	    "Set the number of NVME I/O channels");
+
 /*
 # lpfc_enable_hba_reset: Allow or prevent HBA resets to the hardware.
 #       0  = HBA resets disabled
@@ -4692,6 +4925,7 @@ LPFC_ATTR_R(sg_seg_cnt, LPFC_DEFAULT_SG_SEG_CNT, LPFC_DEFAULT_SG_SEG_CNT,
 LPFC_ATTR_R(enable_mds_diags, 0, 0, 1, "Enable MDS Diagnostics");
 
 struct device_attribute *lpfc_hba_attrs[] = {
+	&dev_attr_nvme_info,
 	&dev_attr_bg_info,
 	&dev_attr_bg_guard_err,
 	&dev_attr_bg_apptag_err,
@@ -4718,6 +4952,8 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_peer_port_login,
 	&dev_attr_lpfc_nodev_tmo,
 	&dev_attr_lpfc_devloss_tmo,
+	&dev_attr_lpfc_enable_fc4_type,
+	&dev_attr_lpfc_xri_split,
 	&dev_attr_lpfc_fcp_class,
 	&dev_attr_lpfc_use_adisc,
 	&dev_attr_lpfc_first_burst_size,
@@ -4752,9 +4988,12 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_poll_tmo,
 	&dev_attr_lpfc_task_mgmt_tmo,
 	&dev_attr_lpfc_use_msi,
+	&dev_attr_lpfc_nvme_oas,
 	&dev_attr_lpfc_fcp_imax,
 	&dev_attr_lpfc_fcp_cpu_map,
 	&dev_attr_lpfc_fcp_io_channel,
+	&dev_attr_lpfc_nvme_io_channel,
+	&dev_attr_lpfc_nvme_enable_fb,
 	&dev_attr_lpfc_enable_bg,
 	&dev_attr_lpfc_soft_wwnn,
 	&dev_attr_lpfc_soft_wwpn,
@@ -5764,9 +6003,9 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	lpfc_fdmi_on_init(phba, lpfc_fdmi_on);
 	lpfc_enable_SmartSAN_init(phba, lpfc_enable_SmartSAN);
 	lpfc_use_msi_init(phba, lpfc_use_msi);
+	lpfc_nvme_oas_init(phba, lpfc_nvme_oas);
 	lpfc_fcp_imax_init(phba, lpfc_fcp_imax);
 	lpfc_fcp_cpu_map_init(phba, lpfc_fcp_cpu_map);
-	lpfc_fcp_io_channel_init(phba, lpfc_fcp_io_channel);
 	lpfc_enable_hba_reset_init(phba, lpfc_enable_hba_reset);
 	lpfc_enable_hba_heartbeat_init(phba, lpfc_enable_hba_heartbeat);
 
@@ -5789,8 +6028,43 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	else
 		phba->cfg_poll = lpfc_poll;
 
+	lpfc_enable_fc4_type_init(phba, lpfc_enable_fc4_type);
+
+	/* Initialize first burst. Target vs Initiator are different. */
+	lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb);
+	lpfc_fcp_io_channel_init(phba, lpfc_fcp_io_channel);
+	lpfc_nvme_io_channel_init(phba, lpfc_nvme_io_channel);
+
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		/* NVME only supported on SLI4 */
+		phba->nvmet_support = 0;
+		phba->cfg_enable_fc4_type = LPFC_ENABLE_FCP;
+	} else {
+		/* We MUST have FCP support */
+		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
+			phba->cfg_enable_fc4_type |= LPFC_ENABLE_FCP;
+	}
+
+	/* A value of 0 means use the number of CPUs found in the system */
+	if (phba->cfg_nvme_io_channel == 0)
+		phba->cfg_nvme_io_channel = phba->sli4_hba.num_present_cpu;
+	if (phba->cfg_fcp_io_channel == 0)
+		phba->cfg_fcp_io_channel = phba->sli4_hba.num_present_cpu;
+
+	if (phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP)
+		phba->cfg_nvme_io_channel = 0;
+
+	if (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)
+		phba->cfg_fcp_io_channel = 0;
+
+	if (phba->cfg_fcp_io_channel > phba->cfg_nvme_io_channel)
+		phba->io_channel_irqs = phba->cfg_fcp_io_channel;
+	else
+		phba->io_channel_irqs = phba->cfg_nvme_io_channel;
+
 	phba->cfg_soft_wwnn = 0L;
 	phba->cfg_soft_wwpn = 0L;
+	lpfc_xri_split_init(phba, lpfc_xri_split);
 	lpfc_sg_seg_cnt_init(phba, lpfc_sg_seg_cnt);
 	lpfc_hba_queue_depth_init(phba, lpfc_hba_queue_depth);
 	lpfc_hba_log_verbose_init(phba, lpfc_log_verbose);
@@ -5806,6 +6080,26 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	return;
 }
 
+/**
+ * lpfc_nvme_mod_param_dep - Adjust module parameter value based on
+ * dependencies between protocols and roles.
+ * @phba: lpfc_hba pointer.
+ **/
+void
+lpfc_nvme_mod_param_dep(struct lpfc_hba *phba)
+{
+	phba->nvmet_support = 0;
+	if (phba->cfg_nvme_io_channel > phba->sli4_hba.num_present_cpu)
+		phba->cfg_nvme_io_channel = phba->sli4_hba.num_present_cpu;
+	if (phba->cfg_fcp_io_channel > phba->sli4_hba.num_present_cpu)
+		phba->cfg_fcp_io_channel = phba->sli4_hba.num_present_cpu;
+
+	if (phba->cfg_fcp_io_channel > phba->cfg_nvme_io_channel)
+		phba->io_channel_irqs = phba->cfg_fcp_io_channel;
+	else
+		phba->io_channel_irqs = phba->cfg_nvme_io_channel;
+}
+
 /**
  * lpfc_get_vport_cfgparam - Used during port create, init the vport structure
  * @vport: lpfc_vport pointer.
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 1ee131f124b9..55a2270cadfc 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -1704,6 +1704,7 @@ lpfc_bsg_diag_mode_enter(struct lpfc_hba *phba)
 	struct lpfc_vport **vports;
 	struct Scsi_Host *shost;
 	struct lpfc_sli *psli;
+	struct lpfc_queue *qp = NULL;
 	struct lpfc_sli_ring *pring;
 	int i = 0;
 
@@ -1711,9 +1712,6 @@ lpfc_bsg_diag_mode_enter(struct lpfc_hba *phba)
 	if (!psli)
 		return -ENODEV;
 
-	pring = &psli->ring[LPFC_FCP_RING];
-	if (!pring)
-		return -ENODEV;
 
 	if ((phba->link_state == LPFC_HBA_ERROR) ||
 	    (psli->sli_flag & LPFC_BLOCK_MGMT_IO) ||
@@ -1732,10 +1730,18 @@ lpfc_bsg_diag_mode_enter(struct lpfc_hba *phba)
 		scsi_block_requests(shost);
 	}
 
-	while (!list_empty(&pring->txcmplq)) {
-		if (i++ > 500)  /* wait up to 5 seconds */
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		pring = &psli->sli3_ring[LPFC_FCP_RING];
+		lpfc_emptyq_wait(phba, &pring->txcmplq, &phba->hbalock);
+		return 0;
+	}
+	list_for_each_entry(qp, &phba->sli4_hba.lpfc_wq_list, wq_list) {
+		pring = qp->pring;
+		if (!pring || (pring->ringno != LPFC_FCP_RING))
+			continue;
+		if (!lpfc_emptyq_wait(phba, &pring->txcmplq,
+				      &pring->ring_lock))
 			break;
-		msleep(10);
 	}
 	return 0;
 }
@@ -2875,8 +2881,7 @@ diag_cmd_data_alloc(struct lpfc_hba *phba,
 static int lpfcdiag_loop_post_rxbufs(struct lpfc_hba *phba, uint16_t rxxri,
 			     size_t len)
 {
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *pring = &psli->ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *cmdiocbq;
 	IOCB_t *cmd = NULL;
 	struct list_head head, *curr, *next;
@@ -2890,6 +2895,8 @@ static int lpfcdiag_loop_post_rxbufs(struct lpfc_hba *phba, uint16_t rxxri,
 	int iocb_stat;
 	int i = 0;
 
+	pring = lpfc_phba_elsring(phba);
+
 	cmdiocbq = lpfc_sli_get_iocbq(phba);
 	rxbmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
 	if (rxbmp != NULL) {
@@ -5403,13 +5410,15 @@ lpfc_bsg_timeout(struct bsg_job *job)
 	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_iocbq *cmdiocb;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 	struct bsg_job_data *dd_data;
 	unsigned long flags;
 	int rc = 0;
 	LIST_HEAD(completions);
 	struct lpfc_iocbq *check_iocb, *next_iocb;
 
+	pring = lpfc_phba_elsring(phba);
+
 	/* if job's driver data is NULL, the command completed or is in the
 	 * the process of completing.  In this case, return status to request
 	 * so the timeout is retried.  This avoids double completion issues
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 309643a2c55c..2e6345ebd6c5 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -21,6 +21,7 @@
 typedef int (*node_filter)(struct lpfc_nodelist *, void *);
 
 struct fc_rport;
+struct fc_frame_header;
 void lpfc_down_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_sli_read_link_ste(struct lpfc_hba *);
 void lpfc_dump_mem(struct lpfc_hba *, LPFC_MBOXQ_t *, uint16_t, uint16_t);
@@ -167,6 +168,8 @@ void lpfc_hb_timeout_handler(struct lpfc_hba *);
 void lpfc_ct_unsol_event(struct lpfc_hba *, struct lpfc_sli_ring *,
 			 struct lpfc_iocbq *);
 int lpfc_ct_handle_unsol_abort(struct lpfc_hba *, struct hbq_dmabuf *);
+int lpfc_issue_gidft(struct lpfc_vport *vport);
+int lpfc_get_gidft_type(struct lpfc_vport *vport, struct lpfc_iocbq *iocbq);
 int lpfc_ns_cmd(struct lpfc_vport *, int, uint8_t, uint32_t);
 int lpfc_fdmi_cmd(struct lpfc_vport *, struct lpfc_nodelist *, int, uint32_t);
 void lpfc_fdmi_num_disc_check(struct lpfc_vport *);
@@ -186,6 +189,8 @@ void lpfc_unblock_mgmt_io(struct lpfc_hba *);
 void lpfc_offline_prep(struct lpfc_hba *, int);
 void lpfc_offline(struct lpfc_hba *);
 void lpfc_reset_hba(struct lpfc_hba *);
+int lpfc_emptyq_wait(struct lpfc_hba *phba, struct list_head *hd,
+			spinlock_t *slock);
 
 int lpfc_fof_queue_create(struct lpfc_hba *);
 int lpfc_fof_queue_setup(struct lpfc_hba *);
@@ -193,7 +198,11 @@ int lpfc_fof_queue_destroy(struct lpfc_hba *);
 irqreturn_t lpfc_sli4_fof_intr_handler(int, void *);
 
 int lpfc_sli_setup(struct lpfc_hba *);
-int lpfc_sli_queue_setup(struct lpfc_hba *);
+int lpfc_sli4_setup(struct lpfc_hba *phba);
+void lpfc_sli_queue_init(struct lpfc_hba *phba);
+void lpfc_sli4_queue_init(struct lpfc_hba *phba);
+struct lpfc_sli_ring *lpfc_sli4_calc_ring(struct lpfc_hba *phba,
+					  struct lpfc_iocbq *iocbq);
 
 void lpfc_handle_eratt(struct lpfc_hba *);
 void lpfc_handle_latt(struct lpfc_hba *);
@@ -233,6 +242,11 @@ struct hbq_dmabuf *lpfc_sli4_rb_alloc(struct lpfc_hba *);
 void lpfc_sli4_rb_free(struct lpfc_hba *, struct hbq_dmabuf *);
 void lpfc_sli4_build_dflt_fcf_record(struct lpfc_hba *, struct fcf_record *,
 			uint16_t);
+int lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
+		     struct lpfc_rqe *hrqe, struct lpfc_rqe *drqe);
+int lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq,
+			struct lpfc_queue *dq, int count);
+int lpfc_free_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq);
 void lpfc_unregister_fcf(struct lpfc_hba *);
 void lpfc_unregister_fcf_rescan(struct lpfc_hba *);
 void lpfc_unregister_unused_fcf(struct lpfc_hba *);
@@ -287,6 +301,9 @@ void lpfc_sli_def_mbox_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *, LPFC_MBOXQ_t *);
 int lpfc_sli_issue_iocb(struct lpfc_hba *, uint32_t,
 			struct lpfc_iocbq *, uint32_t);
+int lpfc_sli4_issue_wqe(struct lpfc_hba *phba, uint32_t rnum,
+			struct lpfc_iocbq *iocbq);
+struct lpfc_sglq *__lpfc_clear_active_sglq(struct lpfc_hba *phba, uint16_t xri);
 void lpfc_sli_pcimem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_bemem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_abort_iocb_ring(struct lpfc_hba *, struct lpfc_sli_ring *);
@@ -356,6 +373,7 @@ extern struct device_attribute *lpfc_hba_attrs[];
 extern struct device_attribute *lpfc_vport_attrs[];
 extern struct scsi_host_template lpfc_template;
 extern struct scsi_host_template lpfc_template_s3;
+extern struct scsi_host_template lpfc_template_nvme;
 extern struct scsi_host_template lpfc_vport_template;
 extern struct fc_function_template lpfc_transport_functions;
 extern struct fc_function_template lpfc_vport_transport_functions;
@@ -471,7 +489,9 @@ int lpfc_issue_unreg_vfi(struct lpfc_vport *);
 int lpfc_selective_reset(struct lpfc_hba *);
 int lpfc_sli4_read_config(struct lpfc_hba *);
 void lpfc_sli4_node_prep(struct lpfc_hba *);
-int lpfc_sli4_xri_sgl_update(struct lpfc_hba *);
+int lpfc_sli4_els_sgl_update(struct lpfc_hba *phba);
+int lpfc_sli4_scsi_sgl_update(struct lpfc_hba *phba);
+int lpfc_sli4_nvme_sgl_update(struct lpfc_hba *phba);
 void lpfc_free_sgl_list(struct lpfc_hba *, struct list_head *);
 uint32_t lpfc_sli_port_speed_get(struct lpfc_hba *);
 int lpfc_sli4_request_firmware_update(struct lpfc_hba *, uint8_t);
@@ -496,3 +516,6 @@ bool lpfc_find_next_oas_lun(struct lpfc_hba *, struct lpfc_name *,
 			    uint32_t *, uint32_t *);
 int lpfc_sli4_dump_page_a0(struct lpfc_hba *phba, struct lpfcMboxq *mbox);
 void lpfc_mbx_cmpl_rdp_page_a0(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb);
+
+/* NVME interfaces. */
+void lpfc_nvme_mod_param_dep(struct lpfc_hba *phba);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 93ddda16c632..d9bbebe8eb37 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -484,20 +484,23 @@ lpfc_debugfs_dumpHostSlim_data(struct lpfc_hba *phba, char *buf, int size)
 		off += (8 * sizeof(uint32_t));
 	}
 
-	for (i = 0; i < 4; i++) {
-		pgpp = &phba->port_gp[i];
-		pring = &psli->ring[i];
-		len +=  snprintf(buf+len, size-len,
-				 "Ring %d: CMD GetInx:%d (Max:%d Next:%d "
-				 "Local:%d flg:x%x)  RSP PutInx:%d Max:%d\n",
-				 i, pgpp->cmdGetInx, pring->sli.sli3.numCiocb,
-				 pring->sli.sli3.next_cmdidx,
-				 pring->sli.sli3.local_getidx,
-				 pring->flag, pgpp->rspPutInx,
-				 pring->sli.sli3.numRiocb);
-	}
-
 	if (phba->sli_rev <= LPFC_SLI_REV3) {
+		for (i = 0; i < 4; i++) {
+			pgpp = &phba->port_gp[i];
+			pring = &psli->sli3_ring[i];
+			len +=  snprintf(buf+len, size-len,
+					 "Ring %d: CMD GetInx:%d "
+					 "(Max:%d Next:%d "
+					 "Local:%d flg:x%x)  "
+					 "RSP PutInx:%d Max:%d\n",
+					 i, pgpp->cmdGetInx,
+					 pring->sli.sli3.numCiocb,
+					 pring->sli.sli3.next_cmdidx,
+					 pring->sli.sli3.local_getidx,
+					 pring->flag, pgpp->rspPutInx,
+					 pring->sli.sli3.numRiocb);
+		}
+
 		word0 = readl(phba->HAregaddr);
 		word1 = readl(phba->CAregaddr);
 		word2 = readl(phba->HSregaddr);
@@ -535,6 +538,7 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 
 	cnt = (LPFC_NODELIST_SIZE / LPFC_NODELIST_ENTRY_SIZE);
 
+	len += snprintf(buf+len, size-len, "\nFCP Nodelist Entries ...\n");
 	spin_lock_irq(shost->host_lock);
 	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
 		if (!cnt) {
@@ -2011,6 +2015,14 @@ lpfc_idiag_wqs_for_cq(struct lpfc_hba *phba, char *wqtype, char *pbuffer,
 		if (*len >= max_cnt)
 			return 1;
 	}
+	for (qidx = 0; qidx < phba->cfg_nvme_io_channel; qidx++) {
+		qp = phba->sli4_hba.nvme_wq[qidx];
+		if (qp->assoc_qid != cq_id)
+			continue;
+		*len = __lpfc_idiag_print_wq(qp, wqtype, pbuffer, *len);
+		if (*len >= max_cnt)
+			return 1;
+	}
 	return 0;
 }
 
@@ -2096,6 +2108,25 @@ lpfc_idiag_cqs_for_eq(struct lpfc_hba *phba, char *pbuffer,
 			return 1;
 	}
 
+	for (qidx = 0; qidx < phba->cfg_nvme_io_channel; qidx++) {
+		qp = phba->sli4_hba.nvme_cq[qidx];
+		if (qp->assoc_qid != eq_id)
+			continue;
+
+		*len = __lpfc_idiag_print_cq(qp, "NVME", pbuffer, *len);
+
+		/* Reset max counter */
+		qp->CQ_max_cqe = 0;
+
+		if (*len >= max_cnt)
+			return 1;
+
+		rc = lpfc_idiag_wqs_for_cq(phba, "NVME", pbuffer, len,
+				max_cnt, qp->queue_id);
+		if (rc)
+			return 1;
+	}
+
 	return 0;
 }
 
@@ -2162,21 +2193,21 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 	spin_lock_irq(&phba->hbalock);
 
 	/* Fast-path event queue */
-	if (phba->sli4_hba.hba_eq && phba->cfg_fcp_io_channel) {
+	if (phba->sli4_hba.hba_eq && phba->io_channel_irqs) {
 
 		x = phba->lpfc_idiag_last_eq;
-		if (phba->cfg_fof && (x >= phba->cfg_fcp_io_channel)) {
+		if (phba->cfg_fof && (x >= phba->io_channel_irqs)) {
 			phba->lpfc_idiag_last_eq = 0;
 			goto fof;
 		}
 		phba->lpfc_idiag_last_eq++;
-		if (phba->lpfc_idiag_last_eq >= phba->cfg_fcp_io_channel)
+		if (phba->lpfc_idiag_last_eq >= phba->io_channel_irqs)
 			if (phba->cfg_fof == 0)
 				phba->lpfc_idiag_last_eq = 0;
 
 		len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
 					"EQ %d out of %d HBA EQs\n",
-					x, phba->cfg_fcp_io_channel);
+					x, phba->io_channel_irqs);
 
 		/* Fast-path EQ */
 		qp = phba->sli4_hba.hba_eq[x];
@@ -2191,6 +2222,7 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 		if (len >= max_cnt)
 			goto too_big;
 
+		/* will dump both fcp and nvme cqs/wqs for the eq */
 		rc = lpfc_idiag_cqs_for_eq(phba, pbuffer, &len,
 			max_cnt, qp->queue_id);
 		if (rc)
@@ -2227,6 +2259,23 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 		if (len >= max_cnt)
 			goto too_big;
 
+		/* Slow-path NVME LS response CQ */
+		qp = phba->sli4_hba.nvmels_cq;
+		len = __lpfc_idiag_print_cq(qp, "NVME LS",
+						pbuffer, len);
+		/* Reset max counter */
+		if (qp)
+			qp->CQ_max_cqe = 0;
+		if (len >= max_cnt)
+			goto too_big;
+
+		/* Slow-path NVME LS WQ */
+		qp = phba->sli4_hba.nvmels_wq;
+		len = __lpfc_idiag_print_wq(qp, "NVME LS",
+						pbuffer, len);
+		if (len >= max_cnt)
+			goto too_big;
+
 		qp = phba->sli4_hba.hdr_rq;
 		len = __lpfc_idiag_print_rqpair(qp, phba->sli4_hba.dat_rq,
 				"RQpair", pbuffer, len);
@@ -2447,7 +2496,7 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 	struct lpfc_hba *phba = (struct lpfc_hba *)debug->i_private;
 	uint32_t qidx, quetp, queid, index, count, offset, value;
 	uint32_t *pentry;
-	struct lpfc_queue *pque;
+	struct lpfc_queue *pque, *qp;
 	int rc;
 
 	/* This is a user write operation */
@@ -2483,19 +2532,15 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 	case LPFC_IDIAG_EQ:
 		/* HBA event queue */
 		if (phba->sli4_hba.hba_eq) {
-			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
-				qidx++) {
-				if (phba->sli4_hba.hba_eq[qidx] &&
-				    phba->sli4_hba.hba_eq[qidx]->queue_id ==
-				    queid) {
+			for (qidx = 0; qidx < phba->io_channel_irqs; qidx++) {
+				qp = phba->sli4_hba.hba_eq[qidx];
+				if (qp && qp->queue_id == queid) {
 					/* Sanity check */
-					rc = lpfc_idiag_que_param_check(
-						phba->sli4_hba.hba_eq[qidx],
+					rc = lpfc_idiag_que_param_check(qp,
 						index, count);
 					if (rc)
 						goto error_out;
-					idiag.ptr_private =
-						phba->sli4_hba.hba_eq[qidx];
+					idiag.ptr_private = qp;
 					goto pass_check;
 				}
 			}
@@ -2525,24 +2570,32 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 			idiag.ptr_private = phba->sli4_hba.els_cq;
 			goto pass_check;
 		}
+		/* NVME LS complete queue */
+		if (phba->sli4_hba.nvmels_cq &&
+		    phba->sli4_hba.nvmels_cq->queue_id == queid) {
+			/* Sanity check */
+			rc = lpfc_idiag_que_param_check(
+					phba->sli4_hba.nvmels_cq, index, count);
+			if (rc)
+				goto error_out;
+			idiag.ptr_private = phba->sli4_hba.nvmels_cq;
+			goto pass_check;
+		}
 		/* FCP complete queue */
 		if (phba->sli4_hba.fcp_cq) {
-			qidx = 0;
-			do {
-				if (phba->sli4_hba.fcp_cq[qidx] &&
-				    phba->sli4_hba.fcp_cq[qidx]->queue_id ==
-				    queid) {
+			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
+								qidx++) {
+				qp = phba->sli4_hba.fcp_cq[qidx];
+				if (qp && qp->queue_id == queid) {
 					/* Sanity check */
 					rc = lpfc_idiag_que_param_check(
-						phba->sli4_hba.fcp_cq[qidx],
-						index, count);
+						qp, index, count);
 					if (rc)
 						goto error_out;
-					idiag.ptr_private =
-						phba->sli4_hba.fcp_cq[qidx];
+					idiag.ptr_private = qp;
 					goto pass_check;
 				}
-			} while (++qidx < phba->cfg_fcp_io_channel);
+			}
 		}
 		goto error_out;
 		break;
@@ -2572,22 +2625,45 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 			idiag.ptr_private = phba->sli4_hba.els_wq;
 			goto pass_check;
 		}
+		/* NVME LS work queue */
+		if (phba->sli4_hba.nvmels_wq &&
+		    phba->sli4_hba.nvmels_wq->queue_id == queid) {
+			/* Sanity check */
+			rc = lpfc_idiag_que_param_check(
+					phba->sli4_hba.nvmels_wq, index, count);
+			if (rc)
+				goto error_out;
+			idiag.ptr_private = phba->sli4_hba.nvmels_wq;
+			goto pass_check;
+		}
 		/* FCP work queue */
 		if (phba->sli4_hba.fcp_wq) {
 			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
-				qidx++) {
-				if (!phba->sli4_hba.fcp_wq[qidx])
-					continue;
-				if (phba->sli4_hba.fcp_wq[qidx]->queue_id ==
-				    queid) {
+								qidx++) {
+				qp = phba->sli4_hba.fcp_wq[qidx];
+				if (qp && qp->queue_id == queid) {
 					/* Sanity check */
 					rc = lpfc_idiag_que_param_check(
-						phba->sli4_hba.fcp_wq[qidx],
-						index, count);
+						qp, index, count);
+					if (rc)
+						goto error_out;
+					idiag.ptr_private = qp;
+					goto pass_check;
+				}
+			}
+		}
+		/* NVME work queue */
+		if (phba->sli4_hba.nvme_wq) {
+			for (qidx = 0; qidx < phba->cfg_nvme_io_channel;
+								qidx++) {
+				qp = phba->sli4_hba.nvme_wq[qidx];
+				if (qp && qp->queue_id == queid) {
+					/* Sanity check */
+					rc = lpfc_idiag_que_param_check(
+						qp, index, count);
 					if (rc)
 						goto error_out;
-					idiag.ptr_private =
-						phba->sli4_hba.fcp_wq[qidx];
+					idiag.ptr_private = qp;
 					goto pass_check;
 				}
 			}
@@ -4562,10 +4638,14 @@ lpfc_debug_dump_all_queues(struct lpfc_hba *phba)
 	 */
 	lpfc_debug_dump_wq(phba, DUMP_MBX, 0);
 	lpfc_debug_dump_wq(phba, DUMP_ELS, 0);
+	lpfc_debug_dump_wq(phba, DUMP_NVMELS, 0);
 
 	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
 		lpfc_debug_dump_wq(phba, DUMP_FCP, idx);
 
+	for (idx = 0; idx < phba->cfg_nvme_io_channel; idx++)
+		lpfc_debug_dump_wq(phba, DUMP_NVME, idx);
+
 	lpfc_debug_dump_hdr_rq(phba);
 	lpfc_debug_dump_dat_rq(phba);
 	/*
@@ -4573,13 +4653,17 @@ lpfc_debug_dump_all_queues(struct lpfc_hba *phba)
 	 */
 	lpfc_debug_dump_cq(phba, DUMP_MBX, 0);
 	lpfc_debug_dump_cq(phba, DUMP_ELS, 0);
+	lpfc_debug_dump_cq(phba, DUMP_NVMELS, 0);
 
 	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
 		lpfc_debug_dump_cq(phba, DUMP_FCP, idx);
 
+	for (idx = 0; idx < phba->cfg_nvme_io_channel; idx++)
+		lpfc_debug_dump_cq(phba, DUMP_NVME, idx);
+
 	/*
 	 * Dump Event Queues (EQs)
 	 */
-	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
+	for (idx = 0; idx < phba->io_channel_irqs; idx++)
 		lpfc_debug_dump_hba_eq(phba, idx);
 }
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index 9ae2c4b5fd12..98814d651239 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -44,8 +44,10 @@
 
 enum {
 	DUMP_FCP,
+	DUMP_NVME,
 	DUMP_MBX,
 	DUMP_ELS,
+	DUMP_NVMELS,
 };
 
 /*
@@ -364,11 +366,11 @@ lpfc_debug_dump_q(struct lpfc_queue *q)
 }
 
 /**
- * lpfc_debug_dump_wq - dump all entries from the fcp work queue
+ * lpfc_debug_dump_wq - dump all entries from the fcp or nvme work queue
  * @phba: Pointer to HBA context object.
- * @wqidx: Index to a FCP work queue.
+ * @wqidx: Index to a FCP or NVME work queue.
  *
- * This function dumps all entries from a FCP work queue specified
+ * This function dumps all entries from a FCP or NVME work queue specified
  * by the wqidx.
  **/
 static inline void
@@ -380,16 +382,22 @@ lpfc_debug_dump_wq(struct lpfc_hba *phba, int qtype, int wqidx)
 	if (qtype == DUMP_FCP) {
 		wq = phba->sli4_hba.fcp_wq[wqidx];
 		qtypestr = "FCP";
+	} else if (qtype == DUMP_NVME) {
+		wq = phba->sli4_hba.nvme_wq[wqidx];
+		qtypestr = "NVME";
 	} else if (qtype == DUMP_MBX) {
 		wq = phba->sli4_hba.mbx_wq;
 		qtypestr = "MBX";
 	} else if (qtype == DUMP_ELS) {
 		wq = phba->sli4_hba.els_wq;
 		qtypestr = "ELS";
+	} else if (qtype == DUMP_NVMELS) {
+		wq = phba->sli4_hba.nvmels_wq;
+		qtypestr = "NVMELS";
 	} else
 		return;
 
-	if (qtype == DUMP_FCP)
+	if (qtype == DUMP_FCP || qtype == DUMP_NVME)
 		pr_err("%s WQ: WQ[Idx:%d|Qid:%d]\n",
 			qtypestr, wqidx, wq->queue_id);
 	else
@@ -400,12 +408,12 @@ lpfc_debug_dump_wq(struct lpfc_hba *phba, int qtype, int wqidx)
 }
 
 /**
- * lpfc_debug_dump_cq - dump all entries from a fcp work queue's
+ * lpfc_debug_dump_cq - dump all entries from a fcp or nvme work queue's
  * cmpl queue
  * @phba: Pointer to HBA context object.
  * @wqidx: Index to a FCP work queue.
  *
- * This function dumps all entries from a FCP completion queue
+ * This function dumps all entries from a FCP or NVME completion queue
  * which is associated to the work queue specified by the @wqidx.
  **/
 static inline void
@@ -415,12 +423,16 @@ lpfc_debug_dump_cq(struct lpfc_hba *phba, int qtype, int wqidx)
 	char *qtypestr;
 	int eqidx;
 
-	/* fcp wq and cq are 1:1, thus same indexes */
+	/* fcp/nvme wq and cq are 1:1, thus same indexes */
 
 	if (qtype == DUMP_FCP) {
 		wq = phba->sli4_hba.fcp_wq[wqidx];
 		cq = phba->sli4_hba.fcp_cq[wqidx];
 		qtypestr = "FCP";
+	} else if (qtype == DUMP_NVME) {
+		wq = phba->sli4_hba.nvme_wq[wqidx];
+		cq = phba->sli4_hba.nvme_cq[wqidx];
+		qtypestr = "NVME";
 	} else if (qtype == DUMP_MBX) {
 		wq = phba->sli4_hba.mbx_wq;
 		cq = phba->sli4_hba.mbx_cq;
@@ -429,21 +441,25 @@ lpfc_debug_dump_cq(struct lpfc_hba *phba, int qtype, int wqidx)
 		wq = phba->sli4_hba.els_wq;
 		cq = phba->sli4_hba.els_cq;
 		qtypestr = "ELS";
+	} else if (qtype == DUMP_NVMELS) {
+		wq = phba->sli4_hba.nvmels_wq;
+		cq = phba->sli4_hba.nvmels_cq;
+		qtypestr = "NVMELS";
 	} else
 		return;
 
-	for (eqidx = 0; eqidx < phba->cfg_fcp_io_channel; eqidx++) {
+	for (eqidx = 0; eqidx < phba->io_channel_irqs; eqidx++) {
 		eq = phba->sli4_hba.hba_eq[eqidx];
 		if (cq->assoc_qid == eq->queue_id)
 			break;
 	}
-	if (eqidx == phba->cfg_fcp_io_channel) {
+	if (eqidx == phba->io_channel_irqs) {
 		pr_err("Couldn't find EQ for CQ. Using EQ[0]\n");
 		eqidx = 0;
 		eq = phba->sli4_hba.hba_eq[0];
 	}
 
-	if (qtype == DUMP_FCP)
+	if (qtype == DUMP_FCP || qtype == DUMP_NVME)
 		pr_err("%s CQ: WQ[Idx:%d|Qid%d]->CQ[Idx%d|Qid%d]"
 			"->EQ[Idx:%d|Qid:%d]:\n",
 			qtypestr, wqidx, wq->queue_id, wqidx, cq->queue_id,
@@ -527,11 +543,25 @@ lpfc_debug_dump_wq_by_id(struct lpfc_hba *phba, int qid)
 		return;
 	}
 
+	for (wq_idx = 0; wq_idx < phba->cfg_nvme_io_channel; wq_idx++)
+		if (phba->sli4_hba.nvme_wq[wq_idx]->queue_id == qid)
+			break;
+	if (wq_idx < phba->cfg_nvme_io_channel) {
+		pr_err("NVME WQ[Idx:%d|Qid:%d]\n", wq_idx, qid);
+		lpfc_debug_dump_q(phba->sli4_hba.nvme_wq[wq_idx]);
+		return;
+	}
+
 	if (phba->sli4_hba.els_wq->queue_id == qid) {
 		pr_err("ELS WQ[Qid:%d]\n", qid);
 		lpfc_debug_dump_q(phba->sli4_hba.els_wq);
 		return;
 	}
+
+	if (phba->sli4_hba.nvmels_wq->queue_id == qid) {
+		pr_err("NVME LS WQ[Qid:%d]\n", qid);
+		lpfc_debug_dump_q(phba->sli4_hba.nvmels_wq);
+	}
 }
 
 /**
@@ -596,12 +626,28 @@ lpfc_debug_dump_cq_by_id(struct lpfc_hba *phba, int qid)
 		return;
 	}
 
+	for (cq_idx = 0; cq_idx < phba->cfg_nvme_io_channel; cq_idx++)
+		if (phba->sli4_hba.nvme_cq[cq_idx]->queue_id == qid)
+			break;
+
+	if (cq_idx < phba->cfg_nvme_io_channel) {
+		pr_err("NVME CQ[Idx:%d|Qid:%d]\n", cq_idx, qid);
+		lpfc_debug_dump_q(phba->sli4_hba.nvme_cq[cq_idx]);
+		return;
+	}
+
 	if (phba->sli4_hba.els_cq->queue_id == qid) {
 		pr_err("ELS CQ[Qid:%d]\n", qid);
 		lpfc_debug_dump_q(phba->sli4_hba.els_cq);
 		return;
 	}
 
+	if (phba->sli4_hba.nvmels_cq->queue_id == qid) {
+		pr_err("NVME LS CQ[Qid:%d]\n", qid);
+		lpfc_debug_dump_q(phba->sli4_hba.nvmels_cq);
+		return;
+	}
+
 	if (phba->sli4_hba.mbx_cq->queue_id == qid) {
 		pr_err("MBX CQ[Qid:%d]\n", qid);
 		lpfc_debug_dump_q(phba->sli4_hba.mbx_cq);
@@ -621,17 +667,15 @@ lpfc_debug_dump_eq_by_id(struct lpfc_hba *phba, int qid)
 {
 	int eq_idx;
 
-	for (eq_idx = 0; eq_idx < phba->cfg_fcp_io_channel; eq_idx++) {
+	for (eq_idx = 0; eq_idx < phba->io_channel_irqs; eq_idx++)
 		if (phba->sli4_hba.hba_eq[eq_idx]->queue_id == qid)
 			break;
-	}
 
-	if (eq_idx < phba->cfg_fcp_io_channel) {
+	if (eq_idx < phba->io_channel_irqs) {
 		printk(KERN_ERR "FCP EQ[Idx:%d|Qid:%d]\n", eq_idx, qid);
 		lpfc_debug_dump_q(phba->sli4_hba.hba_eq[eq_idx]);
 		return;
 	}
-
 }
 
 void lpfc_debug_dump_all_queues(struct lpfc_hba *);
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 3a1f1a2a2b55..7be235457540 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1323,7 +1323,7 @@ lpfc_els_abort_flogi(struct lpfc_hba *phba)
 			"0201 Abort outstanding I/O on NPort x%x\n",
 			Fabric_DID);
 
-	pring = &phba->sli.ring[LPFC_ELS_RING];
+	pring = lpfc_phba_elsring(phba);
 
 	/*
 	 * Check the txcmplq for an iocb that matches the nport the driver is
@@ -7155,7 +7155,8 @@ lpfc_els_timeout_handler(struct lpfc_vport *vport)
 
 	timeout = (uint32_t)(phba->fc_ratov << 1);
 
-	pring = &phba->sli.ring[LPFC_ELS_RING];
+	pring = lpfc_phba_elsring(phba);
+
 	if ((phba->pport->load_flag & FC_UNLOADING))
 		return;
 	spin_lock_irq(&phba->hbalock);
@@ -7224,7 +7225,7 @@ lpfc_els_timeout_handler(struct lpfc_vport *vport)
 		spin_unlock_irq(&phba->hbalock);
 	}
 
-	if (!list_empty(&phba->sli.ring[LPFC_ELS_RING].txcmplq))
+	if (!list_empty(&pring->txcmplq))
 		if (!(phba->pport->load_flag & FC_UNLOADING))
 			mod_timer(&vport->els_tmofunc,
 				  jiffies + msecs_to_jiffies(1000 * timeout));
@@ -7255,7 +7256,7 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 {
 	LIST_HEAD(abort_list);
 	struct lpfc_hba  *phba = vport->phba;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *tmp_iocb, *piocb;
 	IOCB_t *cmd = NULL;
 
@@ -7267,6 +7268,7 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 	 * a working list and release the locks before calling the abort.
 	 */
 	spin_lock_irq(&phba->hbalock);
+	pring = lpfc_phba_elsring(phba);
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		spin_lock(&pring->ring_lock);
 
@@ -9013,7 +9015,9 @@ void lpfc_fabric_abort_nport(struct lpfc_nodelist *ndlp)
 	LIST_HEAD(completions);
 	struct lpfc_hba  *phba = ndlp->phba;
 	struct lpfc_iocbq *tmp_iocb, *piocb;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
+
+	pring = lpfc_phba_elsring(phba);
 
 	spin_lock_irq(&phba->hbalock);
 	list_for_each_entry_safe(piocb, tmp_iocb, &phba->fabric_iocb_list,
@@ -9069,13 +9073,13 @@ lpfc_sli4_vport_delete_els_xri_aborted(struct lpfc_vport *vport)
 	unsigned long iflag = 0;
 
 	spin_lock_irqsave(&phba->hbalock, iflag);
-	spin_lock(&phba->sli4_hba.abts_sgl_list_lock);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
 	list_for_each_entry_safe(sglq_entry, sglq_next,
 			&phba->sli4_hba.lpfc_abts_els_sgl_list, list) {
 		if (sglq_entry->ndlp && sglq_entry->ndlp->vport == vport)
 			sglq_entry->ndlp = NULL;
 	}
-	spin_unlock(&phba->sli4_hba.abts_sgl_list_lock);
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	spin_unlock_irqrestore(&phba->hbalock, iflag);
 	return;
 }
@@ -9099,22 +9103,22 @@ lpfc_sli4_els_xri_aborted(struct lpfc_hba *phba,
 	struct lpfc_sglq *sglq_entry = NULL, *sglq_next = NULL;
 	unsigned long iflag = 0;
 	struct lpfc_nodelist *ndlp;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
+
+	pring = lpfc_phba_elsring(phba);
 
 	spin_lock_irqsave(&phba->hbalock, iflag);
-	spin_lock(&phba->sli4_hba.abts_sgl_list_lock);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
 	list_for_each_entry_safe(sglq_entry, sglq_next,
 			&phba->sli4_hba.lpfc_abts_els_sgl_list, list) {
 		if (sglq_entry->sli4_xritag == xri) {
 			list_del(&sglq_entry->list);
 			ndlp = sglq_entry->ndlp;
 			sglq_entry->ndlp = NULL;
-			spin_lock(&pring->ring_lock);
 			list_add_tail(&sglq_entry->list,
-				&phba->sli4_hba.lpfc_sgl_list);
+				&phba->sli4_hba.lpfc_els_sgl_list);
 			sglq_entry->state = SGL_FREED;
-			spin_unlock(&pring->ring_lock);
-			spin_unlock(&phba->sli4_hba.abts_sgl_list_lock);
+			spin_unlock(&phba->sli4_hba.sgl_list_lock);
 			spin_unlock_irqrestore(&phba->hbalock, iflag);
 			lpfc_set_rrq_active(phba, ndlp,
 				sglq_entry->sli4_lxritag,
@@ -9126,21 +9130,21 @@ lpfc_sli4_els_xri_aborted(struct lpfc_hba *phba,
 			return;
 		}
 	}
-	spin_unlock(&phba->sli4_hba.abts_sgl_list_lock);
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	lxri = lpfc_sli4_xri_inrange(phba, xri);
 	if (lxri == NO_XRI) {
 		spin_unlock_irqrestore(&phba->hbalock, iflag);
 		return;
 	}
-	spin_lock(&pring->ring_lock);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
 	sglq_entry = __lpfc_get_active_sglq(phba, lxri);
 	if (!sglq_entry || (sglq_entry->sli4_xritag != xri)) {
-		spin_unlock(&pring->ring_lock);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
 		spin_unlock_irqrestore(&phba->hbalock, iflag);
 		return;
 	}
 	sglq_entry->state = SGL_XRI_ABORTED;
-	spin_unlock(&pring->ring_lock);
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	spin_unlock_irqrestore(&phba->hbalock, iflag);
 	return;
 }
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 92627df35a58..ede831d1f467 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -93,7 +93,7 @@ lpfc_terminate_rport_io(struct fc_rport *rport)
 
 	if (ndlp->nlp_sid != NLP_NO_SID) {
 		lpfc_sli_abort_iocb(ndlp->vport,
-			&phba->sli.ring[phba->sli.fcp_ring],
+			&phba->sli.sli3_ring[LPFC_FCP_RING],
 			ndlp->nlp_sid, 0, LPFC_CTX_TGT);
 	}
 }
@@ -247,8 +247,8 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 		if (ndlp->nlp_sid != NLP_NO_SID) {
 			/* flush the target */
 			lpfc_sli_abort_iocb(vport,
-					&phba->sli.ring[phba->sli.fcp_ring],
-					ndlp->nlp_sid, 0, LPFC_CTX_TGT);
+					    &phba->sli.sli3_ring[LPFC_FCP_RING],
+					    ndlp->nlp_sid, 0, LPFC_CTX_TGT);
 		}
 		put_node = rdata->pnode != NULL;
 		rdata->pnode = NULL;
@@ -283,7 +283,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 
 	if (ndlp->nlp_sid != NLP_NO_SID) {
 		warn_on = 1;
-		lpfc_sli_abort_iocb(vport, &phba->sli.ring[phba->sli.fcp_ring],
+		lpfc_sli_abort_iocb(vport, &phba->sli.sli3_ring[LPFC_FCP_RING],
 				    ndlp->nlp_sid, 0, LPFC_CTX_TGT);
 	}
 
@@ -495,11 +495,12 @@ lpfc_send_fastpath_evt(struct lpfc_hba *phba,
 		return;
 	}
 
-	fc_host_post_vendor_event(shost,
-		fc_get_event_number(),
-		evt_data_size,
-		evt_data,
-		LPFC_NL_VENDOR_ID);
+	if (phba->cfg_enable_fc4_type != LPFC_ENABLE_NVME)
+		fc_host_post_vendor_event(shost,
+			fc_get_event_number(),
+			evt_data_size,
+			evt_data,
+			LPFC_NL_VENDOR_ID);
 
 	lpfc_free_fast_evt(phba, fast_evt_data);
 	return;
@@ -682,7 +683,7 @@ lpfc_work_done(struct lpfc_hba *phba)
 		}
 	lpfc_destroy_vport_work_array(phba, vports);
 
-	pring = &phba->sli.ring[LPFC_ELS_RING];
+	pring = lpfc_phba_elsring(phba);
 	status = (ha_copy & (HA_RXMASK  << (4*LPFC_ELS_RING)));
 	status >>= (4*LPFC_ELS_RING);
 	if ((status & HA_RXMASK) ||
@@ -894,11 +895,16 @@ lpfc_linkdown(struct lpfc_hba *phba)
 		spin_unlock_irq(shost->host_lock);
 	}
 	vports = lpfc_create_vport_work_array(phba);
-	if (vports != NULL)
+	if (vports != NULL) {
 		for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 			/* Issue a LINK DOWN event to all nodes */
 			lpfc_linkdown_port(vports[i]);
+
+			vports[i]->fc_myDID = 0;
+
+			/* todo: init: revise localport nvme attributes */
 		}
+	}
 	lpfc_destroy_vport_work_array(phba, vports);
 	/* Clean up any firmware default rpi's */
 	mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
@@ -914,7 +920,6 @@ lpfc_linkdown(struct lpfc_hba *phba)
 
 	/* Setup myDID for link up if we are in pt2pt mode */
 	if (phba->pport->fc_flag & FC_PT2PT) {
-		phba->pport->fc_myDID = 0;
 		mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (mb) {
 			lpfc_config_link(phba, mb);
@@ -929,7 +934,6 @@ lpfc_linkdown(struct lpfc_hba *phba)
 		phba->pport->fc_flag &= ~(FC_PT2PT | FC_PT2PT_PLOGI);
 		spin_unlock_irq(shost->host_lock);
 	}
-
 	return 0;
 }
 
@@ -1016,7 +1020,7 @@ lpfc_linkup(struct lpfc_hba *phba)
  * This routine handles processing a CLEAR_LA mailbox
  * command upon completion. It is setup in the LPFC_MBOXQ
  * as the completion routine when the command is
- * handed off to the SLI layer.
+ * handed off to the SLI layer. SLI3 only.
  */
 static void
 lpfc_mbx_cmpl_clear_la(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
@@ -1028,9 +1032,8 @@ lpfc_mbx_cmpl_clear_la(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	uint32_t control;
 
 	/* Since we don't do discovery right now, turn these off here */
-	psli->ring[psli->extra_ring].flag &= ~LPFC_STOP_IOCB_EVENT;
-	psli->ring[psli->fcp_ring].flag &= ~LPFC_STOP_IOCB_EVENT;
-	psli->ring[psli->next_ring].flag &= ~LPFC_STOP_IOCB_EVENT;
+	psli->sli3_ring[LPFC_EXTRA_RING].flag &= ~LPFC_STOP_IOCB_EVENT;
+	psli->sli3_ring[LPFC_FCP_RING].flag &= ~LPFC_STOP_IOCB_EVENT;
 
 	/* Check for error */
 	if ((mb->mbxStatus) && (mb->mbxStatus != 0x1601)) {
@@ -3277,7 +3280,7 @@ lpfc_mbx_issue_link_down(struct lpfc_hba *phba)
  * This routine handles processing a READ_TOPOLOGY mailbox
  * command upon completion. It is setup in the LPFC_MBOXQ
  * as the completion routine when the command is
- * handed off to the SLI layer.
+ * handed off to the SLI layer. SLI4 only.
  */
 void
 lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
@@ -3285,11 +3288,14 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	struct lpfc_vport *vport = pmb->vport;
 	struct Scsi_Host  *shost = lpfc_shost_from_vport(vport);
 	struct lpfc_mbx_read_top *la;
+	struct lpfc_sli_ring *pring;
 	MAILBOX_t *mb = &pmb->u.mb;
 	struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *) (pmb->context1);
 
 	/* Unblock ELS traffic */
-	phba->sli.ring[LPFC_ELS_RING].flag &= ~LPFC_STOP_IOCB_EVENT;
+	pring = lpfc_phba_elsring(phba);
+	pring->flag &= ~LPFC_STOP_IOCB_EVENT;
+
 	/* Check for error */
 	if (mb->mbxStatus) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_LINK_EVENT,
@@ -3458,6 +3464,14 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
 		spin_unlock_irq(shost->host_lock);
+
+		/*
+		 * We cannot leave the RPI registered because
+		 * if we go thru discovery again for this ndlp
+		 * a subsequent REG_RPI will fail.
+		 */
+		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+		lpfc_unreg_rpi(vport, ndlp);
 	}
 
 	/* Call state machine */
@@ -3903,6 +3917,9 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	struct fc_rport_identifiers rport_ids;
 	struct lpfc_hba  *phba = vport->phba;
 
+	if (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)
+		return;
+
 	/* Remote port has reappeared. Re-register w/ FC transport */
 	rport_ids.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn);
 	rport_ids.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn);
@@ -4395,7 +4412,6 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 		    struct lpfc_iocbq *iocb,
 		    struct lpfc_nodelist *ndlp)
 {
-	struct lpfc_sli *psli = &phba->sli;
 	IOCB_t *icmd = &iocb->iocb;
 	struct lpfc_vport    *vport = ndlp->vport;
 
@@ -4414,9 +4430,7 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 			if (iocb->context1 == (uint8_t *) ndlp)
 				return 1;
 		}
-	} else if (pring->ringno == psli->extra_ring) {
-
-	} else if (pring->ringno == psli->fcp_ring) {
+	} else if (pring->ringno == LPFC_FCP_RING) {
 		/* Skip match check if waiting to relogin to FCP target */
 		if ((ndlp->nlp_type & NLP_FCP_TARGET) &&
 		    (ndlp->nlp_flag & NLP_DELAY_TMO)) {
@@ -4429,6 +4443,54 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 	return 0;
 }
 
+static void
+__lpfc_dequeue_nport_iocbs(struct lpfc_hba *phba,
+		struct lpfc_nodelist *ndlp, struct lpfc_sli_ring *pring,
+		struct list_head *dequeue_list)
+{
+	struct lpfc_iocbq *iocb, *next_iocb;
+
+	list_for_each_entry_safe(iocb, next_iocb, &pring->txq, list) {
+		/* Check to see if iocb matches the nport */
+		if (lpfc_check_sli_ndlp(phba, pring, iocb, ndlp))
+			/* match, dequeue */
+			list_move_tail(&iocb->list, dequeue_list);
+	}
+}
+
+static void
+lpfc_sli3_dequeue_nport_iocbs(struct lpfc_hba *phba,
+		struct lpfc_nodelist *ndlp, struct list_head *dequeue_list)
+{
+	struct lpfc_sli *psli = &phba->sli;
+	uint32_t i;
+
+	spin_lock_irq(&phba->hbalock);
+	for (i = 0; i < psli->num_rings; i++)
+		__lpfc_dequeue_nport_iocbs(phba, ndlp, &psli->sli3_ring[i],
+						dequeue_list);
+	spin_unlock_irq(&phba->hbalock);
+}
+
+static void
+lpfc_sli4_dequeue_nport_iocbs(struct lpfc_hba *phba,
+		struct lpfc_nodelist *ndlp, struct list_head *dequeue_list)
+{
+	struct lpfc_sli_ring *pring;
+	struct lpfc_queue *qp = NULL;
+
+	spin_lock_irq(&phba->hbalock);
+	list_for_each_entry(qp, &phba->sli4_hba.lpfc_wq_list, wq_list) {
+		pring = qp->pring;
+		if (!pring)
+			continue;
+		spin_lock_irq(&pring->ring_lock);
+		__lpfc_dequeue_nport_iocbs(phba, ndlp, pring, dequeue_list);
+		spin_unlock_irq(&pring->ring_lock);
+	}
+	spin_unlock_irq(&phba->hbalock);
+}
+
 /*
  * Free resources / clean up outstanding I/Os
  * associated with nlp_rpi in the LPFC_NODELIST entry.
@@ -4437,10 +4499,6 @@ static int
 lpfc_no_rpi(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 {
 	LIST_HEAD(completions);
-	struct lpfc_sli *psli;
-	struct lpfc_sli_ring *pring;
-	struct lpfc_iocbq *iocb, *next_iocb;
-	uint32_t i;
 
 	lpfc_fabric_abort_nport(ndlp);
 
@@ -4448,29 +4506,11 @@ lpfc_no_rpi(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	 * Everything that matches on txcmplq will be returned
 	 * by firmware with a no rpi error.
 	 */
-	psli = &phba->sli;
 	if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
-		/* Now process each ring */
-		for (i = 0; i < psli->num_rings; i++) {
-			pring = &psli->ring[i];
-
-			spin_lock_irq(&phba->hbalock);
-			list_for_each_entry_safe(iocb, next_iocb, &pring->txq,
-						 list) {
-				/*
-				 * Check to see if iocb matches the nport we are
-				 * looking for
-				 */
-				if ((lpfc_check_sli_ndlp(phba, pring, iocb,
-							 ndlp))) {
-					/* It matches, so deque and call compl
-					   with an error */
-					list_move_tail(&iocb->list,
-						       &completions);
-				}
-			}
-			spin_unlock_irq(&phba->hbalock);
-		}
+		if (phba->sli_rev != LPFC_SLI_REV4)
+			lpfc_sli3_dequeue_nport_iocbs(phba, ndlp, &completions);
+		else
+			lpfc_sli4_dequeue_nport_iocbs(phba, ndlp, &completions);
 	}
 
 	/* Cancel all the IOCBs from the completions list */
@@ -5039,14 +5079,14 @@ lpfc_disc_list_loopmap(struct lpfc_vport *vport)
 	return;
 }
 
+/* SLI3 only */
 void
 lpfc_issue_clear_la(struct lpfc_hba *phba, struct lpfc_vport *vport)
 {
 	LPFC_MBOXQ_t *mbox;
 	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *extra_ring = &psli->ring[psli->extra_ring];
-	struct lpfc_sli_ring *fcp_ring   = &psli->ring[psli->fcp_ring];
-	struct lpfc_sli_ring *next_ring  = &psli->ring[psli->next_ring];
+	struct lpfc_sli_ring *extra_ring = &psli->sli3_ring[LPFC_EXTRA_RING];
+	struct lpfc_sli_ring *fcp_ring   = &psli->sli3_ring[LPFC_FCP_RING];
 	int  rc;
 
 	/*
@@ -5070,7 +5110,6 @@ lpfc_issue_clear_la(struct lpfc_hba *phba, struct lpfc_vport *vport)
 			lpfc_disc_flush_list(vport);
 			extra_ring->flag &= ~LPFC_STOP_IOCB_EVENT;
 			fcp_ring->flag &= ~LPFC_STOP_IOCB_EVENT;
-			next_ring->flag &= ~LPFC_STOP_IOCB_EVENT;
 			phba->link_state = LPFC_HBA_ERROR;
 		}
 	}
@@ -5206,7 +5245,7 @@ lpfc_free_tx(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	struct lpfc_sli_ring *pring;
 
 	psli = &phba->sli;
-	pring = &psli->ring[LPFC_ELS_RING];
+	pring = lpfc_phba_elsring(phba);
 
 	/* Error matching iocb on txq or txcmplq
 	 * First check the txq.
@@ -5522,12 +5561,14 @@ lpfc_disc_timeout_handler(struct lpfc_vport *vport)
 
 	if (clrlaerr) {
 		lpfc_disc_flush_list(vport);
-		psli->ring[(psli->extra_ring)].flag &= ~LPFC_STOP_IOCB_EVENT;
-		psli->ring[(psli->fcp_ring)].flag &= ~LPFC_STOP_IOCB_EVENT;
-		psli->ring[(psli->next_ring)].flag &= ~LPFC_STOP_IOCB_EVENT;
+		if (phba->sli_rev != LPFC_SLI_REV4) {
+			psli->sli3_ring[(LPFC_EXTRA_RING)].flag &=
+				~LPFC_STOP_IOCB_EVENT;
+			psli->sli3_ring[LPFC_FCP_RING].flag &=
+				~LPFC_STOP_IOCB_EVENT;
+		}
 		vport->port_state = LPFC_VPORT_READY;
 	}
-
 	return;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 3b970d370600..28247c99b4f2 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -44,8 +44,6 @@
 #define LPFC_FCP_RING            0	/* ring 0 for FCP initiator commands */
 #define LPFC_EXTRA_RING          1	/* ring 1 for other protocols */
 #define LPFC_ELS_RING            2	/* ring 2 for ELS commands */
-#define LPFC_FCP_NEXT_RING       3
-#define LPFC_FCP_OAS_RING        3
 
 #define SLI2_IOCB_CMD_R0_ENTRIES    172	/* SLI-2 FCP command ring entries */
 #define SLI2_IOCB_RSP_R0_ENTRIES    134	/* SLI-2 FCP response ring entries */
@@ -1791,6 +1789,7 @@ typedef struct {		/* FireFly BIU registers */
 #define MBX_INIT_VFI        0xA3
 #define MBX_INIT_VPI        0xA4
 #define MBX_ACCESS_VDATA    0xA5
+#define MBX_REG_FCFI_MRQ    0xAF
 
 #define MBX_AUTH_PORT       0xF8
 #define MBX_SECURITY_MGMT   0xF9
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 964a1fdb076b..c3277c5312c9 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -108,6 +108,7 @@ struct lpfc_sli_intf {
 #define LPFC_MAX_MQ_PAGE		8
 #define LPFC_MAX_WQ_PAGE_V0		4
 #define LPFC_MAX_WQ_PAGE		8
+#define LPFC_MAX_RQ_PAGE		8
 #define LPFC_MAX_CQ_PAGE		4
 #define LPFC_MAX_EQ_PAGE		8
 
@@ -198,7 +199,7 @@ struct lpfc_sli_intf {
 /* Configuration of Interrupts / sec for entire HBA port */
 #define LPFC_MIN_IMAX          5000
 #define LPFC_MAX_IMAX          5000000
-#define LPFC_DEF_IMAX          50000
+#define LPFC_DEF_IMAX          150000
 
 #define LPFC_MIN_CPU_MAP       0
 #define LPFC_MAX_CPU_MAP       2
@@ -348,6 +349,7 @@ struct lpfc_cqe {
 #define CQE_CODE_RECEIVE		0x4
 #define CQE_CODE_XRI_ABORTED		0x5
 #define CQE_CODE_RECEIVE_V1		0x9
+#define CQE_CODE_NVME_ERSP		0xd
 
 /*
  * Define mask value for xri_aborted and wcqe completed CQE extended status.
@@ -367,6 +369,9 @@ struct lpfc_wcqe_complete {
 #define lpfc_wcqe_c_hw_status_SHIFT	0
 #define lpfc_wcqe_c_hw_status_MASK	0x000000FF
 #define lpfc_wcqe_c_hw_status_WORD	word0
+#define lpfc_wcqe_c_ersp0_SHIFT		0
+#define lpfc_wcqe_c_ersp0_MASK		0x0000FFFF
+#define lpfc_wcqe_c_ersp0_WORD		word0
 	uint32_t total_data_placed;
 	uint32_t parameter;
 #define lpfc_wcqe_c_bg_edir_SHIFT	5
@@ -400,6 +405,9 @@ struct lpfc_wcqe_complete {
 #define lpfc_wcqe_c_code_SHIFT		lpfc_cqe_code_SHIFT
 #define lpfc_wcqe_c_code_MASK		lpfc_cqe_code_MASK
 #define lpfc_wcqe_c_code_WORD		lpfc_cqe_code_WORD
+#define lpfc_wcqe_c_sqhead_SHIFT	0
+#define lpfc_wcqe_c_sqhead_MASK		0x0000FFFF
+#define lpfc_wcqe_c_sqhead_WORD		word3
 };
 
 /* completion queue entry for wqe release */
@@ -2841,12 +2849,18 @@ struct lpfc_sli4_parameters {
 #define cfg_mqv_WORD				word6
 	uint32_t word7;
 	uint32_t word8;
+#define cfg_wqpcnt_SHIFT			0
+#define cfg_wqpcnt_MASK				0x0000000f
+#define cfg_wqpcnt_WORD				word8
 #define cfg_wqsize_SHIFT			8
 #define cfg_wqsize_MASK				0x0000000f
 #define cfg_wqsize_WORD				word8
 #define cfg_wqv_SHIFT				14
 #define cfg_wqv_MASK				0x00000003
 #define cfg_wqv_WORD				word8
+#define cfg_wqpsize_SHIFT			16
+#define cfg_wqpsize_MASK			0x000000ff
+#define cfg_wqpsize_WORD			word8
 	uint32_t word9;
 	uint32_t word10;
 #define cfg_rqv_SHIFT				14
@@ -2897,6 +2911,12 @@ struct lpfc_sli4_parameters {
 #define cfg_mds_diags_SHIFT			1
 #define cfg_mds_diags_MASK			0x00000001
 #define cfg_mds_diags_WORD			word19
+#define cfg_nvme_SHIFT				3
+#define cfg_nvme_MASK				0x00000001
+#define cfg_nvme_WORD				word19
+#define cfg_xib_SHIFT				4
+#define cfg_xib_MASK				0x00000001
+#define cfg_xib_WORD				word19
 };
 
 #define LPFC_SET_UE_RECOVERY		0x10
@@ -3659,6 +3679,9 @@ struct wqe_common {
 #define wqe_ebde_cnt_SHIFT    0
 #define wqe_ebde_cnt_MASK     0x0000000f
 #define wqe_ebde_cnt_WORD     word10
+#define wqe_nvme_SHIFT        4
+#define wqe_nvme_MASK         0x00000001
+#define wqe_nvme_WORD         word10
 #define wqe_oas_SHIFT         6
 #define wqe_oas_MASK          0x00000001
 #define wqe_oas_WORD          word10
@@ -4017,11 +4040,39 @@ struct lpfc_grp_hdr {
 	uint8_t revision[32];
 };
 
-#define FCP_COMMAND 0x0
-#define FCP_COMMAND_DATA_OUT 0x1
-#define ELS_COMMAND_NON_FIP 0xC
-#define ELS_COMMAND_FIP 0xD
-#define OTHER_COMMAND 0x8
+/* Defines for WQE command type */
+#define FCP_COMMAND		0x0
+#define NVME_READ_CMD		0x0
+#define FCP_COMMAND_DATA_OUT	0x1
+#define NVME_WRITE_CMD		0x1
+#define FCP_COMMAND_TRECEIVE	0x2
+#define FCP_COMMAND_TRSP	0x3
+#define FCP_COMMAND_TSEND	0x7
+#define OTHER_COMMAND		0x8
+#define ELS_COMMAND_NON_FIP	0xC
+#define ELS_COMMAND_FIP		0xD
+
+#define LPFC_NVME_EMBED_CMD	0x0
+#define LPFC_NVME_EMBED_WRITE	0x1
+#define LPFC_NVME_EMBED_READ	0x2
+
+/* WQE Commands */
+#define CMD_ABORT_XRI_WQE       0x0F
+#define CMD_XMIT_SEQUENCE64_WQE 0x82
+#define CMD_XMIT_BCAST64_WQE    0x84
+#define CMD_ELS_REQUEST64_WQE   0x8A
+#define CMD_XMIT_ELS_RSP64_WQE  0x95
+#define CMD_XMIT_BLS_RSP64_WQE  0x97
+#define CMD_FCP_IWRITE64_WQE    0x98
+#define CMD_FCP_IREAD64_WQE     0x9A
+#define CMD_FCP_ICMND64_WQE     0x9C
+#define CMD_FCP_TSEND64_WQE     0x9F
+#define CMD_FCP_TRECEIVE64_WQE  0xA1
+#define CMD_FCP_TRSP64_WQE      0xA3
+#define CMD_GEN_REQUEST64_WQE   0xC2
+
+#define CMD_WQE_MASK            0xff
+
 
 #define LPFC_FW_DUMP	1
 #define LPFC_FW_RESET	2
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index ec23388ac4f5..57087ba4834f 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -34,6 +34,7 @@
 #include <linux/firmware.h>
 #include <linux/miscdevice.h>
 #include <linux/percpu.h>
+#include <linux/msi.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -46,8 +47,9 @@
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
@@ -499,12 +501,10 @@ lpfc_config_port_post(struct lpfc_hba *phba)
 	phba->link_state = LPFC_LINK_DOWN;
 
 	/* Only process IOCBs on ELS ring till hba_state is READY */
-	if (psli->ring[psli->extra_ring].sli.sli3.cmdringaddr)
-		psli->ring[psli->extra_ring].flag |= LPFC_STOP_IOCB_EVENT;
-	if (psli->ring[psli->fcp_ring].sli.sli3.cmdringaddr)
-		psli->ring[psli->fcp_ring].flag |= LPFC_STOP_IOCB_EVENT;
-	if (psli->ring[psli->next_ring].sli.sli3.cmdringaddr)
-		psli->ring[psli->next_ring].flag |= LPFC_STOP_IOCB_EVENT;
+	if (psli->sli3_ring[LPFC_EXTRA_RING].sli.sli3.cmdringaddr)
+		psli->sli3_ring[LPFC_EXTRA_RING].flag |= LPFC_STOP_IOCB_EVENT;
+	if (psli->sli3_ring[LPFC_FCP_RING].sli.sli3.cmdringaddr)
+		psli->sli3_ring[LPFC_FCP_RING].flag |= LPFC_STOP_IOCB_EVENT;
 
 	/* Post receive buffers for desired rings */
 	if (phba->sli_rev != 3)
@@ -892,7 +892,7 @@ lpfc_hba_free_post_buf(struct lpfc_hba *phba)
 		lpfc_sli_hbqbuf_free_all(phba);
 	else {
 		/* Cleanup preposted buffers on the ELS ring */
-		pring = &psli->ring[LPFC_ELS_RING];
+		pring = &psli->sli3_ring[LPFC_ELS_RING];
 		spin_lock_irq(&phba->hbalock);
 		list_splice_init(&pring->postbufq, &buflist);
 		spin_unlock_irq(&phba->hbalock);
@@ -925,32 +925,43 @@ static void
 lpfc_hba_clean_txcmplq(struct lpfc_hba *phba)
 {
 	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_queue *qp = NULL;
 	struct lpfc_sli_ring *pring;
 	LIST_HEAD(completions);
 	int i;
 
-	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
-		if (phba->sli_rev >= LPFC_SLI_REV4)
-			spin_lock_irq(&pring->ring_lock);
-		else
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		for (i = 0; i < psli->num_rings; i++) {
+			pring = &psli->sli3_ring[i];
 			spin_lock_irq(&phba->hbalock);
-		/* At this point in time the HBA is either reset or DOA. Either
-		 * way, nothing should be on txcmplq as it will NEVER complete.
-		 */
-		list_splice_init(&pring->txcmplq, &completions);
-		pring->txcmplq_cnt = 0;
-
-		if (phba->sli_rev >= LPFC_SLI_REV4)
-			spin_unlock_irq(&pring->ring_lock);
-		else
+			/* At this point in time the HBA is either reset or DOA
+			 * Nothing should be on txcmplq as it will
+			 * NEVER complete.
+			 */
+			list_splice_init(&pring->txcmplq, &completions);
+			pring->txcmplq_cnt = 0;
 			spin_unlock_irq(&phba->hbalock);
 
+			lpfc_sli_abort_iocb_ring(phba, pring);
+		}
 		/* Cancel all the IOCBs from the completions list */
-		lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
-				      IOERR_SLI_ABORTED);
+		lpfc_sli_cancel_iocbs(phba, &completions,
+				      IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED);
+		return;
+	}
+	list_for_each_entry(qp, &phba->sli4_hba.lpfc_wq_list, wq_list) {
+		pring = qp->pring;
+		if (!pring)
+			continue;
+		spin_lock_irq(&pring->ring_lock);
+		list_splice_init(&pring->txcmplq, &completions);
+		pring->txcmplq_cnt = 0;
+		spin_unlock_irq(&pring->ring_lock);
 		lpfc_sli_abort_iocb_ring(phba, pring);
 	}
+	/* Cancel all the IOCBs from the completions list */
+	lpfc_sli_cancel_iocbs(phba, &completions,
+			      IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED);
 }
 
 /**
@@ -989,43 +1000,51 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 {
 	struct lpfc_scsi_buf *psb, *psb_next;
 	LIST_HEAD(aborts);
+	LIST_HEAD(nvme_aborts);
 	unsigned long iflag = 0;
 	struct lpfc_sglq *sglq_entry = NULL;
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *pring;
 
-	lpfc_hba_free_post_buf(phba);
+
+	lpfc_sli_hbqbuf_free_all(phba);
 	lpfc_hba_clean_txcmplq(phba);
-	pring = &psli->ring[LPFC_ELS_RING];
 
 	/* At this point in time the HBA is either reset or DOA. Either
 	 * way, nothing should be on lpfc_abts_els_sgl_list, it needs to be
-	 * on the lpfc_sgl_list so that it can either be freed if the
+	 * on the lpfc_els_sgl_list so that it can either be freed if the
 	 * driver is unloading or reposted if the driver is restarting
 	 * the port.
 	 */
-	spin_lock_irq(&phba->hbalock);  /* required for lpfc_sgl_list and */
+	spin_lock_irq(&phba->hbalock);  /* required for lpfc_els_sgl_list and */
 					/* scsl_buf_list */
-	/* abts_sgl_list_lock required because worker thread uses this
+	/* sgl_list_lock required because worker thread uses this
 	 * list.
 	 */
-	spin_lock(&phba->sli4_hba.abts_sgl_list_lock);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
 	list_for_each_entry(sglq_entry,
 		&phba->sli4_hba.lpfc_abts_els_sgl_list, list)
 		sglq_entry->state = SGL_FREED;
 
-	spin_lock(&pring->ring_lock);
 	list_splice_init(&phba->sli4_hba.lpfc_abts_els_sgl_list,
-			&phba->sli4_hba.lpfc_sgl_list);
-	spin_unlock(&pring->ring_lock);
-	spin_unlock(&phba->sli4_hba.abts_sgl_list_lock);
+			&phba->sli4_hba.lpfc_els_sgl_list);
+
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	/* abts_scsi_buf_list_lock required because worker thread uses this
 	 * list.
 	 */
-	spin_lock(&phba->sli4_hba.abts_scsi_buf_list_lock);
-	list_splice_init(&phba->sli4_hba.lpfc_abts_scsi_buf_list,
-			&aborts);
-	spin_unlock(&phba->sli4_hba.abts_scsi_buf_list_lock);
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
+		spin_lock(&phba->sli4_hba.abts_scsi_buf_list_lock);
+		list_splice_init(&phba->sli4_hba.lpfc_abts_scsi_buf_list,
+				 &aborts);
+		spin_unlock(&phba->sli4_hba.abts_scsi_buf_list_lock);
+	}
+
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+		spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		list_splice_init(&phba->sli4_hba.lpfc_abts_nvme_buf_list,
+				 &nvme_aborts);
+		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+	}
+
 	spin_unlock_irq(&phba->hbalock);
 
 	list_for_each_entry_safe(psb, psb_next, &aborts, list) {
@@ -1036,6 +1055,14 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 	list_splice(&aborts, &phba->lpfc_scsi_buf_list_put);
 	spin_unlock_irqrestore(&phba->scsi_buf_list_put_lock, iflag);
 
+	list_for_each_entry_safe(psb, psb_next, &nvme_aborts, list) {
+		psb->pCmd = NULL;
+		psb->status = IOSTAT_SUCCESS;
+	}
+	spin_lock_irqsave(&phba->nvme_buf_list_put_lock, iflag);
+	list_splice(&nvme_aborts, &phba->lpfc_nvme_buf_list_put);
+	spin_unlock_irqrestore(&phba->nvme_buf_list_put_lock, iflag);
+
 	lpfc_sli4_free_sp_events(phba);
 	return 0;
 }
@@ -1829,7 +1856,7 @@ lpfc_handle_eratt(struct lpfc_hba *phba)
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine is invoked from the worker thread to handle a HBA host
- * attention link event.
+ * attention link event. SLI3 only.
  **/
 void
 lpfc_handle_latt(struct lpfc_hba *phba)
@@ -1867,7 +1894,7 @@ lpfc_handle_latt(struct lpfc_hba *phba)
 	pmb->mbox_cmpl = lpfc_mbx_cmpl_read_topology;
 	pmb->vport = vport;
 	/* Block ELS IOCBs until we have processed this mbox command */
-	phba->sli.ring[LPFC_ELS_RING].flag |= LPFC_STOP_IOCB_EVENT;
+	phba->sli.sli3_ring[LPFC_ELS_RING].flag |= LPFC_STOP_IOCB_EVENT;
 	rc = lpfc_sli_issue_mbox (phba, pmb, MBX_NOWAIT);
 	if (rc == MBX_NOT_FINISHED) {
 		rc = 4;
@@ -1883,7 +1910,7 @@ lpfc_handle_latt(struct lpfc_hba *phba)
 	return;
 
 lpfc_handle_latt_free_mbuf:
-	phba->sli.ring[LPFC_ELS_RING].flag &= ~LPFC_STOP_IOCB_EVENT;
+	phba->sli.sli3_ring[LPFC_ELS_RING].flag &= ~LPFC_STOP_IOCB_EVENT;
 	lpfc_mbuf_free(phba, mp->virt, mp->phys);
 lpfc_handle_latt_free_mp:
 	kfree(mp);
@@ -2441,7 +2468,7 @@ lpfc_post_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, int cnt)
  *
  * This routine posts initial receive IOCB buffers to the ELS ring. The
  * current number of initial IOCB buffers specified by LPFC_BUF_RING0 is
- * set to 64 IOCBs.
+ * set to 64 IOCBs. SLI3 only.
  *
  * Return codes
  *   0 - success (currently always success)
@@ -2452,7 +2479,7 @@ lpfc_post_rcv_buf(struct lpfc_hba *phba)
 	struct lpfc_sli *psli = &phba->sli;
 
 	/* Ring 0, ELS / CT buffers */
-	lpfc_post_buffer(phba, &psli->ring[LPFC_ELS_RING], LPFC_BUF_RING0);
+	lpfc_post_buffer(phba, &psli->sli3_ring[LPFC_ELS_RING], LPFC_BUF_RING0);
 	/* Ring 2 - FCP no buffers needed */
 
 	return 0;
@@ -2894,11 +2921,6 @@ lpfc_online(struct lpfc_hba *phba)
 
 	lpfc_block_mgmt_io(phba, LPFC_MBX_WAIT);
 
-	if (!lpfc_sli_queue_setup(phba)) {
-		lpfc_unblock_mgmt_io(phba);
-		return 1;
-	}
-
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		if (lpfc_sli4_hba_setup(phba)) { /* Initialize SLI4 HBA */
 			lpfc_unblock_mgmt_io(phba);
@@ -2909,6 +2931,7 @@ lpfc_online(struct lpfc_hba *phba)
 			vpis_cleared = true;
 		spin_unlock_irq(&phba->hbalock);
 	} else {
+		lpfc_sli_queue_init(phba);
 		if (lpfc_sli_hba_setup(phba)) {	/* Initialize SLI2/SLI3 HBA */
 			lpfc_unblock_mgmt_io(phba);
 			return 1;
@@ -3100,6 +3123,9 @@ lpfc_scsi_free(struct lpfc_hba *phba)
 	struct lpfc_scsi_buf *sb, *sb_next;
 	struct lpfc_iocbq *io, *io_next;
 
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
+		return;
+
 	spin_lock_irq(&phba->hbalock);
 
 	/* Release all the lpfc_scsi_bufs maintained by this host. */
@@ -3108,7 +3134,7 @@ lpfc_scsi_free(struct lpfc_hba *phba)
 	list_for_each_entry_safe(sb, sb_next, &phba->lpfc_scsi_buf_list_put,
 				 list) {
 		list_del(&sb->list);
-		pci_pool_free(phba->lpfc_scsi_dma_buf_pool, sb->data,
+		pci_pool_free(phba->lpfc_sg_dma_buf_pool, sb->data,
 			      sb->dma_handle);
 		kfree(sb);
 		phba->total_scsi_bufs--;
@@ -3119,7 +3145,7 @@ lpfc_scsi_free(struct lpfc_hba *phba)
 	list_for_each_entry_safe(sb, sb_next, &phba->lpfc_scsi_buf_list_get,
 				 list) {
 		list_del(&sb->list);
-		pci_pool_free(phba->lpfc_scsi_dma_buf_pool, sb->data,
+		pci_pool_free(phba->lpfc_sg_dma_buf_pool, sb->data,
 			      sb->dma_handle);
 		kfree(sb);
 		phba->total_scsi_bufs--;
@@ -3135,9 +3161,59 @@ lpfc_scsi_free(struct lpfc_hba *phba)
 
 	spin_unlock_irq(&phba->hbalock);
 }
+/**
+ * lpfc_nvme_free - Free all the NVME buffers and IOCBs from driver lists
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is to free all the NVME buffers and IOCBs from the driver
+ * list back to kernel. It is called from lpfc_pci_remove_one to free
+ * the internal resources before the device is removed from the system.
+ **/
+static void
+lpfc_nvme_free(struct lpfc_hba *phba)
+{
+	struct lpfc_nvme_buf *lpfc_ncmd, *lpfc_ncmd_next;
+	struct lpfc_iocbq *io, *io_next;
+
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+		return;
+
+	spin_lock_irq(&phba->hbalock);
+
+	/* Release all the lpfc_nvme_bufs maintained by this host. */
+	spin_lock(&phba->nvme_buf_list_put_lock);
+	list_for_each_entry_safe(lpfc_ncmd, lpfc_ncmd_next,
+				 &phba->lpfc_nvme_buf_list_put, list) {
+		list_del(&lpfc_ncmd->list);
+		pci_pool_free(phba->lpfc_sg_dma_buf_pool, lpfc_ncmd->data,
+			      lpfc_ncmd->dma_handle);
+		kfree(lpfc_ncmd);
+		phba->total_nvme_bufs--;
+	}
+	spin_unlock(&phba->nvme_buf_list_put_lock);
+
+	spin_lock(&phba->nvme_buf_list_get_lock);
+	list_for_each_entry_safe(lpfc_ncmd, lpfc_ncmd_next,
+				 &phba->lpfc_nvme_buf_list_get, list) {
+		list_del(&lpfc_ncmd->list);
+		pci_pool_free(phba->lpfc_sg_dma_buf_pool, lpfc_ncmd->data,
+			      lpfc_ncmd->dma_handle);
+		kfree(lpfc_ncmd);
+		phba->total_nvme_bufs--;
+	}
+	spin_unlock(&phba->nvme_buf_list_get_lock);
 
+	/* Release all the lpfc_iocbq entries maintained by this host. */
+	list_for_each_entry_safe(io, io_next, &phba->lpfc_iocb_list, list) {
+		list_del(&io->list);
+		kfree(io);
+		phba->total_iocbq_bufs--;
+	}
+
+	spin_unlock_irq(&phba->hbalock);
+}
 /**
- * lpfc_sli4_xri_sgl_update - update xri-sgl sizing and mapping
+ * lpfc_sli4_els_sgl_update - update ELS xri-sgl sizing and mapping
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine first calculates the sizes of the current els and allocated
@@ -3149,20 +3225,18 @@ lpfc_scsi_free(struct lpfc_hba *phba)
  *   0 - successful (for now, it always returns 0)
  **/
 int
-lpfc_sli4_xri_sgl_update(struct lpfc_hba *phba)
+lpfc_sli4_els_sgl_update(struct lpfc_hba *phba)
 {
 	struct lpfc_sglq *sglq_entry = NULL, *sglq_entry_next = NULL;
-	struct lpfc_scsi_buf *psb = NULL, *psb_next = NULL;
-	uint16_t i, lxri, xri_cnt, els_xri_cnt, scsi_xri_cnt;
+	uint16_t i, lxri, xri_cnt, els_xri_cnt;
 	LIST_HEAD(els_sgl_list);
-	LIST_HEAD(scsi_sgl_list);
 	int rc;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
 
 	/*
 	 * update on pci function's els xri-sgl list
 	 */
 	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
+
 	if (els_xri_cnt > phba->sli4_hba.els_xri_cnt) {
 		/* els xri-sgl expanded */
 		xri_cnt = els_xri_cnt - phba->sli4_hba.els_xri_cnt;
@@ -3198,9 +3272,10 @@ lpfc_sli4_xri_sgl_update(struct lpfc_hba *phba)
 			list_add_tail(&sglq_entry->list, &els_sgl_list);
 		}
 		spin_lock_irq(&phba->hbalock);
-		spin_lock(&pring->ring_lock);
-		list_splice_init(&els_sgl_list, &phba->sli4_hba.lpfc_sgl_list);
-		spin_unlock(&pring->ring_lock);
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
+		list_splice_init(&els_sgl_list,
+				 &phba->sli4_hba.lpfc_els_sgl_list);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
 		spin_unlock_irq(&phba->hbalock);
 	} else if (els_xri_cnt < phba->sli4_hba.els_xri_cnt) {
 		/* els xri-sgl shrinked */
@@ -3210,24 +3285,22 @@ lpfc_sli4_xri_sgl_update(struct lpfc_hba *phba)
 				"%d to %d\n", phba->sli4_hba.els_xri_cnt,
 				els_xri_cnt);
 		spin_lock_irq(&phba->hbalock);
-		spin_lock(&pring->ring_lock);
-		list_splice_init(&phba->sli4_hba.lpfc_sgl_list, &els_sgl_list);
-		spin_unlock(&pring->ring_lock);
-		spin_unlock_irq(&phba->hbalock);
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
+		list_splice_init(&phba->sli4_hba.lpfc_els_sgl_list,
+				 &els_sgl_list);
 		/* release extra els sgls from list */
 		for (i = 0; i < xri_cnt; i++) {
 			list_remove_head(&els_sgl_list,
 					 sglq_entry, struct lpfc_sglq, list);
 			if (sglq_entry) {
-				lpfc_mbuf_free(phba, sglq_entry->virt,
-					       sglq_entry->phys);
+				__lpfc_mbuf_free(phba, sglq_entry->virt,
+						 sglq_entry->phys);
 				kfree(sglq_entry);
 			}
 		}
-		spin_lock_irq(&phba->hbalock);
-		spin_lock(&pring->ring_lock);
-		list_splice_init(&els_sgl_list, &phba->sli4_hba.lpfc_sgl_list);
-		spin_unlock(&pring->ring_lock);
+		list_splice_init(&els_sgl_list,
+				 &phba->sli4_hba.lpfc_els_sgl_list);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
 		spin_unlock_irq(&phba->hbalock);
 	} else
 		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
@@ -3239,7 +3312,7 @@ lpfc_sli4_xri_sgl_update(struct lpfc_hba *phba)
 	sglq_entry = NULL;
 	sglq_entry_next = NULL;
 	list_for_each_entry_safe(sglq_entry, sglq_entry_next,
-				 &phba->sli4_hba.lpfc_sgl_list, list) {
+				 &phba->sli4_hba.lpfc_els_sgl_list, list) {
 		lxri = lpfc_sli4_next_xritag(phba);
 		if (lxri == NO_XRI) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
@@ -3251,21 +3324,53 @@ lpfc_sli4_xri_sgl_update(struct lpfc_hba *phba)
 		sglq_entry->sli4_lxritag = lxri;
 		sglq_entry->sli4_xritag = phba->sli4_hba.xri_ids[lxri];
 	}
+	return 0;
+
+out_free_mem:
+	lpfc_free_els_sgl_list(phba);
+	return rc;
+}
+
+/**
+ * lpfc_sli4_scsi_sgl_update - update xri-sgl sizing and mapping
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine first calculates the sizes of the current els and allocated
+ * scsi sgl lists, and then goes through all sgls to updates the physical
+ * XRIs assigned due to port function reset. During port initialization, the
+ * current els and allocated scsi sgl lists are 0s.
+ *
+ * Return codes
+ *   0 - successful (for now, it always returns 0)
+ **/
+int
+lpfc_sli4_scsi_sgl_update(struct lpfc_hba *phba)
+{
+	struct lpfc_scsi_buf *psb, *psb_next;
+	uint16_t i, lxri, els_xri_cnt, scsi_xri_cnt;
+	LIST_HEAD(scsi_sgl_list);
+	int rc;
 
 	/*
-	 * update on pci function's allocated scsi xri-sgl list
+	 * update on pci function's els xri-sgl list
 	 */
+	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
 	phba->total_scsi_bufs = 0;
 
+	/*
+	 * update on pci function's allocated scsi xri-sgl list
+	 */
 	/* maximum number of xris available for scsi buffers */
 	phba->sli4_hba.scsi_xri_max = phba->sli4_hba.max_cfg_param.max_xri -
 				      els_xri_cnt;
 
-	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-			"2401 Current allocated SCSI xri-sgl count:%d, "
-			"maximum  SCSI xri count:%d\n",
-			phba->sli4_hba.scsi_xri_cnt,
-			phba->sli4_hba.scsi_xri_max);
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
+		return 0;
+
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+		phba->sli4_hba.scsi_xri_max =  /* Split them up */
+			(phba->sli4_hba.scsi_xri_max *
+			 phba->cfg_xri_split) / 100;
 
 	spin_lock_irq(&phba->scsi_buf_list_get_lock);
 	spin_lock(&phba->scsi_buf_list_put_lock);
@@ -3283,7 +3388,7 @@ lpfc_sli4_xri_sgl_update(struct lpfc_hba *phba)
 			list_remove_head(&scsi_sgl_list, psb,
 					 struct lpfc_scsi_buf, list);
 			if (psb) {
-				pci_pool_free(phba->lpfc_scsi_dma_buf_pool,
+				pci_pool_free(phba->lpfc_sg_dma_buf_pool,
 					      psb->data, psb->dma_handle);
 				kfree(psb);
 			}
@@ -3314,15 +3419,112 @@ lpfc_sli4_xri_sgl_update(struct lpfc_hba *phba)
 	INIT_LIST_HEAD(&phba->lpfc_scsi_buf_list_put);
 	spin_unlock(&phba->scsi_buf_list_put_lock);
 	spin_unlock_irq(&phba->scsi_buf_list_get_lock);
-
 	return 0;
 
 out_free_mem:
-	lpfc_free_els_sgl_list(phba);
 	lpfc_scsi_free(phba);
 	return rc;
 }
 
+/**
+ * lpfc_sli4_nvme_sgl_update - update xri-sgl sizing and mapping
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine first calculates the sizes of the current els and allocated
+ * scsi sgl lists, and then goes through all sgls to updates the physical
+ * XRIs assigned due to port function reset. During port initialization, the
+ * current els and allocated scsi sgl lists are 0s.
+ *
+ * Return codes
+ *   0 - successful (for now, it always returns 0)
+ **/
+int
+lpfc_sli4_nvme_sgl_update(struct lpfc_hba *phba)
+{
+	struct lpfc_nvme_buf *lpfc_ncmd = NULL, *lpfc_ncmd_next = NULL;
+	uint16_t i, lxri, els_xri_cnt;
+	uint16_t nvme_xri_cnt, nvme_xri_max;
+	LIST_HEAD(nvme_sgl_list);
+	int rc;
+
+	phba->total_nvme_bufs = 0;
+
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+		return 0;
+	/*
+	 * update on pci function's allocated nvme xri-sgl list
+	 */
+
+	/* maximum number of xris available for nvme buffers */
+	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
+	nvme_xri_max = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
+	phba->sli4_hba.nvme_xri_max = nvme_xri_max;
+	phba->sli4_hba.nvme_xri_max -= phba->sli4_hba.scsi_xri_max;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+			"6074 Current allocated NVME xri-sgl count:%d, "
+			"maximum  NVME xri count:%d\n",
+			phba->sli4_hba.nvme_xri_cnt,
+			phba->sli4_hba.nvme_xri_max);
+
+	spin_lock_irq(&phba->nvme_buf_list_get_lock);
+	spin_lock(&phba->nvme_buf_list_put_lock);
+	list_splice_init(&phba->lpfc_nvme_buf_list_get, &nvme_sgl_list);
+	list_splice(&phba->lpfc_nvme_buf_list_put, &nvme_sgl_list);
+	spin_unlock(&phba->nvme_buf_list_put_lock);
+	spin_unlock_irq(&phba->nvme_buf_list_get_lock);
+
+	if (phba->sli4_hba.nvme_xri_cnt > phba->sli4_hba.nvme_xri_max) {
+		/* max nvme xri shrunk below the allocated nvme buffers */
+		spin_lock_irq(&phba->nvme_buf_list_get_lock);
+		nvme_xri_cnt = phba->sli4_hba.nvme_xri_cnt -
+					phba->sli4_hba.nvme_xri_max;
+		spin_unlock_irq(&phba->nvme_buf_list_get_lock);
+		/* release the extra allocated nvme buffers */
+		for (i = 0; i < nvme_xri_cnt; i++) {
+			list_remove_head(&nvme_sgl_list, lpfc_ncmd,
+					 struct lpfc_nvme_buf, list);
+			if (lpfc_ncmd) {
+				pci_pool_free(phba->lpfc_sg_dma_buf_pool,
+					      lpfc_ncmd->data,
+					      lpfc_ncmd->dma_handle);
+				kfree(lpfc_ncmd);
+			}
+		}
+		spin_lock_irq(&phba->nvme_buf_list_get_lock);
+		phba->sli4_hba.nvme_xri_cnt -= nvme_xri_cnt;
+		spin_unlock_irq(&phba->nvme_buf_list_get_lock);
+	}
+
+	/* update xris associated to remaining allocated nvme buffers */
+	lpfc_ncmd = NULL;
+	lpfc_ncmd_next = NULL;
+	list_for_each_entry_safe(lpfc_ncmd, lpfc_ncmd_next,
+				 &nvme_sgl_list, list) {
+		lxri = lpfc_sli4_next_xritag(phba);
+		if (lxri == NO_XRI) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+					"6075 Failed to allocate xri for "
+					"nvme buffer\n");
+			rc = -ENOMEM;
+			goto out_free_mem;
+		}
+		lpfc_ncmd->cur_iocbq.sli4_lxritag = lxri;
+		lpfc_ncmd->cur_iocbq.sli4_xritag = phba->sli4_hba.xri_ids[lxri];
+	}
+	spin_lock_irq(&phba->nvme_buf_list_get_lock);
+	spin_lock(&phba->nvme_buf_list_put_lock);
+	list_splice_init(&nvme_sgl_list, &phba->lpfc_nvme_buf_list_get);
+	INIT_LIST_HEAD(&phba->lpfc_nvme_buf_list_put);
+	spin_unlock(&phba->nvme_buf_list_put_lock);
+	spin_unlock_irq(&phba->nvme_buf_list_get_lock);
+	return 0;
+
+out_free_mem:
+	lpfc_nvme_free(phba);
+	return rc;
+}
+
 /**
  * lpfc_create_port - Create an FC port
  * @phba: pointer to lpfc hba data structure.
@@ -3343,18 +3545,23 @@ struct lpfc_vport *
 lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
 {
 	struct lpfc_vport *vport;
-	struct Scsi_Host  *shost;
+	struct Scsi_Host  *shost = NULL;
 	int error = 0;
 
-	if (dev != &phba->pcidev->dev) {
-		shost = scsi_host_alloc(&lpfc_vport_template,
-					sizeof(struct lpfc_vport));
-	} else {
-		if (phba->sli_rev == LPFC_SLI_REV4)
-			shost = scsi_host_alloc(&lpfc_template,
-					sizeof(struct lpfc_vport));
-		else
-			shost = scsi_host_alloc(&lpfc_template_s3,
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
+		if (dev != &phba->pcidev->dev) {
+			shost = scsi_host_alloc(&lpfc_vport_template,
+						sizeof(struct lpfc_vport));
+		} else {
+			if (phba->sli_rev == LPFC_SLI_REV4)
+				shost = scsi_host_alloc(&lpfc_template,
+						sizeof(struct lpfc_vport));
+			else
+				shost = scsi_host_alloc(&lpfc_template_s3,
+						sizeof(struct lpfc_vport));
+		}
+	} else if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+		shost = scsi_host_alloc(&lpfc_template_nvme,
 					sizeof(struct lpfc_vport));
 	}
 	if (!shost)
@@ -3365,8 +3572,8 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
 	vport->load_flag |= FC_LOADING;
 	vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI;
 	vport->fc_rscn_flush = 0;
-
 	lpfc_get_vport_cfgparam(vport);
+
 	shost->unique_id = instance;
 	shost->max_id = LPFC_MAX_TARGET;
 	shost->max_lun = vport->cfg_max_luns;
@@ -3944,7 +4151,7 @@ lpfc_sli4_async_link_evt(struct lpfc_hba *phba,
 	lpfc_els_flush_all_cmd(phba);
 
 	/* Block ELS IOCBs until we have done process link event */
-	phba->sli.ring[LPFC_ELS_RING].flag |= LPFC_STOP_IOCB_EVENT;
+	phba->sli4_hba.els_wq->pring->flag |= LPFC_STOP_IOCB_EVENT;
 
 	/* Update link event statistics */
 	phba->sli.slistat.link_event++;
@@ -4103,7 +4310,7 @@ lpfc_sli4_async_fc_evt(struct lpfc_hba *phba, struct lpfc_acqe_fc_la *acqe_fc)
 	lpfc_els_flush_all_cmd(phba);
 
 	/* Block ELS IOCBs until we have done process link event */
-	phba->sli.ring[LPFC_ELS_RING].flag |= LPFC_STOP_IOCB_EVENT;
+	phba->sli4_hba.els_wq->pring->flag |= LPFC_STOP_IOCB_EVENT;
 
 	/* Update link event statistics */
 	phba->sli.slistat.link_event++;
@@ -5000,40 +5207,78 @@ lpfc_sli_probe_sriov_nr_virtfn(struct lpfc_hba *phba, int nr_vfn)
 }
 
 /**
- * lpfc_sli_driver_resource_setup - Setup driver internal resources for SLI3 dev.
+ * lpfc_setup_driver_resource_phase1 - Phase1 etup driver internal resources.
  * @phba: pointer to lpfc hba data structure.
  *
- * This routine is invoked to set up the driver internal resources specific to
- * support the SLI-3 HBA device it attached to.
+ * This routine is invoked to set up the driver internal resources before the
+ * device specific resource setup to support the HBA device it attached to.
  *
  * Return codes
- * 	0 - successful
- * 	other values - error
+ *	0 - successful
+ *	other values - error
  **/
 static int
-lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
+lpfc_setup_driver_resource_phase1(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli;
-	int rc;
+	struct lpfc_sli *psli = &phba->sli;
 
 	/*
-	 * Initialize timers used by driver
+	 * Driver resources common to all SLI revisions
 	 */
+	atomic_set(&phba->fast_event_count, 0);
+	spin_lock_init(&phba->hbalock);
 
-	/* Heartbeat timer */
-	init_timer(&phba->hb_tmofunc);
-	phba->hb_tmofunc.function = lpfc_hb_timeout;
-	phba->hb_tmofunc.data = (unsigned long)phba;
+	/* Initialize ndlp management spinlock */
+	spin_lock_init(&phba->ndlp_lock);
+
+	INIT_LIST_HEAD(&phba->port_list);
+	INIT_LIST_HEAD(&phba->work_list);
+	init_waitqueue_head(&phba->wait_4_mlo_m_q);
+
+	/* Initialize the wait queue head for the kernel thread */
+	init_waitqueue_head(&phba->work_waitq);
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+			"1403 Protocols supported %s %s\n",
+			((phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) ?
+				"SCSI" : " "),
+			((phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) ?
+				"NVME" : " "));
+
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
+		/* Initialize the scsi buffer list used by driver for scsi IO */
+		spin_lock_init(&phba->scsi_buf_list_get_lock);
+		INIT_LIST_HEAD(&phba->lpfc_scsi_buf_list_get);
+		spin_lock_init(&phba->scsi_buf_list_put_lock);
+		INIT_LIST_HEAD(&phba->lpfc_scsi_buf_list_put);
+	}
+
+	if ((phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) &&
+		(phba->nvmet_support == 0)) {
+		/* Initialize the NVME buffer list used by driver for NVME IO */
+		spin_lock_init(&phba->nvme_buf_list_get_lock);
+		INIT_LIST_HEAD(&phba->lpfc_nvme_buf_list_get);
+		spin_lock_init(&phba->nvme_buf_list_put_lock);
+		INIT_LIST_HEAD(&phba->lpfc_nvme_buf_list_put);
+	}
+
+	/* Initialize the fabric iocb list */
+	INIT_LIST_HEAD(&phba->fabric_iocb_list);
+
+	/* Initialize list to save ELS buffers */
+	INIT_LIST_HEAD(&phba->elsbuf);
+
+	/* Initialize FCF connection rec list */
+	INIT_LIST_HEAD(&phba->fcf_conn_rec_list);
+
+	/* Initialize OAS configuration list */
+	spin_lock_init(&phba->devicelock);
+	INIT_LIST_HEAD(&phba->luns);
 
-	psli = &phba->sli;
 	/* MBOX heartbeat timer */
 	init_timer(&psli->mbox_tmo);
 	psli->mbox_tmo.function = lpfc_mbox_timeout;
 	psli->mbox_tmo.data = (unsigned long) phba;
-	/* FCP polling mode timer */
-	init_timer(&phba->fcp_poll_timer);
-	phba->fcp_poll_timer.function = lpfc_poll_timeout;
-	phba->fcp_poll_timer.data = (unsigned long) phba;
 	/* Fabric block timer */
 	init_timer(&phba->fabric_block_timer);
 	phba->fabric_block_timer.function = lpfc_fabric_block_timeout;
@@ -5042,6 +5287,38 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 	init_timer(&phba->eratt_poll);
 	phba->eratt_poll.function = lpfc_poll_eratt;
 	phba->eratt_poll.data = (unsigned long) phba;
+	/* Heartbeat timer */
+	init_timer(&phba->hb_tmofunc);
+	phba->hb_tmofunc.function = lpfc_hb_timeout;
+	phba->hb_tmofunc.data = (unsigned long)phba;
+
+	return 0;
+}
+
+/**
+ * lpfc_sli_driver_resource_setup - Setup driver internal resources for SLI3 dev
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked to set up the driver internal resources specific to
+ * support the SLI-3 HBA device it attached to.
+ *
+ * Return codes
+ * 0 - successful
+ * other values - error
+ **/
+static int
+lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
+{
+	int rc;
+
+	/*
+	 * Initialize timers used by driver
+	 */
+
+	/* FCP polling mode timer */
+	init_timer(&phba->fcp_poll_timer);
+	phba->fcp_poll_timer.function = lpfc_poll_timeout;
+	phba->fcp_poll_timer.data = (unsigned long) phba;
 
 	/* Host attention work mask setup */
 	phba->work_ha_mask = (HA_ERATT | HA_MBATT | HA_LATT);
@@ -5049,6 +5326,12 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 
 	/* Get all the module params for configuring this host */
 	lpfc_get_cfgparam(phba);
+	/* Set up phase-1 common device driver resources */
+
+	rc = lpfc_setup_driver_resource_phase1(phba);
+	if (rc)
+		return -ENODEV;
+
 	if (phba->pcidev->device == PCI_DEVICE_ID_HORNET) {
 		phba->menlo_flag |= HBA_MENLO_SUPPORT;
 		/* check for menlo minimum sg count */
@@ -5056,10 +5339,10 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 			phba->cfg_sg_seg_cnt = LPFC_DEFAULT_MENLO_SG_SEG_CNT;
 	}
 
-	if (!phba->sli.ring)
-		phba->sli.ring = kzalloc(LPFC_SLI3_MAX_RING *
+	if (!phba->sli.sli3_ring)
+		phba->sli.sli3_ring = kzalloc(LPFC_SLI3_MAX_RING *
 			sizeof(struct lpfc_sli_ring), GFP_KERNEL);
-	if (!phba->sli.ring)
+	if (!phba->sli.sli3_ring)
 		return -ENOMEM;
 
 	/*
@@ -5118,7 +5401,7 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
 	 * Initialize the SLI Layer to run with lpfc HBAs.
 	 */
 	lpfc_sli_setup(phba);
-	lpfc_sli_queue_setup(phba);
+	lpfc_sli_queue_init(phba);
 
 	/* Allocate device driver memory */
 	if (lpfc_mem_alloc(phba, BPL_ALIGN_SZ))
@@ -5174,18 +5457,25 @@ lpfc_sli_driver_resource_unset(struct lpfc_hba *phba)
 static int
 lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 {
-	struct lpfc_vector_map_info *cpup;
-	struct lpfc_sli *psli;
 	LPFC_MBOXQ_t *mboxq;
-	int rc, i, hbq_count, max_buf_size;
+	int rc, i, max_buf_size;
 	uint8_t pn_page[LPFC_MAX_SUPPORTED_PAGES] = {0};
 	struct lpfc_mqe *mqe;
 	int longs;
 	int fof_vectors = 0;
 
+	phba->sli4_hba.num_online_cpu = num_online_cpus();
+	phba->sli4_hba.num_present_cpu = lpfc_present_cpu;
+	phba->sli4_hba.curr_disp_cpu = 0;
+
 	/* Get all the module params for configuring this host */
 	lpfc_get_cfgparam(phba);
 
+	/* Set up phase-1 common device driver resources */
+	rc = lpfc_setup_driver_resource_phase1(phba);
+	if (rc)
+		return -ENODEV;
+
 	/* Before proceed, wait for POST done and device ready */
 	rc = lpfc_sli4_post_status_check(phba);
 	if (rc)
@@ -5195,27 +5485,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	 * Initialize timers used by driver
 	 */
 
-	/* Heartbeat timer */
-	init_timer(&phba->hb_tmofunc);
-	phba->hb_tmofunc.function = lpfc_hb_timeout;
-	phba->hb_tmofunc.data = (unsigned long)phba;
 	init_timer(&phba->rrq_tmr);
 	phba->rrq_tmr.function = lpfc_rrq_timeout;
 	phba->rrq_tmr.data = (unsigned long)phba;
 
-	psli = &phba->sli;
-	/* MBOX heartbeat timer */
-	init_timer(&psli->mbox_tmo);
-	psli->mbox_tmo.function = lpfc_mbox_timeout;
-	psli->mbox_tmo.data = (unsigned long) phba;
-	/* Fabric block timer */
-	init_timer(&phba->fabric_block_timer);
-	phba->fabric_block_timer.function = lpfc_fabric_block_timeout;
-	phba->fabric_block_timer.data = (unsigned long) phba;
-	/* EA polling mode timer */
-	init_timer(&phba->eratt_poll);
-	phba->eratt_poll.function = lpfc_poll_eratt;
-	phba->eratt_poll.data = (unsigned long) phba;
 	/* FCF rediscover timer */
 	init_timer(&phba->fcf.redisc_wait);
 	phba->fcf.redisc_wait.function = lpfc_sli4_fcf_redisc_wait_tmo;
@@ -5242,14 +5515,9 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	/*
 	 * For SLI4, instead of using ring 0 (LPFC_FCP_RING) for FCP commands
-	 * we will associate a new ring, for each FCP fastpath EQ/CQ/WQ tuple.
+	 * we will associate a new ring, for each EQ/CQ/WQ tuple.
+	 * The WQ create will allocate the ring.
 	 */
-	if (!phba->sli.ring)
-		phba->sli.ring = kzalloc(
-			(LPFC_SLI3_MAX_RING + phba->cfg_fcp_io_channel) *
-			sizeof(struct lpfc_sli_ring), GFP_KERNEL);
-	if (!phba->sli.ring)
-		return -ENOMEM;
 
 	/*
 	 * It doesn't matter what family our adapter is in, we are
@@ -5261,43 +5529,45 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		phba->cfg_sg_seg_cnt = LPFC_MAX_SGL_SEG_CNT - 2;
 
 	/*
-	 * Since lpfc_sg_seg_cnt is module parameter, the sg_dma_buf_size
-	 * used to create the sg_dma_buf_pool must be dynamically calculated.
+	 * Since lpfc_sg_seg_cnt is module param, the sg_dma_buf_size
+	 * used to create the sg_dma_buf_pool must be calculated.
 	 */
-
 	if (phba->cfg_enable_bg) {
 		/*
-		 * The scsi_buf for a T10-DIF I/O will hold the FCP cmnd,
-		 * the FCP rsp, and a SGE for each. Sice we have no control
-		 * over how many protection data segments the SCSI Layer
+		 * The scsi_buf for a T10-DIF I/O holds the FCP cmnd,
+		 * the FCP rsp, and a SGE. Sice we have no control
+		 * over how many protection segments the SCSI Layer
 		 * will hand us (ie: there could be one for every block
-		 * in the IO), we just allocate enough SGEs to accomidate
-		 * our max amount and we need to limit lpfc_sg_seg_cnt to
-		 * minimize the risk of running out.
+		 * in the IO), just allocate enough SGEs to accomidate
+		 * our max amount and we need to limit lpfc_sg_seg_cnt
+		 * to minimize the risk of running out.
 		 */
 		phba->cfg_sg_dma_buf_size = sizeof(struct fcp_cmnd) +
-			sizeof(struct fcp_rsp) + max_buf_size;
+				sizeof(struct fcp_rsp) + max_buf_size;
 
 		/* Total SGEs for scsi_sg_list and scsi_sg_prot_list */
 		phba->cfg_total_seg_cnt = LPFC_MAX_SGL_SEG_CNT;
 
 		if (phba->cfg_sg_seg_cnt > LPFC_MAX_SG_SLI4_SEG_CNT_DIF)
-			phba->cfg_sg_seg_cnt = LPFC_MAX_SG_SLI4_SEG_CNT_DIF;
+			phba->cfg_sg_seg_cnt =
+				LPFC_MAX_SG_SLI4_SEG_CNT_DIF;
 	} else {
 		/*
-		 * The scsi_buf for a regular I/O will hold the FCP cmnd,
+		 * The scsi_buf for a regular I/O holds the FCP cmnd,
 		 * the FCP rsp, a SGE for each, and a SGE for up to
 		 * cfg_sg_seg_cnt data segments.
 		 */
 		phba->cfg_sg_dma_buf_size = sizeof(struct fcp_cmnd) +
-			sizeof(struct fcp_rsp) +
-			((phba->cfg_sg_seg_cnt + 2) * sizeof(struct sli4_sge));
+				sizeof(struct fcp_rsp) +
+				((phba->cfg_sg_seg_cnt + 2) *
+				sizeof(struct sli4_sge));
 
 		/* Total SGEs for scsi_sg_list */
 		phba->cfg_total_seg_cnt = phba->cfg_sg_seg_cnt + 2;
+
 		/*
-		 * NOTE: if (phba->cfg_sg_seg_cnt + 2) <= 256 we only need
-		 * to post 1 page for the SGL.
+		 * NOTE: if (phba->cfg_sg_seg_cnt + 2) <= 256 we only
+		 * need to post 1 page for the SGL.
 		 */
 	}
 
@@ -5317,21 +5587,27 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 			phba->cfg_total_seg_cnt);
 
 	/* Initialize buffer queue management fields */
-	hbq_count = lpfc_sli_hbq_count();
-	for (i = 0; i < hbq_count; ++i)
-		INIT_LIST_HEAD(&phba->hbqs[i].hbq_buffer_list);
-	INIT_LIST_HEAD(&phba->rb_pend_list);
+	INIT_LIST_HEAD(&phba->hbqs[LPFC_ELS_HBQ].hbq_buffer_list);
 	phba->hbqs[LPFC_ELS_HBQ].hbq_alloc_buffer = lpfc_sli4_rb_alloc;
 	phba->hbqs[LPFC_ELS_HBQ].hbq_free_buffer = lpfc_sli4_rb_free;
 
 	/*
 	 * Initialize the SLI Layer to run with lpfc SLI4 HBAs.
 	 */
-	/* Initialize the Abort scsi buffer list used by driver */
-	spin_lock_init(&phba->sli4_hba.abts_scsi_buf_list_lock);
-	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_scsi_buf_list);
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
+		/* Initialize the Abort scsi buffer list used by driver */
+		spin_lock_init(&phba->sli4_hba.abts_scsi_buf_list_lock);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_scsi_buf_list);
+	}
+
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+		/* Initialize the Abort nvme buffer list used by driver */
+		spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+	}
+
 	/* This abort list used by worker thread */
-	spin_lock_init(&phba->sli4_hba.abts_sgl_list_lock);
+	spin_lock_init(&phba->sli4_hba.sgl_list_lock);
 
 	/*
 	 * Initialize driver internal slow-path work queues
@@ -5359,10 +5635,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	/* initialize optic_state to 0xFF */
 	phba->sli4_hba.lnk_info.optic_state = 0xff;
 
-	/* Initialize the driver internal SLI layer lists. */
-	lpfc_sli_setup(phba);
-	lpfc_sli_queue_setup(phba);
-
 	/* Allocate device driver memory */
 	rc = lpfc_mem_alloc(phba, SGL_ALIGN_SZ);
 	if (rc)
@@ -5372,8 +5644,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) ==
 	    LPFC_SLI_INTF_IF_TYPE_2) {
 		rc = lpfc_pci_function_reset(phba);
-		if (unlikely(rc))
-			return -ENODEV;
+		if (unlikely(rc)) {
+			rc = -ENODEV;
+			goto out_free_mem;
+		}
 		phba->temp_sensor_support = 1;
 	}
 
@@ -5410,6 +5684,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		goto out_free_bsmbx;
 	}
 
+	phba->nvmet_support = 0;
+
+	lpfc_nvme_mod_param_dep(phba);
+
 	/* Get the Supported Pages if PORT_CAPABILITIES is supported by port. */
 	lpfc_supported_pages(mboxq);
 	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
@@ -5448,9 +5726,11 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"2999 Unsupported SLI4 Parameters "
 				"Extents and RPI headers enabled.\n");
-			goto out_free_bsmbx;
 		}
+		mempool_free(mboxq, phba->mbox_mem_pool);
+		goto out_free_bsmbx;
 	}
+
 	mempool_free(mboxq, phba->mbox_mem_pool);
 
 	/* Verify OAS is supported */
@@ -5497,11 +5777,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		goto out_remove_rpi_hdrs;
 	}
 
-	phba->sli4_hba.fcp_eq_hdl =
-			kzalloc((sizeof(struct lpfc_fcp_eq_hdl) *
-			    (fof_vectors + phba->cfg_fcp_io_channel)),
-			    GFP_KERNEL);
-	if (!phba->sli4_hba.fcp_eq_hdl) {
+	phba->sli4_hba.hba_eq_hdl = kcalloc(fof_vectors + phba->io_channel_irqs,
+						sizeof(struct lpfc_hba_eq_hdl),
+						GFP_KERNEL);
+	if (!phba->sli4_hba.hba_eq_hdl) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"2572 Failed allocate memory for "
 				"fast-path per-EQ handle array\n");
@@ -5509,41 +5788,31 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		goto out_free_fcf_rr_bmask;
 	}
 
-	phba->sli4_hba.cpu_map = kzalloc((sizeof(struct lpfc_vector_map_info) *
-					 phba->sli4_hba.num_present_cpu),
-					 GFP_KERNEL);
+	phba->sli4_hba.cpu_map = kcalloc(phba->sli4_hba.num_present_cpu,
+					sizeof(struct lpfc_vector_map_info),
+					GFP_KERNEL);
 	if (!phba->sli4_hba.cpu_map) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"3327 Failed allocate memory for msi-x "
 				"interrupt vector mapping\n");
 		rc = -ENOMEM;
-		goto out_free_fcp_eq_hdl;
+		goto out_free_hba_eq_hdl;
 	}
 	if (lpfc_used_cpu == NULL) {
-		lpfc_used_cpu = kzalloc((sizeof(uint16_t) * lpfc_present_cpu),
-					 GFP_KERNEL);
+		lpfc_used_cpu = kcalloc(lpfc_present_cpu, sizeof(uint16_t),
+						GFP_KERNEL);
 		if (!lpfc_used_cpu) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"3335 Failed allocate memory for msi-x "
 					"interrupt vector mapping\n");
 			kfree(phba->sli4_hba.cpu_map);
 			rc = -ENOMEM;
-			goto out_free_fcp_eq_hdl;
+			goto out_free_hba_eq_hdl;
 		}
 		for (i = 0; i < lpfc_present_cpu; i++)
 			lpfc_used_cpu[i] = LPFC_VECTOR_MAP_EMPTY;
 	}
 
-	/* Initialize io channels for round robin */
-	cpup = phba->sli4_hba.cpu_map;
-	rc = 0;
-	for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) {
-		cpup->channel_id = rc;
-		rc++;
-		if (rc >= phba->cfg_fcp_io_channel)
-			rc = 0;
-	}
-
 	/*
 	 * Enable sr-iov virtual functions if supported and configured
 	 * through the module parameter.
@@ -5563,8 +5832,8 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	return 0;
 
-out_free_fcp_eq_hdl:
-	kfree(phba->sli4_hba.fcp_eq_hdl);
+out_free_hba_eq_hdl:
+	kfree(phba->sli4_hba.hba_eq_hdl);
 out_free_fcf_rr_bmask:
 	kfree(phba->fcf.fcf_rr_bmask);
 out_remove_rpi_hdrs:
@@ -5599,7 +5868,7 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	phba->sli4_hba.curr_disp_cpu = 0;
 
 	/* Free memory allocated for fast-path work queue handles */
-	kfree(phba->sli4_hba.fcp_eq_hdl);
+	kfree(phba->sli4_hba.hba_eq_hdl);
 
 	/* Free the allocated rpi headers. */
 	lpfc_sli4_remove_rpi_hdrs(phba);
@@ -5672,58 +5941,6 @@ lpfc_init_api_table_setup(struct lpfc_hba *phba, uint8_t dev_grp)
 	return 0;
 }
 
-/**
- * lpfc_setup_driver_resource_phase1 - Phase1 etup driver internal resources.
- * @phba: pointer to lpfc hba data structure.
- *
- * This routine is invoked to set up the driver internal resources before the
- * device specific resource setup to support the HBA device it attached to.
- *
- * Return codes
- *	0 - successful
- *	other values - error
- **/
-static int
-lpfc_setup_driver_resource_phase1(struct lpfc_hba *phba)
-{
-	/*
-	 * Driver resources common to all SLI revisions
-	 */
-	atomic_set(&phba->fast_event_count, 0);
-	spin_lock_init(&phba->hbalock);
-
-	/* Initialize ndlp management spinlock */
-	spin_lock_init(&phba->ndlp_lock);
-
-	INIT_LIST_HEAD(&phba->port_list);
-	INIT_LIST_HEAD(&phba->work_list);
-	init_waitqueue_head(&phba->wait_4_mlo_m_q);
-
-	/* Initialize the wait queue head for the kernel thread */
-	init_waitqueue_head(&phba->work_waitq);
-
-	/* Initialize the scsi buffer list used by driver for scsi IO */
-	spin_lock_init(&phba->scsi_buf_list_get_lock);
-	INIT_LIST_HEAD(&phba->lpfc_scsi_buf_list_get);
-	spin_lock_init(&phba->scsi_buf_list_put_lock);
-	INIT_LIST_HEAD(&phba->lpfc_scsi_buf_list_put);
-
-	/* Initialize the fabric iocb list */
-	INIT_LIST_HEAD(&phba->fabric_iocb_list);
-
-	/* Initialize list to save ELS buffers */
-	INIT_LIST_HEAD(&phba->elsbuf);
-
-	/* Initialize FCF connection rec list */
-	INIT_LIST_HEAD(&phba->fcf_conn_rec_list);
-
-	/* Initialize OAS configuration list */
-	spin_lock_init(&phba->devicelock);
-	INIT_LIST_HEAD(&phba->luns);
-
-	return 0;
-}
-
 /**
  * lpfc_setup_driver_resource_phase2 - Phase2 setup driver internal resources.
  * @phba: pointer to lpfc hba data structure.
@@ -5871,13 +6088,12 @@ static void
 lpfc_free_els_sgl_list(struct lpfc_hba *phba)
 {
 	LIST_HEAD(sglq_list);
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
 
 	/* Retrieve all els sgls from driver list */
 	spin_lock_irq(&phba->hbalock);
-	spin_lock(&pring->ring_lock);
-	list_splice_init(&phba->sli4_hba.lpfc_sgl_list, &sglq_list);
-	spin_unlock(&pring->ring_lock);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
+	list_splice_init(&phba->sli4_hba.lpfc_els_sgl_list, &sglq_list);
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	spin_unlock_irq(&phba->hbalock);
 
 	/* Now free the sgl list */
@@ -5931,7 +6147,7 @@ static void
 lpfc_init_sgl_list(struct lpfc_hba *phba)
 {
 	/* Initialize and populate the sglq list per host/VF. */
-	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_sgl_list);
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_els_sgl_list);
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_els_sgl_list);
 
 	/* els xri-sgl book keeping */
@@ -5939,6 +6155,9 @@ lpfc_init_sgl_list(struct lpfc_hba *phba)
 
 	/* scsi xri-buffer book keeping */
 	phba->sli4_hba.scsi_xri_cnt = 0;
+
+	/* nvme xri-buffer book keeping */
+	phba->sli4_hba.nvme_xri_cnt = 0;
 }
 
 /**
@@ -6169,9 +6388,9 @@ lpfc_hba_free(struct lpfc_hba *phba)
 	/* Release the driver assigned board number */
 	idr_remove(&lpfc_hba_index, phba->brd_no);
 
-	/* Free memory allocated with sli rings */
-	kfree(phba->sli.ring);
-	phba->sli.ring = NULL;
+	/* Free memory allocated with sli3 rings */
+	kfree(phba->sli.sli3_ring);
+	phba->sli.sli3_ring = NULL;
 
 	kfree(phba);
 	return;
@@ -6489,8 +6708,6 @@ lpfc_sli_pci_mem_setup(struct lpfc_hba *phba)
 
 	memset(phba->hbqslimp.virt, 0, lpfc_sli_hbq_size());
 
-	INIT_LIST_HEAD(&phba->rb_pend_list);
-
 	phba->MBslimaddr = phba->slim_memmap_p;
 	phba->HAregaddr = phba->ctrl_regs_memmap_p + HA_REG_OFFSET;
 	phba->CAregaddr = phba->ctrl_regs_memmap_p + CA_REG_OFFSET;
@@ -7200,11 +7417,11 @@ lpfc_setup_endian_order(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_sli4_queue_verify - Verify and update EQ and CQ counts
+ * lpfc_sli4_queue_verify - Verify and update EQ counts
  * @phba: pointer to lpfc hba data structure.
  *
- * This routine is invoked to check the user settable queue counts for EQs and
- * CQs. after this routine is called the counts will be set to valid values that
+ * This routine is invoked to check the user settable queue counts for EQs.
+ * After this routine is called the counts will be set to valid values that
  * adhere to the constraints of the system's interrupt vectors and the port's
  * queue resources.
  *
@@ -7215,9 +7432,7 @@ lpfc_setup_endian_order(struct lpfc_hba *phba)
 static int
 lpfc_sli4_queue_verify(struct lpfc_hba *phba)
 {
-	int cfg_fcp_io_channel;
-	uint32_t cpu;
-	uint32_t i = 0;
+	int io_channel;
 	int fof_vectors = phba->cfg_fof ? 1 : 0;
 
 	/*
@@ -7226,49 +7441,38 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba)
 	 */
 
 	/* Sanity check on HBA EQ parameters */
-	cfg_fcp_io_channel = phba->cfg_fcp_io_channel;
+	io_channel = phba->io_channel_irqs;
 
-	/* It doesn't make sense to have more io channels then online CPUs */
-	for_each_present_cpu(cpu) {
-		if (cpu_online(cpu))
-			i++;
-	}
-	phba->sli4_hba.num_online_cpu = i;
-	phba->sli4_hba.num_present_cpu = lpfc_present_cpu;
-	phba->sli4_hba.curr_disp_cpu = 0;
-
-	if (i < cfg_fcp_io_channel) {
+	if (phba->sli4_hba.num_online_cpu < io_channel) {
 		lpfc_printf_log(phba,
 				KERN_ERR, LOG_INIT,
 				"3188 Reducing IO channels to match number of "
 				"online CPUs: from %d to %d\n",
-				cfg_fcp_io_channel, i);
-		cfg_fcp_io_channel = i;
+				io_channel, phba->sli4_hba.num_online_cpu);
+		io_channel = phba->sli4_hba.num_online_cpu;
 	}
 
-	if (cfg_fcp_io_channel + fof_vectors >
-	    phba->sli4_hba.max_cfg_param.max_eq) {
-		if (phba->sli4_hba.max_cfg_param.max_eq <
-		    LPFC_FCP_IO_CHAN_MIN) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"2574 Not enough EQs (%d) from the "
-					"pci function for supporting FCP "
-					"EQs (%d)\n",
-					phba->sli4_hba.max_cfg_param.max_eq,
-					phba->cfg_fcp_io_channel);
-			goto out_error;
-		}
+	if (io_channel + fof_vectors > phba->sli4_hba.max_cfg_param.max_eq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"2575 Reducing IO channels to match number of "
 				"available EQs: from %d to %d\n",
-				cfg_fcp_io_channel,
+				io_channel,
 				phba->sli4_hba.max_cfg_param.max_eq);
-		cfg_fcp_io_channel = phba->sli4_hba.max_cfg_param.max_eq -
-			fof_vectors;
+		io_channel = phba->sli4_hba.max_cfg_param.max_eq - fof_vectors;
 	}
 
-	/* The actual number of FCP event queues adopted */
-	phba->cfg_fcp_io_channel = cfg_fcp_io_channel;
+	/* The actual number of FCP / NVME event queues adopted */
+	if (io_channel != phba->io_channel_irqs)
+		phba->io_channel_irqs = io_channel;
+	if (phba->cfg_fcp_io_channel > io_channel)
+		phba->cfg_fcp_io_channel = io_channel;
+	if (phba->cfg_nvme_io_channel > io_channel)
+		phba->cfg_nvme_io_channel = io_channel;
+
+	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+			"2574 IRQs: %d, IO Channels: fcp %d nvme %d\n",
+			phba->io_channel_irqs, phba->cfg_fcp_io_channel,
+			phba->cfg_nvme_io_channel);
 
 	/* Get EQ depth from module parameter, fake the default for now */
 	phba->sli4_hba.eq_esize = LPFC_EQE_SIZE_4B;
@@ -7277,10 +7481,67 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba)
 	/* Get CQ depth from module parameter, fake the default for now */
 	phba->sli4_hba.cq_esize = LPFC_CQE_SIZE;
 	phba->sli4_hba.cq_ecount = LPFC_CQE_DEF_COUNT;
+	return 0;
+}
+
+static int
+lpfc_alloc_nvme_wq_cq(struct lpfc_hba *phba, int wqidx)
+{
+	struct lpfc_queue *qdesc;
+	int cnt;
 
+	qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.cq_esize,
+					    phba->sli4_hba.cq_ecount);
+	if (!qdesc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0508 Failed allocate fast-path NVME CQ (%d)\n",
+				wqidx);
+		return 1;
+	}
+	phba->sli4_hba.nvme_cq[wqidx] = qdesc;
+
+	cnt = LPFC_NVME_WQSIZE;
+	qdesc = lpfc_sli4_queue_alloc(phba, LPFC_WQE128_SIZE, cnt);
+	if (!qdesc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0509 Failed allocate fast-path NVME WQ (%d)\n",
+				wqidx);
+		return 1;
+	}
+	phba->sli4_hba.nvme_wq[wqidx] = qdesc;
+	list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list);
+	return 0;
+}
+
+static int
+lpfc_alloc_fcp_wq_cq(struct lpfc_hba *phba, int wqidx)
+{
+	struct lpfc_queue *qdesc;
+	uint32_t wqesize;
+
+	/* Create Fast Path FCP CQs */
+	qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.cq_esize,
+					phba->sli4_hba.cq_ecount);
+	if (!qdesc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+			"0499 Failed allocate fast-path FCP CQ (%d)\n", wqidx);
+		return 1;
+	}
+	phba->sli4_hba.fcp_cq[wqidx] = qdesc;
+
+	/* Create Fast Path FCP WQs */
+	wqesize = (phba->fcp_embed_io) ?
+				LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
+	qdesc = lpfc_sli4_queue_alloc(phba, wqesize, phba->sli4_hba.wq_ecount);
+	if (!qdesc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0503 Failed allocate fast-path FCP WQ (%d)\n",
+				wqidx);
+		return 1;
+	}
+	phba->sli4_hba.fcp_wq[wqidx] = qdesc;
+	list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list);
 	return 0;
-out_error:
-	return -ENOMEM;
 }
 
 /**
@@ -7301,13 +7562,14 @@ int
 lpfc_sli4_queue_create(struct lpfc_hba *phba)
 {
 	struct lpfc_queue *qdesc;
-	uint32_t wqesize;
-	int idx;
+	int idx, io_channel;
 
 	/*
 	 * Create HBA Record arrays.
+	 * Both NVME and FCP will share that same vectors / EQs
 	 */
-	if (!phba->cfg_fcp_io_channel)
+	io_channel = phba->io_channel_irqs;
+	if (!io_channel)
 		return -ERANGE;
 
 	phba->sli4_hba.mq_esize = LPFC_MQE_SIZE;
@@ -7316,9 +7578,14 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 	phba->sli4_hba.wq_ecount = LPFC_WQE_DEF_COUNT;
 	phba->sli4_hba.rq_esize = LPFC_RQE_SIZE;
 	phba->sli4_hba.rq_ecount = LPFC_RQE_DEF_COUNT;
+	phba->sli4_hba.eq_esize = LPFC_EQE_SIZE_4B;
+	phba->sli4_hba.eq_ecount = LPFC_EQE_DEF_COUNT;
+	phba->sli4_hba.cq_esize = LPFC_CQE_SIZE;
+	phba->sli4_hba.cq_ecount = LPFC_CQE_DEF_COUNT;
 
-	phba->sli4_hba.hba_eq =  kzalloc((sizeof(struct lpfc_queue *) *
-				phba->cfg_fcp_io_channel), GFP_KERNEL);
+	phba->sli4_hba.hba_eq =  kcalloc(io_channel,
+					sizeof(struct lpfc_queue *),
+					GFP_KERNEL);
 	if (!phba->sli4_hba.hba_eq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			"2576 Failed allocate memory for "
@@ -7326,44 +7593,83 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 		goto out_error;
 	}
 
-	phba->sli4_hba.fcp_cq = kzalloc((sizeof(struct lpfc_queue *) *
-				phba->cfg_fcp_io_channel), GFP_KERNEL);
-	if (!phba->sli4_hba.fcp_cq) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"2577 Failed allocate memory for fast-path "
-				"CQ record array\n");
-		goto out_error;
+	if (phba->cfg_fcp_io_channel) {
+		phba->sli4_hba.fcp_cq = kcalloc(phba->cfg_fcp_io_channel,
+						sizeof(struct lpfc_queue *),
+						GFP_KERNEL);
+		if (!phba->sli4_hba.fcp_cq) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"2577 Failed allocate memory for "
+					"fast-path CQ record array\n");
+			goto out_error;
+		}
+		phba->sli4_hba.fcp_wq = kcalloc(phba->cfg_fcp_io_channel,
+						sizeof(struct lpfc_queue *),
+						GFP_KERNEL);
+		if (!phba->sli4_hba.fcp_wq) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"2578 Failed allocate memory for "
+					"fast-path FCP WQ record array\n");
+			goto out_error;
+		}
+		/*
+		 * Since the first EQ can have multiple CQs associated with it,
+		 * this array is used to quickly see if we have a FCP fast-path
+		 * CQ match.
+		 */
+		phba->sli4_hba.fcp_cq_map = kcalloc(phba->cfg_fcp_io_channel,
+							sizeof(uint16_t),
+							GFP_KERNEL);
+		if (!phba->sli4_hba.fcp_cq_map) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"2545 Failed allocate memory for "
+					"fast-path CQ map\n");
+			goto out_error;
+		}
 	}
 
-	phba->sli4_hba.fcp_wq = kzalloc((sizeof(struct lpfc_queue *) *
-				phba->cfg_fcp_io_channel), GFP_KERNEL);
-	if (!phba->sli4_hba.fcp_wq) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"2578 Failed allocate memory for fast-path "
-				"WQ record array\n");
-		goto out_error;
-	}
+	if (phba->cfg_nvme_io_channel) {
+		phba->sli4_hba.nvme_cq = kcalloc(phba->cfg_nvme_io_channel,
+						sizeof(struct lpfc_queue *),
+						GFP_KERNEL);
+		if (!phba->sli4_hba.nvme_cq) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6077 Failed allocate memory for "
+					"fast-path CQ record array\n");
+			goto out_error;
+		}
 
-	/*
-	 * Since the first EQ can have multiple CQs associated with it,
-	 * this array is used to quickly see if we have a FCP fast-path
-	 * CQ match.
-	 */
-	phba->sli4_hba.fcp_cq_map = kzalloc((sizeof(uint16_t) *
-					 phba->cfg_fcp_io_channel), GFP_KERNEL);
-	if (!phba->sli4_hba.fcp_cq_map) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"2545 Failed allocate memory for fast-path "
-				"CQ map\n");
-		goto out_error;
+
+		phba->sli4_hba.nvme_wq = kcalloc(phba->cfg_nvme_io_channel,
+						sizeof(struct lpfc_queue *),
+						GFP_KERNEL);
+		if (!phba->sli4_hba.nvme_wq) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"2581 Failed allocate memory for "
+					"fast-path NVME WQ record array\n");
+			goto out_error;
+		}
+
+		/*
+		 * Since the first EQ can have multiple CQs associated with it,
+		 * this array is used to quickly see if we have a NVME fast-path
+		 * CQ match.
+		 */
+		phba->sli4_hba.nvme_cq_map = kcalloc(phba->cfg_nvme_io_channel,
+							sizeof(uint16_t),
+							GFP_KERNEL);
+		if (!phba->sli4_hba.nvme_cq_map) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6078 Failed allocate memory for "
+					"fast-path CQ map\n");
+			goto out_error;
+		}
 	}
 
-	/*
-	 * Create HBA Event Queues (EQs).  The cfg_fcp_io_channel specifies
-	 * how many EQs to create.
-	 */
-	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++) {
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_wq_list);
 
+	/* Create HBA Event Queues (EQs) */
+	for (idx = 0; idx < io_channel; idx++) {
 		/* Create EQs */
 		qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.eq_esize,
 					      phba->sli4_hba.eq_ecount);
@@ -7373,32 +7679,17 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 			goto out_error;
 		}
 		phba->sli4_hba.hba_eq[idx] = qdesc;
+	}
 
-		/* Create Fast Path FCP CQs */
-		qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.cq_esize,
-					      phba->sli4_hba.cq_ecount);
-		if (!qdesc) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"0499 Failed allocate fast-path FCP "
-					"CQ (%d)\n", idx);
-			goto out_error;
-		}
-		phba->sli4_hba.fcp_cq[idx] = qdesc;
+	/* FCP and NVME io channels are not required to be balanced */
 
-		/* Create Fast Path FCP WQs */
-		wqesize = (phba->fcp_embed_io) ?
-				LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
-		qdesc = lpfc_sli4_queue_alloc(phba, wqesize,
-						phba->sli4_hba.wq_ecount);
-		if (!qdesc) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"0503 Failed allocate fast-path FCP "
-					"WQ (%d)\n", idx);
+	for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
+		if (lpfc_alloc_fcp_wq_cq(phba, idx))
 			goto out_error;
-		}
-		phba->sli4_hba.fcp_wq[idx] = qdesc;
-	}
 
+	for (idx = 0; idx < phba->cfg_nvme_io_channel; idx++)
+		if (lpfc_alloc_nvme_wq_cq(phba, idx))
+			goto out_error;
 
 	/*
 	 * Create Slow Path Completion Queues (CQs)
@@ -7453,6 +7744,30 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 		goto out_error;
 	}
 	phba->sli4_hba.els_wq = qdesc;
+	list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list);
+
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+		/* Create NVME LS Complete Queue */
+		qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.cq_esize,
+					      phba->sli4_hba.cq_ecount);
+		if (!qdesc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6079 Failed allocate NVME LS CQ\n");
+			goto out_error;
+		}
+		phba->sli4_hba.nvmels_cq = qdesc;
+
+		/* Create NVME LS Work Queue */
+		qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.wq_esize,
+					      phba->sli4_hba.wq_ecount);
+		if (!qdesc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6080 Failed allocate NVME LS WQ\n");
+			goto out_error;
+		}
+		phba->sli4_hba.nvmels_wq = qdesc;
+		list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list);
+	}
 
 	/*
 	 * Create Receive Queue (RQ)
@@ -7488,6 +7803,39 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 	return -ENOMEM;
 }
 
+static inline void
+__lpfc_sli4_release_queue(struct lpfc_queue **qp)
+{
+	if (*qp != NULL) {
+		lpfc_sli4_queue_free(*qp);
+		*qp = NULL;
+	}
+}
+
+static inline void
+lpfc_sli4_release_queues(struct lpfc_queue ***qs, int max)
+{
+	int idx;
+
+	if (*qs == NULL)
+		return;
+
+	for (idx = 0; idx < max; idx++)
+		__lpfc_sli4_release_queue(&(*qs)[idx]);
+
+	kfree(*qs);
+	*qs = NULL;
+}
+
+static inline void
+lpfc_sli4_release_queue_map(uint16_t **qmap)
+{
+	if (*qmap != NULL) {
+		kfree(*qmap);
+		*qmap = NULL;
+	}
+}
+
 /**
  * lpfc_sli4_queue_destroy - Destroy all the SLI4 queues
  * @phba: pointer to lpfc hba data structure.
@@ -7503,91 +7851,188 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 void
 lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 {
-	int idx;
-
 	if (phba->cfg_fof)
 		lpfc_fof_queue_destroy(phba);
 
-	if (phba->sli4_hba.hba_eq != NULL) {
-		/* Release HBA event queue */
-		for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++) {
-			if (phba->sli4_hba.hba_eq[idx] != NULL) {
-				lpfc_sli4_queue_free(
-					phba->sli4_hba.hba_eq[idx]);
-				phba->sli4_hba.hba_eq[idx] = NULL;
-			}
+	/* Release HBA eqs */
+	lpfc_sli4_release_queues(&phba->sli4_hba.hba_eq, phba->io_channel_irqs);
+
+	/* Release FCP cqs */
+	lpfc_sli4_release_queues(&phba->sli4_hba.fcp_cq,
+					phba->cfg_fcp_io_channel);
+
+	/* Release FCP wqs */
+	lpfc_sli4_release_queues(&phba->sli4_hba.fcp_wq,
+					phba->cfg_fcp_io_channel);
+
+	/* Release FCP CQ mapping array */
+	lpfc_sli4_release_queue_map(&phba->sli4_hba.fcp_cq_map);
+
+	/* Release NVME cqs */
+	lpfc_sli4_release_queues(&phba->sli4_hba.nvme_cq,
+					phba->cfg_nvme_io_channel);
+
+	/* Release NVME wqs */
+	lpfc_sli4_release_queues(&phba->sli4_hba.nvme_wq,
+					phba->cfg_nvme_io_channel);
+
+	/* Release NVME CQ mapping array */
+	lpfc_sli4_release_queue_map(&phba->sli4_hba.nvme_cq_map);
+
+	/* Release mailbox command work queue */
+	__lpfc_sli4_release_queue(&phba->sli4_hba.mbx_wq);
+
+	/* Release ELS work queue */
+	__lpfc_sli4_release_queue(&phba->sli4_hba.els_wq);
+
+	/* Release ELS work queue */
+	__lpfc_sli4_release_queue(&phba->sli4_hba.nvmels_wq);
+
+	/* Release unsolicited receive queue */
+	__lpfc_sli4_release_queue(&phba->sli4_hba.hdr_rq);
+	__lpfc_sli4_release_queue(&phba->sli4_hba.dat_rq);
+
+	/* Release ELS complete queue */
+	__lpfc_sli4_release_queue(&phba->sli4_hba.els_cq);
+
+	/* Release NVME LS complete queue */
+	__lpfc_sli4_release_queue(&phba->sli4_hba.nvmels_cq);
+
+	/* Release mailbox command complete queue */
+	__lpfc_sli4_release_queue(&phba->sli4_hba.mbx_cq);
+
+	/* Everything on this list has been freed */
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_wq_list);
+}
+
+int
+lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
+		    struct lpfc_queue *drq, int count)
+{
+	int rc, i;
+	struct lpfc_rqe hrqe;
+	struct lpfc_rqe drqe;
+	struct lpfc_rqb *rqbp;
+	struct rqb_dmabuf *rqb_buffer;
+	LIST_HEAD(rqb_buf_list);
+
+	rqbp = hrq->rqbp;
+	for (i = 0; i < count; i++) {
+		rqb_buffer = (rqbp->rqb_alloc_buffer)(phba);
+		if (!rqb_buffer)
+			break;
+		rqb_buffer->hrq = hrq;
+		rqb_buffer->drq = drq;
+		list_add_tail(&rqb_buffer->hbuf.list, &rqb_buf_list);
+	}
+	while (!list_empty(&rqb_buf_list)) {
+		list_remove_head(&rqb_buf_list, rqb_buffer, struct rqb_dmabuf,
+				 hbuf.list);
+
+		hrqe.address_lo = putPaddrLow(rqb_buffer->hbuf.phys);
+		hrqe.address_hi = putPaddrHigh(rqb_buffer->hbuf.phys);
+		drqe.address_lo = putPaddrLow(rqb_buffer->dbuf.phys);
+		drqe.address_hi = putPaddrHigh(rqb_buffer->dbuf.phys);
+		rc = lpfc_sli4_rq_put(hrq, drq, &hrqe, &drqe);
+		if (rc < 0) {
+			(rqbp->rqb_free_buffer)(phba, rqb_buffer);
+		} else {
+			list_add_tail(&rqb_buffer->hbuf.list,
+				      &rqbp->rqb_buffer_list);
+			rqbp->buffer_count++;
 		}
-		kfree(phba->sli4_hba.hba_eq);
-		phba->sli4_hba.hba_eq = NULL;
 	}
+	return 1;
+}
 
-	if (phba->sli4_hba.fcp_cq != NULL) {
-		/* Release FCP completion queue */
-		for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++) {
-			if (phba->sli4_hba.fcp_cq[idx] != NULL) {
-				lpfc_sli4_queue_free(
-					phba->sli4_hba.fcp_cq[idx]);
-				phba->sli4_hba.fcp_cq[idx] = NULL;
-			}
-		}
-		kfree(phba->sli4_hba.fcp_cq);
-		phba->sli4_hba.fcp_cq = NULL;
+int
+lpfc_free_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *rq)
+{
+	struct lpfc_rqb *rqbp;
+	struct lpfc_dmabuf *h_buf;
+	struct rqb_dmabuf *rqb_buffer;
+
+	rqbp = rq->rqbp;
+	while (!list_empty(&rqbp->rqb_buffer_list)) {
+		list_remove_head(&rqbp->rqb_buffer_list, h_buf,
+				 struct lpfc_dmabuf, list);
+
+		rqb_buffer = container_of(h_buf, struct rqb_dmabuf, hbuf);
+		(rqbp->rqb_free_buffer)(phba, rqb_buffer);
+		rqbp->buffer_count--;
 	}
+	return 1;
+}
 
-	if (phba->sli4_hba.fcp_wq != NULL) {
-		/* Release FCP work queue */
-		for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++) {
-			if (phba->sli4_hba.fcp_wq[idx] != NULL) {
-				lpfc_sli4_queue_free(
-					phba->sli4_hba.fcp_wq[idx]);
-				phba->sli4_hba.fcp_wq[idx] = NULL;
-			}
-		}
-		kfree(phba->sli4_hba.fcp_wq);
-		phba->sli4_hba.fcp_wq = NULL;
+static int
+lpfc_create_wq_cq(struct lpfc_hba *phba, struct lpfc_queue *eq,
+	struct lpfc_queue *cq, struct lpfc_queue *wq, uint16_t *cq_map,
+	int qidx, uint32_t qtype)
+{
+	struct lpfc_sli_ring *pring;
+	int rc;
+
+	if (!eq || !cq || !wq) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+			"6085 Fast-path %s (%d) not allocated\n",
+			((eq) ? ((cq) ? "WQ" : "CQ") : "EQ"), qidx);
+		return -ENOMEM;
+	}
+
+	/* create the Cq first */
+	rc = lpfc_cq_create(phba, cq, eq,
+			(qtype == LPFC_MBOX) ? LPFC_MCQ : LPFC_WCQ, qtype);
+	if (rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+			"6086 Failed setup of CQ (%d), rc = 0x%x\n",
+			qidx, (uint32_t)rc);
+		return rc;
 	}
 
-	/* Release FCP CQ mapping array */
-	if (phba->sli4_hba.fcp_cq_map != NULL) {
-		kfree(phba->sli4_hba.fcp_cq_map);
-		phba->sli4_hba.fcp_cq_map = NULL;
-	}
+	if (qtype != LPFC_MBOX) {
+		/* Setup nvme_cq_map for fast lookup */
+		if (cq_map)
+			*cq_map = cq->queue_id;
 
-	/* Release mailbox command work queue */
-	if (phba->sli4_hba.mbx_wq != NULL) {
-		lpfc_sli4_queue_free(phba->sli4_hba.mbx_wq);
-		phba->sli4_hba.mbx_wq = NULL;
-	}
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+			"6087 CQ setup: cq[%d]-id=%d, parent eq[%d]-id=%d\n",
+			qidx, cq->queue_id, qidx, eq->queue_id);
 
-	/* Release ELS work queue */
-	if (phba->sli4_hba.els_wq != NULL) {
-		lpfc_sli4_queue_free(phba->sli4_hba.els_wq);
-		phba->sli4_hba.els_wq = NULL;
-	}
+		/* create the wq */
+		rc = lpfc_wq_create(phba, wq, cq, qtype);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"6123 Fail setup fastpath WQ (%d), rc = 0x%x\n",
+				qidx, (uint32_t)rc);
+			/* no need to tear down cq - caller will do so */
+			return rc;
+		}
 
-	/* Release unsolicited receive queue */
-	if (phba->sli4_hba.hdr_rq != NULL) {
-		lpfc_sli4_queue_free(phba->sli4_hba.hdr_rq);
-		phba->sli4_hba.hdr_rq = NULL;
-	}
-	if (phba->sli4_hba.dat_rq != NULL) {
-		lpfc_sli4_queue_free(phba->sli4_hba.dat_rq);
-		phba->sli4_hba.dat_rq = NULL;
-	}
+		/* Bind this CQ/WQ to the NVME ring */
+		pring = wq->pring;
+		pring->sli.sli4.wqp = (void *)wq;
+		cq->pring = pring;
 
-	/* Release ELS complete queue */
-	if (phba->sli4_hba.els_cq != NULL) {
-		lpfc_sli4_queue_free(phba->sli4_hba.els_cq);
-		phba->sli4_hba.els_cq = NULL;
-	}
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+			"2593 WQ setup: wq[%d]-id=%d assoc=%d, cq[%d]-id=%d\n",
+			qidx, wq->queue_id, wq->assoc_qid, qidx, cq->queue_id);
+	} else {
+		rc = lpfc_mq_create(phba, wq, cq, LPFC_MBOX);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0539 Failed setup of slow-path MQ: "
+				"rc = 0x%x\n", rc);
+			/* no need to tear down cq - caller will do so */
+			return rc;
+		}
 
-	/* Release mailbox command complete queue */
-	if (phba->sli4_hba.mbx_cq != NULL) {
-		lpfc_sli4_queue_free(phba->sli4_hba.mbx_cq);
-		phba->sli4_hba.mbx_cq = NULL;
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+			"2589 MBX MQ setup: wq-id=%d, parent cq-id=%d\n",
+			phba->sli4_hba.mbx_wq->queue_id,
+			phba->sli4_hba.mbx_cq->queue_id);
 	}
 
-	return;
+	return 0;
 }
 
 /**
@@ -7605,15 +8050,12 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 int
 lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *pring;
-	int rc = -ENOMEM;
-	int fcp_eqidx, fcp_cqidx, fcp_wqidx;
-	int fcp_cq_index = 0;
 	uint32_t shdr_status, shdr_add_status;
 	union lpfc_sli4_cfg_shdr *shdr;
 	LPFC_MBOXQ_t *mboxq;
-	uint32_t length;
+	int qidx;
+	uint32_t length, io_channel;
+	int rc = -ENOMEM;
 
 	/* Check for dual-ULP support */
 	mboxq = (LPFC_MBOXQ_t *)mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
@@ -7663,220 +8105,173 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 	/*
 	 * Set up HBA Event Queues (EQs)
 	 */
+	io_channel = phba->io_channel_irqs;
 
 	/* Set up HBA event queue */
-	if (phba->cfg_fcp_io_channel && !phba->sli4_hba.hba_eq) {
+	if (io_channel && !phba->sli4_hba.hba_eq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"3147 Fast-path EQs not allocated\n");
 		rc = -ENOMEM;
 		goto out_error;
 	}
-	for (fcp_eqidx = 0; fcp_eqidx < phba->cfg_fcp_io_channel; fcp_eqidx++) {
-		if (!phba->sli4_hba.hba_eq[fcp_eqidx]) {
+	for (qidx = 0; qidx < io_channel; qidx++) {
+		if (!phba->sli4_hba.hba_eq[qidx]) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"0522 Fast-path EQ (%d) not "
-					"allocated\n", fcp_eqidx);
+					"allocated\n", qidx);
 			rc = -ENOMEM;
-			goto out_destroy_hba_eq;
+			goto out_destroy;
 		}
-		rc = lpfc_eq_create(phba, phba->sli4_hba.hba_eq[fcp_eqidx],
-			 (phba->cfg_fcp_imax / phba->cfg_fcp_io_channel));
+		rc = lpfc_eq_create(phba, phba->sli4_hba.hba_eq[qidx],
+						phba->cfg_fcp_imax);
 		if (rc) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"0523 Failed setup of fast-path EQ "
-					"(%d), rc = 0x%x\n", fcp_eqidx,
+					"(%d), rc = 0x%x\n", qidx,
 					(uint32_t)rc);
-			goto out_destroy_hba_eq;
+			goto out_destroy;
 		}
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"2584 HBA EQ setup: "
-				"queue[%d]-id=%d\n", fcp_eqidx,
-				phba->sli4_hba.hba_eq[fcp_eqidx]->queue_id);
-	}
-
-	/* Set up fast-path FCP Response Complete Queue */
-	if (!phba->sli4_hba.fcp_cq) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"3148 Fast-path FCP CQ array not "
-				"allocated\n");
-		rc = -ENOMEM;
-		goto out_destroy_hba_eq;
+				"2584 HBA EQ setup: queue[%d]-id=%d\n",
+				qidx, phba->sli4_hba.hba_eq[qidx]->queue_id);
 	}
 
-	for (fcp_cqidx = 0; fcp_cqidx < phba->cfg_fcp_io_channel; fcp_cqidx++) {
-		if (!phba->sli4_hba.fcp_cq[fcp_cqidx]) {
+	if (phba->cfg_nvme_io_channel) {
+		if (!phba->sli4_hba.nvme_cq || !phba->sli4_hba.nvme_wq) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"0526 Fast-path FCP CQ (%d) not "
-					"allocated\n", fcp_cqidx);
+				"6084 Fast-path NVME %s array not allocated\n",
+				(phba->sli4_hba.nvme_cq) ? "CQ" : "WQ");
 			rc = -ENOMEM;
-			goto out_destroy_fcp_cq;
-		}
-		rc = lpfc_cq_create(phba, phba->sli4_hba.fcp_cq[fcp_cqidx],
-			phba->sli4_hba.hba_eq[fcp_cqidx], LPFC_WCQ, LPFC_FCP);
-		if (rc) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"0527 Failed setup of fast-path FCP "
-					"CQ (%d), rc = 0x%x\n", fcp_cqidx,
-					(uint32_t)rc);
-			goto out_destroy_fcp_cq;
+			goto out_destroy;
 		}
 
-		/* Setup fcp_cq_map for fast lookup */
-		phba->sli4_hba.fcp_cq_map[fcp_cqidx] =
-				phba->sli4_hba.fcp_cq[fcp_cqidx]->queue_id;
-
-		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"2588 FCP CQ setup: cq[%d]-id=%d, "
-				"parent seq[%d]-id=%d\n",
-				fcp_cqidx,
-				phba->sli4_hba.fcp_cq[fcp_cqidx]->queue_id,
-				fcp_cqidx,
-				phba->sli4_hba.hba_eq[fcp_cqidx]->queue_id);
-	}
-
-	/* Set up fast-path FCP Work Queue */
-	if (!phba->sli4_hba.fcp_wq) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"3149 Fast-path FCP WQ array not "
-				"allocated\n");
-		rc = -ENOMEM;
-		goto out_destroy_fcp_cq;
+		for (qidx = 0; qidx < phba->cfg_nvme_io_channel; qidx++) {
+			rc = lpfc_create_wq_cq(phba,
+					phba->sli4_hba.hba_eq[
+						qidx % io_channel],
+					phba->sli4_hba.nvme_cq[qidx],
+					phba->sli4_hba.nvme_wq[qidx],
+					&phba->sli4_hba.nvme_cq_map[qidx],
+					qidx, LPFC_NVME);
+			if (rc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6123 Failed to setup fastpath "
+					"NVME WQ/CQ (%d), rc = 0x%x\n",
+					qidx, (uint32_t)rc);
+				goto out_destroy;
+			}
+		}
 	}
 
-	for (fcp_wqidx = 0; fcp_wqidx < phba->cfg_fcp_io_channel; fcp_wqidx++) {
-		if (!phba->sli4_hba.fcp_wq[fcp_wqidx]) {
+	if (phba->cfg_fcp_io_channel) {
+		/* Set up fast-path FCP Response Complete Queue */
+		if (!phba->sli4_hba.fcp_cq || !phba->sli4_hba.fcp_wq) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"0534 Fast-path FCP WQ (%d) not "
-					"allocated\n", fcp_wqidx);
+				"3148 Fast-path FCP %s array not allocated\n",
+				phba->sli4_hba.fcp_cq ? "WQ" : "CQ");
 			rc = -ENOMEM;
-			goto out_destroy_fcp_wq;
-		}
-		rc = lpfc_wq_create(phba, phba->sli4_hba.fcp_wq[fcp_wqidx],
-				    phba->sli4_hba.fcp_cq[fcp_wqidx],
-				    LPFC_FCP);
-		if (rc) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"0535 Failed setup of fast-path FCP "
-					"WQ (%d), rc = 0x%x\n", fcp_wqidx,
-					(uint32_t)rc);
-			goto out_destroy_fcp_wq;
+			goto out_destroy;
 		}
 
-		/* Bind this WQ to the next FCP ring */
-		pring = &psli->ring[MAX_SLI3_CONFIGURED_RINGS + fcp_wqidx];
-		pring->sli.sli4.wqp = (void *)phba->sli4_hba.fcp_wq[fcp_wqidx];
-		phba->sli4_hba.fcp_cq[fcp_wqidx]->pring = pring;
-
-		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"2591 FCP WQ setup: wq[%d]-id=%d, "
-				"parent cq[%d]-id=%d\n",
-				fcp_wqidx,
-				phba->sli4_hba.fcp_wq[fcp_wqidx]->queue_id,
-				fcp_cq_index,
-				phba->sli4_hba.fcp_cq[fcp_wqidx]->queue_id);
+		for (qidx = 0; qidx < phba->cfg_fcp_io_channel; qidx++) {
+			rc = lpfc_create_wq_cq(phba,
+					phba->sli4_hba.hba_eq[
+						qidx % io_channel],
+					phba->sli4_hba.fcp_cq[qidx],
+					phba->sli4_hba.fcp_wq[qidx],
+					&phba->sli4_hba.fcp_cq_map[qidx],
+					qidx, LPFC_FCP);
+			if (rc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"0535 Failed to setup fastpath "
+					"FCP WQ/CQ (%d), rc = 0x%x\n",
+					qidx, (uint32_t)rc);
+				goto out_destroy;
+			}
+		}
 	}
+
 	/*
-	 * Set up Complete Queues (CQs)
+	 * Set up Slow Path Complete Queues (CQs)
 	 */
 
-	/* Set up slow-path MBOX Complete Queue as the first CQ */
-	if (!phba->sli4_hba.mbx_cq) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0528 Mailbox CQ not allocated\n");
-		rc = -ENOMEM;
-		goto out_destroy_fcp_wq;
-	}
-	rc = lpfc_cq_create(phba, phba->sli4_hba.mbx_cq,
-			phba->sli4_hba.hba_eq[0], LPFC_MCQ, LPFC_MBOX);
-	if (rc) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0529 Failed setup of slow-path mailbox CQ: "
-				"rc = 0x%x\n", (uint32_t)rc);
-		goto out_destroy_fcp_wq;
-	}
-	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-			"2585 MBX CQ setup: cq-id=%d, parent eq-id=%d\n",
-			phba->sli4_hba.mbx_cq->queue_id,
-			phba->sli4_hba.hba_eq[0]->queue_id);
+	/* Set up slow-path MBOX CQ/MQ */
 
-	/* Set up slow-path ELS Complete Queue */
-	if (!phba->sli4_hba.els_cq) {
+	if (!phba->sli4_hba.mbx_cq || !phba->sli4_hba.mbx_wq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0530 ELS CQ not allocated\n");
+				"0528 %s not allocated\n",
+				phba->sli4_hba.mbx_cq ?
+						"Mailbox WQ" : "Mailbox CQ");
 		rc = -ENOMEM;
-		goto out_destroy_mbx_cq;
+		goto out_destroy;
 	}
-	rc = lpfc_cq_create(phba, phba->sli4_hba.els_cq,
-			phba->sli4_hba.hba_eq[0], LPFC_WCQ, LPFC_ELS);
-	if (rc) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0531 Failed setup of slow-path ELS CQ: "
-				"rc = 0x%x\n", (uint32_t)rc);
-		goto out_destroy_mbx_cq;
-	}
-	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-			"2586 ELS CQ setup: cq-id=%d, parent eq-id=%d\n",
-			phba->sli4_hba.els_cq->queue_id,
-			phba->sli4_hba.hba_eq[0]->queue_id);
-
-	/*
-	 * Set up all the Work Queues (WQs)
-	 */
 
-	/* Set up Mailbox Command Queue */
-	if (!phba->sli4_hba.mbx_wq) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0538 Slow-path MQ not allocated\n");
-		rc = -ENOMEM;
-		goto out_destroy_els_cq;
-	}
-	rc = lpfc_mq_create(phba, phba->sli4_hba.mbx_wq,
-			    phba->sli4_hba.mbx_cq, LPFC_MBOX);
+	rc = lpfc_create_wq_cq(phba, phba->sli4_hba.hba_eq[0],
+					phba->sli4_hba.mbx_cq,
+					phba->sli4_hba.mbx_wq,
+					NULL, 0, LPFC_MBOX);
 	if (rc) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0539 Failed setup of slow-path MQ: "
-				"rc = 0x%x\n", rc);
-		goto out_destroy_els_cq;
+			"0529 Failed setup of mailbox WQ/CQ: rc = 0x%x\n",
+			(uint32_t)rc);
+		goto out_destroy;
 	}
-	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-			"2589 MBX MQ setup: wq-id=%d, parent cq-id=%d\n",
-			phba->sli4_hba.mbx_wq->queue_id,
-			phba->sli4_hba.mbx_cq->queue_id);
 
-	/* Set up slow-path ELS Work Queue */
-	if (!phba->sli4_hba.els_wq) {
+	/* Set up slow-path ELS WQ/CQ */
+	if (!phba->sli4_hba.els_cq || !phba->sli4_hba.els_wq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0536 Slow-path ELS WQ not allocated\n");
+				"0530 ELS %s not allocated\n",
+				phba->sli4_hba.els_cq ? "WQ" : "CQ");
 		rc = -ENOMEM;
-		goto out_destroy_mbx_wq;
+		goto out_destroy;
 	}
-	rc = lpfc_wq_create(phba, phba->sli4_hba.els_wq,
-			    phba->sli4_hba.els_cq, LPFC_ELS);
+	rc = lpfc_create_wq_cq(phba, phba->sli4_hba.hba_eq[0],
+					phba->sli4_hba.els_cq,
+					phba->sli4_hba.els_wq,
+					NULL, 0, LPFC_ELS);
 	if (rc) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"0537 Failed setup of slow-path ELS WQ: "
-				"rc = 0x%x\n", (uint32_t)rc);
-		goto out_destroy_mbx_wq;
+			"0529 Failed setup of ELS WQ/CQ: rc = 0x%x\n",
+			(uint32_t)rc);
+		goto out_destroy;
 	}
-
-	/* Bind this WQ to the ELS ring */
-	pring = &psli->ring[LPFC_ELS_RING];
-	pring->sli.sli4.wqp = (void *)phba->sli4_hba.els_wq;
-	phba->sli4_hba.els_cq->pring = pring;
-
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 			"2590 ELS WQ setup: wq-id=%d, parent cq-id=%d\n",
 			phba->sli4_hba.els_wq->queue_id,
 			phba->sli4_hba.els_cq->queue_id);
 
-	/*
-	 * Create Receive Queue (RQ)
-	 */
+	if (phba->cfg_nvme_io_channel) {
+		/* Set up NVME LS Complete Queue */
+		if (!phba->sli4_hba.nvmels_cq || !phba->sli4_hba.nvmels_wq) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6091 LS %s not allocated\n",
+					phba->sli4_hba.nvmels_cq ? "WQ" : "CQ");
+			rc = -ENOMEM;
+			goto out_destroy;
+		}
+		rc = lpfc_create_wq_cq(phba, phba->sli4_hba.hba_eq[0],
+					phba->sli4_hba.nvmels_cq,
+					phba->sli4_hba.nvmels_wq,
+					NULL, 0, LPFC_NVME_LS);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0529 Failed setup of NVVME LS WQ/CQ: "
+				"rc = 0x%x\n", (uint32_t)rc);
+			goto out_destroy;
+		}
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"6096 ELS WQ setup: wq-id=%d, "
+				"parent cq-id=%d\n",
+				phba->sli4_hba.nvmels_wq->queue_id,
+				phba->sli4_hba.nvmels_cq->queue_id);
+	}
+
 	if (!phba->sli4_hba.hdr_rq || !phba->sli4_hba.dat_rq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"0540 Receive Queue not allocated\n");
 		rc = -ENOMEM;
-		goto out_destroy_els_wq;
+		goto out_destroy;
 	}
 
 	lpfc_rq_adjust_repost(phba, phba->sli4_hba.hdr_rq, LPFC_ELS_HBQ);
@@ -7888,7 +8283,7 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"0541 Failed setup of Receive Queue: "
 				"rc = 0x%x\n", (uint32_t)rc);
-		goto out_destroy_fcp_wq;
+		goto out_destroy;
 	}
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
@@ -7904,7 +8299,7 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"0549 Failed setup of FOF Queues: "
 					"rc = 0x%x\n", rc);
-			goto out_destroy_els_rq;
+			goto out_destroy;
 		}
 	}
 
@@ -7912,30 +8307,12 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 	 * Configure EQ delay multipier for interrupt coalescing using
 	 * MODIFY_EQ_DELAY for all EQs created, LPFC_MAX_EQ_DELAY at a time.
 	 */
-	for (fcp_eqidx = 0; fcp_eqidx < phba->cfg_fcp_io_channel;
-			fcp_eqidx += LPFC_MAX_EQ_DELAY)
-		lpfc_modify_fcp_eq_delay(phba, fcp_eqidx);
+	for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY)
+		lpfc_modify_hba_eq_delay(phba, qidx);
 	return 0;
 
-out_destroy_els_rq:
-	lpfc_rq_destroy(phba, phba->sli4_hba.hdr_rq, phba->sli4_hba.dat_rq);
-out_destroy_els_wq:
-	lpfc_wq_destroy(phba, phba->sli4_hba.els_wq);
-out_destroy_mbx_wq:
-	lpfc_mq_destroy(phba, phba->sli4_hba.mbx_wq);
-out_destroy_els_cq:
-	lpfc_cq_destroy(phba, phba->sli4_hba.els_cq);
-out_destroy_mbx_cq:
-	lpfc_cq_destroy(phba, phba->sli4_hba.mbx_cq);
-out_destroy_fcp_wq:
-	for (--fcp_wqidx; fcp_wqidx >= 0; fcp_wqidx--)
-		lpfc_wq_destroy(phba, phba->sli4_hba.fcp_wq[fcp_wqidx]);
-out_destroy_fcp_cq:
-	for (--fcp_cqidx; fcp_cqidx >= 0; fcp_cqidx--)
-		lpfc_cq_destroy(phba, phba->sli4_hba.fcp_cq[fcp_cqidx]);
-out_destroy_hba_eq:
-	for (--fcp_eqidx; fcp_eqidx >= 0; fcp_eqidx--)
-		lpfc_eq_destroy(phba, phba->sli4_hba.hba_eq[fcp_eqidx]);
+out_destroy:
+	lpfc_sli4_queue_unset(phba);
 out_error:
 	return rc;
 }
@@ -7955,39 +8332,66 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 void
 lpfc_sli4_queue_unset(struct lpfc_hba *phba)
 {
-	int fcp_qidx;
+	int qidx;
 
 	/* Unset the queues created for Flash Optimized Fabric operations */
 	if (phba->cfg_fof)
 		lpfc_fof_queue_destroy(phba);
+
 	/* Unset mailbox command work queue */
-	lpfc_mq_destroy(phba, phba->sli4_hba.mbx_wq);
+	if (phba->sli4_hba.mbx_wq)
+		lpfc_mq_destroy(phba, phba->sli4_hba.mbx_wq);
+
+	/* Unset NVME LS work queue */
+	if (phba->sli4_hba.nvmels_wq)
+		lpfc_wq_destroy(phba, phba->sli4_hba.nvmels_wq);
+
 	/* Unset ELS work queue */
-	lpfc_wq_destroy(phba, phba->sli4_hba.els_wq);
+	if (phba->sli4_hba.els_cq)
+		lpfc_wq_destroy(phba, phba->sli4_hba.els_wq);
+
 	/* Unset unsolicited receive queue */
-	lpfc_rq_destroy(phba, phba->sli4_hba.hdr_rq, phba->sli4_hba.dat_rq);
+	if (phba->sli4_hba.hdr_rq)
+		lpfc_rq_destroy(phba, phba->sli4_hba.hdr_rq,
+				phba->sli4_hba.dat_rq);
+
 	/* Unset FCP work queue */
-	if (phba->sli4_hba.fcp_wq) {
-		for (fcp_qidx = 0; fcp_qidx < phba->cfg_fcp_io_channel;
-		     fcp_qidx++)
-			lpfc_wq_destroy(phba, phba->sli4_hba.fcp_wq[fcp_qidx]);
+	if (phba->sli4_hba.fcp_wq)
+		for (qidx = 0; qidx < phba->cfg_fcp_io_channel; qidx++)
+			lpfc_wq_destroy(phba, phba->sli4_hba.fcp_wq[qidx]);
+
+	/* Unset NVME work queue */
+	if (phba->sli4_hba.nvme_wq) {
+		for (qidx = 0; qidx < phba->cfg_nvme_io_channel; qidx++)
+			lpfc_wq_destroy(phba, phba->sli4_hba.nvme_wq[qidx]);
 	}
+
 	/* Unset mailbox command complete queue */
-	lpfc_cq_destroy(phba, phba->sli4_hba.mbx_cq);
+	if (phba->sli4_hba.mbx_cq)
+		lpfc_cq_destroy(phba, phba->sli4_hba.mbx_cq);
+
 	/* Unset ELS complete queue */
-	lpfc_cq_destroy(phba, phba->sli4_hba.els_cq);
+	if (phba->sli4_hba.els_cq)
+		lpfc_cq_destroy(phba, phba->sli4_hba.els_cq);
+
+	/* Unset NVME LS complete queue */
+	if (phba->sli4_hba.nvmels_cq)
+		lpfc_cq_destroy(phba, phba->sli4_hba.nvmels_cq);
+
+	/* Unset NVME response complete queue */
+	if (phba->sli4_hba.nvme_cq)
+		for (qidx = 0; qidx < phba->cfg_nvme_io_channel; qidx++)
+			lpfc_cq_destroy(phba, phba->sli4_hba.nvme_cq[qidx]);
+
 	/* Unset FCP response complete queue */
-	if (phba->sli4_hba.fcp_cq) {
-		for (fcp_qidx = 0; fcp_qidx < phba->cfg_fcp_io_channel;
-		     fcp_qidx++)
-			lpfc_cq_destroy(phba, phba->sli4_hba.fcp_cq[fcp_qidx]);
-	}
+	if (phba->sli4_hba.fcp_cq)
+		for (qidx = 0; qidx < phba->cfg_fcp_io_channel; qidx++)
+			lpfc_cq_destroy(phba, phba->sli4_hba.fcp_cq[qidx]);
+
 	/* Unset fast-path event queue */
-	if (phba->sli4_hba.hba_eq) {
-		for (fcp_qidx = 0; fcp_qidx < phba->cfg_fcp_io_channel;
-		     fcp_qidx++)
-			lpfc_eq_destroy(phba, phba->sli4_hba.hba_eq[fcp_qidx]);
-	}
+	if (phba->sli4_hba.hba_eq)
+		for (qidx = 0; qidx < phba->io_channel_irqs; qidx++)
+			lpfc_eq_destroy(phba, phba->sli4_hba.hba_eq[qidx]);
 }
 
 /**
@@ -8697,91 +9101,33 @@ lpfc_sli_disable_intr(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_find_next_cpu - Find next available CPU that matches the phys_id
+ * lpfc_cpu_affinity_check - Check vector CPU affinity mappings
  * @phba: pointer to lpfc hba data structure.
- *
- * Find next available CPU to use for IRQ to CPU affinity.
+ * @vectors: number of msix vectors allocated.
+ *
+ * The routine will figure out the CPU affinity assignment for every
+ * MSI-X vector allocated for the HBA.  The hba_eq_hdl will be updated
+ * with a pointer to the CPU mask that defines ALL the CPUs this vector
+ * can be associated with. If the vector can be unquely associated with
+ * a single CPU, that CPU will be recorded in hba_eq_hdl[index].cpu.
+ * In addition, the CPU to IO channel mapping will be calculated
+ * and the phba->sli4_hba.cpu_map array will reflect this.
  */
-static int
-lpfc_find_next_cpu(struct lpfc_hba *phba, uint32_t phys_id)
+static void
+lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 {
 	struct lpfc_vector_map_info *cpup;
+	int index = 0;
+	int vec = 0;
 	int cpu;
-
-	cpup = phba->sli4_hba.cpu_map;
-	for (cpu = 0; cpu < phba->sli4_hba.num_present_cpu; cpu++) {
-		/* CPU must be online */
-		if (cpu_online(cpu)) {
-			if ((cpup->irq == LPFC_VECTOR_MAP_EMPTY) &&
-			    (lpfc_used_cpu[cpu] == LPFC_VECTOR_MAP_EMPTY) &&
-			    (cpup->phys_id == phys_id)) {
-				return cpu;
-			}
-		}
-		cpup++;
-	}
-
-	/*
-	 * If we get here, we have used ALL CPUs for the specific
-	 * phys_id. Now we need to clear out lpfc_used_cpu and start
-	 * reusing CPUs.
-	 */
-
-	for (cpu = 0; cpu < phba->sli4_hba.num_present_cpu; cpu++) {
-		if (lpfc_used_cpu[cpu] == phys_id)
-			lpfc_used_cpu[cpu] = LPFC_VECTOR_MAP_EMPTY;
-	}
-
-	cpup = phba->sli4_hba.cpu_map;
-	for (cpu = 0; cpu < phba->sli4_hba.num_present_cpu; cpu++) {
-		/* CPU must be online */
-		if (cpu_online(cpu)) {
-			if ((cpup->irq == LPFC_VECTOR_MAP_EMPTY) &&
-			    (cpup->phys_id == phys_id)) {
-				return cpu;
-			}
-		}
-		cpup++;
-	}
-	return LPFC_VECTOR_MAP_EMPTY;
-}
-
-/**
- * lpfc_sli4_set_affinity - Set affinity for HBA IRQ vectors
- * @phba:	pointer to lpfc hba data structure.
- * @vectors:	number of HBA vectors
- *
- * Affinitize MSIX IRQ vectors to CPUs. Try to equally spread vector
- * affinization across multple physical CPUs (numa nodes).
- * In addition, this routine will assign an IO channel for each CPU
- * to use when issuing I/Os.
- */
-static int
-lpfc_sli4_set_affinity(struct lpfc_hba *phba, int vectors)
-{
-	int i, idx, saved_chann, used_chann, cpu, phys_id;
-	int max_phys_id, min_phys_id;
-	int num_io_channel, first_cpu, chan;
-	struct lpfc_vector_map_info *cpup;
 #ifdef CONFIG_X86
 	struct cpuinfo_x86 *cpuinfo;
 #endif
-	uint8_t chann[LPFC_FCP_IO_CHAN_MAX+1];
-
-	/* If there is no mapping, just return */
-	if (!phba->cfg_fcp_cpu_map)
-		return 1;
 
 	/* Init cpu_map array */
 	memset(phba->sli4_hba.cpu_map, 0xff,
 	       (sizeof(struct lpfc_vector_map_info) *
-		phba->sli4_hba.num_present_cpu));
-
-	max_phys_id = 0;
-	min_phys_id = 0xff;
-	phys_id = 0;
-	num_io_channel = 0;
-	first_cpu = LPFC_VECTOR_MAP_EMPTY;
+	       phba->sli4_hba.num_present_cpu));
 
 	/* Update CPU map with physical id and core id of each CPU */
 	cpup = phba->sli4_hba.cpu_map;
@@ -8795,184 +9141,16 @@ lpfc_sli4_set_affinity(struct lpfc_hba *phba, int vectors)
 		cpup->phys_id = 0;
 		cpup->core_id = 0;
 #endif
-
-		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"3328 CPU physid %d coreid %d\n",
-				cpup->phys_id, cpup->core_id);
-
-		if (cpup->phys_id > max_phys_id)
-			max_phys_id = cpup->phys_id;
-		if (cpup->phys_id < min_phys_id)
-			min_phys_id = cpup->phys_id;
+		cpup->channel_id = index;  /* For now round robin */
+		cpup->irq = pci_irq_vector(phba->pcidev, vec);
+		vec++;
+		if (vec >= vectors)
+			vec = 0;
+		index++;
+		if (index >= phba->cfg_fcp_io_channel)
+			index = 0;
 		cpup++;
 	}
-
-	phys_id = min_phys_id;
-	/* Now associate the HBA vectors with specific CPUs */
-	for (idx = 0; idx < vectors; idx++) {
-		cpup = phba->sli4_hba.cpu_map;
-		cpu = lpfc_find_next_cpu(phba, phys_id);
-		if (cpu == LPFC_VECTOR_MAP_EMPTY) {
-
-			/* Try for all phys_id's */
-			for (i = 1; i < max_phys_id; i++) {
-				phys_id++;
-				if (phys_id > max_phys_id)
-					phys_id = min_phys_id;
-				cpu = lpfc_find_next_cpu(phba, phys_id);
-				if (cpu == LPFC_VECTOR_MAP_EMPTY)
-					continue;
-				goto found;
-			}
-
-			/* Use round robin for scheduling */
-			phba->cfg_fcp_io_sched = LPFC_FCP_SCHED_ROUND_ROBIN;
-			chan = 0;
-			cpup = phba->sli4_hba.cpu_map;
-			for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) {
-				cpup->channel_id = chan;
-				cpup++;
-				chan++;
-				if (chan >= phba->cfg_fcp_io_channel)
-					chan = 0;
-			}
-
-			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"3329 Cannot set affinity:"
-					"Error mapping vector %d (%d)\n",
-					idx, vectors);
-			return 0;
-		}
-found:
-		cpup += cpu;
-		if (phba->cfg_fcp_cpu_map == LPFC_DRIVER_CPU_MAP)
-			lpfc_used_cpu[cpu] = phys_id;
-
-		/* Associate vector with selected CPU */
-		cpup->irq = pci_irq_vector(phba->pcidev, idx);
-
-		/* Associate IO channel with selected CPU */
-		cpup->channel_id = idx;
-		num_io_channel++;
-
-		if (first_cpu == LPFC_VECTOR_MAP_EMPTY)
-			first_cpu = cpu;
-
-		/* Now affinitize to the selected CPU */
-		i = irq_set_affinity_hint(pci_irq_vector(phba->pcidev, idx),
-					  get_cpu_mask(cpu));
-
-		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"3330 Set Affinity: CPU %d channel %d "
-				"irq %d (%x)\n",
-				cpu, cpup->channel_id,
-				pci_irq_vector(phba->pcidev, idx), i);
-
-		/* Spread vector mapping across multple physical CPU nodes */
-		phys_id++;
-		if (phys_id > max_phys_id)
-			phys_id = min_phys_id;
-	}
-
-	/*
-	 * Finally fill in the IO channel for any remaining CPUs.
-	 * At this point, all IO channels have been assigned to a specific
-	 * MSIx vector, mapped to a specific CPU.
-	 * Base the remaining IO channel assigned, to IO channels already
-	 * assigned to other CPUs on the same phys_id.
-	 */
-	for (i = min_phys_id; i <= max_phys_id; i++) {
-		/*
-		 * If there are no io channels already mapped to
-		 * this phys_id, just round robin thru the io_channels.
-		 * Setup chann[] for round robin.
-		 */
-		for (idx = 0; idx < phba->cfg_fcp_io_channel; idx++)
-			chann[idx] = idx;
-
-		saved_chann = 0;
-		used_chann = 0;
-
-		/*
-		 * First build a list of IO channels already assigned
-		 * to this phys_id before reassigning the same IO
-		 * channels to the remaining CPUs.
-		 */
-		cpup = phba->sli4_hba.cpu_map;
-		cpu = first_cpu;
-		cpup += cpu;
-		for (idx = 0; idx < phba->sli4_hba.num_present_cpu;
-		     idx++) {
-			if (cpup->phys_id == i) {
-				/*
-				 * Save any IO channels that are
-				 * already mapped to this phys_id.
-				 */
-				if (cpup->irq != LPFC_VECTOR_MAP_EMPTY) {
-					if (saved_chann <=
-					    LPFC_FCP_IO_CHAN_MAX) {
-						chann[saved_chann] =
-							cpup->channel_id;
-						saved_chann++;
-					}
-					goto out;
-				}
-
-				/* See if we are using round-robin */
-				if (saved_chann == 0)
-					saved_chann =
-						phba->cfg_fcp_io_channel;
-
-				/* Associate next IO channel with CPU */
-				cpup->channel_id = chann[used_chann];
-				num_io_channel++;
-				used_chann++;
-				if (used_chann == saved_chann)
-					used_chann = 0;
-
-				lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-						"3331 Set IO_CHANN "
-						"CPU %d channel %d\n",
-						idx, cpup->channel_id);
-			}
-out:
-			cpu++;
-			if (cpu >= phba->sli4_hba.num_present_cpu) {
-				cpup = phba->sli4_hba.cpu_map;
-				cpu = 0;
-			} else {
-				cpup++;
-			}
-		}
-	}
-
-	if (phba->sli4_hba.num_online_cpu != phba->sli4_hba.num_present_cpu) {
-		cpup = phba->sli4_hba.cpu_map;
-		for (idx = 0; idx < phba->sli4_hba.num_present_cpu; idx++) {
-			if (cpup->channel_id == LPFC_VECTOR_MAP_EMPTY) {
-				cpup->channel_id = 0;
-				num_io_channel++;
-
-				lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-						"3332 Assign IO_CHANN "
-						"CPU %d channel %d\n",
-						idx, cpup->channel_id);
-			}
-			cpup++;
-		}
-	}
-
-	/* Sanity check */
-	if (num_io_channel != phba->sli4_hba.num_present_cpu)
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"3333 Set affinity mismatch:"
-				"%d chann != %d cpus: %d vectors\n",
-				num_io_channel, phba->sli4_hba.num_present_cpu,
-				vectors);
-
-	/* Enable using cpu affinity for scheduling */
-	phba->cfg_fcp_io_sched = LPFC_FCP_SCHED_BY_CPU;
-	return 1;
 }
 
 
@@ -8993,11 +9171,12 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 	int vectors, rc, index;
 
 	/* Set up MSI-X multi-message vectors */
-	vectors = phba->cfg_fcp_io_channel;
+	vectors = phba->io_channel_irqs;
 	if (phba->cfg_fof)
 		vectors++;
 
-	rc = pci_alloc_irq_vectors(phba->pcidev, 2, vectors, PCI_IRQ_MSIX);
+	rc = pci_alloc_irq_vectors(phba->pcidev, 2, vectors,
+				PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
 	if (rc < 0) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0484 PCI enable MSI-X failed (%d)\n", rc);
@@ -9012,19 +9191,19 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 			 LPFC_SLI4_HANDLER_NAME_SZ,
 			 LPFC_DRIVER_HANDLER_NAME"%d", index);
 
-		phba->sli4_hba.fcp_eq_hdl[index].idx = index;
-		phba->sli4_hba.fcp_eq_hdl[index].phba = phba;
-		atomic_set(&phba->sli4_hba.fcp_eq_hdl[index].fcp_eq_in_use, 1);
+		phba->sli4_hba.hba_eq_hdl[index].idx = index;
+		phba->sli4_hba.hba_eq_hdl[index].phba = phba;
+		atomic_set(&phba->sli4_hba.hba_eq_hdl[index].hba_eq_in_use, 1);
 		if (phba->cfg_fof && (index == (vectors - 1)))
 			rc = request_irq(pci_irq_vector(phba->pcidev, index),
 				 &lpfc_sli4_fof_intr_handler, 0,
 				 (char *)&phba->sli4_hba.handler_name[index],
-				 &phba->sli4_hba.fcp_eq_hdl[index]);
+				 &phba->sli4_hba.hba_eq_hdl[index]);
 		else
 			rc = request_irq(pci_irq_vector(phba->pcidev, index),
 				 &lpfc_sli4_hba_intr_handler, 0,
 				 (char *)&phba->sli4_hba.handler_name[index],
-				 &phba->sli4_hba.fcp_eq_hdl[index]);
+				 &phba->sli4_hba.hba_eq_hdl[index]);
 		if (rc) {
 			lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
 					"0486 MSI-X fast-path (%d) "
@@ -9036,26 +9215,29 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 	if (phba->cfg_fof)
 		vectors--;
 
-	if (vectors != phba->cfg_fcp_io_channel) {
+	if (vectors != phba->io_channel_irqs) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"3238 Reducing IO channels to match number of "
 				"MSI-X vectors, requested %d got %d\n",
-				phba->cfg_fcp_io_channel, vectors);
-		phba->cfg_fcp_io_channel = vectors;
+				phba->io_channel_irqs, vectors);
+		if (phba->cfg_fcp_io_channel > vectors)
+			phba->cfg_fcp_io_channel = vectors;
+		if (phba->cfg_nvme_io_channel > vectors)
+			phba->cfg_nvme_io_channel = vectors;
+		if (phba->cfg_fcp_io_channel > phba->cfg_nvme_io_channel)
+			phba->io_channel_irqs = phba->cfg_fcp_io_channel;
+		else
+			phba->io_channel_irqs = phba->cfg_nvme_io_channel;
 	}
+	lpfc_cpu_affinity_check(phba, vectors);
 
-	if (!shost_use_blk_mq(lpfc_shost_from_vport(phba->pport)))
-		lpfc_sli4_set_affinity(phba, vectors);
 	return rc;
 
 cfg_fail_out:
 	/* free the irq already requested */
-	for (--index; index >= 0; index--) {
-		int irq = pci_irq_vector(phba->pcidev, index);
-
-		irq_set_affinity_hint(irq, NULL);
-		free_irq(irq, &phba->sli4_hba.fcp_eq_hdl[index]);
-	}
+	for (--index; index >= 0; index--)
+		free_irq(pci_irq_vector(phba->pcidev, index),
+				&phba->sli4_hba.hba_eq_hdl[index]);
 
 	/* Unconfigure MSI-X capability structure */
 	pci_free_irq_vectors(phba->pcidev);
@@ -9102,14 +9284,14 @@ lpfc_sli4_enable_msi(struct lpfc_hba *phba)
 		return rc;
 	}
 
-	for (index = 0; index < phba->cfg_fcp_io_channel; index++) {
-		phba->sli4_hba.fcp_eq_hdl[index].idx = index;
-		phba->sli4_hba.fcp_eq_hdl[index].phba = phba;
+	for (index = 0; index < phba->io_channel_irqs; index++) {
+		phba->sli4_hba.hba_eq_hdl[index].idx = index;
+		phba->sli4_hba.hba_eq_hdl[index].phba = phba;
 	}
 
 	if (phba->cfg_fof) {
-		phba->sli4_hba.fcp_eq_hdl[index].idx = index;
-		phba->sli4_hba.fcp_eq_hdl[index].phba = phba;
+		phba->sli4_hba.hba_eq_hdl[index].idx = index;
+		phba->sli4_hba.hba_eq_hdl[index].phba = phba;
 	}
 	return 0;
 }
@@ -9134,7 +9316,7 @@ static uint32_t
 lpfc_sli4_enable_intr(struct lpfc_hba *phba, uint32_t cfg_mode)
 {
 	uint32_t intr_mode = LPFC_INTR_ERROR;
-	int retval, index;
+	int retval, idx;
 
 	if (cfg_mode == 2) {
 		/* Preparation before conf_msi mbox cmd */
@@ -9165,21 +9347,23 @@ lpfc_sli4_enable_intr(struct lpfc_hba *phba, uint32_t cfg_mode)
 		retval = request_irq(phba->pcidev->irq, lpfc_sli4_intr_handler,
 				     IRQF_SHARED, LPFC_DRIVER_NAME, phba);
 		if (!retval) {
+			struct lpfc_hba_eq_hdl *eqhdl;
+
 			/* Indicate initialization to INTx mode */
 			phba->intr_type = INTx;
 			intr_mode = 0;
-			for (index = 0; index < phba->cfg_fcp_io_channel;
-			     index++) {
-				phba->sli4_hba.fcp_eq_hdl[index].idx = index;
-				phba->sli4_hba.fcp_eq_hdl[index].phba = phba;
-				atomic_set(&phba->sli4_hba.fcp_eq_hdl[index].
-					fcp_eq_in_use, 1);
+
+			for (idx = 0; idx < phba->io_channel_irqs; idx++) {
+				eqhdl = &phba->sli4_hba.hba_eq_hdl[idx];
+				eqhdl->idx = idx;
+				eqhdl->phba = phba;
+				atomic_set(&eqhdl->hba_eq_in_use, 1);
 			}
 			if (phba->cfg_fof) {
-				phba->sli4_hba.fcp_eq_hdl[index].idx = index;
-				phba->sli4_hba.fcp_eq_hdl[index].phba = phba;
-				atomic_set(&phba->sli4_hba.fcp_eq_hdl[index].
-					fcp_eq_in_use, 1);
+				eqhdl = &phba->sli4_hba.hba_eq_hdl[idx];
+				eqhdl->idx = idx;
+				eqhdl->phba = phba;
+				atomic_set(&eqhdl->hba_eq_in_use, 1);
 			}
 		}
 	}
@@ -9203,15 +9387,13 @@ lpfc_sli4_disable_intr(struct lpfc_hba *phba)
 		int index;
 
 		/* Free up MSI-X multi-message vectors */
-		for (index = 0; index < phba->cfg_fcp_io_channel; index++) {
-			int irq = pci_irq_vector(phba->pcidev, index);
-
-			irq_set_affinity_hint(irq, NULL);
-			free_irq(irq, &phba->sli4_hba.fcp_eq_hdl[index]);
-		}
+		for (index = 0; index < phba->io_channel_irqs; index++)
+			free_irq(pci_irq_vector(phba->pcidev, index),
+					&phba->sli4_hba.hba_eq_hdl[index]);
 
 		if (phba->cfg_fof)
-			free_irq(pci_irq_vector(phba->pcidev, index), phba);
+			free_irq(pci_irq_vector(phba->pcidev, index),
+					&phba->sli4_hba.hba_eq_hdl[index]);
 	} else {
 		free_irq(phba->pcidev->irq, phba);
 	}
@@ -9273,11 +9455,24 @@ static void
 lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 {
 	int wait_time = 0;
-	int fcp_xri_cmpl = list_empty(&phba->sli4_hba.lpfc_abts_scsi_buf_list);
+	int nvme_xri_cmpl = 1;
+	int fcp_xri_cmpl = 1;
 	int els_xri_cmpl = list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
 
-	while (!fcp_xri_cmpl || !els_xri_cmpl) {
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
+		fcp_xri_cmpl =
+			list_empty(&phba->sli4_hba.lpfc_abts_scsi_buf_list);
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+		nvme_xri_cmpl =
+			list_empty(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+
+	while (!fcp_xri_cmpl || !els_xri_cmpl || !nvme_xri_cmpl) {
 		if (wait_time > LPFC_XRI_EXCH_BUSY_WAIT_TMO) {
+			if (!nvme_xri_cmpl)
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6100 NVME XRI exchange busy "
+						"wait time: %d seconds.\n",
+						wait_time/1000);
 			if (!fcp_xri_cmpl)
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"2877 FCP XRI exchange busy "
@@ -9294,8 +9489,14 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 			msleep(LPFC_XRI_EXCH_BUSY_WAIT_T1);
 			wait_time += LPFC_XRI_EXCH_BUSY_WAIT_T1;
 		}
-		fcp_xri_cmpl =
-			list_empty(&phba->sli4_hba.lpfc_abts_scsi_buf_list);
+		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+			nvme_xri_cmpl = list_empty(
+				&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+
+		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
+			fcp_xri_cmpl = list_empty(
+				&phba->sli4_hba.lpfc_abts_scsi_buf_list);
+
 		els_xri_cmpl =
 			list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
 	}
@@ -9509,10 +9710,31 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	sli4_params->wqsize = bf_get(cfg_wqsize, mbx_sli4_parameters);
 	sli4_params->sgl_pages_max = bf_get(cfg_sgl_page_cnt,
 					    mbx_sli4_parameters);
+	sli4_params->wqpcnt = bf_get(cfg_wqpcnt, mbx_sli4_parameters);
 	sli4_params->sgl_pp_align = bf_get(cfg_sgl_pp_align,
 					   mbx_sli4_parameters);
 	phba->sli4_hba.extents_in_use = bf_get(cfg_ext, mbx_sli4_parameters);
 	phba->sli4_hba.rpi_hdrs_in_use = bf_get(cfg_hdrr, mbx_sli4_parameters);
+	phba->nvme_support = (bf_get(cfg_nvme, mbx_sli4_parameters) &&
+			      bf_get(cfg_xib, mbx_sli4_parameters));
+
+	if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP) ||
+	    !phba->nvme_support) {
+		phba->nvme_support = 0;
+		phba->nvmet_support = 0;
+		phba->cfg_nvme_io_channel = 0;
+		phba->io_channel_irqs = phba->cfg_fcp_io_channel;
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT | LOG_NVME,
+				"6101 Disabling NVME support: "
+				"Not supported by firmware: %d %d\n",
+				bf_get(cfg_nvme, mbx_sli4_parameters),
+				bf_get(cfg_xib, mbx_sli4_parameters));
+
+		/* If firmware doesn't support NVME, just use SCSI support */
+		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
+			return -ENODEV;
+		phba->cfg_enable_fc4_type = LPFC_ENABLE_FCP;
+	}
 
 	/* Make sure that sge_supp_len can be handled by the driver */
 	if (sli4_params->sge_supp_len > LPFC_MAX_SGE_SIZE)
@@ -9587,14 +9809,6 @@ lpfc_pci_probe_one_s3(struct pci_dev *pdev, const struct pci_device_id *pid)
 		goto out_disable_pci_dev;
 	}
 
-	/* Set up phase-1 common device driver resources */
-	error = lpfc_setup_driver_resource_phase1(phba);
-	if (error) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"1403 Failed to set up driver resource.\n");
-		goto out_unset_pci_mem_s3;
-	}
-
 	/* Set up SLI-3 specific device driver resources */
 	error = lpfc_sli_driver_resource_setup(phba);
 	if (error) {
@@ -10169,6 +10383,21 @@ lpfc_sli4_get_els_iocb_cnt(struct lpfc_hba *phba)
 		return 0;
 }
 
+/**
+ * lpfc_sli4_get_iocb_cnt - Calculate the # of total IOCBs to reserve
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * returns the number of ELS/CT
+ **/
+int
+lpfc_sli4_get_iocb_cnt(struct lpfc_hba *phba)
+{
+	int max_xri = lpfc_sli4_get_els_iocb_cnt(phba);
+
+	return max_xri;
+}
+
+
 /**
  * lpfc_write_firmware - attempt to write a firmware image to the port
  * @fw: pointer to firmware image returned from request_firmware.
@@ -10333,7 +10562,6 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	struct Scsi_Host  *shost = NULL;
 	int error;
 	uint32_t cfg_mode, intr_mode;
-	int adjusted_fcp_io_channel;
 
 	/* Allocate memory for HBA structure */
 	phba = lpfc_hba_alloc(pdev);
@@ -10358,14 +10586,6 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 		goto out_disable_pci_dev;
 	}
 
-	/* Set up phase-1 common device driver resources */
-	error = lpfc_setup_driver_resource_phase1(phba);
-	if (error) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"1411 Failed to set up driver resource.\n");
-		goto out_unset_pci_mem_s4;
-	}
-
 	/* Set up SLI-4 Specific device driver resources */
 	error = lpfc_sli4_driver_resource_setup(phba);
 	if (error) {
@@ -10424,6 +10644,7 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 
 	/* Put device to a known state before enabling interrupt */
 	lpfc_stop_port(phba);
+
 	/* Configure and enable interrupt */
 	intr_mode = lpfc_sli4_enable_intr(phba, cfg_mode);
 	if (intr_mode == LPFC_INTR_ERROR) {
@@ -10433,11 +10654,15 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 		goto out_free_sysfs_attr;
 	}
 	/* Default to single EQ for non-MSI-X */
-	if (phba->intr_type != MSIX)
-		adjusted_fcp_io_channel = 1;
-	else
-		adjusted_fcp_io_channel = phba->cfg_fcp_io_channel;
-	phba->cfg_fcp_io_channel = adjusted_fcp_io_channel;
+	if (phba->intr_type != MSIX) {
+		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
+			phba->cfg_fcp_io_channel = 1;
+		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+			phba->cfg_nvme_io_channel = 1;
+		phba->io_channel_irqs = 1;
+	}
+
+
 	/* Set up SLI-4 HBA */
 	if (lpfc_sli4_hba_setup(phba)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -10453,6 +10678,8 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	/* Perform post initialization setup */
 	lpfc_post_init_setup(phba);
 
+	/* todo: init: register port with nvme */
+
 	/* check for firmware upgrade or downgrade */
 	if (phba->cfg_request_firmware_upgrade)
 		lpfc_sli4_request_firmware_update(phba, INT_FW_UPGRADE);
@@ -10524,8 +10751,11 @@ lpfc_pci_remove_one_s4(struct pci_dev *pdev)
 	fc_remove_host(shost);
 	scsi_remove_host(shost);
 
-	/* Perform cleanup on the physical port */
+	/* Perform ndlp cleanup on the physical port.  The nvme localport
+	 * is destroyed after to ensure all rports are io-disabled.
+	 */
 	lpfc_cleanup(vport);
+	/* todo: init: unregister port with nvme */
 
 	/*
 	 * Bring down the SLI Layer. This step disables all interrupts,
@@ -10543,6 +10773,7 @@ lpfc_pci_remove_one_s4(struct pci_dev *pdev)
 	 * buffers are released to their corresponding pools here.
 	 */
 	lpfc_scsi_free(phba);
+	lpfc_nvme_free(phba);
 
 	lpfc_sli4_driver_resource_unset(phba);
 
@@ -11188,7 +11419,7 @@ lpfc_sli4_oas_verify(struct lpfc_hba *phba)
 int
 lpfc_fof_queue_setup(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_sli_ring *pring;
 	int rc;
 
 	rc = lpfc_eq_create(phba, phba->sli4_hba.fof_eq, LPFC_MAX_IMAX);
@@ -11207,8 +11438,11 @@ lpfc_fof_queue_setup(struct lpfc_hba *phba)
 		if (rc)
 			goto out_oas_wq;
 
-		phba->sli4_hba.oas_cq->pring = &psli->ring[LPFC_FCP_OAS_RING];
-		phba->sli4_hba.oas_ring = &psli->ring[LPFC_FCP_OAS_RING];
+		/* Bind this CQ/WQ to the NVME ring */
+		pring = phba->sli4_hba.oas_wq->pring;
+		pring->sli.sli4.wqp =
+			(void *)phba->sli4_hba.oas_wq;
+		phba->sli4_hba.oas_cq->pring = pring;
 	}
 
 	return 0;
@@ -11265,6 +11499,7 @@ lpfc_fof_queue_create(struct lpfc_hba *phba)
 			goto out_error;
 
 		phba->sli4_hba.oas_wq = qdesc;
+		list_add_tail(&qdesc->wq_list, &phba->sli4_hba.lpfc_wq_list);
 
 	}
 	return 0;
diff --git a/drivers/scsi/lpfc/lpfc_logmsg.h b/drivers/scsi/lpfc/lpfc_logmsg.h
index 2a4e5d21eab2..3faf7a07bfd4 100644
--- a/drivers/scsi/lpfc/lpfc_logmsg.h
+++ b/drivers/scsi/lpfc/lpfc_logmsg.h
@@ -38,6 +38,10 @@
 #define LOG_FIP		0x00020000	/* FIP events */
 #define LOG_FCP_UNDER	0x00040000	/* FCP underruns errors */
 #define LOG_SCSI_CMD	0x00080000	/* ALL SCSI commands */
+#define LOG_NVME	0x00100000	/* NVME general events. */
+#define LOG_NVME_DISC   0x00200000      /* NVME Discovery/Connect events. */
+#define LOG_NVME_ABTS   0x00400000      /* NVME ABTS events. */
+#define LOG_NVME_IOERR  0x00800000      /* NVME IO Error events. */
 #define LOG_ALL_MSG	0xffffffff	/* LOG all messages */
 
 #define lpfc_printf_vlog(vport, level, mask, fmt, arg...) \
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index b234c50c255f..c20dc25a1e79 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -954,7 +954,7 @@ lpfc_config_pcb_setup(struct lpfc_hba * phba)
 	pcbp->maxRing = (psli->num_rings - 1);
 
 	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
+		pring = &psli->sli3_ring[i];
 
 		pring->sli.sli3.sizeCiocb =
 			phba->sli_rev == 3 ? SLI3_IOCB_CMD_SIZE :
@@ -1217,7 +1217,7 @@ lpfc_config_ring(struct lpfc_hba * phba, int ring, LPFC_MBOXQ_t * pmb)
 	mb->un.varCfgRing.recvNotify = 1;
 
 	psli = &phba->sli;
-	pring = &psli->ring[ring];
+	pring = &psli->sli3_ring[ring];
 	mb->un.varCfgRing.numMask = pring->num_mask;
 	mb->mbxCommand = MBX_CONFIG_RING;
 	mb->mbxOwner = OWN_HOST;
@@ -2434,14 +2434,25 @@ lpfc_reg_fcfi(struct lpfc_hba *phba, struct lpfcMboxq *mbox)
 	memset(mbox, 0, sizeof(*mbox));
 	reg_fcfi = &mbox->u.mqe.un.reg_fcfi;
 	bf_set(lpfc_mqe_command, &mbox->u.mqe, MBX_REG_FCFI);
-	bf_set(lpfc_reg_fcfi_rq_id0, reg_fcfi, phba->sli4_hba.hdr_rq->queue_id);
-	bf_set(lpfc_reg_fcfi_rq_id1, reg_fcfi, REG_FCF_INVALID_QID);
+	if (phba->nvmet_support == 0) {
+		bf_set(lpfc_reg_fcfi_rq_id0, reg_fcfi,
+		       phba->sli4_hba.hdr_rq->queue_id);
+		/* Match everything - rq_id0 */
+		bf_set(lpfc_reg_fcfi_type_match0, reg_fcfi, 0);
+		bf_set(lpfc_reg_fcfi_type_mask0, reg_fcfi, 0);
+		bf_set(lpfc_reg_fcfi_rctl_match0, reg_fcfi, 0);
+		bf_set(lpfc_reg_fcfi_rctl_mask0, reg_fcfi, 0);
+
+		bf_set(lpfc_reg_fcfi_rq_id1, reg_fcfi, REG_FCF_INVALID_QID);
+
+		/* addr mode is bit wise inverted value of fcf addr_mode */
+		bf_set(lpfc_reg_fcfi_mam, reg_fcfi,
+		       (~phba->fcf.addr_mode) & 0x3);
+	}
 	bf_set(lpfc_reg_fcfi_rq_id2, reg_fcfi, REG_FCF_INVALID_QID);
 	bf_set(lpfc_reg_fcfi_rq_id3, reg_fcfi, REG_FCF_INVALID_QID);
 	bf_set(lpfc_reg_fcfi_info_index, reg_fcfi,
 	       phba->fcf.current_rec.fcf_indx);
-	/* reg_fcf addr mode is bit wise inverted value of fcf addr_mode */
-	bf_set(lpfc_reg_fcfi_mam, reg_fcfi, (~phba->fcf.addr_mode) & 0x3);
 	if (phba->fcf.current_rec.vlan_id != LPFC_FCOE_NULL_VID) {
 		bf_set(lpfc_reg_fcfi_vv, reg_fcfi, 1);
 		bf_set(lpfc_reg_fcfi_vlan_tag, reg_fcfi,
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index 3fa65338d3f5..c65a1ec3d2e4 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -24,10 +24,12 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 
+#include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/fc/fc_fs.h>
 
-#include <scsi/scsi.h>
+#include <linux/nvme-fc-driver.h>
 
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
@@ -35,8 +37,9 @@
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_crtn.h"
 #include "lpfc_logmsg.h"
 
@@ -66,7 +69,7 @@ lpfc_mem_alloc_active_rrq_pool_s4(struct lpfc_hba *phba) {
  * lpfc_mem_alloc - create and allocate all PCI and memory pools
  * @phba: HBA to allocate pools for
  *
- * Description: Creates and allocates PCI pools lpfc_scsi_dma_buf_pool,
+ * Description: Creates and allocates PCI pools lpfc_sg_dma_buf_pool,
  * lpfc_mbuf_pool, lpfc_hrb_pool.  Creates and allocates kmalloc-backed mempools
  * for LPFC_MBOXQ_t and lpfc_nodelist.  Also allocates the VPI bitmask.
  *
@@ -90,21 +93,23 @@ lpfc_mem_alloc(struct lpfc_hba *phba, int align)
 		else
 			i = SLI4_PAGE_SIZE;
 
-		phba->lpfc_scsi_dma_buf_pool =
-			pci_pool_create("lpfc_scsi_dma_buf_pool",
-				phba->pcidev,
-				phba->cfg_sg_dma_buf_size,
-				i,
-				0);
+		phba->lpfc_sg_dma_buf_pool =
+			pci_pool_create("lpfc_sg_dma_buf_pool",
+					phba->pcidev,
+					phba->cfg_sg_dma_buf_size,
+					i, 0);
+		if (!phba->lpfc_sg_dma_buf_pool)
+			goto fail;
+
 	} else {
-		phba->lpfc_scsi_dma_buf_pool =
-			pci_pool_create("lpfc_scsi_dma_buf_pool",
-				phba->pcidev, phba->cfg_sg_dma_buf_size,
-				align, 0);
-	}
+		phba->lpfc_sg_dma_buf_pool =
+			pci_pool_create("lpfc_sg_dma_buf_pool",
+					phba->pcidev, phba->cfg_sg_dma_buf_size,
+					align, 0);
 
-	if (!phba->lpfc_scsi_dma_buf_pool)
-		goto fail;
+		if (!phba->lpfc_sg_dma_buf_pool)
+			goto fail;
+	}
 
 	phba->lpfc_mbuf_pool = pci_pool_create("lpfc_mbuf_pool", phba->pcidev,
 							LPFC_BPL_SIZE,
@@ -170,12 +175,15 @@ lpfc_mem_alloc(struct lpfc_hba *phba, int align)
 					LPFC_DEVICE_DATA_POOL_SIZE,
 					sizeof(struct lpfc_device_data));
 		if (!phba->device_data_mem_pool)
-			goto fail_free_hrb_pool;
+			goto fail_free_drb_pool;
 	} else {
 		phba->device_data_mem_pool = NULL;
 	}
 
 	return 0;
+fail_free_drb_pool:
+	pci_pool_destroy(phba->lpfc_drb_pool);
+	phba->lpfc_drb_pool = NULL;
  fail_free_hrb_pool:
 	pci_pool_destroy(phba->lpfc_hrb_pool);
 	phba->lpfc_hrb_pool = NULL;
@@ -197,8 +205,8 @@ lpfc_mem_alloc(struct lpfc_hba *phba, int align)
 	pci_pool_destroy(phba->lpfc_mbuf_pool);
 	phba->lpfc_mbuf_pool = NULL;
  fail_free_dma_buf_pool:
-	pci_pool_destroy(phba->lpfc_scsi_dma_buf_pool);
-	phba->lpfc_scsi_dma_buf_pool = NULL;
+	pci_pool_destroy(phba->lpfc_sg_dma_buf_pool);
+	phba->lpfc_sg_dma_buf_pool = NULL;
  fail:
 	return -ENOMEM;
 }
@@ -227,6 +235,9 @@ lpfc_mem_free(struct lpfc_hba *phba)
 	if (phba->lpfc_hrb_pool)
 		pci_pool_destroy(phba->lpfc_hrb_pool);
 	phba->lpfc_hrb_pool = NULL;
+	if (phba->txrdy_payload_pool)
+		pci_pool_destroy(phba->txrdy_payload_pool);
+	phba->txrdy_payload_pool = NULL;
 
 	if (phba->lpfc_hbq_pool)
 		pci_pool_destroy(phba->lpfc_hbq_pool);
@@ -258,8 +269,8 @@ lpfc_mem_free(struct lpfc_hba *phba)
 	phba->lpfc_mbuf_pool = NULL;
 
 	/* Free DMA buffer memory pool */
-	pci_pool_destroy(phba->lpfc_scsi_dma_buf_pool);
-	phba->lpfc_scsi_dma_buf_pool = NULL;
+	pci_pool_destroy(phba->lpfc_sg_dma_buf_pool);
+	phba->lpfc_sg_dma_buf_pool = NULL;
 
 	/* Free Device Data memory pool */
 	if (phba->device_data_mem_pool) {
@@ -282,7 +293,7 @@ lpfc_mem_free(struct lpfc_hba *phba)
  * @phba: HBA to free memory for
  *
  * Description: Free memory from PCI and driver memory pools and also those
- * used : lpfc_scsi_dma_buf_pool, lpfc_mbuf_pool, lpfc_hrb_pool. Frees
+ * used : lpfc_sg_dma_buf_pool, lpfc_mbuf_pool, lpfc_hrb_pool. Frees
  * kmalloc-backed mempools for LPFC_MBOXQ_t and lpfc_nodelist. Also frees
  * the VPI bitmask.
  *
@@ -458,7 +469,7 @@ lpfc_els_hbq_alloc(struct lpfc_hba *phba)
 		kfree(hbqbp);
 		return NULL;
 	}
-	hbqbp->size = LPFC_BPL_SIZE;
+	hbqbp->total_size = LPFC_BPL_SIZE;
 	return hbqbp;
 }
 
@@ -518,7 +529,7 @@ lpfc_sli4_rb_alloc(struct lpfc_hba *phba)
 		kfree(dma_buf);
 		return NULL;
 	}
-	dma_buf->size = LPFC_BPL_SIZE;
+	dma_buf->total_size = LPFC_DATA_BUF_SIZE;
 	return dma_buf;
 }
 
@@ -540,7 +551,6 @@ lpfc_sli4_rb_free(struct lpfc_hba *phba, struct hbq_dmabuf *dmab)
 	pci_pool_free(phba->lpfc_hrb_pool, dmab->hbuf.virt, dmab->hbuf.phys);
 	pci_pool_free(phba->lpfc_drb_pool, dmab->dbuf.virt, dmab->dbuf.phys);
 	kfree(dmab);
-	return;
 }
 
 /**
@@ -565,13 +575,13 @@ lpfc_in_buf_free(struct lpfc_hba *phba, struct lpfc_dmabuf *mp)
 		return;
 
 	if (phba->sli3_options & LPFC_SLI3_HBQ_ENABLED) {
+		hbq_entry = container_of(mp, struct hbq_dmabuf, dbuf);
 		/* Check whether HBQ is still in use */
 		spin_lock_irqsave(&phba->hbalock, flags);
 		if (!phba->hbq_in_use) {
 			spin_unlock_irqrestore(&phba->hbalock, flags);
 			return;
 		}
-		hbq_entry = container_of(mp, struct hbq_dmabuf, dbuf);
 		list_del(&hbq_entry->dbuf.list);
 		if (hbq_entry->tag == -1) {
 			(phba->hbqs[LPFC_ELS_HBQ].hbq_free_buffer)
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 56a3df4fddb0..835ea9f78219 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -204,10 +204,11 @@ int
 lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 {
 	LIST_HEAD(abort_list);
-	struct lpfc_sli  *psli = &phba->sli;
-	struct lpfc_sli_ring *pring = &psli->ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *iocb, *next_iocb;
 
+	pring = lpfc_phba_elsring(phba);
+
 	/* Abort outstanding I/O on NPort <nlp_DID> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_DISCOVERY,
 			 "2819 Abort outstanding I/O on NPort x%x "
@@ -2104,7 +2105,7 @@ lpfc_rcv_prlo_mapped_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
 	/* flush the target */
-	lpfc_sli_abort_iocb(vport, &phba->sli.ring[phba->sli.fcp_ring],
+	lpfc_sli_abort_iocb(vport, &phba->sli.sli3_ring[LPFC_FCP_RING],
 			    ndlp->nlp_sid, 0, LPFC_CTX_TGT);
 
 	/* Treat like rcv logo */
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
new file mode 100644
index 000000000000..2b167933fd26
--- /dev/null
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -0,0 +1,88 @@
+/*******************************************************************
+ * This file is part of the Emulex Linux Device Driver for         *
+ * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
+ *                                                                 *
+ * This program is free software; you can redistribute it and/or   *
+ * modify it under the terms of version 2 of the GNU General       *
+ * Public License as published by the Free Software Foundation.    *
+ * This program is distributed in the hope that it will be useful. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ ********************************************************************/
+
+#define LPFC_NVME_MIN_SEGS		16
+#define LPFC_NVME_DEFAULT_SEGS		66	/* 256K IOs - 64 + 2 */
+#define LPFC_NVME_MAX_SEGS		510
+#define LPFC_NVMET_MIN_POSTBUF		16
+#define LPFC_NVMET_DEFAULT_POSTBUF	1024
+#define LPFC_NVMET_MAX_POSTBUF		4096
+#define LPFC_NVME_WQSIZE		256
+
+#define LPFC_NVME_ERSP_LEN		0x20
+
+/* Declare nvme-based local and remote port definitions. */
+struct lpfc_nvme_lport {
+	struct lpfc_vport *vport;
+	struct list_head rport_list;
+	struct completion lport_unreg_done;
+	/* Add sttats counters here */
+};
+
+struct lpfc_nvme_rport {
+	struct list_head list;
+	struct lpfc_nvme_lport *lport;
+	struct nvme_fc_remote_port *remoteport;
+	struct lpfc_nodelist *ndlp;
+	struct completion rport_unreg_done;
+};
+
+struct lpfc_nvme_buf {
+	struct list_head list;
+	struct nvmefc_fcp_req *nvmeCmd;
+	struct lpfc_nvme_rport *nrport;
+
+	uint32_t timeout;
+
+	uint16_t flags;  /* TBD convert exch_busy to flags */
+#define LPFC_SBUF_XBUSY         0x1     /* SLI4 hba reported XB on WCQE cmpl */
+	uint16_t exch_busy;     /* SLI4 hba reported XB on complete WCQE */
+	uint16_t status;	/* From IOCB Word 7- ulpStatus */
+	uint16_t cpu;
+	uint16_t qidx;
+	uint16_t sqid;
+	uint32_t result;	/* From IOCB Word 4. */
+
+	uint32_t   seg_cnt;	/* Number of scatter-gather segments returned by
+				 * dma_map_sg.  The driver needs this for calls
+				 * to dma_unmap_sg.
+				 */
+	dma_addr_t nonsg_phys;	/* Non scatter-gather physical address. */
+
+	/*
+	 * data and dma_handle are the kernel virtual and bus address of the
+	 * dma-able buffer containing the fcp_cmd, fcp_rsp and a scatter
+	 * gather bde list that supports the sg_tablesize value.
+	 */
+	void *data;
+	dma_addr_t dma_handle;
+
+	struct sli4_sge *nvme_sgl;
+	dma_addr_t dma_phys_sgl;
+
+	/* cur_iocbq has phys of the dma-able buffer.
+	 * Iotag is in here
+	 */
+	struct lpfc_iocbq cur_iocbq;
+
+	wait_queue_head_t *waitq;
+	unsigned long start_time;
+};
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index bd7b75dbb97e..c327fc7b1a54 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -413,7 +413,7 @@ lpfc_new_scsi_buf_s3(struct lpfc_vport *vport, int num_to_alloc)
 		 * struct fcp_cmnd, struct fcp_rsp and the number of bde's
 		 * necessary to support the sg_tablesize.
 		 */
-		psb->data = pci_pool_zalloc(phba->lpfc_scsi_dma_buf_pool,
+		psb->data = pci_pool_zalloc(phba->lpfc_sg_dma_buf_pool,
 					GFP_KERNEL, &psb->dma_handle);
 		if (!psb->data) {
 			kfree(psb);
@@ -424,8 +424,8 @@ lpfc_new_scsi_buf_s3(struct lpfc_vport *vport, int num_to_alloc)
 		/* Allocate iotag for psb->cur_iocbq. */
 		iotag = lpfc_sli_next_iotag(phba, &psb->cur_iocbq);
 		if (iotag == 0) {
-			pci_pool_free(phba->lpfc_scsi_dma_buf_pool,
-					psb->data, psb->dma_handle);
+			pci_pool_free(phba->lpfc_sg_dma_buf_pool,
+				      psb->data, psb->dma_handle);
 			kfree(psb);
 			break;
 		}
@@ -522,6 +522,8 @@ lpfc_sli4_vport_delete_fcp_xri_aborted(struct lpfc_vport *vport)
 	struct lpfc_scsi_buf *psb, *next_psb;
 	unsigned long iflag = 0;
 
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
+		return;
 	spin_lock_irqsave(&phba->hbalock, iflag);
 	spin_lock(&phba->sli4_hba.abts_scsi_buf_list_lock);
 	list_for_each_entry_safe(psb, next_psb,
@@ -554,8 +556,10 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba,
 	int i;
 	struct lpfc_nodelist *ndlp;
 	int rrq_empty = 0;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring = phba->sli4_hba.els_wq->pring;
 
+	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
+		return;
 	spin_lock_irqsave(&phba->hbalock, iflag);
 	spin_lock(&phba->sli4_hba.abts_scsi_buf_list_lock);
 	list_for_each_entry_safe(psb, next_psb,
@@ -819,7 +823,7 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		 * for the struct fcp_cmnd, struct fcp_rsp and the number
 		 * of bde's necessary to support the sg_tablesize.
 		 */
-		psb->data = pci_pool_zalloc(phba->lpfc_scsi_dma_buf_pool,
+		psb->data = pci_pool_zalloc(phba->lpfc_sg_dma_buf_pool,
 						GFP_KERNEL, &psb->dma_handle);
 		if (!psb->data) {
 			kfree(psb);
@@ -832,7 +836,7 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		 */
 		if (phba->cfg_enable_bg  && (((unsigned long)(psb->data) &
 		    (unsigned long)(SLI4_PAGE_SIZE - 1)) != 0)) {
-			pci_pool_free(phba->lpfc_scsi_dma_buf_pool,
+			pci_pool_free(phba->lpfc_sg_dma_buf_pool,
 				      psb->data, psb->dma_handle);
 			kfree(psb);
 			break;
@@ -841,8 +845,8 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 
 		lxri = lpfc_sli4_next_xritag(phba);
 		if (lxri == NO_XRI) {
-			pci_pool_free(phba->lpfc_scsi_dma_buf_pool,
-			      psb->data, psb->dma_handle);
+			pci_pool_free(phba->lpfc_sg_dma_buf_pool,
+				      psb->data, psb->dma_handle);
 			kfree(psb);
 			break;
 		}
@@ -850,8 +854,8 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		/* Allocate iotag for psb->cur_iocbq. */
 		iotag = lpfc_sli_next_iotag(phba, &psb->cur_iocbq);
 		if (iotag == 0) {
-			pci_pool_free(phba->lpfc_scsi_dma_buf_pool,
-				psb->data, psb->dma_handle);
+			pci_pool_free(phba->lpfc_sg_dma_buf_pool,
+				      psb->data, psb->dma_handle);
 			kfree(psb);
 			lpfc_printf_log(phba, KERN_ERR, LOG_FCP,
 					"3368 Failed to allocate IOTAG for"
@@ -920,7 +924,7 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		phba->sli4_hba.scsi_xri_cnt++;
 		spin_unlock_irq(&phba->scsi_buf_list_get_lock);
 	}
-	lpfc_printf_log(phba, KERN_INFO, LOG_BG,
+	lpfc_printf_log(phba, KERN_INFO, LOG_BG | LOG_FCP,
 			"3021 Allocate %d out of %d requested new SCSI "
 			"buffers\n", bcnt, num_to_alloc);
 
@@ -3925,6 +3929,8 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	struct Scsi_Host *shost;
 	uint32_t logit = LOG_FCP;
 
+	phba->fc4ScsiIoCmpls++;
+
 	/* Sanity check on return of outstanding command */
 	cmd = lpfc_cmd->pCmd;
 	if (!cmd)
@@ -4242,19 +4248,19 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 						vport->cfg_first_burst_size;
 			}
 			fcp_cmnd->fcpCntl3 = WRITE_DATA;
-			phba->fc4OutputRequests++;
+			phba->fc4ScsiOutputRequests++;
 		} else {
 			iocb_cmd->ulpCommand = CMD_FCP_IREAD64_CR;
 			iocb_cmd->ulpPU = PARM_READ_CHECK;
 			fcp_cmnd->fcpCntl3 = READ_DATA;
-			phba->fc4InputRequests++;
+			phba->fc4ScsiInputRequests++;
 		}
 	} else {
 		iocb_cmd->ulpCommand = CMD_FCP_ICMND64_CR;
 		iocb_cmd->un.fcpi.fcpi_parm = 0;
 		iocb_cmd->ulpPU = 0;
 		fcp_cmnd->fcpCntl3 = 0;
-		phba->fc4ControlRequests++;
+		phba->fc4ScsiControlRequests++;
 	}
 	if (phba->sli_rev == 3 &&
 	    !(phba->sli3_options & LPFC_SLI3_BG_ENABLED))
@@ -4468,7 +4474,7 @@ static __inline__ void lpfc_poll_rearm_timer(struct lpfc_hba * phba)
 	unsigned long  poll_tmo_expires =
 		(jiffies + msecs_to_jiffies(phba->cfg_poll_tmo));
 
-	if (!list_empty(&phba->sli.ring[LPFC_FCP_RING].txcmplq))
+	if (!list_empty(&phba->sli.sli3_ring[LPFC_FCP_RING].txcmplq))
 		mod_timer(&phba->fcp_poll_timer,
 			  poll_tmo_expires);
 }
@@ -4498,7 +4504,7 @@ void lpfc_poll_timeout(unsigned long ptr)
 
 	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {
 		lpfc_sli_handle_fast_ring_event(phba,
-			&phba->sli.ring[LPFC_FCP_RING], HA_R0RE_REQ);
+			&phba->sli.sli3_ring[LPFC_FCP_RING], HA_R0RE_REQ);
 
 		if (phba->cfg_poll & DISABLE_FCP_RING_INT)
 			lpfc_poll_rearm_timer(phba);
@@ -4562,7 +4568,7 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	if (lpfc_cmd == NULL) {
 		lpfc_rampdown_queue_depth(phba);
 
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_MISC,
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP_ERROR,
 				 "0707 driver's buffer pool is empty, "
 				 "IO busied\n");
 		goto out_host_busy;
@@ -4637,7 +4643,7 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	}
 	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {
 		lpfc_sli_handle_fast_ring_event(phba,
-			&phba->sli.ring[LPFC_FCP_RING], HA_R0RE_REQ);
+			&phba->sli.sli3_ring[LPFC_FCP_RING], HA_R0RE_REQ);
 
 		if (phba->cfg_poll & DISABLE_FCP_RING_INT)
 			lpfc_poll_rearm_timer(phba);
@@ -4682,7 +4688,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	IOCB_t *cmd, *icmd;
 	int ret = SUCCESS, status = 0;
 	struct lpfc_sli_ring *pring_s4;
-	int ring_number, ret_val;
+	int ret_val;
 	unsigned long flags, iflags;
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq);
 
@@ -4770,7 +4776,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	icmd->ulpClass = cmd->ulpClass;
 
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
-	abtsiocb->fcp_wqidx = iocb->fcp_wqidx;
+	abtsiocb->hba_wqidx = iocb->hba_wqidx;
 	abtsiocb->iocb_flag |= LPFC_USE_FCPWQIDX;
 	if (iocb->iocb_flag & LPFC_IO_FOF)
 		abtsiocb->iocb_flag |= LPFC_IO_FOF;
@@ -4783,8 +4789,11 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	abtsiocb->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
 	abtsiocb->vport = vport;
 	if (phba->sli_rev == LPFC_SLI_REV4) {
-		ring_number = MAX_SLI3_CONFIGURED_RINGS + iocb->fcp_wqidx;
-		pring_s4 = &phba->sli.ring[ring_number];
+		pring_s4 = lpfc_sli4_calc_ring(phba, iocb);
+		if (pring_s4 == NULL) {
+			ret = FAILED;
+			goto out_unlock;
+		}
 		/* Note: both hbalock and ring_lock must be set here */
 		spin_lock_irqsave(&pring_s4->ring_lock, iflags);
 		ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
@@ -4806,7 +4815,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 	if (phba->cfg_poll & DISABLE_FCP_RING_INT)
 		lpfc_sli_handle_fast_ring_event(phba,
-			&phba->sli.ring[LPFC_FCP_RING], HA_R0RE_REQ);
+			&phba->sli.sli3_ring[LPFC_FCP_RING], HA_R0RE_REQ);
 
 wait_for_cmpl:
 	lpfc_cmd->waitq = &waitq;
@@ -5106,7 +5115,7 @@ lpfc_reset_flush_io_context(struct lpfc_vport *vport, uint16_t tgt_id,
 	cnt = lpfc_sli_sum_iocb(vport, tgt_id, lun_id, context);
 	if (cnt)
 		lpfc_sli_abort_taskmgmt(vport,
-					&phba->sli.ring[phba->sli.fcp_ring],
+					&phba->sli.sli3_ring[LPFC_FCP_RING],
 					tgt_id, lun_id, context);
 	later = msecs_to_jiffies(2 * vport->cfg_devloss_tmo * 1000) + jiffies;
 	while (time_after(later, jiffies) && cnt) {
@@ -5535,7 +5544,7 @@ lpfc_slave_configure(struct scsi_device *sdev)
 
 	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {
 		lpfc_sli_handle_fast_ring_event(phba,
-			&phba->sli.ring[LPFC_FCP_RING], HA_R0RE_REQ);
+			&phba->sli.sli3_ring[LPFC_FCP_RING], HA_R0RE_REQ);
 		if (phba->cfg_poll & DISABLE_FCP_RING_INT)
 			lpfc_poll_rearm_timer(phba);
 	}
@@ -5899,6 +5908,48 @@ lpfc_disable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	return false;
 }
 
+static int
+lpfc_no_command(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
+{
+	return SCSI_MLQUEUE_HOST_BUSY;
+}
+
+static int
+lpfc_no_handler(struct scsi_cmnd *cmnd)
+{
+	return FAILED;
+}
+
+static int
+lpfc_no_slave(struct scsi_device *sdev)
+{
+	return -ENODEV;
+}
+
+struct scsi_host_template lpfc_template_nvme = {
+	.module			= THIS_MODULE,
+	.name			= LPFC_DRIVER_NAME,
+	.proc_name		= LPFC_DRIVER_NAME,
+	.info			= lpfc_info,
+	.queuecommand		= lpfc_no_command,
+	.eh_abort_handler	= lpfc_no_handler,
+	.eh_device_reset_handler = lpfc_no_handler,
+	.eh_target_reset_handler = lpfc_no_handler,
+	.eh_bus_reset_handler	= lpfc_no_handler,
+	.eh_host_reset_handler  = lpfc_no_handler,
+	.slave_alloc		= lpfc_no_slave,
+	.slave_configure	= lpfc_no_slave,
+	.scan_finished		= lpfc_scan_finished,
+	.this_id		= -1,
+	.sg_tablesize		= 1,
+	.cmd_per_lun		= 1,
+	.use_clustering		= ENABLE_CLUSTERING,
+	.shost_attrs		= lpfc_hba_attrs,
+	.max_sectors		= 0xFFFF,
+	.vendor_id		= LPFC_NL_VENDOR_ID,
+	.track_queue_depth	= 0,
+};
+
 struct scsi_host_template lpfc_template_s3 = {
 	.module			= THIS_MODULE,
 	.name			= LPFC_DRIVER_NAME,
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index 4d7062258cf8..def0c0a5b17e 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -135,6 +135,8 @@ struct lpfc_scsi_buf {
 
 	uint32_t timeout;
 
+	uint16_t flags;  /* TBD convert exch_busy to flags */
+#define LPFC_SBUF_XBUSY         0x1     /* SLI4 hba reported XB on WCQE cmpl */
 	uint16_t exch_busy;     /* SLI4 hba reported XB on complete WCQE */
 	uint16_t status;	/* From IOCB Word 7- ulpStatus */
 	uint32_t result;	/* From IOCB Word 4. */
@@ -164,6 +166,8 @@ struct lpfc_scsi_buf {
 	 * Iotag is in here
 	 */
 	struct lpfc_iocbq cur_iocbq;
+	uint16_t cpu;
+
 	wait_queue_head_t *waitq;
 	unsigned long start_time;
 
@@ -186,5 +190,7 @@ struct lpfc_scsi_buf {
 #define NO_MORE_OAS_LUN		-1
 #define NOT_OAS_ENABLED_LUN	NO_MORE_OAS_LUN
 
+#define TXRDY_PAYLOAD_LEN	12
+
 int lpfc_sli4_scmd_to_wqidx_distr(struct lpfc_hba *phba,
 				  struct lpfc_scsi_buf *lpfc_cmd);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 19543142c94c..52fa5c77f3bc 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -34,14 +34,17 @@
 #include <scsi/fc/fc_fs.h>
 #include <linux/aer.h>
 
+#include <linux/nvme-fc-driver.h>
+
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
 #include "lpfc_sli.h"
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_crtn.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_compat.h"
@@ -67,14 +70,17 @@ static struct lpfc_iocbq *lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *,
 							 struct lpfc_iocbq *);
 static void lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *,
 				      struct hbq_dmabuf *);
-static int lpfc_sli4_fp_handle_wcqe(struct lpfc_hba *, struct lpfc_queue *,
+static int lpfc_sli4_fp_handle_cqe(struct lpfc_hba *, struct lpfc_queue *,
 				    struct lpfc_cqe *);
-static int lpfc_sli4_post_els_sgl_list(struct lpfc_hba *, struct list_head *,
+static int lpfc_sli4_post_sgl_list(struct lpfc_hba *, struct list_head *,
 				       int);
 static void lpfc_sli4_hba_handle_eqe(struct lpfc_hba *, struct lpfc_eqe *,
 			uint32_t);
 static bool lpfc_sli4_mbox_completions_pending(struct lpfc_hba *phba);
 static bool lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba);
+static int lpfc_sli4_abort_nvme_io(struct lpfc_hba *phba,
+				   struct lpfc_sli_ring *pring,
+				   struct lpfc_iocbq *cmdiocb);
 
 static IOCB_t *
 lpfc_get_iocb_from_iocbq(struct lpfc_iocbq *iocbq)
@@ -456,7 +462,7 @@ lpfc_sli4_cq_release(struct lpfc_queue *q, bool arm)
  * on @q then this function will return -ENOMEM.
  * The caller is expected to hold the hbalock when calling this routine.
  **/
-static int
+int
 lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
 		 struct lpfc_rqe *hrqe, struct lpfc_rqe *drqe)
 {
@@ -602,7 +608,7 @@ __lpfc_sli_get_iocbq(struct lpfc_hba *phba)
  *
  * Returns sglq ponter = success, NULL = Failure.
  **/
-static struct lpfc_sglq *
+struct lpfc_sglq *
 __lpfc_clear_active_sglq(struct lpfc_hba *phba, uint16_t xritag)
 {
 	struct lpfc_sglq *sglq;
@@ -902,7 +908,7 @@ lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 }
 
 /**
- * __lpfc_sli_get_sglq - Allocates an iocb object from sgl pool
+ * __lpfc_sli_get_els_sglq - Allocates an iocb object from sgl pool
  * @phba: Pointer to HBA context object.
  * @piocb: Pointer to the iocbq.
  *
@@ -912,9 +918,9 @@ lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
  * allocated sglq object else it returns NULL.
  **/
 static struct lpfc_sglq *
-__lpfc_sli_get_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
+__lpfc_sli_get_els_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 {
-	struct list_head *lpfc_sgl_list = &phba->sli4_hba.lpfc_sgl_list;
+	struct list_head *lpfc_els_sgl_list = &phba->sli4_hba.lpfc_els_sgl_list;
 	struct lpfc_sglq *sglq = NULL;
 	struct lpfc_sglq *start_sglq = NULL;
 	struct lpfc_scsi_buf *lpfc_cmd;
@@ -938,18 +944,21 @@ __lpfc_sli_get_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 		ndlp = piocbq->context1;
 	}
 
-	list_remove_head(lpfc_sgl_list, sglq, struct lpfc_sglq, list);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
+	list_remove_head(lpfc_els_sgl_list, sglq, struct lpfc_sglq, list);
 	start_sglq = sglq;
 	while (!found) {
 		if (!sglq)
 			return NULL;
-		if (lpfc_test_rrq_active(phba, ndlp, sglq->sli4_lxritag)) {
+		if (ndlp && ndlp->active_rrqs_xri_bitmap &&
+		    test_bit(sglq->sli4_lxritag,
+		    ndlp->active_rrqs_xri_bitmap)) {
 			/* This xri has an rrq outstanding for this DID.
 			 * put it back in the list and get another xri.
 			 */
-			list_add_tail(&sglq->list, lpfc_sgl_list);
+			list_add_tail(&sglq->list, lpfc_els_sgl_list);
 			sglq = NULL;
-			list_remove_head(lpfc_sgl_list, sglq,
+			list_remove_head(lpfc_els_sgl_list, sglq,
 						struct lpfc_sglq, list);
 			if (sglq == start_sglq) {
 				sglq = NULL;
@@ -962,6 +971,7 @@ __lpfc_sli_get_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 		phba->sli4_hba.lpfc_sglq_active_list[sglq->sli4_lxritag] = sglq;
 		sglq->state = SGL_ALLOCATED;
 	}
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	return sglq;
 }
 
@@ -1002,7 +1012,7 @@ lpfc_sli_get_iocbq(struct lpfc_hba *phba)
  * this IO was aborted then the sglq entry it put on the
  * lpfc_abts_els_sgl_list until the CQ_ABORTED_XRI is received. If the
  * IO has good status or fails for any other reason then the sglq
- * entry is added to the free list (lpfc_sgl_list).
+ * entry is added to the free list (lpfc_els_sgl_list).
  **/
 static void
 __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
@@ -1010,7 +1020,7 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 	struct lpfc_sglq *sglq;
 	size_t start_clean = offsetof(struct lpfc_iocbq, iocb);
 	unsigned long iflag = 0;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 
 	lockdep_assert_held(&phba->hbalock);
 
@@ -1021,21 +1031,24 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 
 
 	if (sglq)  {
+		pring = phba->sli4_hba.els_wq->pring;
 		if ((iocbq->iocb_flag & LPFC_EXCHANGE_BUSY) &&
 			(sglq->state != SGL_XRI_ABORTED)) {
-			spin_lock_irqsave(&phba->sli4_hba.abts_sgl_list_lock,
-					iflag);
+			spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock,
+					  iflag);
 			list_add(&sglq->list,
-				&phba->sli4_hba.lpfc_abts_els_sgl_list);
+				 &phba->sli4_hba.lpfc_abts_els_sgl_list);
 			spin_unlock_irqrestore(
-				&phba->sli4_hba.abts_sgl_list_lock, iflag);
+				&phba->sli4_hba.sgl_list_lock, iflag);
 		} else {
-			spin_lock_irqsave(&pring->ring_lock, iflag);
+			spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock,
+					  iflag);
 			sglq->state = SGL_FREED;
 			sglq->ndlp = NULL;
 			list_add_tail(&sglq->list,
-				&phba->sli4_hba.lpfc_sgl_list);
-			spin_unlock_irqrestore(&pring->ring_lock, iflag);
+				      &phba->sli4_hba.lpfc_els_sgl_list);
+			spin_unlock_irqrestore(
+				&phba->sli4_hba.sgl_list_lock, iflag);
 
 			/* Check if TXQ queue needs to be serviced */
 			if (!list_empty(&pring->txq))
@@ -1043,13 +1056,13 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 		}
 	}
 
-
 	/*
 	 * Clean all volatile data fields, preserve iotag and node struct.
 	 */
 	memset((char *)iocbq + start_clean, 0, sizeof(*iocbq) - start_clean);
 	iocbq->sli4_lxritag = NO_XRI;
 	iocbq->sli4_xritag = NO_XRI;
+	iocbq->iocb_flag &= ~(LPFC_IO_NVME | LPFC_IO_NVME_LS);
 	list_add_tail(&iocbq->list, &phba->lpfc_iocb_list);
 }
 
@@ -1639,7 +1652,7 @@ lpfc_sli_resume_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 
 	if (lpfc_is_link_up(phba) &&
 	    (!list_empty(&pring->txq)) &&
-	    (pring->ringno != phba->sli.fcp_ring ||
+	    (pring->ringno != LPFC_FCP_RING ||
 	     phba->sli.sli_flag & LPFC_PROCESS_LA)) {
 
 		while ((iocb = lpfc_sli_next_iocb_slot(phba, pring)) &&
@@ -1718,7 +1731,6 @@ lpfc_sli_hbqbuf_free_all(struct lpfc_hba *phba)
 	struct hbq_dmabuf *hbq_buf;
 	unsigned long flags;
 	int i, hbq_count;
-	uint32_t hbqno;
 
 	hbq_count = lpfc_sli_hbq_count();
 	/* Return all memory used by all HBQs */
@@ -1732,24 +1744,6 @@ lpfc_sli_hbqbuf_free_all(struct lpfc_hba *phba)
 		}
 		phba->hbqs[i].buffer_count = 0;
 	}
-	/* Return all HBQ buffer that are in-fly */
-	list_for_each_entry_safe(dmabuf, next_dmabuf, &phba->rb_pend_list,
-				 list) {
-		hbq_buf = container_of(dmabuf, struct hbq_dmabuf, dbuf);
-		list_del(&hbq_buf->dbuf.list);
-		if (hbq_buf->tag == -1) {
-			(phba->hbqs[LPFC_ELS_HBQ].hbq_free_buffer)
-				(phba, hbq_buf);
-		} else {
-			hbqno = hbq_buf->tag >> 16;
-			if (hbqno >= LPFC_MAX_HBQS)
-				(phba->hbqs[LPFC_ELS_HBQ].hbq_free_buffer)
-					(phba, hbq_buf);
-			else
-				(phba->hbqs[hbqno].hbq_free_buffer)(phba,
-					hbq_buf);
-		}
-	}
 
 	/* Mark the HBQs not in use */
 	phba->hbq_in_use = 0;
@@ -1802,7 +1796,7 @@ lpfc_sli_hbq_to_firmware_s3(struct lpfc_hba *phba, uint32_t hbqno,
 
 		hbqe->bde.addrHigh = le32_to_cpu(putPaddrHigh(physaddr));
 		hbqe->bde.addrLow  = le32_to_cpu(putPaddrLow(physaddr));
-		hbqe->bde.tus.f.bdeSize = hbq_buf->size;
+		hbqe->bde.tus.f.bdeSize = hbq_buf->total_size;
 		hbqe->bde.tus.f.bdeFlags = 0;
 		hbqe->bde.tus.w = le32_to_cpu(hbqe->bde.tus.w);
 		hbqe->buffer_tag = le32_to_cpu(hbq_buf->tag);
@@ -1834,17 +1828,23 @@ lpfc_sli_hbq_to_firmware_s4(struct lpfc_hba *phba, uint32_t hbqno,
 	int rc;
 	struct lpfc_rqe hrqe;
 	struct lpfc_rqe drqe;
+	struct lpfc_queue *hrq;
+	struct lpfc_queue *drq;
+
+	if (hbqno != LPFC_ELS_HBQ)
+		return 1;
+	hrq = phba->sli4_hba.hdr_rq;
+	drq = phba->sli4_hba.dat_rq;
 
 	lockdep_assert_held(&phba->hbalock);
 	hrqe.address_lo = putPaddrLow(hbq_buf->hbuf.phys);
 	hrqe.address_hi = putPaddrHigh(hbq_buf->hbuf.phys);
 	drqe.address_lo = putPaddrLow(hbq_buf->dbuf.phys);
 	drqe.address_hi = putPaddrHigh(hbq_buf->dbuf.phys);
-	rc = lpfc_sli4_rq_put(phba->sli4_hba.hdr_rq, phba->sli4_hba.dat_rq,
-			      &hrqe, &drqe);
+	rc = lpfc_sli4_rq_put(hrq, drq, &hrqe, &drqe);
 	if (rc < 0)
 		return rc;
-	hbq_buf->tag = rc;
+	hbq_buf->tag = (rc | (hbqno << 16));
 	list_add_tail(&hbq_buf->dbuf.list, &phba->hbqs[hbqno].hbq_buffer_list);
 	return 0;
 }
@@ -1861,22 +1861,9 @@ static struct lpfc_hbq_init lpfc_els_hbq = {
 	.add_count = 40,
 };
 
-/* HBQ for the extra ring if needed */
-static struct lpfc_hbq_init lpfc_extra_hbq = {
-	.rn = 1,
-	.entry_count = 200,
-	.mask_count = 0,
-	.profile = 0,
-	.ring_mask = (1 << LPFC_EXTRA_RING),
-	.buffer_count = 0,
-	.init_count = 0,
-	.add_count = 5,
-};
-
 /* Array of HBQs */
 struct lpfc_hbq_init *lpfc_hbq_defs[] = {
 	&lpfc_els_hbq,
-	&lpfc_extra_hbq,
 };
 
 /**
@@ -2713,7 +2700,7 @@ static struct lpfc_iocbq *
 lpfc_sli_iocbq_lookup_by_tag(struct lpfc_hba *phba,
 			     struct lpfc_sli_ring *pring, uint16_t iotag)
 {
-	struct lpfc_iocbq *cmd_iocb;
+	struct lpfc_iocbq *cmd_iocb = NULL;
 
 	lockdep_assert_held(&phba->hbalock);
 	if (iotag != 0 && iotag <= phba->sli.last_iotag) {
@@ -2727,8 +2714,10 @@ lpfc_sli_iocbq_lookup_by_tag(struct lpfc_hba *phba,
 	}
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-			"0372 iotag x%x is out of range: max iotag (x%x)\n",
-			iotag, phba->sli.last_iotag);
+			"0372 iotag x%x lookup error: max iotag (x%x) "
+			"iocb_flag x%x\n",
+			iotag, phba->sli.last_iotag,
+			cmd_iocb ? cmd_iocb->iocb_flag : 0xffff);
 	return NULL;
 }
 
@@ -3597,6 +3586,33 @@ lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 			      IOERR_SLI_ABORTED);
 }
 
+/**
+ * lpfc_sli_abort_wqe_ring - Abort all iocbs in the ring
+ * @phba: Pointer to HBA context object.
+ * @pring: Pointer to driver SLI ring object.
+ *
+ * This function aborts all iocbs in the given ring and frees all the iocb
+ * objects in txq. This function issues an abort iocb for all the iocb commands
+ * in txcmplq. The iocbs in the txcmplq is not guaranteed to complete before
+ * the return of this function. The caller is not required to hold any locks.
+ **/
+void
+lpfc_sli_abort_wqe_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
+{
+	LIST_HEAD(completions);
+	struct lpfc_iocbq *iocb, *next_iocb;
+
+	if (pring->ringno == LPFC_ELS_RING)
+		lpfc_fabric_abort_hba(phba);
+
+	spin_lock_irq(&phba->hbalock);
+	/* Next issue ABTS for everything on the txcmplq */
+	list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
+		lpfc_sli4_abort_nvme_io(phba, pring, iocb);
+	spin_unlock_irq(&phba->hbalock);
+}
+
+
 /**
  * lpfc_sli_abort_fcp_rings - Abort all iocbs in all FCP rings
  * @phba: Pointer to HBA context object.
@@ -3617,15 +3633,40 @@ lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba)
 	/* Look on all the FCP Rings for the iotag */
 	if (phba->sli_rev >= LPFC_SLI_REV4) {
 		for (i = 0; i < phba->cfg_fcp_io_channel; i++) {
-			pring = &psli->ring[i + MAX_SLI3_CONFIGURED_RINGS];
+			pring = phba->sli4_hba.fcp_wq[i]->pring;
 			lpfc_sli_abort_iocb_ring(phba, pring);
 		}
 	} else {
-		pring = &psli->ring[psli->fcp_ring];
+		pring = &psli->sli3_ring[LPFC_FCP_RING];
 		lpfc_sli_abort_iocb_ring(phba, pring);
 	}
 }
 
+/**
+ * lpfc_sli_abort_nvme_rings - Abort all wqes in all NVME rings
+ * @phba: Pointer to HBA context object.
+ *
+ * This function aborts all wqes in NVME rings. This function issues an
+ * abort wqe for all the outstanding IO commands in txcmplq. The iocbs in
+ * the txcmplq is not guaranteed to complete before the return of this
+ * function. The caller is not required to hold any locks.
+ **/
+void
+lpfc_sli_abort_nvme_rings(struct lpfc_hba *phba)
+{
+	struct lpfc_sli_ring  *pring;
+	uint32_t i;
+
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		return;
+
+	/* Abort all IO on each NVME ring. */
+	for (i = 0; i < phba->cfg_nvme_io_channel; i++) {
+		pring = phba->sli4_hba.nvme_wq[i]->pring;
+		lpfc_sli_abort_wqe_ring(phba, pring);
+	}
+}
+
 
 /**
  * lpfc_sli_flush_fcp_rings - flush all iocbs in the fcp ring
@@ -3654,7 +3695,7 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba)
 	/* Look on all the FCP Rings for the iotag */
 	if (phba->sli_rev >= LPFC_SLI_REV4) {
 		for (i = 0; i < phba->cfg_fcp_io_channel; i++) {
-			pring = &psli->ring[i + MAX_SLI3_CONFIGURED_RINGS];
+			pring = phba->sli4_hba.fcp_wq[i]->pring;
 
 			spin_lock_irq(&pring->ring_lock);
 			/* Retrieve everything on txq */
@@ -3675,7 +3716,7 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba)
 					      IOERR_SLI_DOWN);
 		}
 	} else {
-		pring = &psli->ring[psli->fcp_ring];
+		pring = &psli->sli3_ring[LPFC_FCP_RING];
 
 		spin_lock_irq(&phba->hbalock);
 		/* Retrieve everything on txq */
@@ -3695,6 +3736,51 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba)
 	}
 }
 
+/**
+ * lpfc_sli_flush_nvme_rings - flush all wqes in the nvme rings
+ * @phba: Pointer to HBA context object.
+ *
+ * This function flushes all wqes in the nvme rings and frees all resources
+ * in the txcmplq. This function does not issue abort wqes for the IO
+ * commands in txcmplq, they will just be returned with
+ * IOERR_SLI_DOWN. This function is invoked with EEH when device's PCI
+ * slot has been permanently disabled.
+ **/
+void
+lpfc_sli_flush_nvme_rings(struct lpfc_hba *phba)
+{
+	LIST_HEAD(txcmplq);
+	struct lpfc_sli_ring  *pring;
+	uint32_t i;
+
+	if (phba->sli_rev < LPFC_SLI_REV4)
+		return;
+
+	/* Hint to other driver operations that a flush is in progress. */
+	spin_lock_irq(&phba->hbalock);
+	phba->hba_flag |= HBA_NVME_IOQ_FLUSH;
+	spin_unlock_irq(&phba->hbalock);
+
+	/* Cycle through all NVME rings and complete each IO with
+	 * a local driver reason code.  This is a flush so no
+	 * abort exchange to FW.
+	 */
+	for (i = 0; i < phba->cfg_nvme_io_channel; i++) {
+		pring = phba->sli4_hba.nvme_wq[i]->pring;
+
+		/* Retrieve everything on the txcmplq */
+		spin_lock_irq(&pring->ring_lock);
+		list_splice_init(&pring->txcmplq, &txcmplq);
+		pring->txcmplq_cnt = 0;
+		spin_unlock_irq(&pring->ring_lock);
+
+		/* Flush the txcmpq &&&PAE */
+		lpfc_sli_cancel_iocbs(phba, &txcmplq,
+				      IOSTAT_LOCAL_REJECT,
+				      IOERR_SLI_DOWN);
+	}
+}
+
 /**
  * lpfc_sli_brdready_s3 - Check for sli3 host ready status
  * @phba: Pointer to HBA context object.
@@ -4069,7 +4155,7 @@ lpfc_sli_brdreset(struct lpfc_hba *phba)
 
 	/* Initialize relevant SLI info */
 	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
+		pring = &psli->sli3_ring[i];
 		pring->flag = 0;
 		pring->sli.sli3.rspidx = 0;
 		pring->sli.sli3.next_cmdidx  = 0;
@@ -4498,10 +4584,11 @@ static int
 lpfc_sli4_rb_setup(struct lpfc_hba *phba)
 {
 	phba->hbq_in_use = 1;
-	phba->hbqs[0].entry_count = lpfc_hbq_defs[0]->entry_count;
+	phba->hbqs[LPFC_ELS_HBQ].entry_count =
+		lpfc_hbq_defs[LPFC_ELS_HBQ]->entry_count;
 	phba->hbq_count = 1;
+	lpfc_sli_hbqbuf_init_hbqs(phba, LPFC_ELS_HBQ);
 	/* Initially populate or replenish the HBQs */
-	lpfc_sli_hbqbuf_init_hbqs(phba, 0);
 	return 0;
 }
 
@@ -5107,27 +5194,31 @@ lpfc_sli4_retrieve_pport_name(struct lpfc_hba *phba)
 static void
 lpfc_sli4_arm_cqeq_intr(struct lpfc_hba *phba)
 {
-	int fcp_eqidx;
+	int qidx;
 
 	lpfc_sli4_cq_release(phba->sli4_hba.mbx_cq, LPFC_QUEUE_REARM);
 	lpfc_sli4_cq_release(phba->sli4_hba.els_cq, LPFC_QUEUE_REARM);
-	fcp_eqidx = 0;
-	if (phba->sli4_hba.fcp_cq) {
-		do {
-			lpfc_sli4_cq_release(phba->sli4_hba.fcp_cq[fcp_eqidx],
-					     LPFC_QUEUE_REARM);
-		} while (++fcp_eqidx < phba->cfg_fcp_io_channel);
-	}
+	if (phba->sli4_hba.nvmels_cq)
+		lpfc_sli4_cq_release(phba->sli4_hba.nvmels_cq,
+						LPFC_QUEUE_REARM);
+
+	if (phba->sli4_hba.fcp_cq)
+		for (qidx = 0; qidx < phba->cfg_fcp_io_channel; qidx++)
+			lpfc_sli4_cq_release(phba->sli4_hba.fcp_cq[qidx],
+						LPFC_QUEUE_REARM);
+
+	if (phba->sli4_hba.nvme_cq)
+		for (qidx = 0; qidx < phba->cfg_nvme_io_channel; qidx++)
+			lpfc_sli4_cq_release(phba->sli4_hba.nvme_cq[qidx],
+						LPFC_QUEUE_REARM);
 
 	if (phba->cfg_fof)
 		lpfc_sli4_cq_release(phba->sli4_hba.oas_cq, LPFC_QUEUE_REARM);
 
-	if (phba->sli4_hba.hba_eq) {
-		for (fcp_eqidx = 0; fcp_eqidx < phba->cfg_fcp_io_channel;
-		     fcp_eqidx++)
-			lpfc_sli4_eq_release(phba->sli4_hba.hba_eq[fcp_eqidx],
-					     LPFC_QUEUE_REARM);
-	}
+	if (phba->sli4_hba.hba_eq)
+		for (qidx = 0; qidx < phba->io_channel_irqs; qidx++)
+			lpfc_sli4_eq_release(phba->sli4_hba.hba_eq[qidx],
+						LPFC_QUEUE_REARM);
 
 	if (phba->cfg_fof)
 		lpfc_sli4_eq_release(phba->sli4_hba.fof_eq, LPFC_QUEUE_REARM);
@@ -5560,9 +5651,13 @@ lpfc_sli4_alloc_extent(struct lpfc_hba *phba, uint16_t type)
 		rsrc_blks->rsrc_size = rsrc_size;
 		list_add_tail(&rsrc_blks->list, ext_blk_list);
 		rsrc_start = rsrc_id;
-		if ((type == LPFC_RSC_TYPE_FCOE_XRI) && (j == 0))
+		if ((type == LPFC_RSC_TYPE_FCOE_XRI) && (j == 0)) {
 			phba->sli4_hba.scsi_xri_start = rsrc_start +
-				lpfc_sli4_get_els_iocb_cnt(phba);
+				lpfc_sli4_get_iocb_cnt(phba);
+			phba->sli4_hba.nvme_xri_start =
+				phba->sli4_hba.scsi_xri_start +
+				phba->sli4_hba.scsi_xri_max;
+		}
 
 		while (rsrc_id < (rsrc_start + rsrc_size)) {
 			ids[j] = rsrc_id;
@@ -5578,6 +5673,8 @@ lpfc_sli4_alloc_extent(struct lpfc_hba *phba, uint16_t type)
 	return rc;
 }
 
+
+
 /**
  * lpfc_sli4_dealloc_extent - Deallocate an SLI4 resource extent.
  * @phba: Pointer to HBA context object.
@@ -6156,42 +6253,45 @@ lpfc_sli4_get_allocated_extnts(struct lpfc_hba *phba, uint16_t type,
 }
 
 /**
- * lpfc_sli4_repost_els_sgl_list - Repsot the els buffers sgl pages as block
+ * lpfc_sli4_repost_sgl_list - Repsot the buffers sgl pages as block
  * @phba: pointer to lpfc hba data structure.
+ * @pring: Pointer to driver SLI ring object.
+ * @sgl_list: linked link of sgl buffers to post
+ * @cnt: number of linked list buffers
  *
- * This routine walks the list of els buffers that have been allocated and
+ * This routine walks the list of buffers that have been allocated and
  * repost them to the port by using SGL block post. This is needed after a
  * pci_function_reset/warm_start or start. It attempts to construct blocks
- * of els buffer sgls which contains contiguous xris and uses the non-embedded
- * SGL block post mailbox commands to post them to the port. For single els
+ * of buffer sgls which contains contiguous xris and uses the non-embedded
+ * SGL block post mailbox commands to post them to the port. For single
  * buffer sgl with non-contiguous xri, if any, it shall use embedded SGL post
  * mailbox command for posting.
  *
  * Returns: 0 = success, non-zero failure.
  **/
 static int
-lpfc_sli4_repost_els_sgl_list(struct lpfc_hba *phba)
+lpfc_sli4_repost_sgl_list(struct lpfc_hba *phba,
+			  struct list_head *sgl_list, int cnt)
 {
 	struct lpfc_sglq *sglq_entry = NULL;
 	struct lpfc_sglq *sglq_entry_next = NULL;
 	struct lpfc_sglq *sglq_entry_first = NULL;
-	int status, total_cnt, post_cnt = 0, num_posted = 0, block_cnt = 0;
+	int status, total_cnt;
+	int post_cnt = 0, num_posted = 0, block_cnt = 0;
 	int last_xritag = NO_XRI;
-	struct lpfc_sli_ring *pring;
 	LIST_HEAD(prep_sgl_list);
 	LIST_HEAD(blck_sgl_list);
 	LIST_HEAD(allc_sgl_list);
 	LIST_HEAD(post_sgl_list);
 	LIST_HEAD(free_sgl_list);
 
-	pring = &phba->sli.ring[LPFC_ELS_RING];
 	spin_lock_irq(&phba->hbalock);
-	spin_lock(&pring->ring_lock);
-	list_splice_init(&phba->sli4_hba.lpfc_sgl_list, &allc_sgl_list);
-	spin_unlock(&pring->ring_lock);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
+	list_splice_init(sgl_list, &allc_sgl_list);
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	spin_unlock_irq(&phba->hbalock);
 
-	total_cnt = phba->sli4_hba.els_xri_cnt;
+	total_cnt = cnt;
 	list_for_each_entry_safe(sglq_entry, sglq_entry_next,
 				 &allc_sgl_list, list) {
 		list_del_init(&sglq_entry->list);
@@ -6220,8 +6320,8 @@ lpfc_sli4_repost_els_sgl_list(struct lpfc_hba *phba)
 		/* keep track of last sgl's xritag */
 		last_xritag = sglq_entry->sli4_xritag;
 
-		/* end of repost sgl list condition for els buffers */
-		if (num_posted == phba->sli4_hba.els_xri_cnt) {
+		/* end of repost sgl list condition for buffers */
+		if (num_posted == total_cnt) {
 			if (post_cnt == 0) {
 				list_splice_init(&prep_sgl_list,
 						 &blck_sgl_list);
@@ -6238,7 +6338,7 @@ lpfc_sli4_repost_els_sgl_list(struct lpfc_hba *phba)
 					/* Failure, put sgl to free list */
 					lpfc_printf_log(phba, KERN_WARNING,
 						LOG_SLI,
-						"3159 Failed to post els "
+						"3159 Failed to post "
 						"sgl, xritag:x%x\n",
 						sglq_entry->sli4_xritag);
 					list_add_tail(&sglq_entry->list,
@@ -6252,9 +6352,9 @@ lpfc_sli4_repost_els_sgl_list(struct lpfc_hba *phba)
 		if (post_cnt == 0)
 			continue;
 
-		/* post the els buffer list sgls as a block */
-		status = lpfc_sli4_post_els_sgl_list(phba, &blck_sgl_list,
-						     post_cnt);
+		/* post the buffer list sgls as a block */
+		status = lpfc_sli4_post_sgl_list(phba, &blck_sgl_list,
+						 post_cnt);
 
 		if (!status) {
 			/* success, put sgl list to posted sgl list */
@@ -6265,7 +6365,7 @@ lpfc_sli4_repost_els_sgl_list(struct lpfc_hba *phba)
 							    struct lpfc_sglq,
 							    list);
 			lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
-					"3160 Failed to post els sgl-list, "
+					"3160 Failed to post sgl-list, "
 					"xritag:x%x-x%x\n",
 					sglq_entry_first->sli4_xritag,
 					(sglq_entry_first->sli4_xritag +
@@ -6278,29 +6378,28 @@ lpfc_sli4_repost_els_sgl_list(struct lpfc_hba *phba)
 		if (block_cnt == 0)
 			last_xritag = NO_XRI;
 
-		/* reset els sgl post count for next round of posting */
+		/* reset sgl post count for next round of posting */
 		post_cnt = 0;
 	}
-	/* update the number of XRIs posted for ELS */
-	phba->sli4_hba.els_xri_cnt = total_cnt;
 
-	/* free the els sgls failed to post */
+	/* free the sgls failed to post */
 	lpfc_free_sgl_list(phba, &free_sgl_list);
 
-	/* push els sgls posted to the availble list */
+	/* push sgls posted to the available list */
 	if (!list_empty(&post_sgl_list)) {
 		spin_lock_irq(&phba->hbalock);
-		spin_lock(&pring->ring_lock);
-		list_splice_init(&post_sgl_list,
-				 &phba->sli4_hba.lpfc_sgl_list);
-		spin_unlock(&pring->ring_lock);
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
+		list_splice_init(&post_sgl_list, sgl_list);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
 		spin_unlock_irq(&phba->hbalock);
 	} else {
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-				"3161 Failure to post els sgl to port.\n");
+				"3161 Failure to post sgl to port.\n");
 		return -EIO;
 	}
-	return 0;
+
+	/* return the number of XRIs actually posted */
+	return total_cnt;
 }
 
 void
@@ -6622,35 +6721,78 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	fc_host_node_name(shost) = wwn_to_u64(vport->fc_nodename.u.wwn);
 	fc_host_port_name(shost) = wwn_to_u64(vport->fc_portname.u.wwn);
 
-	/* update host els and scsi xri-sgl sizes and mappings */
-	rc = lpfc_sli4_xri_sgl_update(phba);
+	/* Create all the SLI4 queues */
+	rc = lpfc_sli4_queue_create(phba);
+	if (rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3089 Failed to allocate queues\n");
+		rc = -ENODEV;
+		goto out_free_mbox;
+	}
+	/* Set up all the queues to the device */
+	rc = lpfc_sli4_queue_setup(phba);
+	if (unlikely(rc)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+				"0381 Error %d during queue setup.\n ", rc);
+		goto out_stop_timers;
+	}
+	/* Initialize the driver internal SLI layer lists. */
+	lpfc_sli4_setup(phba);
+	lpfc_sli4_queue_init(phba);
+
+	/* update host els xri-sgl sizes and mappings */
+	rc = lpfc_sli4_els_sgl_update(phba);
 	if (unlikely(rc)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
 				"1400 Failed to update xri-sgl size and "
 				"mapping: %d\n", rc);
-		goto out_free_mbox;
+		goto out_destroy_queue;
 	}
 
 	/* register the els sgl pool to the port */
-	rc = lpfc_sli4_repost_els_sgl_list(phba);
-	if (unlikely(rc)) {
+	rc = lpfc_sli4_repost_sgl_list(phba, &phba->sli4_hba.lpfc_els_sgl_list,
+				       phba->sli4_hba.els_xri_cnt);
+	if (unlikely(rc < 0)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
 				"0582 Error %d during els sgl post "
 				"operation\n", rc);
 		rc = -ENODEV;
-		goto out_free_mbox;
+		goto out_destroy_queue;
 	}
+	phba->sli4_hba.els_xri_cnt = rc;
 
-	/* register the allocated scsi sgl pool to the port */
-	rc = lpfc_sli4_repost_scsi_sgl_list(phba);
-	if (unlikely(rc)) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
-				"0383 Error %d during scsi sgl post "
-				"operation\n", rc);
-		/* Some Scsi buffers were moved to the abort scsi list */
-		/* A pci function reset will repost them */
-		rc = -ENODEV;
-		goto out_free_mbox;
+	if (phba->nvmet_support == 0) {
+		/* update host scsi xri-sgl sizes and mappings */
+		rc = lpfc_sli4_scsi_sgl_update(phba);
+		if (unlikely(rc)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"6309 Failed to update scsi-sgl size "
+					"and mapping: %d\n", rc);
+			goto out_destroy_queue;
+		}
+
+		/* update host nvme xri-sgl sizes and mappings */
+		rc = lpfc_sli4_nvme_sgl_update(phba);
+		if (unlikely(rc)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"6082 Failed to update nvme-sgl size "
+					"and mapping: %d\n", rc);
+			goto out_destroy_queue;
+		}
+	}
+
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
+		/* register the allocated scsi sgl pool to the port */
+		rc = lpfc_sli4_repost_scsi_sgl_list(phba);
+		if (unlikely(rc)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"0383 Error %d during scsi sgl post "
+					"operation\n", rc);
+			/* Some Scsi buffers were moved to abort scsi list */
+			/* A pci function reset will repost them */
+			rc = -ENODEV;
+			goto out_destroy_queue;
+		}
 	}
 
 	/* Post the rpi header region to the device. */
@@ -6660,24 +6802,26 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 				"0393 Error %d during rpi post operation\n",
 				rc);
 		rc = -ENODEV;
-		goto out_free_mbox;
+		goto out_destroy_queue;
 	}
 	lpfc_sli4_node_prep(phba);
 
-	/* Create all the SLI4 queues */
-	rc = lpfc_sli4_queue_create(phba);
-	if (rc) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"3089 Failed to allocate queues\n");
-		rc = -ENODEV;
-		goto out_stop_timers;
-	}
-	/* Set up all the queues to the device */
-	rc = lpfc_sli4_queue_setup(phba);
-	if (unlikely(rc)) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
-				"0381 Error %d during queue setup.\n ", rc);
-		goto out_destroy_queue;
+	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
+		if (phba->nvmet_support == 0) {
+			/*
+			 * The FC Port needs to register FCFI (index 0)
+			 */
+			lpfc_reg_fcfi(phba, mboxq);
+			mboxq->vport = phba->pport;
+			rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+			if (rc != MBX_SUCCESS)
+				goto out_unset_queue;
+			rc = 0;
+			phba->fcf.fcfi = bf_get(lpfc_reg_fcfi_fcfi,
+						&mboxq->u.mqe.un.reg_fcfi);
+		}
+		/* Check if the port is configured to be disabled */
+		lpfc_sli_read_link_ste(phba);
 	}
 
 	/* Arm the CQs and then EQs on device */
@@ -6731,23 +6875,6 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		rc = 0;
 	}
 
-	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
-		/*
-		 * The FC Port needs to register FCFI (index 0)
-		 */
-		lpfc_reg_fcfi(phba, mboxq);
-		mboxq->vport = phba->pport;
-		rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
-		if (rc != MBX_SUCCESS)
-			goto out_unset_queue;
-		rc = 0;
-		phba->fcf.fcfi = bf_get(lpfc_reg_fcfi_fcfi,
-					&mboxq->u.mqe.un.reg_fcfi);
-
-		/* Check if the port is configured to be disabled */
-		lpfc_sli_read_link_ste(phba);
-	}
-
 	/*
 	 * The port is ready, set the host's link state to LINK_DOWN
 	 * in preparation for link interrupts.
@@ -6884,7 +7011,7 @@ lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba)
 	/* Find the eq associated with the mcq */
 
 	if (phba->sli4_hba.hba_eq)
-		for (eqidx = 0; eqidx < phba->cfg_fcp_io_channel; eqidx++)
+		for (eqidx = 0; eqidx < phba->io_channel_irqs; eqidx++)
 			if (phba->sli4_hba.hba_eq[eqidx]->queue_id ==
 			    phba->sli4_hba.mbx_cq->assoc_qid) {
 				fpeq = phba->sli4_hba.hba_eq[eqidx];
@@ -7243,16 +7370,15 @@ lpfc_sli_issue_mbox_s3(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmbox,
 				= MAILBOX_HBA_EXT_OFFSET;
 
 		/* Copy the mailbox extension data */
-		if (pmbox->in_ext_byte_len && pmbox->context2) {
+		if (pmbox->in_ext_byte_len && pmbox->context2)
 			lpfc_memcpy_to_slim(phba->MBslimaddr +
 				MAILBOX_HBA_EXT_OFFSET,
 				pmbox->context2, pmbox->in_ext_byte_len);
 
-		}
-		if (mbx->mbxCommand == MBX_CONFIG_PORT) {
+		if (mbx->mbxCommand == MBX_CONFIG_PORT)
 			/* copy command data into host mbox for cmpl */
-			lpfc_sli_pcimem_bcopy(mbx, phba->mbox, MAILBOX_CMD_SIZE);
-		}
+			lpfc_sli_pcimem_bcopy(mbx, phba->mbox,
+					      MAILBOX_CMD_SIZE);
 
 		/* First copy mbox command data to HBA SLIM, skip past first
 		   word */
@@ -7266,10 +7392,9 @@ lpfc_sli_issue_mbox_s3(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmbox,
 		writel(ldata, to_slim);
 		readl(to_slim); /* flush */
 
-		if (mbx->mbxCommand == MBX_CONFIG_PORT) {
+		if (mbx->mbxCommand == MBX_CONFIG_PORT)
 			/* switch over to host mailbox */
 			psli->sli_flag |= LPFC_SLI_ACTIVE;
-		}
 	}
 
 	wmb();
@@ -8060,7 +8185,7 @@ __lpfc_sli_issue_iocb_s3(struct lpfc_hba *phba, uint32_t ring_number,
 {
 	struct lpfc_iocbq *nextiocb;
 	IOCB_t *iocb;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[ring_number];
+	struct lpfc_sli_ring *pring = &phba->sli.sli3_ring[ring_number];
 
 	lockdep_assert_held(&phba->hbalock);
 
@@ -8134,7 +8259,7 @@ __lpfc_sli_issue_iocb_s3(struct lpfc_hba *phba, uint32_t ring_number,
 	 * For FCP commands, we must be in a state where we can process link
 	 * attention events.
 	 */
-	} else if (unlikely(pring->ringno == phba->sli.fcp_ring &&
+	} else if (unlikely(pring->ringno == LPFC_FCP_RING &&
 			    !(phba->sli.sli_flag & LPFC_PROCESS_LA))) {
 		goto iocb_busy;
 	}
@@ -8871,9 +8996,21 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	union lpfc_wqe *wqe;
 	union lpfc_wqe128 wqe128;
 	struct lpfc_queue *wq;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[ring_number];
+	struct lpfc_sli_ring *pring;
 
-	lockdep_assert_held(&phba->hbalock);
+	/* Get the WQ */
+	if ((piocb->iocb_flag & LPFC_IO_FCP) ||
+	    (piocb->iocb_flag & LPFC_USE_FCPWQIDX)) {
+		if (!phba->cfg_fof || (!(piocb->iocb_flag & LPFC_IO_OAS)))
+			wq = phba->sli4_hba.fcp_wq[piocb->hba_wqidx];
+		else
+			wq = phba->sli4_hba.oas_wq;
+	} else {
+		wq = phba->sli4_hba.els_wq;
+	}
+
+	/* Get corresponding ring */
+	pring = wq->pring;
 
 	/*
 	 * The WQE can be either 64 or 128 bytes,
@@ -8881,6 +9018,8 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	 */
 	wqe = (union lpfc_wqe *)&wqe128;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	if (piocb->sli4_xritag == NO_XRI) {
 		if (piocb->iocb.ulpCommand == CMD_ABORT_XRI_CN ||
 		    piocb->iocb.ulpCommand == CMD_CLOSE_XRI_CN)
@@ -8895,7 +9034,7 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 					return IOCB_BUSY;
 				}
 			} else {
-				sglq = __lpfc_sli_get_sglq(phba, piocb);
+				sglq = __lpfc_sli_get_els_sglq(phba, piocb);
 				if (!sglq) {
 					if (!(flag & SLI_IOCB_RET_IOCB)) {
 						__lpfc_sli_ringtx_put(phba,
@@ -8930,21 +9069,8 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	if (lpfc_sli4_iocb2wqe(phba, piocb, wqe))
 		return IOCB_ERROR;
 
-	if ((piocb->iocb_flag & LPFC_IO_FCP) ||
-	    (piocb->iocb_flag & LPFC_USE_FCPWQIDX)) {
-		if (!phba->cfg_fof || (!(piocb->iocb_flag & LPFC_IO_OAS))) {
-			wq = phba->sli4_hba.fcp_wq[piocb->fcp_wqidx];
-		} else {
-			wq = phba->sli4_hba.oas_wq;
-		}
-		if (lpfc_sli4_wq_put(wq, wqe))
-			return IOCB_ERROR;
-	} else {
-		if (unlikely(!phba->sli4_hba.els_wq))
-			return IOCB_ERROR;
-		if (lpfc_sli4_wq_put(phba->sli4_hba.els_wq, wqe))
-			return IOCB_ERROR;
-	}
+	if (lpfc_sli4_wq_put(wq, wqe))
+		return IOCB_ERROR;
 	lpfc_sli_ringtxcmpl_put(phba, pring, piocb);
 
 	return 0;
@@ -9002,46 +9128,44 @@ lpfc_sli_api_table_setup(struct lpfc_hba *phba, uint8_t dev_grp)
 }
 
 /**
- * lpfc_sli_calc_ring - Calculates which ring to use
+ * lpfc_sli4_calc_ring - Calculates which ring to use
  * @phba: Pointer to HBA context object.
- * @ring_number: Initial ring
  * @piocb: Pointer to command iocb.
  *
- * For SLI4, FCP IO can deferred to one fo many WQs, based on
- * fcp_wqidx, thus we need to calculate the corresponding ring.
+ * For SLI4 only, FCP IO can deferred to one fo many WQs, based on
+ * hba_wqidx, thus we need to calculate the corresponding ring.
  * Since ABORTS must go on the same WQ of the command they are
- * aborting, we use command's fcp_wqidx.
+ * aborting, we use command's hba_wqidx.
  */
-static int
-lpfc_sli_calc_ring(struct lpfc_hba *phba, uint32_t ring_number,
-		    struct lpfc_iocbq *piocb)
+struct lpfc_sli_ring *
+lpfc_sli4_calc_ring(struct lpfc_hba *phba, struct lpfc_iocbq *piocb)
 {
-	if (phba->sli_rev < LPFC_SLI_REV4)
-		return ring_number;
-
-	if (piocb->iocb_flag &  (LPFC_IO_FCP | LPFC_USE_FCPWQIDX)) {
+	if (piocb->iocb_flag & (LPFC_IO_FCP | LPFC_USE_FCPWQIDX)) {
 		if (!(phba->cfg_fof) ||
-				(!(piocb->iocb_flag & LPFC_IO_FOF))) {
+		    (!(piocb->iocb_flag & LPFC_IO_FOF))) {
 			if (unlikely(!phba->sli4_hba.fcp_wq))
-				return LPFC_HBA_ERROR;
+				return NULL;
 			/*
-			 * for abort iocb fcp_wqidx should already
+			 * for abort iocb hba_wqidx should already
 			 * be setup based on what work queue we used.
 			 */
 			if (!(piocb->iocb_flag & LPFC_USE_FCPWQIDX))
-				piocb->fcp_wqidx =
+				piocb->hba_wqidx =
 					lpfc_sli4_scmd_to_wqidx_distr(phba,
 							      piocb->context1);
-			ring_number = MAX_SLI3_CONFIGURED_RINGS +
-				piocb->fcp_wqidx;
+			return phba->sli4_hba.fcp_wq[piocb->hba_wqidx]->pring;
 		} else {
 			if (unlikely(!phba->sli4_hba.oas_wq))
-				return LPFC_HBA_ERROR;
-			piocb->fcp_wqidx = 0;
-			ring_number =  LPFC_FCP_OAS_RING;
+				return NULL;
+			piocb->hba_wqidx = 0;
+			return phba->sli4_hba.oas_wq->pring;
 		}
+	} else {
+		if (unlikely(!phba->sli4_hba.els_wq))
+			return NULL;
+		piocb->hba_wqidx = 0;
+		return phba->sli4_hba.els_wq->pring;
 	}
-	return ring_number;
 }
 
 /**
@@ -9061,7 +9185,7 @@ int
 lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 		    struct lpfc_iocbq *piocb, uint32_t flag)
 {
-	struct lpfc_fcp_eq_hdl *fcp_eq_hdl;
+	struct lpfc_hba_eq_hdl *hba_eq_hdl;
 	struct lpfc_sli_ring *pring;
 	struct lpfc_queue *fpeq;
 	struct lpfc_eqe *eqe;
@@ -9069,21 +9193,19 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 	int rc, idx;
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
-		ring_number = lpfc_sli_calc_ring(phba, ring_number, piocb);
-		if (unlikely(ring_number == LPFC_HBA_ERROR))
+		pring = lpfc_sli4_calc_ring(phba, piocb);
+		if (unlikely(pring == NULL))
 			return IOCB_ERROR;
-		idx = piocb->fcp_wqidx;
 
-		pring = &phba->sli.ring[ring_number];
 		spin_lock_irqsave(&pring->ring_lock, iflags);
 		rc = __lpfc_sli_issue_iocb(phba, ring_number, piocb, flag);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
 
 		if (lpfc_fcp_look_ahead && (piocb->iocb_flag &  LPFC_IO_FCP)) {
-			fcp_eq_hdl = &phba->sli4_hba.fcp_eq_hdl[idx];
+			idx = piocb->hba_wqidx;
+			hba_eq_hdl = &phba->sli4_hba.hba_eq_hdl[idx];
 
-			if (atomic_dec_and_test(&fcp_eq_hdl->
-				fcp_eq_in_use)) {
+			if (atomic_dec_and_test(&hba_eq_hdl->hba_eq_in_use)) {
 
 				/* Get associated EQ with this index */
 				fpeq = phba->sli4_hba.hba_eq[idx];
@@ -9104,7 +9226,7 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 				lpfc_sli4_eq_release(fpeq,
 					LPFC_QUEUE_REARM);
 			}
-			atomic_inc(&fcp_eq_hdl->fcp_eq_in_use);
+			atomic_inc(&hba_eq_hdl->hba_eq_in_use);
 		}
 	} else {
 		/* For now, SLI2/3 will still use hbalock */
@@ -9124,7 +9246,7 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
  * only when driver needs to support target mode functionality
  * or IP over FC functionalities.
  *
- * This function is called with no lock held.
+ * This function is called with no lock held. SLI3 only.
  **/
 static int
 lpfc_extra_ring_setup( struct lpfc_hba *phba)
@@ -9137,14 +9259,14 @@ lpfc_extra_ring_setup( struct lpfc_hba *phba)
 	/* Adjust cmd/rsp ring iocb entries more evenly */
 
 	/* Take some away from the FCP ring */
-	pring = &psli->ring[psli->fcp_ring];
+	pring = &psli->sli3_ring[LPFC_FCP_RING];
 	pring->sli.sli3.numCiocb -= SLI2_IOCB_CMD_R1XTRA_ENTRIES;
 	pring->sli.sli3.numRiocb -= SLI2_IOCB_RSP_R1XTRA_ENTRIES;
 	pring->sli.sli3.numCiocb -= SLI2_IOCB_CMD_R3XTRA_ENTRIES;
 	pring->sli.sli3.numRiocb -= SLI2_IOCB_RSP_R3XTRA_ENTRIES;
 
 	/* and give them to the extra ring */
-	pring = &psli->ring[psli->extra_ring];
+	pring = &psli->sli3_ring[LPFC_EXTRA_RING];
 
 	pring->sli.sli3.numCiocb += SLI2_IOCB_CMD_R1XTRA_ENTRIES;
 	pring->sli.sli3.numRiocb += SLI2_IOCB_RSP_R1XTRA_ENTRIES;
@@ -9329,7 +9451,7 @@ lpfc_sli_async_event_handler(struct lpfc_hba * phba,
 
 
 /**
- * lpfc_sli_setup - SLI ring setup function
+ * lpfc_sli4_setup - SLI ring setup function
  * @phba: Pointer to HBA context object.
  *
  * lpfc_sli_setup sets up rings of the SLI interface with
@@ -9340,6 +9462,51 @@ lpfc_sli_async_event_handler(struct lpfc_hba * phba,
  * This function always returns 0.
  **/
 int
+lpfc_sli4_setup(struct lpfc_hba *phba)
+{
+	struct lpfc_sli_ring *pring;
+
+	pring = phba->sli4_hba.els_wq->pring;
+	pring->num_mask = LPFC_MAX_RING_MASK;
+	pring->prt[0].profile = 0;	/* Mask 0 */
+	pring->prt[0].rctl = FC_RCTL_ELS_REQ;
+	pring->prt[0].type = FC_TYPE_ELS;
+	pring->prt[0].lpfc_sli_rcv_unsol_event =
+	    lpfc_els_unsol_event;
+	pring->prt[1].profile = 0;	/* Mask 1 */
+	pring->prt[1].rctl = FC_RCTL_ELS_REP;
+	pring->prt[1].type = FC_TYPE_ELS;
+	pring->prt[1].lpfc_sli_rcv_unsol_event =
+	    lpfc_els_unsol_event;
+	pring->prt[2].profile = 0;	/* Mask 2 */
+	/* NameServer Inquiry */
+	pring->prt[2].rctl = FC_RCTL_DD_UNSOL_CTL;
+	/* NameServer */
+	pring->prt[2].type = FC_TYPE_CT;
+	pring->prt[2].lpfc_sli_rcv_unsol_event =
+	    lpfc_ct_unsol_event;
+	pring->prt[3].profile = 0;	/* Mask 3 */
+	/* NameServer response */
+	pring->prt[3].rctl = FC_RCTL_DD_SOL_CTL;
+	/* NameServer */
+	pring->prt[3].type = FC_TYPE_CT;
+	pring->prt[3].lpfc_sli_rcv_unsol_event =
+	    lpfc_ct_unsol_event;
+	return 0;
+}
+
+/**
+ * lpfc_sli_setup - SLI ring setup function
+ * @phba: Pointer to HBA context object.
+ *
+ * lpfc_sli_setup sets up rings of the SLI interface with
+ * number of iocbs per ring and iotags. This function is
+ * called while driver attach to the HBA and before the
+ * interrupts are enabled. So there is no need for locking.
+ *
+ * This function always returns 0. SLI3 only.
+ **/
+int
 lpfc_sli_setup(struct lpfc_hba *phba)
 {
 	int i, totiocbsize = 0;
@@ -9347,19 +9514,14 @@ lpfc_sli_setup(struct lpfc_hba *phba)
 	struct lpfc_sli_ring *pring;
 
 	psli->num_rings = MAX_SLI3_CONFIGURED_RINGS;
-	if (phba->sli_rev == LPFC_SLI_REV4)
-		psli->num_rings += phba->cfg_fcp_io_channel;
 	psli->sli_flag = 0;
-	psli->fcp_ring = LPFC_FCP_RING;
-	psli->next_ring = LPFC_FCP_NEXT_RING;
-	psli->extra_ring = LPFC_EXTRA_RING;
 
 	psli->iocbq_lookup = NULL;
 	psli->iocbq_lookup_len = 0;
 	psli->last_iotag = 0;
 
 	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
+		pring = &psli->sli3_ring[i];
 		switch (i) {
 		case LPFC_FCP_RING:	/* ring 0 - FCP */
 			/* numCiocb and numRiocb are used in config_port */
@@ -9458,18 +9620,18 @@ lpfc_sli_setup(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_sli_queue_setup - Queue initialization function
+ * lpfc_sli4_queue_init - Queue initialization function
  * @phba: Pointer to HBA context object.
  *
- * lpfc_sli_queue_setup sets up mailbox queues and iocb queues for each
+ * lpfc_sli4_queue_init sets up mailbox queues and iocb queues for each
  * ring. This function also initializes ring indices of each ring.
  * This function is called during the initialization of the SLI
  * interface of an HBA.
  * This function is called with no lock held and always returns
  * 1.
  **/
-int
-lpfc_sli_queue_setup(struct lpfc_hba *phba)
+void
+lpfc_sli4_queue_init(struct lpfc_hba *phba)
 {
 	struct lpfc_sli *psli;
 	struct lpfc_sli_ring *pring;
@@ -9480,31 +9642,102 @@ lpfc_sli_queue_setup(struct lpfc_hba *phba)
 	INIT_LIST_HEAD(&psli->mboxq);
 	INIT_LIST_HEAD(&psli->mboxq_cmpl);
 	/* Initialize list headers for txq and txcmplq as double linked lists */
-	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
-		pring->ringno = i;
-		pring->sli.sli3.next_cmdidx  = 0;
-		pring->sli.sli3.local_getidx = 0;
-		pring->sli.sli3.cmdidx = 0;
+	for (i = 0; i < phba->cfg_fcp_io_channel; i++) {
+		pring = phba->sli4_hba.fcp_wq[i]->pring;
 		pring->flag = 0;
+		pring->ringno = LPFC_FCP_RING;
 		INIT_LIST_HEAD(&pring->txq);
 		INIT_LIST_HEAD(&pring->txcmplq);
 		INIT_LIST_HEAD(&pring->iocb_continueq);
-		INIT_LIST_HEAD(&pring->iocb_continue_saveq);
-		INIT_LIST_HEAD(&pring->postbufq);
 		spin_lock_init(&pring->ring_lock);
 	}
-	spin_unlock_irq(&phba->hbalock);
-	return 1;
-}
+	for (i = 0; i < phba->cfg_nvme_io_channel; i++) {
+		pring = phba->sli4_hba.nvme_wq[i]->pring;
+		pring->flag = 0;
+		pring->ringno = LPFC_FCP_RING;
+		INIT_LIST_HEAD(&pring->txq);
+		INIT_LIST_HEAD(&pring->txcmplq);
+		INIT_LIST_HEAD(&pring->iocb_continueq);
+		spin_lock_init(&pring->ring_lock);
+	}
+	pring = phba->sli4_hba.els_wq->pring;
+	pring->flag = 0;
+	pring->ringno = LPFC_ELS_RING;
+	INIT_LIST_HEAD(&pring->txq);
+	INIT_LIST_HEAD(&pring->txcmplq);
+	INIT_LIST_HEAD(&pring->iocb_continueq);
+	spin_lock_init(&pring->ring_lock);
 
-/**
- * lpfc_sli_mbox_sys_flush - Flush mailbox command sub-system
- * @phba: Pointer to HBA context object.
- *
- * This routine flushes the mailbox command subsystem. It will unconditionally
- * flush all the mailbox commands in the three possible stages in the mailbox
- * command sub-system: pending mailbox command queue; the outstanding mailbox
+	if (phba->cfg_nvme_io_channel) {
+		pring = phba->sli4_hba.nvmels_wq->pring;
+		pring->flag = 0;
+		pring->ringno = LPFC_ELS_RING;
+		INIT_LIST_HEAD(&pring->txq);
+		INIT_LIST_HEAD(&pring->txcmplq);
+		INIT_LIST_HEAD(&pring->iocb_continueq);
+		spin_lock_init(&pring->ring_lock);
+	}
+
+	if (phba->cfg_fof) {
+		pring = phba->sli4_hba.oas_wq->pring;
+		pring->flag = 0;
+		pring->ringno = LPFC_FCP_RING;
+		INIT_LIST_HEAD(&pring->txq);
+		INIT_LIST_HEAD(&pring->txcmplq);
+		INIT_LIST_HEAD(&pring->iocb_continueq);
+		spin_lock_init(&pring->ring_lock);
+	}
+
+	spin_unlock_irq(&phba->hbalock);
+}
+
+/**
+ * lpfc_sli_queue_init - Queue initialization function
+ * @phba: Pointer to HBA context object.
+ *
+ * lpfc_sli_queue_init sets up mailbox queues and iocb queues for each
+ * ring. This function also initializes ring indices of each ring.
+ * This function is called during the initialization of the SLI
+ * interface of an HBA.
+ * This function is called with no lock held and always returns
+ * 1.
+ **/
+void
+lpfc_sli_queue_init(struct lpfc_hba *phba)
+{
+	struct lpfc_sli *psli;
+	struct lpfc_sli_ring *pring;
+	int i;
+
+	psli = &phba->sli;
+	spin_lock_irq(&phba->hbalock);
+	INIT_LIST_HEAD(&psli->mboxq);
+	INIT_LIST_HEAD(&psli->mboxq_cmpl);
+	/* Initialize list headers for txq and txcmplq as double linked lists */
+	for (i = 0; i < psli->num_rings; i++) {
+		pring = &psli->sli3_ring[i];
+		pring->ringno = i;
+		pring->sli.sli3.next_cmdidx  = 0;
+		pring->sli.sli3.local_getidx = 0;
+		pring->sli.sli3.cmdidx = 0;
+		INIT_LIST_HEAD(&pring->iocb_continueq);
+		INIT_LIST_HEAD(&pring->iocb_continue_saveq);
+		INIT_LIST_HEAD(&pring->postbufq);
+		pring->flag = 0;
+		INIT_LIST_HEAD(&pring->txq);
+		INIT_LIST_HEAD(&pring->txcmplq);
+		spin_lock_init(&pring->ring_lock);
+	}
+	spin_unlock_irq(&phba->hbalock);
+}
+
+/**
+ * lpfc_sli_mbox_sys_flush - Flush mailbox command sub-system
+ * @phba: Pointer to HBA context object.
+ *
+ * This routine flushes the mailbox command subsystem. It will unconditionally
+ * flush all the mailbox commands in the three possible stages in the mailbox
+ * command sub-system: pending mailbox command queue; the outstanding mailbox
  * command; and completed mailbox command queue. It is caller's responsibility
  * to make sure that the driver is in the proper state to flush the mailbox
  * command sub-system. Namely, the posting of mailbox commands into the
@@ -9567,6 +9800,7 @@ lpfc_sli_host_down(struct lpfc_vport *vport)
 	LIST_HEAD(completions);
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_queue *qp = NULL;
 	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *iocb, *next_iocb;
 	int i;
@@ -9576,36 +9810,64 @@ lpfc_sli_host_down(struct lpfc_vport *vport)
 	lpfc_cleanup_discovery_resources(vport);
 
 	spin_lock_irqsave(&phba->hbalock, flags);
-	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
-		prev_pring_flag = pring->flag;
-		/* Only slow rings */
-		if (pring->ringno == LPFC_ELS_RING) {
-			pring->flag |= LPFC_DEFERRED_RING_EVENT;
-			/* Set the lpfc data pending flag */
-			set_bit(LPFC_DATA_READY, &phba->data_flags);
-		}
-		/*
-		 * Error everything on the txq since these iocbs have not been
-		 * given to the FW yet.
-		 */
-		list_for_each_entry_safe(iocb, next_iocb, &pring->txq, list) {
-			if (iocb->vport != vport)
-				continue;
-			list_move_tail(&iocb->list, &completions);
-		}
 
-		/* Next issue ABTS for everything on the txcmplq */
-		list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq,
-									list) {
-			if (iocb->vport != vport)
+	/*
+	 * Error everything on the txq since these iocbs
+	 * have not been given to the FW yet.
+	 * Also issue ABTS for everything on the txcmplq
+	 */
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		for (i = 0; i < psli->num_rings; i++) {
+			pring = &psli->sli3_ring[i];
+			prev_pring_flag = pring->flag;
+			/* Only slow rings */
+			if (pring->ringno == LPFC_ELS_RING) {
+				pring->flag |= LPFC_DEFERRED_RING_EVENT;
+				/* Set the lpfc data pending flag */
+				set_bit(LPFC_DATA_READY, &phba->data_flags);
+			}
+			list_for_each_entry_safe(iocb, next_iocb,
+						 &pring->txq, list) {
+				if (iocb->vport != vport)
+					continue;
+				list_move_tail(&iocb->list, &completions);
+			}
+			list_for_each_entry_safe(iocb, next_iocb,
+						 &pring->txcmplq, list) {
+				if (iocb->vport != vport)
+					continue;
+				lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+			}
+			pring->flag = prev_pring_flag;
+		}
+	} else {
+		list_for_each_entry(qp, &phba->sli4_hba.lpfc_wq_list, wq_list) {
+			pring = qp->pring;
+			if (!pring)
 				continue;
-			lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+			if (pring == phba->sli4_hba.els_wq->pring) {
+				pring->flag |= LPFC_DEFERRED_RING_EVENT;
+				/* Set the lpfc data pending flag */
+				set_bit(LPFC_DATA_READY, &phba->data_flags);
+			}
+			prev_pring_flag = pring->flag;
+			spin_lock_irq(&pring->ring_lock);
+			list_for_each_entry_safe(iocb, next_iocb,
+						 &pring->txq, list) {
+				if (iocb->vport != vport)
+					continue;
+				list_move_tail(&iocb->list, &completions);
+			}
+			spin_unlock_irq(&pring->ring_lock);
+			list_for_each_entry_safe(iocb, next_iocb,
+						 &pring->txcmplq, list) {
+				if (iocb->vport != vport)
+					continue;
+				lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+			}
+			pring->flag = prev_pring_flag;
 		}
-
-		pring->flag = prev_pring_flag;
 	}
-
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
 	/* Cancel all the IOCBs from the completions list */
@@ -9634,6 +9896,7 @@ lpfc_sli_hba_down(struct lpfc_hba *phba)
 {
 	LIST_HEAD(completions);
 	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_queue *qp = NULL;
 	struct lpfc_sli_ring *pring;
 	struct lpfc_dmabuf *buf_ptr;
 	unsigned long flags = 0;
@@ -9647,20 +9910,36 @@ lpfc_sli_hba_down(struct lpfc_hba *phba)
 	lpfc_fabric_abort_hba(phba);
 
 	spin_lock_irqsave(&phba->hbalock, flags);
-	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
-		/* Only slow rings */
-		if (pring->ringno == LPFC_ELS_RING) {
-			pring->flag |= LPFC_DEFERRED_RING_EVENT;
-			/* Set the lpfc data pending flag */
-			set_bit(LPFC_DATA_READY, &phba->data_flags);
-		}
 
-		/*
-		 * Error everything on the txq since these iocbs have not been
-		 * given to the FW yet.
-		 */
-		list_splice_init(&pring->txq, &completions);
+	/*
+	 * Error everything on the txq since these iocbs
+	 * have not been given to the FW yet.
+	 */
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		for (i = 0; i < psli->num_rings; i++) {
+			pring = &psli->sli3_ring[i];
+			/* Only slow rings */
+			if (pring->ringno == LPFC_ELS_RING) {
+				pring->flag |= LPFC_DEFERRED_RING_EVENT;
+				/* Set the lpfc data pending flag */
+				set_bit(LPFC_DATA_READY, &phba->data_flags);
+			}
+			list_splice_init(&pring->txq, &completions);
+		}
+	} else {
+		list_for_each_entry(qp, &phba->sli4_hba.lpfc_wq_list, wq_list) {
+			pring = qp->pring;
+			if (!pring)
+				continue;
+			spin_lock_irq(&pring->ring_lock);
+			list_splice_init(&pring->txq, &completions);
+			spin_unlock_irq(&pring->ring_lock);
+			if (pring == phba->sli4_hba.els_wq->pring) {
+				pring->flag |= LPFC_DEFERRED_RING_EVENT;
+				/* Set the lpfc data pending flag */
+				set_bit(LPFC_DATA_READY, &phba->data_flags);
+			}
+		}
 	}
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
@@ -9987,7 +10266,6 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	struct lpfc_iocbq *abtsiocbp;
 	IOCB_t *icmd = NULL;
 	IOCB_t *iabt = NULL;
-	int ring_number;
 	int retval;
 	unsigned long iflags;
 
@@ -10027,7 +10305,7 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	iabt->ulpClass = icmd->ulpClass;
 
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
-	abtsiocbp->fcp_wqidx = cmdiocb->fcp_wqidx;
+	abtsiocbp->hba_wqidx = cmdiocb->hba_wqidx;
 	if (cmdiocb->iocb_flag & LPFC_IO_FCP)
 		abtsiocbp->iocb_flag |= LPFC_USE_FCPWQIDX;
 	if (cmdiocb->iocb_flag & LPFC_IO_FOF)
@@ -10049,11 +10327,9 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			 abtsiocbp->iotag);
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
-		ring_number =
-			lpfc_sli_calc_ring(phba, pring->ringno, abtsiocbp);
-		if (unlikely(ring_number == LPFC_HBA_ERROR))
+		pring = lpfc_sli4_calc_ring(phba, abtsiocbp);
+		if (unlikely(pring == NULL))
 			return 0;
-		pring = &phba->sli.ring[ring_number];
 		/* Note: both hbalock and ring_lock need to be set here */
 		spin_lock_irqsave(&pring->ring_lock, iflags);
 		retval = __lpfc_sli_issue_iocb(phba, pring->ringno,
@@ -10134,6 +10410,111 @@ lpfc_sli_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	return retval;
 }
 
+/**
+ * lpfc_sli4_abort_nvme_io - Issue abort for a command iocb
+ * @phba: Pointer to HBA context object.
+ * @pring: Pointer to driver SLI ring object.
+ * @cmdiocb: Pointer to driver command iocb object.
+ *
+ * This function issues an abort iocb for the provided command iocb down to
+ * the port. Other than the case the outstanding command iocb is an abort
+ * request, this function issues abort out unconditionally. This function is
+ * called with hbalock held. The function returns 0 when it fails due to
+ * memory allocation failure or when the command iocb is an abort request.
+ **/
+static int
+lpfc_sli4_abort_nvme_io(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
+			struct lpfc_iocbq *cmdiocb)
+{
+	struct lpfc_vport *vport = cmdiocb->vport;
+	struct lpfc_iocbq *abtsiocbp;
+	union lpfc_wqe *abts_wqe;
+	int retval;
+
+	/*
+	 * There are certain command types we don't want to abort.  And we
+	 * don't want to abort commands that are already in the process of
+	 * being aborted.
+	 */
+	if (cmdiocb->iocb.ulpCommand == CMD_ABORT_XRI_CN ||
+	    cmdiocb->iocb.ulpCommand == CMD_CLOSE_XRI_CN ||
+	    (cmdiocb->iocb_flag & LPFC_DRIVER_ABORTED) != 0)
+		return 0;
+
+	/* issue ABTS for this io based on iotag */
+	abtsiocbp = __lpfc_sli_get_iocbq(phba);
+	if (abtsiocbp == NULL)
+		return 0;
+
+	/* This signals the response to set the correct status
+	 * before calling the completion handler
+	 */
+	cmdiocb->iocb_flag |= LPFC_DRIVER_ABORTED;
+
+	/* Complete prepping the abort wqe and issue to the FW. */
+	abts_wqe = &abtsiocbp->wqe;
+	bf_set(abort_cmd_ia, &abts_wqe->abort_cmd, 0);
+	bf_set(abort_cmd_criteria, &abts_wqe->abort_cmd, T_XRI_TAG);
+
+	/* Explicitly set reserved fields to zero.*/
+	abts_wqe->abort_cmd.rsrvd4 = 0;
+	abts_wqe->abort_cmd.rsrvd5 = 0;
+
+	/* WQE Common - word 6.  Context is XRI tag.  Set 0. */
+	bf_set(wqe_xri_tag, &abts_wqe->abort_cmd.wqe_com, 0);
+	bf_set(wqe_ctxt_tag, &abts_wqe->abort_cmd.wqe_com, 0);
+
+	/* word 7 */
+	bf_set(wqe_ct, &abts_wqe->abort_cmd.wqe_com, 0);
+	bf_set(wqe_cmnd, &abts_wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX);
+	bf_set(wqe_class, &abts_wqe->abort_cmd.wqe_com,
+	       cmdiocb->iocb.ulpClass);
+
+	/* word 8 - tell the FW to abort the IO associated with this
+	 * outstanding exchange ID.
+	 */
+	abts_wqe->abort_cmd.wqe_com.abort_tag = cmdiocb->sli4_xritag;
+
+	/* word 9 - this is the iotag for the abts_wqe completion. */
+	bf_set(wqe_reqtag, &abts_wqe->abort_cmd.wqe_com,
+	       abtsiocbp->iotag);
+
+	/* word 10 */
+	bf_set(wqe_wqid, &abts_wqe->abort_cmd.wqe_com, cmdiocb->hba_wqidx);
+	bf_set(wqe_qosd, &abts_wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_lenloc, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE);
+
+	/* word 11 */
+	bf_set(wqe_cmd_type, &abts_wqe->abort_cmd.wqe_com, OTHER_COMMAND);
+	bf_set(wqe_wqec, &abts_wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_cqid, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+
+	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
+	abtsiocbp->iocb_flag |= LPFC_IO_NVME;
+	abtsiocbp->vport = vport;
+	/* todo: assign wqe_cmpl to lpfc_nvme_abort_fcreq_cmpl
+	 * subsequent patch will add routine. For now, just skip assignment
+	 * as won't ever be called.
+	 */
+	retval = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abtsiocbp);
+	if (retval == IOCB_ERROR) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6147 Failed abts issue_wqe with status x%x "
+				 "for oxid x%x\n",
+				 retval, cmdiocb->sli4_xritag);
+		lpfc_sli_release_iocbq(phba, abtsiocbp);
+		return retval;
+	}
+
+	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+			 "6148 Drv Abort NVME Request Issued for "
+			 "ox_id x%x on reqtag x%x\n",
+			 cmdiocb->sli4_xritag,
+			 abtsiocbp->iotag);
+
+	return retval;
+}
+
 /**
  * lpfc_sli_hba_iocb_abort - Abort all iocbs to an hba.
  * @phba: pointer to lpfc HBA data structure.
@@ -10145,10 +10526,20 @@ lpfc_sli_hba_iocb_abort(struct lpfc_hba *phba)
 {
 	struct lpfc_sli *psli = &phba->sli;
 	struct lpfc_sli_ring *pring;
+	struct lpfc_queue *qp = NULL;
 	int i;
 
-	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		for (i = 0; i < psli->num_rings; i++) {
+			pring = &psli->sli3_ring[i];
+			lpfc_sli_abort_iocb_ring(phba, pring);
+		}
+		return;
+	}
+	list_for_each_entry(qp, &phba->sli4_hba.lpfc_wq_list, wq_list) {
+		pring = qp->pring;
+		if (!pring)
+			continue;
 		lpfc_sli_abort_iocb_ring(phba, pring);
 	}
 }
@@ -10352,7 +10743,7 @@ lpfc_sli_abort_iocb(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 		abtsiocb->vport = vport;
 
 		/* ABTS WQE must go to the same WQ as the WQE to be aborted */
-		abtsiocb->fcp_wqidx = iocbq->fcp_wqidx;
+		abtsiocb->hba_wqidx = iocbq->hba_wqidx;
 		if (iocbq->iocb_flag & LPFC_IO_FCP)
 			abtsiocb->iocb_flag |= LPFC_USE_FCPWQIDX;
 		if (iocbq->iocb_flag & LPFC_IO_FOF)
@@ -10412,7 +10803,6 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 	int sum, i, ret_val;
 	unsigned long iflags;
 	struct lpfc_sli_ring *pring_s4;
-	uint32_t ring_number;
 
 	spin_lock_irq(&phba->hbalock);
 
@@ -10455,7 +10845,7 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 		abtsiocbq->vport = vport;
 
 		/* ABTS WQE must go to the same WQ as the WQE to be aborted */
-		abtsiocbq->fcp_wqidx = iocbq->fcp_wqidx;
+		abtsiocbq->hba_wqidx = iocbq->hba_wqidx;
 		if (iocbq->iocb_flag & LPFC_IO_FCP)
 			abtsiocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
 		if (iocbq->iocb_flag & LPFC_IO_FOF)
@@ -10480,9 +10870,9 @@ lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 		iocbq->iocb_flag |= LPFC_DRIVER_ABORTED;
 
 		if (phba->sli_rev == LPFC_SLI_REV4) {
-			ring_number = MAX_SLI3_CONFIGURED_RINGS +
-					 iocbq->fcp_wqidx;
-			pring_s4 = &phba->sli.ring[ring_number];
+			pring_s4 = lpfc_sli4_calc_ring(phba, iocbq);
+			if (pring_s4 == NULL)
+				continue;
 			/* Note: both hbalock and ring_lock must be set here */
 			spin_lock_irqsave(&pring_s4->ring_lock, iflags);
 			ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
@@ -10644,10 +11034,14 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
 	struct lpfc_iocbq *iocb;
 	int txq_cnt = 0;
 	int txcmplq_cnt = 0;
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 	unsigned long iflags;
 	bool iocb_completed = true;
 
+	if (phba->sli_rev >= LPFC_SLI_REV4)
+		pring = lpfc_sli4_calc_ring(phba, piocb);
+	else
+		pring = &phba->sli.sli3_ring[ring_number];
 	/*
 	 * If the caller has provided a response iocbq buffer, then context2
 	 * is NULL or its an error.
@@ -11442,6 +11836,7 @@ lpfc_sli_fp_intr_handler(int irq, void *dev_id)
 	uint32_t ha_copy;
 	unsigned long status;
 	unsigned long iflag;
+	struct lpfc_sli_ring *pring;
 
 	/* Get the driver's phba structure from the dev_id and
 	 * assume the HBA is not interrupting.
@@ -11486,10 +11881,9 @@ lpfc_sli_fp_intr_handler(int irq, void *dev_id)
 
 	status = (ha_copy & (HA_RXMASK << (4*LPFC_FCP_RING)));
 	status >>= (4*LPFC_FCP_RING);
+	pring = &phba->sli.sli3_ring[LPFC_FCP_RING];
 	if (status & HA_RXMASK)
-		lpfc_sli_handle_fast_ring_event(phba,
-						&phba->sli.ring[LPFC_FCP_RING],
-						status);
+		lpfc_sli_handle_fast_ring_event(phba, pring, status);
 
 	if (phba->cfg_multi_ring_support == 2) {
 		/*
@@ -11500,7 +11894,7 @@ lpfc_sli_fp_intr_handler(int irq, void *dev_id)
 		status >>= (4*LPFC_EXTRA_RING);
 		if (status & HA_RXMASK) {
 			lpfc_sli_handle_fast_ring_event(phba,
-					&phba->sli.ring[LPFC_EXTRA_RING],
+					&phba->sli.sli3_ring[LPFC_EXTRA_RING],
 					status);
 		}
 	}
@@ -11813,11 +12207,13 @@ static struct lpfc_iocbq *
 lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *phba,
 			       struct lpfc_iocbq *irspiocbq)
 {
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *cmdiocbq;
 	struct lpfc_wcqe_complete *wcqe;
 	unsigned long iflags;
 
+	pring = lpfc_phba_elsring(phba);
+
 	wcqe = &irspiocbq->cq_event.cqe.wcqe_cmpl;
 	spin_lock_irqsave(&pring->ring_lock, iflags);
 	pring->stats.iocb_event++;
@@ -12053,8 +12449,6 @@ lpfc_sli4_sp_handle_els_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 			txq_cnt++;
 		if (!list_empty(&pring->txcmplq))
 			txcmplq_cnt++;
-		if (!list_empty(&phba->sli.ring[LPFC_FCP_RING].txcmplq))
-			fcp_txcmplq_cnt++;
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 			"0387 NO IOCBQ data: txq_cnt=%d iocb_cnt=%d "
 			"fcp_txcmplq_cnt=%d, els_txcmplq_cnt=%d\n",
@@ -12173,6 +12567,7 @@ static bool
 lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 {
 	bool workposted = false;
+	struct fc_frame_header *fc_hdr;
 	struct lpfc_queue *hrq = phba->sli4_hba.hdr_rq;
 	struct lpfc_queue *drq = phba->sli4_hba.dat_rq;
 	struct hbq_dmabuf *dma_buf;
@@ -12207,6 +12602,10 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 		}
 		hrq->RQ_rcv_buf++;
 		memcpy(&dma_buf->cq_event.cqe.rcqe_cmpl, rcqe, sizeof(*rcqe));
+
+		/* If a NVME LS event (type 0x28), treat it as Fast path */
+		fc_hdr = (struct fc_frame_header *)dma_buf->hbuf.virt;
+
 		/* save off the frame for the word thread to process */
 		list_add_tail(&dma_buf->cq_event.list,
 			      &phba->sli4_hba.sp_queue_event);
@@ -12325,6 +12724,9 @@ lpfc_sli4_sp_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 		return;
 	}
 
+	/* Save EQ associated with this CQ */
+	cq->assoc_qp = speq;
+
 	/* Process all the entries to the CQ */
 	switch (cq->type) {
 	case LPFC_MCQ:
@@ -12337,8 +12739,9 @@ lpfc_sli4_sp_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 		break;
 	case LPFC_WCQ:
 		while ((cqe = lpfc_sli4_cq_get(cq))) {
-			if (cq->subtype == LPFC_FCP)
-				workposted |= lpfc_sli4_fp_handle_wcqe(phba, cq,
+			if ((cq->subtype == LPFC_FCP) ||
+			    (cq->subtype == LPFC_NVME))
+				workposted |= lpfc_sli4_fp_handle_cqe(phba, cq,
 								       cqe);
 			else
 				workposted |= lpfc_sli4_sp_handle_cqe(phba, cq,
@@ -12425,7 +12828,23 @@ lpfc_sli4_fp_handle_fcp_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 				bf_get(lpfc_wcqe_c_request_tag, wcqe));
 		return;
 	}
-	if (unlikely(!cmdiocbq->iocb_cmpl)) {
+
+	if (cq->assoc_qp)
+		cmdiocbq->isr_timestamp =
+			cq->assoc_qp->isr_timestamp;
+
+	if (cmdiocbq->iocb_cmpl == NULL) {
+		if (cmdiocbq->wqe_cmpl) {
+			if (cmdiocbq->iocb_flag & LPFC_DRIVER_ABORTED) {
+				spin_lock_irqsave(&phba->hbalock, iflags);
+				cmdiocbq->iocb_flag &= ~LPFC_DRIVER_ABORTED;
+				spin_unlock_irqrestore(&phba->hbalock, iflags);
+			}
+
+			/* Pass the cmd_iocb and the wcqe to the upper layer */
+			(cmdiocbq->wqe_cmpl)(phba, cmdiocbq, wcqe);
+			return;
+		}
 		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
 				"0375 FCP cmdiocb not callback function "
 				"iotag: (%d)\n",
@@ -12461,12 +12880,12 @@ lpfc_sli4_fp_handle_rel_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 {
 	struct lpfc_queue *childwq;
 	bool wqid_matched = false;
-	uint16_t fcp_wqid;
+	uint16_t hba_wqid;
 
 	/* Check for fast-path FCP work queue release */
-	fcp_wqid = bf_get(lpfc_wcqe_r_wq_id, wcqe);
+	hba_wqid = bf_get(lpfc_wcqe_r_wq_id, wcqe);
 	list_for_each_entry(childwq, &cq->child_list, list) {
-		if (childwq->queue_id == fcp_wqid) {
+		if (childwq->queue_id == hba_wqid) {
 			lpfc_sli4_wq_release(childwq,
 					bf_get(lpfc_wcqe_r_wqe_index, wcqe));
 			wqid_matched = true;
@@ -12477,11 +12896,11 @@ lpfc_sli4_fp_handle_rel_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	if (wqid_matched != true)
 		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
 				"2580 Fast-path wqe consume event carries "
-				"miss-matched qid: wcqe-qid=x%x\n", fcp_wqid);
+				"miss-matched qid: wcqe-qid=x%x\n", hba_wqid);
 }
 
 /**
- * lpfc_sli4_fp_handle_wcqe - Process fast-path work queue completion entry
+ * lpfc_sli4_fp_handle_cqe - Process fast-path work queue completion entry
  * @cq: Pointer to the completion queue.
  * @eqe: Pointer to fast-path completion queue entry.
  *
@@ -12489,7 +12908,7 @@ lpfc_sli4_fp_handle_rel_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
  * event queue for FCP command response completion.
  **/
 static int
-lpfc_sli4_fp_handle_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
+lpfc_sli4_fp_handle_cqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 			 struct lpfc_cqe *cqe)
 {
 	struct lpfc_wcqe_release wcqe;
@@ -12501,10 +12920,15 @@ lpfc_sli4_fp_handle_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	/* Check and process for different type of WCQE and dispatch */
 	switch (bf_get(lpfc_wcqe_c_code, &wcqe)) {
 	case CQE_CODE_COMPL_WQE:
+	case CQE_CODE_NVME_ERSP:
 		cq->CQ_wq++;
 		/* Process the WQ complete event */
 		phba->last_completion_time = jiffies;
-		lpfc_sli4_fp_handle_fcp_wcqe(phba, cq,
+		if ((cq->subtype == LPFC_FCP) || (cq->subtype == LPFC_NVME))
+			lpfc_sli4_fp_handle_fcp_wcqe(phba, cq,
+				(struct lpfc_wcqe_complete *)&wcqe);
+		if (cq->subtype == LPFC_NVME_LS)
+			lpfc_sli4_fp_handle_fcp_wcqe(phba, cq,
 				(struct lpfc_wcqe_complete *)&wcqe);
 		break;
 	case CQE_CODE_RELEASE_WQE:
@@ -12520,9 +12944,13 @@ lpfc_sli4_fp_handle_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 		workposted = lpfc_sli4_sp_handle_abort_xri_wcqe(phba, cq,
 				(struct sli4_wcqe_xri_aborted *)&wcqe);
 		break;
+	case CQE_CODE_RECEIVE_V1:
+	case CQE_CODE_RECEIVE:
+		phba->last_completion_time = jiffies;
+		break;
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-				"0144 Not a valid WCQE code: x%x\n",
+				"0144 Not a valid CQE code: x%x\n",
 				bf_get(lpfc_wcqe_c_code, &wcqe));
 		break;
 	}
@@ -12545,7 +12973,7 @@ static void
 lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 			uint32_t qidx)
 {
-	struct lpfc_queue *cq;
+	struct lpfc_queue *cq = NULL;
 	struct lpfc_cqe *cqe;
 	bool workposted = false;
 	uint16_t cqid;
@@ -12563,28 +12991,33 @@ lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 	/* Get the reference to the corresponding CQ */
 	cqid = bf_get_le32(lpfc_eqe_resource_id, eqe);
 
-	/* Check if this is a Slow path event */
-	if (unlikely(cqid != phba->sli4_hba.fcp_cq_map[qidx])) {
-		lpfc_sli4_sp_handle_eqe(phba, eqe,
-			phba->sli4_hba.hba_eq[qidx]);
-		return;
+	if (phba->sli4_hba.nvme_cq_map &&
+	    (cqid == phba->sli4_hba.nvme_cq_map[qidx])) {
+		/* Process NVME command completion */
+		cq = phba->sli4_hba.nvme_cq[qidx];
+		goto  process_cq;
 	}
 
-	if (unlikely(!phba->sli4_hba.fcp_cq)) {
-		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
-				"3146 Fast-path completion queues "
-				"does not exist\n");
-		return;
+	if (phba->sli4_hba.fcp_cq_map &&
+	    (cqid == phba->sli4_hba.fcp_cq_map[qidx])) {
+		/* Process FCP command completion */
+		cq = phba->sli4_hba.fcp_cq[qidx];
+		goto  process_cq;
 	}
-	cq = phba->sli4_hba.fcp_cq[qidx];
-	if (unlikely(!cq)) {
-		if (phba->sli.sli_flag & LPFC_SLI_ACTIVE)
-			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-					"0367 Fast-path completion queue "
-					"(%d) does not exist\n", qidx);
+
+	if (phba->sli4_hba.nvmels_cq &&
+	    (cqid == phba->sli4_hba.nvmels_cq->queue_id)) {
+		/* Process NVME unsol rcv */
+		cq = phba->sli4_hba.nvmels_cq;
+	}
+
+	/* Otherwise this is a Slow path event */
+	if (cq == NULL) {
+		lpfc_sli4_sp_handle_eqe(phba, eqe, phba->sli4_hba.hba_eq[qidx]);
 		return;
 	}
 
+process_cq:
 	if (unlikely(cqid != cq->queue_id)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"0368 Miss-matched fast-path completion "
@@ -12593,9 +13026,12 @@ lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 		return;
 	}
 
+	/* Save EQ associated with this CQ */
+	cq->assoc_qp = phba->sli4_hba.hba_eq[qidx];
+
 	/* Process all the entries to the CQ */
 	while ((cqe = lpfc_sli4_cq_get(cq))) {
-		workposted |= lpfc_sli4_fp_handle_wcqe(phba, cq, cqe);
+		workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
 		if (!(++ecount % cq->entry_repost))
 			lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
 	}
@@ -12686,7 +13122,7 @@ lpfc_sli4_fof_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe)
 
 	/* Process all the entries to the OAS CQ */
 	while ((cqe = lpfc_sli4_cq_get(cq))) {
-		workposted |= lpfc_sli4_fp_handle_wcqe(phba, cq, cqe);
+		workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
 		if (!(++ecount % cq->entry_repost))
 			lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
 	}
@@ -12734,15 +13170,15 @@ irqreturn_t
 lpfc_sli4_fof_intr_handler(int irq, void *dev_id)
 {
 	struct lpfc_hba *phba;
-	struct lpfc_fcp_eq_hdl *fcp_eq_hdl;
+	struct lpfc_hba_eq_hdl *hba_eq_hdl;
 	struct lpfc_queue *eq;
 	struct lpfc_eqe *eqe;
 	unsigned long iflag;
 	int ecount = 0;
 
 	/* Get the driver's phba structure from the dev_id */
-	fcp_eq_hdl = (struct lpfc_fcp_eq_hdl *)dev_id;
-	phba = fcp_eq_hdl->phba;
+	hba_eq_hdl = (struct lpfc_hba_eq_hdl *)dev_id;
+	phba = hba_eq_hdl->phba;
 
 	if (unlikely(!phba))
 		return IRQ_NONE;
@@ -12828,17 +13264,17 @@ irqreturn_t
 lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 {
 	struct lpfc_hba *phba;
-	struct lpfc_fcp_eq_hdl *fcp_eq_hdl;
+	struct lpfc_hba_eq_hdl *hba_eq_hdl;
 	struct lpfc_queue *fpeq;
 	struct lpfc_eqe *eqe;
 	unsigned long iflag;
 	int ecount = 0;
-	int fcp_eqidx;
+	int hba_eqidx;
 
 	/* Get the driver's phba structure from the dev_id */
-	fcp_eq_hdl = (struct lpfc_fcp_eq_hdl *)dev_id;
-	phba = fcp_eq_hdl->phba;
-	fcp_eqidx = fcp_eq_hdl->idx;
+	hba_eq_hdl = (struct lpfc_hba_eq_hdl *)dev_id;
+	phba = hba_eq_hdl->phba;
+	hba_eqidx = hba_eq_hdl->idx;
 
 	if (unlikely(!phba))
 		return IRQ_NONE;
@@ -12846,15 +13282,15 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	/* Get to the EQ struct associated with this vector */
-	fpeq = phba->sli4_hba.hba_eq[fcp_eqidx];
+	fpeq = phba->sli4_hba.hba_eq[hba_eqidx];
 	if (unlikely(!fpeq))
 		return IRQ_NONE;
 
 	if (lpfc_fcp_look_ahead) {
-		if (atomic_dec_and_test(&fcp_eq_hdl->fcp_eq_in_use))
+		if (atomic_dec_and_test(&hba_eq_hdl->hba_eq_in_use))
 			lpfc_sli4_eq_clr_intr(fpeq);
 		else {
-			atomic_inc(&fcp_eq_hdl->fcp_eq_in_use);
+			atomic_inc(&hba_eq_hdl->hba_eq_in_use);
 			return IRQ_NONE;
 		}
 	}
@@ -12869,7 +13305,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 			lpfc_sli4_eq_flush(phba, fpeq);
 		spin_unlock_irqrestore(&phba->hbalock, iflag);
 		if (lpfc_fcp_look_ahead)
-			atomic_inc(&fcp_eq_hdl->fcp_eq_in_use);
+			atomic_inc(&hba_eq_hdl->hba_eq_in_use);
 		return IRQ_NONE;
 	}
 
@@ -12880,7 +13316,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 		if (eqe == NULL)
 			break;
 
-		lpfc_sli4_hba_handle_eqe(phba, eqe, fcp_eqidx);
+		lpfc_sli4_hba_handle_eqe(phba, eqe, hba_eqidx);
 		if (!(++ecount % fpeq->entry_repost))
 			lpfc_sli4_eq_release(fpeq, LPFC_QUEUE_NOARM);
 		fpeq->EQ_processed++;
@@ -12897,7 +13333,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 		fpeq->EQ_no_entry++;
 
 		if (lpfc_fcp_look_ahead) {
-			atomic_inc(&fcp_eq_hdl->fcp_eq_in_use);
+			atomic_inc(&hba_eq_hdl->hba_eq_in_use);
 			return IRQ_NONE;
 		}
 
@@ -12911,7 +13347,8 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 	}
 
 	if (lpfc_fcp_look_ahead)
-		atomic_inc(&fcp_eq_hdl->fcp_eq_in_use);
+		atomic_inc(&hba_eq_hdl->hba_eq_in_use);
+
 	return IRQ_HANDLED;
 } /* lpfc_sli4_fp_intr_handler */
 
@@ -12938,7 +13375,7 @@ lpfc_sli4_intr_handler(int irq, void *dev_id)
 	struct lpfc_hba  *phba;
 	irqreturn_t hba_irq_rc;
 	bool hba_handled = false;
-	int fcp_eqidx;
+	int qidx;
 
 	/* Get the driver's phba structure from the dev_id */
 	phba = (struct lpfc_hba *)dev_id;
@@ -12949,16 +13386,16 @@ lpfc_sli4_intr_handler(int irq, void *dev_id)
 	/*
 	 * Invoke fast-path host attention interrupt handling as appropriate.
 	 */
-	for (fcp_eqidx = 0; fcp_eqidx < phba->cfg_fcp_io_channel; fcp_eqidx++) {
+	for (qidx = 0; qidx < phba->io_channel_irqs; qidx++) {
 		hba_irq_rc = lpfc_sli4_hba_intr_handler(irq,
-					&phba->sli4_hba.fcp_eq_hdl[fcp_eqidx]);
+					&phba->sli4_hba.hba_eq_hdl[qidx]);
 		if (hba_irq_rc == IRQ_HANDLED)
 			hba_handled |= true;
 	}
 
 	if (phba->cfg_fof) {
 		hba_irq_rc = lpfc_sli4_fof_intr_handler(irq,
-					&phba->sli4_hba.fcp_eq_hdl[0]);
+					&phba->sli4_hba.hba_eq_hdl[qidx]);
 		if (hba_irq_rc == IRQ_HANDLED)
 			hba_handled |= true;
 	}
@@ -12989,6 +13426,11 @@ lpfc_sli4_queue_free(struct lpfc_queue *queue)
 				  dmabuf->virt, dmabuf->phys);
 		kfree(dmabuf);
 	}
+	if (queue->rqbp) {
+		lpfc_free_rq_buffer(queue->phba, queue);
+		kfree(queue->rqbp);
+	}
+	kfree(queue->pring);
 	kfree(queue);
 	return;
 }
@@ -13022,7 +13464,13 @@ lpfc_sli4_queue_alloc(struct lpfc_hba *phba, uint32_t entry_size,
 		return NULL;
 	queue->page_count = (ALIGN(entry_size * entry_count,
 			hw_page_size))/hw_page_size;
+
+	/* If needed, Adjust page count to match the max the adapter supports */
+	if (queue->page_count > phba->sli4_hba.pc_sli4_params.wqpcnt)
+		queue->page_count = phba->sli4_hba.pc_sli4_params.wqpcnt;
+
 	INIT_LIST_HEAD(&queue->list);
+	INIT_LIST_HEAD(&queue->wq_list);
 	INIT_LIST_HEAD(&queue->page_list);
 	INIT_LIST_HEAD(&queue->child_list);
 	for (x = 0, total_qe_count = 0; x < queue->page_count; x++) {
@@ -13094,7 +13542,7 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset)
 }
 
 /**
- * lpfc_modify_fcp_eq_delay - Modify Delay Multiplier on FCP EQs
+ * lpfc_modify_hba_eq_delay - Modify Delay Multiplier on FCP EQs
  * @phba: HBA structure that indicates port to create a queue on.
  * @startq: The starting FCP EQ to modify
  *
@@ -13110,7 +13558,7 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset)
  * fails this function will return -ENXIO.
  **/
 int
-lpfc_modify_fcp_eq_delay(struct lpfc_hba *phba, uint32_t startq)
+lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq)
 {
 	struct lpfc_mbx_modify_eq_delay *eq_delay;
 	LPFC_MBOXQ_t *mbox;
@@ -13118,11 +13566,11 @@ lpfc_modify_fcp_eq_delay(struct lpfc_hba *phba, uint32_t startq)
 	int cnt, rc, length, status = 0;
 	uint32_t shdr_status, shdr_add_status;
 	uint32_t result;
-	int fcp_eqidx;
+	int qidx;
 	union lpfc_sli4_cfg_shdr *shdr;
 	uint16_t dmult;
 
-	if (startq >= phba->cfg_fcp_io_channel)
+	if (startq >= phba->io_channel_irqs)
 		return 0;
 
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
@@ -13136,16 +13584,15 @@ lpfc_modify_fcp_eq_delay(struct lpfc_hba *phba, uint32_t startq)
 	eq_delay = &mbox->u.mqe.un.eq_delay;
 
 	/* Calculate delay multiper from maximum interrupt per second */
-	result = phba->cfg_fcp_imax / phba->cfg_fcp_io_channel;
-	if (result > LPFC_DMULT_CONST)
+	result = phba->cfg_fcp_imax / phba->io_channel_irqs;
+	if (result > LPFC_DMULT_CONST || result == 0)
 		dmult = 0;
 	else
 		dmult = LPFC_DMULT_CONST/result - 1;
 
 	cnt = 0;
-	for (fcp_eqidx = startq; fcp_eqidx < phba->cfg_fcp_io_channel;
-	    fcp_eqidx++) {
-		eq = phba->sli4_hba.hba_eq[fcp_eqidx];
+	for (qidx = startq; qidx < phba->io_channel_irqs; qidx++) {
+		eq = phba->sli4_hba.hba_eq[qidx];
 		if (!eq)
 			continue;
 		eq_delay->u.request.eq[cnt].eq_id = eq->queue_id;
@@ -13829,6 +14276,11 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 		wq->db_format = LPFC_DB_LIST_FORMAT;
 		wq->db_regaddr = phba->sli4_hba.WQDBregaddr;
 	}
+	wq->pring = kzalloc(sizeof(struct lpfc_sli_ring), GFP_KERNEL);
+	if (wq->pring == NULL) {
+		status = -ENOMEM;
+		goto out;
+	}
 	wq->type = LPFC_WQ;
 	wq->assoc_qid = cq->queue_id;
 	wq->subtype = subtype;
@@ -14613,7 +15065,7 @@ lpfc_sli4_next_xritag(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_sli4_post_els_sgl_list - post a block of ELS sgls to the port.
+ * lpfc_sli4_post_sgl_list - post a block of ELS sgls to the port.
  * @phba: pointer to lpfc hba data structure.
  * @post_sgl_list: pointer to els sgl entry list.
  * @count: number of els sgl entries on the list.
@@ -14624,7 +15076,7 @@ lpfc_sli4_next_xritag(struct lpfc_hba *phba)
  * stopped.
  **/
 static int
-lpfc_sli4_post_els_sgl_list(struct lpfc_hba *phba,
+lpfc_sli4_post_sgl_list(struct lpfc_hba *phba,
 			    struct list_head *post_sgl_list,
 			    int post_cnt)
 {
@@ -14640,14 +15092,15 @@ lpfc_sli4_post_els_sgl_list(struct lpfc_hba *phba,
 	uint32_t shdr_status, shdr_add_status;
 	union lpfc_sli4_cfg_shdr *shdr;
 
-	reqlen = phba->sli4_hba.els_xri_cnt * sizeof(struct sgl_page_pairs) +
+	reqlen = post_cnt * sizeof(struct sgl_page_pairs) +
 		 sizeof(union lpfc_sli4_cfg_shdr) + sizeof(uint32_t);
 	if (reqlen > SLI4_PAGE_SIZE) {
-		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"2559 Block sgl registration required DMA "
 				"size (%d) great than a page\n", reqlen);
 		return -ENOMEM;
 	}
+
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		return -ENOMEM;
@@ -14691,8 +15144,9 @@ lpfc_sli4_post_els_sgl_list(struct lpfc_hba *phba,
 
 	/* Complete initialization and perform endian conversion. */
 	bf_set(lpfc_post_sgl_pages_xri, sgl, xritag_start);
-	bf_set(lpfc_post_sgl_pages_xricnt, sgl, phba->sli4_hba.els_xri_cnt);
+	bf_set(lpfc_post_sgl_pages_xricnt, sgl, post_cnt);
 	sgl->word0 = cpu_to_le32(sgl->word0);
+
 	if (!phba->sli4_hba.intr_enable)
 		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
 	else {
@@ -14888,6 +15342,7 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	case FC_TYPE_ELS:
 	case FC_TYPE_FCP:
 	case FC_TYPE_CT:
+	case FC_TYPE_NVME:
 		break;
 	case FC_TYPE_IP:
 	case FC_TYPE_ILS:
@@ -14945,14 +15400,11 @@ lpfc_fc_hdr_get_vfi(struct fc_frame_header *fc_hdr)
  **/
 static struct lpfc_vport *
 lpfc_fc_frame_to_vport(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr,
-		       uint16_t fcfi)
+		       uint16_t fcfi, uint32_t did)
 {
 	struct lpfc_vport **vports;
 	struct lpfc_vport *vport = NULL;
 	int i;
-	uint32_t did = (fc_hdr->fh_d_id[0] << 16 |
-			fc_hdr->fh_d_id[1] << 8 |
-			fc_hdr->fh_d_id[2]);
 
 	if (did == Fabric_DID)
 		return phba->pport;
@@ -14961,7 +15413,7 @@ lpfc_fc_frame_to_vport(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr,
 		return phba->pport;
 
 	vports = lpfc_create_vport_work_array(phba);
-	if (vports != NULL)
+	if (vports != NULL) {
 		for (i = 0; i <= phba->max_vpi && vports[i] != NULL; i++) {
 			if (phba->fcf.fcfi == fcfi &&
 			    vports[i]->vfi == lpfc_fc_hdr_get_vfi(fc_hdr) &&
@@ -14970,6 +15422,7 @@ lpfc_fc_frame_to_vport(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr,
 				break;
 			}
 		}
+	}
 	lpfc_destroy_vport_work_array(phba, vports);
 	return vport;
 }
@@ -15399,7 +15852,7 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
 	 * a BA_RJT.
 	 */
 	if ((fctl & FC_FC_EX_CTX) &&
-	    (lxri > lpfc_sli4_get_els_iocb_cnt(phba))) {
+	    (lxri > lpfc_sli4_get_iocb_cnt(phba))) {
 		icmd->un.xseq64.w5.hcsw.Rctl = FC_RCTL_BA_RJT;
 		bf_set(lpfc_vndr_code, &icmd->un.bls_rsp, 0);
 		bf_set(lpfc_rsn_expln, &icmd->un.bls_rsp, FC_BA_RJT_INV_XID);
@@ -15576,6 +16029,7 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf)
 		/* Initialize the first IOCB. */
 		first_iocbq->iocb.unsli3.rcvsli3.acc_len = 0;
 		first_iocbq->iocb.ulpStatus = IOSTAT_SUCCESS;
+		first_iocbq->vport = vport;
 
 		/* Check FC Header to see what TYPE of frame we are rcv'ing */
 		if (sli4_type_from_fc_hdr(fc_hdr) == FC_TYPE_ELS) {
@@ -15688,7 +16142,7 @@ lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *vport,
 		return;
 	}
 	if (!lpfc_complete_unsol_iocb(phba,
-				      &phba->sli.ring[LPFC_ELS_RING],
+				      phba->sli4_hba.els_wq->pring,
 				      iocbq, fc_hdr->fh_r_ctl,
 				      fc_hdr->fh_type))
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
@@ -15713,8 +16167,7 @@ lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *vport,
  * This function is called with no lock held. This function processes all
  * the received buffers and gives it to upper layers when a received buffer
  * indicates that it is the final frame in the sequence. The interrupt
- * service routine processes received buffers at interrupt contexts and adds
- * received dma buffers to the rb_pend_list queue and signals the worker thread.
+ * service routine processes received buffers at interrupt contexts.
  * Worker thread calls lpfc_sli4_handle_received_buffer, which will call the
  * appropriate receive function when the final frame in a sequence is received.
  **/
@@ -15745,16 +16198,16 @@ lpfc_sli4_handle_received_buffer(struct lpfc_hba *phba,
 		fcfi = bf_get(lpfc_rcqe_fcf_id,
 			      &dmabuf->cq_event.cqe.rcqe_cmpl);
 
-	vport = lpfc_fc_frame_to_vport(phba, fc_hdr, fcfi);
+	/* d_id this frame is directed to */
+	did = sli4_did_from_fc_hdr(fc_hdr);
+
+	vport = lpfc_fc_frame_to_vport(phba, fc_hdr, fcfi, did);
 	if (!vport) {
 		/* throw out the frame */
 		lpfc_in_buf_free(phba, &dmabuf->dbuf);
 		return;
 	}
 
-	/* d_id this frame is directed to */
-	did = sli4_did_from_fc_hdr(fc_hdr);
-
 	/* vport is registered unless we rcv a FLOGI directed to Fabric_DID */
 	if (!(vport->vpi_state & LPFC_VPI_REGISTERED) &&
 		(did != Fabric_DID)) {
@@ -17232,7 +17685,7 @@ uint32_t
 lpfc_drain_txq(struct lpfc_hba *phba)
 {
 	LIST_HEAD(completions);
-	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *piocbq = NULL;
 	unsigned long iflags = 0;
 	char *fail_msg = NULL;
@@ -17241,6 +17694,8 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 	union lpfc_wqe *wqe = (union lpfc_wqe *) &wqe128;
 	uint32_t txq_cnt = 0;
 
+	pring = lpfc_phba_elsring(phba);
+
 	spin_lock_irqsave(&pring->ring_lock, iflags);
 	list_for_each_entry(piocbq, &pring->txq, list) {
 		txq_cnt++;
@@ -17262,7 +17717,7 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 				txq_cnt);
 			break;
 		}
-		sglq = __lpfc_sli_get_sglq(phba, piocbq);
+		sglq = __lpfc_sli_get_els_sglq(phba, piocbq);
 		if (!sglq) {
 			__lpfc_sli_ringtx_put(phba, pring, piocbq);
 			spin_unlock_irqrestore(&pring->ring_lock, iflags);
@@ -17302,3 +17757,191 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 
 	return txq_cnt;
 }
+
+/**
+ * lpfc_wqe_bpl2sgl - Convert the bpl/bde to a sgl.
+ * @phba: Pointer to HBA context object.
+ * @pwqe: Pointer to command WQE.
+ * @sglq: Pointer to the scatter gather queue object.
+ *
+ * This routine converts the bpl or bde that is in the WQE
+ * to a sgl list for the sli4 hardware. The physical address
+ * of the bpl/bde is converted back to a virtual address.
+ * If the WQE contains a BPL then the list of BDE's is
+ * converted to sli4_sge's. If the WQE contains a single
+ * BDE then it is converted to a single sli_sge.
+ * The WQE is still in cpu endianness so the contents of
+ * the bpl can be used without byte swapping.
+ *
+ * Returns valid XRI = Success, NO_XRI = Failure.
+ */
+static uint16_t
+lpfc_wqe_bpl2sgl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeq,
+		 struct lpfc_sglq *sglq)
+{
+	uint16_t xritag = NO_XRI;
+	struct ulp_bde64 *bpl = NULL;
+	struct ulp_bde64 bde;
+	struct sli4_sge *sgl  = NULL;
+	struct lpfc_dmabuf *dmabuf;
+	union lpfc_wqe *wqe;
+	int numBdes = 0;
+	int i = 0;
+	uint32_t offset = 0; /* accumulated offset in the sg request list */
+	int inbound = 0; /* number of sg reply entries inbound from firmware */
+	uint32_t cmd;
+
+	if (!pwqeq || !sglq)
+		return xritag;
+
+	sgl  = (struct sli4_sge *)sglq->sgl;
+	wqe = &pwqeq->wqe;
+	pwqeq->iocb.ulpIoTag = pwqeq->iotag;
+
+	cmd = bf_get(wqe_cmnd, &wqe->generic.wqe_com);
+	if (cmd == CMD_XMIT_BLS_RSP64_WQE)
+		return sglq->sli4_xritag;
+	numBdes = pwqeq->rsvd2;
+	if (numBdes) {
+		/* The addrHigh and addrLow fields within the WQE
+		 * have not been byteswapped yet so there is no
+		 * need to swap them back.
+		 */
+		if (pwqeq->context3)
+			dmabuf = (struct lpfc_dmabuf *)pwqeq->context3;
+		else
+			return xritag;
+
+		bpl  = (struct ulp_bde64 *)dmabuf->virt;
+		if (!bpl)
+			return xritag;
+
+		for (i = 0; i < numBdes; i++) {
+			/* Should already be byte swapped. */
+			sgl->addr_hi = bpl->addrHigh;
+			sgl->addr_lo = bpl->addrLow;
+
+			sgl->word2 = le32_to_cpu(sgl->word2);
+			if ((i+1) == numBdes)
+				bf_set(lpfc_sli4_sge_last, sgl, 1);
+			else
+				bf_set(lpfc_sli4_sge_last, sgl, 0);
+			/* swap the size field back to the cpu so we
+			 * can assign it to the sgl.
+			 */
+			bde.tus.w = le32_to_cpu(bpl->tus.w);
+			sgl->sge_len = cpu_to_le32(bde.tus.f.bdeSize);
+			/* The offsets in the sgl need to be accumulated
+			 * separately for the request and reply lists.
+			 * The request is always first, the reply follows.
+			 */
+			switch (cmd) {
+			case CMD_GEN_REQUEST64_WQE:
+				/* add up the reply sg entries */
+				if (bpl->tus.f.bdeFlags == BUFF_TYPE_BDE_64I)
+					inbound++;
+				/* first inbound? reset the offset */
+				if (inbound == 1)
+					offset = 0;
+				bf_set(lpfc_sli4_sge_offset, sgl, offset);
+				bf_set(lpfc_sli4_sge_type, sgl,
+					LPFC_SGE_TYPE_DATA);
+				offset += bde.tus.f.bdeSize;
+				break;
+			case CMD_FCP_TRSP64_WQE:
+				bf_set(lpfc_sli4_sge_offset, sgl, 0);
+				bf_set(lpfc_sli4_sge_type, sgl,
+					LPFC_SGE_TYPE_DATA);
+				break;
+			case CMD_FCP_TSEND64_WQE:
+			case CMD_FCP_TRECEIVE64_WQE:
+				bf_set(lpfc_sli4_sge_type, sgl,
+					bpl->tus.f.bdeFlags);
+				if (i < 3)
+					offset = 0;
+				else
+					offset += bde.tus.f.bdeSize;
+				bf_set(lpfc_sli4_sge_offset, sgl, offset);
+				break;
+			}
+			sgl->word2 = cpu_to_le32(sgl->word2);
+			bpl++;
+			sgl++;
+		}
+	} else if (wqe->gen_req.bde.tus.f.bdeFlags == BUFF_TYPE_BDE_64) {
+		/* The addrHigh and addrLow fields of the BDE have not
+		 * been byteswapped yet so they need to be swapped
+		 * before putting them in the sgl.
+		 */
+		sgl->addr_hi = cpu_to_le32(wqe->gen_req.bde.addrHigh);
+		sgl->addr_lo = cpu_to_le32(wqe->gen_req.bde.addrLow);
+		sgl->word2 = le32_to_cpu(sgl->word2);
+		bf_set(lpfc_sli4_sge_last, sgl, 1);
+		sgl->word2 = cpu_to_le32(sgl->word2);
+		sgl->sge_len = cpu_to_le32(wqe->gen_req.bde.tus.f.bdeSize);
+	}
+	return sglq->sli4_xritag;
+}
+
+/**
+ * lpfc_sli4_issue_wqe - Issue an SLI4 Work Queue Entry (WQE)
+ * @phba: Pointer to HBA context object.
+ * @ring_number: Base sli ring number
+ * @pwqe: Pointer to command WQE.
+ **/
+int
+lpfc_sli4_issue_wqe(struct lpfc_hba *phba, uint32_t ring_number,
+		    struct lpfc_iocbq *pwqe)
+{
+	union lpfc_wqe *wqe = &pwqe->wqe;
+	struct lpfc_queue *wq;
+	struct lpfc_sglq *sglq;
+	struct lpfc_sli_ring *pring;
+	unsigned long iflags;
+
+	/* NVME_LS and NVME_LS ABTS requests. */
+	if (pwqe->iocb_flag & LPFC_IO_NVME_LS) {
+		pring =  phba->sli4_hba.nvmels_wq->pring;
+		spin_lock_irqsave(&pring->ring_lock, iflags);
+		sglq = __lpfc_sli_get_els_sglq(phba, pwqe);
+		if (!sglq) {
+			spin_unlock_irqrestore(&pring->ring_lock, iflags);
+			return WQE_BUSY;
+		}
+		pwqe->sli4_lxritag = sglq->sli4_lxritag;
+		pwqe->sli4_xritag = sglq->sli4_xritag;
+		if (lpfc_wqe_bpl2sgl(phba, pwqe, sglq) == NO_XRI) {
+			spin_unlock_irqrestore(&pring->ring_lock, iflags);
+			return WQE_ERROR;
+		}
+		bf_set(wqe_xri_tag, &pwqe->wqe.xmit_bls_rsp.wqe_com,
+		       pwqe->sli4_xritag);
+		if (lpfc_sli4_wq_put(phba->sli4_hba.nvmels_wq, wqe)) {
+			spin_unlock_irqrestore(&pring->ring_lock, iflags);
+			return WQE_ERROR;
+		}
+		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
+		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+		return 0;
+	}
+
+	/* NVME_FCREQ and NVME_ABTS requests */
+	if (pwqe->iocb_flag & LPFC_IO_NVME) {
+		/* Get the IO distribution (hba_wqidx) for WQ assignment. */
+		pring = phba->sli4_hba.nvme_wq[pwqe->hba_wqidx]->pring;
+
+		spin_lock_irqsave(&pring->ring_lock, iflags);
+		wq = phba->sli4_hba.nvme_wq[pwqe->hba_wqidx];
+		bf_set(wqe_cqid, &wqe->generic.wqe_com,
+		      phba->sli4_hba.nvme_cq[pwqe->hba_wqidx]->queue_id);
+		if (lpfc_sli4_wq_put(wq, wqe)) {
+			spin_unlock_irqrestore(&pring->ring_lock, iflags);
+			return WQE_ERROR;
+		}
+		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
+		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+		return 0;
+	}
+
+	return WQE_ERROR;
+}
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 3fad5657514b..72520125251b 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -54,9 +54,16 @@ struct lpfc_iocbq {
 	uint16_t iotag;         /* pre-assigned IO tag */
 	uint16_t sli4_lxritag;  /* logical pre-assigned XRI. */
 	uint16_t sli4_xritag;   /* pre-assigned XRI, (OXID) tag. */
+	uint16_t hba_wqidx;     /* index to HBA work queue */
 	struct lpfc_cq_event cq_event;
+	struct lpfc_wcqe_complete wcqe_cmpl;	/* WQE cmpl */
+	uint64_t isr_timestamp;
 
-	IOCB_t iocb;		/* IOCB cmd */
+	/* Be careful here */
+	union lpfc_wqe wqe;	/* WQE cmd */
+	IOCB_t iocb;		/* For IOCB cmd or if we want 128 byte WQE */
+
+	uint8_t rsvd2;
 	uint8_t priority;	/* OAS priority */
 	uint8_t retry;		/* retry counter for IOCB cmd - if needed */
 	uint32_t iocb_flag;
@@ -82,9 +89,12 @@ struct lpfc_iocbq {
 #define LPFC_IO_OAS		0x10000 /* OAS FCP IO */
 #define LPFC_IO_FOF		0x20000 /* FOF FCP IO */
 #define LPFC_IO_LOOPBACK	0x40000 /* Loopback IO */
+#define LPFC_PRLI_NVME_REQ	0x80000 /* This is an NVME PRLI. */
+#define LPFC_PRLI_FCP_REQ	0x100000 /* This is an NVME PRLI. */
+#define LPFC_IO_NVME	        0x200000 /* NVME FCP command */
+#define LPFC_IO_NVME_LS		0x400000 /* NVME LS command */
 
 	uint32_t drvrTimeout;	/* driver timeout in seconds */
-	uint32_t fcp_wqidx;	/* index to FCP work queue */
 	struct lpfc_vport *vport;/* virtual port pointer */
 	void *context1;		/* caller context information */
 	void *context2;		/* caller context information */
@@ -103,6 +113,8 @@ struct lpfc_iocbq {
 			   struct lpfc_iocbq *);
 	void (*iocb_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
 			   struct lpfc_iocbq *);
+	void (*wqe_cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
+			  struct lpfc_wcqe_complete *);
 };
 
 #define SLI_IOCB_RET_IOCB      1	/* Return IOCB if cmd ring full */
@@ -112,6 +124,14 @@ struct lpfc_iocbq {
 #define IOCB_ERROR          2
 #define IOCB_TIMEDOUT       3
 
+#define SLI_WQE_RET_WQE    1    /* Return WQE if cmd ring full */
+
+#define WQE_SUCCESS        0
+#define WQE_BUSY           1
+#define WQE_ERROR          2
+#define WQE_TIMEDOUT       3
+#define WQE_ABORTED        4
+
 #define LPFC_MBX_WAKE		1
 #define LPFC_MBX_IMED_UNREG	2
 
@@ -298,11 +318,7 @@ struct lpfc_sli {
 #define LPFC_MENLO_MAINT          0x1000 /* need for menl fw download */
 #define LPFC_SLI_ASYNC_MBX_BLK    0x2000 /* Async mailbox is blocked */
 
-	struct lpfc_sli_ring *ring;
-	int fcp_ring;		/* ring used for FCP initiator commands */
-	int next_ring;
-
-	int extra_ring;		/* extra ring used for other protocols */
+	struct lpfc_sli_ring *sli3_ring;
 
 	struct lpfc_sli_stat slistat;	/* SLI statistical info */
 	struct list_head mboxq;
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index dfbb25e5c5b6..b5b4f6b843c0 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -35,9 +35,10 @@
 #define LPFC_NEMBED_MBOX_SGL_CNT		254
 
 /* Multi-queue arrangement for FCP EQ/CQ/WQ tuples */
-#define LPFC_FCP_IO_CHAN_DEF       4
-#define LPFC_FCP_IO_CHAN_MIN       1
-#define LPFC_FCP_IO_CHAN_MAX       16
+#define LPFC_HBA_IO_CHAN_MIN	0
+#define LPFC_HBA_IO_CHAN_MAX	32
+#define LPFC_FCP_IO_CHAN_DEF	4
+#define LPFC_NVME_IO_CHAN_DEF	0
 
 /* Number of channels used for Flash Optimized Fabric (FOF) operations */
 
@@ -107,6 +108,8 @@ enum lpfc_sli4_queue_subtype {
 	LPFC_MBOX,
 	LPFC_FCP,
 	LPFC_ELS,
+	LPFC_NVME,
+	LPFC_NVME_LS,
 	LPFC_USOL
 };
 
@@ -125,25 +128,41 @@ union sli4_qe {
 	struct lpfc_rqe *rqe;
 };
 
+/* RQ buffer list */
+struct lpfc_rqb {
+	uint16_t entry_count;	  /* Current number of RQ slots */
+	uint16_t buffer_count;	  /* Current number of buffers posted */
+	struct list_head rqb_buffer_list;  /* buffers assigned to this HBQ */
+				  /* Callback for HBQ buffer allocation */
+	struct rqb_dmabuf *(*rqb_alloc_buffer)(struct lpfc_hba *);
+				  /* Callback for HBQ buffer free */
+	void               (*rqb_free_buffer)(struct lpfc_hba *,
+					       struct rqb_dmabuf *);
+};
+
 struct lpfc_queue {
 	struct list_head list;
+	struct list_head wq_list;
 	enum lpfc_sli4_queue_type type;
 	enum lpfc_sli4_queue_subtype subtype;
 	struct lpfc_hba *phba;
 	struct list_head child_list;
+	struct list_head page_list;
+	struct list_head sgl_list;
 	uint32_t entry_count;	/* Number of entries to support on the queue */
 	uint32_t entry_size;	/* Size of each queue entry. */
 	uint32_t entry_repost;	/* Count of entries before doorbell is rung */
 #define LPFC_QUEUE_MIN_REPOST	8
 	uint32_t queue_id;	/* Queue ID assigned by the hardware */
 	uint32_t assoc_qid;     /* Queue ID associated with, for CQ/WQ/MQ */
-	struct list_head page_list;
 	uint32_t page_count;	/* Number of pages allocated for this queue */
 	uint32_t host_index;	/* The host's index for putting or getting */
 	uint32_t hba_index;	/* The last known hba index for get or put */
 
 	struct lpfc_sli_ring *pring; /* ptr to io ring associated with q */
+	struct lpfc_rqb *rqbp;	/* ptr to RQ buffers */
 
+	uint16_t sgl_list_cnt;
 	uint16_t db_format;
 #define LPFC_DB_RING_FORMAT	0x01
 #define LPFC_DB_LIST_FORMAT	0x02
@@ -176,6 +195,8 @@ struct lpfc_queue {
 #define	RQ_buf_trunc		q_cnt_3
 #define	RQ_rcv_buf		q_cnt_4
 
+	uint64_t isr_timestamp;
+	struct lpfc_queue *assoc_qp;
 	union sli4_qe qe[1];	/* array to index entries (must be last) */
 };
 
@@ -338,6 +359,7 @@ struct lpfc_bmbx {
 #define LPFC_CQE_DEF_COUNT      1024
 #define LPFC_WQE_DEF_COUNT      256
 #define LPFC_WQE128_DEF_COUNT   128
+#define LPFC_WQE128_MAX_COUNT   256
 #define LPFC_MQE_DEF_COUNT      16
 #define LPFC_RQE_DEF_COUNT	512
 
@@ -379,10 +401,14 @@ struct lpfc_max_cfg_param {
 
 struct lpfc_hba;
 /* SLI4 HBA multi-fcp queue handler struct */
-struct lpfc_fcp_eq_hdl {
+struct lpfc_hba_eq_hdl {
 	uint32_t idx;
 	struct lpfc_hba *phba;
-	atomic_t fcp_eq_in_use;
+	atomic_t hba_eq_in_use;
+	struct cpumask *cpumask;
+	/* CPU affinitsed to or 0xffffffff if multiple */
+	uint32_t cpu;
+#define LPFC_MULTI_CPU_AFFINITY 0xffffffff
 };
 
 /* Port Capabilities for SLI4 Parameters */
@@ -427,6 +453,7 @@ struct lpfc_pc_sli4_params {
 	uint8_t wqsize;
 #define LPFC_WQ_SZ64_SUPPORT	1
 #define LPFC_WQ_SZ128_SUPPORT	2
+	uint8_t wqpcnt;
 };
 
 struct lpfc_iov {
@@ -445,7 +472,7 @@ struct lpfc_sli4_lnk_info {
 	uint8_t optic_state;
 };
 
-#define LPFC_SLI4_HANDLER_CNT		(LPFC_FCP_IO_CHAN_MAX+ \
+#define LPFC_SLI4_HANDLER_CNT		(LPFC_HBA_IO_CHAN_MAX+ \
 					 LPFC_FOF_IO_CHAN_NUM)
 #define LPFC_SLI4_HANDLER_NAME_SZ	16
 
@@ -516,21 +543,30 @@ struct lpfc_sli4_hba {
 	struct lpfc_register sli_intf;
 	struct lpfc_pc_sli4_params pc_sli4_params;
 	uint8_t handler_name[LPFC_SLI4_HANDLER_CNT][LPFC_SLI4_HANDLER_NAME_SZ];
-	struct lpfc_fcp_eq_hdl *fcp_eq_hdl; /* FCP per-WQ handle */
+	struct lpfc_hba_eq_hdl *hba_eq_hdl; /* HBA per-WQ handle */
 
 	/* Pointers to the constructed SLI4 queues */
-	struct lpfc_queue **hba_eq;/* Event queues for HBA */
-	struct lpfc_queue **fcp_cq;/* Fast-path FCP compl queue */
-	struct lpfc_queue **fcp_wq;/* Fast-path FCP work queue */
+	struct lpfc_queue **hba_eq;  /* Event queues for HBA */
+	struct lpfc_queue **fcp_cq;  /* Fast-path FCP compl queue */
+	struct lpfc_queue **nvme_cq; /* Fast-path NVME compl queue */
+	struct lpfc_queue **fcp_wq;  /* Fast-path FCP work queue */
+	struct lpfc_queue **nvme_wq; /* Fast-path NVME work queue */
 	uint16_t *fcp_cq_map;
+	uint16_t *nvme_cq_map;
+	struct list_head lpfc_wq_list;
 
 	struct lpfc_queue *mbx_cq; /* Slow-path mailbox complete queue */
 	struct lpfc_queue *els_cq; /* Slow-path ELS response complete queue */
+	struct lpfc_queue *nvmels_cq; /* NVME LS complete queue */
 	struct lpfc_queue *mbx_wq; /* Slow-path MBOX work queue */
 	struct lpfc_queue *els_wq; /* Slow-path ELS work queue */
+	struct lpfc_queue *nvmels_wq; /* NVME LS work queue */
 	struct lpfc_queue *hdr_rq; /* Slow-path Header Receive queue */
 	struct lpfc_queue *dat_rq; /* Slow-path Data Receive queue */
 
+	struct lpfc_name wwnn;
+	struct lpfc_name wwpn;
+
 	uint32_t fw_func_mode;	/* FW function protocol mode */
 	uint32_t ulp0_mode;	/* ULP0 protocol mode */
 	uint32_t ulp1_mode;	/* ULP1 protocol mode */
@@ -567,14 +603,17 @@ struct lpfc_sli4_hba {
 	uint16_t rpi_hdrs_in_use; /* must post rpi hdrs if set. */
 	uint16_t next_xri; /* last_xri - max_cfg_param.xri_base = used */
 	uint16_t next_rpi;
+	uint16_t nvme_xri_max;
+	uint16_t nvme_xri_cnt;
+	uint16_t nvme_xri_start;
 	uint16_t scsi_xri_max;
 	uint16_t scsi_xri_cnt;
-	uint16_t els_xri_cnt;
 	uint16_t scsi_xri_start;
-	struct list_head lpfc_free_sgl_list;
-	struct list_head lpfc_sgl_list;
+	uint16_t els_xri_cnt;
+	struct list_head lpfc_els_sgl_list;
 	struct list_head lpfc_abts_els_sgl_list;
 	struct list_head lpfc_abts_scsi_buf_list;
+	struct list_head lpfc_abts_nvme_buf_list;
 	struct lpfc_sglq **lpfc_sglq_active_list;
 	struct list_head lpfc_rpi_hdr_list;
 	unsigned long *rpi_bmask;
@@ -601,8 +640,9 @@ struct lpfc_sli4_hba {
 #define LPFC_SLI4_PPNAME_NON	0
 #define LPFC_SLI4_PPNAME_GET	1
 	struct lpfc_iov iov;
+	spinlock_t abts_nvme_buf_list_lock; /* list of aborted SCSI IOs */
 	spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */
-	spinlock_t abts_sgl_list_lock; /* list of aborted els IOs */
+	spinlock_t sgl_list_lock; /* list of aborted els IOs */
 	uint32_t physical_port;
 
 	/* CPU to vector mapping information */
@@ -614,7 +654,7 @@ struct lpfc_sli4_hba {
 
 enum lpfc_sge_type {
 	GEN_BUFF_TYPE,
-	SCSI_BUFF_TYPE
+	SCSI_BUFF_TYPE,
 };
 
 enum lpfc_sgl_state {
@@ -693,7 +733,7 @@ struct lpfc_queue *lpfc_sli4_queue_alloc(struct lpfc_hba *, uint32_t,
 			uint32_t);
 void lpfc_sli4_queue_free(struct lpfc_queue *);
 int lpfc_eq_create(struct lpfc_hba *, struct lpfc_queue *, uint32_t);
-int lpfc_modify_fcp_eq_delay(struct lpfc_hba *, uint32_t);
+int lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq);
 int lpfc_cq_create(struct lpfc_hba *, struct lpfc_queue *,
 			struct lpfc_queue *, uint32_t, uint32_t);
 int32_t lpfc_mq_create(struct lpfc_hba *, struct lpfc_queue *,
@@ -745,6 +785,7 @@ int lpfc_sli4_brdreset(struct lpfc_hba *);
 int lpfc_sli4_add_fcf_record(struct lpfc_hba *, struct fcf_record *);
 void lpfc_sli_remove_dflt_fcf(struct lpfc_hba *);
 int lpfc_sli4_get_els_iocb_cnt(struct lpfc_hba *);
+int lpfc_sli4_get_iocb_cnt(struct lpfc_hba *phba);
 int lpfc_sli4_init_vpi(struct lpfc_vport *);
 uint32_t lpfc_sli4_cq_release(struct lpfc_queue *, bool);
 uint32_t lpfc_sli4_eq_release(struct lpfc_queue *, bool);
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 5bbe6af148dd..07c7c5f9fdde 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -403,6 +403,8 @@ lpfc_vport_create(struct fc_vport *fc_vport, bool disable)
 		vport->fdmi_port_mask = phba->pport->fdmi_port_mask;
 	}
 
+	/* todo: init: register port with nvme */
+
 	/*
 	 * In SLI4, the vpi must be activated before it can be used
 	 * by the port.
-- 
GitLab


From a0f2d3ef374fd8d2f51b8cc1ea723014b1aa2c9b Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:31 -0800
Subject: [PATCH 146/898] scsi: lpfc: NVME Initiator: Merge into FC discovery

NVME Initiator: Merge into FC discovery

Adds NVME PRLI support and Nameserver registrations and Queries for NVME

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h           |   6 +-
 drivers/scsi/lpfc/lpfc_ct.c        | 357 +++++++++++++++++++----------
 drivers/scsi/lpfc/lpfc_disc.h      |  19 +-
 drivers/scsi/lpfc/lpfc_els.c       | 280 +++++++++++++++-------
 drivers/scsi/lpfc/lpfc_hbadisc.c   | 169 +++++++++++---
 drivers/scsi/lpfc/lpfc_hw.h        |  69 ++++--
 drivers/scsi/lpfc/lpfc_hw4.h       |  43 ++++
 drivers/scsi/lpfc/lpfc_init.c      |   7 +
 drivers/scsi/lpfc/lpfc_nportdisc.c | 177 ++++++++++++--
 drivers/scsi/lpfc/lpfc_scsi.c      |   3 +-
 10 files changed, 851 insertions(+), 279 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 77ad757ca231..81c47d1aebb2 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -123,6 +123,8 @@ struct perf_prof {
 	uint16_t wqidx[40];
 };
 
+#define LPFC_FC4_TYPE_BITMASK	0x00000100
+
 /* Provide DMA memory definitions the driver uses per port instance. */
 struct lpfc_dmabuf {
 	struct list_head list;
@@ -390,7 +392,8 @@ struct lpfc_vport {
 	int32_t stopped;   /* HBA has not been restarted since last ERATT */
 	uint8_t fc_linkspeed;	/* Link speed after last READ_LA */
 
-	uint32_t num_disc_nodes;	/*in addition to hba_state */
+	uint32_t num_disc_nodes;	/* in addition to hba_state */
+	uint32_t gidft_inp;		/* cnt of outstanding GID_FTs */
 
 	uint32_t fc_nlp_cnt;	/* outstanding NODELIST requests */
 	uint32_t fc_rscn_id_cnt;	/* count of RSCNs payloads in list */
@@ -443,7 +446,6 @@ struct lpfc_vport {
 	uint32_t cfg_max_scsicmpl_time;
 	uint32_t cfg_tgt_queue_depth;
 	uint32_t cfg_first_burst_size;
-
 	uint32_t dev_loss_tmo_changed;
 
 	struct fc_vport *fc_vport;
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 4ac03b16d17f..afb25369bc3b 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -40,8 +40,9 @@
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_version.h"
@@ -453,8 +454,73 @@ lpfc_find_vport_by_did(struct lpfc_hba *phba, uint32_t did) {
 	return NULL;
 }
 
+static void
+lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
+{
+	struct lpfc_nodelist *ndlp;
+
+	if ((vport->port_type != LPFC_NPIV_PORT) ||
+	    !(vport->ct_flags & FC_CT_RFF_ID) || !vport->cfg_restrict_login) {
+
+		ndlp = lpfc_setup_disc_node(vport, Did);
+
+		if (ndlp && NLP_CHK_NODE_ACT(ndlp)) {
+			/* By default, the driver expects to support FCP FC4 */
+			if (fc4_type == FC_TYPE_FCP)
+				ndlp->nlp_fc4_type |= NLP_FC4_FCP;
+
+			if (fc4_type == FC_TYPE_NVME)
+				ndlp->nlp_fc4_type |= NLP_FC4_NVME;
+
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+					 "0238 Process x%06x NameServer Rsp "
+					 "Data: x%x x%x x%x x%x\n", Did,
+					 ndlp->nlp_flag, ndlp->nlp_fc4_type,
+					 vport->fc_flag,
+					 vport->fc_rscn_id_cnt);
+		} else
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+					 "0239 Skip x%06x NameServer Rsp "
+					 "Data: x%x x%x\n", Did,
+					 vport->fc_flag,
+					 vport->fc_rscn_id_cnt);
+
+	} else {
+		if (!(vport->fc_flag & FC_RSCN_MODE) ||
+		    lpfc_rscn_payload_check(vport, Did)) {
+			/*
+			 * This NPortID was previously a FCP target,
+			 * Don't even bother to send GFF_ID.
+			 */
+			ndlp = lpfc_findnode_did(vport, Did);
+			if (ndlp && NLP_CHK_NODE_ACT(ndlp))
+				ndlp->nlp_fc4_type = fc4_type;
+
+			if (ndlp && NLP_CHK_NODE_ACT(ndlp)) {
+				ndlp->nlp_fc4_type = fc4_type;
+
+				if (ndlp->nlp_type & NLP_FCP_TARGET)
+					lpfc_setup_disc_node(vport, Did);
+
+				else if (lpfc_ns_cmd(vport, SLI_CTNS_GFF_ID,
+							0, Did) == 0)
+					vport->num_disc_nodes++;
+
+				else
+					lpfc_setup_disc_node(vport, Did);
+			}
+		} else
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+					 "0245 Skip x%06x NameServer Rsp "
+					 "Data: x%x x%x\n", Did,
+					 vport->fc_flag,
+					 vport->fc_rscn_id_cnt);
+	}
+}
+
 static int
-lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint32_t Size)
+lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type,
+	    uint32_t Size)
 {
 	struct lpfc_hba  *phba = vport->phba;
 	struct lpfc_sli_ct_request *Response =
@@ -499,97 +565,12 @@ lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint32_t Size)
 			 */
 			if ((Did != vport->fc_myDID) &&
 			    ((lpfc_find_vport_by_did(phba, Did) == NULL) ||
-			     vport->cfg_peer_port_login)) {
-				if ((vport->port_type != LPFC_NPIV_PORT) ||
-				    (!(vport->ct_flags & FC_CT_RFF_ID)) ||
-				    (!vport->cfg_restrict_login)) {
-					ndlp = lpfc_setup_disc_node(vport, Did);
-					if (ndlp && NLP_CHK_NODE_ACT(ndlp)) {
-						lpfc_debugfs_disc_trc(vport,
-						LPFC_DISC_TRC_CT,
-						"Parse GID_FTrsp: "
-						"did:x%x flg:x%x x%x",
-						Did, ndlp->nlp_flag,
-						vport->fc_flag);
-
-						lpfc_printf_vlog(vport,
-							KERN_INFO,
-							LOG_DISCOVERY,
-							"0238 Process "
-							"x%x NameServer Rsp"
-							"Data: x%x x%x x%x\n",
-							Did, ndlp->nlp_flag,
-							vport->fc_flag,
-							vport->fc_rscn_id_cnt);
-					} else {
-						lpfc_debugfs_disc_trc(vport,
-						LPFC_DISC_TRC_CT,
-						"Skip1 GID_FTrsp: "
-						"did:x%x flg:x%x cnt:%d",
-						Did, vport->fc_flag,
-						vport->fc_rscn_id_cnt);
-
-						lpfc_printf_vlog(vport,
-							KERN_INFO,
-							LOG_DISCOVERY,
-							"0239 Skip x%x "
-							"NameServer Rsp Data: "
-							"x%x x%x\n",
-							Did, vport->fc_flag,
-							vport->fc_rscn_id_cnt);
-					}
-
-				} else {
-					if (!(vport->fc_flag & FC_RSCN_MODE) ||
-					(lpfc_rscn_payload_check(vport, Did))) {
-						lpfc_debugfs_disc_trc(vport,
-						LPFC_DISC_TRC_CT,
-						"Query GID_FTrsp: "
-						"did:x%x flg:x%x cnt:%d",
-						Did, vport->fc_flag,
-						vport->fc_rscn_id_cnt);
-
-						/* This NPortID was previously
-						 * a FCP target, * Don't even
-						 * bother to send GFF_ID.
-						 */
-						ndlp = lpfc_findnode_did(vport,
-							Did);
-						if (ndlp &&
-						    NLP_CHK_NODE_ACT(ndlp)
-						    && (ndlp->nlp_type &
-						     NLP_FCP_TARGET))
-							lpfc_setup_disc_node
-								(vport, Did);
-						else if (lpfc_ns_cmd(vport,
-							SLI_CTNS_GFF_ID,
-							0, Did) == 0)
-							vport->num_disc_nodes++;
-						else
-							lpfc_setup_disc_node
-								(vport, Did);
-					}
-					else {
-						lpfc_debugfs_disc_trc(vport,
-						LPFC_DISC_TRC_CT,
-						"Skip2 GID_FTrsp: "
-						"did:x%x flg:x%x cnt:%d",
-						Did, vport->fc_flag,
-						vport->fc_rscn_id_cnt);
-
-						lpfc_printf_vlog(vport,
-							KERN_INFO,
-							LOG_DISCOVERY,
-							"0245 Skip x%x "
-							"NameServer Rsp Data: "
-							"x%x x%x\n",
-							Did, vport->fc_flag,
-							vport->fc_rscn_id_cnt);
-					}
-				}
-			}
+			     vport->cfg_peer_port_login))
+				lpfc_prep_node_fc4type(vport, Did, fc4_type);
+
 			if (CTentry & (cpu_to_be32(SLI_CT_LAST_ENTRY)))
 				goto nsout1;
+
 			Cnt -= sizeof(uint32_t);
 		}
 		ctptr = NULL;
@@ -609,16 +590,18 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 	IOCB_t *irsp;
 	struct lpfc_dmabuf *outp;
+	struct lpfc_dmabuf *inp;
 	struct lpfc_sli_ct_request *CTrsp;
+	struct lpfc_sli_ct_request *CTreq;
 	struct lpfc_nodelist *ndlp;
-	int rc;
+	int rc, type;
 
 	/* First save ndlp, before we overwrite it */
 	ndlp = cmdiocb->context_un.ndlp;
 
 	/* we pass cmdiocb to state machine which needs rspiocb as well */
 	cmdiocb->context_un.rsp_iocb = rspiocb;
-
+	inp = (struct lpfc_dmabuf *) cmdiocb->context1;
 	outp = (struct lpfc_dmabuf *) cmdiocb->context2;
 	irsp = &rspiocb->iocb;
 
@@ -656,9 +639,14 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			    IOERR_NO_RESOURCES)
 				vport->fc_ns_retry++;
 
+			type = lpfc_get_gidft_type(vport, cmdiocb);
+			if (type == 0)
+				goto out;
+
 			/* CT command is being retried */
+			vport->gidft_inp--;
 			rc = lpfc_ns_cmd(vport, SLI_CTNS_GID_FT,
-					 vport->fc_ns_retry, 0);
+					 vport->fc_ns_retry, type);
 			if (rc == 0)
 				goto out;
 		}
@@ -670,13 +658,18 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				 irsp->ulpStatus, vport->fc_ns_retry);
 	} else {
 		/* Good status, continue checking */
+		CTreq = (struct lpfc_sli_ct_request *) inp->virt;
 		CTrsp = (struct lpfc_sli_ct_request *) outp->virt;
 		if (CTrsp->CommandResponse.bits.CmdRsp ==
 		    cpu_to_be16(SLI_CT_RESPONSE_FS_ACC)) {
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
-					 "0208 NameServer Rsp Data: x%x\n",
-					 vport->fc_flag);
-			lpfc_ns_rsp(vport, outp,
+					 "0208 NameServer Rsp Data: x%x x%x\n",
+					 vport->fc_flag,
+					 CTreq->un.gid.Fc4Type);
+
+			lpfc_ns_rsp(vport,
+				    outp,
+				    CTreq->un.gid.Fc4Type,
 				    (uint32_t) (irsp->un.genreq64.bdl.bdeSize));
 		} else if (CTrsp->CommandResponse.bits.CmdRsp ==
 			   be16_to_cpu(SLI_CT_RESPONSE_FS_RJT)) {
@@ -731,9 +724,11 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				(uint32_t) CTrsp->ReasonCode,
 				(uint32_t) CTrsp->Explanation);
 		}
+		vport->gidft_inp--;
 	}
 	/* Link up / RSCN discovery */
-	if (vport->num_disc_nodes == 0) {
+	if ((vport->num_disc_nodes == 0) &&
+	    (vport->gidft_inp == 0)) {
 		/*
 		 * The driver has cycled through all Nports in the RSCN payload.
 		 * Complete the handling by cleaning up and marking the
@@ -881,6 +876,56 @@ lpfc_cmpl_ct_cmd_gff_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	return;
 }
 
+static void
+lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
+				struct lpfc_iocbq *rspiocb)
+{
+	struct lpfc_vport *vport = cmdiocb->vport;
+	IOCB_t *irsp = &rspiocb->iocb;
+	struct lpfc_dmabuf *inp = (struct lpfc_dmabuf *)cmdiocb->context1;
+	struct lpfc_dmabuf *outp = (struct lpfc_dmabuf *)cmdiocb->context2;
+	struct lpfc_sli_ct_request *CTrsp;
+	int did;
+	struct lpfc_nodelist *ndlp;
+	uint32_t fc4_data_0, fc4_data_1;
+
+	did = ((struct lpfc_sli_ct_request *)inp->virt)->un.gft.PortId;
+	did = be32_to_cpu(did);
+
+	if (irsp->ulpStatus == IOSTAT_SUCCESS) {
+		/* Good status, continue checking */
+		CTrsp = (struct lpfc_sli_ct_request *)outp->virt;
+		fc4_data_0 = be32_to_cpu(CTrsp->un.gft_acc.fc4_types[0]);
+		fc4_data_1 = be32_to_cpu(CTrsp->un.gft_acc.fc4_types[1]);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
+				 "3062 DID x%06x GFT Wd0 x%08x Wd1 x%08x\n",
+				 did, fc4_data_0, fc4_data_1);
+
+		ndlp = lpfc_findnode_did(vport, did);
+		if (ndlp) {
+			/* The bitmask value for FCP and NVME FCP types is
+			 * the same because they are 32 bits distant from
+			 * each other in word0 and word0.
+			 */
+			if (fc4_data_0 & LPFC_FC4_TYPE_BITMASK)
+				ndlp->nlp_fc4_type |= NLP_FC4_FCP;
+			if (fc4_data_1 &  LPFC_FC4_TYPE_BITMASK)
+				ndlp->nlp_fc4_type |= NLP_FC4_NVME;
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
+					 "3064 Setting ndlp %p, DID x%06x with "
+					 "FC4 x%08x, Data: x%08x x%08x\n",
+					 ndlp, did, ndlp->nlp_fc4_type,
+					 FC_TYPE_FCP, FC_TYPE_NVME);
+		}
+		ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
+		lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
+		lpfc_issue_els_prli(vport, ndlp, 0);
+	} else
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
+				 "3065 GFT_ID failed x%08x\n", irsp->ulpStatus);
+
+	lpfc_ct_free_iocb(phba, cmdiocb);
+}
 
 static void
 lpfc_cmpl_ct(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
@@ -1071,31 +1116,27 @@ lpfc_cmpl_ct_cmd_rff_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	return;
 }
 
+/*
+ * Although the symbolic port name is thought to be an integer
+ * as of January 18, 2016, leave it as a string until more of
+ * the record state becomes defined.
+ */
 int
 lpfc_vport_symbolic_port_name(struct lpfc_vport *vport, char *symbol,
 	size_t size)
 {
 	int n;
-	uint8_t *wwn = vport->phba->wwpn;
-
-	n = snprintf(symbol, size,
-		     "Emulex PPN-%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x",
-		     wwn[0], wwn[1], wwn[2], wwn[3],
-		     wwn[4], wwn[5], wwn[6], wwn[7]);
 
-	if (vport->port_type == LPFC_PHYSICAL_PORT)
-		return n;
-
-	if (n < size)
-		n += snprintf(symbol + n, size - n, " VPort-%d", vport->vpi);
-
-	if (n < size &&
-	    strlen(vport->fc_vport->symbolic_name))
-		n += snprintf(symbol + n, size - n, " VName-%s",
-			      vport->fc_vport->symbolic_name);
+	/*
+	 * Use the lpfc board number as the Symbolic Port
+	 * Name object.  NPIV is not in play so this integer
+	 * value is sufficient and unique per FC-ID.
+	 */
+	n = snprintf(symbol, size, "%d", vport->phba->brd_no);
 	return n;
 }
 
+
 int
 lpfc_vport_symbolic_node_name(struct lpfc_vport *vport, char *symbol,
 	size_t size)
@@ -1106,24 +1147,26 @@ lpfc_vport_symbolic_node_name(struct lpfc_vport *vport, char *symbol,
 	lpfc_decode_firmware_rev(vport->phba, fwrev, 0);
 
 	n = snprintf(symbol, size, "Emulex %s", vport->phba->ModelName);
-
 	if (size < n)
 		return n;
-	n += snprintf(symbol + n, size - n, " FV%s", fwrev);
 
+	n += snprintf(symbol + n, size - n, " FV%s", fwrev);
 	if (size < n)
 		return n;
-	n += snprintf(symbol + n, size - n, " DV%s", lpfc_release_version);
 
+	n += snprintf(symbol + n, size - n, " DV%s.",
+		      lpfc_release_version);
 	if (size < n)
 		return n;
-	n += snprintf(symbol + n, size - n, " HN:%s", init_utsname()->nodename);
 
-	/* Note :- OS name is "Linux" */
+	n += snprintf(symbol + n, size - n, " HN:%s.",
+		      init_utsname()->nodename);
 	if (size < n)
 		return n;
-	n += snprintf(symbol + n, size - n, " OS:%s", init_utsname()->sysname);
 
+	/* Note :- OS name is "Linux" */
+	n += snprintf(symbol + n, size - n, " OS:%s\n",
+		      init_utsname()->sysname);
 	return n;
 }
 
@@ -1147,6 +1190,27 @@ lpfc_find_map_node(struct lpfc_vport *vport)
 	return cnt;
 }
 
+/*
+ * This routine will return the FC4 Type associated with the CT
+ * GID_FT command.
+ */
+int
+lpfc_get_gidft_type(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb)
+{
+	struct lpfc_sli_ct_request *CtReq;
+	struct lpfc_dmabuf *mp;
+	uint32_t type;
+
+	mp = cmdiocb->context1;
+	if (mp == NULL)
+		return 0;
+	CtReq = (struct lpfc_sli_ct_request *)mp->virt;
+	type = (uint32_t)CtReq->un.gid.Fc4Type;
+	if ((type != SLI_CTPT_FCP) && (type != SLI_CTPT_NVME))
+		return 0;
+	return type;
+}
+
 /*
  * lpfc_ns_cmd
  * Description:
@@ -1207,8 +1271,9 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 
 	/* NameServer Req */
 	lpfc_printf_vlog(vport, KERN_INFO ,LOG_DISCOVERY,
-			 "0236 NameServer Req Data: x%x x%x x%x\n",
-			 cmdcode, vport->fc_flag, vport->fc_rscn_id_cnt);
+			 "0236 NameServer Req Data: x%x x%x x%x x%x\n",
+			 cmdcode, vport->fc_flag, vport->fc_rscn_id_cnt,
+			 context);
 
 	bpl = (struct ulp_bde64 *) bmp->virt;
 	memset(bpl, 0, sizeof(struct ulp_bde64));
@@ -1219,6 +1284,8 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 		bpl->tus.f.bdeSize = GID_REQUEST_SZ;
 	else if (cmdcode == SLI_CTNS_GFF_ID)
 		bpl->tus.f.bdeSize = GFF_REQUEST_SZ;
+	else if (cmdcode == SLI_CTNS_GFT_ID)
+		bpl->tus.f.bdeSize = GFT_REQUEST_SZ;
 	else if (cmdcode == SLI_CTNS_RFT_ID)
 		bpl->tus.f.bdeSize = RFT_REQUEST_SZ;
 	else if (cmdcode == SLI_CTNS_RNN_ID)
@@ -1246,7 +1313,8 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 	case SLI_CTNS_GID_FT:
 		CtReq->CommandResponse.bits.CmdRsp =
 		    cpu_to_be16(SLI_CTNS_GID_FT);
-		CtReq->un.gid.Fc4Type = SLI_CTPT_FCP;
+		CtReq->un.gid.Fc4Type = context;
+
 		if (vport->port_state < LPFC_NS_QRY)
 			vport->port_state = LPFC_NS_QRY;
 		lpfc_set_disctmo(vport);
@@ -1261,12 +1329,32 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 		cmpl = lpfc_cmpl_ct_cmd_gff_id;
 		break;
 
+	case SLI_CTNS_GFT_ID:
+		CtReq->CommandResponse.bits.CmdRsp =
+			cpu_to_be16(SLI_CTNS_GFT_ID);
+		CtReq->un.gft.PortId = cpu_to_be32(context);
+		cmpl = lpfc_cmpl_ct_cmd_gft_id;
+		break;
+
 	case SLI_CTNS_RFT_ID:
 		vport->ct_flags &= ~FC_CT_RFT_ID;
 		CtReq->CommandResponse.bits.CmdRsp =
 		    cpu_to_be16(SLI_CTNS_RFT_ID);
 		CtReq->un.rft.PortId = cpu_to_be32(vport->fc_myDID);
-		CtReq->un.rft.fcpReg = 1;
+
+		/* Register FC4 FCP type if enabled.  */
+		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP))
+			CtReq->un.rft.fcpReg = 1;
+
+		/* Register NVME type if enabled.  Defined LE and swapped.
+		 * rsvd[0] is used as word1 because of the hard-coded
+		 * word0 usage in the ct_request data structure.
+		 */
+		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
+			CtReq->un.rft.rsvd[0] = cpu_to_be32(0x00000100);
+
 		cmpl = lpfc_cmpl_ct_cmd_rft_id;
 		break;
 
@@ -1316,7 +1404,25 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 		    cpu_to_be16(SLI_CTNS_RFF_ID);
 		CtReq->un.rff.PortId = cpu_to_be32(vport->fc_myDID);
 		CtReq->un.rff.fbits = FC4_FEATURE_INIT;
-		CtReq->un.rff.type_code = FC_TYPE_FCP;
+
+		/* The driver always supports FC_TYPE_FCP.  However, the
+		 * caller can specify NVME (type x28) as well.  But only
+		 * these that FC4 type is supported.
+		 */
+		if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) &&
+		    (context == FC_TYPE_NVME)) {
+			/* todo: init: revise localport nvme attributes */
+			CtReq->un.rff.type_code = context;
+
+		} else if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+			    (phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP)) &&
+			   (context == FC_TYPE_FCP))
+			CtReq->un.rff.type_code = context;
+
+		else
+			goto ns_cmd_free_bmpvirt;
+
 		cmpl = lpfc_cmpl_ct_cmd_rff_id;
 		break;
 	}
@@ -1337,6 +1443,7 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 	 */
 	lpfc_nlp_put(ndlp);
 
+ns_cmd_free_bmpvirt:
 	lpfc_mbuf_free(phba, bmp->virt, bmp->phys);
 ns_cmd_free_bmp:
 	kfree(bmp);
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 361f5b3d9d93..13cc1d19b336 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -86,6 +86,17 @@ struct lpfc_nodelist {
 #define NLP_FABRIC         0x4			/* entry rep a Fabric entity */
 #define NLP_FCP_TARGET     0x8			/* entry is an FCP target */
 #define NLP_FCP_INITIATOR  0x10			/* entry is an FCP Initiator */
+#define NLP_NVME_TARGET    0x20			/* entry is a NVME Target */
+#define NLP_NVME_INITIATOR 0x40			/* entry is a NVME Initiator */
+
+	uint16_t	nlp_fc4_type;		/* FC types node supports. */
+						/* Assigned from GID_FF, only
+						 * FCP (0x8) and NVME (0x28)
+						 * supported.
+						 */
+#define NLP_FC4_NONE	0x0
+#define NLP_FC4_FCP	0x1			/* FC4 Type FCP (value x8)) */
+#define NLP_FC4_NVME	0x2			/* FC4 TYPE NVME (value x28) */
 
 	uint16_t        nlp_rpi;
 	uint16_t        nlp_state;		/* state transition indicator */
@@ -107,8 +118,8 @@ struct lpfc_nodelist {
 
 	struct timer_list   nlp_delayfunc;	/* Used for delayed ELS cmds */
 	struct lpfc_hba *phba;
-	struct fc_rport *rport;			/* Corresponding FC transport
-						   port structure */
+	struct fc_rport *rport;		/* scsi_transport_fc port structure */
+	struct lpfc_nvme_rport *nrport;	/* nvme transport rport struct. */
 	struct lpfc_vport *vport;
 	struct lpfc_work_evt els_retry_evt;
 	struct lpfc_work_evt dev_loss_evt;
@@ -118,6 +129,10 @@ struct lpfc_nodelist {
 	unsigned long last_change_time;
 	unsigned long *active_rrqs_xri_bitmap;
 	struct lpfc_scsicmd_bkt *lat_data;	/* Latency data */
+	uint32_t fc4_prli_sent;
+	uint32_t upcall_flags;
+	uint32_t nvme_fb_size; /* NVME target's supported byte cnt */
+#define NVME_FB_BIT_SHIFT 9    /* PRLI Rsp first burst in 512B units. */
 };
 struct lpfc_node_rrq {
 	struct list_head list;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 7be235457540..e164eed25e3d 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -29,7 +29,6 @@
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport_fc.h>
 
-
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
 #include "lpfc_sli.h"
@@ -1513,7 +1512,7 @@ static struct lpfc_nodelist *
 lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 			 struct lpfc_nodelist *ndlp)
 {
-	struct lpfc_vport    *vport = ndlp->vport;
+	struct lpfc_vport *vport = ndlp->vport;
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 	struct lpfc_nodelist *new_ndlp;
 	struct lpfc_rport_data *rdata;
@@ -1868,10 +1867,12 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	/* PLOGI completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0102 PLOGI completes to NPort x%x "
+			 "0102 PLOGI completes to NPort x%06x "
 			 "Data: x%x x%x x%x x%x x%x\n",
-			 ndlp->nlp_DID, irsp->ulpStatus, irsp->un.ulpWord[4],
-			 irsp->ulpTimeout, disc, vport->num_disc_nodes);
+			 ndlp->nlp_DID, ndlp->nlp_fc4_type,
+			 irsp->ulpStatus, irsp->un.ulpWord[4],
+			 disc, vport->num_disc_nodes);
+
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport)) {
 		spin_lock_irq(shost->host_lock);
@@ -2000,7 +2001,6 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry)
 		sp->cmn.fcphHigh = FC_PH3;
 
 	sp->cmn.valid_vendor_ver_level = 0;
-	memset(sp->vendorVersion, 0, sizeof(sp->vendorVersion));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Issue PLOGI:     did:x%x",
@@ -2052,14 +2052,17 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		"PRLI cmpl:       status:x%x/x%x did:x%x",
 		irsp->ulpStatus, irsp->un.ulpWord[4],
 		ndlp->nlp_DID);
+
+	/* Ddriver supports multiple FC4 types.  Counters matter. */
+	vport->fc_prli_sent--;
+
 	/* PRLI completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0103 PRLI completes to NPort x%x "
+			 "0103 PRLI completes to NPort x%06x "
 			 "Data: x%x x%x x%x x%x\n",
 			 ndlp->nlp_DID, irsp->ulpStatus, irsp->un.ulpWord[4],
-			 irsp->ulpTimeout, vport->num_disc_nodes);
+			 vport->num_disc_nodes, ndlp->fc4_prli_sent);
 
-	vport->fc_prli_sent--;
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport))
 		goto out;
@@ -2068,6 +2071,7 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* Check for retry */
 		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
 			/* ELS command is being retried */
+			ndlp->fc4_prli_sent--;
 			goto out;
 		}
 		/* PRLI failed */
@@ -2082,9 +2086,14 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			lpfc_disc_state_machine(vport, ndlp, cmdiocb,
 						NLP_EVT_CMPL_PRLI);
 	} else
-		/* Good status, call state machine */
+		/* Good status, call state machine.  However, if another
+		 * PRLI is outstanding, don't call the state machine
+		 * because final disposition to Mapped or Unmapped is
+		 * completed there.
+		 */
 		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
 					NLP_EVT_CMPL_PRLI);
+
 out:
 	lpfc_els_free_iocb(phba, cmdiocb);
 	return;
@@ -2118,42 +2127,94 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 	struct lpfc_hba *phba = vport->phba;
 	PRLI *npr;
+	struct lpfc_nvme_prli *npr_nvme;
 	struct lpfc_iocbq *elsiocb;
 	uint8_t *pcmd;
 	uint16_t cmdsize;
-
-	cmdsize = (sizeof(uint32_t) + sizeof(PRLI));
+	u32 local_nlp_type, elscmd;
+
+	local_nlp_type = ndlp->nlp_fc4_type;
+
+ send_next_prli:
+	if (local_nlp_type & NLP_FC4_FCP) {
+		/* Payload is 4 + 16 = 20 x14 bytes. */
+		cmdsize = (sizeof(uint32_t) + sizeof(PRLI));
+		elscmd = ELS_CMD_PRLI;
+	} else if (local_nlp_type & NLP_FC4_NVME) {
+		/* Payload is 4 + 20 = 24 x18 bytes. */
+		cmdsize = (sizeof(uint32_t) + sizeof(struct lpfc_nvme_prli));
+		elscmd = ELS_CMD_NVMEPRLI;
+	} else {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+				 "3083 Unknown FC_TYPE x%x ndlp x%06x\n",
+				 ndlp->nlp_fc4_type, ndlp->nlp_DID);
+		return 1;
+	}
 	elsiocb = lpfc_prep_els_iocb(vport, 1, cmdsize, retry, ndlp,
-				     ndlp->nlp_DID, ELS_CMD_PRLI);
+				     ndlp->nlp_DID, elscmd);
 	if (!elsiocb)
 		return 1;
 
 	pcmd = (uint8_t *) (((struct lpfc_dmabuf *) elsiocb->context2)->virt);
 
 	/* For PRLI request, remainder of payload is service parameters */
-	memset(pcmd, 0, (sizeof(PRLI) + sizeof(uint32_t)));
-	*((uint32_t *) (pcmd)) = ELS_CMD_PRLI;
-	pcmd += sizeof(uint32_t);
+	memset(pcmd, 0, cmdsize);
 
-	/* For PRLI, remainder of payload is PRLI parameter page */
-	npr = (PRLI *) pcmd;
-	/*
-	 * If our firmware version is 3.20 or later,
-	 * set the following bits for FC-TAPE support.
-	 */
-	if (phba->vpd.rev.feaLevelHigh >= 0x02) {
-		npr->ConfmComplAllowed = 1;
-		npr->Retry = 1;
-		npr->TaskRetryIdReq = 1;
-	}
-	npr->estabImagePair = 1;
-	npr->readXferRdyDis = 1;
-	 if (vport->cfg_first_burst_size)
-		npr->writeXferRdyDis = 1;
+	if (local_nlp_type & NLP_FC4_FCP) {
+		/* Remainder of payload is FCP PRLI parameter page.
+		 * Note: this data structure is defined as
+		 * BE/LE in the structure definition so no
+		 * byte swap call is made.
+		 */
+		*((uint32_t *)(pcmd)) = ELS_CMD_PRLI;
+		pcmd += sizeof(uint32_t);
+		npr = (PRLI *)pcmd;
 
-	/* For FCP support */
-	npr->prliType = PRLI_FCP_TYPE;
-	npr->initiatorFunc = 1;
+		/*
+		 * If our firmware version is 3.20 or later,
+		 * set the following bits for FC-TAPE support.
+		 */
+		if (phba->vpd.rev.feaLevelHigh >= 0x02) {
+			npr->ConfmComplAllowed = 1;
+			npr->Retry = 1;
+			npr->TaskRetryIdReq = 1;
+		}
+		npr->estabImagePair = 1;
+		npr->readXferRdyDis = 1;
+		if (vport->cfg_first_burst_size)
+			npr->writeXferRdyDis = 1;
+
+		/* For FCP support */
+		npr->prliType = PRLI_FCP_TYPE;
+		npr->initiatorFunc = 1;
+		elsiocb->iocb_flag |= LPFC_PRLI_FCP_REQ;
+
+		/* Remove FCP type - processed. */
+		local_nlp_type &= ~NLP_FC4_FCP;
+	} else if (local_nlp_type & NLP_FC4_NVME) {
+		/* Remainder of payload is NVME PRLI parameter page.
+		 * This data structure is the newer definition that
+		 * uses bf macros so a byte swap is required.
+		 */
+		*((uint32_t *)(pcmd)) = ELS_CMD_NVMEPRLI;
+		pcmd += sizeof(uint32_t);
+		npr_nvme = (struct lpfc_nvme_prli *)pcmd;
+		bf_set(prli_type_code, npr_nvme, PRLI_NVME_TYPE);
+		bf_set(prli_estabImagePair, npr_nvme, 0);  /* Should be 0 */
+
+		/* Only initiators request first burst. */
+		if ((phba->cfg_nvme_enable_fb) &&
+		    !phba->nvmet_support)
+			bf_set(prli_fba, npr_nvme, 1);
+
+		bf_set(prli_init, npr_nvme, 1);
+		npr_nvme->word1 = cpu_to_be32(npr_nvme->word1);
+		npr_nvme->word4 = cpu_to_be32(npr_nvme->word4);
+		elsiocb->iocb_flag |= LPFC_PRLI_NVME_REQ;
+
+		/* Remove NVME type - processed. */
+		local_nlp_type &= ~NLP_FC4_NVME;
+	}
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Issue PRLI:      did:x%x",
@@ -2172,7 +2233,20 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		lpfc_els_free_iocb(phba, elsiocb);
 		return 1;
 	}
+
+	/* The vport counters are used for lpfc_scan_finished, but
+	 * the ndlp is used to track outstanding PRLIs for different
+	 * FC4 types.
+	 */
 	vport->fc_prli_sent++;
+	ndlp->fc4_prli_sent++;
+
+	/* The driver supports 2 FC4 types.  Make sure
+	 * a PRLI is issued for all types before exiting.
+	 */
+	if (local_nlp_type & (NLP_FC4_FCP | NLP_FC4_NVME))
+		goto send_next_prli;
+
 	return 0;
 }
 
@@ -2543,6 +2617,9 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	if ((vport->fc_flag & FC_PT2PT) &&
 		!(vport->fc_flag & FC_PT2PT_PLOGI)) {
 		phba->pport->fc_myDID = 0;
+
+		/* todo: init: revise localport nvme attributes */
+
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (mbox) {
 			lpfc_config_link(phba, mbox);
@@ -3055,6 +3132,7 @@ lpfc_els_retry_delay_handler(struct lpfc_nodelist *ndlp)
 		}
 		break;
 	case ELS_CMD_PRLI:
+	case ELS_CMD_NVMEPRLI:
 		if (!lpfc_issue_els_prli(vport, ndlp, retry)) {
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
@@ -3245,7 +3323,8 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				break;
 			}
 			if ((cmd == ELS_CMD_PLOGI) ||
-			    (cmd == ELS_CMD_PRLI)) {
+			    (cmd == ELS_CMD_PRLI) ||
+			    (cmd == ELS_CMD_NVMEPRLI)) {
 				delay = 1000;
 				maxretry = lpfc_max_els_tries + 1;
 				retry = 1;
@@ -3265,7 +3344,8 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 		case LSRJT_LOGICAL_BSY:
 			if ((cmd == ELS_CMD_PLOGI) ||
-			    (cmd == ELS_CMD_PRLI)) {
+			    (cmd == ELS_CMD_PRLI) ||
+			    (cmd == ELS_CMD_NVMEPRLI)) {
 				delay = 1000;
 				maxretry = 48;
 			} else if (cmd == ELS_CMD_FDISC) {
@@ -3399,7 +3479,8 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			spin_unlock_irq(shost->host_lock);
 
 			ndlp->nlp_prev_state = ndlp->nlp_state;
-			if (cmd == ELS_CMD_PRLI)
+			if ((cmd == ELS_CMD_PRLI) ||
+			    (cmd == ELS_CMD_NVMEPRLI))
 				lpfc_nlp_set_state(vport, ndlp,
 					NLP_STE_PRLI_ISSUE);
 			else
@@ -3430,6 +3511,7 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			lpfc_issue_els_adisc(vport, ndlp, cmdiocb->retry);
 			return 1;
 		case ELS_CMD_PRLI:
+		case ELS_CMD_NVMEPRLI:
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
 			lpfc_issue_els_prli(vport, ndlp, cmdiocb->retry);
@@ -3990,14 +4072,10 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 			       sizeof(struct lpfc_name));
 			memcpy(&sp->nodeName, &vport->fc_sparam.nodeName,
 			       sizeof(struct lpfc_name));
-		} else {
+		} else
 			memcpy(pcmd, &vport->fc_sparam,
 			       sizeof(struct serv_parm));
 
-			sp->cmn.valid_vendor_ver_level = 0;
-			memset(sp->vendorVersion, 0, sizeof(sp->vendorVersion));
-		}
-
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
 			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
@@ -4231,17 +4309,43 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 {
 	struct lpfc_hba  *phba = vport->phba;
 	PRLI *npr;
+	struct lpfc_nvme_prli *npr_nvme;
 	lpfc_vpd_t *vpd;
 	IOCB_t *icmd;
 	IOCB_t *oldcmd;
 	struct lpfc_iocbq *elsiocb;
 	uint8_t *pcmd;
 	uint16_t cmdsize;
+	uint32_t prli_fc4_req, *req_payload;
+	struct lpfc_dmabuf *req_buf;
 	int rc;
+	u32 elsrspcmd;
+
+	/* Need the incoming PRLI payload to determine if the ACC is for an
+	 * FC4 or NVME PRLI type.  The PRLI type is at word 1.
+	 */
+	req_buf = (struct lpfc_dmabuf *)oldiocb->context2;
+	req_payload = (((uint32_t *)req_buf->virt) + 1);
+
+	/* PRLI type payload is at byte 3 for FCP or NVME. */
+	prli_fc4_req = be32_to_cpu(*req_payload);
+	prli_fc4_req = (prli_fc4_req >> 24) & 0xff;
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
+			 "6127 PRLI_ACC:  Req Type x%x, Word1 x%08x\n",
+			 prli_fc4_req, *((uint32_t *)req_payload));
+
+	if (prli_fc4_req == PRLI_FCP_TYPE) {
+		cmdsize = sizeof(uint32_t) + sizeof(PRLI);
+		elsrspcmd = (ELS_CMD_ACC | (ELS_CMD_PRLI & ~ELS_RSP_MASK));
+	} else if (prli_fc4_req & PRLI_NVME_TYPE) {
+		cmdsize = sizeof(uint32_t) + sizeof(struct lpfc_nvme_prli);
+		elsrspcmd = (ELS_CMD_ACC | (ELS_CMD_NVMEPRLI & ~ELS_RSP_MASK));
+	} else {
+		return 1;
+	}
 
-	cmdsize = sizeof(uint32_t) + sizeof(PRLI);
 	elsiocb = lpfc_prep_els_iocb(vport, 0, cmdsize, oldiocb->retry, ndlp,
-		ndlp->nlp_DID, (ELS_CMD_ACC | (ELS_CMD_PRLI & ~ELS_RSP_MASK)));
+		ndlp->nlp_DID, elsrspcmd);
 	if (!elsiocb)
 		return 1;
 
@@ -4258,33 +4362,56 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
 	pcmd = (uint8_t *) (((struct lpfc_dmabuf *) elsiocb->context2)->virt);
+	memset(pcmd, 0, cmdsize);
 
 	*((uint32_t *) (pcmd)) = (ELS_CMD_ACC | (ELS_CMD_PRLI & ~ELS_RSP_MASK));
 	pcmd += sizeof(uint32_t);
 
 	/* For PRLI, remainder of payload is PRLI parameter page */
-	memset(pcmd, 0, sizeof(PRLI));
-
-	npr = (PRLI *) pcmd;
 	vpd = &phba->vpd;
-	/*
-	 * If the remote port is a target and our firmware version is 3.20 or
-	 * later, set the following bits for FC-TAPE support.
-	 */
-	if ((ndlp->nlp_type & NLP_FCP_TARGET) &&
-	    (vpd->rev.feaLevelHigh >= 0x02)) {
-		npr->ConfmComplAllowed = 1;
-		npr->Retry = 1;
-		npr->TaskRetryIdReq = 1;
-	}
-
-	npr->acceptRspCode = PRLI_REQ_EXECUTED;
-	npr->estabImagePair = 1;
-	npr->readXferRdyDis = 1;
-	npr->ConfmComplAllowed = 1;
 
-	npr->prliType = PRLI_FCP_TYPE;
-	npr->initiatorFunc = 1;
+	if (prli_fc4_req == PRLI_FCP_TYPE) {
+		/*
+		 * If the remote port is a target and our firmware version
+		 * is 3.20 or later, set the following bits for FC-TAPE
+		 * support.
+		 */
+		npr = (PRLI *) pcmd;
+		if ((ndlp->nlp_type & NLP_FCP_TARGET) &&
+		    (vpd->rev.feaLevelHigh >= 0x02)) {
+			npr->ConfmComplAllowed = 1;
+			npr->Retry = 1;
+			npr->TaskRetryIdReq = 1;
+		}
+		npr->acceptRspCode = PRLI_REQ_EXECUTED;
+		npr->estabImagePair = 1;
+		npr->readXferRdyDis = 1;
+		npr->ConfmComplAllowed = 1;
+		npr->prliType = PRLI_FCP_TYPE;
+		npr->initiatorFunc = 1;
+	} else if (prli_fc4_req & PRLI_NVME_TYPE) {
+		/* Respond with an NVME PRLI Type */
+		npr_nvme = (struct lpfc_nvme_prli *) pcmd;
+		bf_set(prli_type_code, npr_nvme, PRLI_NVME_TYPE);
+		bf_set(prli_estabImagePair, npr_nvme, 0);  /* Should be 0 */
+		bf_set(prli_acc_rsp_code, npr_nvme, PRLI_REQ_EXECUTED);
+		bf_set(prli_init, npr_nvme, 1);
+
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+				 "6015 NVME issue PRLI ACC word1 x%08x "
+				 "word4 x%08x word5 x%08x flag x%x, "
+				 "fcp_info x%x nlp_type x%x\n",
+				 npr_nvme->word1, npr_nvme->word4,
+				 npr_nvme->word5, ndlp->nlp_flag,
+				 ndlp->nlp_fcp_info, ndlp->nlp_type);
+		npr_nvme->word1 = cpu_to_be32(npr_nvme->word1);
+		npr_nvme->word4 = cpu_to_be32(npr_nvme->word4);
+		npr_nvme->word5 = cpu_to_be32(npr_nvme->word5);
+	} else
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+				 "6128 Unknown FC_TYPE x%x x%x ndlp x%06x\n",
+				 prli_fc4_req, ndlp->nlp_fc4_type,
+				 ndlp->nlp_DID);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
 		"Issue ACC PRLI:  did:x%x flg:x%x",
@@ -4411,7 +4538,7 @@ lpfc_els_rsp_rnid_acc(struct lpfc_vport *vport, uint8_t format,
  **/
 static void
 lpfc_els_clear_rrq(struct lpfc_vport *vport,
-      struct lpfc_iocbq *iocb, struct lpfc_nodelist *ndlp)
+		   struct lpfc_iocbq *iocb, struct lpfc_nodelist *ndlp)
 {
 	struct lpfc_hba  *phba = vport->phba;
 	uint8_t *pcmd;
@@ -4909,7 +5036,7 @@ lpfc_rdp_res_opd_desc(struct fc_rdp_opd_sfp_desc *desc,
 	memcpy(desc->opd_info.vendor_name, &page_a0[SSF_VENDOR_NAME], 16);
 	memcpy(desc->opd_info.model_number, &page_a0[SSF_VENDOR_PN], 16);
 	memcpy(desc->opd_info.serial_number, &page_a0[SSF_VENDOR_SN], 16);
-	memcpy(desc->opd_info.revision, &page_a0[SSF_VENDOR_REV], 2);
+	memcpy(desc->opd_info.revision, &page_a0[SSF_VENDOR_REV], 4);
 	memcpy(desc->opd_info.date, &page_a0[SSF_DATE_CODE], 8);
 	desc->length = cpu_to_be32(sizeof(desc->opd_info));
 	return sizeof(struct fc_rdp_opd_sfp_desc);
@@ -5004,7 +5131,7 @@ lpfc_rdp_res_diag_port_names(struct fc_rdp_port_name_desc *desc,
 	memcpy(desc->port_names.wwnn, phba->wwnn,
 			sizeof(desc->port_names.wwnn));
 
-	memcpy(desc->port_names.wwpn, &phba->wwpn,
+	memcpy(desc->port_names.wwpn, phba->wwpn,
 			sizeof(desc->port_names.wwpn));
 
 	desc->length = cpu_to_be32(sizeof(desc->port_names));
@@ -5233,9 +5360,8 @@ lpfc_els_rcv_rdp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	struct ls_rjt stat;
 
 	if (phba->sli_rev < LPFC_SLI_REV4 ||
-			(bf_get(lpfc_sli_intf_if_type,
-				&phba->sli4_hba.sli_intf) !=
-						LPFC_SLI_INTF_IF_TYPE_2)) {
+	    bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+						LPFC_SLI_INTF_IF_TYPE_2) {
 		rjt_err = LSRJT_UNABLE_TPC;
 		rjt_expl = LSEXP_REQ_UNSUPPORTED;
 		goto error;
@@ -5976,9 +6102,11 @@ lpfc_els_handle_rscn(struct lpfc_vport *vport)
 	if (ndlp && NLP_CHK_NODE_ACT(ndlp)
 	    && ndlp->nlp_state == NLP_STE_UNMAPPED_NODE) {
 		/* Good ndlp, issue CT Request to NameServer */
-		if (lpfc_ns_cmd(vport, SLI_CTNS_GID_FT, 0, 0) == 0)
+		vport->gidft_inp = 0;
+		if (lpfc_issue_gidft(vport) == 0)
 			/* Wait for NameServer query cmpl before we can
-			   continue */
+			 * continue
+			 */
 			return 1;
 	} else {
 		/* If login to NameServer does not exist, issue one */
@@ -6082,7 +6210,6 @@ lpfc_els_rcv_flogi(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 
 	(void) lpfc_check_sparm(vport, ndlp, sp, CLASS3, 1);
 
-
 	/*
 	 * If our portname is greater than the remote portname,
 	 * then we initiate Nport login.
@@ -7779,6 +7906,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		lpfc_els_rcv_fan(vport, elsiocb, ndlp);
 		break;
 	case ELS_CMD_PRLI:
+	case ELS_CMD_NVMEPRLI:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
 			"RCV PRLI:        did:x%x/ste:x%x flg:x%x",
 			did, vport->port_state, ndlp->nlp_flag);
@@ -8883,8 +9011,7 @@ lpfc_cmpl_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			break;
 	}
 
-	if (atomic_read(&phba->fabric_iocb_count) == 0)
-		BUG();
+	BUG_ON(atomic_read(&phba->fabric_iocb_count) == 0);
 
 	cmdiocb->iocb_cmpl = cmdiocb->fabric_iocb_cmpl;
 	cmdiocb->fabric_iocb_cmpl = NULL;
@@ -8929,8 +9056,7 @@ lpfc_issue_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *iocb)
 	int ready;
 	int ret;
 
-	if (atomic_read(&phba->fabric_iocb_count) > 1)
-		BUG();
+	BUG_ON(atomic_read(&phba->fabric_iocb_count) > 1);
 
 	spin_lock_irqsave(&phba->hbalock, iflags);
 	ready = atomic_read(&phba->fabric_iocb_count) == 0 &&
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index ede831d1f467..6e64c8e8e44f 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -31,6 +31,9 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/fc/fc_fs.h>
+
+#include <linux/nvme-fc-driver.h>
 
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
@@ -38,8 +41,9 @@
 #include "lpfc_disc.h"
 #include "lpfc_sli.h"
 #include "lpfc_sli4.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
@@ -853,9 +857,12 @@ lpfc_port_link_failure(struct lpfc_vport *vport)
 void
 lpfc_linkdown_port(struct lpfc_vport *vport)
 {
+	struct lpfc_hba  *phba = vport->phba;
 	struct Scsi_Host  *shost = lpfc_shost_from_vport(vport);
 
-	fc_host_post_event(shost, fc_get_event_number(), FCH_EVT_LINKDOWN, 0);
+	if (phba->cfg_enable_fc4_type != LPFC_ENABLE_NVME)
+		fc_host_post_event(shost, fc_get_event_number(),
+				   FCH_EVT_LINKDOWN, 0);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Link Down:       state:x%x rtry:x%x flg:x%x",
@@ -981,7 +988,9 @@ lpfc_linkup_port(struct lpfc_vport *vport)
 		(vport != phba->pport))
 		return;
 
-	fc_host_post_event(shost, fc_get_event_number(), FCH_EVT_LINKUP, 0);
+	if (phba->cfg_enable_fc4_type != LPFC_ENABLE_NVME)
+		fc_host_post_event(shost, fc_get_event_number(),
+				   FCH_EVT_LINKUP, 0);
 
 	spin_lock_irq(shost->host_lock);
 	vport->fc_flag &= ~(FC_PT2PT | FC_PT2PT_PLOGI | FC_ABORT_DISCOVERY |
@@ -3570,6 +3579,8 @@ lpfc_mbx_cmpl_reg_vpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
 		spin_unlock_irq(shost->host_lock);
 		vport->fc_myDID = 0;
+
+		/* todo: init: revise localport nvme attributes */
 		goto out;
 	}
 
@@ -3819,6 +3830,52 @@ lpfc_mbx_cmpl_fabric_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	return;
 }
 
+ /*
+  * This routine will issue a GID_FT for each FC4 Type supported
+  * by the driver. ALL GID_FTs must complete before discovery is started.
+  */
+int
+lpfc_issue_gidft(struct lpfc_vport *vport)
+{
+	struct lpfc_hba *phba = vport->phba;
+
+	/* Good status, issue CT Request to NameServer */
+	if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+	    (phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP)) {
+		if (lpfc_ns_cmd(vport, SLI_CTNS_GID_FT, 0, SLI_CTPT_FCP)) {
+			/* Cannot issue NameServer FCP Query, so finish up
+			 * discovery
+			 */
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_SLI,
+					 "0604 %s FC TYPE %x %s\n",
+					 "Failed to issue GID_FT to ",
+					 FC_TYPE_FCP,
+					 "Finishing discovery.");
+			return 0;
+		}
+		vport->gidft_inp++;
+	}
+
+	if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+	    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
+		if (lpfc_ns_cmd(vport, SLI_CTNS_GID_FT, 0, SLI_CTPT_NVME)) {
+			/* Cannot issue NameServer NVME Query, so finish up
+			 * discovery
+			 */
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_SLI,
+					 "0605 %s FC_TYPE %x %s %d\n",
+					 "Failed to issue GID_FT to ",
+					 FC_TYPE_NVME,
+					 "Finishing discovery: gidftinp ",
+					 vport->gidft_inp);
+			if (vport->gidft_inp == 0)
+				return 0;
+		} else
+			vport->gidft_inp++;
+	}
+	return vport->gidft_inp;
+}
+
 /*
  * This routine handles processing a NameServer REG_LOGIN mailbox
  * command upon completion. It is setup in the LPFC_MBOXQ
@@ -3835,12 +3892,14 @@ lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	pmb->context1 = NULL;
 	pmb->context2 = NULL;
+	vport->gidft_inp = 0;
 
 	if (mb->mbxStatus) {
-out:
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
 				 "0260 Register NameServer error: 0x%x\n",
 				 mb->mbxStatus);
+
+out:
 		/* decrement the node reference count held for this
 		 * callback function.
 		 */
@@ -3884,20 +3943,28 @@ lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		lpfc_ns_cmd(vport, SLI_CTNS_RSNN_NN, 0, 0);
 		lpfc_ns_cmd(vport, SLI_CTNS_RSPN_ID, 0, 0);
 		lpfc_ns_cmd(vport, SLI_CTNS_RFT_ID, 0, 0);
-		lpfc_ns_cmd(vport, SLI_CTNS_RFF_ID, 0, 0);
+
+		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP))
+			lpfc_ns_cmd(vport, SLI_CTNS_RFF_ID, 0, FC_TYPE_FCP);
+
+		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
+			lpfc_ns_cmd(vport, SLI_CTNS_RFF_ID, 0, FC_TYPE_NVME);
 
 		/* Issue SCR just before NameServer GID_FT Query */
 		lpfc_issue_els_scr(vport, SCR_DID, 0);
 	}
 
 	vport->fc_ns_retry = 0;
-	/* Good status, issue CT Request to NameServer */
-	if (lpfc_ns_cmd(vport, SLI_CTNS_GID_FT, 0, 0)) {
-		/* Cannot issue NameServer Query, so finish up discovery */
+	if (lpfc_issue_gidft(vport) == 0)
 		goto out;
-	}
 
-	/* decrement the node reference count held for this
+	/*
+	 * At this point in time we may need to wait for multiple
+	 * SLI_CTNS_GID_FT CT commands to complete before we start discovery.
+	 *
+	 * decrement the node reference count held for this
 	 * callback function.
 	 */
 	lpfc_nlp_put(ndlp);
@@ -3990,6 +4057,10 @@ lpfc_unregister_remote_port(struct lpfc_nodelist *ndlp)
 {
 	struct fc_rport *rport = ndlp->rport;
 	struct lpfc_vport *vport = ndlp->vport;
+	struct lpfc_hba  *phba = vport->phba;
+
+	if (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)
+		return;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
 		"rport delete:    did:x%x flg:x%x type x%x",
@@ -4047,6 +4118,7 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		       int old_state, int new_state)
 {
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+	struct lpfc_hba *phba = vport->phba;
 
 	if (new_state == NLP_STE_UNMAPPED_NODE) {
 		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
@@ -4057,23 +4129,51 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	if (new_state == NLP_STE_NPR_NODE)
 		ndlp->nlp_flag &= ~NLP_RCV_PLOGI;
 
-	/* Transport interface */
-	if (ndlp->rport && (old_state == NLP_STE_MAPPED_NODE ||
-			    old_state == NLP_STE_UNMAPPED_NODE)) {
-		vport->phba->nport_event_cnt++;
-		lpfc_unregister_remote_port(ndlp);
+	/* FCP and NVME Transport interface */
+	if ((old_state == NLP_STE_MAPPED_NODE ||
+	     old_state == NLP_STE_UNMAPPED_NODE)) {
+		if (ndlp->rport) {
+			vport->phba->nport_event_cnt++;
+			lpfc_unregister_remote_port(ndlp);
+		}
+
+		/* Notify the NVME transport of this rport's loss */
+		if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) &&
+		    (vport->phba->nvmet_support == 0) &&
+		    ((ndlp->nlp_fc4_type & NLP_FC4_NVME) ||
+		    (ndlp->nlp_DID == Fabric_DID))) {
+			vport->phba->nport_event_cnt++;
+			/* todo: init: unregister rport from nvme */
+		}
 	}
 
+	/* FCP and NVME Transport interfaces */
+
 	if (new_state ==  NLP_STE_MAPPED_NODE ||
 	    new_state == NLP_STE_UNMAPPED_NODE) {
-		vport->phba->nport_event_cnt++;
-		/*
-		 * Tell the fc transport about the port, if we haven't
-		 * already. If we have, and it's a scsi entity, be
-		 * sure to unblock any attached scsi devices
-		 */
-		lpfc_register_remote_port(vport, ndlp);
+		if ((ndlp->nlp_fc4_type & NLP_FC4_FCP) ||
+		    (ndlp->nlp_DID == Fabric_DID)) {
+			vport->phba->nport_event_cnt++;
+			/*
+			 * Tell the fc transport about the port, if we haven't
+			 * already. If we have, and it's a scsi entity, be
+			 */
+			lpfc_register_remote_port(vport, ndlp);
+		}
+		/* Notify the NVME transport of this new rport. */
+		if (ndlp->nlp_fc4_type & NLP_FC4_NVME) {
+			if (vport->phba->nvmet_support == 0) {
+				/* Register this rport with the transport.
+				 * Initiators take the NDLP ref count in
+				 * the register.
+				 */
+				vport->phba->nport_event_cnt++;
+				/* todo: init: register rport with nvme */
+			}
+		}
 	}
+
 	if ((new_state ==  NLP_STE_MAPPED_NODE) &&
 		(vport->stat_data_enabled)) {
 		/*
@@ -4091,12 +4191,13 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				"0x%x\n", ndlp->nlp_DID);
 	}
 	/*
-	 * if we added to Mapped list, but the remote port
-	 * registration failed or assigned a target id outside
-	 * our presentable range - move the node to the
-	 * Unmapped List
+	 * If the node just added to Mapped list was an FCP target,
+	 * but the remote port registration failed or assigned a target
+	 * id outside the presentable range - move the node to the
+	 * Unmapped List.
 	 */
-	if (new_state == NLP_STE_MAPPED_NODE &&
+	if ((new_state == NLP_STE_MAPPED_NODE) &&
+	    (ndlp->nlp_type & NLP_FCP_TARGET) &&
 	    (!ndlp->rport ||
 	     ndlp->rport->scsi_target_id == -1 ||
 	     ndlp->rport->scsi_target_id >= LPFC_MAX_TARGET)) {
@@ -4230,6 +4331,7 @@ lpfc_initialize_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->vport = vport;
 	ndlp->phba = vport->phba;
 	ndlp->nlp_sid = NLP_NO_SID;
+	ndlp->nlp_fc4_type = NLP_FC4_NONE;
 	kref_init(&ndlp->kref);
 	NLP_INT_NODE_ACT(ndlp);
 	atomic_set(&ndlp->cmd_pending, 0);
@@ -5369,12 +5471,13 @@ lpfc_disc_timeout_handler(struct lpfc_vport *vport)
 	switch (vport->port_state) {
 
 	case LPFC_LOCAL_CFG_LINK:
-	/* port_state is identically  LPFC_LOCAL_CFG_LINK while waiting for
-	 * FAN
-	 */
-				/* FAN timeout */
+		/*
+		 * port_state is identically  LPFC_LOCAL_CFG_LINK while
+		 * waiting for FAN timeout
+		 */
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_DISCOVERY,
 				 "0221 FAN timeout\n");
+
 		/* Start discovery by sending FLOGI, clean up old rpis */
 		list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes,
 					 nlp_listp) {
@@ -5445,8 +5548,8 @@ lpfc_disc_timeout_handler(struct lpfc_vport *vport)
 		if (vport->fc_ns_retry < LPFC_MAX_NS_RETRY) {
 			/* Try it one more time */
 			vport->fc_ns_retry++;
-			rc = lpfc_ns_cmd(vport, SLI_CTNS_GID_FT,
-					 vport->fc_ns_retry, 0);
+			vport->gidft_inp = 0;
+			rc = lpfc_issue_gidft(vport);
 			if (rc == 0)
 				break;
 		}
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 28247c99b4f2..883e6d2a7bc7 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -90,8 +90,10 @@ union CtCommandResponse {
 	uint32_t word;
 };
 
-#define FC4_FEATURE_INIT 0x2
-#define FC4_FEATURE_TARGET 0x1
+/* FC4 Feature bits for RFF_ID */
+#define FC4_FEATURE_TARGET	0x1
+#define FC4_FEATURE_INIT	0x2
+#define FC4_FEATURE_NVME_DISC	0x4
 
 struct lpfc_sli_ct_request {
 	/* Structure is in Big Endian format */
@@ -115,6 +117,16 @@ struct lpfc_sli_ct_request {
 			uint8_t AreaScope;
 			uint8_t Fc4Type;	/* for GID_FT requests */
 		} gid;
+		struct gid_ff {
+			uint8_t Flags;
+			uint8_t DomainScope;
+			uint8_t AreaScope;
+			uint8_t rsvd1;
+			uint8_t rsvd2;
+			uint8_t rsvd3;
+			uint8_t Fc4FBits;
+			uint8_t Fc4Type;
+		} gid_ff;
 		struct rft {
 			uint32_t PortId;	/* For RFT_ID requests */
 
@@ -159,6 +171,12 @@ struct lpfc_sli_ct_request {
 		struct gff_acc {
 			uint8_t fbits[128];
 		} gff_acc;
+		struct gft {
+			uint32_t PortId;
+		} gft;
+		struct gft_acc {
+			uint32_t fc4_types[8];
+		} gft_acc;
 #define FCP_TYPE_FEATURE_OFFSET 7
 		struct rff {
 			uint32_t PortId;
@@ -174,8 +192,12 @@ struct lpfc_sli_ct_request {
 #define  SLI_CT_REVISION        1
 #define  GID_REQUEST_SZ   (offsetof(struct lpfc_sli_ct_request, un) + \
 			   sizeof(struct gid))
+#define  GIDFF_REQUEST_SZ (offsetof(struct lpfc_sli_ct_request, un) + \
+			   sizeof(struct gid_ff))
 #define  GFF_REQUEST_SZ   (offsetof(struct lpfc_sli_ct_request, un) + \
 			   sizeof(struct gff))
+#define  GFT_REQUEST_SZ   (offsetof(struct lpfc_sli_ct_request, un) + \
+			   sizeof(struct gft))
 #define  RFT_REQUEST_SZ   (offsetof(struct lpfc_sli_ct_request, un) + \
 			   sizeof(struct rft))
 #define  RFF_REQUEST_SZ   (offsetof(struct lpfc_sli_ct_request, un) + \
@@ -271,6 +293,7 @@ struct lpfc_sli_ct_request {
 #define  SLI_CTNS_GNN_IP      0x0153
 #define  SLI_CTNS_GIPA_IP     0x0156
 #define  SLI_CTNS_GID_FT      0x0171
+#define  SLI_CTNS_GID_FF      0x01F1
 #define  SLI_CTNS_GID_PT      0x01A1
 #define  SLI_CTNS_RPN_ID      0x0212
 #define  SLI_CTNS_RNN_ID      0x0213
@@ -288,15 +311,16 @@ struct lpfc_sli_ct_request {
  * Port Types
  */
 
-#define  SLI_CTPT_N_PORT      0x01
-#define  SLI_CTPT_NL_PORT     0x02
-#define  SLI_CTPT_FNL_PORT    0x03
-#define  SLI_CTPT_IP          0x04
-#define  SLI_CTPT_FCP         0x08
-#define  SLI_CTPT_NX_PORT     0x7F
-#define  SLI_CTPT_F_PORT      0x81
-#define  SLI_CTPT_FL_PORT     0x82
-#define  SLI_CTPT_E_PORT      0x84
+#define SLI_CTPT_N_PORT		0x01
+#define SLI_CTPT_NL_PORT	0x02
+#define SLI_CTPT_FNL_PORT	0x03
+#define SLI_CTPT_IP		0x04
+#define SLI_CTPT_FCP		0x08
+#define SLI_CTPT_NVME		0x28
+#define SLI_CTPT_NX_PORT	0x7F
+#define SLI_CTPT_F_PORT		0x81
+#define SLI_CTPT_FL_PORT	0x82
+#define SLI_CTPT_E_PORT		0x84
 
 #define SLI_CT_LAST_ENTRY     0x80000000
 
@@ -337,6 +361,7 @@ struct lpfc_name {
 			uint8_t IEEE[6];	/* FC IEEE address */
 		} s;
 		uint8_t wwn[8];
+		uint64_t name;
 	} u;
 };
 
@@ -549,6 +574,7 @@ struct fc_vft_header {
 #define ELS_CMD_REC       0x13000000
 #define ELS_CMD_RDP       0x18000000
 #define ELS_CMD_PRLI      0x20100014
+#define ELS_CMD_NVMEPRLI  0x20140018
 #define ELS_CMD_PRLO      0x21100014
 #define ELS_CMD_PRLO_ACC  0x02100014
 #define ELS_CMD_PDISC     0x50000000
@@ -588,6 +614,7 @@ struct fc_vft_header {
 #define ELS_CMD_REC       0x13
 #define ELS_CMD_RDP	  0x18
 #define ELS_CMD_PRLI      0x14001020
+#define ELS_CMD_NVMEPRLI  0x18001420
 #define ELS_CMD_PRLO      0x14001021
 #define ELS_CMD_PRLO_ACC  0x14001002
 #define ELS_CMD_PDISC     0x50
@@ -684,6 +711,7 @@ typedef struct _PRLI {		/* Structure is in Big Endian format */
 	uint8_t prliType;	/* FC Parm Word 0, bit 24:31 */
 
 #define PRLI_FCP_TYPE 0x08
+#define PRLI_NVME_TYPE 0x28
 	uint8_t word0Reserved1;	/* FC Parm Word 0, bit 16:23 */
 
 #ifdef __BIG_ENDIAN_BITFIELD
@@ -1243,8 +1271,7 @@ struct fc_rdp_opd_sfp_info {
 	uint8_t            vendor_name[16];
 	uint8_t            model_number[16];
 	uint8_t            serial_number[16];
-	uint8_t            revision[2];
-	uint8_t            reserved[2];
+	uint8_t            revision[4];
 	uint8_t            date[8];
 };
 
@@ -1263,14 +1290,14 @@ struct fc_rdp_req_frame {
 
 
 struct fc_rdp_res_frame {
-	uint32_t	reply_sequence;		/* FC word0 LS_ACC or LS_RJT */
-	uint32_t	length;			/* FC Word 1      */
-	struct fc_rdp_link_service_desc link_service_desc;    /* Word 2 -4  */
-	struct fc_rdp_sfp_desc sfp_desc;                      /* Word 5 -9  */
-	struct fc_rdp_port_speed_desc portspeed_desc;         /* Word 10-12 */
-	struct fc_rdp_link_error_status_desc link_error_desc; /* Word 13-21 */
-	struct fc_rdp_port_name_desc diag_port_names_desc;    /* Word 22-27 */
-	struct fc_rdp_port_name_desc attached_port_names_desc;/* Word 28-33 */
+	uint32_t    reply_sequence;		/* FC word0 LS_ACC or LS_RJT */
+	uint32_t   length;			/* FC Word 1      */
+	struct fc_rdp_link_service_desc link_service_desc;    /* Word 2 -4   */
+	struct fc_rdp_sfp_desc sfp_desc;                      /* Word 5 -9   */
+	struct fc_rdp_port_speed_desc portspeed_desc;         /* Word 10 -12 */
+	struct fc_rdp_link_error_status_desc link_error_desc; /* Word 13 -21 */
+	struct fc_rdp_port_name_desc diag_port_names_desc;    /* Word 22 -27 */
+	struct fc_rdp_port_name_desc attached_port_names_desc;/* Word 28 -33 */
 	struct fc_fec_rdp_desc fec_desc;                      /* FC word 34-37*/
 	struct fc_rdp_bbc_desc bbc_desc;                      /* FC Word 38-42*/
 	struct fc_rdp_oed_sfp_desc oed_temp_desc;             /* FC Word 43-47*/
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index c3277c5312c9..fcc083cc00e0 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -3922,6 +3922,49 @@ struct gen_req64_wqe {
 	uint32_t max_response_payload_len;
 };
 
+/* Define NVME PRLI request to fabric. NVME is a
+ * fabric-only protocol.
+ * Updated to red-lined v1.08 on Sept 16, 2016
+ */
+struct lpfc_nvme_prli {
+	uint32_t word1;
+	/* The Response Code is defined in the FCP PRLI lpfc_hw.h */
+#define prli_acc_rsp_code_SHIFT         8
+#define prli_acc_rsp_code_MASK          0x0000000f
+#define prli_acc_rsp_code_WORD          word1
+#define prli_estabImagePair_SHIFT       13
+#define prli_estabImagePair_MASK        0x00000001
+#define prli_estabImagePair_WORD        word1
+#define prli_type_code_ext_SHIFT        16
+#define prli_type_code_ext_MASK         0x000000ff
+#define prli_type_code_ext_WORD         word1
+#define prli_type_code_SHIFT            24
+#define prli_type_code_MASK             0x000000ff
+#define prli_type_code_WORD             word1
+	uint32_t word_rsvd2;
+	uint32_t word_rsvd3;
+	uint32_t word4;
+#define prli_fba_SHIFT                  0
+#define prli_fba_MASK                   0x00000001
+#define prli_fba_WORD                   word4
+#define prli_disc_SHIFT                 3
+#define prli_disc_MASK                  0x00000001
+#define prli_disc_WORD                  word4
+#define prli_tgt_SHIFT                  4
+#define prli_tgt_MASK                   0x00000001
+#define prli_tgt_WORD                   word4
+#define prli_init_SHIFT                 5
+#define prli_init_MASK                  0x00000001
+#define prli_init_WORD                  word4
+#define prli_recov_SHIFT                8
+#define prli_recov_MASK                 0x00000001
+#define prli_recov_WORD                 word4
+	uint32_t word5;
+#define prli_fb_sz_SHIFT                0
+#define prli_fb_sz_MASK                 0x0000ffff
+#define prli_fb_sz_WORD                 word5
+};
+
 struct create_xri_wqe {
 	uint32_t rsrvd[5];           /* words 0-4 */
 	struct wqe_did	wqe_dest;  /* word 5 */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 57087ba4834f..e609afaa472a 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -2667,6 +2667,13 @@ lpfc_cleanup(struct lpfc_vport *vport)
 			lpfc_disc_state_machine(vport, ndlp, NULL,
 					NLP_EVT_DEVICE_RECOVERY);
 
+		if (ndlp->nlp_fc4_type & NLP_FC4_NVME) {
+			/* Remove the NVME transport reference now and
+			 * continue to remove the node.
+			 */
+			lpfc_nlp_put(ndlp);
+		}
+
 		lpfc_disc_state_machine(vport, ndlp, NULL,
 					     NLP_EVT_DEVICE_RM);
 	}
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 835ea9f78219..65e7b2433ee7 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -28,6 +28,9 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/fc/fc_fs.h>
+
+#include <linux/nvme-fc-driver.h>
 
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
@@ -35,8 +38,9 @@
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
@@ -708,6 +712,7 @@ static void
 lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	      struct lpfc_iocbq *cmdiocb)
 {
+	struct lpfc_hba  *phba = vport->phba;
 	struct lpfc_dmabuf *pcmd;
 	uint32_t *lp;
 	PRLI *npr;
@@ -721,11 +726,19 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_type &= ~(NLP_FCP_TARGET | NLP_FCP_INITIATOR);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 	ndlp->nlp_flag &= ~NLP_FIRSTBURST;
-	if (npr->prliType == PRLI_FCP_TYPE) {
-		if (npr->initiatorFunc)
-			ndlp->nlp_type |= NLP_FCP_INITIATOR;
+	if ((npr->prliType == PRLI_FCP_TYPE) ||
+	    (npr->prliType == PRLI_NVME_TYPE)) {
+		if (npr->initiatorFunc) {
+			if (npr->prliType == PRLI_FCP_TYPE)
+				ndlp->nlp_type |= NLP_FCP_INITIATOR;
+			if (npr->prliType == PRLI_NVME_TYPE)
+				ndlp->nlp_type |= NLP_NVME_INITIATOR;
+		}
 		if (npr->targetFunc) {
-			ndlp->nlp_type |= NLP_FCP_TARGET;
+			if (npr->prliType == PRLI_FCP_TYPE)
+				ndlp->nlp_type |= NLP_FCP_TARGET;
+			if (npr->prliType == PRLI_NVME_TYPE)
+				ndlp->nlp_type |= NLP_NVME_TARGET;
 			if (npr->writeXferRdyDis)
 				ndlp->nlp_flag |= NLP_FIRSTBURST;
 		}
@@ -744,7 +757,8 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			"rport rolechg:   role:x%x did:x%x flg:x%x",
 			roles, ndlp->nlp_DID, ndlp->nlp_flag);
 
-		fc_remote_port_rolechg(rport, roles);
+		if (phba->cfg_enable_fc4_type != LPFC_ENABLE_NVME)
+			fc_remote_port_rolechg(rport, roles);
 	}
 }
 
@@ -1491,7 +1505,9 @@ lpfc_rcv_prli_reglogin_issue(struct lpfc_vport *vport,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
+	/* Initiator mode. */
 	lpfc_els_rsp_prli_acc(vport, cmdiocb, ndlp);
+
 	return ndlp->nlp_state;
 }
 
@@ -1574,9 +1590,11 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 				  uint32_t evt)
 {
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+	struct lpfc_hba *phba = vport->phba;
 	LPFC_MBOXQ_t *pmb = (LPFC_MBOXQ_t *) arg;
 	MAILBOX_t *mb = &pmb->u.mb;
 	uint32_t did  = mb->un.varWords[1];
+	int rc = 0;
 
 	if (mb->mbxStatus) {
 		/* RegLogin failed */
@@ -1611,19 +1629,52 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 	}
 
 	/* SLI4 ports have preallocated logical rpis. */
-	if (vport->phba->sli_rev < LPFC_SLI_REV4)
+	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
 
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 
 	/* Only if we are not a fabric nport do we issue PRLI */
-	if (!(ndlp->nlp_type & NLP_FABRIC)) {
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+			 "3066 RegLogin Complete on x%x x%x x%x\n",
+			 did, ndlp->nlp_type, ndlp->nlp_fc4_type);
+	if (!(ndlp->nlp_type & NLP_FABRIC) &&
+	    (phba->nvmet_support == 0)) {
+		/* The driver supports FCP and NVME concurrently.  If the
+		 * ndlp's nlp_fc4_type is still zero, the driver doesn't
+		 * know what PRLI to send yet.  Figure that out now and
+		 * call PRLI depending on the outcome.
+		 */
+		if (vport->fc_flag & FC_PT2PT) {
+			/* If we are pt2pt, there is no Fabric to determine
+			 * the FC4 type of the remote nport. So if NVME
+			 * is configured try it.
+			 */
+			ndlp->nlp_fc4_type |= NLP_FC4_FCP;
+			if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+			     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
+				ndlp->nlp_fc4_type |= NLP_FC4_NVME;
+				/* We need to update the localport also */
+				/* todo: init: revise localport nvme
+				 * attributes
+				 */
+			}
+
+		} else if (ndlp->nlp_fc4_type == 0) {
+			rc = lpfc_ns_cmd(vport, SLI_CTNS_GFT_ID,
+					 0, ndlp->nlp_DID);
+			return ndlp->nlp_state;
+		}
+
 		ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
 		lpfc_issue_els_prli(vport, ndlp, 0);
 	} else {
-		ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
-		lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
+		/* Only Fabric ports should transition */
+		if (ndlp->nlp_type & NLP_FABRIC) {
+			ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
+			lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
+		}
 	}
 	return ndlp->nlp_state;
 }
@@ -1664,7 +1715,7 @@ lpfc_device_recov_reglogin_issue(struct lpfc_vport *vport,
 	ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
 	spin_lock_irq(shost->host_lock);
-	ndlp->nlp_flag |= NLP_IGNR_REG_CMPL;
+
 	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	spin_unlock_irq(shost->host_lock);
 	lpfc_disc_set_adisc(vport, ndlp);
@@ -1740,10 +1791,23 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	struct lpfc_hba   *phba = vport->phba;
 	IOCB_t *irsp;
 	PRLI *npr;
+	struct lpfc_nvme_prli *nvpr;
+	void *temp_ptr;
 
 	cmdiocb = (struct lpfc_iocbq *) arg;
 	rspiocb = cmdiocb->context_un.rsp_iocb;
-	npr = (PRLI *)lpfc_check_elscmpl_iocb(phba, cmdiocb, rspiocb);
+
+	/* A solicited PRLI is either FCP or NVME.  The PRLI cmd/rsp
+	 * format is different so NULL the two PRLI types so that the
+	 * driver correctly gets the correct context.
+	 */
+	npr = NULL;
+	nvpr = NULL;
+	temp_ptr = lpfc_check_elscmpl_iocb(phba, cmdiocb, rspiocb);
+	if (cmdiocb->iocb_flag & LPFC_PRLI_FCP_REQ)
+		npr = (PRLI *) temp_ptr;
+	else if (cmdiocb->iocb_flag & LPFC_PRLI_NVME_REQ)
+		nvpr = (struct lpfc_nvme_prli *) temp_ptr;
 
 	irsp = &rspiocb->iocb;
 	if (irsp->ulpStatus) {
@@ -1751,7 +1815,21 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		    vport->cfg_restrict_login) {
 			goto out;
 		}
+
+		/* The LS Req had some error.  Don't let this be a
+		 * target.
+		 */
+		if ((ndlp->fc4_prli_sent == 1) &&
+		    (ndlp->nlp_state == NLP_STE_PRLI_ISSUE) &&
+		    (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_FCP_INITIATOR)))
+			/* The FCP PRLI completed successfully but
+			 * the NVME PRLI failed.  Since they are sent in
+			 * succession, allow the FCP to complete.
+			 */
+			goto out_err;
+
 		ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
+		ndlp->nlp_type |= NLP_FCP_INITIATOR;
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 		return ndlp->nlp_state;
 	}
@@ -1759,9 +1837,16 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* Check out PRLI rsp */
 	ndlp->nlp_type &= ~(NLP_FCP_TARGET | NLP_FCP_INITIATOR);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
+
+	/* NVME or FCP first burst must be negotiated for each PRLI. */
 	ndlp->nlp_flag &= ~NLP_FIRSTBURST;
-	if ((npr->acceptRspCode == PRLI_REQ_EXECUTED) &&
+	ndlp->nvme_fb_size = 0;
+	if (npr && (npr->acceptRspCode == PRLI_REQ_EXECUTED) &&
 	    (npr->prliType == PRLI_FCP_TYPE)) {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+				 "6028 FCP NPR PRLI Cmpl Init %d Target %d\n",
+				 npr->initiatorFunc,
+				 npr->targetFunc);
 		if (npr->initiatorFunc)
 			ndlp->nlp_type |= NLP_FCP_INITIATOR;
 		if (npr->targetFunc) {
@@ -1771,6 +1856,49 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		}
 		if (npr->Retry)
 			ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE;
+
+		/* PRLI completed.  Decrement count. */
+		ndlp->fc4_prli_sent--;
+	} else if (nvpr &&
+		   (bf_get_be32(prli_acc_rsp_code, nvpr) ==
+		    PRLI_REQ_EXECUTED) &&
+		   (bf_get_be32(prli_type_code, nvpr) ==
+		    PRLI_NVME_TYPE)) {
+
+		/* Complete setting up the remote ndlp personality. */
+		if (bf_get_be32(prli_init, nvpr))
+			ndlp->nlp_type |= NLP_NVME_INITIATOR;
+
+		/* Target driver cannot solicit NVME FB. */
+		if (bf_get_be32(prli_tgt, nvpr)) {
+			ndlp->nlp_type |= NLP_NVME_TARGET;
+			if ((bf_get_be32(prli_fba, nvpr) == 1) &&
+			    (bf_get_be32(prli_fb_sz, nvpr) > 0) &&
+			    (phba->cfg_nvme_enable_fb) &&
+			    (!phba->nvmet_support)) {
+				/* Both sides support FB. The target's first
+				 * burst size is a 512 byte encoded value.
+				 */
+				ndlp->nlp_flag |= NLP_FIRSTBURST;
+				ndlp->nvme_fb_size = bf_get_be32(prli_fb_sz,
+								 nvpr);
+			}
+		}
+
+		if (bf_get_be32(prli_recov, nvpr))
+			ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE;
+
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+				 "6029 NVME PRLI Cmpl w1 x%08x "
+				 "w4 x%08x w5 x%08x flag x%x, "
+				 "fcp_info x%x nlp_type x%x\n",
+				 be32_to_cpu(nvpr->word1),
+				 be32_to_cpu(nvpr->word4),
+				 be32_to_cpu(nvpr->word5),
+				 ndlp->nlp_flag, ndlp->nlp_fcp_info,
+				 ndlp->nlp_type);
+		/* PRLI completed.  Decrement count. */
+		ndlp->fc4_prli_sent--;
 	}
 	if (!(ndlp->nlp_type & NLP_FCP_TARGET) &&
 	    (vport->port_type == LPFC_NPIV_PORT) &&
@@ -1786,11 +1914,24 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		return ndlp->nlp_state;
 	}
 
-	ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
-	if (ndlp->nlp_type & NLP_FCP_TARGET)
-		lpfc_nlp_set_state(vport, ndlp, NLP_STE_MAPPED_NODE);
-	else
-		lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
+out_err:
+	/* The ndlp state cannot move to MAPPED or UNMAPPED before all PRLIs
+	 * are complete.
+	 */
+	if (ndlp->fc4_prli_sent == 0) {
+		ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
+		if (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_NVME_TARGET))
+			lpfc_nlp_set_state(vport, ndlp, NLP_STE_MAPPED_NODE);
+		else
+			lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
+	} else
+		lpfc_printf_vlog(vport,
+				 KERN_INFO, LOG_ELS,
+				 "3067 PRLI's still outstanding "
+				 "on x%06x - count %d, Pend Node Mode "
+				 "transition...\n",
+				 ndlp->nlp_DID, ndlp->fc4_prli_sent);
+
 	return ndlp->nlp_state;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index c327fc7b1a54..6ba2b3412337 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5333,7 +5333,8 @@ lpfc_bus_reset_handler(struct scsi_cmnd *cmnd)
 				continue;
 			if (ndlp->nlp_state == NLP_STE_MAPPED_NODE &&
 			    ndlp->nlp_sid == i &&
-			    ndlp->rport) {
+			    ndlp->rport &&
+			    ndlp->nlp_type & NLP_FCP_TARGET) {
 				match = 1;
 				break;
 			}
-- 
GitLab


From 01649561a8b4b77247bd234f240d737367bb8a52 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:32 -0800
Subject: [PATCH 147/898] scsi: lpfc: NVME Initiator: bind to nvme_fc api

NVME Initiator: Tie in to NVME Fabrics nvme_fc LLDD initiator api

Adds the routines to:
- register and deregister the FC port as a nvme-fc initiator localport
- register and deregister remote FC ports as a nvme-fc remoteport
- binding of nvme queues to adapter WQs
- send/perform NVME LS's
- send/perform NVME FCP initiator io operations

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/Makefile         |    7 +-
 drivers/scsi/lpfc/lpfc.h           |    5 +
 drivers/scsi/lpfc/lpfc_crtn.h      |   10 +
 drivers/scsi/lpfc/lpfc_ct.c        |    2 +-
 drivers/scsi/lpfc/lpfc_els.c       |    4 +-
 drivers/scsi/lpfc/lpfc_hbadisc.c   |   15 +-
 drivers/scsi/lpfc/lpfc_init.c      |   39 +-
 drivers/scsi/lpfc/lpfc_nportdisc.c |    4 +-
 drivers/scsi/lpfc/lpfc_nvme.c      | 2319 ++++++++++++++++++++++++++++
 drivers/scsi/lpfc/lpfc_nvme.h      |    6 +
 drivers/scsi/lpfc/lpfc_sli.c       |   21 +-
 drivers/scsi/lpfc/lpfc_sli4.h      |    1 +
 drivers/scsi/lpfc/lpfc_vport.c     |   16 +-
 13 files changed, 2411 insertions(+), 38 deletions(-)
 create mode 100644 drivers/scsi/lpfc/lpfc_nvme.c

diff --git a/drivers/scsi/lpfc/Makefile b/drivers/scsi/lpfc/Makefile
index e2516ba8ebfa..cd7e1fcf52c6 100644
--- a/drivers/scsi/lpfc/Makefile
+++ b/drivers/scsi/lpfc/Makefile
@@ -28,6 +28,7 @@ endif
 
 obj-$(CONFIG_SCSI_LPFC) := lpfc.o
 
-lpfc-objs := lpfc_mem.o lpfc_sli.o lpfc_ct.o lpfc_els.o lpfc_hbadisc.o	\
-	lpfc_init.o lpfc_mbox.o lpfc_nportdisc.o lpfc_scsi.o lpfc_attr.o \
-	lpfc_vport.o lpfc_debugfs.o lpfc_bsg.o
+lpfc-objs := lpfc_mem.o lpfc_sli.o lpfc_ct.o lpfc_els.o \
+	lpfc_hbadisc.o	lpfc_init.o lpfc_mbox.o lpfc_nportdisc.o   \
+	lpfc_scsi.o lpfc_attr.o lpfc_vport.o lpfc_debugfs.o lpfc_bsg.o \
+	lpfc_nvme.o
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 81c47d1aebb2..9ad63a47425b 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -123,6 +123,11 @@ struct perf_prof {
 	uint16_t wqidx[40];
 };
 
+/*
+ * Provide for FC4 TYPE x28 - NVME.  The
+ * bit mask for FCP and NVME is 0x8 identically
+ * because they are 32 bit positions distance.
+ */
 #define LPFC_FC4_TYPE_BITMASK	0x00000100
 
 /* Provide DMA memory definitions the driver uses per port instance. */
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 2e6345ebd6c5..a9c8a0a41b16 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -518,4 +518,14 @@ int lpfc_sli4_dump_page_a0(struct lpfc_hba *phba, struct lpfcMboxq *mbox);
 void lpfc_mbx_cmpl_rdp_page_a0(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb);
 
 /* NVME interfaces. */
+void lpfc_nvme_unregister_port(struct lpfc_vport *vport,
+			struct lpfc_nodelist *ndlp);
+int lpfc_nvme_register_port(struct lpfc_vport *vport,
+			struct lpfc_nodelist *ndlp);
+int lpfc_nvme_create_localport(struct lpfc_vport *vport);
+void lpfc_nvme_destroy_localport(struct lpfc_vport *vport);
+void lpfc_nvme_update_localport(struct lpfc_vport *vport);
 void lpfc_nvme_mod_param_dep(struct lpfc_hba *phba);
+void lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba,
+				struct lpfc_iocbq *cmdiocb,
+				struct lpfc_wcqe_complete *abts_cmpl);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index afb25369bc3b..8cfeffe312e0 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1412,7 +1412,7 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 		if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
 		     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) &&
 		    (context == FC_TYPE_NVME)) {
-			/* todo: init: revise localport nvme attributes */
+			lpfc_nvme_update_localport(vport);
 			CtReq->un.rff.type_code = context;
 
 		} else if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index e164eed25e3d..23546b3c950c 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2618,7 +2618,9 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		!(vport->fc_flag & FC_PT2PT_PLOGI)) {
 		phba->pport->fc_myDID = 0;
 
-		/* todo: init: revise localport nvme attributes */
+		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
+			lpfc_nvme_update_localport(phba->pport);
 
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (mbox) {
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 6e64c8e8e44f..8936f5d91c87 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -909,7 +909,9 @@ lpfc_linkdown(struct lpfc_hba *phba)
 
 			vports[i]->fc_myDID = 0;
 
-			/* todo: init: revise localport nvme attributes */
+			if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+			    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
+				lpfc_nvme_update_localport(vports[i]);
 		}
 	}
 	lpfc_destroy_vport_work_array(phba, vports);
@@ -3580,7 +3582,9 @@ lpfc_mbx_cmpl_reg_vpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		spin_unlock_irq(shost->host_lock);
 		vport->fc_myDID = 0;
 
-		/* todo: init: revise localport nvme attributes */
+		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
+			lpfc_nvme_update_localport(vport);
 		goto out;
 	}
 
@@ -3950,7 +3954,8 @@ lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
 		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
-			lpfc_ns_cmd(vport, SLI_CTNS_RFF_ID, 0, FC_TYPE_NVME);
+			lpfc_ns_cmd(vport, SLI_CTNS_RFF_ID, 0,
+				    FC_TYPE_NVME);
 
 		/* Issue SCR just before NameServer GID_FT Query */
 		lpfc_issue_els_scr(vport, SCR_DID, 0);
@@ -4144,7 +4149,7 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		    ((ndlp->nlp_fc4_type & NLP_FC4_NVME) ||
 		    (ndlp->nlp_DID == Fabric_DID))) {
 			vport->phba->nport_event_cnt++;
-			/* todo: init: unregister rport from nvme */
+			lpfc_nvme_unregister_port(vport, ndlp);
 		}
 	}
 
@@ -4169,7 +4174,7 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				 * the register.
 				 */
 				vport->phba->nport_event_cnt++;
-				/* todo: init: register rport with nvme */
+				lpfc_nvme_register_port(vport, ndlp);
 			}
 		}
 	}
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index e609afaa472a..474bafc63055 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -3128,7 +3128,6 @@ static void
 lpfc_scsi_free(struct lpfc_hba *phba)
 {
 	struct lpfc_scsi_buf *sb, *sb_next;
-	struct lpfc_iocbq *io, *io_next;
 
 	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
 		return;
@@ -3158,14 +3157,6 @@ lpfc_scsi_free(struct lpfc_hba *phba)
 		phba->total_scsi_bufs--;
 	}
 	spin_unlock(&phba->scsi_buf_list_get_lock);
-
-	/* Release all the lpfc_iocbq entries maintained by this host. */
-	list_for_each_entry_safe(io, io_next, &phba->lpfc_iocb_list, list) {
-		list_del(&io->list);
-		kfree(io);
-		phba->total_iocbq_bufs--;
-	}
-
 	spin_unlock_irq(&phba->hbalock);
 }
 /**
@@ -3180,7 +3171,6 @@ static void
 lpfc_nvme_free(struct lpfc_hba *phba)
 {
 	struct lpfc_nvme_buf *lpfc_ncmd, *lpfc_ncmd_next;
-	struct lpfc_iocbq *io, *io_next;
 
 	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
 		return;
@@ -3209,14 +3199,6 @@ lpfc_nvme_free(struct lpfc_hba *phba)
 		phba->total_nvme_bufs--;
 	}
 	spin_unlock(&phba->nvme_buf_list_get_lock);
-
-	/* Release all the lpfc_iocbq entries maintained by this host. */
-	list_for_each_entry_safe(io, io_next, &phba->lpfc_iocb_list, list) {
-		list_del(&io->list);
-		kfree(io);
-		phba->total_iocbq_bufs--;
-	}
-
 	spin_unlock_irq(&phba->hbalock);
 }
 /**
@@ -10685,7 +10667,23 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	/* Perform post initialization setup */
 	lpfc_post_init_setup(phba);
 
-	/* todo: init: register port with nvme */
+	/* NVME support in FW earlier in the driver load corrects the
+	 * FC4 type making a check for nvme_support unnecessary.
+	 */
+	if ((phba->nvmet_support == 0) &&
+	    (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) {
+		/* Create NVME binding with nvme_fc_transport. This
+		 * ensures the vport is initialized.
+		 */
+		error = lpfc_nvme_create_localport(vport);
+		if (error) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6004 NVME registration failed, "
+					"error x%x\n",
+					error);
+			goto out_disable_intr;
+		}
+	}
 
 	/* check for firmware upgrade or downgrade */
 	if (phba->cfg_request_firmware_upgrade)
@@ -10761,8 +10759,8 @@ lpfc_pci_remove_one_s4(struct pci_dev *pdev)
 	/* Perform ndlp cleanup on the physical port.  The nvme localport
 	 * is destroyed after to ensure all rports are io-disabled.
 	 */
+	lpfc_nvme_destroy_localport(vport);
 	lpfc_cleanup(vport);
-	/* todo: init: unregister port with nvme */
 
 	/*
 	 * Bring down the SLI Layer. This step disables all interrupts,
@@ -10781,6 +10779,7 @@ lpfc_pci_remove_one_s4(struct pci_dev *pdev)
 	 */
 	lpfc_scsi_free(phba);
 	lpfc_nvme_free(phba);
+	lpfc_free_iocb_list(phba);
 
 	lpfc_sli4_driver_resource_unset(phba);
 
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 65e7b2433ee7..470f9586192f 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -1655,9 +1655,7 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 			     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
 				ndlp->nlp_fc4_type |= NLP_FC4_NVME;
 				/* We need to update the localport also */
-				/* todo: init: revise localport nvme
-				 * attributes
-				 */
+				lpfc_nvme_update_localport(vport);
 			}
 
 		} else if (ndlp->nlp_fc4_type == 0) {
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
new file mode 100644
index 000000000000..729803dacf15
--- /dev/null
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -0,0 +1,2319 @@
+/*******************************************************************
+ * This file is part of the Emulex Linux Device Driver for         *
+ * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
+ *                                                                 *
+ * This program is free software; you can redistribute it and/or   *
+ * modify it under the terms of version 2 of the GNU General       *
+ * Public License as published by the Free Software Foundation.    *
+ * This program is distributed in the hope that it will be useful. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ ********************************************************************/
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <asm/unaligned.h>
+#include <linux/crc-t10dif.h>
+#include <net/checksum.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_tcq.h>
+#include <scsi/scsi_transport_fc.h>
+#include <scsi/fc/fc_fs.h>
+
+#include <linux/nvme.h>
+#include <linux/nvme-fc-driver.h>
+#include <linux/nvme-fc.h>
+#include "lpfc_version.h"
+#include "lpfc_hw4.h"
+#include "lpfc_hw.h"
+#include "lpfc_sli.h"
+#include "lpfc_sli4.h"
+#include "lpfc_nl.h"
+#include "lpfc_disc.h"
+#include "lpfc.h"
+#include "lpfc_nvme.h"
+#include "lpfc_scsi.h"
+#include "lpfc_logmsg.h"
+#include "lpfc_crtn.h"
+#include "lpfc_vport.h"
+
+/* NVME initiator-based functions */
+
+static struct lpfc_nvme_buf *
+lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp);
+
+static void
+lpfc_release_nvme_buf(struct lpfc_hba *, struct lpfc_nvme_buf *);
+
+
+/**
+ * lpfc_nvme_create_queue -
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @qidx: An cpu index used to affinitize IO queues and MSIX vectors.
+ * @handle: An opaque driver handle used in follow-up calls.
+ *
+ * Driver registers this routine to preallocate and initialize any
+ * internal data structures to bind the @qidx to its internal IO queues.
+ * A hardware queue maps (qidx) to a specific driver MSI-X vector/EQ/CQ/WQ.
+ *
+ * Return value :
+ *   0 - Success
+ *   -EINVAL - Unsupported input value.
+ *   -ENOMEM - Could not alloc necessary memory
+ **/
+static int
+lpfc_nvme_create_queue(struct nvme_fc_local_port *pnvme_lport,
+		       unsigned int qidx, u16 qsize,
+		       void **handle)
+{
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_vport *vport;
+	struct lpfc_nvme_qhandle *qhandle;
+	char *str;
+
+	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
+	vport = lport->vport;
+	qhandle = kzalloc(sizeof(struct lpfc_nvme_qhandle), GFP_KERNEL);
+	if (qhandle == NULL)
+		return -ENOMEM;
+
+	qhandle->cpu_id = smp_processor_id();
+	qhandle->qidx = qidx;
+	/*
+	 * NVME qidx == 0 is the admin queue, so both admin queue
+	 * and first IO queue will use MSI-X vector and associated
+	 * EQ/CQ/WQ at index 0. After that they are sequentially assigned.
+	 */
+	if (qidx) {
+		str = "IO ";  /* IO queue */
+		qhandle->index = ((qidx - 1) %
+			vport->phba->cfg_nvme_io_channel);
+	} else {
+		str = "ADM";  /* Admin queue */
+		qhandle->index = qidx;
+	}
+
+	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+			 "6073 Binding %s HdwQueue %d  (cpu %d) to "
+			 "io_channel %d qhandle %p\n", str,
+			 qidx, qhandle->cpu_id, qhandle->index, qhandle);
+	*handle = (void *)qhandle;
+	return 0;
+}
+
+/**
+ * lpfc_nvme_delete_queue -
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @qidx: An cpu index used to affinitize IO queues and MSIX vectors.
+ * @handle: An opaque driver handle from lpfc_nvme_create_queue
+ *
+ * Driver registers this routine to free
+ * any internal data structures to bind the @qidx to its internal
+ * IO queues.
+ *
+ * Return value :
+ *   0 - Success
+ *   TODO:  What are the failure codes.
+ **/
+static void
+lpfc_nvme_delete_queue(struct nvme_fc_local_port *pnvme_lport,
+		       unsigned int qidx,
+		       void *handle)
+{
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_vport *vport;
+
+	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
+	vport = lport->vport;
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
+			"6001 ENTER.  lpfc_pnvme %p, qidx x%xi qhandle %p\n",
+			lport, qidx, handle);
+	kfree(handle);
+}
+
+static void
+lpfc_nvme_localport_delete(struct nvme_fc_local_port *localport)
+{
+	struct lpfc_nvme_lport *lport = localport->private;
+
+	/* release any threads waiting for the unreg to complete */
+	complete(&lport->lport_unreg_done);
+}
+
+/* lpfc_nvme_remoteport_delete
+ *
+ * @remoteport: Pointer to an nvme transport remoteport instance.
+ *
+ * This is a template downcall.  NVME transport calls this function
+ * when it has completed the unregistration of a previously
+ * registered remoteport.
+ *
+ * Return value :
+ * None
+ */
+void
+lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport)
+{
+	struct lpfc_nvme_rport *rport = remoteport->private;
+	struct lpfc_vport *vport;
+	struct lpfc_nodelist *ndlp;
+
+	ndlp = rport->ndlp;
+	if (!ndlp)
+		goto rport_err;
+
+	vport = ndlp->vport;
+	if (!vport)
+		goto rport_err;
+
+	/* Remove this rport from the lport's list - memory is owned by the
+	 * transport. Remove the ndlp reference for the NVME transport before
+	 * calling state machine to remove the node, this is devloss = 0
+	 * semantics.
+	 */
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+			"6146 remoteport delete complete %p\n",
+			remoteport);
+	list_del(&rport->list);
+	lpfc_nlp_put(ndlp);
+
+ rport_err:
+	/* This call has to execute as long as the rport is valid.
+	 * Release any threads waiting for the unreg to complete.
+	 */
+	complete(&rport->rport_unreg_done);
+}
+
+static void
+lpfc_nvme_cmpl_gen_req(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+		       struct lpfc_wcqe_complete *wcqe)
+{
+	struct lpfc_vport *vport = cmdwqe->vport;
+	uint32_t status;
+	struct nvmefc_ls_req *pnvme_lsreq;
+	struct lpfc_dmabuf *buf_ptr;
+	struct lpfc_nodelist *ndlp;
+
+	vport->phba->fc4NvmeLsCmpls++;
+
+	pnvme_lsreq = (struct nvmefc_ls_req *)cmdwqe->context2;
+	status = bf_get(lpfc_wcqe_c_status, wcqe) & LPFC_IOCB_STATUS_MASK;
+	ndlp = (struct lpfc_nodelist *)cmdwqe->context1;
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+			 "6047 nvme cmpl Enter "
+			 "Data %p DID %x Xri: %x status %x cmd:%p lsreg:%p "
+			 "bmp:%p ndlp:%p\n",
+			 pnvme_lsreq, ndlp ? ndlp->nlp_DID : 0,
+			 cmdwqe->sli4_xritag, status,
+			 cmdwqe, pnvme_lsreq, cmdwqe->context3, ndlp);
+
+	if (cmdwqe->context3) {
+		buf_ptr = (struct lpfc_dmabuf *)cmdwqe->context3;
+		lpfc_mbuf_free(phba, buf_ptr->virt, buf_ptr->phys);
+		kfree(buf_ptr);
+		cmdwqe->context3 = NULL;
+	}
+	if (pnvme_lsreq->done)
+		pnvme_lsreq->done(pnvme_lsreq, status);
+	else
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+				 "6046 nvme cmpl without done call back? "
+				 "Data %p DID %x Xri: %x status %x\n",
+				pnvme_lsreq, ndlp ? ndlp->nlp_DID : 0,
+				cmdwqe->sli4_xritag, status);
+	if (ndlp) {
+		lpfc_nlp_put(ndlp);
+		cmdwqe->context1 = NULL;
+	}
+	lpfc_sli_release_iocbq(phba, cmdwqe);
+}
+
+static int
+lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
+		  struct lpfc_dmabuf *inp,
+		 struct nvmefc_ls_req *pnvme_lsreq,
+	     void (*cmpl)(struct lpfc_hba *, struct lpfc_iocbq *,
+			   struct lpfc_wcqe_complete *),
+	     struct lpfc_nodelist *ndlp, uint32_t num_entry,
+	     uint32_t tmo, uint8_t retry)
+{
+	struct lpfc_hba  *phba = vport->phba;
+	union lpfc_wqe *wqe;
+	struct lpfc_iocbq *genwqe;
+	struct ulp_bde64 *bpl;
+	struct ulp_bde64 bde;
+	int i, rc, xmit_len, first_len;
+
+	/* Allocate buffer for  command WQE */
+	genwqe = lpfc_sli_get_iocbq(phba);
+	if (genwqe == NULL)
+		return 1;
+
+	wqe = &genwqe->wqe;
+	memset(wqe, 0, sizeof(union lpfc_wqe));
+
+	genwqe->context3 = (uint8_t *)bmp;
+	genwqe->iocb_flag |= LPFC_IO_NVME_LS;
+
+	/* Save for completion so we can release these resources */
+	genwqe->context1 = lpfc_nlp_get(ndlp);
+	genwqe->context2 = (uint8_t *)pnvme_lsreq;
+	/* Fill in payload, bp points to frame payload */
+
+	if (!tmo)
+		/* FC spec states we need 3 * ratov for CT requests */
+		tmo = (3 * phba->fc_ratov);
+
+	/* For this command calculate the xmit length of the request bde. */
+	xmit_len = 0;
+	first_len = 0;
+	bpl = (struct ulp_bde64 *)bmp->virt;
+	for (i = 0; i < num_entry; i++) {
+		bde.tus.w = bpl[i].tus.w;
+		if (bde.tus.f.bdeFlags != BUFF_TYPE_BDE_64)
+			break;
+		xmit_len += bde.tus.f.bdeSize;
+		if (i == 0)
+			first_len = xmit_len;
+	}
+
+	genwqe->rsvd2 = num_entry;
+	genwqe->hba_wqidx = 0;
+
+	/* Words 0 - 2 */
+	wqe->generic.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+	wqe->generic.bde.tus.f.bdeSize = first_len;
+	wqe->generic.bde.addrLow = bpl[0].addrLow;
+	wqe->generic.bde.addrHigh = bpl[0].addrHigh;
+
+	/* Word 3 */
+	wqe->gen_req.request_payload_len = first_len;
+
+	/* Word 4 */
+
+	/* Word 5 */
+	bf_set(wqe_dfctl, &wqe->gen_req.wge_ctl, 0);
+	bf_set(wqe_si, &wqe->gen_req.wge_ctl, 1);
+	bf_set(wqe_la, &wqe->gen_req.wge_ctl, 1);
+	bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_DD_UNSOL_CTL);
+	bf_set(wqe_type, &wqe->gen_req.wge_ctl, FC_TYPE_NVME);
+
+	/* Word 6 */
+	bf_set(wqe_ctxt_tag, &wqe->gen_req.wqe_com,
+	       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
+	bf_set(wqe_xri_tag, &wqe->gen_req.wqe_com, genwqe->sli4_xritag);
+
+	/* Word 7 */
+	bf_set(wqe_tmo, &wqe->gen_req.wqe_com, (vport->phba->fc_ratov-1));
+	bf_set(wqe_class, &wqe->gen_req.wqe_com, CLASS3);
+	bf_set(wqe_cmnd, &wqe->gen_req.wqe_com, CMD_GEN_REQUEST64_WQE);
+	bf_set(wqe_ct, &wqe->gen_req.wqe_com, SLI4_CT_RPI);
+
+	/* Word 8 */
+	wqe->gen_req.wqe_com.abort_tag = genwqe->iotag;
+
+	/* Word 9 */
+	bf_set(wqe_reqtag, &wqe->gen_req.wqe_com, genwqe->iotag);
+
+	/* Word 10 */
+	bf_set(wqe_dbde, &wqe->gen_req.wqe_com, 1);
+	bf_set(wqe_iod, &wqe->gen_req.wqe_com, LPFC_WQE_IOD_READ);
+	bf_set(wqe_qosd, &wqe->gen_req.wqe_com, 1);
+	bf_set(wqe_lenloc, &wqe->gen_req.wqe_com, LPFC_WQE_LENLOC_NONE);
+	bf_set(wqe_ebde_cnt, &wqe->gen_req.wqe_com, 0);
+
+	/* Word 11 */
+	bf_set(wqe_cqid, &wqe->gen_req.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+	bf_set(wqe_cmd_type, &wqe->gen_req.wqe_com, OTHER_COMMAND);
+
+
+	/* Issue GEN REQ WQE for NPORT <did> */
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
+			 "6050 Issue GEN REQ WQE to NPORT x%x "
+			 "Data: x%x x%x wq:%p lsreq:%p bmp:%p xmit:%d 1st:%d\n",
+			 ndlp->nlp_DID, genwqe->iotag,
+			 vport->port_state,
+			genwqe, pnvme_lsreq, bmp, xmit_len, first_len);
+	genwqe->wqe_cmpl = cmpl;
+	genwqe->iocb_cmpl = NULL;
+	genwqe->drvrTimeout = tmo + LPFC_DRVR_TIMEOUT;
+	genwqe->vport = vport;
+	genwqe->retry = retry;
+
+	rc = lpfc_sli4_issue_wqe(phba, LPFC_ELS_RING, genwqe);
+	if (rc == WQE_ERROR) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
+				 "6045 Issue GEN REQ WQE to NPORT x%x "
+				 "Data: x%x x%x\n",
+				 ndlp->nlp_DID, genwqe->iotag,
+				 vport->port_state);
+		lpfc_sli_release_iocbq(phba, genwqe);
+		return 1;
+	}
+	return 0;
+}
+
+/**
+ * lpfc_nvme_ls_req - Issue an Link Service request
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @lpfc_nvme_lport: Pointer to the driver's local port data
+ * @lpfc_nvme_rport: Pointer to the rport getting the @lpfc_nvme_ereq
+ *
+ * Driver registers this routine to handle any link service request
+ * from the nvme_fc transport to a remote nvme-aware port.
+ *
+ * Return value :
+ *   0 - Success
+ *   TODO: What are the failure codes.
+ **/
+static int
+lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
+		 struct nvme_fc_remote_port *pnvme_rport,
+		 struct nvmefc_ls_req *pnvme_lsreq)
+{
+	int ret = 0;
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_vport *vport;
+	struct lpfc_nodelist *ndlp;
+	struct ulp_bde64 *bpl;
+	struct lpfc_dmabuf *bmp;
+
+	/* there are two dma buf in the request, actually there is one and
+	 * the second one is just the start address + cmd size.
+	 * Before calling lpfc_nvme_gen_req these buffers need to be wrapped
+	 * in a lpfc_dmabuf struct. When freeing we just free the wrapper
+	 * because the nvem layer owns the data bufs.
+	 * We do not have to break these packets open, we don't care what is in
+	 * them. And we do not have to look at the resonse data, we only care
+	 * that we got a response. All of the caring is going to happen in the
+	 * nvme-fc layer.
+	 */
+
+	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
+	vport = lport->vport;
+
+	ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
+	if (!ndlp) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+				 "6043 Could not find node for DID %x\n",
+				 pnvme_rport->port_id);
+		return 1;
+	}
+	bmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
+	if (!bmp) {
+
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+				 "6044 Could not find node for DID %x\n",
+				 pnvme_rport->port_id);
+		return 2;
+	}
+	INIT_LIST_HEAD(&bmp->list);
+	bmp->virt = lpfc_mbuf_alloc(vport->phba, MEM_PRI, &(bmp->phys));
+	if (!bmp->virt) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+				 "6042 Could not find node for DID %x\n",
+				 pnvme_rport->port_id);
+		kfree(bmp);
+		return 3;
+	}
+	bpl = (struct ulp_bde64 *)bmp->virt;
+	bpl->addrHigh = le32_to_cpu(putPaddrHigh(pnvme_lsreq->rqstdma));
+	bpl->addrLow = le32_to_cpu(putPaddrLow(pnvme_lsreq->rqstdma));
+	bpl->tus.f.bdeFlags = 0;
+	bpl->tus.f.bdeSize = pnvme_lsreq->rqstlen;
+	bpl->tus.w = le32_to_cpu(bpl->tus.w);
+	bpl++;
+
+	bpl->addrHigh = le32_to_cpu(putPaddrHigh(pnvme_lsreq->rspdma));
+	bpl->addrLow = le32_to_cpu(putPaddrLow(pnvme_lsreq->rspdma));
+	bpl->tus.f.bdeFlags = BUFF_TYPE_BDE_64I;
+	bpl->tus.f.bdeSize = pnvme_lsreq->rsplen;
+	bpl->tus.w = le32_to_cpu(bpl->tus.w);
+
+	/* Expand print to include key fields. */
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+			 "6051 ENTER.  lport %p, rport %p lsreq%p rqstlen:%d "
+			 "rsplen:%d %llux %llux\n",
+			 pnvme_lport, pnvme_rport,
+			 pnvme_lsreq, pnvme_lsreq->rqstlen,
+			 pnvme_lsreq->rsplen, pnvme_lsreq->rqstdma,
+			 pnvme_lsreq->rspdma);
+
+	vport->phba->fc4NvmeLsRequests++;
+
+	/* Hardcode the wait to 30 seconds.  Connections are failing otherwise.
+	 * This code allows it all to work.
+	 */
+	ret = lpfc_nvme_gen_req(vport, bmp, pnvme_lsreq->rqstaddr,
+				pnvme_lsreq, lpfc_nvme_cmpl_gen_req,
+				ndlp, 2, 30, 0);
+	if (ret != WQE_SUCCESS) {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+				 "6052 EXIT. issue ls wqe failed lport %p, "
+				 "rport %p lsreq%p Status %x DID %x\n",
+				 pnvme_lport, pnvme_rport, pnvme_lsreq,
+				 ret, ndlp->nlp_DID);
+		lpfc_mbuf_free(vport->phba, bmp->virt, bmp->phys);
+		kfree(bmp);
+		return ret;
+	}
+
+	/* Stub in routine and return 0 for now. */
+	return ret;
+}
+
+/**
+ * lpfc_nvme_ls_abort - Issue an Link Service request
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @lpfc_nvme_lport: Pointer to the driver's local port data
+ * @lpfc_nvme_rport: Pointer to the rport getting the @lpfc_nvme_ereq
+ *
+ * Driver registers this routine to handle any link service request
+ * from the nvme_fc transport to a remote nvme-aware port.
+ *
+ * Return value :
+ *   0 - Success
+ *   TODO: What are the failure codes.
+ **/
+static void
+lpfc_nvme_ls_abort(struct nvme_fc_local_port *pnvme_lport,
+		   struct nvme_fc_remote_port *pnvme_rport,
+		   struct nvmefc_ls_req *pnvme_lsreq)
+{
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_vport *vport;
+	struct lpfc_hba *phba;
+	struct lpfc_nodelist *ndlp;
+	LIST_HEAD(abort_list);
+	struct lpfc_sli_ring *pring;
+	struct lpfc_iocbq *wqe, *next_wqe;
+
+	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
+	vport = lport->vport;
+	phba = vport->phba;
+
+	ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
+	if (!ndlp) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
+				 "6049 Could not find node for DID %x\n",
+				 pnvme_rport->port_id);
+		return;
+	}
+
+	/* Expand print to include key fields. */
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS,
+			 "6040 ENTER.  lport %p, rport %p lsreq %p rqstlen:%d "
+			 "rsplen:%d %llux %llux\n",
+			 pnvme_lport, pnvme_rport,
+			 pnvme_lsreq, pnvme_lsreq->rqstlen,
+			 pnvme_lsreq->rsplen, pnvme_lsreq->rqstdma,
+			 pnvme_lsreq->rspdma);
+
+	/*
+	 * Lock the ELS ring txcmplq and build a local list of all ELS IOs
+	 * that need an ABTS.  The IOs need to stay on the txcmplq so that
+	 * the abort operation completes them successfully.
+	 */
+	pring = phba->sli4_hba.nvmels_wq->pring;
+	spin_lock_irq(&phba->hbalock);
+	spin_lock(&pring->ring_lock);
+	list_for_each_entry_safe(wqe, next_wqe, &pring->txcmplq, list) {
+		/* Add to abort_list on on NDLP match. */
+		if (lpfc_check_sli_ndlp(phba, pring, wqe, ndlp)) {
+			wqe->iocb_flag |= LPFC_DRIVER_ABORTED;
+			list_add_tail(&wqe->dlist, &abort_list);
+		}
+	}
+	spin_unlock(&pring->ring_lock);
+	spin_unlock_irq(&phba->hbalock);
+
+	/* Abort the targeted IOs and remove them from the abort list. */
+	list_for_each_entry_safe(wqe, next_wqe, &abort_list, dlist) {
+		spin_lock_irq(&phba->hbalock);
+		list_del_init(&wqe->dlist);
+		lpfc_sli_issue_abort_iotag(phba, pring, wqe);
+		spin_unlock_irq(&phba->hbalock);
+	}
+}
+
+/* Fix up the existing sgls for NVME IO. */
+static void
+lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport,
+		       struct lpfc_nvme_buf *lpfc_ncmd,
+		       struct nvmefc_fcp_req *nCmd)
+{
+	struct sli4_sge *sgl;
+	union lpfc_wqe128 *wqe;
+	uint32_t *wptr, *dptr;
+
+	/*
+	 * Adjust the FCP_CMD and FCP_RSP DMA data and sge_len to
+	 * match NVME.  NVME sends 96 bytes. Also, use the
+	 * nvme commands command and response dma addresses
+	 * rather than the virtual memory to ease the restore
+	 * operation.
+	 */
+	sgl = lpfc_ncmd->nvme_sgl;
+	sgl->sge_len = cpu_to_le32(nCmd->cmdlen);
+
+	sgl++;
+
+	/* Setup the physical region for the FCP RSP */
+	sgl->addr_hi = cpu_to_le32(putPaddrHigh(nCmd->rspdma));
+	sgl->addr_lo = cpu_to_le32(putPaddrLow(nCmd->rspdma));
+	sgl->word2 = le32_to_cpu(sgl->word2);
+	if (nCmd->sg_cnt)
+		bf_set(lpfc_sli4_sge_last, sgl, 0);
+	else
+		bf_set(lpfc_sli4_sge_last, sgl, 1);
+	sgl->word2 = cpu_to_le32(sgl->word2);
+	sgl->sge_len = cpu_to_le32(nCmd->rsplen);
+
+	/*
+	 * Get a local pointer to the built-in wqe and correct
+	 * the cmd size to match NVME's 96 bytes and fix
+	 * the dma address.
+	 */
+
+	/* 128 byte wqe support here */
+	wqe = (union lpfc_wqe128 *)&lpfc_ncmd->cur_iocbq.wqe;
+
+	/* Word 0-2 - NVME CMND IU (embedded payload) */
+	wqe->generic.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_IMMED;
+	wqe->generic.bde.tus.f.bdeSize = 60;
+	wqe->generic.bde.addrHigh = 0;
+	wqe->generic.bde.addrLow =  64;  /* Word 16 */
+
+	/* Word 3 */
+	bf_set(payload_offset_len, &wqe->fcp_icmd,
+	       (nCmd->rsplen + nCmd->cmdlen));
+
+	/* Word 10 */
+	bf_set(wqe_nvme, &wqe->fcp_icmd.wqe_com, 1);
+	bf_set(wqe_wqes, &wqe->fcp_icmd.wqe_com, 1);
+
+	/*
+	 * Embed the payload in the last half of the WQE
+	 * WQE words 16-30 get the NVME CMD IU payload
+	 *
+	 * WQE Word 16 is already setup with flags
+	 * WQE words 17-19 get payload Words 2-4
+	 * WQE words 20-21 get payload Words 6-7
+	 * WQE words 22-29 get payload Words 16-23
+	 */
+	wptr = &wqe->words[17];  /* WQE ptr */
+	dptr = (uint32_t *)nCmd->cmdaddr;  /* payload ptr */
+	dptr += 2;		/* Skip Words 0-1 in payload */
+
+	*wptr++ = *dptr++;	/* Word 2 */
+	*wptr++ = *dptr++;	/* Word 3 */
+	*wptr++ = *dptr++;	/* Word 4 */
+	dptr++;			/* Skip Word 5 in payload */
+	*wptr++ = *dptr++;	/* Word 6 */
+	*wptr++ = *dptr++;	/* Word 7 */
+	dptr += 8;		/* Skip Words 8-15 in payload */
+	*wptr++ = *dptr++;	/* Word 16 */
+	*wptr++ = *dptr++;	/* Word 17 */
+	*wptr++ = *dptr++;	/* Word 18 */
+	*wptr++ = *dptr++;	/* Word 19 */
+	*wptr++ = *dptr++;	/* Word 20 */
+	*wptr++ = *dptr++;	/* Word 21 */
+	*wptr++ = *dptr++;	/* Word 22 */
+	*wptr   = *dptr;	/* Word 23 */
+}
+
+/**
+ * lpfc_nvme_io_cmd_wqe_cmpl - Complete an NVME-over-FCP IO
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @lpfc_nvme_lport: Pointer to the driver's local port data
+ * @lpfc_nvme_rport: Pointer to the rport getting the @lpfc_nvme_ereq
+ *
+ * Driver registers this routine as it io request handler.  This
+ * routine issues an fcp WQE with data from the @lpfc_nvme_fcpreq
+ * data structure to the rport indicated in @lpfc_nvme_rport.
+ *
+ * Return value :
+ *   0 - Success
+ *   TODO: What are the failure codes.
+ **/
+static void
+lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
+			  struct lpfc_wcqe_complete *wcqe)
+{
+	struct lpfc_nvme_buf *lpfc_ncmd =
+		(struct lpfc_nvme_buf *)pwqeIn->context1;
+	struct lpfc_vport *vport = pwqeIn->vport;
+	struct nvmefc_fcp_req *nCmd;
+	struct nvme_fc_ersp_iu *ep;
+	struct nvme_fc_cmd_iu *cp;
+	struct lpfc_nvme_rport *rport;
+	struct lpfc_nodelist *ndlp;
+	unsigned long flags;
+	uint32_t code;
+	uint16_t cid, sqhd, data;
+	uint32_t *ptr;
+
+	/* Sanity check on return of outstanding command */
+	if (!lpfc_ncmd || !lpfc_ncmd->nvmeCmd || !lpfc_ncmd->nrport) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+				 "6071 Completion pointers bad on wqe %p.\n",
+				 wcqe);
+		return;
+	}
+	phba->fc4NvmeIoCmpls++;
+
+	nCmd = lpfc_ncmd->nvmeCmd;
+	rport = lpfc_ncmd->nrport;
+
+	/*
+	 * Catch race where our node has transitioned, but the
+	 * transport is still transitioning.
+	 */
+	ndlp = rport->ndlp;
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+				 "6061 rport %p, ndlp %p, DID x%06x ndlp "
+				 "not ready.\n",
+				 rport, ndlp, rport->remoteport->port_id);
+
+		ndlp = lpfc_findnode_did(vport, rport->remoteport->port_id);
+		if (!ndlp) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
+					 "6062 Ignoring NVME cmpl.  No ndlp\n");
+			goto out_err;
+		}
+	}
+
+	code = bf_get(lpfc_wcqe_c_code, wcqe);
+	if (code == CQE_CODE_NVME_ERSP) {
+		/* For this type of CQE, we need to rebuild the rsp */
+		ep = (struct nvme_fc_ersp_iu *)nCmd->rspaddr;
+
+		/*
+		 * Get Command Id from cmd to plug into response. This
+		 * code is not needed in the next NVME Transport drop.
+		 */
+		cp = (struct nvme_fc_cmd_iu *)nCmd->cmdaddr;
+		cid = cp->sqe.common.command_id;
+
+		/*
+		 * RSN is in CQE word 2
+		 * SQHD is in CQE Word 3 bits 15:0
+		 * Cmd Specific info is in CQE Word 1
+		 * and in CQE Word 0 bits 15:0
+		 */
+		sqhd = bf_get(lpfc_wcqe_c_sqhead, wcqe);
+
+		/* Now lets build the NVME ERSP IU */
+		ep->iu_len = cpu_to_be16(8);
+		ep->rsn = wcqe->parameter;
+		ep->xfrd_len = cpu_to_be32(nCmd->payload_length);
+		ep->rsvd12 = 0;
+		ptr = (uint32_t *)&ep->cqe.result.u64;
+		*ptr++ = wcqe->total_data_placed;
+		data = bf_get(lpfc_wcqe_c_ersp0, wcqe);
+		*ptr = (uint32_t)data;
+		ep->cqe.sq_head = sqhd;
+		ep->cqe.sq_id =  nCmd->sqid;
+		ep->cqe.command_id = cid;
+		ep->cqe.status = 0;
+
+		lpfc_ncmd->status = IOSTAT_SUCCESS;
+		lpfc_ncmd->result = 0;
+		nCmd->rcv_rsplen = LPFC_NVME_ERSP_LEN;
+		nCmd->transferred_length = nCmd->payload_length;
+	} else {
+		lpfc_ncmd->status = (bf_get(lpfc_wcqe_c_status, wcqe) &
+			    LPFC_IOCB_STATUS_MASK);
+		lpfc_ncmd->result = wcqe->parameter;
+
+		/* For NVME, the only failure path that results in an
+		 * IO error is when the adapter rejects it.  All other
+		 * conditions are a success case and resolved by the
+		 * transport.
+		 * IOSTAT_FCP_RSP_ERROR means:
+		 * 1. Length of data received doesn't match total
+		 *    transfer length in WQE
+		 * 2. If the RSP payload does NOT match these cases:
+		 *    a. RSP length 12/24 bytes and all zeros
+		 *    b. NVME ERSP
+		 */
+		switch (lpfc_ncmd->status) {
+		case IOSTAT_SUCCESS:
+			nCmd->transferred_length = wcqe->total_data_placed;
+			nCmd->rcv_rsplen = 0;
+			nCmd->status = 0;
+			break;
+		case IOSTAT_FCP_RSP_ERROR:
+			nCmd->transferred_length = wcqe->total_data_placed;
+			nCmd->rcv_rsplen = wcqe->parameter;
+			nCmd->status = 0;
+			/* Sanity check */
+			if (nCmd->rcv_rsplen == LPFC_NVME_ERSP_LEN)
+				break;
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
+					 "6081 NVME Completion Protocol Error: "
+					 "status x%x result x%x placed x%x\n",
+					 lpfc_ncmd->status, lpfc_ncmd->result,
+					 wcqe->total_data_placed);
+			break;
+		default:
+out_err:
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
+					 "6072 NVME Completion Error: "
+					 "status x%x result x%x placed x%x\n",
+					 lpfc_ncmd->status, lpfc_ncmd->result,
+					 wcqe->total_data_placed);
+			nCmd->transferred_length = 0;
+			nCmd->rcv_rsplen = 0;
+			nCmd->status = NVME_SC_FC_TRANSPORT_ERROR;
+		}
+	}
+
+	/* pick up SLI4 exhange busy condition */
+	if (bf_get(lpfc_wcqe_c_xb, wcqe))
+		lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
+	else
+		lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
+
+	if (ndlp && NLP_CHK_NODE_ACT(ndlp))
+		atomic_dec(&ndlp->cmd_pending);
+
+	/* Update stats and complete the IO.  There is
+	 * no need for dma unprep because the nvme_transport
+	 * owns the dma address.
+	 */
+	nCmd->done(nCmd);
+
+	spin_lock_irqsave(&phba->hbalock, flags);
+	lpfc_ncmd->nrport = NULL;
+	spin_unlock_irqrestore(&phba->hbalock, flags);
+
+	lpfc_release_nvme_buf(phba, lpfc_ncmd);
+}
+
+
+/**
+ * lpfc_nvme_prep_io_cmd - Issue an NVME-over-FCP IO
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @lpfc_nvme_lport: Pointer to the driver's local port data
+ * @lpfc_nvme_rport: Pointer to the rport getting the @lpfc_nvme_ereq
+ * @lpfc_nvme_fcreq: IO request from nvme fc to driver.
+ * @hw_queue_handle: Driver-returned handle in lpfc_nvme_create_queue
+ *
+ * Driver registers this routine as it io request handler.  This
+ * routine issues an fcp WQE with data from the @lpfc_nvme_fcpreq
+ * data structure to the rport indicated in @lpfc_nvme_rport.
+ *
+ * Return value :
+ *   0 - Success
+ *   TODO: What are the failure codes.
+ **/
+static int
+lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
+		      struct lpfc_nvme_buf *lpfc_ncmd,
+		      struct lpfc_nodelist *pnode)
+{
+	struct lpfc_hba *phba = vport->phba;
+	struct nvmefc_fcp_req *nCmd = lpfc_ncmd->nvmeCmd;
+	struct lpfc_iocbq *pwqeq = &(lpfc_ncmd->cur_iocbq);
+	union lpfc_wqe128 *wqe = (union lpfc_wqe128 *)&pwqeq->wqe;
+	uint32_t req_len;
+
+	if (!pnode || !NLP_CHK_NODE_ACT(pnode))
+		return -EINVAL;
+
+	/*
+	 * There are three possibilities here - use scatter-gather segment, use
+	 * the single mapping, or neither.
+	 */
+	wqe->fcp_iwrite.initial_xfer_len = 0;
+	if (nCmd->sg_cnt) {
+		if (nCmd->io_dir == NVMEFC_FCP_WRITE) {
+			/* Word 5 */
+			if ((phba->cfg_nvme_enable_fb) &&
+			    (pnode->nlp_flag & NLP_FIRSTBURST)) {
+				req_len = lpfc_ncmd->nvmeCmd->payload_length;
+				if (req_len < pnode->nvme_fb_size)
+					wqe->fcp_iwrite.initial_xfer_len =
+						req_len;
+				else
+					wqe->fcp_iwrite.initial_xfer_len =
+						pnode->nvme_fb_size;
+			}
+
+			/* Word 7 */
+			bf_set(wqe_cmnd, &wqe->generic.wqe_com,
+			       CMD_FCP_IWRITE64_WQE);
+			bf_set(wqe_pu, &wqe->generic.wqe_com,
+			       PARM_READ_CHECK);
+
+			/* Word 10 */
+			bf_set(wqe_qosd, &wqe->fcp_iwrite.wqe_com, 0);
+			bf_set(wqe_iod, &wqe->fcp_iwrite.wqe_com,
+			       LPFC_WQE_IOD_WRITE);
+			bf_set(wqe_lenloc, &wqe->fcp_iwrite.wqe_com,
+			       LPFC_WQE_LENLOC_WORD4);
+			if (phba->cfg_nvme_oas)
+				bf_set(wqe_oas, &wqe->fcp_iwrite.wqe_com, 1);
+
+			/* Word 11 */
+			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
+			       NVME_WRITE_CMD);
+
+			/* Word 16 */
+			wqe->words[16] = LPFC_NVME_EMBED_WRITE;
+
+			phba->fc4NvmeOutputRequests++;
+		} else {
+			/* Word 7 */
+			bf_set(wqe_cmnd, &wqe->generic.wqe_com,
+			       CMD_FCP_IREAD64_WQE);
+			bf_set(wqe_pu, &wqe->generic.wqe_com,
+			       PARM_READ_CHECK);
+
+			/* Word 10 */
+			bf_set(wqe_qosd, &wqe->fcp_iread.wqe_com, 0);
+			bf_set(wqe_iod, &wqe->fcp_iread.wqe_com,
+			       LPFC_WQE_IOD_READ);
+			bf_set(wqe_lenloc, &wqe->fcp_iread.wqe_com,
+			       LPFC_WQE_LENLOC_WORD4);
+			if (phba->cfg_nvme_oas)
+				bf_set(wqe_oas, &wqe->fcp_iread.wqe_com, 1);
+
+			/* Word 11 */
+			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
+			       NVME_READ_CMD);
+
+			/* Word 16 */
+			wqe->words[16] = LPFC_NVME_EMBED_READ;
+
+			phba->fc4NvmeInputRequests++;
+		}
+	} else {
+		/* Word 4 */
+		wqe->fcp_icmd.rsrvd4 = 0;
+
+		/* Word 7 */
+		bf_set(wqe_cmnd, &wqe->generic.wqe_com, CMD_FCP_ICMND64_WQE);
+		bf_set(wqe_pu, &wqe->generic.wqe_com, 0);
+
+		/* Word 10 */
+		bf_set(wqe_qosd, &wqe->fcp_icmd.wqe_com, 1);
+		bf_set(wqe_iod, &wqe->fcp_icmd.wqe_com, LPFC_WQE_IOD_WRITE);
+		bf_set(wqe_lenloc, &wqe->fcp_icmd.wqe_com,
+		       LPFC_WQE_LENLOC_NONE);
+		if (phba->cfg_nvme_oas)
+			bf_set(wqe_oas, &wqe->fcp_icmd.wqe_com, 1);
+
+		/* Word 11 */
+		bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_READ_CMD);
+
+		/* Word 16 */
+		wqe->words[16] = LPFC_NVME_EMBED_CMD;
+
+		phba->fc4NvmeControlRequests++;
+	}
+	/*
+	 * Finish initializing those WQE fields that are independent
+	 * of the nvme_cmnd request_buffer
+	 */
+
+	/* Word 6 */
+	bf_set(wqe_ctxt_tag, &wqe->generic.wqe_com,
+	       phba->sli4_hba.rpi_ids[pnode->nlp_rpi]);
+	bf_set(wqe_xri_tag, &wqe->generic.wqe_com, pwqeq->sli4_xritag);
+
+	/* Word 7 */
+	/* Preserve Class data in the ndlp. */
+	bf_set(wqe_class, &wqe->generic.wqe_com,
+	       (pnode->nlp_fcp_info & 0x0f));
+
+	/* Word 8 */
+	wqe->generic.wqe_com.abort_tag = pwqeq->iotag;
+
+	/* Word 9 */
+	bf_set(wqe_reqtag, &wqe->generic.wqe_com, pwqeq->iotag);
+
+	/* Word 11 */
+	bf_set(wqe_cqid, &wqe->generic.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+
+	pwqeq->vport = vport;
+	return 0;
+}
+
+
+/**
+ * lpfc_nvme_prep_io_dma - Issue an NVME-over-FCP IO
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @lpfc_nvme_lport: Pointer to the driver's local port data
+ * @lpfc_nvme_rport: Pointer to the rport getting the @lpfc_nvme_ereq
+ * @lpfc_nvme_fcreq: IO request from nvme fc to driver.
+ * @hw_queue_handle: Driver-returned handle in lpfc_nvme_create_queue
+ *
+ * Driver registers this routine as it io request handler.  This
+ * routine issues an fcp WQE with data from the @lpfc_nvme_fcpreq
+ * data structure to the rport indicated in @lpfc_nvme_rport.
+ *
+ * Return value :
+ *   0 - Success
+ *   TODO: What are the failure codes.
+ **/
+static int
+lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
+		      struct lpfc_nvme_buf *lpfc_ncmd)
+{
+	struct lpfc_hba *phba = vport->phba;
+	struct nvmefc_fcp_req *nCmd = lpfc_ncmd->nvmeCmd;
+	union lpfc_wqe128 *wqe = (union lpfc_wqe128 *)&lpfc_ncmd->cur_iocbq.wqe;
+	struct sli4_sge *sgl = lpfc_ncmd->nvme_sgl;
+	struct scatterlist *data_sg;
+	struct sli4_sge *first_data_sgl;
+	dma_addr_t physaddr;
+	uint32_t num_bde = 0;
+	uint32_t dma_len;
+	uint32_t dma_offset = 0;
+	int nseg, i;
+
+	/* Fix up the command and response DMA stuff. */
+	lpfc_nvme_adj_fcp_sgls(vport, lpfc_ncmd, nCmd);
+
+	/*
+	 * There are three possibilities here - use scatter-gather segment, use
+	 * the single mapping, or neither.
+	 */
+	if (nCmd->sg_cnt) {
+		/*
+		 * Jump over the cmd and rsp SGEs.  The fix routine
+		 * has already adjusted for this.
+		 */
+		sgl += 2;
+
+		first_data_sgl = sgl;
+		lpfc_ncmd->seg_cnt = nCmd->sg_cnt;
+		if (lpfc_ncmd->seg_cnt > phba->cfg_sg_seg_cnt) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+					"6058 Too many sg segments from "
+					"NVME Transport.  Max %d, "
+					"nvmeIO sg_cnt %d\n",
+					phba->cfg_sg_seg_cnt,
+					lpfc_ncmd->seg_cnt);
+			lpfc_ncmd->seg_cnt = 0;
+			return 1;
+		}
+
+		/*
+		 * The driver established a maximum scatter-gather segment count
+		 * during probe that limits the number of sg elements in any
+		 * single nvme command.  Just run through the seg_cnt and format
+		 * the sge's.
+		 */
+		nseg = nCmd->sg_cnt;
+		data_sg = nCmd->first_sgl;
+		for (i = 0; i < nseg; i++) {
+			if (data_sg == NULL) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+						"6059 dptr err %d, nseg %d\n",
+						i, nseg);
+				lpfc_ncmd->seg_cnt = 0;
+				return 1;
+			}
+			physaddr = data_sg->dma_address;
+			dma_len = data_sg->length;
+			sgl->addr_lo = cpu_to_le32(putPaddrLow(physaddr));
+			sgl->addr_hi = cpu_to_le32(putPaddrHigh(physaddr));
+			sgl->word2 = le32_to_cpu(sgl->word2);
+			if ((num_bde + 1) == nseg)
+				bf_set(lpfc_sli4_sge_last, sgl, 1);
+			else
+				bf_set(lpfc_sli4_sge_last, sgl, 0);
+			bf_set(lpfc_sli4_sge_offset, sgl, dma_offset);
+			bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA);
+			sgl->word2 = cpu_to_le32(sgl->word2);
+			sgl->sge_len = cpu_to_le32(dma_len);
+
+			dma_offset += dma_len;
+			data_sg = sg_next(data_sg);
+			sgl++;
+		}
+	} else {
+		/* For this clause to be valid, the payload_length
+		 * and sg_cnt must zero.
+		 */
+		if (nCmd->payload_length != 0) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+					"6063 NVME DMA Prep Err: sg_cnt %d "
+					"payload_length x%x\n",
+					nCmd->sg_cnt, nCmd->payload_length);
+			return 1;
+		}
+	}
+
+	/*
+	 * Due to difference in data length between DIF/non-DIF paths,
+	 * we need to set word 4 of WQE here
+	 */
+	wqe->fcp_iread.total_xfer_len = nCmd->payload_length;
+	return 0;
+}
+
+/**
+ * lpfc_nvme_fcp_io_submit - Issue an NVME-over-FCP IO
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @lpfc_nvme_lport: Pointer to the driver's local port data
+ * @lpfc_nvme_rport: Pointer to the rport getting the @lpfc_nvme_ereq
+ * @lpfc_nvme_fcreq: IO request from nvme fc to driver.
+ * @hw_queue_handle: Driver-returned handle in lpfc_nvme_create_queue
+ *
+ * Driver registers this routine as it io request handler.  This
+ * routine issues an fcp WQE with data from the @lpfc_nvme_fcpreq
+ * data structure to the rport
+ indicated in @lpfc_nvme_rport.
+ *
+ * Return value :
+ *   0 - Success
+ *   TODO: What are the failure codes.
+ **/
+static int
+lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
+			struct nvme_fc_remote_port *pnvme_rport,
+			void *hw_queue_handle,
+			struct nvmefc_fcp_req *pnvme_fcreq)
+{
+	int ret = 0;
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_vport *vport;
+	struct lpfc_hba *phba;
+	struct lpfc_nodelist *ndlp;
+	struct lpfc_nvme_buf *lpfc_ncmd;
+	struct lpfc_nvme_rport *rport;
+	struct lpfc_nvme_qhandle *lpfc_queue_info;
+
+	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
+	vport = lport->vport;
+	phba = vport->phba;
+
+	rport = (struct lpfc_nvme_rport *)pnvme_rport->private;
+	lpfc_queue_info = (struct lpfc_nvme_qhandle *)hw_queue_handle;
+
+	/*
+	 * Catch race where our node has transitioned, but the
+	 * transport is still transitioning.
+	 */
+	ndlp = rport->ndlp;
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+				 "6053 rport %p, ndlp %p, DID x%06x "
+				 "ndlp not ready.\n",
+				 rport, ndlp, pnvme_rport->port_id);
+
+		ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
+		if (!ndlp) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
+					 "6066 Missing node for DID %x\n",
+					 pnvme_rport->port_id);
+			ret = -ENODEV;
+			goto out_fail;
+		}
+	}
+
+	/* The remote node has to be a mapped target or it's an error. */
+	if ((ndlp->nlp_type & NLP_NVME_TARGET) &&
+	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+				 "6036 rport %p, DID x%06x not ready for "
+				 "IO. State x%x, Type x%x\n",
+				 rport, pnvme_rport->port_id,
+				 ndlp->nlp_state, ndlp->nlp_type);
+		ret = -ENODEV;
+		goto out_fail;
+
+	}
+
+	/* The node is shared with FCP IO, make sure the IO pending count does
+	 * not exceed the programmed depth.
+	 */
+	if (atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) {
+		ret = -EAGAIN;
+		goto out_fail;
+	}
+
+	lpfc_ncmd = lpfc_get_nvme_buf(phba, ndlp);
+	if (lpfc_ncmd == NULL) {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
+				 "6065 driver's buffer pool is empty, "
+				 "IO failed\n");
+		ret = -ENOMEM;
+		goto out_fail;
+	}
+
+	/*
+	 * Store the data needed by the driver to issue, abort, and complete
+	 * an IO.
+	 * Do not let the IO hang out forever.  There is no midlayer issuing
+	 * an abort so inform the FW of the maximum IO pending time.
+	 */
+	pnvme_fcreq->private = (void *)lpfc_ncmd;
+	lpfc_ncmd->nvmeCmd = pnvme_fcreq;
+	lpfc_ncmd->nrport = rport;
+	lpfc_ncmd->start_time = jiffies;
+
+	lpfc_nvme_prep_io_cmd(vport, lpfc_ncmd, ndlp);
+	ret = lpfc_nvme_prep_io_dma(vport, lpfc_ncmd);
+	if (ret) {
+		ret = -ENOMEM;
+		goto out_free_nvme_buf;
+	}
+
+	atomic_inc(&ndlp->cmd_pending);
+
+	/*
+	 * Issue the IO on the WQ indicated by index in the hw_queue_handle.
+	 * This identfier was create in our hardware queue create callback
+	 * routine. The driver now is dependent on the IO queue steering from
+	 * the transport.  We are trusting the upper NVME layers know which
+	 * index to use and that they have affinitized a CPU to this hardware
+	 * queue. A hardware queue maps to a driver MSI-X vector/EQ/CQ/WQ.
+	 */
+	lpfc_ncmd->cur_iocbq.hba_wqidx = lpfc_queue_info->index;
+
+	ret = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, &lpfc_ncmd->cur_iocbq);
+	if (ret) {
+		atomic_dec(&ndlp->cmd_pending);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
+				 "6113 FCP could not issue WQE err %x "
+				 "sid: x%x did: x%x oxid: x%x\n",
+				 ret, vport->fc_myDID, ndlp->nlp_DID,
+				 lpfc_ncmd->cur_iocbq.sli4_xritag);
+		ret = -EINVAL;
+		goto out_free_nvme_buf;
+	}
+
+	return 0;
+
+ out_free_nvme_buf:
+	lpfc_release_nvme_buf(phba, lpfc_ncmd);
+ out_fail:
+	return ret;
+}
+
+/**
+ * lpfc_nvme_abort_fcreq_cmpl - Complete an NVME FCP abort request.
+ * @phba: Pointer to HBA context object
+ * @cmdiocb: Pointer to command iocb object.
+ * @rspiocb: Pointer to response iocb object.
+ *
+ * This is the callback function for any NVME FCP IO that was aborted.
+ *
+ * Return value:
+ *   None
+ **/
+void
+lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
+			   struct lpfc_wcqe_complete *abts_cmpl)
+{
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+			"6145 ABORT_XRI_CN completing on rpi x%x "
+			"original iotag x%x, abort cmd iotag x%x "
+			"req_tag x%x, status x%x, hwstatus x%x\n",
+			cmdiocb->iocb.un.acxri.abortContextTag,
+			cmdiocb->iocb.un.acxri.abortIoTag,
+			cmdiocb->iotag,
+			bf_get(lpfc_wcqe_c_request_tag, abts_cmpl),
+			bf_get(lpfc_wcqe_c_status, abts_cmpl),
+			bf_get(lpfc_wcqe_c_hw_status, abts_cmpl));
+	lpfc_sli_release_iocbq(phba, cmdiocb);
+}
+
+/**
+ * lpfc_nvme_fcp_abort - Issue an NVME-over-FCP ABTS
+ * @lpfc_pnvme: Pointer to the driver's nvme instance data
+ * @lpfc_nvme_lport: Pointer to the driver's local port data
+ * @lpfc_nvme_rport: Pointer to the rport getting the @lpfc_nvme_ereq
+ * @lpfc_nvme_fcreq: IO request from nvme fc to driver.
+ * @hw_queue_handle: Driver-returned handle in lpfc_nvme_create_queue
+ *
+ * Driver registers this routine as its nvme request io abort handler.  This
+ * routine issues an fcp Abort WQE with data from the @lpfc_nvme_fcpreq
+ * data structure to the rport indicated in @lpfc_nvme_rport.  This routine
+ * is executed asynchronously - one the target is validated as "MAPPED" and
+ * ready for IO, the driver issues the abort request and returns.
+ *
+ * Return value:
+ *   None
+ **/
+static void
+lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
+		    struct nvme_fc_remote_port *pnvme_rport,
+		    void *hw_queue_handle,
+		    struct nvmefc_fcp_req *pnvme_fcreq)
+{
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_vport *vport;
+	struct lpfc_hba *phba;
+	struct lpfc_nodelist *ndlp;
+	struct lpfc_nvme_rport *rport;
+	struct lpfc_nvme_buf *lpfc_nbuf;
+	struct lpfc_iocbq *abts_buf;
+	struct lpfc_iocbq *nvmereq_wqe;
+	union lpfc_wqe *abts_wqe;
+	unsigned long flags;
+	int ret_val;
+
+	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
+	rport = (struct lpfc_nvme_rport *)pnvme_rport->private;
+	vport = lport->vport;
+	phba = vport->phba;
+
+	/* Announce entry to new IO submit field. */
+	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
+			 "6002 Abort Request to rport DID x%06x "
+			 "for nvme_fc_req %p\n",
+			 pnvme_rport->port_id,
+			 pnvme_fcreq);
+
+	/*
+	 * Catch race where our node has transitioned, but the
+	 * transport is still transitioning.
+	 */
+	ndlp = rport->ndlp;
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_ABTS,
+				 "6054 rport %p, ndlp %p, DID x%06x ndlp "
+				 " not ready.\n",
+				 rport, ndlp, pnvme_rport->port_id);
+
+		ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
+		if (!ndlp) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
+					 "6055 Could not find node for "
+					 "DID %x\n",
+					 pnvme_rport->port_id);
+			return;
+		}
+	}
+
+	/* The remote node has to be ready to send an abort. */
+	if ((ndlp->nlp_state != NLP_STE_MAPPED_NODE) &&
+	    !(ndlp->nlp_type & NLP_NVME_TARGET)) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_ABTS,
+				 "6048 rport %p, DID x%06x not ready for "
+				 "IO. State x%x, Type x%x\n",
+				 rport, pnvme_rport->port_id,
+				 ndlp->nlp_state, ndlp->nlp_type);
+		return;
+	}
+
+	/* If the hba is getting reset, this flag is set.  It is
+	 * cleared when the reset is complete and rings reestablished.
+	 */
+	spin_lock_irqsave(&phba->hbalock, flags);
+	/* driver queued commands are in process of being flushed */
+	if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6139 Driver in reset cleanup - flushing "
+				 "NVME Req now.  hba_flag x%x\n",
+				 phba->hba_flag);
+		return;
+	}
+
+	lpfc_nbuf = (struct lpfc_nvme_buf *)pnvme_fcreq->private;
+	if (!lpfc_nbuf) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6140 NVME IO req has no matching lpfc nvme "
+				 "io buffer.  Skipping abort req.\n");
+		return;
+	} else if (!lpfc_nbuf->nvmeCmd) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6141 lpfc NVME IO req has no nvme_fcreq "
+				 "io buffer.  Skipping abort req.\n");
+		return;
+	}
+
+	/*
+	 * The lpfc_nbuf and the mapped nvme_fcreq in the driver's
+	 * state must match the nvme_fcreq passed by the nvme
+	 * transport.  If they don't match, it is likely the driver
+	 * has already completed the NVME IO and the nvme transport
+	 * has not seen it yet.
+	 */
+	if (lpfc_nbuf->nvmeCmd != pnvme_fcreq) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6143 NVME req mismatch: "
+				 "lpfc_nbuf %p nvmeCmd %p, "
+				 "pnvme_fcreq %p.  Skipping Abort\n",
+				 lpfc_nbuf, lpfc_nbuf->nvmeCmd,
+				 pnvme_fcreq);
+		return;
+	}
+
+	/* Don't abort IOs no longer on the pending queue. */
+	nvmereq_wqe = &lpfc_nbuf->cur_iocbq;
+	if (!(nvmereq_wqe->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6142 NVME IO req %p not queued - skipping "
+				 "abort req\n",
+				 pnvme_fcreq);
+		return;
+	}
+
+	/* Outstanding abort is in progress */
+	if (nvmereq_wqe->iocb_flag & LPFC_DRIVER_ABORTED) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6144 Outstanding NVME I/O Abort Request "
+				 "still pending on nvme_fcreq %p, "
+				 "lpfc_ncmd %p\n",
+				 pnvme_fcreq, lpfc_nbuf);
+		return;
+	}
+
+	abts_buf = __lpfc_sli_get_iocbq(phba);
+	if (!abts_buf) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6136 No available abort wqes. Skipping "
+				 "Abts req for nvme_fcreq %p.\n",
+				 pnvme_fcreq);
+		return;
+	}
+
+	/* Ready - mark outstanding as aborted by driver. */
+	nvmereq_wqe->iocb_flag |= LPFC_DRIVER_ABORTED;
+
+	/* Complete prepping the abort wqe and issue to the FW. */
+	abts_wqe = &abts_buf->wqe;
+
+	/* WQEs are reused.  Clear stale data and set key fields to
+	 * zero like ia, iaab, iaar, xri_tag, and ctxt_tag.
+	 */
+	memset(abts_wqe, 0, sizeof(union lpfc_wqe));
+	bf_set(abort_cmd_criteria, &abts_wqe->abort_cmd, T_XRI_TAG);
+
+	/* word 7 */
+	bf_set(wqe_ct, &abts_wqe->abort_cmd.wqe_com, 0);
+	bf_set(wqe_cmnd, &abts_wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX);
+	bf_set(wqe_class, &abts_wqe->abort_cmd.wqe_com,
+	       nvmereq_wqe->iocb.ulpClass);
+
+	/* word 8 - tell the FW to abort the IO associated with this
+	 * outstanding exchange ID.
+	 */
+	abts_wqe->abort_cmd.wqe_com.abort_tag = nvmereq_wqe->sli4_xritag;
+
+	/* word 9 - this is the iotag for the abts_wqe completion. */
+	bf_set(wqe_reqtag, &abts_wqe->abort_cmd.wqe_com,
+	       abts_buf->iotag);
+
+	/* word 10 */
+	bf_set(wqe_wqid, &abts_wqe->abort_cmd.wqe_com, nvmereq_wqe->hba_wqidx);
+	bf_set(wqe_qosd, &abts_wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_lenloc, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE);
+
+	/* word 11 */
+	bf_set(wqe_cmd_type, &abts_wqe->abort_cmd.wqe_com, OTHER_COMMAND);
+	bf_set(wqe_wqec, &abts_wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_cqid, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+
+	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
+	abts_buf->iocb_flag |= LPFC_IO_NVME;
+	abts_buf->hba_wqidx = nvmereq_wqe->hba_wqidx;
+	abts_buf->vport = vport;
+	abts_buf->wqe_cmpl = lpfc_nvme_abort_fcreq_cmpl;
+	ret_val = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_buf);
+	spin_unlock_irqrestore(&phba->hbalock, flags);
+	if (ret_val == IOCB_ERROR) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+				 "6137 Failed abts issue_wqe with status x%x "
+				 "for nvme_fcreq %p.\n",
+				 ret_val, pnvme_fcreq);
+		lpfc_sli_release_iocbq(phba, abts_buf);
+		return;
+	}
+
+	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+			 "6138 Transport Abort NVME Request Issued for\n"
+			 "ox_id x%x on reqtag x%x\n",
+			 nvmereq_wqe->sli4_xritag,
+			 abts_buf->iotag);
+}
+
+/* Declare and initialization an instance of the FC NVME template. */
+static struct nvme_fc_port_template lpfc_nvme_template = {
+	/* initiator-based functions */
+	.localport_delete  = lpfc_nvme_localport_delete,
+	.remoteport_delete = lpfc_nvme_remoteport_delete,
+	.create_queue = lpfc_nvme_create_queue,
+	.delete_queue = lpfc_nvme_delete_queue,
+	.ls_req       = lpfc_nvme_ls_req,
+	.fcp_io       = lpfc_nvme_fcp_io_submit,
+	.ls_abort     = lpfc_nvme_ls_abort,
+	.fcp_abort    = lpfc_nvme_fcp_abort,
+
+	.max_hw_queues = 1,
+	.max_sgl_segments = LPFC_NVME_DEFAULT_SEGS,
+	.max_dif_sgl_segments = LPFC_NVME_DEFAULT_SEGS,
+	.dma_boundary = 0xFFFFFFFF,
+
+	/* Sizes of additional private data for data structures.
+	 * No use for the last two sizes at this time.
+	 */
+	.local_priv_sz = sizeof(struct lpfc_nvme_lport),
+	.remote_priv_sz = sizeof(struct lpfc_nvme_rport),
+	.lsrqst_priv_sz = 0,
+	.fcprqst_priv_sz = 0,
+};
+
+/**
+ * lpfc_sli4_post_nvme_sgl_block - post a block of nvme sgl list to firmware
+ * @phba: pointer to lpfc hba data structure.
+ * @nblist: pointer to nvme buffer list.
+ * @count: number of scsi buffers on the list.
+ *
+ * This routine is invoked to post a block of @count scsi sgl pages from a
+ * SCSI buffer list @nblist to the HBA using non-embedded mailbox command.
+ * No Lock is held.
+ *
+ **/
+static int
+lpfc_sli4_post_nvme_sgl_block(struct lpfc_hba *phba,
+			      struct list_head *nblist,
+			      int count)
+{
+	struct lpfc_nvme_buf *lpfc_ncmd;
+	struct lpfc_mbx_post_uembed_sgl_page1 *sgl;
+	struct sgl_page_pairs *sgl_pg_pairs;
+	void *viraddr;
+	LPFC_MBOXQ_t *mbox;
+	uint32_t reqlen, alloclen, pg_pairs;
+	uint32_t mbox_tmo;
+	uint16_t xritag_start = 0;
+	int rc = 0;
+	uint32_t shdr_status, shdr_add_status;
+	dma_addr_t pdma_phys_bpl1;
+	union lpfc_sli4_cfg_shdr *shdr;
+
+	/* Calculate the requested length of the dma memory */
+	reqlen = count * sizeof(struct sgl_page_pairs) +
+		 sizeof(union lpfc_sli4_cfg_shdr) + sizeof(uint32_t);
+	if (reqlen > SLI4_PAGE_SIZE) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+				"6118 Block sgl registration required DMA "
+				"size (%d) great than a page\n", reqlen);
+		return -ENOMEM;
+	}
+	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"6119 Failed to allocate mbox cmd memory\n");
+		return -ENOMEM;
+	}
+
+	/* Allocate DMA memory and set up the non-embedded mailbox command */
+	alloclen = lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_FCOE,
+				LPFC_MBOX_OPCODE_FCOE_POST_SGL_PAGES, reqlen,
+				LPFC_SLI4_MBX_NEMBED);
+
+	if (alloclen < reqlen) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"6120 Allocated DMA memory size (%d) is "
+				"less than the requested DMA memory "
+				"size (%d)\n", alloclen, reqlen);
+		lpfc_sli4_mbox_cmd_free(phba, mbox);
+		return -ENOMEM;
+	}
+
+	/* Get the first SGE entry from the non-embedded DMA memory */
+	viraddr = mbox->sge_array->addr[0];
+
+	/* Set up the SGL pages in the non-embedded DMA pages */
+	sgl = (struct lpfc_mbx_post_uembed_sgl_page1 *)viraddr;
+	sgl_pg_pairs = &sgl->sgl_pg_pairs;
+
+	pg_pairs = 0;
+	list_for_each_entry(lpfc_ncmd, nblist, list) {
+		/* Set up the sge entry */
+		sgl_pg_pairs->sgl_pg0_addr_lo =
+			cpu_to_le32(putPaddrLow(lpfc_ncmd->dma_phys_sgl));
+		sgl_pg_pairs->sgl_pg0_addr_hi =
+			cpu_to_le32(putPaddrHigh(lpfc_ncmd->dma_phys_sgl));
+		if (phba->cfg_sg_dma_buf_size > SGL_PAGE_SIZE)
+			pdma_phys_bpl1 = lpfc_ncmd->dma_phys_sgl +
+						SGL_PAGE_SIZE;
+		else
+			pdma_phys_bpl1 = 0;
+		sgl_pg_pairs->sgl_pg1_addr_lo =
+			cpu_to_le32(putPaddrLow(pdma_phys_bpl1));
+		sgl_pg_pairs->sgl_pg1_addr_hi =
+			cpu_to_le32(putPaddrHigh(pdma_phys_bpl1));
+		/* Keep the first xritag on the list */
+		if (pg_pairs == 0)
+			xritag_start = lpfc_ncmd->cur_iocbq.sli4_xritag;
+		sgl_pg_pairs++;
+		pg_pairs++;
+	}
+	bf_set(lpfc_post_sgl_pages_xri, sgl, xritag_start);
+	bf_set(lpfc_post_sgl_pages_xricnt, sgl, pg_pairs);
+	/* Perform endian conversion if necessary */
+	sgl->word0 = cpu_to_le32(sgl->word0);
+
+	if (!phba->sli4_hba.intr_enable)
+		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+	else {
+		mbox_tmo = lpfc_mbox_tmo_val(phba, mbox);
+		rc = lpfc_sli_issue_mbox_wait(phba, mbox, mbox_tmo);
+	}
+	shdr = (union lpfc_sli4_cfg_shdr *)&sgl->cfg_shdr;
+	shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+	shdr_add_status = bf_get(lpfc_mbox_hdr_add_status, &shdr->response);
+	if (rc != MBX_TIMEOUT)
+		lpfc_sli4_mbox_cmd_free(phba, mbox);
+	if (shdr_status || shdr_add_status || rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"6125 POST_SGL_BLOCK mailbox command failed "
+				"status x%x add_status x%x mbx status x%x\n",
+				shdr_status, shdr_add_status, rc);
+		rc = -ENXIO;
+	}
+	return rc;
+}
+
+/**
+ * lpfc_post_nvme_sgl_list - Post blocks of nvme buffer sgls from a list
+ * @phba: pointer to lpfc hba data structure.
+ * @post_nblist: pointer to the nvme buffer list.
+ *
+ * This routine walks a list of nvme buffers that was passed in. It attempts
+ * to construct blocks of nvme buffer sgls which contains contiguous xris and
+ * uses the non-embedded SGL block post mailbox commands to post to the port.
+ * For single NVME buffer sgl with non-contiguous xri, if any, it shall use
+ * embedded SGL post mailbox command for posting. The @post_nblist passed in
+ * must be local list, thus no lock is needed when manipulate the list.
+ *
+ * Returns: 0 = failure, non-zero number of successfully posted buffers.
+ **/
+static int
+lpfc_post_nvme_sgl_list(struct lpfc_hba *phba,
+			     struct list_head *post_nblist, int sb_count)
+{
+	struct lpfc_nvme_buf *lpfc_ncmd, *lpfc_ncmd_next;
+	int status, sgl_size;
+	int post_cnt = 0, block_cnt = 0, num_posting = 0, num_posted = 0;
+	dma_addr_t pdma_phys_sgl1;
+	int last_xritag = NO_XRI;
+	int cur_xritag;
+	LIST_HEAD(prep_nblist);
+	LIST_HEAD(blck_nblist);
+	LIST_HEAD(nvme_nblist);
+
+	/* sanity check */
+	if (sb_count <= 0)
+		return -EINVAL;
+
+	sgl_size = phba->cfg_sg_dma_buf_size;
+
+	list_for_each_entry_safe(lpfc_ncmd, lpfc_ncmd_next, post_nblist, list) {
+		list_del_init(&lpfc_ncmd->list);
+		block_cnt++;
+		if ((last_xritag != NO_XRI) &&
+		    (lpfc_ncmd->cur_iocbq.sli4_xritag != last_xritag + 1)) {
+			/* a hole in xri block, form a sgl posting block */
+			list_splice_init(&prep_nblist, &blck_nblist);
+			post_cnt = block_cnt - 1;
+			/* prepare list for next posting block */
+			list_add_tail(&lpfc_ncmd->list, &prep_nblist);
+			block_cnt = 1;
+		} else {
+			/* prepare list for next posting block */
+			list_add_tail(&lpfc_ncmd->list, &prep_nblist);
+			/* enough sgls for non-embed sgl mbox command */
+			if (block_cnt == LPFC_NEMBED_MBOX_SGL_CNT) {
+				list_splice_init(&prep_nblist, &blck_nblist);
+				post_cnt = block_cnt;
+				block_cnt = 0;
+			}
+		}
+		num_posting++;
+		last_xritag = lpfc_ncmd->cur_iocbq.sli4_xritag;
+
+		/* end of repost sgl list condition for NVME buffers */
+		if (num_posting == sb_count) {
+			if (post_cnt == 0) {
+				/* last sgl posting block */
+				list_splice_init(&prep_nblist, &blck_nblist);
+				post_cnt = block_cnt;
+			} else if (block_cnt == 1) {
+				/* last single sgl with non-contiguous xri */
+				if (sgl_size > SGL_PAGE_SIZE)
+					pdma_phys_sgl1 =
+						lpfc_ncmd->dma_phys_sgl +
+						SGL_PAGE_SIZE;
+				else
+					pdma_phys_sgl1 = 0;
+				cur_xritag = lpfc_ncmd->cur_iocbq.sli4_xritag;
+				status = lpfc_sli4_post_sgl(phba,
+						lpfc_ncmd->dma_phys_sgl,
+						pdma_phys_sgl1, cur_xritag);
+				if (status) {
+					/* failure, put on abort nvme list */
+					lpfc_ncmd->exch_busy = 1;
+				} else {
+					/* success, put on NVME buffer list */
+					lpfc_ncmd->exch_busy = 0;
+					lpfc_ncmd->status = IOSTAT_SUCCESS;
+					num_posted++;
+				}
+				/* success, put on NVME buffer sgl list */
+				list_add_tail(&lpfc_ncmd->list, &nvme_nblist);
+			}
+		}
+
+		/* continue until a nembed page worth of sgls */
+		if (post_cnt == 0)
+			continue;
+
+		/* post block of NVME buffer list sgls */
+		status = lpfc_sli4_post_nvme_sgl_block(phba, &blck_nblist,
+						       post_cnt);
+
+		/* don't reset xirtag due to hole in xri block */
+		if (block_cnt == 0)
+			last_xritag = NO_XRI;
+
+		/* reset NVME buffer post count for next round of posting */
+		post_cnt = 0;
+
+		/* put posted NVME buffer-sgl posted on NVME buffer sgl list */
+		while (!list_empty(&blck_nblist)) {
+			list_remove_head(&blck_nblist, lpfc_ncmd,
+					 struct lpfc_nvme_buf, list);
+			if (status) {
+				/* failure, put on abort nvme list */
+				lpfc_ncmd->exch_busy = 1;
+			} else {
+				/* success, put on NVME buffer list */
+				lpfc_ncmd->exch_busy = 0;
+				lpfc_ncmd->status = IOSTAT_SUCCESS;
+				num_posted++;
+			}
+			list_add_tail(&lpfc_ncmd->list, &nvme_nblist);
+		}
+	}
+	/* Push NVME buffers with sgl posted to the available list */
+	while (!list_empty(&nvme_nblist)) {
+		list_remove_head(&nvme_nblist, lpfc_ncmd,
+				 struct lpfc_nvme_buf, list);
+		lpfc_release_nvme_buf(phba, lpfc_ncmd);
+	}
+	return num_posted;
+}
+
+/**
+ * lpfc_repost_nvme_sgl_list - Repost all the allocated nvme buffer sgls
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine walks the list of nvme buffers that have been allocated and
+ * repost them to the port by using SGL block post. This is needed after a
+ * pci_function_reset/warm_start or start. The lpfc_hba_down_post_s4 routine
+ * is responsible for moving all nvme buffers on the lpfc_abts_nvme_sgl_list
+ * to the lpfc_nvme_buf_list. If the repost fails, reject all nvme buffers.
+ *
+ * Returns: 0 = success, non-zero failure.
+ **/
+int
+lpfc_repost_nvme_sgl_list(struct lpfc_hba *phba)
+{
+	LIST_HEAD(post_nblist);
+	int num_posted, rc = 0;
+
+	/* get all NVME buffers need to repost to a local list */
+	spin_lock_irq(&phba->nvme_buf_list_get_lock);
+	spin_lock(&phba->nvme_buf_list_put_lock);
+	list_splice_init(&phba->lpfc_nvme_buf_list_get, &post_nblist);
+	list_splice(&phba->lpfc_nvme_buf_list_put, &post_nblist);
+	spin_unlock(&phba->nvme_buf_list_put_lock);
+	spin_unlock_irq(&phba->nvme_buf_list_get_lock);
+
+	/* post the list of nvme buffer sgls to port if available */
+	if (!list_empty(&post_nblist)) {
+		num_posted = lpfc_post_nvme_sgl_list(phba, &post_nblist,
+						phba->sli4_hba.nvme_xri_cnt);
+		/* failed to post any nvme buffer, return error */
+		if (num_posted == 0)
+			rc = -EIO;
+	}
+	return rc;
+}
+
+/**
+ * lpfc_new_nvme_buf - Scsi buffer allocator for HBA with SLI4 IF spec
+ * @vport: The virtual port for which this call being executed.
+ * @num_to_allocate: The requested number of buffers to allocate.
+ *
+ * This routine allocates nvme buffers for device with SLI-4 interface spec,
+ * the nvme buffer contains all the necessary information needed to initiate
+ * a NVME I/O. After allocating up to @num_to_allocate NVME buffers and put
+ * them on a list, it post them to the port by using SGL block post.
+ *
+ * Return codes:
+ *   int - number of nvme buffers that were allocated and posted.
+ *   0 = failure, less than num_to_alloc is a partial failure.
+ **/
+static int
+lpfc_new_nvme_buf(struct lpfc_vport *vport, int num_to_alloc)
+{
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_nvme_buf *lpfc_ncmd;
+	struct lpfc_iocbq *pwqeq;
+	union lpfc_wqe128 *wqe;
+	struct sli4_sge *sgl;
+	dma_addr_t pdma_phys_sgl;
+	uint16_t iotag, lxri = 0;
+	int bcnt, num_posted, sgl_size;
+	LIST_HEAD(prep_nblist);
+	LIST_HEAD(post_nblist);
+	LIST_HEAD(nvme_nblist);
+
+	sgl_size = phba->cfg_sg_dma_buf_size;
+
+	for (bcnt = 0; bcnt < num_to_alloc; bcnt++) {
+		lpfc_ncmd = kzalloc(sizeof(struct lpfc_nvme_buf), GFP_KERNEL);
+		if (!lpfc_ncmd)
+			break;
+		/*
+		 * Get memory from the pci pool to map the virt space to
+		 * pci bus space for an I/O. The DMA buffer includes the
+		 * number of SGE's necessary to support the sg_tablesize.
+		 */
+		lpfc_ncmd->data = pci_pool_alloc(phba->lpfc_sg_dma_buf_pool,
+						 GFP_KERNEL,
+						 &lpfc_ncmd->dma_handle);
+		if (!lpfc_ncmd->data) {
+			kfree(lpfc_ncmd);
+			break;
+		}
+		memset(lpfc_ncmd->data, 0, phba->cfg_sg_dma_buf_size);
+
+		lxri = lpfc_sli4_next_xritag(phba);
+		if (lxri == NO_XRI) {
+			pci_pool_free(phba->lpfc_sg_dma_buf_pool,
+				      lpfc_ncmd->data, lpfc_ncmd->dma_handle);
+			kfree(lpfc_ncmd);
+			break;
+		}
+		pwqeq = &(lpfc_ncmd->cur_iocbq);
+		wqe = (union lpfc_wqe128 *)&pwqeq->wqe;
+
+		/* Allocate iotag for lpfc_ncmd->cur_iocbq. */
+		iotag = lpfc_sli_next_iotag(phba, pwqeq);
+		if (iotag == 0) {
+			pci_pool_free(phba->lpfc_sg_dma_buf_pool,
+				      lpfc_ncmd->data, lpfc_ncmd->dma_handle);
+			kfree(lpfc_ncmd);
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+					"6121 Failed to allocated IOTAG for"
+					" XRI:0x%x\n", lxri);
+			lpfc_sli4_free_xri(phba, lxri);
+			break;
+		}
+		pwqeq->sli4_lxritag = lxri;
+		pwqeq->sli4_xritag = phba->sli4_hba.xri_ids[lxri];
+		pwqeq->iocb_flag |= LPFC_IO_NVME;
+		pwqeq->context1 = lpfc_ncmd;
+		pwqeq->wqe_cmpl = lpfc_nvme_io_cmd_wqe_cmpl;
+
+		/* Initialize local short-hand pointers. */
+		lpfc_ncmd->nvme_sgl = lpfc_ncmd->data;
+		sgl = lpfc_ncmd->nvme_sgl;
+		pdma_phys_sgl = lpfc_ncmd->dma_handle;
+		lpfc_ncmd->dma_phys_sgl = pdma_phys_sgl;
+
+		/* Rsp SGE will be filled in when we rcv an IO
+		 * from the NVME Layer to be sent.
+		 * The cmd is going to be embedded so we need a SKIP SGE.
+		 */
+		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_SKIP);
+		bf_set(lpfc_sli4_sge_last, sgl, 0);
+		sgl->word2 = cpu_to_le32(sgl->word2);
+		/* Fill in word 3 / sgl_len during cmd submission */
+
+		lpfc_ncmd->cur_iocbq.context1 = lpfc_ncmd;
+
+		/* Word 7 */
+		bf_set(wqe_erp, &wqe->generic.wqe_com, 0);
+		/* NVME upper layers will time things out, if needed */
+		bf_set(wqe_tmo, &wqe->generic.wqe_com, 0);
+
+		/* Word 10 */
+		bf_set(wqe_ebde_cnt, &wqe->generic.wqe_com, 0);
+		bf_set(wqe_dbde, &wqe->generic.wqe_com, 1);
+
+		/* add the nvme buffer to a post list */
+		list_add_tail(&lpfc_ncmd->list, &post_nblist);
+		spin_lock_irq(&phba->nvme_buf_list_get_lock);
+		phba->sli4_hba.nvme_xri_cnt++;
+		spin_unlock_irq(&phba->nvme_buf_list_get_lock);
+	}
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME,
+			"6114 Allocate %d out of %d requested new NVME "
+			"buffers\n", bcnt, num_to_alloc);
+
+	/* post the list of nvme buffer sgls to port if available */
+	if (!list_empty(&post_nblist))
+		num_posted = lpfc_post_nvme_sgl_list(phba,
+						     &post_nblist, bcnt);
+	else
+		num_posted = 0;
+
+	return num_posted;
+}
+
+/**
+ * lpfc_get_nvme_buf - Get a nvme buffer from lpfc_nvme_buf_list of the HBA
+ * @phba: The HBA for which this call is being executed.
+ *
+ * This routine removes a nvme buffer from head of @phba lpfc_nvme_buf_list list
+ * and returns to caller.
+ *
+ * Return codes:
+ *   NULL - Error
+ *   Pointer to lpfc_nvme_buf - Success
+ **/
+static struct lpfc_nvme_buf *
+lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
+{
+	struct lpfc_nvme_buf *lpfc_ncmd, *lpfc_ncmd_next;
+	unsigned long iflag = 0;
+	int found = 0;
+
+	spin_lock_irqsave(&phba->nvme_buf_list_get_lock, iflag);
+	list_for_each_entry_safe(lpfc_ncmd, lpfc_ncmd_next,
+				 &phba->lpfc_nvme_buf_list_get, list) {
+		if (lpfc_test_rrq_active(phba, ndlp,
+					 lpfc_ncmd->cur_iocbq.sli4_lxritag))
+			continue;
+		list_del(&lpfc_ncmd->list);
+		found = 1;
+		break;
+	}
+	if (!found) {
+		spin_lock(&phba->nvme_buf_list_put_lock);
+		list_splice(&phba->lpfc_nvme_buf_list_put,
+			    &phba->lpfc_nvme_buf_list_get);
+		INIT_LIST_HEAD(&phba->lpfc_nvme_buf_list_put);
+		spin_unlock(&phba->nvme_buf_list_put_lock);
+		list_for_each_entry_safe(lpfc_ncmd, lpfc_ncmd_next,
+					 &phba->lpfc_nvme_buf_list_get, list) {
+			if (lpfc_test_rrq_active(
+				phba, ndlp, lpfc_ncmd->cur_iocbq.sli4_lxritag))
+				continue;
+			list_del(&lpfc_ncmd->list);
+			found = 1;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&phba->nvme_buf_list_get_lock, iflag);
+	if (!found)
+		return NULL;
+	return  lpfc_ncmd;
+}
+
+/**
+ * lpfc_release_nvme_buf: Return a nvme buffer back to hba nvme buf list.
+ * @phba: The Hba for which this call is being executed.
+ * @lpfc_ncmd: The nvme buffer which is being released.
+ *
+ * This routine releases @lpfc_ncmd nvme buffer by adding it to tail of @phba
+ * lpfc_nvme_buf_list list. For SLI4 XRI's are tied to the nvme buffer
+ * and cannot be reused for at least RA_TOV amount of time if it was
+ * aborted.
+ **/
+static void
+lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd)
+{
+	unsigned long iflag = 0;
+
+	lpfc_ncmd->nonsg_phys = 0;
+	if (lpfc_ncmd->exch_busy) {
+		spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock,
+					iflag);
+		lpfc_ncmd->nvmeCmd = NULL;
+		list_add_tail(&lpfc_ncmd->list,
+			&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+		spin_unlock_irqrestore(&phba->sli4_hba.abts_nvme_buf_list_lock,
+					iflag);
+	} else {
+		lpfc_ncmd->nvmeCmd = NULL;
+		lpfc_ncmd->cur_iocbq.iocb_flag = LPFC_IO_NVME;
+		spin_lock_irqsave(&phba->nvme_buf_list_put_lock, iflag);
+		list_add_tail(&lpfc_ncmd->list, &phba->lpfc_nvme_buf_list_put);
+		spin_unlock_irqrestore(&phba->nvme_buf_list_put_lock, iflag);
+	}
+}
+
+/**
+ * lpfc_nvme_create_localport - Create/Bind an nvme localport instance.
+ * @pvport - the lpfc_vport instance requesting a localport.
+ *
+ * This routine is invoked to create an nvme localport instance to bind
+ * to the nvme_fc_transport.  It is called once during driver load
+ * like lpfc_create_shost after all other services are initialized.
+ * It requires a vport, vpi, and wwns at call time.  Other localport
+ * parameters are modified as the driver's FCID and the Fabric WWN
+ * are established.
+ *
+ * Return codes
+ *      0 - successful
+ *      -ENOMEM - no heap memory available
+ *      other values - from nvme registration upcall
+ **/
+int
+lpfc_nvme_create_localport(struct lpfc_vport *vport)
+{
+	struct lpfc_hba  *phba = vport->phba;
+	struct nvme_fc_port_info nfcp_info;
+	struct nvme_fc_local_port *localport;
+	struct lpfc_nvme_lport *lport;
+	int len, ret = 0;
+
+	/* Initialize this localport instance.  The vport wwn usage ensures
+	 * that NPIV is accounted for.
+	 */
+	memset(&nfcp_info, 0, sizeof(struct nvme_fc_port_info));
+	nfcp_info.port_role = FC_PORT_ROLE_NVME_INITIATOR;
+	nfcp_info.node_name = wwn_to_u64(vport->fc_nodename.u.wwn);
+	nfcp_info.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
+
+	/* For now need + 1 to get around NVME transport logic */
+	lpfc_nvme_template.max_sgl_segments = phba->cfg_sg_seg_cnt + 1;
+	lpfc_nvme_template.max_hw_queues = phba->cfg_nvme_io_channel;
+
+	/* localport is allocated from the stack, but the registration
+	 * call allocates heap memory as well as the private area.
+	 */
+	ret = nvme_fc_register_localport(&nfcp_info, &lpfc_nvme_template,
+					 &vport->phba->pcidev->dev, &localport);
+	if (!ret) {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_NVME_DISC,
+				 "6005 Successfully registered local "
+				 "NVME port num %d, localP %p, private %p, "
+				 "sg_seg %d\n",
+				 localport->port_num, localport,
+				 localport->private,
+				 lpfc_nvme_template.max_sgl_segments);
+
+		/* Private is our lport size declared in the template. */
+		lport = (struct lpfc_nvme_lport *)localport->private;
+		vport->localport = localport;
+		lport->vport = vport;
+		INIT_LIST_HEAD(&lport->rport_list);
+		vport->nvmei_support = 1;
+	}
+
+	len  = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
+	vport->phba->total_nvme_bufs += len;
+	return ret;
+}
+
+/**
+ * lpfc_nvme_destroy_localport - Destroy lpfc_nvme bound to nvme transport.
+ * @pnvme: pointer to lpfc nvme data structure.
+ *
+ * This routine is invoked to destroy all lports bound to the phba.
+ * The lport memory was allocated by the nvme fc transport and is
+ * released there.  This routine ensures all rports bound to the
+ * lport have been disconnected.
+ *
+ **/
+void
+lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
+{
+	struct nvme_fc_local_port *localport;
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_nvme_rport *rport = NULL, *rport_next = NULL;
+	int ret;
+
+	if (vport->nvmei_support == 0)
+		return;
+
+	localport = vport->localport;
+	vport->localport = NULL;
+	lport = (struct lpfc_nvme_lport *)localport->private;
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
+			 "6011 Destroying NVME localport %p\n",
+			 localport);
+
+	list_for_each_entry_safe(rport, rport_next, &lport->rport_list, list) {
+		/* The last node ref has to get released now before the rport
+		 * private memory area is released by the transport.
+		 */
+		list_del(&rport->list);
+
+		init_completion(&rport->rport_unreg_done);
+		ret = nvme_fc_unregister_remoteport(rport->remoteport);
+		if (ret)
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+					 "6008 rport fail destroy %x\n", ret);
+		wait_for_completion_timeout(&rport->rport_unreg_done, 5);
+	}
+	/* lport's rport list is clear.  Unregister
+	 * lport and release resources.
+	 */
+	init_completion(&lport->lport_unreg_done);
+	ret = nvme_fc_unregister_localport(localport);
+	wait_for_completion_timeout(&lport->lport_unreg_done, 5);
+
+	/* Regardless of the unregister upcall response, clear
+	 * nvmei_support.  All rports are unregistered and the
+	 * driver will clean up.
+	 */
+	vport->nvmei_support = 0;
+	if (ret == 0) {
+		lpfc_printf_vlog(vport,
+				 KERN_INFO, LOG_NVME_DISC,
+				 "6009 Unregistered lport Success\n");
+	} else {
+		lpfc_printf_vlog(vport,
+				 KERN_INFO, LOG_NVME_DISC,
+				 "6010 Unregistered lport "
+				 "Failed, status x%x\n",
+				 ret);
+	}
+}
+
+void
+lpfc_nvme_update_localport(struct lpfc_vport *vport)
+{
+	struct nvme_fc_local_port *localport;
+	struct lpfc_nvme_lport *lport;
+
+	localport = vport->localport;
+	lport = (struct lpfc_nvme_lport *)localport->private;
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
+			 "6012 Update NVME lport %p did x%x\n",
+			 localport, vport->fc_myDID);
+
+	localport->port_id = vport->fc_myDID;
+	if (localport->port_id == 0)
+		localport->port_role = FC_PORT_ROLE_NVME_DISCOVERY;
+	else
+		localport->port_role = FC_PORT_ROLE_NVME_INITIATOR;
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+			 "6030 bound lport %p to DID x%06x\n",
+			 lport, localport->port_id);
+
+}
+
+int
+lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
+{
+	int ret = 0;
+	struct nvme_fc_local_port *localport;
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_nvme_rport *rport;
+	struct nvme_fc_remote_port *remote_port;
+	struct nvme_fc_port_info rpinfo;
+
+	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NVME_DISC,
+			 "6006 Register NVME PORT. DID x%06x nlptype x%x\n",
+			 ndlp->nlp_DID, ndlp->nlp_type);
+
+	localport = vport->localport;
+	lport = (struct lpfc_nvme_lport *)localport->private;
+
+	if (ndlp->nlp_type & (NLP_NVME_TARGET | NLP_NVME_INITIATOR)) {
+
+		/* The driver isn't expecting the rport wwn to change
+		 * but it might get a different DID on a different
+		 * fabric.
+		 */
+		list_for_each_entry(rport, &lport->rport_list, list) {
+			if (rport->remoteport->port_name !=
+			    wwn_to_u64(ndlp->nlp_portname.u.wwn))
+				continue;
+			lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NVME_DISC,
+					 "6035 lport %p, found matching rport "
+					 "at wwpn 0x%llx, Data: x%x x%x x%x "
+					 "x%06x\n",
+					 lport,
+					 rport->remoteport->port_name,
+					 rport->remoteport->port_id,
+					 rport->remoteport->port_role,
+					 ndlp->nlp_type,
+					 ndlp->nlp_DID);
+			remote_port = rport->remoteport;
+			if ((remote_port->port_id == 0) &&
+			    (remote_port->port_role ==
+			     FC_PORT_ROLE_NVME_DISCOVERY)) {
+				remote_port->port_id = ndlp->nlp_DID;
+				remote_port->port_role &=
+					~FC_PORT_ROLE_NVME_DISCOVERY;
+				if (ndlp->nlp_type & NLP_NVME_TARGET)
+					remote_port->port_role |=
+						FC_PORT_ROLE_NVME_TARGET;
+				if (ndlp->nlp_type & NLP_NVME_INITIATOR)
+					remote_port->port_role |=
+						FC_PORT_ROLE_NVME_INITIATOR;
+
+				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
+						 LOG_NVME_DISC,
+						 "6014 Rebinding lport to "
+						 "rport wwpn 0x%llx, "
+						 "Data: x%x x%x x%x x%06x\n",
+						 remote_port->port_name,
+						 remote_port->port_id,
+						 remote_port->port_role,
+						 ndlp->nlp_type,
+						 ndlp->nlp_DID);
+			}
+			return 0;
+		}
+
+		/* NVME rports are not preserved across devloss.
+		 * Just register this instance.
+		 */
+		rpinfo.port_id = ndlp->nlp_DID;
+		rpinfo.port_role = 0;
+		if (ndlp->nlp_type & NLP_NVME_TARGET)
+			rpinfo.port_role |= FC_PORT_ROLE_NVME_TARGET;
+		if (ndlp->nlp_type & NLP_NVME_INITIATOR)
+			rpinfo.port_role |= FC_PORT_ROLE_NVME_INITIATOR;
+		rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn);
+		rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn);
+
+		ret = nvme_fc_register_remoteport(localport, &rpinfo,
+						  &remote_port);
+		if (!ret) {
+			rport = remote_port->private;
+			rport->remoteport = remote_port;
+			rport->lport = lport;
+			rport->ndlp = lpfc_nlp_get(ndlp);
+			if (!rport->ndlp)
+				return -1;
+			ndlp->nrport = rport;
+			INIT_LIST_HEAD(&rport->list);
+			list_add_tail(&rport->list, &lport->rport_list);
+			lpfc_printf_vlog(vport, KERN_INFO,
+					 LOG_NVME_DISC | LOG_NODE,
+					 "6022 Binding new rport to lport %p "
+					 "Rport WWNN 0x%llx, Rport WWPN 0x%llx "
+					 "DID x%06x Role x%x\n",
+					 lport,
+					 rpinfo.node_name, rpinfo.port_name,
+					 rpinfo.port_id, rpinfo.port_role);
+		} else {
+			lpfc_printf_vlog(vport, KERN_ERR,
+					 LOG_NVME_DISC | LOG_NODE,
+					 "6031 RemotePort Registration failed "
+					 "err: %d, DID x%06x\n",
+					 ret, ndlp->nlp_DID);
+		}
+	} else {
+		ret = -EINVAL;
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+				 "6027 Unknown nlp_type x%x on DID x%06x "
+				 "ndlp %p.  Not Registering nvme rport\n",
+				 ndlp->nlp_type, ndlp->nlp_DID, ndlp);
+	}
+	return ret;
+}
+
+/* lpfc_nvme_unregister_port - unbind the DID and port_role from this rport.
+ *
+ * There is no notion of Devloss or rport recovery from the current
+ * nvme_transport perspective.  Loss of an rport just means IO cannot
+ * be sent and recovery is completely up to the initator.
+ * For now, the driver just unbinds the DID and port_role so that
+ * no further IO can be issued.  Changes are planned for later.
+ *
+ * Notes - the ndlp reference count is not decremented here since
+ * since there is no nvme_transport api for devloss.  Node ref count
+ * is only adjusted in driver unload.
+ */
+void
+lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
+{
+	int ret;
+	struct nvme_fc_local_port *localport;
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_nvme_rport *rport;
+	struct nvme_fc_remote_port *remoteport;
+
+	localport = vport->localport;
+
+	/* This is fundamental error.  The localport is always
+	 * available until driver unload.  Just exit.
+	 */
+	if (!localport)
+		return;
+
+	lport = (struct lpfc_nvme_lport *)localport->private;
+	if (!lport)
+		goto input_err;
+
+	rport = ndlp->nrport;
+	if (!rport)
+		goto input_err;
+
+	remoteport = rport->remoteport;
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
+			 "6033 Unreg nvme remoteport %p, portname x%llx, "
+			 "port_id x%06x, portstate x%x port type x%x\n",
+			 remoteport, remoteport->port_name,
+			 remoteport->port_id, remoteport->port_state,
+			 ndlp->nlp_type);
+
+	/* Sanity check ndlp type.  Only call for NVME ports. Don't
+	 * clear any rport state until the transport calls back.
+	 */
+	if (ndlp->nlp_type & (NLP_NVME_TARGET | NLP_NVME_INITIATOR)) {
+		init_completion(&rport->rport_unreg_done);
+		ret = nvme_fc_unregister_remoteport(remoteport);
+		if (ret != 0) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+					 "6167 NVME unregister failed %d "
+					 "port_state x%x\n",
+					 ret, remoteport->port_state);
+		}
+
+		/* Wait for the driver's delete completion routine to finish
+		 * before proceeding.  This guarantees the transport and driver
+		 * have completed the unreg process.
+		 */
+		ret = wait_for_completion_timeout(&rport->rport_unreg_done, 5);
+		if (ret == 0) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+					 "6169 Unreg nvme wait failed %d\n",
+					 ret);
+		}
+	}
+	return;
+
+ input_err:
+	lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
+			 "6168: State error: lport %p, rport%p FCID x%06x\n",
+			 vport->localport, ndlp->rport, ndlp->nlp_DID);
+}
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index 2b167933fd26..4cc51086a5f7 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -29,6 +29,12 @@
 
 #define LPFC_NVME_ERSP_LEN		0x20
 
+struct lpfc_nvme_qhandle {
+	uint32_t index;		/* WQ index to use */
+	uint32_t qidx;		/* queue index passed to create */
+	uint32_t cpu_id;	/* current cpu id at time of create */
+};
+
 /* Declare nvme-based local and remote port definitions. */
 struct lpfc_nvme_lport {
 	struct lpfc_vport *vport;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 52fa5c77f3bc..ccda1f73ae84 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -6795,6 +6795,22 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		}
 	}
 
+	if ((phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) &&
+	    (phba->nvmet_support == 0)) {
+
+		/* register the allocated nvme sgl pool to the port */
+		rc = lpfc_repost_nvme_sgl_list(phba);
+		if (unlikely(rc)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"6116 Error %d during nvme sgl post "
+					"operation\n", rc);
+			/* Some NVME buffers were moved to abort nvme list */
+			/* A pci function reset will repost them */
+			rc = -ENODEV;
+			goto out_destroy_queue;
+		}
+	}
+
 	/* Post the rpi header region to the device. */
 	rc = lpfc_sli4_post_all_rpi_hdrs(phba);
 	if (unlikely(rc)) {
@@ -10492,10 +10508,7 @@ lpfc_sli4_abort_nvme_io(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
 	abtsiocbp->iocb_flag |= LPFC_IO_NVME;
 	abtsiocbp->vport = vport;
-	/* todo: assign wqe_cmpl to lpfc_nvme_abort_fcreq_cmpl
-	 * subsequent patch will add routine. For now, just skip assignment
-	 * as won't ever be called.
-	 */
+	abtsiocbp->wqe_cmpl = lpfc_nvme_abort_fcreq_cmpl;
 	retval = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abtsiocbp);
 	if (retval == IOCB_ERROR) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index b5b4f6b843c0..9cb8508b4b4b 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -753,6 +753,7 @@ int lpfc_sli4_queue_setup(struct lpfc_hba *);
 void lpfc_sli4_queue_unset(struct lpfc_hba *);
 int lpfc_sli4_post_sgl(struct lpfc_hba *, dma_addr_t, dma_addr_t, uint16_t);
 int lpfc_sli4_repost_scsi_sgl_list(struct lpfc_hba *);
+int lpfc_repost_nvme_sgl_list(struct lpfc_hba *phba);
 uint16_t lpfc_sli4_next_xritag(struct lpfc_hba *);
 void lpfc_sli4_free_xri(struct lpfc_hba *, int);
 int lpfc_sli4_post_async_mbox(struct lpfc_hba *);
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 07c7c5f9fdde..b0d94f2e5b44 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -403,7 +403,21 @@ lpfc_vport_create(struct fc_vport *fc_vport, bool disable)
 		vport->fdmi_port_mask = phba->pport->fdmi_port_mask;
 	}
 
-	/* todo: init: register port with nvme */
+	if ((phba->nvmet_support == 0) &&
+	    ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
+	     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))) {
+		/* Create NVME binding with nvme_fc_transport. This
+		 * ensures the vport is initialized.
+		 */
+		rc = lpfc_nvme_create_localport(vport);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6003 %s status x%x\n",
+					"NVME registration failed, ",
+					rc);
+			goto error_out;
+		}
+	}
 
 	/*
 	 * In SLI4, the vpi must be activated before it can be used
-- 
GitLab


From bd2cdd5e400f5914bc30d5cfb0a0185cf51e4424 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:33 -0800
Subject: [PATCH 148/898] scsi: lpfc: NVME Initiator: Add debugfs support

NVME Initiator: Add debugfs support

Adds debugfs snippets to cover the new NVME initiator functionality

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h         |   55 ++
 drivers/scsi/lpfc/lpfc_crtn.h    |    6 +-
 drivers/scsi/lpfc/lpfc_ct.c      |   27 +-
 drivers/scsi/lpfc/lpfc_debugfs.c | 1160 +++++++++++++++++++++++++++---
 drivers/scsi/lpfc/lpfc_debugfs.h |   21 +
 drivers/scsi/lpfc/lpfc_nvme.c    |  143 ++++
 drivers/scsi/lpfc/lpfc_nvme.h    |    7 +
 drivers/scsi/lpfc/lpfc_sli.c     |    5 +
 8 files changed, 1300 insertions(+), 124 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 9ad63a47425b..fdb314b3282d 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -458,6 +458,9 @@ struct lpfc_vport {
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	struct dentry *debug_disc_trc;
 	struct dentry *debug_nodelist;
+	struct dentry *debug_nvmestat;
+	struct dentry *debug_nvmektime;
+	struct dentry *debug_cpucheck;
 	struct dentry *vport_debugfs_root;
 	struct lpfc_debugfs_trc *disc_trc;
 	atomic_t disc_trc_cnt;
@@ -984,6 +987,12 @@ struct lpfc_hba {
 	struct dentry *debug_readApp;    /* inject read app_tag errors */
 	struct dentry *debug_readRef;    /* inject read ref_tag errors */
 
+	struct dentry *debug_nvmeio_trc;
+	struct lpfc_debugfs_nvmeio_trc *nvmeio_trc;
+	atomic_t nvmeio_trc_cnt;
+	uint32_t nvmeio_trc_size;
+	uint32_t nvmeio_trc_output_idx;
+
 	/* T10 DIF error injection */
 	uint32_t lpfc_injerr_wgrd_cnt;
 	uint32_t lpfc_injerr_wapp_cnt;
@@ -1011,6 +1020,7 @@ struct lpfc_hba {
 	struct dentry *idiag_ext_acc;
 	uint8_t lpfc_idiag_last_eq;
 #endif
+	uint16_t nvmeio_trc_on;
 
 	/* Used for deferred freeing of ELS data buffers */
 	struct list_head elsbuf;
@@ -1083,6 +1093,51 @@ struct lpfc_hba {
 #define LPFC_TRANSGRESSION_LOW_RXPOWER		0x4000
 	uint16_t sfp_alarm;
 	uint16_t sfp_warning;
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+#define LPFC_CHECK_CPU_CNT    32
+	uint32_t cpucheck_rcv_io[LPFC_CHECK_CPU_CNT];
+	uint32_t cpucheck_xmt_io[LPFC_CHECK_CPU_CNT];
+	uint32_t cpucheck_cmpl_io[LPFC_CHECK_CPU_CNT];
+	uint32_t cpucheck_ccmpl_io[LPFC_CHECK_CPU_CNT];
+	uint16_t cpucheck_on;
+#define LPFC_CHECK_OFF		0
+#define LPFC_CHECK_NVME_IO	1
+	uint16_t ktime_on;
+	uint64_t ktime_data_samples;
+	uint64_t ktime_status_samples;
+	uint64_t ktime_last_cmd;
+	uint64_t ktime_seg1_total;
+	uint64_t ktime_seg1_min;
+	uint64_t ktime_seg1_max;
+	uint64_t ktime_seg2_total;
+	uint64_t ktime_seg2_min;
+	uint64_t ktime_seg2_max;
+	uint64_t ktime_seg3_total;
+	uint64_t ktime_seg3_min;
+	uint64_t ktime_seg3_max;
+	uint64_t ktime_seg4_total;
+	uint64_t ktime_seg4_min;
+	uint64_t ktime_seg4_max;
+	uint64_t ktime_seg5_total;
+	uint64_t ktime_seg5_min;
+	uint64_t ktime_seg5_max;
+	uint64_t ktime_seg6_total;
+	uint64_t ktime_seg6_min;
+	uint64_t ktime_seg6_max;
+	uint64_t ktime_seg7_total;
+	uint64_t ktime_seg7_min;
+	uint64_t ktime_seg7_max;
+	uint64_t ktime_seg8_total;
+	uint64_t ktime_seg8_min;
+	uint64_t ktime_seg8_max;
+	uint64_t ktime_seg9_total;
+	uint64_t ktime_seg9_min;
+	uint64_t ktime_seg9_max;
+	uint64_t ktime_seg10_total;
+	uint64_t ktime_seg10_min;
+	uint64_t ktime_seg10_max;
+#endif
 };
 
 static inline struct Scsi_Host *
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index a9c8a0a41b16..4a0db3895993 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -393,9 +393,11 @@ void lpfc_host_attrib_init(struct Scsi_Host *);
 extern void lpfc_debugfs_initialize(struct lpfc_vport *);
 extern void lpfc_debugfs_terminate(struct lpfc_vport *);
 extern void lpfc_debugfs_disc_trc(struct lpfc_vport *, int, char *, uint32_t,
-	uint32_t, uint32_t);
+				  uint32_t, uint32_t);
 extern void lpfc_debugfs_slow_ring_trc(struct lpfc_hba *, char *, uint32_t,
-	uint32_t, uint32_t);
+				       uint32_t, uint32_t);
+extern void lpfc_debugfs_nvme_trc(struct lpfc_hba *phba, char *fmt,
+				uint16_t data1, uint16_t data2, uint32_t data3);
 extern struct lpfc_hbq_init *lpfc_hbq_defs[];
 
 /* SLI4 if_type 2 externs. */
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 8cfeffe312e0..2c051369857a 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -465,6 +465,10 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 		ndlp = lpfc_setup_disc_node(vport, Did);
 
 		if (ndlp && NLP_CHK_NODE_ACT(ndlp)) {
+			lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_CT,
+				"Parse GID_FTrsp: did:x%x flg:x%x x%x",
+				Did, ndlp->nlp_flag, vport->fc_flag);
+
 			/* By default, the driver expects to support FCP FC4 */
 			if (fc4_type == FC_TYPE_FCP)
 				ndlp->nlp_fc4_type |= NLP_FC4_FCP;
@@ -478,16 +482,24 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 					 ndlp->nlp_flag, ndlp->nlp_fc4_type,
 					 vport->fc_flag,
 					 vport->fc_rscn_id_cnt);
-		} else
+		} else {
+			lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_CT,
+				"Skip1 GID_FTrsp: did:x%x flg:x%x cnt:%d",
+				Did, vport->fc_flag, vport->fc_rscn_id_cnt);
+
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "0239 Skip x%06x NameServer Rsp "
 					 "Data: x%x x%x\n", Did,
 					 vport->fc_flag,
 					 vport->fc_rscn_id_cnt);
-
+		}
 	} else {
 		if (!(vport->fc_flag & FC_RSCN_MODE) ||
 		    lpfc_rscn_payload_check(vport, Did)) {
+			lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_CT,
+				"Query GID_FTrsp: did:x%x flg:x%x cnt:%d",
+				Did, vport->fc_flag, vport->fc_rscn_id_cnt);
+
 			/*
 			 * This NPortID was previously a FCP target,
 			 * Don't even bother to send GFF_ID.
@@ -509,12 +521,17 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 				else
 					lpfc_setup_disc_node(vport, Did);
 			}
-		} else
+		} else {
+			lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_CT,
+				"Skip2 GID_FTrsp: did:x%x flg:x%x cnt:%d",
+				Did, vport->fc_flag, vport->fc_rscn_id_cnt);
+
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "0245 Skip x%06x NameServer Rsp "
 					 "Data: x%x x%x\n", Did,
 					 vport->fc_flag,
 					 vport->fc_rscn_id_cnt);
+		}
 	}
 }
 
@@ -892,6 +909,10 @@ lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	did = ((struct lpfc_sli_ct_request *)inp->virt)->un.gft.PortId;
 	did = be32_to_cpu(did);
 
+	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_CT,
+			      "GFT_ID cmpl: status:x%x/x%x did:x%x",
+			      irsp->ulpStatus, irsp->un.ulpWord[4], did);
+
 	if (irsp->ulpStatus == IOSTAT_SUCCESS) {
 		/* Good status, continue checking */
 		CTrsp = (struct lpfc_sli_ct_request *)outp->virt;
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index d9bbebe8eb37..3fcba26623eb 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -34,6 +34,9 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/fc/fc_fs.h>
+
+#include <linux/nvme-fc-driver.h>
 
 #include "lpfc_hw4.h"
 #include "lpfc_hw.h"
@@ -41,8 +44,9 @@
 #include "lpfc_sli4.h"
 #include "lpfc_nl.h"
 #include "lpfc_disc.h"
-#include "lpfc_scsi.h"
 #include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
@@ -99,6 +103,12 @@ module_param(lpfc_debugfs_max_slow_ring_trc, int, S_IRUGO);
 MODULE_PARM_DESC(lpfc_debugfs_max_slow_ring_trc,
 	"Set debugfs slow ring trace depth");
 
+/* This MUST be a power of 2 */
+static int lpfc_debugfs_max_nvmeio_trc;
+module_param(lpfc_debugfs_max_nvmeio_trc, int, 0444);
+MODULE_PARM_DESC(lpfc_debugfs_max_nvmeio_trc,
+		 "Set debugfs NVME IO trace depth");
+
 static int lpfc_debugfs_mask_disc_trc;
 module_param(lpfc_debugfs_mask_disc_trc, int, S_IRUGO);
 MODULE_PARM_DESC(lpfc_debugfs_mask_disc_trc,
@@ -535,6 +545,10 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 	struct lpfc_nodelist *ndlp;
 	unsigned char *statep;
+	struct nvme_fc_local_port *localport;
+	struct lpfc_nvme_lport *lport;
+	struct lpfc_nvme_rport *rport;
+	struct nvme_fc_remote_port *nrport;
 
 	cnt = (LPFC_NODELIST_SIZE / LPFC_NODELIST_ENTRY_SIZE);
 
@@ -612,6 +626,358 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 	}
 	spin_unlock_irq(shost->host_lock);
 
+	len += snprintf(buf + len, size - len,
+				"\nNVME Lport/Rport Entries ...\n");
+
+	localport = vport->localport;
+	if (!localport)
+		goto out_exit;
+
+	spin_lock_irq(shost->host_lock);
+	lport = (struct lpfc_nvme_lport *)localport->private;
+
+	/* Port state is only one of two values for now. */
+	if (localport->port_id)
+		statep = "ONLINE";
+	else
+		statep = "UNKNOWN ";
+
+	len += snprintf(buf + len, size - len,
+			"Lport DID x%06x PortState %s\n",
+			localport->port_id, statep);
+
+	len += snprintf(buf + len, size - len, "\tRport List:\n");
+	list_for_each_entry(rport, &lport->rport_list, list) {
+		/* local short-hand pointer. */
+		nrport = rport->remoteport;
+
+		/* Port state is only one of two values for now. */
+		switch (nrport->port_state) {
+		case FC_OBJSTATE_ONLINE:
+			statep = "ONLINE";
+			break;
+		case FC_OBJSTATE_UNKNOWN:
+			statep = "UNKNOWN ";
+			break;
+		default:
+			statep = "UNSUPPORTED";
+			break;
+		}
+
+		/* Tab in to show lport ownership. */
+		len += snprintf(buf + len, size - len,
+				"\t%s Port ID:x%06x ",
+				statep, nrport->port_id);
+		len += snprintf(buf + len, size - len, "WWPN x%llx ",
+				nrport->port_name);
+		len += snprintf(buf + len, size - len, "WWNN x%llx ",
+				nrport->node_name);
+		switch (nrport->port_role) {
+		case FC_PORT_ROLE_NVME_INITIATOR:
+			len +=  snprintf(buf + len, size - len,
+					 "NVME INITIATOR ");
+			break;
+		case FC_PORT_ROLE_NVME_TARGET:
+			len +=  snprintf(buf + len, size - len,
+					 "NVME TARGET ");
+			break;
+		case FC_PORT_ROLE_NVME_DISCOVERY:
+			len +=  snprintf(buf + len, size - len,
+					 "NVME DISCOVERY ");
+			break;
+		default:
+			len +=  snprintf(buf + len, size - len,
+					 "UNKNOWN ROLE x%x",
+					 nrport->port_role);
+			break;
+		}
+
+		/* Terminate the string. */
+		len +=  snprintf(buf + len, size - len, "\n");
+	}
+
+	spin_unlock_irq(shost->host_lock);
+ out_exit:
+	return len;
+}
+
+/**
+ * lpfc_debugfs_nvmestat_data - Dump target node list to a buffer
+ * @vport: The vport to gather target node info from.
+ * @buf: The buffer to dump log into.
+ * @size: The maximum amount of data to process.
+ *
+ * Description:
+ * This routine dumps the NVME statistics associated with @vport
+ *
+ * Return Value:
+ * This routine returns the amount of bytes that were dumped into @buf and will
+ * not exceed @size.
+ **/
+static int
+lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
+{
+	struct lpfc_hba   *phba = vport->phba;
+	int len = 0;
+
+	if (phba->nvmet_support == 0) {
+		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+			return len;
+
+		len += snprintf(buf + len, size - len,
+				"\nNVME Lport Statistics\n");
+
+		len += snprintf(buf + len, size - len,
+				"LS: Xmt %016llx Cmpl %016llx\n",
+				phba->fc4NvmeLsRequests,
+				phba->fc4NvmeLsCmpls);
+
+		len += snprintf(buf + len, size - len,
+				"FCP: Rd %016llx Wr %016llx IO %016llx\n",
+				phba->fc4NvmeInputRequests,
+				phba->fc4NvmeOutputRequests,
+				phba->fc4NvmeControlRequests);
+
+		len += snprintf(buf + len, size - len,
+				"    Cmpl %016llx\n", phba->fc4NvmeIoCmpls);
+	}
+
+	return len;
+}
+
+
+/**
+ * lpfc_debugfs_nvmektime_data - Dump target node list to a buffer
+ * @vport: The vport to gather target node info from.
+ * @buf: The buffer to dump log into.
+ * @size: The maximum amount of data to process.
+ *
+ * Description:
+ * This routine dumps the NVME statistics associated with @vport
+ *
+ * Return Value:
+ * This routine returns the amount of bytes that were dumped into @buf and will
+ * not exceed @size.
+ **/
+static int
+lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
+{
+	struct lpfc_hba   *phba = vport->phba;
+	int len = 0;
+
+	if (phba->nvmet_support == 0) {
+		/* NVME Initiator */
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"ktime %s: Total Samples: %lld\n",
+				(phba->ktime_on ?  "Enabled" : "Disabled"),
+				phba->ktime_data_samples);
+		if (phba->ktime_data_samples == 0)
+			return len;
+
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"Segment 1: Last NVME Cmd cmpl "
+			"done -to- Start of next NVME cnd (in driver)\n");
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg1_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg1_min,
+			phba->ktime_seg1_max);
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"Segment 2: Driver start of NVME cmd "
+			"-to- Firmware WQ doorbell\n");
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg2_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg2_min,
+			phba->ktime_seg2_max);
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"Segment 3: Firmware WQ doorbell -to- "
+			"MSI-X ISR cmpl\n");
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg3_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg3_min,
+			phba->ktime_seg3_max);
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"Segment 4: MSI-X ISR cmpl -to- "
+			"NVME cmpl done\n");
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg4_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg4_min,
+			phba->ktime_seg4_max);
+		len += snprintf(
+			buf + len, PAGE_SIZE - len,
+			"Total IO avg time: %08lld\n",
+			((phba->ktime_seg1_total +
+			phba->ktime_seg2_total  +
+			phba->ktime_seg3_total +
+			phba->ktime_seg4_total) /
+			phba->ktime_data_samples));
+		return len;
+	}
+
+	return len;
+}
+
+/**
+ * lpfc_debugfs_nvmeio_trc_data - Dump NVME IO trace list to a buffer
+ * @phba: The phba to gather target node info from.
+ * @buf: The buffer to dump log into.
+ * @size: The maximum amount of data to process.
+ *
+ * Description:
+ * This routine dumps the NVME IO trace associated with @phba
+ *
+ * Return Value:
+ * This routine returns the amount of bytes that were dumped into @buf and will
+ * not exceed @size.
+ **/
+static int
+lpfc_debugfs_nvmeio_trc_data(struct lpfc_hba *phba, char *buf, int size)
+{
+	struct lpfc_debugfs_nvmeio_trc *dtp;
+	int i, state, index, skip;
+	int len = 0;
+
+	state = phba->nvmeio_trc_on;
+
+	index = (atomic_read(&phba->nvmeio_trc_cnt) + 1) &
+		(phba->nvmeio_trc_size - 1);
+	skip = phba->nvmeio_trc_output_idx;
+
+	len += snprintf(buf + len, size - len,
+			"%s IO Trace %s: next_idx %d skip %d size %d\n",
+			(phba->nvmet_support ? "NVME" : "NVMET"),
+			(state ? "Enabled" : "Disabled"),
+			index, skip, phba->nvmeio_trc_size);
+
+	if (!phba->nvmeio_trc || state)
+		return len;
+
+	/* trace MUST bhe off to continue */
+
+	for (i = index; i < phba->nvmeio_trc_size; i++) {
+		if (skip) {
+			skip--;
+			continue;
+		}
+		dtp = phba->nvmeio_trc + i;
+		phba->nvmeio_trc_output_idx++;
+
+		if (!dtp->fmt)
+			continue;
+
+		len +=  snprintf(buf + len, size - len, dtp->fmt,
+			dtp->data1, dtp->data2, dtp->data3);
+
+		if (phba->nvmeio_trc_output_idx >= phba->nvmeio_trc_size) {
+			phba->nvmeio_trc_output_idx = 0;
+			len += snprintf(buf + len, size - len,
+					"Trace Complete\n");
+			goto out;
+		}
+
+		if (len >= (size - LPFC_DEBUG_OUT_LINE_SZ)) {
+			len += snprintf(buf + len, size - len,
+					"Trace Continue (%d of %d)\n",
+					phba->nvmeio_trc_output_idx,
+					phba->nvmeio_trc_size);
+			goto out;
+		}
+	}
+	for (i = 0; i < index; i++) {
+		if (skip) {
+			skip--;
+			continue;
+		}
+		dtp = phba->nvmeio_trc + i;
+		phba->nvmeio_trc_output_idx++;
+
+		if (!dtp->fmt)
+			continue;
+
+		len +=  snprintf(buf + len, size - len, dtp->fmt,
+			dtp->data1, dtp->data2, dtp->data3);
+
+		if (phba->nvmeio_trc_output_idx >= phba->nvmeio_trc_size) {
+			phba->nvmeio_trc_output_idx = 0;
+			len += snprintf(buf + len, size - len,
+					"Trace Complete\n");
+			goto out;
+		}
+
+		if (len >= (size - LPFC_DEBUG_OUT_LINE_SZ)) {
+			len += snprintf(buf + len, size - len,
+					"Trace Continue (%d of %d)\n",
+					phba->nvmeio_trc_output_idx,
+					phba->nvmeio_trc_size);
+			goto out;
+		}
+	}
+
+	len += snprintf(buf + len, size - len,
+			"Trace Done\n");
+out:
+	return len;
+}
+
+/**
+ * lpfc_debugfs_cpucheck_data - Dump target node list to a buffer
+ * @vport: The vport to gather target node info from.
+ * @buf: The buffer to dump log into.
+ * @size: The maximum amount of data to process.
+ *
+ * Description:
+ * This routine dumps the NVME statistics associated with @vport
+ *
+ * Return Value:
+ * This routine returns the amount of bytes that were dumped into @buf and will
+ * not exceed @size.
+ **/
+static int
+lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size)
+{
+	struct lpfc_hba   *phba = vport->phba;
+	int i;
+	int len = 0;
+	uint32_t tot_xmt = 0;
+	uint32_t tot_cmpl = 0;
+
+	if (phba->nvmet_support == 0) {
+		/* NVME Initiator */
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"CPUcheck %s\n",
+				(phba->cpucheck_on & LPFC_CHECK_NVME_IO ?
+					"Enabled" : "Disabled"));
+		for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) {
+			if (i >= LPFC_CHECK_CPU_CNT)
+				break;
+			len += snprintf(buf + len, PAGE_SIZE - len,
+					"%02d: xmit x%08x cmpl x%08x\n",
+					i, phba->cpucheck_xmt_io[i],
+					phba->cpucheck_cmpl_io[i]);
+			tot_xmt += phba->cpucheck_xmt_io[i];
+			tot_cmpl += phba->cpucheck_cmpl_io[i];
+		}
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"tot:xmit x%08x cmpl x%08x\n",
+				tot_xmt, tot_cmpl);
+		return len;
+	}
+
 	return len;
 }
 
@@ -699,6 +1065,40 @@ lpfc_debugfs_slow_ring_trc(struct lpfc_hba *phba, char *fmt,
 	return;
 }
 
+/**
+ * lpfc_debugfs_nvme_trc - Store NVME/NVMET trace log
+ * @phba: The phba to associate this trace string with for retrieval.
+ * @fmt: Format string to be displayed when dumping the log.
+ * @data1: 1st data parameter to be applied to @fmt.
+ * @data2: 2nd data parameter to be applied to @fmt.
+ * @data3: 3rd data parameter to be applied to @fmt.
+ *
+ * Description:
+ * This routine is used by the driver code to add a debugfs log entry to the
+ * nvme trace buffer associated with @phba. @fmt, @data1, @data2, and
+ * @data3 are used like printf when displaying the log.
+ **/
+inline void
+lpfc_debugfs_nvme_trc(struct lpfc_hba *phba, char *fmt,
+		      uint16_t data1, uint16_t data2, uint32_t data3)
+{
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	struct lpfc_debugfs_nvmeio_trc *dtp;
+	int index;
+
+	if (!phba->nvmeio_trc_on || !phba->nvmeio_trc)
+		return;
+
+	index = atomic_inc_return(&phba->nvmeio_trc_cnt) &
+		(phba->nvmeio_trc_size - 1);
+	dtp = phba->nvmeio_trc + index;
+	dtp->fmt = fmt;
+	dtp->data1 = data1;
+	dtp->data2 = data2;
+	dtp->data3 = data3;
+#endif
+}
+
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 /**
  * lpfc_debugfs_disc_trc_open - Open the discovery trace log
@@ -1231,6 +1631,356 @@ lpfc_debugfs_dumpDataDif_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+
+static int
+lpfc_debugfs_nvmestat_open(struct inode *inode, struct file *file)
+{
+	struct lpfc_vport *vport = inode->i_private;
+	struct lpfc_debug *debug;
+	int rc = -ENOMEM;
+
+	debug = kmalloc(sizeof(*debug), GFP_KERNEL);
+	if (!debug)
+		goto out;
+
+	 /* Round to page boundary */
+	debug->buffer = kmalloc(LPFC_NVMESTAT_SIZE, GFP_KERNEL);
+	if (!debug->buffer) {
+		kfree(debug);
+		goto out;
+	}
+
+	debug->len = lpfc_debugfs_nvmestat_data(vport, debug->buffer,
+		LPFC_NVMESTAT_SIZE);
+
+	debug->i_private = inode->i_private;
+	file->private_data = debug;
+
+	rc = 0;
+out:
+	return rc;
+}
+
+static int
+lpfc_debugfs_nvmektime_open(struct inode *inode, struct file *file)
+{
+	struct lpfc_vport *vport = inode->i_private;
+	struct lpfc_debug *debug;
+	int rc = -ENOMEM;
+
+	debug = kmalloc(sizeof(*debug), GFP_KERNEL);
+	if (!debug)
+		goto out;
+
+	 /* Round to page boundary */
+	debug->buffer = kmalloc(LPFC_NVMEKTIME_SIZE, GFP_KERNEL);
+	if (!debug->buffer) {
+		kfree(debug);
+		goto out;
+	}
+
+	debug->len = lpfc_debugfs_nvmektime_data(vport, debug->buffer,
+		LPFC_NVMEKTIME_SIZE);
+
+	debug->i_private = inode->i_private;
+	file->private_data = debug;
+
+	rc = 0;
+out:
+	return rc;
+}
+
+static ssize_t
+lpfc_debugfs_nvmektime_write(struct file *file, const char __user *buf,
+			     size_t nbytes, loff_t *ppos)
+{
+	struct lpfc_debug *debug = file->private_data;
+	struct lpfc_vport *vport = (struct lpfc_vport *)debug->i_private;
+	struct lpfc_hba   *phba = vport->phba;
+	char mybuf[64];
+	char *pbuf;
+
+	if (nbytes > 64)
+		nbytes = 64;
+
+	/* Protect copy from user */
+	if (!access_ok(VERIFY_READ, buf, nbytes))
+		return -EFAULT;
+
+	memset(mybuf, 0, sizeof(mybuf));
+
+	if (copy_from_user(mybuf, buf, nbytes))
+		return -EFAULT;
+	pbuf = &mybuf[0];
+
+	if ((strncmp(pbuf, "on", sizeof("on") - 1) == 0)) {
+		phba->ktime_data_samples = 0;
+		phba->ktime_status_samples = 0;
+		phba->ktime_seg1_total = 0;
+		phba->ktime_seg1_max = 0;
+		phba->ktime_seg1_min = 0xffffffff;
+		phba->ktime_seg2_total = 0;
+		phba->ktime_seg2_max = 0;
+		phba->ktime_seg2_min = 0xffffffff;
+		phba->ktime_seg3_total = 0;
+		phba->ktime_seg3_max = 0;
+		phba->ktime_seg3_min = 0xffffffff;
+		phba->ktime_seg4_total = 0;
+		phba->ktime_seg4_max = 0;
+		phba->ktime_seg4_min = 0xffffffff;
+		phba->ktime_seg5_total = 0;
+		phba->ktime_seg5_max = 0;
+		phba->ktime_seg5_min = 0xffffffff;
+		phba->ktime_seg6_total = 0;
+		phba->ktime_seg6_max = 0;
+		phba->ktime_seg6_min = 0xffffffff;
+		phba->ktime_seg7_total = 0;
+		phba->ktime_seg7_max = 0;
+		phba->ktime_seg7_min = 0xffffffff;
+		phba->ktime_seg8_total = 0;
+		phba->ktime_seg8_max = 0;
+		phba->ktime_seg8_min = 0xffffffff;
+		phba->ktime_seg9_total = 0;
+		phba->ktime_seg9_max = 0;
+		phba->ktime_seg9_min = 0xffffffff;
+		phba->ktime_seg10_total = 0;
+		phba->ktime_seg10_max = 0;
+		phba->ktime_seg10_min = 0xffffffff;
+
+		phba->ktime_on = 1;
+		return strlen(pbuf);
+	} else if ((strncmp(pbuf, "off",
+		   sizeof("off") - 1) == 0)) {
+		phba->ktime_on = 0;
+		return strlen(pbuf);
+	} else if ((strncmp(pbuf, "zero",
+		   sizeof("zero") - 1) == 0)) {
+		phba->ktime_data_samples = 0;
+		phba->ktime_status_samples = 0;
+		phba->ktime_seg1_total = 0;
+		phba->ktime_seg1_max = 0;
+		phba->ktime_seg1_min = 0xffffffff;
+		phba->ktime_seg2_total = 0;
+		phba->ktime_seg2_max = 0;
+		phba->ktime_seg2_min = 0xffffffff;
+		phba->ktime_seg3_total = 0;
+		phba->ktime_seg3_max = 0;
+		phba->ktime_seg3_min = 0xffffffff;
+		phba->ktime_seg4_total = 0;
+		phba->ktime_seg4_max = 0;
+		phba->ktime_seg4_min = 0xffffffff;
+		phba->ktime_seg5_total = 0;
+		phba->ktime_seg5_max = 0;
+		phba->ktime_seg5_min = 0xffffffff;
+		phba->ktime_seg6_total = 0;
+		phba->ktime_seg6_max = 0;
+		phba->ktime_seg6_min = 0xffffffff;
+		phba->ktime_seg7_total = 0;
+		phba->ktime_seg7_max = 0;
+		phba->ktime_seg7_min = 0xffffffff;
+		phba->ktime_seg8_total = 0;
+		phba->ktime_seg8_max = 0;
+		phba->ktime_seg8_min = 0xffffffff;
+		phba->ktime_seg9_total = 0;
+		phba->ktime_seg9_max = 0;
+		phba->ktime_seg9_min = 0xffffffff;
+		phba->ktime_seg10_total = 0;
+		phba->ktime_seg10_max = 0;
+		phba->ktime_seg10_min = 0xffffffff;
+		return strlen(pbuf);
+	}
+	return -EINVAL;
+}
+
+static int
+lpfc_debugfs_nvmeio_trc_open(struct inode *inode, struct file *file)
+{
+	struct lpfc_hba *phba = inode->i_private;
+	struct lpfc_debug *debug;
+	int rc = -ENOMEM;
+
+	debug = kmalloc(sizeof(*debug), GFP_KERNEL);
+	if (!debug)
+		goto out;
+
+	 /* Round to page boundary */
+	debug->buffer = kmalloc(LPFC_NVMEIO_TRC_SIZE, GFP_KERNEL);
+	if (!debug->buffer) {
+		kfree(debug);
+		goto out;
+	}
+
+	debug->len = lpfc_debugfs_nvmeio_trc_data(phba, debug->buffer,
+		LPFC_NVMEIO_TRC_SIZE);
+
+	debug->i_private = inode->i_private;
+	file->private_data = debug;
+
+	rc = 0;
+out:
+	return rc;
+}
+
+static ssize_t
+lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf,
+			      size_t nbytes, loff_t *ppos)
+{
+	struct lpfc_debug *debug = file->private_data;
+	struct lpfc_hba *phba = (struct lpfc_hba *)debug->i_private;
+	int i;
+	unsigned long sz;
+	char mybuf[64];
+	char *pbuf;
+
+	if (nbytes > 64)
+		nbytes = 64;
+
+	/* Protect copy from user */
+	if (!access_ok(VERIFY_READ, buf, nbytes))
+		return -EFAULT;
+
+	memset(mybuf, 0, sizeof(mybuf));
+
+	if (copy_from_user(mybuf, buf, nbytes))
+		return -EFAULT;
+	pbuf = &mybuf[0];
+
+	if ((strncmp(pbuf, "off", sizeof("off") - 1) == 0)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0570 nvmeio_trc_off\n");
+		phba->nvmeio_trc_output_idx = 0;
+		phba->nvmeio_trc_on = 0;
+		return strlen(pbuf);
+	} else if ((strncmp(pbuf, "on", sizeof("on") - 1) == 0)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0571 nvmeio_trc_on\n");
+		phba->nvmeio_trc_output_idx = 0;
+		phba->nvmeio_trc_on = 1;
+		return strlen(pbuf);
+	}
+
+	/* We must be off to allocate the trace buffer */
+	if (phba->nvmeio_trc_on != 0)
+		return -EINVAL;
+
+	/* If not on or off, the parameter is the trace buffer size */
+	i = kstrtoul(pbuf, 0, &sz);
+	if (i)
+		return -EINVAL;
+	phba->nvmeio_trc_size = (uint32_t)sz;
+
+	/* It must be a power of 2 - round down */
+	i = 0;
+	while (sz > 1) {
+		sz = sz >> 1;
+		i++;
+	}
+	sz = (1 << i);
+	if (phba->nvmeio_trc_size != sz)
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0572 nvmeio_trc_size changed to %ld\n",
+				sz);
+	phba->nvmeio_trc_size = (uint32_t)sz;
+
+	/* If one previously exists, free it */
+	kfree(phba->nvmeio_trc);
+
+	/* Allocate new trace buffer and initialize */
+	phba->nvmeio_trc = kmalloc((sizeof(struct lpfc_debugfs_nvmeio_trc) *
+				    sz), GFP_KERNEL);
+	if (!phba->nvmeio_trc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"0573 Cannot create debugfs "
+				"nvmeio_trc buffer\n");
+		return -ENOMEM;
+	}
+	memset(phba->nvmeio_trc, 0,
+	       (sizeof(struct lpfc_debugfs_nvmeio_trc) * sz));
+	atomic_set(&phba->nvmeio_trc_cnt, 0);
+	phba->nvmeio_trc_on = 0;
+	phba->nvmeio_trc_output_idx = 0;
+
+	return strlen(pbuf);
+}
+
+static int
+lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file)
+{
+	struct lpfc_vport *vport = inode->i_private;
+	struct lpfc_debug *debug;
+	int rc = -ENOMEM;
+
+	debug = kmalloc(sizeof(*debug), GFP_KERNEL);
+	if (!debug)
+		goto out;
+
+	 /* Round to page boundary */
+	debug->buffer = kmalloc(LPFC_CPUCHECK_SIZE, GFP_KERNEL);
+	if (!debug->buffer) {
+		kfree(debug);
+		goto out;
+	}
+
+	debug->len = lpfc_debugfs_cpucheck_data(vport, debug->buffer,
+		LPFC_NVMEKTIME_SIZE);
+
+	debug->i_private = inode->i_private;
+	file->private_data = debug;
+
+	rc = 0;
+out:
+	return rc;
+}
+
+static ssize_t
+lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf,
+			    size_t nbytes, loff_t *ppos)
+{
+	struct lpfc_debug *debug = file->private_data;
+	struct lpfc_vport *vport = (struct lpfc_vport *)debug->i_private;
+	struct lpfc_hba   *phba = vport->phba;
+	char mybuf[64];
+	char *pbuf;
+	int i;
+
+	if (nbytes > 64)
+		nbytes = 64;
+
+	/* Protect copy from user */
+	if (!access_ok(VERIFY_READ, buf, nbytes))
+		return -EFAULT;
+
+	memset(mybuf, 0, sizeof(mybuf));
+
+	if (copy_from_user(mybuf, buf, nbytes))
+		return -EFAULT;
+	pbuf = &mybuf[0];
+
+	if ((strncmp(pbuf, "on", sizeof("on") - 1) == 0)) {
+		phba->cpucheck_on |= LPFC_CHECK_NVME_IO;
+		return strlen(pbuf);
+	} else if ((strncmp(pbuf, "rcv",
+		   sizeof("rcv") - 1) == 0)) {
+		return -EINVAL;
+	} else if ((strncmp(pbuf, "off",
+		   sizeof("off") - 1) == 0)) {
+		phba->cpucheck_on = LPFC_CHECK_OFF;
+		return strlen(pbuf);
+	} else if ((strncmp(pbuf, "zero",
+		   sizeof("zero") - 1) == 0)) {
+		for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) {
+			if (i >= LPFC_CHECK_CPU_CNT)
+				break;
+			phba->cpucheck_rcv_io[i] = 0;
+			phba->cpucheck_xmt_io[i] = 0;
+			phba->cpucheck_cmpl_io[i] = 0;
+			phba->cpucheck_ccmpl_io[i] = 0;
+		}
+		return strlen(pbuf);
+	}
+	return -EINVAL;
+}
+
 /*
  * ---------------------------------
  * iDiag debugfs file access methods
@@ -2581,6 +3331,17 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 			idiag.ptr_private = phba->sli4_hba.nvmels_cq;
 			goto pass_check;
 		}
+		/* NVME LS complete queue */
+		if (phba->sli4_hba.nvmels_cq &&
+		    phba->sli4_hba.nvmels_cq->queue_id == queid) {
+			/* Sanity check */
+			rc = lpfc_idiag_que_param_check(
+					phba->sli4_hba.nvmels_cq, index, count);
+			if (rc)
+				goto error_out;
+			idiag.ptr_private = phba->sli4_hba.nvmels_cq;
+			goto pass_check;
+		}
 		/* FCP complete queue */
 		if (phba->sli4_hba.fcp_cq) {
 			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
@@ -2597,6 +3358,25 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 				}
 			}
 		}
+		/* NVME complete queue */
+		if (phba->sli4_hba.nvme_cq) {
+			qidx = 0;
+			do {
+				if (phba->sli4_hba.nvme_cq[qidx] &&
+				    phba->sli4_hba.nvme_cq[qidx]->queue_id ==
+				    queid) {
+					/* Sanity check */
+					rc = lpfc_idiag_que_param_check(
+						phba->sli4_hba.nvme_cq[qidx],
+						index, count);
+					if (rc)
+						goto error_out;
+					idiag.ptr_private =
+						phba->sli4_hba.nvme_cq[qidx];
+					goto pass_check;
+				}
+			} while (++qidx < phba->cfg_nvme_io_channel);
+		}
 		goto error_out;
 		break;
 	case LPFC_IDIAG_MQ:
@@ -2636,6 +3416,17 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 			idiag.ptr_private = phba->sli4_hba.nvmels_wq;
 			goto pass_check;
 		}
+		/* NVME LS work queue */
+		if (phba->sli4_hba.nvmels_wq &&
+		    phba->sli4_hba.nvmels_wq->queue_id == queid) {
+			/* Sanity check */
+			rc = lpfc_idiag_que_param_check(
+					phba->sli4_hba.nvmels_wq, index, count);
+			if (rc)
+				goto error_out;
+			idiag.ptr_private = phba->sli4_hba.nvmels_wq;
+			goto pass_check;
+		}
 		/* FCP work queue */
 		if (phba->sli4_hba.fcp_wq) {
 			for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
@@ -2668,6 +3459,27 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
 				}
 			}
 		}
+
+		/* NVME work queues */
+		if (phba->sli4_hba.nvme_wq) {
+			for (qidx = 0; qidx < phba->cfg_nvme_io_channel;
+				qidx++) {
+				if (!phba->sli4_hba.nvme_wq[qidx])
+					continue;
+				if (phba->sli4_hba.nvme_wq[qidx]->queue_id ==
+				    queid) {
+					/* Sanity check */
+					rc = lpfc_idiag_que_param_check(
+						phba->sli4_hba.nvme_wq[qidx],
+						index, count);
+					if (rc)
+						goto error_out;
+					idiag.ptr_private =
+						phba->sli4_hba.nvme_wq[qidx];
+					goto pass_check;
+				}
+			}
+		}
 		goto error_out;
 		break;
 	case LPFC_IDIAG_RQ:
@@ -3651,6 +4463,45 @@ static const struct file_operations lpfc_debugfs_op_dumpHostSlim = {
 	.release =      lpfc_debugfs_release,
 };
 
+#undef lpfc_debugfs_op_nvmestat
+static const struct file_operations lpfc_debugfs_op_nvmestat = {
+	.owner =        THIS_MODULE,
+	.open =         lpfc_debugfs_nvmestat_open,
+	.llseek =       lpfc_debugfs_lseek,
+	.read =         lpfc_debugfs_read,
+	.release =      lpfc_debugfs_release,
+};
+
+#undef lpfc_debugfs_op_nvmektime
+static const struct file_operations lpfc_debugfs_op_nvmektime = {
+	.owner =        THIS_MODULE,
+	.open =         lpfc_debugfs_nvmektime_open,
+	.llseek =       lpfc_debugfs_lseek,
+	.read =         lpfc_debugfs_read,
+	.write =	lpfc_debugfs_nvmektime_write,
+	.release =      lpfc_debugfs_release,
+};
+
+#undef lpfc_debugfs_op_nvmeio_trc
+static const struct file_operations lpfc_debugfs_op_nvmeio_trc = {
+	.owner =        THIS_MODULE,
+	.open =         lpfc_debugfs_nvmeio_trc_open,
+	.llseek =       lpfc_debugfs_lseek,
+	.read =         lpfc_debugfs_read,
+	.write =	lpfc_debugfs_nvmeio_trc_write,
+	.release =      lpfc_debugfs_release,
+};
+
+#undef lpfc_debugfs_op_cpucheck
+static const struct file_operations lpfc_debugfs_op_cpucheck = {
+	.owner =        THIS_MODULE,
+	.open =         lpfc_debugfs_cpucheck_open,
+	.llseek =       lpfc_debugfs_lseek,
+	.read =         lpfc_debugfs_read,
+	.write =	lpfc_debugfs_cpucheck_write,
+	.release =      lpfc_debugfs_release,
+};
+
 #undef lpfc_debugfs_op_dumpData
 static const struct file_operations lpfc_debugfs_op_dumpData = {
 	.owner =        THIS_MODULE,
@@ -4237,6 +5088,60 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 				lpfc_debugfs_max_slow_ring_trc));
 		}
 
+		snprintf(name, sizeof(name), "nvmeio_trc");
+		phba->debug_nvmeio_trc =
+			debugfs_create_file(name, 0644,
+					    phba->hba_debugfs_root,
+					    phba, &lpfc_debugfs_op_nvmeio_trc);
+		if (!phba->debug_nvmeio_trc) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
+					 "0574 No create debugfs nvmeio_trc\n");
+			goto debug_failed;
+		}
+
+		atomic_set(&phba->nvmeio_trc_cnt, 0);
+		if (lpfc_debugfs_max_nvmeio_trc) {
+			num = lpfc_debugfs_max_nvmeio_trc - 1;
+			if (num & lpfc_debugfs_max_disc_trc) {
+				/* Change to be a power of 2 */
+				num = lpfc_debugfs_max_nvmeio_trc;
+				i = 0;
+				while (num > 1) {
+					num = num >> 1;
+					i++;
+				}
+				lpfc_debugfs_max_nvmeio_trc = (1 << i);
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"0575 lpfc_debugfs_max_nvmeio_trc "
+						"changed to %d\n",
+						lpfc_debugfs_max_nvmeio_trc);
+			}
+			phba->nvmeio_trc_size = lpfc_debugfs_max_nvmeio_trc;
+
+			/* Allocate trace buffer and initialize */
+			phba->nvmeio_trc = kmalloc(
+				(sizeof(struct lpfc_debugfs_nvmeio_trc) *
+				phba->nvmeio_trc_size), GFP_KERNEL);
+
+			if (!phba->nvmeio_trc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"0576 Cannot create debugfs "
+						"nvmeio_trc buffer\n");
+				goto nvmeio_off;
+			}
+			memset(phba->nvmeio_trc, 0,
+			       (sizeof(struct lpfc_debugfs_nvmeio_trc) *
+			       phba->nvmeio_trc_size));
+			phba->nvmeio_trc_on = 1;
+			phba->nvmeio_trc_output_idx = 0;
+			phba->nvmeio_trc = NULL;
+		} else {
+nvmeio_off:
+			phba->nvmeio_trc_size = 0;
+			phba->nvmeio_trc_on = 0;
+			phba->nvmeio_trc_output_idx = 0;
+			phba->nvmeio_trc = NULL;
+		}
 	}
 
 	snprintf(name, sizeof(name), "vport%d", vport->vpi);
@@ -4301,6 +5206,39 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 		goto debug_failed;
 	}
 
+	snprintf(name, sizeof(name), "nvmestat");
+	vport->debug_nvmestat =
+		debugfs_create_file(name, 0644,
+				    vport->vport_debugfs_root,
+				    vport, &lpfc_debugfs_op_nvmestat);
+	if (!vport->debug_nvmestat) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
+				 "0811 Cannot create debugfs nvmestat\n");
+		goto debug_failed;
+	}
+
+	snprintf(name, sizeof(name), "nvmektime");
+	vport->debug_nvmektime =
+		debugfs_create_file(name, 0644,
+				    vport->vport_debugfs_root,
+				    vport, &lpfc_debugfs_op_nvmektime);
+	if (!vport->debug_nvmektime) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
+				 "0815 Cannot create debugfs nvmektime\n");
+		goto debug_failed;
+	}
+
+	snprintf(name, sizeof(name), "cpucheck");
+	vport->debug_cpucheck =
+		debugfs_create_file(name, 0644,
+				    vport->vport_debugfs_root,
+				    vport, &lpfc_debugfs_op_cpucheck);
+	if (!vport->debug_cpucheck) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
+				 "0819 Cannot create debugfs cpucheck\n");
+		goto debug_failed;
+	}
+
 	/*
 	 * The following section is for additional directories/files for the
 	 * physical port.
@@ -4465,140 +5403,126 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 		kfree(vport->disc_trc);
 		vport->disc_trc = NULL;
 	}
-	if (vport->debug_disc_trc) {
-		debugfs_remove(vport->debug_disc_trc); /* discovery_trace */
-		vport->debug_disc_trc = NULL;
-	}
-	if (vport->debug_nodelist) {
-		debugfs_remove(vport->debug_nodelist); /* nodelist */
-		vport->debug_nodelist = NULL;
-	}
+
+	debugfs_remove(vport->debug_disc_trc); /* discovery_trace */
+	vport->debug_disc_trc = NULL;
+
+	debugfs_remove(vport->debug_nodelist); /* nodelist */
+	vport->debug_nodelist = NULL;
+
+	debugfs_remove(vport->debug_nvmestat); /* nvmestat */
+	vport->debug_nvmestat = NULL;
+
+	debugfs_remove(vport->debug_nvmektime); /* nvmektime */
+	vport->debug_nvmektime = NULL;
+
+	debugfs_remove(vport->debug_cpucheck); /* cpucheck */
+	vport->debug_cpucheck = NULL;
+
 	if (vport->vport_debugfs_root) {
 		debugfs_remove(vport->vport_debugfs_root); /* vportX */
 		vport->vport_debugfs_root = NULL;
 		atomic_dec(&phba->debugfs_vport_count);
 	}
+
 	if (atomic_read(&phba->debugfs_vport_count) == 0) {
 
-		if (phba->debug_hbqinfo) {
-			debugfs_remove(phba->debug_hbqinfo); /* hbqinfo */
-			phba->debug_hbqinfo = NULL;
-		}
-		if (phba->debug_dumpHBASlim) {
-			debugfs_remove(phba->debug_dumpHBASlim); /* HBASlim */
-			phba->debug_dumpHBASlim = NULL;
-		}
-		if (phba->debug_dumpHostSlim) {
-			debugfs_remove(phba->debug_dumpHostSlim); /* HostSlim */
-			phba->debug_dumpHostSlim = NULL;
-		}
-		if (phba->debug_dumpData) {
-			debugfs_remove(phba->debug_dumpData); /* dumpData */
-			phba->debug_dumpData = NULL;
-		}
+		debugfs_remove(phba->debug_hbqinfo); /* hbqinfo */
+		phba->debug_hbqinfo = NULL;
 
-		if (phba->debug_dumpDif) {
-			debugfs_remove(phba->debug_dumpDif); /* dumpDif */
-			phba->debug_dumpDif = NULL;
-		}
-		if (phba->debug_InjErrLBA) {
-			debugfs_remove(phba->debug_InjErrLBA); /* InjErrLBA */
-			phba->debug_InjErrLBA = NULL;
-		}
-		if (phba->debug_InjErrNPortID) {	 /* InjErrNPortID */
-			debugfs_remove(phba->debug_InjErrNPortID);
-			phba->debug_InjErrNPortID = NULL;
-		}
-		if (phba->debug_InjErrWWPN) {
-			debugfs_remove(phba->debug_InjErrWWPN); /* InjErrWWPN */
-			phba->debug_InjErrWWPN = NULL;
-		}
-		if (phba->debug_writeGuard) {
-			debugfs_remove(phba->debug_writeGuard); /* writeGuard */
-			phba->debug_writeGuard = NULL;
-		}
-		if (phba->debug_writeApp) {
-			debugfs_remove(phba->debug_writeApp); /* writeApp */
-			phba->debug_writeApp = NULL;
-		}
-		if (phba->debug_writeRef) {
-			debugfs_remove(phba->debug_writeRef); /* writeRef */
-			phba->debug_writeRef = NULL;
-		}
-		if (phba->debug_readGuard) {
-			debugfs_remove(phba->debug_readGuard); /* readGuard */
-			phba->debug_readGuard = NULL;
-		}
-		if (phba->debug_readApp) {
-			debugfs_remove(phba->debug_readApp); /* readApp */
-			phba->debug_readApp = NULL;
-		}
-		if (phba->debug_readRef) {
-			debugfs_remove(phba->debug_readRef); /* readRef */
-			phba->debug_readRef = NULL;
-		}
+		debugfs_remove(phba->debug_dumpHBASlim); /* HBASlim */
+		phba->debug_dumpHBASlim = NULL;
+
+		debugfs_remove(phba->debug_dumpHostSlim); /* HostSlim */
+		phba->debug_dumpHostSlim = NULL;
+
+		debugfs_remove(phba->debug_dumpData); /* dumpData */
+		phba->debug_dumpData = NULL;
+
+		debugfs_remove(phba->debug_dumpDif); /* dumpDif */
+		phba->debug_dumpDif = NULL;
+
+		debugfs_remove(phba->debug_InjErrLBA); /* InjErrLBA */
+		phba->debug_InjErrLBA = NULL;
+
+		debugfs_remove(phba->debug_InjErrNPortID);
+		phba->debug_InjErrNPortID = NULL;
+
+		debugfs_remove(phba->debug_InjErrWWPN); /* InjErrWWPN */
+		phba->debug_InjErrWWPN = NULL;
+
+		debugfs_remove(phba->debug_writeGuard); /* writeGuard */
+		phba->debug_writeGuard = NULL;
+
+		debugfs_remove(phba->debug_writeApp); /* writeApp */
+		phba->debug_writeApp = NULL;
+
+		debugfs_remove(phba->debug_writeRef); /* writeRef */
+		phba->debug_writeRef = NULL;
+
+		debugfs_remove(phba->debug_readGuard); /* readGuard */
+		phba->debug_readGuard = NULL;
+
+		debugfs_remove(phba->debug_readApp); /* readApp */
+		phba->debug_readApp = NULL;
+
+		debugfs_remove(phba->debug_readRef); /* readRef */
+		phba->debug_readRef = NULL;
 
 		if (phba->slow_ring_trc) {
 			kfree(phba->slow_ring_trc);
 			phba->slow_ring_trc = NULL;
 		}
-		if (phba->debug_slow_ring_trc) {
-			/* slow_ring_trace */
-			debugfs_remove(phba->debug_slow_ring_trc);
-			phba->debug_slow_ring_trc = NULL;
-		}
+
+		/* slow_ring_trace */
+		debugfs_remove(phba->debug_slow_ring_trc);
+		phba->debug_slow_ring_trc = NULL;
+
+		debugfs_remove(phba->debug_nvmeio_trc);
+		phba->debug_nvmeio_trc = NULL;
+
+		kfree(phba->nvmeio_trc);
+		phba->nvmeio_trc = NULL;
 
 		/*
 		 * iDiag release
 		 */
 		if (phba->sli_rev == LPFC_SLI_REV4) {
-			if (phba->idiag_ext_acc) {
-				/* iDiag extAcc */
-				debugfs_remove(phba->idiag_ext_acc);
-				phba->idiag_ext_acc = NULL;
-			}
-			if (phba->idiag_mbx_acc) {
-				/* iDiag mbxAcc */
-				debugfs_remove(phba->idiag_mbx_acc);
-				phba->idiag_mbx_acc = NULL;
-			}
-			if (phba->idiag_ctl_acc) {
-				/* iDiag ctlAcc */
-				debugfs_remove(phba->idiag_ctl_acc);
-				phba->idiag_ctl_acc = NULL;
-			}
-			if (phba->idiag_drb_acc) {
-				/* iDiag drbAcc */
-				debugfs_remove(phba->idiag_drb_acc);
-				phba->idiag_drb_acc = NULL;
-			}
-			if (phba->idiag_que_acc) {
-				/* iDiag queAcc */
-				debugfs_remove(phba->idiag_que_acc);
-				phba->idiag_que_acc = NULL;
-			}
-			if (phba->idiag_que_info) {
-				/* iDiag queInfo */
-				debugfs_remove(phba->idiag_que_info);
-				phba->idiag_que_info = NULL;
-			}
-			if (phba->idiag_bar_acc) {
-				/* iDiag barAcc */
-				debugfs_remove(phba->idiag_bar_acc);
-				phba->idiag_bar_acc = NULL;
-			}
-			if (phba->idiag_pci_cfg) {
-				/* iDiag pciCfg */
-				debugfs_remove(phba->idiag_pci_cfg);
-				phba->idiag_pci_cfg = NULL;
-			}
+			/* iDiag extAcc */
+			debugfs_remove(phba->idiag_ext_acc);
+			phba->idiag_ext_acc = NULL;
+
+			/* iDiag mbxAcc */
+			debugfs_remove(phba->idiag_mbx_acc);
+			phba->idiag_mbx_acc = NULL;
+
+			/* iDiag ctlAcc */
+			debugfs_remove(phba->idiag_ctl_acc);
+			phba->idiag_ctl_acc = NULL;
+
+			/* iDiag drbAcc */
+			debugfs_remove(phba->idiag_drb_acc);
+			phba->idiag_drb_acc = NULL;
+
+			/* iDiag queAcc */
+			debugfs_remove(phba->idiag_que_acc);
+			phba->idiag_que_acc = NULL;
+
+			/* iDiag queInfo */
+			debugfs_remove(phba->idiag_que_info);
+			phba->idiag_que_info = NULL;
+
+			/* iDiag barAcc */
+			debugfs_remove(phba->idiag_bar_acc);
+			phba->idiag_bar_acc = NULL;
+
+			/* iDiag pciCfg */
+			debugfs_remove(phba->idiag_pci_cfg);
+			phba->idiag_pci_cfg = NULL;
 
 			/* Finally remove the iDiag debugfs root */
-			if (phba->idiag_root) {
-				/* iDiag root */
-				debugfs_remove(phba->idiag_root);
-				phba->idiag_root = NULL;
-			}
+			debugfs_remove(phba->idiag_root);
+			phba->idiag_root = NULL;
 		}
 
 		if (phba->hba_debugfs_root) {
@@ -4607,10 +5531,8 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 			atomic_dec(&lpfc_debugfs_hba_count);
 		}
 
-		if (atomic_read(&lpfc_debugfs_hba_count) == 0) {
-			debugfs_remove(lpfc_debugfs_root); /* lpfc */
-			lpfc_debugfs_root = NULL;
-		}
+		debugfs_remove(lpfc_debugfs_root); /* lpfc */
+		lpfc_debugfs_root = NULL;
 	}
 #endif
 	return;
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index 98814d651239..5312e0f9deb6 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -50,6 +50,14 @@ enum {
 	DUMP_NVMELS,
 };
 
+/* nvmestat output buffer size */
+#define LPFC_NVMESTAT_SIZE 8192
+#define LPFC_NVMEKTIME_SIZE 8192
+#define LPFC_CPUCHECK_SIZE 8192
+#define LPFC_NVMEIO_TRC_SIZE 8192
+
+#define LPFC_DEBUG_OUT_LINE_SZ	80
+
 /*
  * For SLI4 iDiag debugfs diagnostics tool
  */
@@ -196,6 +204,12 @@ enum {
 #define SIZE_U16 sizeof(uint16_t)
 #define SIZE_U32 sizeof(uint32_t)
 
+#define lpfc_nvmeio_data(phba, fmt, arg...) \
+	{ \
+	if (phba->nvmeio_trc_on) \
+		lpfc_debugfs_nvme_trc(phba, fmt, ##arg); \
+	}
+
 struct lpfc_debug {
 	char *i_private;
 	char op;
@@ -214,6 +228,13 @@ struct lpfc_debugfs_trc {
 	unsigned long jif;
 };
 
+struct lpfc_debugfs_nvmeio_trc {
+	char *fmt;
+	uint16_t data1;
+	uint16_t data2;
+	uint32_t data3;
+};
+
 struct lpfc_idiag_offset {
 	uint32_t last_rd;
 };
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 729803dacf15..56b4b94a372e 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -50,6 +50,7 @@
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
+#include "lpfc_debugfs.h"
 
 /* NVME initiator-based functions */
 
@@ -222,6 +223,9 @@ lpfc_nvme_cmpl_gen_req(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 			 cmdwqe->sli4_xritag, status,
 			 cmdwqe, pnvme_lsreq, cmdwqe->context3, ndlp);
 
+	lpfc_nvmeio_data(phba, "NVME LS  CMPL: xri x%x stat x%x parm x%x\n",
+			 cmdwqe->sli4_xritag, status, wcqe->parameter);
+
 	if (cmdwqe->context3) {
 		buf_ptr = (struct lpfc_dmabuf *)cmdwqe->context3;
 		lpfc_mbuf_free(phba, buf_ptr->virt, buf_ptr->phys);
@@ -355,6 +359,9 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
 	genwqe->vport = vport;
 	genwqe->retry = retry;
 
+	lpfc_nvmeio_data(phba, "NVME LS  XMIT: xri x%x iotag x%x to x%06x\n",
+			 genwqe->sli4_xritag, genwqe->iotag, ndlp->nlp_DID);
+
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_ELS_RING, genwqe);
 	if (rc == WQE_ERROR) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
@@ -637,6 +644,79 @@ lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport,
 	*wptr   = *dptr;	/* Word 23 */
 }
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+static void
+lpfc_nvme_ktime(struct lpfc_hba *phba,
+		struct lpfc_nvme_buf *lpfc_ncmd)
+{
+	uint64_t seg1, seg2, seg3, seg4;
+
+	if (!phba->ktime_on)
+		return;
+	if (!lpfc_ncmd->ts_last_cmd ||
+	    !lpfc_ncmd->ts_cmd_start ||
+	    !lpfc_ncmd->ts_cmd_wqput ||
+	    !lpfc_ncmd->ts_isr_cmpl ||
+	    !lpfc_ncmd->ts_data_nvme)
+		return;
+	if (lpfc_ncmd->ts_cmd_start < lpfc_ncmd->ts_last_cmd)
+		return;
+	if (lpfc_ncmd->ts_cmd_wqput < lpfc_ncmd->ts_cmd_start)
+		return;
+	if (lpfc_ncmd->ts_isr_cmpl < lpfc_ncmd->ts_cmd_wqput)
+		return;
+	if (lpfc_ncmd->ts_data_nvme < lpfc_ncmd->ts_isr_cmpl)
+		return;
+	/*
+	 * Segment 1 - Time from Last FCP command cmpl is handed
+	 * off to NVME Layer to start of next command.
+	 * Segment 2 - Time from Driver receives a IO cmd start
+	 * from NVME Layer to WQ put is done on IO cmd.
+	 * Segment 3 - Time from Driver WQ put is done on IO cmd
+	 * to MSI-X ISR for IO cmpl.
+	 * Segment 4 - Time from MSI-X ISR for IO cmpl to when
+	 * cmpl is handled off to the NVME Layer.
+	 */
+	seg1 = lpfc_ncmd->ts_cmd_start - lpfc_ncmd->ts_last_cmd;
+	if (seg1 > 5000000)  /* 5 ms - for sequential IOs */
+		return;
+
+	/* Calculate times relative to start of IO */
+	seg2 = (lpfc_ncmd->ts_cmd_wqput - lpfc_ncmd->ts_cmd_start);
+	seg3 = (lpfc_ncmd->ts_isr_cmpl -
+		lpfc_ncmd->ts_cmd_start) - seg2;
+	seg4 = (lpfc_ncmd->ts_data_nvme -
+		lpfc_ncmd->ts_cmd_start) - seg2 - seg3;
+	phba->ktime_data_samples++;
+	phba->ktime_seg1_total += seg1;
+	if (seg1 < phba->ktime_seg1_min)
+		phba->ktime_seg1_min = seg1;
+	else if (seg1 > phba->ktime_seg1_max)
+		phba->ktime_seg1_max = seg1;
+	phba->ktime_seg2_total += seg2;
+	if (seg2 < phba->ktime_seg2_min)
+		phba->ktime_seg2_min = seg2;
+	else if (seg2 > phba->ktime_seg2_max)
+		phba->ktime_seg2_max = seg2;
+	phba->ktime_seg3_total += seg3;
+	if (seg3 < phba->ktime_seg3_min)
+		phba->ktime_seg3_min = seg3;
+	else if (seg3 > phba->ktime_seg3_max)
+		phba->ktime_seg3_max = seg3;
+	phba->ktime_seg4_total += seg4;
+	if (seg4 < phba->ktime_seg4_min)
+		phba->ktime_seg4_min = seg4;
+	else if (seg4 > phba->ktime_seg4_max)
+		phba->ktime_seg4_max = seg4;
+
+	lpfc_ncmd->ts_last_cmd = 0;
+	lpfc_ncmd->ts_cmd_start = 0;
+	lpfc_ncmd->ts_cmd_wqput  = 0;
+	lpfc_ncmd->ts_isr_cmpl = 0;
+	lpfc_ncmd->ts_data_nvme = 0;
+}
+#endif
+
 /**
  * lpfc_nvme_io_cmd_wqe_cmpl - Complete an NVME-over-FCP IO
  * @lpfc_pnvme: Pointer to the driver's nvme instance data
@@ -680,6 +760,9 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	nCmd = lpfc_ncmd->nvmeCmd;
 	rport = lpfc_ncmd->nrport;
 
+	lpfc_nvmeio_data(phba, "NVME FCP CMPL: xri x%x stat x%x parm x%x\n",
+			 lpfc_ncmd->cur_iocbq.sli4_xritag,
+			 bf_get(lpfc_wcqe_c_status, wcqe), wcqe->parameter);
 	/*
 	 * Catch race where our node has transitioned, but the
 	 * transport is still transitioning.
@@ -798,6 +881,23 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	 * no need for dma unprep because the nvme_transport
 	 * owns the dma address.
 	 */
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->ktime_on) {
+		lpfc_ncmd->ts_isr_cmpl = pwqeIn->isr_timestamp;
+		lpfc_ncmd->ts_data_nvme = ktime_get_ns();
+		phba->ktime_last_cmd = lpfc_ncmd->ts_data_nvme;
+		lpfc_nvme_ktime(phba, lpfc_ncmd);
+	}
+	if (phba->cpucheck_on & LPFC_CHECK_NVME_IO) {
+		if (lpfc_ncmd->cpu != smp_processor_id())
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
+					 "6701 CPU Check cmpl: "
+					 "cpu %d expect %d\n",
+					 smp_processor_id(), lpfc_ncmd->cpu);
+		if (lpfc_ncmd->cpu < LPFC_CHECK_CPU_CNT)
+			phba->cpucheck_cmpl_io[lpfc_ncmd->cpu]++;
+	}
+#endif
 	nCmd->done(nCmd);
 
 	spin_lock_irqsave(&phba->hbalock, flags);
@@ -1103,11 +1203,18 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	struct lpfc_nvme_buf *lpfc_ncmd;
 	struct lpfc_nvme_rport *rport;
 	struct lpfc_nvme_qhandle *lpfc_queue_info;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	uint64_t start = 0;
+#endif
 
 	lport = (struct lpfc_nvme_lport *)pnvme_lport->private;
 	vport = lport->vport;
 	phba = vport->phba;
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->ktime_on)
+		start = ktime_get_ns();
+#endif
 	rport = (struct lpfc_nvme_rport *)pnvme_rport->private;
 	lpfc_queue_info = (struct lpfc_nvme_qhandle *)hw_queue_handle;
 
@@ -1161,6 +1268,12 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 		ret = -ENOMEM;
 		goto out_fail;
 	}
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->ktime_on) {
+		lpfc_ncmd->ts_cmd_start = start;
+		lpfc_ncmd->ts_last_cmd = phba->ktime_last_cmd;
+	}
+#endif
 
 	/*
 	 * Store the data needed by the driver to issue, abort, and complete
@@ -1192,6 +1305,10 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	 */
 	lpfc_ncmd->cur_iocbq.hba_wqidx = lpfc_queue_info->index;
 
+	lpfc_nvmeio_data(phba, "NVME FCP XMIT: xri x%x idx %d to %06x\n",
+			 lpfc_ncmd->cur_iocbq.sli4_xritag,
+			 lpfc_queue_info->index, ndlp->nlp_DID);
+
 	ret = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, &lpfc_ncmd->cur_iocbq);
 	if (ret) {
 		atomic_dec(&ndlp->cmd_pending);
@@ -1204,6 +1321,28 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 		goto out_free_nvme_buf;
 	}
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->ktime_on)
+		lpfc_ncmd->ts_cmd_wqput = ktime_get_ns();
+
+	if (phba->cpucheck_on & LPFC_CHECK_NVME_IO) {
+		lpfc_ncmd->cpu = smp_processor_id();
+		if (lpfc_ncmd->cpu != lpfc_queue_info->index) {
+			/* Check for admin queue */
+			if (lpfc_queue_info->qidx) {
+				lpfc_printf_vlog(vport,
+						 KERN_ERR, LOG_NVME_IOERR,
+						"6702 CPU Check cmd: "
+						"cpu %d wq %d\n",
+						lpfc_ncmd->cpu,
+						lpfc_queue_info->index);
+			}
+			lpfc_ncmd->cpu = lpfc_queue_info->index;
+		}
+		if (lpfc_ncmd->cpu < LPFC_CHECK_CPU_CNT)
+			phba->cpucheck_xmt_io[lpfc_ncmd->cpu]++;
+	}
+#endif
 	return 0;
 
  out_free_nvme_buf:
@@ -1377,6 +1516,10 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 		return;
 	}
 
+	lpfc_nvmeio_data(phba, "NVME FCP ABORT: xri x%x idx %d to %06x\n",
+			 nvmereq_wqe->sli4_xritag,
+			 nvmereq_wqe->hba_wqidx, ndlp->nlp_DID);
+
 	/* Outstanding abort is in progress */
 	if (nvmereq_wqe->iocb_flag & LPFC_DRIVER_ABORTED) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index 4cc51086a5f7..85961c1ddecf 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -91,4 +91,11 @@ struct lpfc_nvme_buf {
 
 	wait_queue_head_t *waitq;
 	unsigned long start_time;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	uint64_t ts_cmd_start;
+	uint64_t ts_last_cmd;
+	uint64_t ts_cmd_wqput;
+	uint64_t ts_isr_cmpl;
+	uint64_t ts_data_nvme;
+#endif
 };
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index ccda1f73ae84..5f6ad67d5a73 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -13299,6 +13299,11 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 	if (unlikely(!fpeq))
 		return IRQ_NONE;
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->ktime_on)
+		fpeq->isr_timestamp = ktime_get_ns();
+#endif
+
 	if (lpfc_fcp_look_ahead) {
 		if (atomic_dec_and_test(&hba_eq_hdl->hba_eq_in_use))
 			lpfc_sli4_eq_clr_intr(fpeq);
-- 
GitLab


From f358dd0ca26c152a5e0922e269996268dcb98a9d Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:34 -0800
Subject: [PATCH 149/898] scsi: lpfc: NVME Target: Base modifications

NVME Target: Base modifications

This set of patches adds the base modifications for NVME target support

The base modifications consist of:
- Additional module parameters or configuration tuning
- Enablement of configuration mode for NVME target. Ties into the
  queueing model put into place by the initiator basemods patches.
- Target-specific buffer pools, dma pools, sgl pools

[mkp: fixed space at end of file]

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h         |   6 +
 drivers/scsi/lpfc/lpfc_attr.c    | 131 ++++++++++++++++-
 drivers/scsi/lpfc/lpfc_crtn.h    |  10 ++
 drivers/scsi/lpfc/lpfc_debugfs.c |   7 +-
 drivers/scsi/lpfc/lpfc_disc.h    |   1 +
 drivers/scsi/lpfc/lpfc_hw4.h     |  45 ++++++
 drivers/scsi/lpfc/lpfc_init.c    | 244 ++++++++++++++++++++++++++++++-
 drivers/scsi/lpfc/lpfc_mem.c     | 167 +++++++++++++++++++++
 drivers/scsi/lpfc/lpfc_nvmet.h   | 101 +++++++++++++
 drivers/scsi/lpfc/lpfc_sli.c     | 107 +++++++++++++-
 drivers/scsi/lpfc/lpfc_sli.h     |   2 +
 drivers/scsi/lpfc/lpfc_sli4.h    |   6 +
 12 files changed, 807 insertions(+), 20 deletions(-)
 create mode 100644 drivers/scsi/lpfc/lpfc_nvmet.h

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index fdb314b3282d..b7361474880e 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -741,6 +741,7 @@ struct lpfc_hba {
 	uint8_t  fcp_embed_io;
 	uint8_t  nvme_support;	/* Firmware supports NVME */
 	uint8_t  nvmet_support;	/* driver supports NVMET */
+#define LPFC_NVMET_MAX_PORTS	32
 	uint8_t  mds_diags_support;
 
 	/* HBA Config Parameters */
@@ -766,8 +767,10 @@ struct lpfc_hba {
 	uint32_t cfg_fcp_imax;
 	uint32_t cfg_fcp_cpu_map;
 	uint32_t cfg_fcp_io_channel;
+	uint32_t cfg_suppress_rsp;
 	uint32_t cfg_nvme_oas;
 	uint32_t cfg_nvme_io_channel;
+	uint32_t cfg_enable_nvmet;
 	uint32_t cfg_nvme_enable_fb;
 	uint32_t cfg_total_seg_cnt;
 	uint32_t cfg_sg_seg_cnt;
@@ -820,6 +823,7 @@ struct lpfc_hba {
 #define LPFC_ENABLE_NVME 2
 #define LPFC_ENABLE_BOTH 3
 	uint32_t io_channel_irqs;	/* number of irqs for io channels */
+	struct nvmet_fc_target_port *targetport;
 	lpfc_vpd_t vpd;		/* vital product data */
 
 	struct pci_dev *pcidev;
@@ -1103,6 +1107,8 @@ struct lpfc_hba {
 	uint16_t cpucheck_on;
 #define LPFC_CHECK_OFF		0
 #define LPFC_CHECK_NVME_IO	1
+#define LPFC_CHECK_NVMET_RCV	2
+#define LPFC_CHECK_NVMET_IO	4
 	uint16_t ktime_on;
 	uint64_t ktime_data_samples;
 	uint64_t ktime_status_samples;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index b91b4bb1062d..835c6c1f4cd4 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -46,6 +46,7 @@
 #include "lpfc.h"
 #include "lpfc_scsi.h"
 #include "lpfc_nvme.h"
+#include "lpfc_nvmet.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_version.h"
 #include "lpfc_compat.h"
@@ -139,6 +140,7 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct lpfc_vport *vport = shost_priv(shost);
 	struct lpfc_hba   *phba = vport->phba;
+	struct lpfc_nvmet_tgtport *tgtp;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
 	struct lpfc_nvme_rport *rport;
@@ -150,6 +152,92 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		len += snprintf(buf, PAGE_SIZE, "NVME Disabled\n");
 		return len;
 	}
+	if (phba->nvmet_support) {
+		if (!phba->targetport) {
+			len = snprintf(buf, PAGE_SIZE,
+					"NVME Target: x%llx is not allocated\n",
+					wwn_to_u64(vport->fc_portname.u.wwn));
+			return len;
+		}
+		/* Port state is only one of two values for now. */
+		if (phba->targetport->port_id)
+			statep = "REGISTERED";
+		else
+			statep = "INIT";
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"NVME Target: Enabled  State %s\n",
+				statep);
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"%s%d WWPN x%llx WWNN x%llx DID x%06x\n",
+				"NVME Target: lpfc",
+				phba->brd_no,
+				wwn_to_u64(vport->fc_portname.u.wwn),
+				wwn_to_u64(vport->fc_nodename.u.wwn),
+				phba->targetport->port_id);
+
+		len += snprintf(buf + len, PAGE_SIZE,
+				"\nNVME Target: Statistics\n");
+		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+		len += snprintf(buf+len, PAGE_SIZE-len,
+				"LS: Rcv %08x Drop %08x Abort %08x\n",
+				atomic_read(&tgtp->rcv_ls_req_in),
+				atomic_read(&tgtp->rcv_ls_req_drop),
+				atomic_read(&tgtp->xmt_ls_abort));
+		if (atomic_read(&tgtp->rcv_ls_req_in) !=
+		    atomic_read(&tgtp->rcv_ls_req_out)) {
+			len += snprintf(buf+len, PAGE_SIZE-len,
+					"Rcv LS: in %08x != out %08x\n",
+					atomic_read(&tgtp->rcv_ls_req_in),
+					atomic_read(&tgtp->rcv_ls_req_out));
+		}
+
+		len += snprintf(buf+len, PAGE_SIZE-len,
+				"LS: Xmt %08x Drop %08x Cmpl %08x Err %08x\n",
+				atomic_read(&tgtp->xmt_ls_rsp),
+				atomic_read(&tgtp->xmt_ls_drop),
+				atomic_read(&tgtp->xmt_ls_rsp_cmpl),
+				atomic_read(&tgtp->xmt_ls_rsp_error));
+
+		len += snprintf(buf+len, PAGE_SIZE-len,
+				"FCP: Rcv %08x Drop %08x\n",
+				atomic_read(&tgtp->rcv_fcp_cmd_in),
+				atomic_read(&tgtp->rcv_fcp_cmd_drop));
+
+		if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
+		    atomic_read(&tgtp->rcv_fcp_cmd_out)) {
+			len += snprintf(buf+len, PAGE_SIZE-len,
+					"Rcv FCP: in %08x != out %08x\n",
+					atomic_read(&tgtp->rcv_fcp_cmd_in),
+					atomic_read(&tgtp->rcv_fcp_cmd_out));
+		}
+
+		len += snprintf(buf+len, PAGE_SIZE-len,
+				"FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x\n",
+				atomic_read(&tgtp->xmt_fcp_read),
+				atomic_read(&tgtp->xmt_fcp_read_rsp),
+				atomic_read(&tgtp->xmt_fcp_write),
+				atomic_read(&tgtp->xmt_fcp_rsp));
+
+		len += snprintf(buf+len, PAGE_SIZE-len,
+				"FCP Rsp: abort %08x drop %08x\n",
+				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_drop));
+
+		len += snprintf(buf+len, PAGE_SIZE-len,
+				"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
+				atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
+				atomic_read(&tgtp->xmt_fcp_rsp_error),
+				atomic_read(&tgtp->xmt_fcp_rsp_drop));
+
+		len += snprintf(buf+len, PAGE_SIZE-len,
+				"ABORT: Xmt %08x Err %08x Cmpl %08x",
+				atomic_read(&tgtp->xmt_abort_rsp),
+				atomic_read(&tgtp->xmt_abort_rsp_error),
+				atomic_read(&tgtp->xmt_abort_cmpl));
+
+		len +=  snprintf(buf+len, PAGE_SIZE-len, "\n");
+		return len;
+	}
 
 	localport = vport->localport;
 	if (!localport) {
@@ -2899,6 +2987,13 @@ lpfc_oas_lun_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(lpfc_xlane_lun, S_IRUGO | S_IWUSR,
 		   lpfc_oas_lun_show, lpfc_oas_lun_store);
 
+int lpfc_enable_nvmet_cnt;
+unsigned long long lpfc_enable_nvmet[LPFC_NVMET_MAX_PORTS] = {
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+module_param_array(lpfc_enable_nvmet, ullong, &lpfc_enable_nvmet_cnt, 0444);
+MODULE_PARM_DESC(lpfc_enable_nvmet, "Enable HBA port(s) WWPN as a NVME Target");
+
 static int lpfc_poll = 0;
 module_param(lpfc_poll, int, S_IRUGO);
 MODULE_PARM_DESC(lpfc_poll, "FCP ring polling mode control:"
@@ -3177,6 +3272,15 @@ lpfc_vport_param_store(devloss_tmo)
 static DEVICE_ATTR(lpfc_devloss_tmo, S_IRUGO | S_IWUSR,
 		   lpfc_devloss_tmo_show, lpfc_devloss_tmo_store);
 
+/*
+ * lpfc_suppress_rsp: Enable suppress rsp feature is firmware supports it
+ * lpfc_suppress_rsp = 0  Disable
+ * lpfc_suppress_rsp = 1  Enable (default)
+ *
+ */
+LPFC_ATTR_R(suppress_rsp, 1, 0, 1,
+	    "Enable suppress rsp feature is firmware supports it");
+
 /*
  * lpfc_enable_fc4_type: Defines what FC4 types are supported.
  * Supported Values:  1 - register just FCP
@@ -3190,7 +3294,8 @@ LPFC_ATTR_R(enable_fc4_type, LPFC_ENABLE_BOTH,
 /*
  * lpfc_xri_split: Defines the division of XRI resources between SCSI and NVME
  * This parameter is only used if:
- *     lpfc_enable_fc4_type is 3 - register both FCP and NVME
+ *     lpfc_enable_fc4_type is 3 - register both FCP and NVME and
+ *     port is not configured for NVMET.
  *
  * ELS/CT always get 10% of XRIs, up to a maximum of 250
  * The remaining XRIs get split up based on lpfc_xri_split per port:
@@ -4754,7 +4859,7 @@ LPFC_ATTR_R(use_msi, 2, 0, 2, "Use Message Signaled Interrupts (1) or "
 	    "MSI-X (2), if possible");
 
 /*
- * lpfc_nvme_oas: Use the oas bit when sending NVME IOs
+ * lpfc_nvme_oas: Use the oas bit when sending NVME/NVMET IOs
  *
  *      0  = NVME OAS disabled
  *      1  = NVME OAS enabled
@@ -4992,6 +5097,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_fcp_imax,
 	&dev_attr_lpfc_fcp_cpu_map,
 	&dev_attr_lpfc_fcp_io_channel,
+	&dev_attr_lpfc_suppress_rsp,
 	&dev_attr_lpfc_nvme_io_channel,
 	&dev_attr_lpfc_nvme_enable_fb,
 	&dev_attr_lpfc_enable_bg,
@@ -6027,6 +6133,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 		phba->cfg_poll = 0;
 	else
 		phba->cfg_poll = lpfc_poll;
+	lpfc_suppress_rsp_init(phba, lpfc_suppress_rsp);
 
 	lpfc_enable_fc4_type_init(phba, lpfc_enable_fc4_type);
 
@@ -6046,17 +6153,17 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	}
 
 	/* A value of 0 means use the number of CPUs found in the system */
-	if (phba->cfg_nvme_io_channel == 0)
-		phba->cfg_nvme_io_channel = phba->sli4_hba.num_present_cpu;
 	if (phba->cfg_fcp_io_channel == 0)
 		phba->cfg_fcp_io_channel = phba->sli4_hba.num_present_cpu;
-
-	if (phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP)
-		phba->cfg_nvme_io_channel = 0;
+	if (phba->cfg_nvme_io_channel == 0)
+		phba->cfg_nvme_io_channel = phba->sli4_hba.num_present_cpu;
 
 	if (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)
 		phba->cfg_fcp_io_channel = 0;
 
+	if (phba->cfg_enable_fc4_type == LPFC_ENABLE_FCP)
+		phba->cfg_nvme_io_channel = 0;
+
 	if (phba->cfg_fcp_io_channel > phba->cfg_nvme_io_channel)
 		phba->io_channel_irqs = phba->cfg_fcp_io_channel;
 	else
@@ -6088,12 +6195,20 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 void
 lpfc_nvme_mod_param_dep(struct lpfc_hba *phba)
 {
-	phba->nvmet_support = 0;
 	if (phba->cfg_nvme_io_channel > phba->sli4_hba.num_present_cpu)
 		phba->cfg_nvme_io_channel = phba->sli4_hba.num_present_cpu;
+
 	if (phba->cfg_fcp_io_channel > phba->sli4_hba.num_present_cpu)
 		phba->cfg_fcp_io_channel = phba->sli4_hba.num_present_cpu;
 
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME &&
+	    phba->nvmet_support) {
+		phba->cfg_enable_fc4_type &= ~LPFC_ENABLE_FCP;
+		phba->cfg_fcp_io_channel = 0;
+	} else
+		/* Not NVME Target mode.  Turn off Target parameters. */
+		phba->nvmet_support = 0;
+
 	if (phba->cfg_fcp_io_channel > phba->cfg_nvme_io_channel)
 		phba->io_channel_irqs = phba->cfg_fcp_io_channel;
 	else
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 4a0db3895993..1e97b1a106c5 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -240,6 +240,8 @@ struct hbq_dmabuf *lpfc_els_hbq_alloc(struct lpfc_hba *);
 void lpfc_els_hbq_free(struct lpfc_hba *, struct hbq_dmabuf *);
 struct hbq_dmabuf *lpfc_sli4_rb_alloc(struct lpfc_hba *);
 void lpfc_sli4_rb_free(struct lpfc_hba *, struct hbq_dmabuf *);
+struct rqb_dmabuf *lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba);
+void lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab);
 void lpfc_sli4_build_dflt_fcf_record(struct lpfc_hba *, struct fcf_record *,
 			uint16_t);
 int lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
@@ -304,6 +306,8 @@ int lpfc_sli_issue_iocb(struct lpfc_hba *, uint32_t,
 int lpfc_sli4_issue_wqe(struct lpfc_hba *phba, uint32_t rnum,
 			struct lpfc_iocbq *iocbq);
 struct lpfc_sglq *__lpfc_clear_active_sglq(struct lpfc_hba *phba, uint16_t xri);
+struct lpfc_sglq *__lpfc_sli_get_nvmet_sglq(struct lpfc_hba *phba,
+					    struct lpfc_iocbq *piocbq);
 void lpfc_sli_pcimem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_bemem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_abort_iocb_ring(struct lpfc_hba *, struct lpfc_sli_ring *);
@@ -353,6 +357,9 @@ void lpfc_sli_free_hbq(struct lpfc_hba *, struct hbq_dmabuf *);
 void *lpfc_mbuf_alloc(struct lpfc_hba *, int, dma_addr_t *);
 void __lpfc_mbuf_free(struct lpfc_hba *, void *, dma_addr_t);
 void lpfc_mbuf_free(struct lpfc_hba *, void *, dma_addr_t);
+void *lpfc_nvmet_buf_alloc(struct lpfc_hba *phba, int flags,
+			dma_addr_t *handle);
+void lpfc_nvmet_buf_free(struct lpfc_hba *phba, void *virtp, dma_addr_t dma);
 
 void lpfc_in_buf_free(struct lpfc_hba *, struct lpfc_dmabuf *);
 /* Function prototypes. */
@@ -492,6 +499,7 @@ int lpfc_selective_reset(struct lpfc_hba *);
 int lpfc_sli4_read_config(struct lpfc_hba *);
 void lpfc_sli4_node_prep(struct lpfc_hba *);
 int lpfc_sli4_els_sgl_update(struct lpfc_hba *phba);
+int lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba);
 int lpfc_sli4_scsi_sgl_update(struct lpfc_hba *phba);
 int lpfc_sli4_nvme_sgl_update(struct lpfc_hba *phba);
 void lpfc_free_sgl_list(struct lpfc_hba *, struct list_head *);
@@ -531,3 +539,5 @@ void lpfc_nvme_mod_param_dep(struct lpfc_hba *phba);
 void lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba,
 				struct lpfc_iocbq *cmdiocb,
 				struct lpfc_wcqe_complete *abts_cmpl);
+extern int lpfc_enable_nvmet_cnt;
+extern unsigned long long lpfc_enable_nvmet[];
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 3fcba26623eb..e54307dff8be 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -828,7 +828,6 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			phba->ktime_data_samples));
 		return len;
 	}
-
 	return len;
 }
 
@@ -1961,7 +1960,11 @@ lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf,
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "rcv",
 		   sizeof("rcv") - 1) == 0)) {
-		return -EINVAL;
+		if (phba->nvmet_support)
+			phba->cpucheck_on |= LPFC_CHECK_NVMET_RCV;
+		else
+			return -EINVAL;
+		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "off",
 		   sizeof("off") - 1) == 0)) {
 		phba->cpucheck_on = LPFC_CHECK_OFF;
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 13cc1d19b336..e305e97e05a9 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -148,6 +148,7 @@ struct lpfc_node_rrq {
 /* Defines for nlp_flag (uint32) */
 #define NLP_IGNR_REG_CMPL  0x00000001 /* Rcvd rscn before we cmpl reg login */
 #define NLP_REG_LOGIN_SEND 0x00000002   /* sent reglogin to adapter */
+#define NLP_SUPPRESS_RSP   0x00000010	/* Remote NPort supports suppress rsp */
 #define NLP_PLOGI_SND      0x00000020	/* sent PLOGI request for this entry */
 #define NLP_PRLI_SND       0x00000040	/* sent PRLI request for this entry */
 #define NLP_ADISC_SND      0x00000080	/* sent ADISC request for this entry */
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index fcc083cc00e0..9bee888b7dc4 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -3742,9 +3742,18 @@ struct wqe_common {
 #define LPFC_ELS_ID_FDISC	2
 #define LPFC_ELS_ID_LOGO	1
 #define LPFC_ELS_ID_DEFAULT	0
+#define wqe_irsp_SHIFT        4
+#define wqe_irsp_MASK         0x00000001
+#define wqe_irsp_WORD         word11
+#define wqe_sup_SHIFT         6
+#define wqe_sup_MASK          0x00000001
+#define wqe_sup_WORD          word11
 #define wqe_wqec_SHIFT        7
 #define wqe_wqec_MASK         0x00000001
 #define wqe_wqec_WORD         word11
+#define wqe_irsplen_SHIFT     8
+#define wqe_irsplen_MASK      0x0000000f
+#define wqe_irsplen_WORD      word11
 #define wqe_cqid_SHIFT        16
 #define wqe_cqid_MASK         0x0000ffff
 #define wqe_cqid_WORD         word11
@@ -4037,6 +4046,35 @@ struct fcp_icmnd64_wqe {
 	uint32_t rsvd_12_15[4];        /* word 12-15 */
 };
 
+struct fcp_trsp64_wqe {
+	struct ulp_bde64 bde;
+	uint32_t response_len;
+	uint32_t rsvd_4_5[2];
+	struct wqe_common wqe_com;      /* words 6-11 */
+	uint32_t rsvd_12_15[4];         /* word 12-15 */
+};
+
+struct fcp_tsend64_wqe {
+	struct ulp_bde64 bde;
+	uint32_t payload_offset_len;
+	uint32_t relative_offset;
+	uint32_t reserved;
+	struct wqe_common wqe_com;     /* words 6-11 */
+	uint32_t fcp_data_len;         /* word 12 */
+	uint32_t rsvd_13_15[3];        /* word 13-15 */
+};
+
+struct fcp_treceive64_wqe {
+	struct ulp_bde64 bde;
+	uint32_t payload_offset_len;
+	uint32_t relative_offset;
+	uint32_t reserved;
+	struct wqe_common wqe_com;     /* words 6-11 */
+	uint32_t fcp_data_len;         /* word 12 */
+	uint32_t rsvd_13_15[3];        /* word 13-15 */
+};
+#define TXRDY_PAYLOAD_LEN      12
+
 
 union lpfc_wqe {
 	uint32_t words[16];
@@ -4052,6 +4090,10 @@ union lpfc_wqe {
 	struct xmit_els_rsp64_wqe xmit_els_rsp;
 	struct els_request64_wqe els_req;
 	struct gen_req64_wqe gen_req;
+	struct fcp_trsp64_wqe fcp_trsp;
+	struct fcp_tsend64_wqe fcp_tsend;
+	struct fcp_treceive64_wqe fcp_treceive;
+
 };
 
 union lpfc_wqe128 {
@@ -4060,6 +4102,9 @@ union lpfc_wqe128 {
 	struct fcp_icmnd64_wqe fcp_icmd;
 	struct fcp_iread64_wqe fcp_iread;
 	struct fcp_iwrite64_wqe fcp_iwrite;
+	struct fcp_trsp64_wqe fcp_trsp;
+	struct fcp_tsend64_wqe fcp_tsend;
+	struct fcp_treceive64_wqe fcp_treceive;
 	struct xmit_seq64_wqe xmit_sequence;
 	struct gen_req64_wqe gen_req;
 };
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 474bafc63055..03fa3f02e33e 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -73,6 +73,7 @@ static int lpfc_create_bootstrap_mbox(struct lpfc_hba *);
 static int lpfc_setup_endian_order(struct lpfc_hba *);
 static void lpfc_destroy_bootstrap_mbox(struct lpfc_hba *);
 static void lpfc_free_els_sgl_list(struct lpfc_hba *);
+static void lpfc_free_nvmet_sgl_list(struct lpfc_hba *);
 static void lpfc_init_sgl_list(struct lpfc_hba *);
 static int lpfc_init_active_sgl_array(struct lpfc_hba *);
 static void lpfc_free_active_sgl(struct lpfc_hba *);
@@ -88,6 +89,7 @@ static void lpfc_sli4_oas_verify(struct lpfc_hba *phba);
 static struct scsi_transport_template *lpfc_transport_template = NULL;
 static struct scsi_transport_template *lpfc_vport_transport_template = NULL;
 static DEFINE_IDR(lpfc_hba_index);
+#define LPFC_NVMET_BUF_POST 254
 
 /**
  * lpfc_config_port_prep - Perform lpfc initialization prior to config port
@@ -1023,10 +1025,17 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 	list_for_each_entry(sglq_entry,
 		&phba->sli4_hba.lpfc_abts_els_sgl_list, list)
 		sglq_entry->state = SGL_FREED;
+	list_for_each_entry(sglq_entry,
+		&phba->sli4_hba.lpfc_abts_nvmet_sgl_list, list)
+		sglq_entry->state = SGL_FREED;
 
 	list_splice_init(&phba->sli4_hba.lpfc_abts_els_sgl_list,
 			&phba->sli4_hba.lpfc_els_sgl_list);
 
+	if (phba->sli4_hba.nvme_wq)
+		list_splice_init(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list,
+				 &phba->sli4_hba.lpfc_nvmet_sgl_list);
+
 	spin_unlock(&phba->sli4_hba.sgl_list_lock);
 	/* abts_scsi_buf_list_lock required because worker thread uses this
 	 * list.
@@ -3320,6 +3329,128 @@ lpfc_sli4_els_sgl_update(struct lpfc_hba *phba)
 	return rc;
 }
 
+/**
+ * lpfc_sli4_nvmet_sgl_update - update xri-sgl sizing and mapping
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine first calculates the sizes of the current els and allocated
+ * scsi sgl lists, and then goes through all sgls to updates the physical
+ * XRIs assigned due to port function reset. During port initialization, the
+ * current els and allocated scsi sgl lists are 0s.
+ *
+ * Return codes
+ *   0 - successful (for now, it always returns 0)
+ **/
+int
+lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba)
+{
+	struct lpfc_sglq *sglq_entry = NULL, *sglq_entry_next = NULL;
+	uint16_t i, lxri, xri_cnt, els_xri_cnt;
+	uint16_t nvmet_xri_cnt, tot_cnt;
+	LIST_HEAD(nvmet_sgl_list);
+	int rc;
+
+	/*
+	 * update on pci function's nvmet xri-sgl list
+	 */
+	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
+	nvmet_xri_cnt = 0;
+	tot_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
+
+	if (nvmet_xri_cnt > phba->sli4_hba.nvmet_xri_cnt) {
+		/* els xri-sgl expanded */
+		xri_cnt = nvmet_xri_cnt - phba->sli4_hba.nvmet_xri_cnt;
+		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+				"6302 NVMET xri-sgl cnt grew from %d to %d\n",
+				phba->sli4_hba.nvmet_xri_cnt, nvmet_xri_cnt);
+		/* allocate the additional nvmet sgls */
+		for (i = 0; i < xri_cnt; i++) {
+			sglq_entry = kzalloc(sizeof(struct lpfc_sglq),
+					     GFP_KERNEL);
+			if (sglq_entry == NULL) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+						"6303 Failure to allocate an "
+						"NVMET sgl entry:%d\n", i);
+				rc = -ENOMEM;
+				goto out_free_mem;
+			}
+			sglq_entry->buff_type = NVMET_BUFF_TYPE;
+			sglq_entry->virt = lpfc_nvmet_buf_alloc(phba, 0,
+							   &sglq_entry->phys);
+			if (sglq_entry->virt == NULL) {
+				kfree(sglq_entry);
+				lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+						"6304 Failure to allocate an "
+						"NVMET buf:%d\n", i);
+				rc = -ENOMEM;
+				goto out_free_mem;
+			}
+			sglq_entry->sgl = sglq_entry->virt;
+			memset(sglq_entry->sgl, 0,
+			       phba->cfg_sg_dma_buf_size);
+			sglq_entry->state = SGL_FREED;
+			list_add_tail(&sglq_entry->list, &nvmet_sgl_list);
+		}
+		spin_lock_irq(&phba->hbalock);
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
+		list_splice_init(&nvmet_sgl_list,
+				 &phba->sli4_hba.lpfc_nvmet_sgl_list);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
+		spin_unlock_irq(&phba->hbalock);
+	} else if (nvmet_xri_cnt < phba->sli4_hba.nvmet_xri_cnt) {
+		/* nvmet xri-sgl shrunk */
+		xri_cnt = phba->sli4_hba.nvmet_xri_cnt - nvmet_xri_cnt;
+		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+				"6305 NVMET xri-sgl count decreased from "
+				"%d to %d\n", phba->sli4_hba.nvmet_xri_cnt,
+				nvmet_xri_cnt);
+		spin_lock_irq(&phba->hbalock);
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
+		list_splice_init(&phba->sli4_hba.lpfc_nvmet_sgl_list,
+				 &nvmet_sgl_list);
+		/* release extra nvmet sgls from list */
+		for (i = 0; i < xri_cnt; i++) {
+			list_remove_head(&nvmet_sgl_list,
+					 sglq_entry, struct lpfc_sglq, list);
+			if (sglq_entry) {
+				lpfc_nvmet_buf_free(phba, sglq_entry->virt,
+						    sglq_entry->phys);
+				kfree(sglq_entry);
+			}
+		}
+		list_splice_init(&nvmet_sgl_list,
+				 &phba->sli4_hba.lpfc_nvmet_sgl_list);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
+		spin_unlock_irq(&phba->hbalock);
+	} else
+		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+				"6306 NVMET xri-sgl count unchanged: %d\n",
+				nvmet_xri_cnt);
+	phba->sli4_hba.nvmet_xri_cnt = nvmet_xri_cnt;
+
+	/* update xris to nvmet sgls on the list */
+	sglq_entry = NULL;
+	sglq_entry_next = NULL;
+	list_for_each_entry_safe(sglq_entry, sglq_entry_next,
+				 &phba->sli4_hba.lpfc_nvmet_sgl_list, list) {
+		lxri = lpfc_sli4_next_xritag(phba);
+		if (lxri == NO_XRI) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+					"6307 Failed to allocate xri for "
+					"NVMET sgl\n");
+			rc = -ENOMEM;
+			goto out_free_mem;
+		}
+		sglq_entry->sli4_lxritag = lxri;
+		sglq_entry->sli4_xritag = phba->sli4_hba.xri_ids[lxri];
+	}
+	return 0;
+
+out_free_mem:
+	lpfc_free_nvmet_sgl_list(phba);
+	return rc;
+}
+
 /**
  * lpfc_sli4_scsi_sgl_update - update xri-sgl sizing and mapping
  * @phba: pointer to lpfc hba data structure.
@@ -5228,11 +5359,12 @@ lpfc_setup_driver_resource_phase1(struct lpfc_hba *phba)
 	init_waitqueue_head(&phba->work_waitq);
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-			"1403 Protocols supported %s %s\n",
+			"1403 Protocols supported %s %s %s\n",
 			((phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) ?
 				"SCSI" : " "),
 			((phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) ?
-				"NVME" : " "));
+				"NVME" : " "),
+			(phba->nvmet_support ? "NVMET" : " "));
 
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
 		/* Initialize the scsi buffer list used by driver for scsi IO */
@@ -5447,11 +5579,13 @@ static int
 lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 {
 	LPFC_MBOXQ_t *mboxq;
+	MAILBOX_t *mb;
 	int rc, i, max_buf_size;
 	uint8_t pn_page[LPFC_MAX_SUPPORTED_PAGES] = {0};
 	struct lpfc_mqe *mqe;
 	int longs;
 	int fof_vectors = 0;
+	uint64_t wwn;
 
 	phba->sli4_hba.num_online_cpu = num_online_cpus();
 	phba->sli4_hba.num_present_cpu = lpfc_present_cpu;
@@ -5597,6 +5731,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	/* This abort list used by worker thread */
 	spin_lock_init(&phba->sli4_hba.sgl_list_lock);
+	spin_lock_init(&phba->sli4_hba.nvmet_io_lock);
 
 	/*
 	 * Initialize driver internal slow-path work queues
@@ -5673,7 +5808,43 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		goto out_free_bsmbx;
 	}
 
+	/* Check for NVMET being configured */
 	phba->nvmet_support = 0;
+	if (lpfc_enable_nvmet_cnt) {
+
+		/* First get WWN of HBA instance */
+		lpfc_read_nv(phba, mboxq);
+		rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+		if (rc != MBX_SUCCESS) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+					"6016 Mailbox failed , mbxCmd x%x "
+					"READ_NV, mbxStatus x%x\n",
+					bf_get(lpfc_mqe_command, &mboxq->u.mqe),
+					bf_get(lpfc_mqe_status, &mboxq->u.mqe));
+			rc = -EIO;
+			goto out_free_bsmbx;
+		}
+		mb = &mboxq->u.mb;
+		memcpy(&wwn, (char *)mb->un.varRDnvp.nodename,
+		       sizeof(uint64_t));
+		wwn = cpu_to_be64(wwn);
+		phba->sli4_hba.wwnn.u.name = wwn;
+		memcpy(&wwn, (char *)mb->un.varRDnvp.portname,
+		       sizeof(uint64_t));
+		/* wwn is WWPN of HBA instance */
+		wwn = cpu_to_be64(wwn);
+		phba->sli4_hba.wwpn.u.name = wwn;
+
+		/* Check to see if it matches any module parameter */
+		for (i = 0; i < lpfc_enable_nvmet_cnt; i++) {
+			if (wwn == lpfc_enable_nvmet[i]) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6017 NVME Target %016llx\n",
+						wwn);
+				phba->nvmet_support = 1; /* a match */
+			}
+		}
+	}
 
 	lpfc_nvme_mod_param_dep(phba);
 
@@ -5869,6 +6040,7 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	/* Free the ELS sgl list */
 	lpfc_free_active_sgl(phba);
 	lpfc_free_els_sgl_list(phba);
+	lpfc_free_nvmet_sgl_list(phba);
 
 	/* Free the completion queue EQ event pool */
 	lpfc_sli4_cq_event_release_all(phba);
@@ -6089,6 +6261,33 @@ lpfc_free_els_sgl_list(struct lpfc_hba *phba)
 	lpfc_free_sgl_list(phba, &sglq_list);
 }
 
+/**
+ * lpfc_free_nvmet_sgl_list - Free nvmet sgl list.
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked to free the driver's nvmet sgl list and memory.
+ **/
+static void
+lpfc_free_nvmet_sgl_list(struct lpfc_hba *phba)
+{
+	struct lpfc_sglq *sglq_entry = NULL, *sglq_next = NULL;
+	LIST_HEAD(sglq_list);
+
+	/* Retrieve all nvmet sgls from driver list */
+	spin_lock_irq(&phba->hbalock);
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
+	list_splice_init(&phba->sli4_hba.lpfc_nvmet_sgl_list, &sglq_list);
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
+	spin_unlock_irq(&phba->hbalock);
+
+	/* Now free the sgl list */
+	list_for_each_entry_safe(sglq_entry, sglq_next, &sglq_list, list) {
+		list_del(&sglq_entry->list);
+		lpfc_nvmet_buf_free(phba, sglq_entry->virt, sglq_entry->phys);
+		kfree(sglq_entry);
+	}
+}
+
 /**
  * lpfc_init_active_sgl_array - Allocate the buf to track active ELS XRIs.
  * @phba: pointer to lpfc hba data structure.
@@ -6138,6 +6337,8 @@ lpfc_init_sgl_list(struct lpfc_hba *phba)
 	/* Initialize and populate the sglq list per host/VF. */
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_els_sgl_list);
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_els_sgl_list);
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_sgl_list);
+	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
 
 	/* els xri-sgl book keeping */
 	phba->sli4_hba.els_xri_cnt = 0;
@@ -6416,6 +6617,22 @@ lpfc_create_shost(struct lpfc_hba *phba)
 	shost = lpfc_shost_from_vport(vport);
 	phba->pport = vport;
 
+	if (phba->nvmet_support) {
+		/* Only 1 vport (pport) will support NVME target */
+		if (phba->txrdy_payload_pool == NULL) {
+			phba->txrdy_payload_pool = pci_pool_create(
+				"txrdy_pool", phba->pcidev,
+				TXRDY_PAYLOAD_LEN, 16, 0);
+			if (phba->txrdy_payload_pool) {
+				phba->targetport = NULL;
+				phba->cfg_enable_fc4_type = LPFC_ENABLE_NVME;
+				lpfc_printf_log(phba, KERN_INFO,
+						LOG_INIT | LOG_NVME_DISC,
+						"6076 NVME Target Found\n");
+			}
+		}
+	}
+
 	lpfc_debugfs_initialize(vport);
 	/* Put reference to SCSI host to driver's device private data */
 	pci_set_drvdata(phba->pcidev, shost);
@@ -7459,7 +7676,7 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba)
 		phba->cfg_nvme_io_channel = io_channel;
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"2574 IRQs: %d, IO Channels: fcp %d nvme %d\n",
+			"2574 IO channels: irqs %d fcp %d nvme %d\n",
 			phba->io_channel_irqs, phba->cfg_fcp_io_channel,
 			phba->cfg_nvme_io_channel);
 
@@ -9164,8 +9381,9 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 	if (phba->cfg_fof)
 		vectors++;
 
-	rc = pci_alloc_irq_vectors(phba->pcidev, 2, vectors,
-				PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+	rc = pci_alloc_irq_vectors(phba->pcidev,
+				(phba->nvmet_support) ? 1 : 2,
+				vectors, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
 	if (rc < 0) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0484 PCI enable MSI-X failed (%d)\n", rc);
@@ -9447,6 +9665,8 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 	int nvme_xri_cmpl = 1;
 	int fcp_xri_cmpl = 1;
 	int els_xri_cmpl = list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
+	int nvmet_xri_cmpl =
+			list_empty(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
 
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
 		fcp_xri_cmpl =
@@ -9455,7 +9675,8 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 		nvme_xri_cmpl =
 			list_empty(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
 
-	while (!fcp_xri_cmpl || !els_xri_cmpl || !nvme_xri_cmpl) {
+	while (!fcp_xri_cmpl || !els_xri_cmpl || !nvme_xri_cmpl ||
+	       !nvmet_xri_cmpl) {
 		if (wait_time > LPFC_XRI_EXCH_BUSY_WAIT_TMO) {
 			if (!nvme_xri_cmpl)
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -9488,6 +9709,9 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 
 		els_xri_cmpl =
 			list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
+
+		nvmet_xri_cmpl =
+			list_empty(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
 	}
 }
 
@@ -9725,6 +9949,9 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 		phba->cfg_enable_fc4_type = LPFC_ENABLE_FCP;
 	}
 
+	if (bf_get(cfg_xib, mbx_sli4_parameters) && phba->cfg_suppress_rsp)
+		phba->sli.sli_flag |= LPFC_SLI_SUPPRESS_RSP;
+
 	/* Make sure that sge_supp_len can be handled by the driver */
 	if (sli4_params->sge_supp_len > LPFC_MAX_SGE_SIZE)
 		sli4_params->sge_supp_len = LPFC_MAX_SGE_SIZE;
@@ -10376,13 +10603,15 @@ lpfc_sli4_get_els_iocb_cnt(struct lpfc_hba *phba)
  * lpfc_sli4_get_iocb_cnt - Calculate the # of total IOCBs to reserve
  * @phba: pointer to lpfc hba data structure.
  *
- * returns the number of ELS/CT
+ * returns the number of ELS/CT + NVMET IOCBs to reserve
  **/
 int
 lpfc_sli4_get_iocb_cnt(struct lpfc_hba *phba)
 {
 	int max_xri = lpfc_sli4_get_els_iocb_cnt(phba);
 
+	if (phba->nvmet_support)
+		max_xri += LPFC_NVMET_BUF_POST;
 	return max_xri;
 }
 
@@ -10755,6 +10984,7 @@ lpfc_pci_remove_one_s4(struct pci_dev *pdev)
 	/* Remove FC host and then SCSI host with the physical port */
 	fc_remove_host(shost);
 	scsi_remove_host(shost);
+	/* todo: tgt: remove targetport */
 
 	/* Perform ndlp cleanup on the physical port.  The nvme localport
 	 * is destroyed after to ensure all rports are io-disabled.
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index c65a1ec3d2e4..32db255f5216 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -40,6 +40,7 @@
 #include "lpfc.h"
 #include "lpfc_scsi.h"
 #include "lpfc_nvme.h"
+#include "lpfc_nvmet.h"
 #include "lpfc_crtn.h"
 #include "lpfc_logmsg.h"
 
@@ -441,6 +442,44 @@ lpfc_mbuf_free(struct lpfc_hba * phba, void *virt, dma_addr_t dma)
 	return;
 }
 
+/**
+ * lpfc_nvmet_buf_alloc - Allocate an nvmet_buf from the
+ * lpfc_sg_dma_buf_pool PCI pool
+ * @phba: HBA which owns the pool to allocate from
+ * @mem_flags: indicates if this is a priority (MEM_PRI) allocation
+ * @handle: used to return the DMA-mapped address of the nvmet_buf
+ *
+ * Description: Allocates a DMA-mapped buffer from the lpfc_sg_dma_buf_pool
+ * PCI pool.  Allocates from generic pci_pool_alloc function.
+ *
+ * Returns:
+ *   pointer to the allocated nvmet_buf on success
+ *   NULL on failure
+ **/
+void *
+lpfc_nvmet_buf_alloc(struct lpfc_hba *phba, int mem_flags, dma_addr_t *handle)
+{
+	void *ret;
+
+	ret = pci_pool_alloc(phba->lpfc_sg_dma_buf_pool, GFP_KERNEL, handle);
+	return ret;
+}
+
+/**
+ * lpfc_nvmet_buf_free - Free an nvmet_buf from the lpfc_sg_dma_buf_pool
+ * PCI pool
+ * @phba: HBA which owns the pool to return to
+ * @virt: nvmet_buf to free
+ * @dma: the DMA-mapped address of the lpfc_sg_dma_buf_pool to be freed
+ *
+ * Returns: None
+ **/
+void
+lpfc_nvmet_buf_free(struct lpfc_hba *phba, void *virt, dma_addr_t dma)
+{
+	pci_pool_free(phba->lpfc_sg_dma_buf_pool, virt, dma);
+}
+
 /**
  * lpfc_els_hbq_alloc - Allocate an HBQ buffer
  * @phba: HBA to allocate HBQ buffer for
@@ -553,6 +592,134 @@ lpfc_sli4_rb_free(struct lpfc_hba *phba, struct hbq_dmabuf *dmab)
 	kfree(dmab);
 }
 
+/**
+ * lpfc_sli4_nvmet_alloc - Allocate an SLI4 Receive buffer
+ * @phba: HBA to allocate a receive buffer for
+ *
+ * Description: Allocates a DMA-mapped receive buffer from the lpfc_hrb_pool PCI
+ * pool along a non-DMA-mapped container for it.
+ *
+ * Notes: Not interrupt-safe.  Must be called with no locks held.
+ *
+ * Returns:
+ *   pointer to HBQ on success
+ *   NULL on failure
+ **/
+struct rqb_dmabuf *
+lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
+{
+	struct rqb_dmabuf *dma_buf;
+	struct lpfc_iocbq *nvmewqe;
+	union lpfc_wqe128 *wqe;
+
+	dma_buf = kzalloc(sizeof(struct rqb_dmabuf), GFP_KERNEL);
+	if (!dma_buf)
+		return NULL;
+
+	dma_buf->hbuf.virt = pci_pool_alloc(phba->lpfc_hrb_pool, GFP_KERNEL,
+					    &dma_buf->hbuf.phys);
+	if (!dma_buf->hbuf.virt) {
+		kfree(dma_buf);
+		return NULL;
+	}
+	dma_buf->dbuf.virt = pci_pool_alloc(phba->lpfc_drb_pool, GFP_KERNEL,
+					    &dma_buf->dbuf.phys);
+	if (!dma_buf->dbuf.virt) {
+		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
+			      dma_buf->hbuf.phys);
+		kfree(dma_buf);
+		return NULL;
+	}
+	dma_buf->total_size = LPFC_DATA_BUF_SIZE;
+
+	dma_buf->context = kzalloc(sizeof(struct lpfc_nvmet_rcv_ctx),
+				   GFP_KERNEL);
+	if (!dma_buf->context) {
+		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
+			      dma_buf->dbuf.phys);
+		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
+			      dma_buf->hbuf.phys);
+		kfree(dma_buf);
+		return NULL;
+	}
+
+	dma_buf->iocbq = lpfc_sli_get_iocbq(phba);
+	dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
+	if (!dma_buf->iocbq) {
+		kfree(dma_buf->context);
+		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
+			      dma_buf->dbuf.phys);
+		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
+			      dma_buf->hbuf.phys);
+		kfree(dma_buf);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+				"2621 Ran out of nvmet iocb/WQEs\n");
+		return NULL;
+	}
+	nvmewqe = dma_buf->iocbq;
+	wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
+	/* Initialize WQE */
+	memset(wqe, 0, sizeof(union lpfc_wqe));
+	/* Word 7 */
+	bf_set(wqe_ct, &wqe->generic.wqe_com, SLI4_CT_RPI);
+	bf_set(wqe_class, &wqe->generic.wqe_com, CLASS3);
+	bf_set(wqe_pu, &wqe->generic.wqe_com, 1);
+	/* Word 10 */
+	bf_set(wqe_nvme, &wqe->fcp_tsend.wqe_com, 1);
+	bf_set(wqe_ebde_cnt, &wqe->generic.wqe_com, 0);
+	bf_set(wqe_qosd, &wqe->generic.wqe_com, 0);
+
+	dma_buf->iocbq->context1 = NULL;
+	spin_lock(&phba->sli4_hba.sgl_list_lock);
+	dma_buf->sglq = __lpfc_sli_get_nvmet_sglq(phba, dma_buf->iocbq);
+	spin_unlock(&phba->sli4_hba.sgl_list_lock);
+	if (!dma_buf->sglq) {
+		lpfc_sli_release_iocbq(phba, dma_buf->iocbq);
+		kfree(dma_buf->context);
+		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
+			      dma_buf->dbuf.phys);
+		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
+			      dma_buf->hbuf.phys);
+		kfree(dma_buf);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+				"6132 Ran out of nvmet XRIs\n");
+		return NULL;
+	}
+	return dma_buf;
+}
+
+/**
+ * lpfc_sli4_nvmet_free - Frees a receive buffer
+ * @phba: HBA buffer was allocated for
+ * @dmab: DMA Buffer container returned by lpfc_sli4_rbq_alloc
+ *
+ * Description: Frees both the container and the DMA-mapped buffers returned by
+ * lpfc_sli4_nvmet_alloc.
+ *
+ * Notes: Can be called with or without locks held.
+ *
+ * Returns: None
+ **/
+void
+lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab)
+{
+	unsigned long flags;
+
+	__lpfc_clear_active_sglq(phba, dmab->sglq->sli4_lxritag);
+	dmab->sglq->state = SGL_FREED;
+	dmab->sglq->ndlp = NULL;
+
+	spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock, flags);
+	list_add_tail(&dmab->sglq->list, &phba->sli4_hba.lpfc_nvmet_sgl_list);
+	spin_unlock_irqrestore(&phba->sli4_hba.sgl_list_lock, flags);
+
+	lpfc_sli_release_iocbq(phba, dmab->iocbq);
+	kfree(dmab->context);
+	pci_pool_free(phba->lpfc_hrb_pool, dmab->hbuf.virt, dmab->hbuf.phys);
+	pci_pool_free(phba->lpfc_drb_pool, dmab->dbuf.virt, dmab->dbuf.phys);
+	kfree(dmab);
+}
+
 /**
  * lpfc_in_buf_free - Free a DMA buffer
  * @phba: HBA buffer is associated with
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
new file mode 100644
index 000000000000..f7b6a3f374a4
--- /dev/null
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -0,0 +1,101 @@
+/*******************************************************************
+ * This file is part of the Emulex Linux Device Driver for         *
+ * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
+ *                                                                 *
+ * This program is free software; you can redistribute it and/or   *
+ * modify it under the terms of version 2 of the GNU General       *
+ * Public License as published by the Free Software Foundation.    *
+ * This program is distributed in the hope that it will be useful. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ ********************************************************************/
+
+#define LPFC_NVMET_MIN_SEGS		16
+#define LPFC_NVMET_DEFAULT_SEGS		64	/* 256K IOs */
+#define LPFC_NVMET_MAX_SEGS		510
+#define LPFC_NVMET_SUCCESS_LEN	12
+
+/* Used for NVME Target */
+struct lpfc_nvmet_tgtport {
+	struct lpfc_hba *phba;
+	struct completion tport_unreg_done;
+
+	/* Stats counters - lpfc_nvmet_unsol_ls_buffer */
+	atomic_t rcv_ls_req_in;
+	atomic_t rcv_ls_req_out;
+	atomic_t rcv_ls_req_drop;
+	atomic_t xmt_ls_abort;
+
+	/* Stats counters - lpfc_nvmet_xmt_ls_rsp */
+	atomic_t xmt_ls_rsp;
+	atomic_t xmt_ls_drop;
+
+	/* Stats counters - lpfc_nvmet_xmt_ls_rsp_cmp */
+	atomic_t xmt_ls_rsp_error;
+	atomic_t xmt_ls_rsp_cmpl;
+
+	/* Stats counters - lpfc_nvmet_unsol_fcp_buffer */
+	atomic_t rcv_fcp_cmd_in;
+	atomic_t rcv_fcp_cmd_out;
+	atomic_t rcv_fcp_cmd_drop;
+
+	/* Stats counters - lpfc_nvmet_xmt_fcp_op */
+	atomic_t xmt_fcp_abort;
+	atomic_t xmt_fcp_drop;
+	atomic_t xmt_fcp_read_rsp;
+	atomic_t xmt_fcp_read;
+	atomic_t xmt_fcp_write;
+	atomic_t xmt_fcp_rsp;
+
+	/* Stats counters - lpfc_nvmet_xmt_fcp_op_cmp */
+	atomic_t xmt_fcp_rsp_cmpl;
+	atomic_t xmt_fcp_rsp_error;
+	atomic_t xmt_fcp_rsp_drop;
+
+
+	/* Stats counters - lpfc_nvmet_unsol_issue_abort */
+	atomic_t xmt_abort_rsp;
+	atomic_t xmt_abort_rsp_error;
+
+	/* Stats counters - lpfc_nvmet_xmt_abort_cmp */
+	atomic_t xmt_abort_cmpl;
+};
+
+struct lpfc_nvmet_rcv_ctx {
+	union {
+		struct nvmefc_tgt_ls_req ls_req;
+		struct nvmefc_tgt_fcp_req fcp_req;
+	} ctx;
+	struct lpfc_hba *phba;
+	struct lpfc_iocbq *wqeq;
+	struct lpfc_iocbq *abort_wqeq;
+	dma_addr_t txrdy_phys;
+	uint32_t *txrdy;
+	uint32_t sid;
+	uint32_t offset;
+	uint16_t oxid;
+	uint16_t size;
+	uint16_t entry_cnt;
+	uint16_t cpu;
+	uint16_t state;
+	/* States */
+#define LPFC_NVMET_STE_FREE		0
+#define LPFC_NVMET_STE_RCV		1
+#define LPFC_NVMET_STE_DATA		2
+#define LPFC_NVMET_STE_ABORT		3
+#define LPFC_NVMET_STE_RSP		4
+#define LPFC_NVMET_STE_DONE		5
+	uint16_t flag;
+#define LPFC_NVMET_IO_INP		1
+#define LPFC_NVMET_ABORT_OP		2
+	struct rqb_dmabuf *rqb_buffer;
+};
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 5f6ad67d5a73..f2cd0f37e03f 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -45,6 +45,7 @@
 #include "lpfc.h"
 #include "lpfc_scsi.h"
 #include "lpfc_nvme.h"
+#include "lpfc_nvmet.h"
 #include "lpfc_crtn.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_compat.h"
@@ -975,6 +976,34 @@ __lpfc_sli_get_els_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 	return sglq;
 }
 
+/**
+ * __lpfc_sli_get_nvmet_sglq - Allocates an iocb object from sgl pool
+ * @phba: Pointer to HBA context object.
+ * @piocb: Pointer to the iocbq.
+ *
+ * This function is called with the sgl_list lock held. This function
+ * gets a new driver sglq object from the sglq list. If the
+ * list is not empty then it is successful, it returns pointer to the newly
+ * allocated sglq object else it returns NULL.
+ **/
+struct lpfc_sglq *
+__lpfc_sli_get_nvmet_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
+{
+	struct list_head *lpfc_nvmet_sgl_list;
+	struct lpfc_sglq *sglq = NULL;
+
+	lpfc_nvmet_sgl_list = &phba->sli4_hba.lpfc_nvmet_sgl_list;
+
+	lockdep_assert_held(&phba->sli4_hba.sgl_list_lock);
+
+	list_remove_head(lpfc_nvmet_sgl_list, sglq, struct lpfc_sglq, list);
+	if (!sglq)
+		return NULL;
+	phba->sli4_hba.lpfc_sglq_active_list[sglq->sli4_lxritag] = sglq;
+	sglq->state = SGL_ALLOCATED;
+	return sglq;
+}
+
 /**
  * lpfc_sli_get_iocbq - Allocates an iocb object from iocb pool
  * @phba: Pointer to HBA context object.
@@ -1031,6 +1060,18 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 
 
 	if (sglq)  {
+		if (iocbq->iocb_flag & LPFC_IO_NVMET) {
+			spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock,
+					  iflag);
+			sglq->state = SGL_FREED;
+			sglq->ndlp = NULL;
+			list_add_tail(&sglq->list,
+				      &phba->sli4_hba.lpfc_nvmet_sgl_list);
+			spin_unlock_irqrestore(
+				&phba->sli4_hba.sgl_list_lock, iflag);
+			goto out;
+		}
+
 		pring = phba->sli4_hba.els_wq->pring;
 		if ((iocbq->iocb_flag & LPFC_EXCHANGE_BUSY) &&
 			(sglq->state != SGL_XRI_ABORTED)) {
@@ -1056,13 +1097,15 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 		}
 	}
 
+out:
 	/*
 	 * Clean all volatile data fields, preserve iotag and node struct.
 	 */
 	memset((char *)iocbq + start_clean, 0, sizeof(*iocbq) - start_clean);
 	iocbq->sli4_lxritag = NO_XRI;
 	iocbq->sli4_xritag = NO_XRI;
-	iocbq->iocb_flag &= ~(LPFC_IO_NVME | LPFC_IO_NVME_LS);
+	iocbq->iocb_flag &= ~(LPFC_IO_NVME | LPFC_IO_NVMET |
+			      LPFC_IO_NVME_LS);
 	list_add_tail(&iocbq->list, &phba->lpfc_iocb_list);
 }
 
@@ -2450,6 +2493,14 @@ lpfc_complete_unsol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 {
 	int i;
 
+	switch (fch_type) {
+	case FC_TYPE_NVME:
+		/* todo: tgt: forward NVME LS to transport */
+		return 1;
+	default:
+		break;
+	}
+
 	/* unSolicited Responses */
 	if (pring->prt[0].profile) {
 		if (pring->prt[0].lpfc_sli_rcv_unsol_event)
@@ -6761,7 +6812,31 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	}
 	phba->sli4_hba.els_xri_cnt = rc;
 
-	if (phba->nvmet_support == 0) {
+	if (phba->nvmet_support) {
+		/* update host nvmet xri-sgl sizes and mappings */
+		rc = lpfc_sli4_nvmet_sgl_update(phba);
+		if (unlikely(rc)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"6308 Failed to update nvmet-sgl size "
+					"and mapping: %d\n", rc);
+			goto out_destroy_queue;
+		}
+
+		/* register the nvmet sgl pool to the port */
+		rc = lpfc_sli4_repost_sgl_list(
+			phba,
+			&phba->sli4_hba.lpfc_nvmet_sgl_list,
+			phba->sli4_hba.nvmet_xri_cnt);
+		if (unlikely(rc < 0)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
+					"3117 Error %d during nvmet "
+					"sgl post\n", rc);
+			rc = -ENODEV;
+			goto out_destroy_queue;
+		}
+		phba->sli4_hba.nvmet_xri_cnt = rc;
+		/* todo: tgt: create targetport */
+	} else {
 		/* update host scsi xri-sgl sizes and mappings */
 		rc = lpfc_sli4_scsi_sgl_update(phba);
 		if (unlikely(rc)) {
@@ -13006,7 +13081,7 @@ lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 
 	if (phba->sli4_hba.nvme_cq_map &&
 	    (cqid == phba->sli4_hba.nvme_cq_map[qidx])) {
-		/* Process NVME command completion */
+		/* Process NVME / NVMET command completion */
 		cq = phba->sli4_hba.nvme_cq[qidx];
 		goto  process_cq;
 	}
@@ -17912,6 +17987,7 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, uint32_t ring_number,
 		    struct lpfc_iocbq *pwqe)
 {
 	union lpfc_wqe *wqe = &pwqe->wqe;
+	struct lpfc_nvmet_rcv_ctx *ctxp;
 	struct lpfc_queue *wq;
 	struct lpfc_sglq *sglq;
 	struct lpfc_sli_ring *pring;
@@ -17961,5 +18037,30 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, uint32_t ring_number,
 		return 0;
 	}
 
+	/* NVMET requests */
+	if (pwqe->iocb_flag & LPFC_IO_NVMET) {
+		/* Get the IO distribution (hba_wqidx) for WQ assignment. */
+		pring = phba->sli4_hba.nvme_wq[pwqe->hba_wqidx]->pring;
+
+		spin_lock_irqsave(&pring->ring_lock, iflags);
+		ctxp = pwqe->context2;
+		sglq = ctxp->rqb_buffer->sglq;
+		if (pwqe->sli4_xritag ==  NO_XRI) {
+			pwqe->sli4_lxritag = sglq->sli4_lxritag;
+			pwqe->sli4_xritag = sglq->sli4_xritag;
+		}
+		bf_set(wqe_xri_tag, &pwqe->wqe.xmit_bls_rsp.wqe_com,
+		       pwqe->sli4_xritag);
+		wq = phba->sli4_hba.nvme_wq[pwqe->hba_wqidx];
+		bf_set(wqe_cqid, &wqe->generic.wqe_com,
+		      phba->sli4_hba.nvme_cq[pwqe->hba_wqidx]->queue_id);
+		if (lpfc_sli4_wq_put(wq, wqe)) {
+			spin_unlock_irqrestore(&pring->ring_lock, iflags);
+			return WQE_ERROR;
+		}
+		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
+		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+		return 0;
+	}
 	return WQE_ERROR;
 }
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 72520125251b..f6cea02adc7c 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -93,6 +93,7 @@ struct lpfc_iocbq {
 #define LPFC_PRLI_FCP_REQ	0x100000 /* This is an NVME PRLI. */
 #define LPFC_IO_NVME	        0x200000 /* NVME FCP command */
 #define LPFC_IO_NVME_LS		0x400000 /* NVME LS command */
+#define LPFC_IO_NVMET		0x800000 /* NVMET command */
 
 	uint32_t drvrTimeout;	/* driver timeout in seconds */
 	struct lpfc_vport *vport;/* virtual port pointer */
@@ -317,6 +318,7 @@ struct lpfc_sli {
 #define LPFC_BLOCK_MGMT_IO        0x800	/* Don't allow mgmt mbx or iocb cmds */
 #define LPFC_MENLO_MAINT          0x1000 /* need for menl fw download */
 #define LPFC_SLI_ASYNC_MBX_BLK    0x2000 /* Async mailbox is blocked */
+#define LPFC_SLI_SUPPRESS_RSP     0x4000 /* Suppress RSP feature is supported */
 
 	struct lpfc_sli_ring *sli3_ring;
 
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 9cb8508b4b4b..99546eaef087 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -109,6 +109,7 @@ enum lpfc_sli4_queue_subtype {
 	LPFC_FCP,
 	LPFC_ELS,
 	LPFC_NVME,
+	LPFC_NVMET,
 	LPFC_NVME_LS,
 	LPFC_USOL
 };
@@ -610,8 +611,11 @@ struct lpfc_sli4_hba {
 	uint16_t scsi_xri_cnt;
 	uint16_t scsi_xri_start;
 	uint16_t els_xri_cnt;
+	uint16_t nvmet_xri_cnt;
 	struct list_head lpfc_els_sgl_list;
 	struct list_head lpfc_abts_els_sgl_list;
+	struct list_head lpfc_nvmet_sgl_list;
+	struct list_head lpfc_abts_nvmet_sgl_list;
 	struct list_head lpfc_abts_scsi_buf_list;
 	struct list_head lpfc_abts_nvme_buf_list;
 	struct lpfc_sglq **lpfc_sglq_active_list;
@@ -643,6 +647,7 @@ struct lpfc_sli4_hba {
 	spinlock_t abts_nvme_buf_list_lock; /* list of aborted SCSI IOs */
 	spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */
 	spinlock_t sgl_list_lock; /* list of aborted els IOs */
+	spinlock_t nvmet_io_lock;
 	uint32_t physical_port;
 
 	/* CPU to vector mapping information */
@@ -655,6 +660,7 @@ struct lpfc_sli4_hba {
 enum lpfc_sge_type {
 	GEN_BUFF_TYPE,
 	SCSI_BUFF_TYPE,
+	NVMET_BUFF_TYPE
 };
 
 enum lpfc_sgl_state {
-- 
GitLab


From 2d7dbc4c2775eb30df97be00090adbfcc7fc5086 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:35 -0800
Subject: [PATCH 150/898] scsi: lpfc: NVME Target: Receive buffer updates

NVME Target: Receive buffer updates

Allocates buffer pools and configures adapter interfaces to handle
receive buffer (asynchronous FCP CMD ius, first burst data)
from the adapter. Splits by protocol, etc.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h         |   3 +
 drivers/scsi/lpfc/lpfc_attr.c    |  81 +++-
 drivers/scsi/lpfc/lpfc_crtn.h    |   1 +
 drivers/scsi/lpfc/lpfc_debugfs.c |  25 +-
 drivers/scsi/lpfc/lpfc_hw4.h     | 347 +++++++++++++++++-
 drivers/scsi/lpfc/lpfc_init.c    | 233 +++++++++++-
 drivers/scsi/lpfc/lpfc_mbox.c    |  87 +++++
 drivers/scsi/lpfc/lpfc_sli.c     | 608 ++++++++++++++++++++++++++++++-
 drivers/scsi/lpfc/lpfc_sli4.h    |  11 +
 9 files changed, 1374 insertions(+), 22 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index b7361474880e..8a4090c6771c 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -770,8 +770,11 @@ struct lpfc_hba {
 	uint32_t cfg_suppress_rsp;
 	uint32_t cfg_nvme_oas;
 	uint32_t cfg_nvme_io_channel;
+	uint32_t cfg_nvmet_mrq;
+	uint32_t cfg_nvmet_mrq_post;
 	uint32_t cfg_enable_nvmet;
 	uint32_t cfg_nvme_enable_fb;
+	uint32_t cfg_nvmet_fb_size;
 	uint32_t cfg_total_seg_cnt;
 	uint32_t cfg_sg_seg_cnt;
 	uint32_t cfg_sg_dma_buf_size;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 835c6c1f4cd4..700a68f303f3 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -58,6 +58,10 @@
 #define LPFC_MIN_DEVLOSS_TMO	1
 #define LPFC_MAX_DEVLOSS_TMO	255
 
+#define LPFC_DEF_MRQ_POST	256
+#define LPFC_MIN_MRQ_POST	32
+#define LPFC_MAX_MRQ_POST	512
+
 /*
  * Write key size should be multiple of 4. If write key is changed
  * make sure that library write key is also changed.
@@ -3281,6 +3285,24 @@ static DEVICE_ATTR(lpfc_devloss_tmo, S_IRUGO | S_IWUSR,
 LPFC_ATTR_R(suppress_rsp, 1, 0, 1,
 	    "Enable suppress rsp feature is firmware supports it");
 
+/*
+ * lpfc_nvmet_mrq: Specify number of RQ pairs for processing NVMET cmds
+ * lpfc_nvmet_mrq = 1  use a single RQ pair
+ * lpfc_nvmet_mrq >= 2  use specified RQ pairs for MRQ
+ *
+ */
+LPFC_ATTR_R(nvmet_mrq,
+	    1, 1, 16,
+	    "Specify number of RQ pairs for processing NVMET cmds");
+
+/*
+ * lpfc_nvmet_mrq_post: Specify number buffers to post on every MRQ
+ *
+ */
+LPFC_ATTR_R(nvmet_mrq_post, LPFC_DEF_MRQ_POST,
+	    LPFC_MIN_MRQ_POST, LPFC_MAX_MRQ_POST,
+	    "Specify number of buffers to post on every MRQ");
+
 /*
  * lpfc_enable_fc4_type: Defines what FC4 types are supported.
  * Supported Values:  1 - register just FCP
@@ -4657,13 +4679,28 @@ LPFC_VPORT_ATTR_RW(first_burst_size, 0, 0, 65536,
 		   "First burst size for Targets that support first burst");
 
 /*
-* lpfc_nvme_enable_fb: Enable NVME first burst on I and T functions.
-* For the Initiator (I), enabling this parameter means that an NVME
-* PRLI response with FBA enabled and an FB_SIZE set to a nonzero value
-* will be processed by the initiator for subsequent NVME FCP IO.
+* lpfc_nvmet_fb_size: NVME Target mode supported first burst size.
+* When the driver is configured as an NVME target, this value is
+* communicated to the NVME initiator in the PRLI response.  It is
+* used only when the lpfc_nvme_enable_fb and lpfc_nvmet_support
+* parameters are set and the target is sending the PRLI RSP.
 * Parameter supported on physical port only - no NPIV support.
-* Value range is [0,1]. Default value is 0 (disabled).
+* Value range is [0,65536]. Default value is 0.
 */
+LPFC_ATTR_RW(nvmet_fb_size, 0, 0, 65536,
+	     "NVME Target mode first burst size in 512B increments.");
+
+/*
+ * lpfc_nvme_enable_fb: Enable NVME first burst on I and T functions.
+ * For the Initiator (I), enabling this parameter means that an NVMET
+ * PRLI response with FBA enabled and an FB_SIZE set to a nonzero value will be
+ * processed by the initiator for subsequent NVME FCP IO. For the target
+ * function (T), enabling this parameter qualifies the lpfc_nvmet_fb_size
+ * driver parameter as the target function's first burst size returned to the
+ * initiator in the target's NVME PRLI response. Parameter supported on physical
+ * port only - no NPIV support.
+ * Value range is [0,1]. Default value is 0 (disabled).
+ */
 LPFC_ATTR_RW(nvme_enable_fb, 0, 0, 1,
 	     "Enable First Burst feature on I and T functions.");
 
@@ -5099,7 +5136,10 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_fcp_io_channel,
 	&dev_attr_lpfc_suppress_rsp,
 	&dev_attr_lpfc_nvme_io_channel,
+	&dev_attr_lpfc_nvmet_mrq,
+	&dev_attr_lpfc_nvmet_mrq_post,
 	&dev_attr_lpfc_nvme_enable_fb,
+	&dev_attr_lpfc_nvmet_fb_size,
 	&dev_attr_lpfc_enable_bg,
 	&dev_attr_lpfc_soft_wwnn,
 	&dev_attr_lpfc_soft_wwpn,
@@ -6136,9 +6176,12 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	lpfc_suppress_rsp_init(phba, lpfc_suppress_rsp);
 
 	lpfc_enable_fc4_type_init(phba, lpfc_enable_fc4_type);
+	lpfc_nvmet_mrq_init(phba, lpfc_nvmet_mrq);
+	lpfc_nvmet_mrq_post_init(phba, lpfc_nvmet_mrq_post);
 
 	/* Initialize first burst. Target vs Initiator are different. */
 	lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb);
+	lpfc_nvmet_fb_size_init(phba, lpfc_nvmet_fb_size);
 	lpfc_fcp_io_channel_init(phba, lpfc_fcp_io_channel);
 	lpfc_nvme_io_channel_init(phba, lpfc_nvme_io_channel);
 
@@ -6205,9 +6248,35 @@ lpfc_nvme_mod_param_dep(struct lpfc_hba *phba)
 	    phba->nvmet_support) {
 		phba->cfg_enable_fc4_type &= ~LPFC_ENABLE_FCP;
 		phba->cfg_fcp_io_channel = 0;
-	} else
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
+				"6013 %s x%x fb_size x%x, fb_max x%x\n",
+				"NVME Target PRLI ACC enable_fb ",
+				phba->cfg_nvme_enable_fb,
+				phba->cfg_nvmet_fb_size,
+				LPFC_NVMET_FB_SZ_MAX);
+
+		if (phba->cfg_nvme_enable_fb == 0)
+			phba->cfg_nvmet_fb_size = 0;
+		else {
+			if (phba->cfg_nvmet_fb_size > LPFC_NVMET_FB_SZ_MAX)
+				phba->cfg_nvmet_fb_size = LPFC_NVMET_FB_SZ_MAX;
+		}
+
+		/* Adjust lpfc_nvmet_mrq to avoid running out of WQE slots */
+		if (phba->cfg_nvmet_mrq > phba->cfg_nvme_io_channel) {
+			phba->cfg_nvmet_mrq = phba->cfg_nvme_io_channel;
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
+					"6018 Adjust lpfc_nvmet_mrq to %d\n",
+					phba->cfg_nvmet_mrq);
+		}
+	} else {
 		/* Not NVME Target mode.  Turn off Target parameters. */
 		phba->nvmet_support = 0;
+		phba->cfg_nvmet_mrq = 0;
+		phba->cfg_nvmet_mrq_post = 0;
+		phba->cfg_nvmet_fb_size = 0;
+	}
 
 	if (phba->cfg_fcp_io_channel > phba->cfg_nvme_io_channel)
 		phba->io_channel_irqs = phba->cfg_fcp_io_channel;
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 1e97b1a106c5..2e7a7f7f43b2 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -229,6 +229,7 @@ void lpfc_reg_vfi(struct lpfcMboxq *, struct lpfc_vport *, dma_addr_t);
 void lpfc_init_vpi(struct lpfc_hba *, struct lpfcMboxq *, uint16_t);
 void lpfc_unreg_vfi(struct lpfcMboxq *, struct lpfc_vport *);
 void lpfc_reg_fcfi(struct lpfc_hba *, struct lpfcMboxq *);
+void lpfc_reg_fcfi_mrq(struct lpfc_hba *phba, struct lpfcMboxq *mbox, int mode);
 void lpfc_unreg_fcfi(struct lpfcMboxq *, uint16_t);
 void lpfc_resume_rpi(struct lpfcMboxq *, struct lpfc_nodelist *);
 int lpfc_check_pending_fcoe_event(struct lpfc_hba *, uint8_t);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index e54307dff8be..abc39f605960 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -2837,7 +2837,7 @@ __lpfc_idiag_print_rqpair(struct lpfc_queue *qp, struct lpfc_queue *datqp,
 
 static int
 lpfc_idiag_cqs_for_eq(struct lpfc_hba *phba, char *pbuffer,
-		int *len, int max_cnt, int eq_id)
+		int *len, int max_cnt, int eqidx, int eq_id)
 {
 	struct lpfc_queue *qp;
 	int qidx, rc;
@@ -2880,6 +2880,27 @@ lpfc_idiag_cqs_for_eq(struct lpfc_hba *phba, char *pbuffer,
 			return 1;
 	}
 
+	if (phba->cfg_nvmet_mrq > eqidx) {
+		/* NVMET CQset */
+		qp = phba->sli4_hba.nvmet_cqset[eqidx];
+		*len = __lpfc_idiag_print_cq(qp, "NVMET CQset", pbuffer, *len);
+
+		/* Reset max counter */
+		qp->CQ_max_cqe = 0;
+
+		if (*len >= max_cnt)
+			return 1;
+
+		/* RQ header */
+		qp = phba->sli4_hba.nvmet_mrq_hdr[eqidx];
+		*len = __lpfc_idiag_print_rqpair(qp,
+				phba->sli4_hba.nvmet_mrq_data[eqidx],
+				"NVMET MRQ", pbuffer, *len);
+
+		if (*len >= max_cnt)
+			return 1;
+	}
+
 	return 0;
 }
 
@@ -2977,7 +2998,7 @@ lpfc_idiag_queinfo_read(struct file *file, char __user *buf, size_t nbytes,
 
 		/* will dump both fcp and nvme cqs/wqs for the eq */
 		rc = lpfc_idiag_cqs_for_eq(phba, pbuffer, &len,
-			max_cnt, qp->queue_id);
+			max_cnt, x, qp->queue_id);
 		if (rc)
 			goto too_big;
 
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 9bee888b7dc4..0fddb2317875 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -962,6 +962,7 @@ struct mbox_header {
 #define LPFC_MBOX_OPCODE_FCOE_DELETE_FCF		0x0A
 #define LPFC_MBOX_OPCODE_FCOE_POST_HDR_TEMPLATE		0x0B
 #define LPFC_MBOX_OPCODE_FCOE_REDISCOVER_FCF		0x10
+#define LPFC_MBOX_OPCODE_FCOE_CQ_CREATE_SET		0x1D
 #define LPFC_MBOX_OPCODE_FCOE_SET_FCLINK_SETTINGS	0x21
 #define LPFC_MBOX_OPCODE_FCOE_LINK_DIAG_STATE		0x22
 #define LPFC_MBOX_OPCODE_FCOE_LINK_DIAG_LOOPBACK	0x23
@@ -1143,6 +1144,116 @@ struct lpfc_mbx_cq_create {
 	} u;
 };
 
+struct lpfc_mbx_cq_create_set {
+	union  lpfc_sli4_cfg_shdr cfg_shdr;
+	union {
+		struct {
+			uint32_t word0;
+#define lpfc_mbx_cq_create_set_page_size_SHIFT	16	/* Version 2 Only */
+#define lpfc_mbx_cq_create_set_page_size_MASK	0x000000FF
+#define lpfc_mbx_cq_create_set_page_size_WORD	word0
+#define lpfc_mbx_cq_create_set_num_pages_SHIFT	0
+#define lpfc_mbx_cq_create_set_num_pages_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_num_pages_WORD	word0
+			uint32_t word1;
+#define lpfc_mbx_cq_create_set_evt_SHIFT	31
+#define lpfc_mbx_cq_create_set_evt_MASK		0x00000001
+#define lpfc_mbx_cq_create_set_evt_WORD		word1
+#define lpfc_mbx_cq_create_set_valid_SHIFT	29
+#define lpfc_mbx_cq_create_set_valid_MASK	0x00000001
+#define lpfc_mbx_cq_create_set_valid_WORD	word1
+#define lpfc_mbx_cq_create_set_cqe_cnt_SHIFT	27
+#define lpfc_mbx_cq_create_set_cqe_cnt_MASK	0x00000003
+#define lpfc_mbx_cq_create_set_cqe_cnt_WORD	word1
+#define lpfc_mbx_cq_create_set_cqe_size_SHIFT	25
+#define lpfc_mbx_cq_create_set_cqe_size_MASK	0x00000003
+#define lpfc_mbx_cq_create_set_cqe_size_WORD	word1
+#define lpfc_mbx_cq_create_set_auto_SHIFT	15
+#define lpfc_mbx_cq_create_set_auto_MASK	0x0000001
+#define lpfc_mbx_cq_create_set_auto_WORD	word1
+#define lpfc_mbx_cq_create_set_nodelay_SHIFT	14
+#define lpfc_mbx_cq_create_set_nodelay_MASK	0x00000001
+#define lpfc_mbx_cq_create_set_nodelay_WORD	word1
+#define lpfc_mbx_cq_create_set_clswm_SHIFT	12
+#define lpfc_mbx_cq_create_set_clswm_MASK	0x00000003
+#define lpfc_mbx_cq_create_set_clswm_WORD	word1
+			uint32_t word2;
+#define lpfc_mbx_cq_create_set_arm_SHIFT	31
+#define lpfc_mbx_cq_create_set_arm_MASK		0x00000001
+#define lpfc_mbx_cq_create_set_arm_WORD		word2
+#define lpfc_mbx_cq_create_set_num_cq_SHIFT	0
+#define lpfc_mbx_cq_create_set_num_cq_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_num_cq_WORD	word2
+			uint32_t word3;
+#define lpfc_mbx_cq_create_set_eq_id1_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id1_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id1_WORD	word3
+#define lpfc_mbx_cq_create_set_eq_id0_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id0_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id0_WORD	word3
+			uint32_t word4;
+#define lpfc_mbx_cq_create_set_eq_id3_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id3_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id3_WORD	word4
+#define lpfc_mbx_cq_create_set_eq_id2_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id2_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id2_WORD	word4
+			uint32_t word5;
+#define lpfc_mbx_cq_create_set_eq_id5_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id5_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id5_WORD	word5
+#define lpfc_mbx_cq_create_set_eq_id4_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id4_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id4_WORD	word5
+			uint32_t word6;
+#define lpfc_mbx_cq_create_set_eq_id7_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id7_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id7_WORD	word6
+#define lpfc_mbx_cq_create_set_eq_id6_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id6_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id6_WORD	word6
+			uint32_t word7;
+#define lpfc_mbx_cq_create_set_eq_id9_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id9_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id9_WORD	word7
+#define lpfc_mbx_cq_create_set_eq_id8_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id8_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id8_WORD	word7
+			uint32_t word8;
+#define lpfc_mbx_cq_create_set_eq_id11_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id11_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id11_WORD	word8
+#define lpfc_mbx_cq_create_set_eq_id10_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id10_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id10_WORD	word8
+			uint32_t word9;
+#define lpfc_mbx_cq_create_set_eq_id13_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id13_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id13_WORD	word9
+#define lpfc_mbx_cq_create_set_eq_id12_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id12_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id12_WORD	word9
+			uint32_t word10;
+#define lpfc_mbx_cq_create_set_eq_id15_SHIFT	16
+#define lpfc_mbx_cq_create_set_eq_id15_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id15_WORD	word10
+#define lpfc_mbx_cq_create_set_eq_id14_SHIFT	0
+#define lpfc_mbx_cq_create_set_eq_id14_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_eq_id14_WORD	word10
+			struct dma_address page[1];
+		} request;
+		struct {
+			uint32_t word0;
+#define lpfc_mbx_cq_create_set_num_alloc_SHIFT	16
+#define lpfc_mbx_cq_create_set_num_alloc_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_num_alloc_WORD	word0
+#define lpfc_mbx_cq_create_set_base_id_SHIFT	0
+#define lpfc_mbx_cq_create_set_base_id_MASK	0x0000FFFF
+#define lpfc_mbx_cq_create_set_base_id_WORD	word0
+		} response;
+	} u;
+};
+
 struct lpfc_mbx_cq_destroy {
 	struct mbox_header header;
 	union {
@@ -1252,10 +1363,10 @@ struct rq_context {
 #define LPFC_RQ_RING_SIZE_1024		10	/* 1024 entries */
 #define LPFC_RQ_RING_SIZE_2048		11	/* 2048 entries */
 #define LPFC_RQ_RING_SIZE_4096		12	/* 4096 entries */
-#define lpfc_rq_context_rqe_count_1_SHIFT	16	/* Version 1 Only */
+#define lpfc_rq_context_rqe_count_1_SHIFT	16	/* Version 1-2 Only */
 #define lpfc_rq_context_rqe_count_1_MASK	0x0000FFFF
 #define lpfc_rq_context_rqe_count_1_WORD	word0
-#define lpfc_rq_context_rqe_size_SHIFT	8		/* Version 1 Only */
+#define lpfc_rq_context_rqe_size_SHIFT	8		/* Version 1-2 Only */
 #define lpfc_rq_context_rqe_size_MASK	0x0000000F
 #define lpfc_rq_context_rqe_size_WORD	word0
 #define LPFC_RQE_SIZE_8		2
@@ -1267,7 +1378,13 @@ struct rq_context {
 #define lpfc_rq_context_page_size_MASK	0x000000FF
 #define lpfc_rq_context_page_size_WORD	word0
 #define	LPFC_RQ_PAGE_SIZE_4096	0x1
-	uint32_t reserved1;
+	uint32_t word1;
+#define lpfc_rq_context_data_size_SHIFT	16		/* Version 2 Only */
+#define lpfc_rq_context_data_size_MASK	0x0000FFFF
+#define lpfc_rq_context_data_size_WORD	word1
+#define lpfc_rq_context_hdr_size_SHIFT	0		/* Version 2 Only */
+#define lpfc_rq_context_hdr_size_MASK	0x0000FFFF
+#define lpfc_rq_context_hdr_size_WORD	word1
 	uint32_t word2;
 #define lpfc_rq_context_cq_id_SHIFT	16
 #define lpfc_rq_context_cq_id_MASK	0x000003FF
@@ -1275,6 +1392,9 @@ struct rq_context {
 #define lpfc_rq_context_buf_size_SHIFT	0
 #define lpfc_rq_context_buf_size_MASK	0x0000FFFF
 #define lpfc_rq_context_buf_size_WORD	word2
+#define lpfc_rq_context_base_cq_SHIFT	0		/* Version 2 Only */
+#define lpfc_rq_context_base_cq_MASK	0x0000FFFF
+#define lpfc_rq_context_base_cq_WORD	word2
 	uint32_t buffer_size;				/* Version 1 Only */
 };
 
@@ -1296,10 +1416,65 @@ struct lpfc_mbx_rq_create {
 #define lpfc_mbx_rq_create_ulp_num_MASK		0x000000FF
 #define lpfc_mbx_rq_create_ulp_num_WORD		word0
 			struct rq_context context;
-			struct dma_address page[LPFC_MAX_WQ_PAGE];
+			struct dma_address page[LPFC_MAX_RQ_PAGE];
 		} request;
 		struct {
 			uint32_t word0;
+#define lpfc_mbx_rq_create_q_cnt_v2_SHIFT	16
+#define lpfc_mbx_rq_create_q_cnt_v2_MASK	0x0000FFFF
+#define lpfc_mbx_rq_create_q_cnt_v2_WORD	word0
+#define lpfc_mbx_rq_create_q_id_SHIFT		0
+#define lpfc_mbx_rq_create_q_id_MASK		0x0000FFFF
+#define lpfc_mbx_rq_create_q_id_WORD		word0
+			uint32_t doorbell_offset;
+			uint32_t word2;
+#define lpfc_mbx_rq_create_bar_set_SHIFT	0
+#define lpfc_mbx_rq_create_bar_set_MASK		0x0000FFFF
+#define lpfc_mbx_rq_create_bar_set_WORD		word2
+#define lpfc_mbx_rq_create_db_format_SHIFT	16
+#define lpfc_mbx_rq_create_db_format_MASK	0x0000FFFF
+#define lpfc_mbx_rq_create_db_format_WORD	word2
+		} response;
+	} u;
+};
+
+struct lpfc_mbx_rq_create_v2 {
+	union  lpfc_sli4_cfg_shdr cfg_shdr;
+	union {
+		struct {
+			uint32_t word0;
+#define lpfc_mbx_rq_create_num_pages_SHIFT	0
+#define lpfc_mbx_rq_create_num_pages_MASK	0x0000FFFF
+#define lpfc_mbx_rq_create_num_pages_WORD	word0
+#define lpfc_mbx_rq_create_rq_cnt_SHIFT		16
+#define lpfc_mbx_rq_create_rq_cnt_MASK		0x000000FF
+#define lpfc_mbx_rq_create_rq_cnt_WORD		word0
+#define lpfc_mbx_rq_create_dua_SHIFT		16
+#define lpfc_mbx_rq_create_dua_MASK		0x00000001
+#define lpfc_mbx_rq_create_dua_WORD		word0
+#define lpfc_mbx_rq_create_bqu_SHIFT		17
+#define lpfc_mbx_rq_create_bqu_MASK		0x00000001
+#define lpfc_mbx_rq_create_bqu_WORD		word0
+#define lpfc_mbx_rq_create_ulp_num_SHIFT	24
+#define lpfc_mbx_rq_create_ulp_num_MASK		0x000000FF
+#define lpfc_mbx_rq_create_ulp_num_WORD		word0
+#define lpfc_mbx_rq_create_dim_SHIFT		29
+#define lpfc_mbx_rq_create_dim_MASK		0x00000001
+#define lpfc_mbx_rq_create_dim_WORD		word0
+#define lpfc_mbx_rq_create_dfd_SHIFT		30
+#define lpfc_mbx_rq_create_dfd_MASK		0x00000001
+#define lpfc_mbx_rq_create_dfd_WORD		word0
+#define lpfc_mbx_rq_create_dnb_SHIFT		31
+#define lpfc_mbx_rq_create_dnb_MASK		0x00000001
+#define lpfc_mbx_rq_create_dnb_WORD		word0
+			struct rq_context context;
+			struct dma_address page[1];
+		} request;
+		struct {
+			uint32_t word0;
+#define lpfc_mbx_rq_create_q_cnt_v2_SHIFT	16
+#define lpfc_mbx_rq_create_q_cnt_v2_MASK	0x0000FFFF
+#define lpfc_mbx_rq_create_q_cnt_v2_WORD	word0
 #define lpfc_mbx_rq_create_q_id_SHIFT		0
 #define lpfc_mbx_rq_create_q_id_MASK		0x0000FFFF
 #define lpfc_mbx_rq_create_q_id_WORD		word0
@@ -2213,6 +2388,160 @@ struct lpfc_mbx_reg_fcfi {
 #define lpfc_reg_fcfi_vlan_tag_WORD	word8
 };
 
+struct lpfc_mbx_reg_fcfi_mrq {
+	uint32_t word1;
+#define lpfc_reg_fcfi_mrq_info_index_SHIFT	0
+#define lpfc_reg_fcfi_mrq_info_index_MASK	0x0000FFFF
+#define lpfc_reg_fcfi_mrq_info_index_WORD	word1
+#define lpfc_reg_fcfi_mrq_fcfi_SHIFT		16
+#define lpfc_reg_fcfi_mrq_fcfi_MASK		0x0000FFFF
+#define lpfc_reg_fcfi_mrq_fcfi_WORD		word1
+	uint32_t word2;
+#define lpfc_reg_fcfi_mrq_rq_id1_SHIFT		0
+#define lpfc_reg_fcfi_mrq_rq_id1_MASK		0x0000FFFF
+#define lpfc_reg_fcfi_mrq_rq_id1_WORD		word2
+#define lpfc_reg_fcfi_mrq_rq_id0_SHIFT		16
+#define lpfc_reg_fcfi_mrq_rq_id0_MASK		0x0000FFFF
+#define lpfc_reg_fcfi_mrq_rq_id0_WORD		word2
+	uint32_t word3;
+#define lpfc_reg_fcfi_mrq_rq_id3_SHIFT		0
+#define lpfc_reg_fcfi_mrq_rq_id3_MASK		0x0000FFFF
+#define lpfc_reg_fcfi_mrq_rq_id3_WORD		word3
+#define lpfc_reg_fcfi_mrq_rq_id2_SHIFT		16
+#define lpfc_reg_fcfi_mrq_rq_id2_MASK		0x0000FFFF
+#define lpfc_reg_fcfi_mrq_rq_id2_WORD		word3
+	uint32_t word4;
+#define lpfc_reg_fcfi_mrq_type_match0_SHIFT	24
+#define lpfc_reg_fcfi_mrq_type_match0_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_match0_WORD	word4
+#define lpfc_reg_fcfi_mrq_type_mask0_SHIFT	16
+#define lpfc_reg_fcfi_mrq_type_mask0_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_mask0_WORD	word4
+#define lpfc_reg_fcfi_mrq_rctl_match0_SHIFT	8
+#define lpfc_reg_fcfi_mrq_rctl_match0_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_match0_WORD	word4
+#define lpfc_reg_fcfi_mrq_rctl_mask0_SHIFT	0
+#define lpfc_reg_fcfi_mrq_rctl_mask0_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_mask0_WORD	word4
+	uint32_t word5;
+#define lpfc_reg_fcfi_mrq_type_match1_SHIFT	24
+#define lpfc_reg_fcfi_mrq_type_match1_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_match1_WORD	word5
+#define lpfc_reg_fcfi_mrq_type_mask1_SHIFT	16
+#define lpfc_reg_fcfi_mrq_type_mask1_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_mask1_WORD	word5
+#define lpfc_reg_fcfi_mrq_rctl_match1_SHIFT	8
+#define lpfc_reg_fcfi_mrq_rctl_match1_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_match1_WORD	word5
+#define lpfc_reg_fcfi_mrq_rctl_mask1_SHIFT	0
+#define lpfc_reg_fcfi_mrq_rctl_mask1_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_mask1_WORD	word5
+	uint32_t word6;
+#define lpfc_reg_fcfi_mrq_type_match2_SHIFT	24
+#define lpfc_reg_fcfi_mrq_type_match2_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_match2_WORD	word6
+#define lpfc_reg_fcfi_mrq_type_mask2_SHIFT	16
+#define lpfc_reg_fcfi_mrq_type_mask2_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_mask2_WORD	word6
+#define lpfc_reg_fcfi_mrq_rctl_match2_SHIFT	8
+#define lpfc_reg_fcfi_mrq_rctl_match2_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_match2_WORD	word6
+#define lpfc_reg_fcfi_mrq_rctl_mask2_SHIFT	0
+#define lpfc_reg_fcfi_mrq_rctl_mask2_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_mask2_WORD	word6
+	uint32_t word7;
+#define lpfc_reg_fcfi_mrq_type_match3_SHIFT	24
+#define lpfc_reg_fcfi_mrq_type_match3_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_match3_WORD	word7
+#define lpfc_reg_fcfi_mrq_type_mask3_SHIFT	16
+#define lpfc_reg_fcfi_mrq_type_mask3_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_type_mask3_WORD	word7
+#define lpfc_reg_fcfi_mrq_rctl_match3_SHIFT	8
+#define lpfc_reg_fcfi_mrq_rctl_match3_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_match3_WORD	word7
+#define lpfc_reg_fcfi_mrq_rctl_mask3_SHIFT	0
+#define lpfc_reg_fcfi_mrq_rctl_mask3_MASK	0x000000FF
+#define lpfc_reg_fcfi_mrq_rctl_mask3_WORD	word7
+	uint32_t word8;
+#define lpfc_reg_fcfi_mrq_ptc7_SHIFT		31
+#define lpfc_reg_fcfi_mrq_ptc7_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc7_WORD		word8
+#define lpfc_reg_fcfi_mrq_ptc6_SHIFT		30
+#define lpfc_reg_fcfi_mrq_ptc6_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc6_WORD		word8
+#define lpfc_reg_fcfi_mrq_ptc5_SHIFT		29
+#define lpfc_reg_fcfi_mrq_ptc5_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc5_WORD		word8
+#define lpfc_reg_fcfi_mrq_ptc4_SHIFT		28
+#define lpfc_reg_fcfi_mrq_ptc4_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc4_WORD		word8
+#define lpfc_reg_fcfi_mrq_ptc3_SHIFT		27
+#define lpfc_reg_fcfi_mrq_ptc3_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc3_WORD		word8
+#define lpfc_reg_fcfi_mrq_ptc2_SHIFT		26
+#define lpfc_reg_fcfi_mrq_ptc2_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc2_WORD		word8
+#define lpfc_reg_fcfi_mrq_ptc1_SHIFT		25
+#define lpfc_reg_fcfi_mrq_ptc1_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc1_WORD		word8
+#define lpfc_reg_fcfi_mrq_ptc0_SHIFT		24
+#define lpfc_reg_fcfi_mrq_ptc0_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_ptc0_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt7_SHIFT		23
+#define lpfc_reg_fcfi_mrq_pt7_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt7_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt6_SHIFT		22
+#define lpfc_reg_fcfi_mrq_pt6_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt6_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt5_SHIFT		21
+#define lpfc_reg_fcfi_mrq_pt5_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt5_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt4_SHIFT		20
+#define lpfc_reg_fcfi_mrq_pt4_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt4_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt3_SHIFT		19
+#define lpfc_reg_fcfi_mrq_pt3_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt3_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt2_SHIFT		18
+#define lpfc_reg_fcfi_mrq_pt2_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt2_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt1_SHIFT		17
+#define lpfc_reg_fcfi_mrq_pt1_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt1_WORD		word8
+#define lpfc_reg_fcfi_mrq_pt0_SHIFT		16
+#define lpfc_reg_fcfi_mrq_pt0_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_pt0_WORD		word8
+#define lpfc_reg_fcfi_mrq_xmv_SHIFT		15
+#define lpfc_reg_fcfi_mrq_xmv_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_xmv_WORD		word8
+#define lpfc_reg_fcfi_mrq_mode_SHIFT		13
+#define lpfc_reg_fcfi_mrq_mode_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_mode_WORD		word8
+#define lpfc_reg_fcfi_mrq_vv_SHIFT		12
+#define lpfc_reg_fcfi_mrq_vv_MASK		0x00000001
+#define lpfc_reg_fcfi_mrq_vv_WORD		word8
+#define lpfc_reg_fcfi_mrq_vlan_tag_SHIFT	0
+#define lpfc_reg_fcfi_mrq_vlan_tag_MASK		0x00000FFF
+#define lpfc_reg_fcfi_mrq_vlan_tag_WORD		word8
+	uint32_t word9;
+#define lpfc_reg_fcfi_mrq_policy_SHIFT		12
+#define lpfc_reg_fcfi_mrq_policy_MASK		0x0000000F
+#define lpfc_reg_fcfi_mrq_policy_WORD		word9
+#define lpfc_reg_fcfi_mrq_filter_SHIFT		8
+#define lpfc_reg_fcfi_mrq_filter_MASK		0x0000000F
+#define lpfc_reg_fcfi_mrq_filter_WORD		word9
+#define lpfc_reg_fcfi_mrq_npairs_SHIFT		0
+#define lpfc_reg_fcfi_mrq_npairs_MASK		0x000000FF
+#define lpfc_reg_fcfi_mrq_npairs_WORD		word9
+	uint32_t word10;
+	uint32_t word11;
+	uint32_t word12;
+	uint32_t word13;
+	uint32_t word14;
+	uint32_t word15;
+	uint32_t word16;
+};
+
 struct lpfc_mbx_unreg_fcfi {
 	uint32_t word1_rsv;
 	uint32_t word2;
@@ -2392,6 +2721,9 @@ struct lpfc_mbx_request_features {
 #define lpfc_mbx_rq_ftr_rq_perfh_SHIFT		11
 #define lpfc_mbx_rq_ftr_rq_perfh_MASK		0x00000001
 #define lpfc_mbx_rq_ftr_rq_perfh_WORD		word2
+#define lpfc_mbx_rq_ftr_rq_mrqp_SHIFT		16
+#define lpfc_mbx_rq_ftr_rq_mrqp_MASK		0x00000001
+#define lpfc_mbx_rq_ftr_rq_mrqp_WORD		word2
 	uint32_t word3;
 #define lpfc_mbx_rq_ftr_rsp_iaab_SHIFT		0
 #define lpfc_mbx_rq_ftr_rsp_iaab_MASK		0x00000001
@@ -2420,6 +2752,9 @@ struct lpfc_mbx_request_features {
 #define lpfc_mbx_rq_ftr_rsp_perfh_SHIFT		11
 #define lpfc_mbx_rq_ftr_rsp_perfh_MASK		0x00000001
 #define lpfc_mbx_rq_ftr_rsp_perfh_WORD		word3
+#define lpfc_mbx_rq_ftr_rsp_mrqp_SHIFT		16
+#define lpfc_mbx_rq_ftr_rsp_mrqp_MASK		0x00000001
+#define lpfc_mbx_rq_ftr_rsp_mrqp_WORD		word3
 };
 
 struct lpfc_mbx_supp_pages {
@@ -3312,14 +3647,17 @@ struct lpfc_mqe {
 		struct lpfc_mbx_del_fcf_tbl_entry del_fcf_entry;
 		struct lpfc_mbx_redisc_fcf_tbl redisc_fcf_tbl;
 		struct lpfc_mbx_reg_fcfi reg_fcfi;
+		struct lpfc_mbx_reg_fcfi_mrq reg_fcfi_mrq;
 		struct lpfc_mbx_unreg_fcfi unreg_fcfi;
 		struct lpfc_mbx_mq_create mq_create;
 		struct lpfc_mbx_mq_create_ext mq_create_ext;
 		struct lpfc_mbx_eq_create eq_create;
 		struct lpfc_mbx_modify_eq_delay eq_delay;
 		struct lpfc_mbx_cq_create cq_create;
+		struct lpfc_mbx_cq_create_set cq_create_set;
 		struct lpfc_mbx_wq_create wq_create;
 		struct lpfc_mbx_rq_create rq_create;
+		struct lpfc_mbx_rq_create_v2 rq_create_v2;
 		struct lpfc_mbx_mq_destroy mq_destroy;
 		struct lpfc_mbx_eq_destroy eq_destroy;
 		struct lpfc_mbx_cq_destroy cq_destroy;
@@ -3972,6 +4310,7 @@ struct lpfc_nvme_prli {
 #define prli_fb_sz_SHIFT                0
 #define prli_fb_sz_MASK                 0x0000ffff
 #define prli_fb_sz_WORD                 word5
+#define LPFC_NVMET_FB_SZ_MAX  65536   /* Driver target mode only. */
 };
 
 struct create_xri_wqe {
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 03fa3f02e33e..e6cbc0bac029 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -3354,8 +3354,15 @@ lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba)
 	 * update on pci function's nvmet xri-sgl list
 	 */
 	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
-	nvmet_xri_cnt = 0;
+	nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
 	tot_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
+	if (nvmet_xri_cnt > tot_cnt) {
+		phba->cfg_nvmet_mrq_post = tot_cnt / phba->cfg_nvmet_mrq;
+		nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
+		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+				"6301 NVMET post-sgl count changed to %d\n",
+				phba->cfg_nvmet_mrq_post);
+	}
 
 	if (nvmet_xri_cnt > phba->sli4_hba.nvmet_xri_cnt) {
 		/* els xri-sgl expanded */
@@ -7674,11 +7681,13 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba)
 		phba->cfg_fcp_io_channel = io_channel;
 	if (phba->cfg_nvme_io_channel > io_channel)
 		phba->cfg_nvme_io_channel = io_channel;
+	if (phba->cfg_nvme_io_channel < phba->cfg_nvmet_mrq)
+		phba->cfg_nvmet_mrq = phba->cfg_nvme_io_channel;
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"2574 IO channels: irqs %d fcp %d nvme %d\n",
+			"2574 IO channels: irqs %d fcp %d nvme %d MRQ: %d\n",
 			phba->io_channel_irqs, phba->cfg_fcp_io_channel,
-			phba->cfg_nvme_io_channel);
+			phba->cfg_nvme_io_channel, phba->cfg_nvmet_mrq);
 
 	/* Get EQ depth from module parameter, fake the default for now */
 	phba->sli4_hba.eq_esize = LPFC_EQE_SIZE_4B;
@@ -7768,7 +7777,7 @@ int
 lpfc_sli4_queue_create(struct lpfc_hba *phba)
 {
 	struct lpfc_queue *qdesc;
-	int idx, io_channel;
+	int idx, io_channel, max;
 
 	/*
 	 * Create HBA Record arrays.
@@ -7845,7 +7854,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 			goto out_error;
 		}
 
-
 		phba->sli4_hba.nvme_wq = kcalloc(phba->cfg_nvme_io_channel,
 						sizeof(struct lpfc_queue *),
 						GFP_KERNEL);
@@ -7870,6 +7878,39 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 					"fast-path CQ map\n");
 			goto out_error;
 		}
+
+		if (phba->nvmet_support) {
+			phba->sli4_hba.nvmet_cqset = kcalloc(
+					phba->cfg_nvmet_mrq,
+					sizeof(struct lpfc_queue *),
+					GFP_KERNEL);
+			if (!phba->sli4_hba.nvmet_cqset) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"3121 Fail allocate memory for "
+					"fast-path CQ set array\n");
+				goto out_error;
+			}
+			phba->sli4_hba.nvmet_mrq_hdr = kcalloc(
+					phba->cfg_nvmet_mrq,
+					sizeof(struct lpfc_queue *),
+					GFP_KERNEL);
+			if (!phba->sli4_hba.nvmet_mrq_hdr) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"3122 Fail allocate memory for "
+					"fast-path RQ set hdr array\n");
+				goto out_error;
+			}
+			phba->sli4_hba.nvmet_mrq_data = kcalloc(
+					phba->cfg_nvmet_mrq,
+					sizeof(struct lpfc_queue *),
+					GFP_KERNEL);
+			if (!phba->sli4_hba.nvmet_mrq_data) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"3124 Fail allocate memory for "
+					"fast-path RQ set data array\n");
+				goto out_error;
+			}
+		}
 	}
 
 	INIT_LIST_HEAD(&phba->sli4_hba.lpfc_wq_list);
@@ -7897,6 +7938,30 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 		if (lpfc_alloc_nvme_wq_cq(phba, idx))
 			goto out_error;
 
+	/* allocate MRQ CQs */
+	max = phba->cfg_nvme_io_channel;
+	if (max < phba->cfg_nvmet_mrq)
+		max = phba->cfg_nvmet_mrq;
+
+	for (idx = 0; idx < max; idx++)
+		if (lpfc_alloc_nvme_wq_cq(phba, idx))
+			goto out_error;
+
+	if (phba->nvmet_support) {
+		for (idx = 0; idx < phba->cfg_nvmet_mrq; idx++) {
+			qdesc = lpfc_sli4_queue_alloc(phba,
+					phba->sli4_hba.cq_esize,
+					phba->sli4_hba.cq_ecount);
+			if (!qdesc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"3142 Failed allocate NVME "
+					"CQ Set (%d)\n", idx);
+				goto out_error;
+			}
+			phba->sli4_hba.nvmet_cqset[idx] = qdesc;
+		}
+	}
+
 	/*
 	 * Create Slow Path Completion Queues (CQs)
 	 */
@@ -7999,6 +8064,44 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 	}
 	phba->sli4_hba.dat_rq = qdesc;
 
+	if (phba->nvmet_support) {
+		for (idx = 0; idx < phba->cfg_nvmet_mrq; idx++) {
+			/* Create NVMET Receive Queue for header */
+			qdesc = lpfc_sli4_queue_alloc(phba,
+						      phba->sli4_hba.rq_esize,
+						      phba->sli4_hba.rq_ecount);
+			if (!qdesc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"3146 Failed allocate "
+						"receive HRQ\n");
+				goto out_error;
+			}
+			phba->sli4_hba.nvmet_mrq_hdr[idx] = qdesc;
+
+			/* Only needed for header of RQ pair */
+			qdesc->rqbp = kzalloc(sizeof(struct lpfc_rqb),
+					      GFP_KERNEL);
+			if (qdesc->rqbp == NULL) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6131 Failed allocate "
+						"Header RQBP\n");
+				goto out_error;
+			}
+
+			/* Create NVMET Receive Queue for data */
+			qdesc = lpfc_sli4_queue_alloc(phba,
+						      phba->sli4_hba.rq_esize,
+						      phba->sli4_hba.rq_ecount);
+			if (!qdesc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"3156 Failed allocate "
+						"receive DRQ\n");
+				goto out_error;
+			}
+			phba->sli4_hba.nvmet_mrq_data[idx] = qdesc;
+		}
+	}
+
 	/* Create the Queues needed for Flash Optimized Fabric operations */
 	if (phba->cfg_fof)
 		lpfc_fof_queue_create(phba);
@@ -8085,6 +8188,14 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 	/* Release NVME CQ mapping array */
 	lpfc_sli4_release_queue_map(&phba->sli4_hba.nvme_cq_map);
 
+	lpfc_sli4_release_queues(&phba->sli4_hba.nvmet_cqset,
+					phba->cfg_nvmet_mrq);
+
+	lpfc_sli4_release_queues(&phba->sli4_hba.nvmet_mrq_hdr,
+					phba->cfg_nvmet_mrq);
+	lpfc_sli4_release_queues(&phba->sli4_hba.nvmet_mrq_data,
+					phba->cfg_nvmet_mrq);
+
 	/* Release mailbox command work queue */
 	__lpfc_sli4_release_queue(&phba->sli4_hba.mbx_wq);
 
@@ -8422,6 +8533,44 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 			(uint32_t)rc);
 		goto out_destroy;
 	}
+	if (phba->nvmet_support) {
+		if (!phba->sli4_hba.nvmet_cqset) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"3165 Fast-path NVME CQ Set "
+					"array not allocated\n");
+			rc = -ENOMEM;
+			goto out_destroy;
+		}
+		if (phba->cfg_nvmet_mrq > 1) {
+			rc = lpfc_cq_create_set(phba,
+					phba->sli4_hba.nvmet_cqset,
+					phba->sli4_hba.hba_eq,
+					LPFC_WCQ, LPFC_NVMET);
+			if (rc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"3164 Failed setup of NVME CQ "
+						"Set, rc = 0x%x\n",
+						(uint32_t)rc);
+				goto out_destroy;
+			}
+		} else {
+			/* Set up NVMET Receive Complete Queue */
+			rc = lpfc_cq_create(phba, phba->sli4_hba.nvmet_cqset[0],
+					    phba->sli4_hba.hba_eq[0],
+					    LPFC_WCQ, LPFC_NVMET);
+			if (rc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6089 Failed setup NVMET CQ: "
+						"rc = 0x%x\n", (uint32_t)rc);
+				goto out_destroy;
+			}
+			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+					"6090 NVMET CQ setup: cq-id=%d, "
+					"parent eq-id=%d\n",
+					phba->sli4_hba.nvmet_cqset[0]->queue_id,
+					phba->sli4_hba.hba_eq[0]->queue_id);
+		}
+	}
 
 	/* Set up slow-path ELS WQ/CQ */
 	if (!phba->sli4_hba.els_cq || !phba->sli4_hba.els_wq) {
@@ -8473,6 +8622,58 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 				phba->sli4_hba.nvmels_cq->queue_id);
 	}
 
+	/*
+	 * Create NVMET Receive Queue (RQ)
+	 */
+	if (phba->nvmet_support) {
+		if ((!phba->sli4_hba.nvmet_cqset) ||
+		    (!phba->sli4_hba.nvmet_mrq_hdr) ||
+		    (!phba->sli4_hba.nvmet_mrq_data)) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6130 MRQ CQ Queues not "
+					"allocated\n");
+			rc = -ENOMEM;
+			goto out_destroy;
+		}
+		if (phba->cfg_nvmet_mrq > 1) {
+			rc = lpfc_mrq_create(phba,
+					     phba->sli4_hba.nvmet_mrq_hdr,
+					     phba->sli4_hba.nvmet_mrq_data,
+					     phba->sli4_hba.nvmet_cqset,
+					     LPFC_NVMET);
+			if (rc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6098 Failed setup of NVMET "
+						"MRQ: rc = 0x%x\n",
+						(uint32_t)rc);
+				goto out_destroy;
+			}
+
+		} else {
+			rc = lpfc_rq_create(phba,
+					    phba->sli4_hba.nvmet_mrq_hdr[0],
+					    phba->sli4_hba.nvmet_mrq_data[0],
+					    phba->sli4_hba.nvmet_cqset[0],
+					    LPFC_NVMET);
+			if (rc) {
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6057 Failed setup of NVMET "
+						"Receive Queue: rc = 0x%x\n",
+						(uint32_t)rc);
+				goto out_destroy;
+			}
+
+			lpfc_printf_log(
+				phba, KERN_INFO, LOG_INIT,
+				"6099 NVMET RQ setup: hdr-rq-id=%d, "
+				"dat-rq-id=%d parent cq-id=%d\n",
+				phba->sli4_hba.nvmet_mrq_hdr[0]->queue_id,
+				phba->sli4_hba.nvmet_mrq_data[0]->queue_id,
+				phba->sli4_hba.nvmet_cqset[0]->queue_id);
+
+		}
+	}
+
 	if (!phba->sli4_hba.hdr_rq || !phba->sli4_hba.dat_rq) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"0540 Receive Queue not allocated\n");
@@ -8589,6 +8790,21 @@ lpfc_sli4_queue_unset(struct lpfc_hba *phba)
 		for (qidx = 0; qidx < phba->cfg_nvme_io_channel; qidx++)
 			lpfc_cq_destroy(phba, phba->sli4_hba.nvme_cq[qidx]);
 
+	/* Unset NVMET MRQ queue */
+	if (phba->sli4_hba.nvmet_mrq_hdr) {
+		for (qidx = 0; qidx < phba->cfg_nvmet_mrq; qidx++)
+			lpfc_rq_destroy(phba,
+					phba->sli4_hba.nvmet_mrq_hdr[qidx],
+					phba->sli4_hba.nvmet_mrq_data[qidx]);
+	}
+
+	/* Unset NVMET CQ Set complete queue */
+	if (phba->sli4_hba.nvmet_cqset) {
+		for (qidx = 0; qidx < phba->cfg_nvmet_mrq; qidx++)
+			lpfc_cq_destroy(phba,
+					phba->sli4_hba.nvmet_cqset[qidx]);
+	}
+
 	/* Unset FCP response complete queue */
 	if (phba->sli4_hba.fcp_cq)
 		for (qidx = 0; qidx < phba->cfg_fcp_io_channel; qidx++)
@@ -9935,6 +10151,7 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	    !phba->nvme_support) {
 		phba->nvme_support = 0;
 		phba->nvmet_support = 0;
+		phba->cfg_nvmet_mrq = 0;
 		phba->cfg_nvme_io_channel = 0;
 		phba->io_channel_irqs = phba->cfg_fcp_io_channel;
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT | LOG_NVME,
@@ -10875,12 +11092,14 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	if (phba->intr_type != MSIX) {
 		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
 			phba->cfg_fcp_io_channel = 1;
-		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
 			phba->cfg_nvme_io_channel = 1;
+			if (phba->nvmet_support)
+				phba->cfg_nvmet_mrq = 1;
+		}
 		phba->io_channel_irqs = 1;
 	}
 
-
 	/* Set up SLI-4 HBA */
 	if (lpfc_sli4_hba_setup(phba)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index c20dc25a1e79..8f4bfdfd9910 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -2081,6 +2081,9 @@ lpfc_request_features(struct lpfc_hba *phba, struct lpfcMboxq *mboxq)
 	if (phba->max_vpi && phba->cfg_enable_npiv)
 		bf_set(lpfc_mbx_rq_ftr_rq_npiv, &mboxq->u.mqe.un.req_ftrs, 1);
 
+	if (phba->nvmet_support)
+		bf_set(lpfc_mbx_rq_ftr_rq_mrqp, &mboxq->u.mqe.un.req_ftrs, 1);
+
 	return;
 }
 
@@ -2448,6 +2451,26 @@ lpfc_reg_fcfi(struct lpfc_hba *phba, struct lpfcMboxq *mbox)
 		/* addr mode is bit wise inverted value of fcf addr_mode */
 		bf_set(lpfc_reg_fcfi_mam, reg_fcfi,
 		       (~phba->fcf.addr_mode) & 0x3);
+	} else {
+		/* This is ONLY for NVMET MRQ == 1 */
+		if (phba->cfg_nvmet_mrq != 1)
+			return;
+
+		bf_set(lpfc_reg_fcfi_rq_id0, reg_fcfi,
+		       phba->sli4_hba.nvmet_mrq_hdr[0]->queue_id);
+		/* Match type FCP - rq_id0 */
+		bf_set(lpfc_reg_fcfi_type_match0, reg_fcfi, FC_TYPE_FCP);
+		bf_set(lpfc_reg_fcfi_type_mask0, reg_fcfi, 0xff);
+		bf_set(lpfc_reg_fcfi_rctl_match0, reg_fcfi,
+		       FC_RCTL_DD_UNSOL_CMD);
+
+		bf_set(lpfc_reg_fcfi_rq_id1, reg_fcfi,
+		       phba->sli4_hba.hdr_rq->queue_id);
+		/* Match everything else - rq_id1 */
+		bf_set(lpfc_reg_fcfi_type_match1, reg_fcfi, 0);
+		bf_set(lpfc_reg_fcfi_type_mask1, reg_fcfi, 0);
+		bf_set(lpfc_reg_fcfi_rctl_match1, reg_fcfi, 0);
+		bf_set(lpfc_reg_fcfi_rctl_mask1, reg_fcfi, 0);
 	}
 	bf_set(lpfc_reg_fcfi_rq_id2, reg_fcfi, REG_FCF_INVALID_QID);
 	bf_set(lpfc_reg_fcfi_rq_id3, reg_fcfi, REG_FCF_INVALID_QID);
@@ -2460,6 +2483,70 @@ lpfc_reg_fcfi(struct lpfc_hba *phba, struct lpfcMboxq *mbox)
 	}
 }
 
+/**
+ * lpfc_reg_fcfi_mrq - Initialize the REG_FCFI_MRQ mailbox command
+ * @phba: pointer to the hba structure containing the FCF index and RQ ID.
+ * @mbox: pointer to lpfc mbox command to initialize.
+ * @mode: 0 to register FCFI, 1 to register MRQs
+ *
+ * The REG_FCFI_MRQ mailbox command supports Fibre Channel Forwarders (FCFs).
+ * The SLI Host uses the command to activate an FCF after it has acquired FCF
+ * information via a READ_FCF mailbox command. This mailbox command also is used
+ * to indicate where received unsolicited frames from this FCF will be sent. By
+ * default this routine will set up the FCF to forward all unsolicited frames
+ * the the RQ ID passed in the @phba. This can be overridden by the caller for
+ * more complicated setups.
+ **/
+void
+lpfc_reg_fcfi_mrq(struct lpfc_hba *phba, struct lpfcMboxq *mbox, int mode)
+{
+	struct lpfc_mbx_reg_fcfi_mrq *reg_fcfi;
+
+	/* This is ONLY for MRQ */
+	if (phba->cfg_nvmet_mrq <= 1)
+		return;
+
+	memset(mbox, 0, sizeof(*mbox));
+	reg_fcfi = &mbox->u.mqe.un.reg_fcfi_mrq;
+	bf_set(lpfc_mqe_command, &mbox->u.mqe, MBX_REG_FCFI_MRQ);
+	if (mode == 0) {
+		bf_set(lpfc_reg_fcfi_mrq_info_index, reg_fcfi,
+		       phba->fcf.current_rec.fcf_indx);
+		if (phba->fcf.current_rec.vlan_id != LPFC_FCOE_NULL_VID) {
+			bf_set(lpfc_reg_fcfi_mrq_vv, reg_fcfi, 1);
+			bf_set(lpfc_reg_fcfi_mrq_vlan_tag, reg_fcfi,
+			       phba->fcf.current_rec.vlan_id);
+		}
+		return;
+	}
+
+	bf_set(lpfc_reg_fcfi_mrq_rq_id0, reg_fcfi,
+	       phba->sli4_hba.nvmet_mrq_hdr[0]->queue_id);
+	/* Match NVME frames of type FCP (protocol NVME) - rq_id0 */
+	bf_set(lpfc_reg_fcfi_mrq_type_match0, reg_fcfi, FC_TYPE_FCP);
+	bf_set(lpfc_reg_fcfi_mrq_type_mask0, reg_fcfi, 0xff);
+	bf_set(lpfc_reg_fcfi_mrq_rctl_match0, reg_fcfi, FC_RCTL_DD_UNSOL_CMD);
+	bf_set(lpfc_reg_fcfi_mrq_rctl_mask0, reg_fcfi, 0xff);
+	bf_set(lpfc_reg_fcfi_mrq_ptc0, reg_fcfi, 1);
+	bf_set(lpfc_reg_fcfi_mrq_pt0, reg_fcfi, 1);
+
+	bf_set(lpfc_reg_fcfi_mrq_policy, reg_fcfi, 3); /* NVME connection id */
+	bf_set(lpfc_reg_fcfi_mrq_mode, reg_fcfi, 1);
+	bf_set(lpfc_reg_fcfi_mrq_filter, reg_fcfi, 1); /* rq_id0 */
+	bf_set(lpfc_reg_fcfi_mrq_npairs, reg_fcfi, phba->cfg_nvmet_mrq);
+
+	bf_set(lpfc_reg_fcfi_mrq_rq_id1, reg_fcfi,
+	       phba->sli4_hba.hdr_rq->queue_id);
+	/* Match everything - rq_id1 */
+	bf_set(lpfc_reg_fcfi_mrq_type_match1, reg_fcfi, 0);
+	bf_set(lpfc_reg_fcfi_mrq_type_mask1, reg_fcfi, 0);
+	bf_set(lpfc_reg_fcfi_mrq_rctl_match1, reg_fcfi, 0);
+	bf_set(lpfc_reg_fcfi_mrq_rctl_mask1, reg_fcfi, 0);
+
+	bf_set(lpfc_reg_fcfi_mrq_rq_id2, reg_fcfi, REG_FCF_INVALID_QID);
+	bf_set(lpfc_reg_fcfi_mrq_rq_id3, reg_fcfi, REG_FCF_INVALID_QID);
+}
+
 /**
  * lpfc_unreg_fcfi - Initialize the UNREG_FCFI mailbox command
  * @mbox: pointer to lpfc mbox command to initialize.
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index f2cd0f37e03f..72164acb6656 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2027,6 +2027,29 @@ lpfc_sli_hbqbuf_get(struct list_head *rb_list)
 	return container_of(d_buf, struct hbq_dmabuf, dbuf);
 }
 
+/**
+ * lpfc_sli_rqbuf_get - Remove the first dma buffer off of an RQ list
+ * @phba: Pointer to HBA context object.
+ * @hbqno: HBQ number.
+ *
+ * This function removes the first RQ buffer on an RQ buffer list and returns a
+ * pointer to that buffer. If it finds no buffers on the list it returns NULL.
+ **/
+static struct rqb_dmabuf *
+lpfc_sli_rqbuf_get(struct lpfc_hba *phba, struct lpfc_queue *hrq)
+{
+	struct lpfc_dmabuf *h_buf;
+	struct lpfc_rqb *rqbp;
+
+	rqbp = hrq->rqbp;
+	list_remove_head(&rqbp->rqb_buffer_list, h_buf,
+			 struct lpfc_dmabuf, list);
+	if (!h_buf)
+		return NULL;
+	rqbp->buffer_count--;
+	return container_of(h_buf, struct rqb_dmabuf, hbuf);
+}
+
 /**
  * lpfc_sli_hbqbuf_find - Find the hbq buffer associated with a tag
  * @phba: Pointer to HBA context object.
@@ -5271,6 +5294,14 @@ lpfc_sli4_arm_cqeq_intr(struct lpfc_hba *phba)
 			lpfc_sli4_eq_release(phba->sli4_hba.hba_eq[qidx],
 						LPFC_QUEUE_REARM);
 
+	if (phba->nvmet_support) {
+		for (qidx = 0; qidx < phba->cfg_nvmet_mrq; qidx++) {
+			lpfc_sli4_cq_release(
+				phba->sli4_hba.nvmet_cqset[qidx],
+				LPFC_QUEUE_REARM);
+		}
+	}
+
 	if (phba->cfg_fof)
 		lpfc_sli4_eq_release(phba->sli4_hba.fof_eq, LPFC_QUEUE_REARM);
 }
@@ -6485,7 +6516,7 @@ lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
 int
 lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 {
-	int rc;
+	int rc, i;
 	LPFC_MBOXQ_t *mboxq;
 	struct lpfc_mqe *mqe;
 	uint8_t *vpd;
@@ -6494,6 +6525,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	struct Scsi_Host *shost = lpfc_shost_from_vport(phba->pport);
 	struct lpfc_vport *vport = phba->pport;
 	struct lpfc_dmabuf *mp;
+	struct lpfc_rqb *rqbp;
 
 	/* Perform a PCI function reset to start from clean */
 	rc = lpfc_pci_function_reset(phba);
@@ -6856,6 +6888,29 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		}
 	}
 
+	if (phba->nvmet_support && phba->cfg_nvmet_mrq) {
+
+		/* Post initial buffers to all RQs created */
+		for (i = 0; i < phba->cfg_nvmet_mrq; i++) {
+			rqbp = phba->sli4_hba.nvmet_mrq_hdr[i]->rqbp;
+			INIT_LIST_HEAD(&rqbp->rqb_buffer_list);
+			rqbp->rqb_alloc_buffer = lpfc_sli4_nvmet_alloc;
+			rqbp->rqb_free_buffer = lpfc_sli4_nvmet_free;
+			rqbp->entry_count = 256;
+			rqbp->buffer_count = 0;
+
+			/* Divide by 4 and round down to multiple of 16 */
+			rc = (phba->cfg_nvmet_mrq_post >> 2) & 0xfff8;
+			phba->sli4_hba.nvmet_mrq_hdr[i]->entry_repost = rc;
+			phba->sli4_hba.nvmet_mrq_data[i]->entry_repost = rc;
+
+			lpfc_post_rq_buffer(
+				phba, phba->sli4_hba.nvmet_mrq_hdr[i],
+				phba->sli4_hba.nvmet_mrq_data[i],
+				phba->cfg_nvmet_mrq_post);
+		}
+	}
+
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
 		/* register the allocated scsi sgl pool to the port */
 		rc = lpfc_sli4_repost_scsi_sgl_list(phba);
@@ -6898,7 +6953,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	lpfc_sli4_node_prep(phba);
 
 	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
-		if (phba->nvmet_support == 0) {
+		if ((phba->nvmet_support == 0) || (phba->cfg_nvmet_mrq == 1)) {
 			/*
 			 * The FC Port needs to register FCFI (index 0)
 			 */
@@ -6910,6 +6965,26 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 			rc = 0;
 			phba->fcf.fcfi = bf_get(lpfc_reg_fcfi_fcfi,
 						&mboxq->u.mqe.un.reg_fcfi);
+		} else {
+			/* We are a NVME Target mode with MRQ > 1 */
+
+			/* First register the FCFI */
+			lpfc_reg_fcfi_mrq(phba, mboxq, 0);
+			mboxq->vport = phba->pport;
+			rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+			if (rc != MBX_SUCCESS)
+				goto out_unset_queue;
+			rc = 0;
+			phba->fcf.fcfi = bf_get(lpfc_reg_fcfi_mrq_fcfi,
+						&mboxq->u.mqe.un.reg_fcfi_mrq);
+
+			/* Next register the MRQs */
+			lpfc_reg_fcfi_mrq(phba, mboxq, 1);
+			mboxq->vport = phba->pport;
+			rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+			if (rc != MBX_SUCCESS)
+				goto out_unset_queue;
+			rc = 0;
 		}
 		/* Check if the port is configured to be disabled */
 		lpfc_sli_read_link_ste(phba);
@@ -12987,6 +13062,101 @@ lpfc_sli4_fp_handle_rel_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 				"miss-matched qid: wcqe-qid=x%x\n", hba_wqid);
 }
 
+/**
+ * lpfc_sli4_nvmet_handle_rcqe - Process a receive-queue completion queue entry
+ * @phba: Pointer to HBA context object.
+ * @rcqe: Pointer to receive-queue completion queue entry.
+ *
+ * This routine process a receive-queue completion queue entry.
+ *
+ * Return: true if work posted to worker thread, otherwise false.
+ **/
+static bool
+lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
+			    struct lpfc_rcqe *rcqe)
+{
+	bool workposted = false;
+	struct lpfc_queue *hrq;
+	struct lpfc_queue *drq;
+	struct rqb_dmabuf *dma_buf;
+	struct fc_frame_header *fc_hdr;
+	uint32_t status, rq_id;
+	unsigned long iflags;
+	uint32_t fctl, idx;
+
+	if ((phba->nvmet_support == 0) ||
+	    (phba->sli4_hba.nvmet_cqset == NULL))
+		return workposted;
+
+	idx = cq->queue_id - phba->sli4_hba.nvmet_cqset[0]->queue_id;
+	hrq = phba->sli4_hba.nvmet_mrq_hdr[idx];
+	drq = phba->sli4_hba.nvmet_mrq_data[idx];
+
+	/* sanity check on queue memory */
+	if (unlikely(!hrq) || unlikely(!drq))
+		return workposted;
+
+	if (bf_get(lpfc_cqe_code, rcqe) == CQE_CODE_RECEIVE_V1)
+		rq_id = bf_get(lpfc_rcqe_rq_id_v1, rcqe);
+	else
+		rq_id = bf_get(lpfc_rcqe_rq_id, rcqe);
+
+	if ((phba->nvmet_support == 0) ||
+	    (rq_id != hrq->queue_id))
+		return workposted;
+
+	status = bf_get(lpfc_rcqe_status, rcqe);
+	switch (status) {
+	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"6126 Receive Frame Truncated!!\n");
+		hrq->RQ_buf_trunc++;
+		break;
+	case FC_STATUS_RQ_SUCCESS:
+		lpfc_sli4_rq_release(hrq, drq);
+		spin_lock_irqsave(&phba->hbalock, iflags);
+		dma_buf = lpfc_sli_rqbuf_get(phba, hrq);
+		if (!dma_buf) {
+			hrq->RQ_no_buf_found++;
+			spin_unlock_irqrestore(&phba->hbalock, iflags);
+			goto out;
+		}
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
+		hrq->RQ_rcv_buf++;
+		fc_hdr = (struct fc_frame_header *)dma_buf->hbuf.virt;
+
+		/* Just some basic sanity checks on FCP Command frame */
+		fctl = (fc_hdr->fh_f_ctl[0] << 16 |
+		fc_hdr->fh_f_ctl[1] << 8 |
+		fc_hdr->fh_f_ctl[2]);
+		if (((fctl &
+		    (FC_FC_FIRST_SEQ | FC_FC_END_SEQ | FC_FC_SEQ_INIT)) !=
+		    (FC_FC_FIRST_SEQ | FC_FC_END_SEQ | FC_FC_SEQ_INIT)) ||
+		    (fc_hdr->fh_seq_cnt != 0)) /* 0 byte swapped is still 0 */
+			goto drop;
+
+		if (fc_hdr->fh_type == FC_TYPE_FCP) {
+			dma_buf->bytes_recv = bf_get(lpfc_rcqe_length,  rcqe);
+			/* todo: tgt: forward cmd iu to transport */
+			return false;
+		}
+drop:
+		lpfc_in_buf_free(phba, &dma_buf->dbuf);
+		break;
+	case FC_STATUS_INSUFF_BUF_NEED_BUF:
+	case FC_STATUS_INSUFF_BUF_FRM_DISC:
+		hrq->RQ_no_posted_buf++;
+		/* Post more buffers if possible */
+		spin_lock_irqsave(&phba->hbalock, iflags);
+		phba->hba_flag |= HBA_POST_RECEIVE_BUFFER;
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
+		workposted = true;
+		break;
+	}
+out:
+	return workposted;
+}
+
 /**
  * lpfc_sli4_fp_handle_cqe - Process fast-path work queue completion entry
  * @cq: Pointer to the completion queue.
@@ -13035,6 +13205,10 @@ lpfc_sli4_fp_handle_cqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	case CQE_CODE_RECEIVE_V1:
 	case CQE_CODE_RECEIVE:
 		phba->last_completion_time = jiffies;
+		if (cq->subtype == LPFC_NVMET) {
+			workposted = lpfc_sli4_nvmet_handle_rcqe(
+				phba, cq, (struct lpfc_rcqe *)&wcqe);
+		}
 		break;
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
@@ -13064,7 +13238,7 @@ lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 	struct lpfc_queue *cq = NULL;
 	struct lpfc_cqe *cqe;
 	bool workposted = false;
-	uint16_t cqid;
+	uint16_t cqid, id;
 	int ecount = 0;
 
 	if (unlikely(bf_get_le32(lpfc_eqe_major_code, eqe) != 0)) {
@@ -13079,6 +13253,15 @@ lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 	/* Get the reference to the corresponding CQ */
 	cqid = bf_get_le32(lpfc_eqe_resource_id, eqe);
 
+	if (phba->cfg_nvmet_mrq && phba->sli4_hba.nvmet_cqset) {
+		id = phba->sli4_hba.nvmet_cqset[0]->queue_id;
+		if ((cqid >= id) && (cqid < (id + phba->cfg_nvmet_mrq))) {
+			/* Process NVMET unsol rcv */
+			cq = phba->sli4_hba.nvmet_cqset[cqid - id];
+			goto  process_cq;
+		}
+	}
+
 	if (phba->sli4_hba.nvme_cq_map &&
 	    (cqid == phba->sli4_hba.nvme_cq_map[qidx])) {
 		/* Process NVME / NVMET command completion */
@@ -13962,6 +14145,234 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	return status;
 }
 
+/**
+ * lpfc_cq_create_set - Create a set of Completion Queues on the HBA for MRQ
+ * @phba: HBA structure that indicates port to create a queue on.
+ * @cqp: The queue structure array to use to create the completion queues.
+ * @eqp: The event queue array to bind these completion queues to.
+ *
+ * This function creates a set of  completion queue, s to support MRQ
+ * as detailed in @cqp, on a port,
+ * described by @phba by sending a CREATE_CQ_SET mailbox command to the HBA.
+ *
+ * The @phba struct is used to send mailbox command to HBA. The @cq struct
+ * is used to get the entry count and entry size that are necessary to
+ * determine the number of pages to allocate and use for this queue. The @eq
+ * is used to indicate which event queue to bind this completion queue to. This
+ * function will send the CREATE_CQ_SET mailbox command to the HBA to setup the
+ * completion queue. This function is asynchronous and will wait for the mailbox
+ * command to finish before continuing.
+ *
+ * On success this function will return a zero. If unable to allocate enough
+ * memory this function will return -ENOMEM. If the queue create mailbox command
+ * fails this function will return -ENXIO.
+ **/
+int
+lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp,
+		   struct lpfc_queue **eqp, uint32_t type, uint32_t subtype)
+{
+	struct lpfc_queue *cq;
+	struct lpfc_queue *eq;
+	struct lpfc_mbx_cq_create_set *cq_set;
+	struct lpfc_dmabuf *dmabuf;
+	LPFC_MBOXQ_t *mbox;
+	int rc, length, alloclen, status = 0;
+	int cnt, idx, numcq, page_idx = 0;
+	uint32_t shdr_status, shdr_add_status;
+	union lpfc_sli4_cfg_shdr *shdr;
+	uint32_t hw_page_size = phba->sli4_hba.pc_sli4_params.if_page_sz;
+
+	/* sanity check on queue memory */
+	numcq = phba->cfg_nvmet_mrq;
+	if (!cqp || !eqp || !numcq)
+		return -ENODEV;
+	if (!phba->sli4_hba.pc_sli4_params.supported)
+		hw_page_size = SLI4_PAGE_SIZE;
+
+	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	length = sizeof(struct lpfc_mbx_cq_create_set);
+	length += ((numcq * cqp[0]->page_count) *
+		   sizeof(struct dma_address));
+	alloclen = lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_FCOE,
+			LPFC_MBOX_OPCODE_FCOE_CQ_CREATE_SET, length,
+			LPFC_SLI4_MBX_NEMBED);
+	if (alloclen < length) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"3098 Allocated DMA memory size (%d) is "
+				"less than the requested DMA memory size "
+				"(%d)\n", alloclen, length);
+		status = -ENOMEM;
+		goto out;
+	}
+	cq_set = mbox->sge_array->addr[0];
+	shdr = (union lpfc_sli4_cfg_shdr *)&cq_set->cfg_shdr;
+	bf_set(lpfc_mbox_hdr_version, &shdr->request, 0);
+
+	for (idx = 0; idx < numcq; idx++) {
+		cq = cqp[idx];
+		eq = eqp[idx];
+		if (!cq || !eq) {
+			status = -ENOMEM;
+			goto out;
+		}
+
+		switch (idx) {
+		case 0:
+			bf_set(lpfc_mbx_cq_create_set_page_size,
+			       &cq_set->u.request,
+			       (hw_page_size / SLI4_PAGE_SIZE));
+			bf_set(lpfc_mbx_cq_create_set_num_pages,
+			       &cq_set->u.request, cq->page_count);
+			bf_set(lpfc_mbx_cq_create_set_evt,
+			       &cq_set->u.request, 1);
+			bf_set(lpfc_mbx_cq_create_set_valid,
+			       &cq_set->u.request, 1);
+			bf_set(lpfc_mbx_cq_create_set_cqe_size,
+			       &cq_set->u.request, 0);
+			bf_set(lpfc_mbx_cq_create_set_num_cq,
+			       &cq_set->u.request, numcq);
+			switch (cq->entry_count) {
+			default:
+				lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+						"3118 Bad CQ count. (%d)\n",
+						cq->entry_count);
+				if (cq->entry_count < 256) {
+					status = -EINVAL;
+					goto out;
+				}
+				/* otherwise default to smallest (drop thru) */
+			case 256:
+				bf_set(lpfc_mbx_cq_create_set_cqe_cnt,
+				       &cq_set->u.request, LPFC_CQ_CNT_256);
+				break;
+			case 512:
+				bf_set(lpfc_mbx_cq_create_set_cqe_cnt,
+				       &cq_set->u.request, LPFC_CQ_CNT_512);
+				break;
+			case 1024:
+				bf_set(lpfc_mbx_cq_create_set_cqe_cnt,
+				       &cq_set->u.request, LPFC_CQ_CNT_1024);
+				break;
+			}
+			bf_set(lpfc_mbx_cq_create_set_eq_id0,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 1:
+			bf_set(lpfc_mbx_cq_create_set_eq_id1,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 2:
+			bf_set(lpfc_mbx_cq_create_set_eq_id2,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 3:
+			bf_set(lpfc_mbx_cq_create_set_eq_id3,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 4:
+			bf_set(lpfc_mbx_cq_create_set_eq_id4,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 5:
+			bf_set(lpfc_mbx_cq_create_set_eq_id5,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 6:
+			bf_set(lpfc_mbx_cq_create_set_eq_id6,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 7:
+			bf_set(lpfc_mbx_cq_create_set_eq_id7,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 8:
+			bf_set(lpfc_mbx_cq_create_set_eq_id8,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 9:
+			bf_set(lpfc_mbx_cq_create_set_eq_id9,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 10:
+			bf_set(lpfc_mbx_cq_create_set_eq_id10,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 11:
+			bf_set(lpfc_mbx_cq_create_set_eq_id11,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 12:
+			bf_set(lpfc_mbx_cq_create_set_eq_id12,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 13:
+			bf_set(lpfc_mbx_cq_create_set_eq_id13,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 14:
+			bf_set(lpfc_mbx_cq_create_set_eq_id14,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		case 15:
+			bf_set(lpfc_mbx_cq_create_set_eq_id15,
+			       &cq_set->u.request, eq->queue_id);
+			break;
+		}
+
+		/* link the cq onto the parent eq child list */
+		list_add_tail(&cq->list, &eq->child_list);
+		/* Set up completion queue's type and subtype */
+		cq->type = type;
+		cq->subtype = subtype;
+		cq->assoc_qid = eq->queue_id;
+		cq->host_index = 0;
+		cq->hba_index = 0;
+
+		rc = 0;
+		list_for_each_entry(dmabuf, &cq->page_list, list) {
+			memset(dmabuf->virt, 0, hw_page_size);
+			cnt = page_idx + dmabuf->buffer_tag;
+			cq_set->u.request.page[cnt].addr_lo =
+					putPaddrLow(dmabuf->phys);
+			cq_set->u.request.page[cnt].addr_hi =
+					putPaddrHigh(dmabuf->phys);
+			rc++;
+		}
+		page_idx += rc;
+	}
+
+	rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+
+	/* The IOCTL status is embedded in the mailbox subheader. */
+	shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+	shdr_add_status = bf_get(lpfc_mbox_hdr_add_status, &shdr->response);
+	if (shdr_status || shdr_add_status || rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3119 CQ_CREATE_SET mailbox failed with "
+				"status x%x add_status x%x, mbx status x%x\n",
+				shdr_status, shdr_add_status, rc);
+		status = -ENXIO;
+		goto out;
+	}
+	rc = bf_get(lpfc_mbx_cq_create_set_base_id, &cq_set->u.response);
+	if (rc == 0xFFFF) {
+		status = -ENXIO;
+		goto out;
+	}
+
+	for (idx = 0; idx < numcq; idx++) {
+		cq = cqp[idx];
+		cq->queue_id = rc + idx;
+	}
+
+out:
+	lpfc_sli4_mbox_cmd_free(phba, mbox);
+	return status;
+}
+
 /**
  * lpfc_mq_create_fb_init - Send MCC_CREATE without async events registration
  * @phba: HBA structure that indicates port to create a queue on.
@@ -14692,6 +15103,197 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	return status;
 }
 
+/**
+ * lpfc_mrq_create - Create MRQ Receive Queues on the HBA
+ * @phba: HBA structure that indicates port to create a queue on.
+ * @hrqp: The queue structure array to use to create the header receive queues.
+ * @drqp: The queue structure array to use to create the data receive queues.
+ * @cqp: The completion queue array to bind these receive queues to.
+ *
+ * This function creates a receive buffer queue pair , as detailed in @hrq and
+ * @drq, on a port, described by @phba by sending a RQ_CREATE mailbox command
+ * to the HBA.
+ *
+ * The @phba struct is used to send mailbox command to HBA. The @drq and @hrq
+ * struct is used to get the entry count that is necessary to determine the
+ * number of pages to use for this queue. The @cq is used to indicate which
+ * completion queue to bind received buffers that are posted to these queues to.
+ * This function will send the RQ_CREATE mailbox command to the HBA to setup the
+ * receive queue pair. This function is asynchronous and will wait for the
+ * mailbox command to finish before continuing.
+ *
+ * On success this function will return a zero. If unable to allocate enough
+ * memory this function will return -ENOMEM. If the queue create mailbox command
+ * fails this function will return -ENXIO.
+ **/
+int
+lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
+		struct lpfc_queue **drqp, struct lpfc_queue **cqp,
+		uint32_t subtype)
+{
+	struct lpfc_queue *hrq, *drq, *cq;
+	struct lpfc_mbx_rq_create_v2 *rq_create;
+	struct lpfc_dmabuf *dmabuf;
+	LPFC_MBOXQ_t *mbox;
+	int rc, length, alloclen, status = 0;
+	int cnt, idx, numrq, page_idx = 0;
+	uint32_t shdr_status, shdr_add_status;
+	union lpfc_sli4_cfg_shdr *shdr;
+	uint32_t hw_page_size = phba->sli4_hba.pc_sli4_params.if_page_sz;
+
+	numrq = phba->cfg_nvmet_mrq;
+	/* sanity check on array memory */
+	if (!hrqp || !drqp || !cqp || !numrq)
+		return -ENODEV;
+	if (!phba->sli4_hba.pc_sli4_params.supported)
+		hw_page_size = SLI4_PAGE_SIZE;
+
+	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	length = sizeof(struct lpfc_mbx_rq_create_v2);
+	length += ((2 * numrq * hrqp[0]->page_count) *
+		   sizeof(struct dma_address));
+
+	alloclen = lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_FCOE,
+				    LPFC_MBOX_OPCODE_FCOE_RQ_CREATE, length,
+				    LPFC_SLI4_MBX_NEMBED);
+	if (alloclen < length) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+				"3099 Allocated DMA memory size (%d) is "
+				"less than the requested DMA memory size "
+				"(%d)\n", alloclen, length);
+		status = -ENOMEM;
+		goto out;
+	}
+
+
+
+	rq_create = mbox->sge_array->addr[0];
+	shdr = (union lpfc_sli4_cfg_shdr *)&rq_create->cfg_shdr;
+
+	bf_set(lpfc_mbox_hdr_version, &shdr->request, LPFC_Q_CREATE_VERSION_2);
+	cnt = 0;
+
+	for (idx = 0; idx < numrq; idx++) {
+		hrq = hrqp[idx];
+		drq = drqp[idx];
+		cq  = cqp[idx];
+
+		if (hrq->entry_count != drq->entry_count) {
+			status = -EINVAL;
+			goto out;
+		}
+
+		/* sanity check on queue memory */
+		if (!hrq || !drq || !cq) {
+			status = -ENODEV;
+			goto out;
+		}
+
+		if (idx == 0) {
+			bf_set(lpfc_mbx_rq_create_num_pages,
+			       &rq_create->u.request,
+			       hrq->page_count);
+			bf_set(lpfc_mbx_rq_create_rq_cnt,
+			       &rq_create->u.request, (numrq * 2));
+			bf_set(lpfc_mbx_rq_create_dnb, &rq_create->u.request,
+			       1);
+			bf_set(lpfc_rq_context_base_cq,
+			       &rq_create->u.request.context,
+			       cq->queue_id);
+			bf_set(lpfc_rq_context_data_size,
+			       &rq_create->u.request.context,
+			       LPFC_DATA_BUF_SIZE);
+			bf_set(lpfc_rq_context_hdr_size,
+			       &rq_create->u.request.context,
+			       LPFC_HDR_BUF_SIZE);
+			bf_set(lpfc_rq_context_rqe_count_1,
+			       &rq_create->u.request.context,
+			       hrq->entry_count);
+			bf_set(lpfc_rq_context_rqe_size,
+			       &rq_create->u.request.context,
+			       LPFC_RQE_SIZE_8);
+			bf_set(lpfc_rq_context_page_size,
+			       &rq_create->u.request.context,
+			       (PAGE_SIZE/SLI4_PAGE_SIZE));
+		}
+		rc = 0;
+		list_for_each_entry(dmabuf, &hrq->page_list, list) {
+			memset(dmabuf->virt, 0, hw_page_size);
+			cnt = page_idx + dmabuf->buffer_tag;
+			rq_create->u.request.page[cnt].addr_lo =
+					putPaddrLow(dmabuf->phys);
+			rq_create->u.request.page[cnt].addr_hi =
+					putPaddrHigh(dmabuf->phys);
+			rc++;
+		}
+		page_idx += rc;
+
+		rc = 0;
+		list_for_each_entry(dmabuf, &drq->page_list, list) {
+			memset(dmabuf->virt, 0, hw_page_size);
+			cnt = page_idx + dmabuf->buffer_tag;
+			rq_create->u.request.page[cnt].addr_lo =
+					putPaddrLow(dmabuf->phys);
+			rq_create->u.request.page[cnt].addr_hi =
+					putPaddrHigh(dmabuf->phys);
+			rc++;
+		}
+		page_idx += rc;
+
+		hrq->db_format = LPFC_DB_RING_FORMAT;
+		hrq->db_regaddr = phba->sli4_hba.RQDBregaddr;
+		hrq->type = LPFC_HRQ;
+		hrq->assoc_qid = cq->queue_id;
+		hrq->subtype = subtype;
+		hrq->host_index = 0;
+		hrq->hba_index = 0;
+
+		drq->db_format = LPFC_DB_RING_FORMAT;
+		drq->db_regaddr = phba->sli4_hba.RQDBregaddr;
+		drq->type = LPFC_DRQ;
+		drq->assoc_qid = cq->queue_id;
+		drq->subtype = subtype;
+		drq->host_index = 0;
+		drq->hba_index = 0;
+
+		list_add_tail(&hrq->list, &cq->child_list);
+		list_add_tail(&drq->list, &cq->child_list);
+	}
+
+	rc = lpfc_sli_issue_mbox(phba, mbox, MBX_POLL);
+	/* The IOCTL status is embedded in the mailbox subheader. */
+	shdr_status = bf_get(lpfc_mbox_hdr_status, &shdr->response);
+	shdr_add_status = bf_get(lpfc_mbox_hdr_add_status, &shdr->response);
+	if (shdr_status || shdr_add_status || rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3120 RQ_CREATE mailbox failed with "
+				"status x%x add_status x%x, mbx status x%x\n",
+				shdr_status, shdr_add_status, rc);
+		status = -ENXIO;
+		goto out;
+	}
+	rc = bf_get(lpfc_mbx_rq_create_q_id, &rq_create->u.response);
+	if (rc == 0xFFFF) {
+		status = -ENXIO;
+		goto out;
+	}
+
+	/* Initialize all RQs with associated queue id */
+	for (idx = 0; idx < numrq; idx++) {
+		hrq = hrqp[idx];
+		hrq->queue_id = rc + (2 * idx);
+		drq = drqp[idx];
+		drq->queue_id = rc + (2 * idx) + 1;
+	}
+
+out:
+	lpfc_sli4_mbox_cmd_free(phba, mbox);
+	return status;
+}
+
 /**
  * lpfc_eq_destroy - Destroy an event Queue on the HBA
  * @eq: The queue structure associated with the queue to destroy.
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 99546eaef087..3bfdff1a4c53 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -550,6 +550,9 @@ struct lpfc_sli4_hba {
 	struct lpfc_queue **hba_eq;  /* Event queues for HBA */
 	struct lpfc_queue **fcp_cq;  /* Fast-path FCP compl queue */
 	struct lpfc_queue **nvme_cq; /* Fast-path NVME compl queue */
+	struct lpfc_queue **nvmet_cqset; /* Fast-path NVMET CQ Set queues */
+	struct lpfc_queue **nvmet_mrq_hdr; /* Fast-path NVMET hdr MRQs */
+	struct lpfc_queue **nvmet_mrq_data; /* Fast-path NVMET data MRQs */
 	struct lpfc_queue **fcp_wq;  /* Fast-path FCP work queue */
 	struct lpfc_queue **nvme_wq; /* Fast-path NVME work queue */
 	uint16_t *fcp_cq_map;
@@ -655,6 +658,8 @@ struct lpfc_sli4_hba {
 	uint16_t num_online_cpu;
 	uint16_t num_present_cpu;
 	uint16_t curr_disp_cpu;
+
+	uint16_t nvmet_mrq_post_idx;
 };
 
 enum lpfc_sge_type {
@@ -742,12 +747,18 @@ int lpfc_eq_create(struct lpfc_hba *, struct lpfc_queue *, uint32_t);
 int lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq);
 int lpfc_cq_create(struct lpfc_hba *, struct lpfc_queue *,
 			struct lpfc_queue *, uint32_t, uint32_t);
+int lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp,
+			struct lpfc_queue **eqp, uint32_t type,
+			uint32_t subtype);
 int32_t lpfc_mq_create(struct lpfc_hba *, struct lpfc_queue *,
 		       struct lpfc_queue *, uint32_t);
 int lpfc_wq_create(struct lpfc_hba *, struct lpfc_queue *,
 			struct lpfc_queue *, uint32_t);
 int lpfc_rq_create(struct lpfc_hba *, struct lpfc_queue *,
 			struct lpfc_queue *, struct lpfc_queue *, uint32_t);
+int lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
+			struct lpfc_queue **drqp, struct lpfc_queue **cqp,
+			uint32_t subtype);
 void lpfc_rq_adjust_repost(struct lpfc_hba *, struct lpfc_queue *, int);
 int lpfc_eq_destroy(struct lpfc_hba *, struct lpfc_queue *);
 int lpfc_cq_destroy(struct lpfc_hba *, struct lpfc_queue *);
-- 
GitLab


From 8c258641e01cfcc5620c4fb191300bea224bcc99 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:36 -0800
Subject: [PATCH 151/898] scsi: lpfc: NVME Target: Merge into FC discovery

NVME Target: Merge into FC discovery

Adds NVME PRLI handling and Nameserver registrations for NVME

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_ct.c        |  8 +++-
 drivers/scsi/lpfc/lpfc_els.c       | 61 ++++++++++++++++++++++--
 drivers/scsi/lpfc/lpfc_hbadisc.c   | 27 +++++++++--
 drivers/scsi/lpfc/lpfc_hw.h        | 10 +++-
 drivers/scsi/lpfc/lpfc_nportdisc.c | 75 ++++++++++++++++++++++++++++--
 5 files changed, 167 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 2c051369857a..d576da4d3afb 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1433,7 +1433,13 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 		if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
 		     (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) &&
 		    (context == FC_TYPE_NVME)) {
-			lpfc_nvme_update_localport(vport);
+			if ((vport == phba->pport) && phba->nvmet_support) {
+				CtReq->un.rff.fbits = (FC4_FEATURE_TARGET |
+					FC4_FEATURE_NVME_DISC);
+				/* todo: update targetport attributes */
+			} else {
+				lpfc_nvme_update_localport(vport);
+			}
 			CtReq->un.rff.type_code = context;
 
 		} else if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 23546b3c950c..5ee3ae88a080 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2001,11 +2001,21 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry)
 		sp->cmn.fcphHigh = FC_PH3;
 
 	sp->cmn.valid_vendor_ver_level = 0;
+	memset(sp->un.vendorVersion, 0, sizeof(sp->un.vendorVersion));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Issue PLOGI:     did:x%x",
 		did, 0, 0);
 
+	/* If our firmware supports this feature, convey that
+	 * information to the target using the vendor specific field.
+	 */
+	if (phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) {
+		sp->cmn.valid_vendor_ver_level = 1;
+		sp->un.vv.vid = cpu_to_be32(LPFC_VV_EMLX_ID);
+		sp->un.vv.flags = cpu_to_be32(LPFC_VV_SUPPRESS_RSP);
+	}
+
 	phba->fc_stat.elsXmitPLOGI++;
 	elsiocb->iocb_cmpl = lpfc_cmpl_els_plogi;
 	ret = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, elsiocb, 0);
@@ -2207,7 +2217,13 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		    !phba->nvmet_support)
 			bf_set(prli_fba, npr_nvme, 1);
 
-		bf_set(prli_init, npr_nvme, 1);
+		if (phba->nvmet_support) {
+			bf_set(prli_tgt, npr_nvme, 1);
+			bf_set(prli_disc, npr_nvme, 1);
+
+		} else {
+			bf_set(prli_init, npr_nvme, 1);
+		}
 		npr_nvme->word1 = cpu_to_be32(npr_nvme->word1);
 		npr_nvme->word4 = cpu_to_be32(npr_nvme->word4);
 		elsiocb->iocb_flag |= LPFC_PRLI_NVME_REQ;
@@ -2619,8 +2635,11 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		phba->pport->fc_myDID = 0;
 
 		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
-		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
-			lpfc_nvme_update_localport(phba->pport);
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
+			if (!phba->nvmet_support)
+				lpfc_nvme_update_localport(phba->pport);
+			/* todo: tgt: update targetport attributes */
+		}
 
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (mbox) {
@@ -4074,10 +4093,25 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 			       sizeof(struct lpfc_name));
 			memcpy(&sp->nodeName, &vport->fc_sparam.nodeName,
 			       sizeof(struct lpfc_name));
-		} else
+		} else {
 			memcpy(pcmd, &vport->fc_sparam,
 			       sizeof(struct serv_parm));
 
+			sp->cmn.valid_vendor_ver_level = 0;
+			memset(sp->un.vendorVersion, 0,
+			       sizeof(sp->un.vendorVersion));
+
+			/* If our firmware supports this feature, convey that
+			 * info to the target using the vendor specific field.
+			 */
+			if (phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) {
+				sp->cmn.valid_vendor_ver_level = 1;
+				sp->un.vv.vid = cpu_to_be32(LPFC_VV_EMLX_ID);
+				sp->un.vv.flags =
+					cpu_to_be32(LPFC_VV_SUPPRESS_RSP);
+			}
+		}
+
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
 			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
@@ -4397,7 +4431,22 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 		bf_set(prli_type_code, npr_nvme, PRLI_NVME_TYPE);
 		bf_set(prli_estabImagePair, npr_nvme, 0);  /* Should be 0 */
 		bf_set(prli_acc_rsp_code, npr_nvme, PRLI_REQ_EXECUTED);
-		bf_set(prli_init, npr_nvme, 1);
+		if (phba->nvmet_support) {
+			bf_set(prli_tgt, npr_nvme, 1);
+			bf_set(prli_disc, npr_nvme, 1);
+			if (phba->cfg_nvme_enable_fb) {
+				bf_set(prli_fba, npr_nvme, 1);
+
+				/* TBD.  Target mode needs to post buffers
+				 * that support the configured first burst
+				 * byte size.
+				 */
+				bf_set(prli_fb_sz, npr_nvme,
+				       phba->cfg_nvmet_fb_size);
+			}
+		} else {
+			bf_set(prli_init, npr_nvme, 1);
+		}
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 				 "6015 NVME issue PRLI ACC word1 x%08x "
@@ -5815,6 +5864,8 @@ lpfc_rscn_recovery_check(struct lpfc_vport *vport)
 		    (ndlp->nlp_state == NLP_STE_UNUSED_NODE) ||
 		    !lpfc_rscn_payload_check(vport, ndlp->nlp_DID))
 			continue;
+		if (vport->phba->nvmet_support)
+			continue;
 		lpfc_disc_state_machine(vport, ndlp, NULL,
 					NLP_EVT_DEVICE_RECOVERY);
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 8936f5d91c87..6bbb988dd8da 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -910,8 +910,11 @@ lpfc_linkdown(struct lpfc_hba *phba)
 			vports[i]->fc_myDID = 0;
 
 			if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
-			    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
-				lpfc_nvme_update_localport(vports[i]);
+			    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
+				if (!phba->nvmet_support)
+					lpfc_nvme_update_localport(vports[i]);
+				/* todo: tgt: update targetport attributes */
+			}
 		}
 	}
 	lpfc_destroy_vport_work_array(phba, vports);
@@ -3583,8 +3586,11 @@ lpfc_mbx_cmpl_reg_vpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		vport->fc_myDID = 0;
 
 		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
-		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME))
-			lpfc_nvme_update_localport(vport);
+		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
+			if (!phba->nvmet_support)
+				lpfc_nvme_update_localport(vport);
+			/* todo: update targetport attributes */
+		}
 		goto out;
 	}
 
@@ -4175,6 +4181,11 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				 */
 				vport->phba->nport_event_cnt++;
 				lpfc_nvme_register_port(vport, ndlp);
+			} else {
+				/* Just take an NDLP ref count since the
+				 * target does not register rports.
+				 */
+				lpfc_nlp_get(ndlp);
 			}
 		}
 	}
@@ -5096,6 +5107,8 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 			return NULL;
 		lpfc_nlp_init(vport, ndlp, did);
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+		if (vport->phba->nvmet_support)
+			return ndlp;
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
@@ -5104,6 +5117,8 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 		ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_NPR_NODE);
 		if (!ndlp)
 			return NULL;
+		if (vport->phba->nvmet_support)
+			return ndlp;
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
@@ -5123,6 +5138,8 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 			 * delay timeout is not needed.
 			 */
 			lpfc_cancel_retry_delay_tmo(vport, ndlp);
+			if (vport->phba->nvmet_support)
+				return ndlp;
 			spin_lock_irq(shost->host_lock);
 			ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 			spin_unlock_irq(shost->host_lock);
@@ -5138,6 +5155,8 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 		    ndlp->nlp_flag & NLP_RCV_PLOGI)
 			return NULL;
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+		if (vport->phba->nvmet_support)
+			return ndlp;
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 883e6d2a7bc7..c2221377e246 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -515,7 +515,15 @@ struct serv_parm {	/* Structure is in Big Endian format */
 	struct class_parms cls2;
 	struct class_parms cls3;
 	struct class_parms cls4;
-	uint8_t vendorVersion[16];
+	union {
+		uint8_t vendorVersion[16];
+		struct {
+			uint32_t vid;
+#define LPFC_VV_EMLX_ID	0x454d4c58	/* EMLX */
+			uint32_t flags;
+#define LPFC_VV_SUPPRESS_RSP	1
+		} vv;
+	} un;
 };
 
 /*
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 470f9586192f..0716818f269f 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -288,6 +288,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	uint32_t ed_tov;
 	LPFC_MBOXQ_t *mbox;
 	struct ls_rjt stat;
+	uint32_t vid, flag;
 	int rc;
 
 	memset(&stat, 0, sizeof (struct ls_rjt));
@@ -423,6 +424,15 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		lpfc_can_disctmo(vport);
 	}
 
+	ndlp->nlp_flag &= ~NLP_SUPPRESS_RSP;
+	if ((phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) &&
+	    sp->cmn.valid_vendor_ver_level) {
+		vid = be32_to_cpu(sp->un.vv.vid);
+		flag = be32_to_cpu(sp->un.vv.flags);
+		if ((vid == LPFC_VV_EMLX_ID) && (flag & LPFC_VV_SUPPRESS_RSP))
+			ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
+	}
+
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		goto out;
@@ -744,6 +754,14 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		}
 		if (npr->Retry)
 			ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE;
+
+		/* If this driver is in nvme target mode, set the ndlp's fc4
+		 * type to NVME provided the PRLI response claims NVME FC4
+		 * type.  Target mode does not issue gft_id so doesn't get
+		 * the fc4 type set until now.
+		 */
+		if ((phba->nvmet_support) && (npr->prliType == PRLI_NVME_TYPE))
+			ndlp->nlp_fc4_type |= NLP_FC4_NVME;
 	}
 	if (rport) {
 		/* We need to update the rport role values */
@@ -1041,6 +1059,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 	struct lpfc_iocbq  *cmdiocb, *rspiocb;
 	struct lpfc_dmabuf *pcmd, *prsp, *mp;
 	uint32_t *lp;
+	uint32_t vid, flag;
 	IOCB_t *irsp;
 	struct serv_parm *sp;
 	uint32_t ed_tov;
@@ -1109,6 +1128,16 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 			ed_tov = (phba->fc_edtov + 999999) / 1000000;
 		}
 
+		ndlp->nlp_flag &= ~NLP_SUPPRESS_RSP;
+		if ((phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) &&
+		    sp->cmn.valid_vendor_ver_level) {
+			vid = be32_to_cpu(sp->un.vv.vid);
+			flag = be32_to_cpu(sp->un.vv.flags);
+			if ((vid == LPFC_VV_EMLX_ID) &&
+			    (flag & LPFC_VV_SUPPRESS_RSP))
+				ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
+		}
+
 		/*
 		 * Use the larger EDTOV
 		 * RATOV = 2 * EDTOV for pt-to-pt
@@ -1504,9 +1533,37 @@ lpfc_rcv_prli_reglogin_issue(struct lpfc_vport *vport,
 			     uint32_t evt)
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
+	struct ls_rjt     stat;
 
-	/* Initiator mode. */
-	lpfc_els_rsp_prli_acc(vport, cmdiocb, ndlp);
+	if (vport->phba->nvmet_support) {
+		/* NVME Target mode.  Handle and respond to the PRLI and
+		 * transition to UNMAPPED provided the RPI has completed
+		 * registration.
+		 */
+		if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+			lpfc_rcv_prli(vport, ndlp, cmdiocb);
+			lpfc_els_rsp_prli_acc(vport, cmdiocb, ndlp);
+			lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
+		} else {
+			/* RPI registration has not completed. Reject the PRLI
+			 * to prevent an illegal state transition when the
+			 * rpi registration does complete.
+			 */
+			lpfc_printf_vlog(vport, KERN_WARNING, LOG_NVME_DISC,
+					 "6115 NVMET ndlp rpi %d state "
+					 "unknown, state x%x flags x%08x\n",
+					 ndlp->nlp_rpi, ndlp->nlp_state,
+					 ndlp->nlp_flag);
+			memset(&stat, 0, sizeof(struct ls_rjt));
+			stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC;
+			stat.un.b.lsRjtRsnCodeExp = LSEXP_CMD_IN_PROGRESS;
+			lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb,
+					    ndlp, NULL);
+		}
+	} else {
+		/* Initiator mode. */
+		lpfc_els_rsp_prli_acc(vport, cmdiocb, ndlp);
+	}
 
 	return ndlp->nlp_state;
 }
@@ -1668,7 +1725,12 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
 		lpfc_issue_els_prli(vport, ndlp, 0);
 	} else {
-		/* Only Fabric ports should transition */
+		if ((vport->fc_flag & FC_PT2PT) && phba->nvmet_support)
+			phba->targetport->port_id = vport->fc_myDID;
+
+		/* Only Fabric ports should transition. NVME target
+		 * must complete PRLI.
+		 */
 		if (ndlp->nlp_type & NLP_FABRIC) {
 			ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
@@ -1714,6 +1776,13 @@ lpfc_device_recov_reglogin_issue(struct lpfc_vport *vport,
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
 	spin_lock_irq(shost->host_lock);
 
+	/* If we are a target we won't immediately transition into PRLI,
+	 * so if REG_LOGIN already completed we don't need to ignore it.
+	 */
+	if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED) ||
+	    !vport->phba->nvmet_support)
+		ndlp->nlp_flag |= NLP_IGNR_REG_CMPL;
+
 	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	spin_unlock_irq(shost->host_lock);
 	lpfc_disc_set_adisc(vport, ndlp);
-- 
GitLab


From d613b6a7aa922690e341c9ff0faba66ae299b5ad Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:37 -0800
Subject: [PATCH 152/898] scsi: lpfc: NVME Target: bind to nvmet_fc api

NVME Target: Tie in to NVME Fabrics nvmet_fc LLDD target api

Adds the routines to:
- register and deregister the FC port as a nvmet-fc targetport
- binding of nvme queues to adapter WQs
- receipt and passing of NVME LS's to transport, sending transport response
- receipt of NVME FCP CMD IUs, processing FCP target io data transmission
  commands; transmission of FCP io response
- Abort operations for tgt io exchanges

[mkp: fixed space at end of file warning]

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/Makefile       |    2 +-
 drivers/scsi/lpfc/lpfc_crtn.h    |   10 +
 drivers/scsi/lpfc/lpfc_ct.c      |    2 +-
 drivers/scsi/lpfc/lpfc_els.c     |    5 +-
 drivers/scsi/lpfc/lpfc_hbadisc.c |   10 +-
 drivers/scsi/lpfc/lpfc_init.c    |   14 +-
 drivers/scsi/lpfc/lpfc_mem.c     |   45 +
 drivers/scsi/lpfc/lpfc_nvmet.c   | 1671 ++++++++++++++++++++++++++++++
 drivers/scsi/lpfc/lpfc_sli.c     |    8 +-
 9 files changed, 1752 insertions(+), 15 deletions(-)
 create mode 100644 drivers/scsi/lpfc/lpfc_nvmet.c

diff --git a/drivers/scsi/lpfc/Makefile b/drivers/scsi/lpfc/Makefile
index cd7e1fcf52c6..30a6a35abafd 100644
--- a/drivers/scsi/lpfc/Makefile
+++ b/drivers/scsi/lpfc/Makefile
@@ -31,4 +31,4 @@ obj-$(CONFIG_SCSI_LPFC) := lpfc.o
 lpfc-objs := lpfc_mem.o lpfc_sli.o lpfc_ct.o lpfc_els.o \
 	lpfc_hbadisc.o	lpfc_init.o lpfc_mbox.o lpfc_nportdisc.o   \
 	lpfc_scsi.o lpfc_attr.o lpfc_vport.o lpfc_debugfs.o lpfc_bsg.o \
-	lpfc_nvme.o
+	lpfc_nvme.o lpfc_nvmet.o
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 2e7a7f7f43b2..f56015b78525 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -363,6 +363,8 @@ void *lpfc_nvmet_buf_alloc(struct lpfc_hba *phba, int flags,
 void lpfc_nvmet_buf_free(struct lpfc_hba *phba, void *virtp, dma_addr_t dma);
 
 void lpfc_in_buf_free(struct lpfc_hba *, struct lpfc_dmabuf *);
+void lpfc_rq_buf_free(struct lpfc_hba *phba, struct lpfc_dmabuf *mp);
+
 /* Function prototypes. */
 const char* lpfc_info(struct Scsi_Host *);
 int lpfc_scan_finished(struct Scsi_Host *, unsigned long);
@@ -536,6 +538,14 @@ int lpfc_nvme_register_port(struct lpfc_vport *vport,
 int lpfc_nvme_create_localport(struct lpfc_vport *vport);
 void lpfc_nvme_destroy_localport(struct lpfc_vport *vport);
 void lpfc_nvme_update_localport(struct lpfc_vport *vport);
+int lpfc_nvmet_create_targetport(struct lpfc_hba *phba);
+int lpfc_nvmet_update_targetport(struct lpfc_hba *phba);
+void lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba);
+void lpfc_nvmet_unsol_ls_event(struct lpfc_hba *phba,
+			struct lpfc_sli_ring *pring, struct lpfc_iocbq *piocb);
+void lpfc_nvmet_unsol_fcp_event(struct lpfc_hba *phba,
+			struct lpfc_sli_ring *pring,
+			struct rqb_dmabuf *nvmebuf, uint64_t isr_ts);
 void lpfc_nvme_mod_param_dep(struct lpfc_hba *phba);
 void lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba,
 				struct lpfc_iocbq *cmdiocb,
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index d576da4d3afb..53bdfe421251 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1436,7 +1436,7 @@ lpfc_ns_cmd(struct lpfc_vport *vport, int cmdcode,
 			if ((vport == phba->pport) && phba->nvmet_support) {
 				CtReq->un.rff.fbits = (FC4_FEATURE_TARGET |
 					FC4_FEATURE_NVME_DISC);
-				/* todo: update targetport attributes */
+				lpfc_nvmet_update_targetport(phba);
 			} else {
 				lpfc_nvme_update_localport(vport);
 			}
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 5ee3ae88a080..1c0ac509e6db 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2636,9 +2636,10 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
 		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
-			if (!phba->nvmet_support)
+			if (phba->nvmet_support)
+				lpfc_nvmet_update_targetport(phba);
+			else
 				lpfc_nvme_update_localport(phba->pport);
-			/* todo: tgt: update targetport attributes */
 		}
 
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 6bbb988dd8da..542797bd3134 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -911,9 +911,10 @@ lpfc_linkdown(struct lpfc_hba *phba)
 
 			if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
 			    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
-				if (!phba->nvmet_support)
+				if (phba->nvmet_support)
+					lpfc_nvmet_update_targetport(phba);
+				else
 					lpfc_nvme_update_localport(vports[i]);
-				/* todo: tgt: update targetport attributes */
 			}
 		}
 	}
@@ -3587,9 +3588,10 @@ lpfc_mbx_cmpl_reg_vpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 		if ((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
 		    (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) {
-			if (!phba->nvmet_support)
+			if (phba->nvmet_support)
+				lpfc_nvmet_update_targetport(phba);
+			else
 				lpfc_nvme_update_localport(vport);
-			/* todo: update targetport attributes */
 		}
 		goto out;
 	}
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index e6cbc0bac029..5eafd0db758d 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -10397,7 +10397,13 @@ lpfc_pci_remove_one_s3(struct pci_dev *pdev)
 	/* Remove FC host and then SCSI host with the physical port */
 	fc_remove_host(shost);
 	scsi_remove_host(shost);
+
+	/* Perform ndlp cleanup on the physical port.  The nvme and nvmet
+	 * localports are destroyed after to cleanup all transport memory.
+	 */
 	lpfc_cleanup(vport);
+	lpfc_nvmet_destroy_targetport(phba);
+	lpfc_nvme_destroy_localport(vport);
 
 	/*
 	 * Bring down the SLI Layer. This step disable all interrupts,
@@ -11203,13 +11209,13 @@ lpfc_pci_remove_one_s4(struct pci_dev *pdev)
 	/* Remove FC host and then SCSI host with the physical port */
 	fc_remove_host(shost);
 	scsi_remove_host(shost);
-	/* todo: tgt: remove targetport */
 
-	/* Perform ndlp cleanup on the physical port.  The nvme localport
-	 * is destroyed after to ensure all rports are io-disabled.
+	/* Perform ndlp cleanup on the physical port.  The nvme and nvmet
+	 * localports are destroyed after to cleanup all transport memory.
 	 */
-	lpfc_nvme_destroy_localport(vport);
 	lpfc_cleanup(vport);
+	lpfc_nvmet_destroy_targetport(phba);
+	lpfc_nvme_destroy_localport(vport);
 
 	/*
 	 * Bring down the SLI Layer. This step disables all interrupts,
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index 32db255f5216..2437ec5f4863 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -763,3 +763,48 @@ lpfc_in_buf_free(struct lpfc_hba *phba, struct lpfc_dmabuf *mp)
 	}
 	return;
 }
+
+/**
+ * lpfc_rq_buf_free - Free a RQ DMA buffer
+ * @phba: HBA buffer is associated with
+ * @mp: Buffer to free
+ *
+ * Description: Frees the given DMA buffer in the appropriate way given by
+ * reposting it to its associated RQ so it can be reused.
+ *
+ * Notes: Takes phba->hbalock.  Can be called with or without other locks held.
+ *
+ * Returns: None
+ **/
+void
+lpfc_rq_buf_free(struct lpfc_hba *phba, struct lpfc_dmabuf *mp)
+{
+	struct lpfc_rqb *rqbp;
+	struct lpfc_rqe hrqe;
+	struct lpfc_rqe drqe;
+	struct rqb_dmabuf *rqb_entry;
+	unsigned long flags;
+	int rc;
+
+	if (!mp)
+		return;
+
+	rqb_entry = container_of(mp, struct rqb_dmabuf, hbuf);
+	rqbp = rqb_entry->hrq->rqbp;
+
+	spin_lock_irqsave(&phba->hbalock, flags);
+	list_del(&rqb_entry->hbuf.list);
+	hrqe.address_lo = putPaddrLow(rqb_entry->hbuf.phys);
+	hrqe.address_hi = putPaddrHigh(rqb_entry->hbuf.phys);
+	drqe.address_lo = putPaddrLow(rqb_entry->dbuf.phys);
+	drqe.address_hi = putPaddrHigh(rqb_entry->dbuf.phys);
+	rc = lpfc_sli4_rq_put(rqb_entry->hrq, rqb_entry->drq, &hrqe, &drqe);
+	if (rc < 0) {
+		(rqbp->rqb_free_buffer)(phba, rqb_entry);
+	} else {
+		list_add_tail(&rqb_entry->hbuf.list, &rqbp->rqb_buffer_list);
+		rqbp->buffer_count++;
+	}
+
+	spin_unlock_irqrestore(&phba->hbalock, flags);
+}
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
new file mode 100644
index 000000000000..d4efd86bb156
--- /dev/null
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -0,0 +1,1671 @@
+/*******************************************************************
+ * This file is part of the Emulex Linux Device Driver for         *
+ * Fibre Channsel Host Bus Adapters.                                *
+ * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
+ * EMULEX and SLI are trademarks of Emulex.                        *
+ * www.emulex.com                                                  *
+ * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
+ *                                                                 *
+ * This program is free software; you can redistribute it and/or   *
+ * modify it under the terms of version 2 of the GNU General       *
+ * Public License as published by the Free Software Foundation.    *
+ * This program is distributed in the hope that it will be useful. *
+ * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
+ * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
+ * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
+ * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
+ * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
+ * more details, a copy of which can be found in the file COPYING  *
+ * included with this package.                                     *
+ ********************************************************************/
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <asm/unaligned.h>
+#include <linux/crc-t10dif.h>
+#include <net/checksum.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_tcq.h>
+#include <scsi/scsi_transport_fc.h>
+#include <scsi/fc/fc_fs.h>
+
+#include <../drivers/nvme/host/nvme.h>
+#include <linux/nvme-fc-driver.h>
+
+#include "lpfc_version.h"
+#include "lpfc_hw4.h"
+#include "lpfc_hw.h"
+#include "lpfc_sli.h"
+#include "lpfc_sli4.h"
+#include "lpfc_nl.h"
+#include "lpfc_disc.h"
+#include "lpfc.h"
+#include "lpfc_scsi.h"
+#include "lpfc_nvme.h"
+#include "lpfc_nvmet.h"
+#include "lpfc_logmsg.h"
+#include "lpfc_crtn.h"
+#include "lpfc_vport.h"
+
+static struct lpfc_iocbq *lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *,
+						 struct lpfc_nvmet_rcv_ctx *,
+						 dma_addr_t rspbuf,
+						 uint16_t rspsize);
+static struct lpfc_iocbq *lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *,
+						  struct lpfc_nvmet_rcv_ctx *);
+static int lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *,
+					  struct lpfc_nvmet_rcv_ctx *,
+					  uint32_t, uint16_t);
+static int lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *,
+					    struct lpfc_nvmet_rcv_ctx *,
+					    uint32_t, uint16_t);
+static int lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *,
+					   struct lpfc_nvmet_rcv_ctx *,
+					   uint32_t, uint16_t);
+
+/**
+ * lpfc_nvmet_xmt_ls_rsp_cmp - Completion handler for LS Response
+ * @phba: Pointer to HBA context object.
+ * @cmdwqe: Pointer to driver command WQE object.
+ * @wcqe: Pointer to driver response CQE object.
+ *
+ * The function is called from SLI ring event handler with no
+ * lock held. This function is the completion handler for NVME LS commands
+ * The function frees memory resources used for the NVME commands.
+ **/
+static void
+lpfc_nvmet_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+			  struct lpfc_wcqe_complete *wcqe)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct nvmefc_tgt_ls_req *rsp;
+	struct lpfc_nvmet_rcv_ctx *ctxp;
+	uint32_t status, result;
+
+	status = bf_get(lpfc_wcqe_c_status, wcqe);
+	result = wcqe->parameter;
+	if (!phba->targetport)
+		goto out;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+
+	if (status)
+		atomic_inc(&tgtp->xmt_ls_rsp_error);
+	else
+		atomic_inc(&tgtp->xmt_ls_rsp_cmpl);
+
+out:
+	ctxp = cmdwqe->context2;
+	rsp = &ctxp->ctx.ls_req;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
+			"6038 %s: Entrypoint: ctx %p status %x/%x\n", __func__,
+			ctxp, status, result);
+
+	lpfc_nlp_put(cmdwqe->context1);
+	cmdwqe->context2 = NULL;
+	cmdwqe->context3 = NULL;
+	lpfc_sli_release_iocbq(phba, cmdwqe);
+	rsp->done(rsp);
+	kfree(ctxp);
+}
+
+/**
+ * lpfc_nvmet_rq_post - Repost a NVMET RQ DMA buffer and clean up context
+ * @phba: HBA buffer is associated with
+ * @ctxp: context to clean up
+ * @mp: Buffer to free
+ *
+ * Description: Frees the given DMA buffer in the appropriate way given by
+ * reposting it to its associated RQ so it can be reused.
+ *
+ * Notes: Takes phba->hbalock.  Can be called with or without other locks held.
+ *
+ * Returns: None
+ **/
+void
+lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
+		   struct lpfc_dmabuf *mp)
+{
+	if (ctxp) {
+		if (ctxp->txrdy) {
+			pci_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
+				      ctxp->txrdy_phys);
+			ctxp->txrdy = NULL;
+			ctxp->txrdy_phys = 0;
+		}
+		ctxp->state = LPFC_NVMET_STE_FREE;
+	}
+	lpfc_rq_buf_free(phba, mp);
+}
+
+/**
+ * lpfc_nvmet_xmt_fcp_op_cmp - Completion handler for FCP Response
+ * @phba: Pointer to HBA context object.
+ * @cmdwqe: Pointer to driver command WQE object.
+ * @wcqe: Pointer to driver response CQE object.
+ *
+ * The function is called from SLI ring event handler with no
+ * lock held. This function is the completion handler for NVME FCP commands
+ * The function frees memory resources used for the NVME commands.
+ **/
+static void
+lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+			  struct lpfc_wcqe_complete *wcqe)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct nvmefc_tgt_fcp_req *rsp;
+	struct lpfc_nvmet_rcv_ctx *ctxp;
+	uint32_t status, result, op, start_clean;
+
+	ctxp = cmdwqe->context2;
+	rsp = &ctxp->ctx.fcp_req;
+	op = rsp->op;
+	ctxp->flag &= ~LPFC_NVMET_IO_INP;
+
+	status = bf_get(lpfc_wcqe_c_status, wcqe);
+	result = wcqe->parameter;
+
+	if (!phba->targetport)
+		goto out;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	if (status) {
+		rsp->fcp_error = NVME_SC_DATA_XFER_ERROR;
+		rsp->transferred_length = 0;
+		atomic_inc(&tgtp->xmt_fcp_rsp_error);
+	} else {
+		rsp->fcp_error = NVME_SC_SUCCESS;
+		if (op == NVMET_FCOP_RSP)
+			rsp->transferred_length = rsp->rsplen;
+		else
+			rsp->transferred_length = rsp->transfer_length;
+		atomic_inc(&tgtp->xmt_fcp_rsp_cmpl);
+	}
+
+out:
+	if ((op == NVMET_FCOP_READDATA_RSP) ||
+	    (op == NVMET_FCOP_RSP)) {
+		/* Sanity check */
+		ctxp->state = LPFC_NVMET_STE_DONE;
+		ctxp->entry_cnt++;
+		rsp->done(rsp);
+		/* Let Abort cmpl repost the context */
+		if (!(ctxp->flag & LPFC_NVMET_ABORT_OP))
+			lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+	} else {
+		ctxp->entry_cnt++;
+		start_clean = offsetof(struct lpfc_iocbq, wqe);
+		memset(((char *)cmdwqe) + start_clean, 0,
+		       (sizeof(struct lpfc_iocbq) - start_clean));
+		rsp->done(rsp);
+	}
+}
+
+static int
+lpfc_nvmet_xmt_ls_rsp(struct nvmet_fc_target_port *tgtport,
+		      struct nvmefc_tgt_ls_req *rsp)
+{
+	struct lpfc_nvmet_rcv_ctx *ctxp =
+		container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.ls_req);
+	struct lpfc_hba *phba = ctxp->phba;
+	struct hbq_dmabuf *nvmebuf =
+		(struct hbq_dmabuf *)ctxp->rqb_buffer;
+	struct lpfc_iocbq *nvmewqeq;
+	struct lpfc_nvmet_tgtport *nvmep = tgtport->private;
+	struct lpfc_dmabuf dmabuf;
+	struct ulp_bde64 bpl;
+	int rc;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
+			"6023 %s: Entrypoint ctx %p %p\n", __func__,
+			ctxp, tgtport);
+
+	nvmewqeq = lpfc_nvmet_prep_ls_wqe(phba, ctxp, rsp->rspdma,
+				      rsp->rsplen);
+	if (nvmewqeq == NULL) {
+		atomic_inc(&nvmep->xmt_ls_drop);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6150 LS Drop IO x%x: Prep\n",
+				ctxp->oxid);
+		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+		lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp,
+						ctxp->sid, ctxp->oxid);
+		return -ENOMEM;
+	}
+
+	/* Save numBdes for bpl2sgl */
+	nvmewqeq->rsvd2 = 1;
+	nvmewqeq->hba_wqidx = 0;
+	nvmewqeq->context3 = &dmabuf;
+	dmabuf.virt = &bpl;
+	bpl.addrLow = nvmewqeq->wqe.xmit_sequence.bde.addrLow;
+	bpl.addrHigh = nvmewqeq->wqe.xmit_sequence.bde.addrHigh;
+	bpl.tus.f.bdeSize = rsp->rsplen;
+	bpl.tus.f.bdeFlags = 0;
+	bpl.tus.w = le32_to_cpu(bpl.tus.w);
+
+	nvmewqeq->wqe_cmpl = lpfc_nvmet_xmt_ls_rsp_cmp;
+	nvmewqeq->iocb_cmpl = NULL;
+	nvmewqeq->context2 = ctxp;
+
+	rc = lpfc_sli4_issue_wqe(phba, LPFC_ELS_RING, nvmewqeq);
+	if (rc == WQE_SUCCESS) {
+		/*
+		 * Okay to repost buffer here, but wait till cmpl
+		 * before freeing ctxp and iocbq.
+		 */
+		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+		ctxp->rqb_buffer = 0;
+		atomic_inc(&nvmep->xmt_ls_rsp);
+		return 0;
+	}
+	/* Give back resources */
+	atomic_inc(&nvmep->xmt_ls_drop);
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+			"6151 LS Drop IO x%x: Issue %d\n",
+			ctxp->oxid, rc);
+
+	lpfc_nlp_put(nvmewqeq->context1);
+
+	lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+	lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, ctxp->sid, ctxp->oxid);
+	return -ENXIO;
+}
+
+static int
+lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
+		      struct nvmefc_tgt_fcp_req *rsp)
+{
+	struct lpfc_nvmet_tgtport *lpfc_nvmep = tgtport->private;
+	struct lpfc_nvmet_rcv_ctx *ctxp =
+		container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
+	struct lpfc_hba *phba = ctxp->phba;
+	struct lpfc_iocbq *nvmewqeq;
+	unsigned long iflags;
+	int rc;
+
+	if (rsp->op == NVMET_FCOP_ABORT) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+				"6103 Abort op: oxri x%x %d cnt %d\n",
+				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+		atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
+		ctxp->entry_cnt++;
+		ctxp->flag |= LPFC_NVMET_ABORT_OP;
+		if (ctxp->flag & LPFC_NVMET_IO_INP)
+			lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+						       ctxp->oxid);
+		else
+			lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+							 ctxp->oxid);
+		return 0;
+	}
+
+	/* Sanity check */
+	if (ctxp->state == LPFC_NVMET_STE_ABORT) {
+		atomic_inc(&lpfc_nvmep->xmt_fcp_drop);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6102 Bad state IO x%x aborted\n",
+				ctxp->oxid);
+		goto aerr;
+	}
+
+	nvmewqeq = lpfc_nvmet_prep_fcp_wqe(phba, ctxp);
+	if (nvmewqeq == NULL) {
+		atomic_inc(&lpfc_nvmep->xmt_fcp_drop);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6152 FCP Drop IO x%x: Prep\n",
+				ctxp->oxid);
+		goto aerr;
+	}
+
+	nvmewqeq->wqe_cmpl = lpfc_nvmet_xmt_fcp_op_cmp;
+	nvmewqeq->iocb_cmpl = NULL;
+	nvmewqeq->context2 = ctxp;
+	nvmewqeq->iocb_flag |=  LPFC_IO_NVMET;
+	ctxp->wqeq->hba_wqidx = rsp->hwqid;
+
+	/* For now we take hbalock */
+	spin_lock_irqsave(&phba->hbalock, iflags);
+	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, nvmewqeq);
+	spin_unlock_irqrestore(&phba->hbalock, iflags);
+	if (rc == WQE_SUCCESS) {
+		ctxp->flag |= LPFC_NVMET_IO_INP;
+		return 0;
+	}
+
+	/* Give back resources */
+	atomic_inc(&lpfc_nvmep->xmt_fcp_drop);
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+			"6153 FCP Drop IO x%x: Issue: %d\n",
+			ctxp->oxid, rc);
+
+	ctxp->wqeq->hba_wqidx = 0;
+	nvmewqeq->context2 = NULL;
+	nvmewqeq->context3 = NULL;
+aerr:
+	return -ENXIO;
+}
+
+static void
+lpfc_nvmet_targetport_delete(struct nvmet_fc_target_port *targetport)
+{
+	struct lpfc_nvmet_tgtport *tport = targetport->private;
+
+	/* release any threads waiting for the unreg to complete */
+	complete(&tport->tport_unreg_done);
+}
+
+static struct nvmet_fc_target_template lpfc_tgttemplate = {
+	.targetport_delete = lpfc_nvmet_targetport_delete,
+	.xmt_ls_rsp     = lpfc_nvmet_xmt_ls_rsp,
+	.fcp_op         = lpfc_nvmet_xmt_fcp_op,
+
+	.max_hw_queues  = 1,
+	.max_sgl_segments = LPFC_NVMET_DEFAULT_SEGS,
+	.max_dif_sgl_segments = LPFC_NVMET_DEFAULT_SEGS,
+	.dma_boundary = 0xFFFFFFFF,
+
+	/* optional features */
+	.target_features = 0,
+	/* sizes of additional private data for data structures */
+	.target_priv_sz = sizeof(struct lpfc_nvmet_tgtport),
+};
+
+int
+lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
+{
+	struct lpfc_vport  *vport = phba->pport;
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct nvmet_fc_port_info pinfo;
+	int error = 0;
+
+	if (phba->targetport)
+		return 0;
+
+	memset(&pinfo, 0, sizeof(struct nvmet_fc_port_info));
+	pinfo.node_name = wwn_to_u64(vport->fc_nodename.u.wwn);
+	pinfo.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
+	pinfo.port_id = vport->fc_myDID;
+
+	lpfc_tgttemplate.max_hw_queues = phba->cfg_nvme_io_channel;
+	lpfc_tgttemplate.max_sgl_segments = phba->cfg_sg_seg_cnt;
+	lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP |
+					   NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED;
+
+	error = nvmet_fc_register_targetport(&pinfo, &lpfc_tgttemplate,
+					     &phba->pcidev->dev,
+					     &phba->targetport);
+	if (error) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
+				"6025 Cannot register NVME targetport "
+				"x%x\n", error);
+		phba->targetport = NULL;
+	} else {
+		tgtp = (struct lpfc_nvmet_tgtport *)
+			phba->targetport->private;
+		tgtp->phba = phba;
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
+				"6026 Registered NVME "
+				"targetport: %p, private %p "
+				"portnm %llx nodenm %llx\n",
+				phba->targetport, tgtp,
+				pinfo.port_name, pinfo.node_name);
+
+		atomic_set(&tgtp->rcv_ls_req_in, 0);
+		atomic_set(&tgtp->rcv_ls_req_out, 0);
+		atomic_set(&tgtp->rcv_ls_req_drop, 0);
+		atomic_set(&tgtp->xmt_ls_abort, 0);
+		atomic_set(&tgtp->xmt_ls_rsp, 0);
+		atomic_set(&tgtp->xmt_ls_drop, 0);
+		atomic_set(&tgtp->xmt_ls_rsp_error, 0);
+		atomic_set(&tgtp->xmt_ls_rsp_cmpl, 0);
+		atomic_set(&tgtp->rcv_fcp_cmd_in, 0);
+		atomic_set(&tgtp->rcv_fcp_cmd_out, 0);
+		atomic_set(&tgtp->rcv_fcp_cmd_drop, 0);
+		atomic_set(&tgtp->xmt_fcp_abort, 0);
+		atomic_set(&tgtp->xmt_fcp_drop, 0);
+		atomic_set(&tgtp->xmt_fcp_read_rsp, 0);
+		atomic_set(&tgtp->xmt_fcp_read, 0);
+		atomic_set(&tgtp->xmt_fcp_write, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp_cmpl, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp_error, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp_drop, 0);
+		atomic_set(&tgtp->xmt_abort_rsp, 0);
+		atomic_set(&tgtp->xmt_abort_rsp_error, 0);
+		atomic_set(&tgtp->xmt_abort_cmpl, 0);
+	}
+	return error;
+}
+
+int
+lpfc_nvmet_update_targetport(struct lpfc_hba *phba)
+{
+	struct lpfc_vport  *vport = phba->pport;
+
+	if (!phba->targetport)
+		return 0;
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
+			 "6007 Update NVMET port %p did x%x\n",
+			 phba->targetport, vport->fc_myDID);
+
+	phba->targetport->port_id = vport->fc_myDID;
+	return 0;
+}
+
+void
+lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+
+	if (phba->nvmet_support == 0)
+		return;
+	if (phba->targetport) {
+		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+		init_completion(&tgtp->tport_unreg_done);
+		nvmet_fc_unregister_targetport(phba->targetport);
+		wait_for_completion_timeout(&tgtp->tport_unreg_done, 5);
+	}
+	phba->targetport = NULL;
+}
+
+/**
+ * lpfc_nvmet_unsol_ls_buffer - Process an unsolicited event data buffer
+ * @phba: pointer to lpfc hba data structure.
+ * @pring: pointer to a SLI ring.
+ * @nvmebuf: pointer to lpfc nvme command HBQ data structure.
+ *
+ * This routine is used for processing the WQE associated with a unsolicited
+ * event. It first determines whether there is an existing ndlp that matches
+ * the DID from the unsolicited WQE. If not, it will create a new one with
+ * the DID from the unsolicited WQE. The ELS command from the unsolicited
+ * WQE is then used to invoke the proper routine and to set up proper state
+ * of the discovery state machine.
+ **/
+static void
+lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
+			   struct hbq_dmabuf *nvmebuf)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct fc_frame_header *fc_hdr;
+	struct lpfc_nvmet_rcv_ctx *ctxp;
+	uint32_t *payload;
+	uint32_t size, oxid, sid, rc;
+
+	if (!nvmebuf || !phba->targetport) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6154 LS Drop IO\n");
+		goto dropit;
+	}
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	payload = (uint32_t *)(nvmebuf->dbuf.virt);
+	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
+	size = bf_get(lpfc_rcqe_length,  &nvmebuf->cq_event.cqe.rcqe_cmpl);
+	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
+	sid = sli4_sid_from_fc_hdr(fc_hdr);
+
+	ctxp = kzalloc(sizeof(struct lpfc_nvmet_rcv_ctx), GFP_ATOMIC);
+	if (ctxp == NULL) {
+		atomic_inc(&tgtp->rcv_ls_req_drop);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6155 LS Drop IO x%x: Alloc\n",
+				oxid);
+dropit:
+		if (nvmebuf)
+			lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+		return;
+	}
+	ctxp->phba = phba;
+	ctxp->size = size;
+	ctxp->oxid = oxid;
+	ctxp->sid = sid;
+	ctxp->wqeq = NULL;
+	ctxp->state = LPFC_NVMET_STE_RCV;
+	ctxp->rqb_buffer = (void *)nvmebuf;
+	/*
+	 * The calling sequence should be:
+	 * nvmet_fc_rcv_ls_req -> lpfc_nvmet_xmt_ls_rsp/cmp ->_req->done
+	 * lpfc_nvmet_xmt_ls_rsp_cmp should free the allocated ctxp.
+	 */
+	atomic_inc(&tgtp->rcv_ls_req_in);
+	rc = nvmet_fc_rcv_ls_req(phba->targetport, &ctxp->ctx.ls_req,
+				 payload, size);
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
+			"6037 %s: ctx %p sz %d rc %d: %08x %08x %08x "
+			"%08x %08x %08x\n", __func__, ctxp, size, rc,
+			*payload, *(payload+1), *(payload+2),
+			*(payload+3), *(payload+4), *(payload+5));
+	if (rc == 0) {
+		atomic_inc(&tgtp->rcv_ls_req_out);
+		return;
+	}
+	atomic_inc(&tgtp->rcv_ls_req_drop);
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+			"6156 LS Drop IO x%x: nvmet_fc_rcv_ls_req %d\n",
+			ctxp->oxid, rc);
+
+	/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
+	if (nvmebuf)
+		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+
+	atomic_inc(&tgtp->xmt_ls_abort);
+	lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, sid, oxid);
+}
+
+/**
+ * lpfc_nvmet_unsol_fcp_buffer - Process an unsolicited event data buffer
+ * @phba: pointer to lpfc hba data structure.
+ * @pring: pointer to a SLI ring.
+ * @nvmebuf: pointer to lpfc nvme command HBQ data structure.
+ *
+ * This routine is used for processing the WQE associated with a unsolicited
+ * event. It first determines whether there is an existing ndlp that matches
+ * the DID from the unsolicited WQE. If not, it will create a new one with
+ * the DID from the unsolicited WQE. The ELS command from the unsolicited
+ * WQE is then used to invoke the proper routine and to set up proper state
+ * of the discovery state machine.
+ **/
+static void
+lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
+			    struct lpfc_sli_ring *pring,
+			    struct rqb_dmabuf *nvmebuf,
+			    uint64_t isr_timestamp)
+{
+	struct lpfc_nvmet_rcv_ctx *ctxp;
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct fc_frame_header *fc_hdr;
+	uint32_t *payload;
+	uint32_t size, oxid, sid, rc;
+
+	oxid = 0;
+	if (!nvmebuf || !phba->targetport) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6157 FCP Drop IO\n");
+		goto dropit;
+	}
+
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	payload = (uint32_t *)(nvmebuf->dbuf.virt);
+	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
+	size = nvmebuf->bytes_recv;
+	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
+	sid = sli4_sid_from_fc_hdr(fc_hdr);
+
+	ctxp = (struct lpfc_nvmet_rcv_ctx *)nvmebuf->context;
+	if (ctxp == NULL) {
+		atomic_inc(&tgtp->rcv_fcp_cmd_drop);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6158 FCP Drop IO x%x: Alloc\n",
+				oxid);
+		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
+		/* Cannot send ABTS without context */
+		return;
+	}
+	memset(ctxp, 0, sizeof(ctxp->ctx));
+	ctxp->wqeq = NULL;
+	ctxp->txrdy = NULL;
+	ctxp->offset = 0;
+	ctxp->phba = phba;
+	ctxp->size = size;
+	ctxp->oxid = oxid;
+	ctxp->sid = sid;
+	ctxp->state = LPFC_NVMET_STE_RCV;
+	ctxp->rqb_buffer = nvmebuf;
+	ctxp->entry_cnt = 1;
+	ctxp->flag = 0;
+
+	atomic_inc(&tgtp->rcv_fcp_cmd_in);
+	/*
+	 * The calling sequence should be:
+	 * nvmet_fc_rcv_fcp_req -> lpfc_nvmet_xmt_fcp_op/cmp -> req->done
+	 * lpfc_nvmet_xmt_fcp_op_cmp should free the allocated ctxp.
+	 */
+	rc = nvmet_fc_rcv_fcp_req(phba->targetport, &ctxp->ctx.fcp_req,
+				  payload, size);
+
+	/* Process FCP command */
+	if (rc == 0) {
+		atomic_inc(&tgtp->rcv_fcp_cmd_out);
+		return;
+	}
+
+	atomic_inc(&tgtp->rcv_fcp_cmd_drop);
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+			"6159 FCP Drop IO x%x: nvmet_fc_rcv_fcp_req x%x\n",
+			ctxp->oxid, rc);
+dropit:
+	if (oxid) {
+		lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, sid, oxid);
+		return;
+	}
+
+	if (nvmebuf) {
+		nvmebuf->iocbq->hba_wqidx = 0;
+		/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
+		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
+	}
+}
+
+/**
+ * lpfc_nvmet_unsol_ls_event - Process an unsolicited event from an nvme nport
+ * @phba: pointer to lpfc hba data structure.
+ * @pring: pointer to a SLI ring.
+ * @nvmebuf: pointer to received nvme data structure.
+ *
+ * This routine is used to process an unsolicited event received from a SLI
+ * (Service Level Interface) ring. The actual processing of the data buffer
+ * associated with the unsolicited event is done by invoking the routine
+ * lpfc_nvmet_unsol_ls_buffer() after properly set up the buffer from the
+ * SLI RQ on which the unsolicited event was received.
+ **/
+void
+lpfc_nvmet_unsol_ls_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
+			  struct lpfc_iocbq *piocb)
+{
+	struct lpfc_dmabuf *d_buf;
+	struct hbq_dmabuf *nvmebuf;
+
+	d_buf = piocb->context2;
+	nvmebuf = container_of(d_buf, struct hbq_dmabuf, dbuf);
+
+	if (phba->nvmet_support == 0) {
+		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+		return;
+	}
+	lpfc_nvmet_unsol_ls_buffer(phba, pring, nvmebuf);
+}
+
+/**
+ * lpfc_nvmet_unsol_fcp_event - Process an unsolicited event from an nvme nport
+ * @phba: pointer to lpfc hba data structure.
+ * @pring: pointer to a SLI ring.
+ * @nvmebuf: pointer to received nvme data structure.
+ *
+ * This routine is used to process an unsolicited event received from a SLI
+ * (Service Level Interface) ring. The actual processing of the data buffer
+ * associated with the unsolicited event is done by invoking the routine
+ * lpfc_nvmet_unsol_fcp_buffer() after properly set up the buffer from the
+ * SLI RQ on which the unsolicited event was received.
+ **/
+void
+lpfc_nvmet_unsol_fcp_event(struct lpfc_hba *phba,
+			   struct lpfc_sli_ring *pring,
+			   struct rqb_dmabuf *nvmebuf,
+			   uint64_t isr_timestamp)
+{
+	if (phba->nvmet_support == 0) {
+		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
+		return;
+	}
+	lpfc_nvmet_unsol_fcp_buffer(phba, pring, nvmebuf,
+				    isr_timestamp);
+}
+
+/**
+ * lpfc_nvmet_prep_ls_wqe - Allocate and prepare a lpfc wqe data structure
+ * @phba: pointer to a host N_Port data structure.
+ * @ctxp: Context info for NVME LS Request
+ * @rspbuf: DMA buffer of NVME command.
+ * @rspsize: size of the NVME command.
+ *
+ * This routine is used for allocating a lpfc-WQE data structure from
+ * the driver lpfc-WQE free-list and prepare the WQE with the parameters
+ * passed into the routine for discovery state machine to issue an Extended
+ * Link Service (NVME) commands. It is a generic lpfc-WQE allocation
+ * and preparation routine that is used by all the discovery state machine
+ * routines and the NVME command-specific fields will be later set up by
+ * the individual discovery machine routines after calling this routine
+ * allocating and preparing a generic WQE data structure. It fills in the
+ * Buffer Descriptor Entries (BDEs), allocates buffers for both command
+ * payload and response payload (if expected). The reference count on the
+ * ndlp is incremented by 1 and the reference to the ndlp is put into
+ * context1 of the WQE data structure for this WQE to hold the ndlp
+ * reference for the command's callback function to access later.
+ *
+ * Return code
+ *   Pointer to the newly allocated/prepared nvme wqe data structure
+ *   NULL - when nvme wqe data structure allocation/preparation failed
+ **/
+static struct lpfc_iocbq *
+lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
+		       struct lpfc_nvmet_rcv_ctx *ctxp,
+		       dma_addr_t rspbuf, uint16_t rspsize)
+{
+	struct lpfc_nodelist *ndlp;
+	struct lpfc_iocbq *nvmewqe;
+	union lpfc_wqe *wqe;
+
+	if (!lpfc_is_link_up(phba)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
+				"6104 lpfc_nvmet_prep_ls_wqe: link err: "
+				"NPORT x%x oxid:x%x\n",
+				ctxp->sid, ctxp->oxid);
+		return NULL;
+	}
+
+	/* Allocate buffer for  command wqe */
+	nvmewqe = lpfc_sli_get_iocbq(phba);
+	if (nvmewqe == NULL) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
+				"6105 lpfc_nvmet_prep_ls_wqe: No WQE: "
+				"NPORT x%x oxid:x%x\n",
+				ctxp->sid, ctxp->oxid);
+		return NULL;
+	}
+
+	ndlp = lpfc_findnode_did(phba->pport, ctxp->sid);
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
+	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
+	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
+				"6106 lpfc_nvmet_prep_ls_wqe: No ndlp: "
+				"NPORT x%x oxid:x%x\n",
+				ctxp->sid, ctxp->oxid);
+		goto nvme_wqe_free_wqeq_exit;
+	}
+	ctxp->wqeq = nvmewqe;
+
+	/* prevent preparing wqe with NULL ndlp reference */
+	nvmewqe->context1 = lpfc_nlp_get(ndlp);
+	if (nvmewqe->context1 == NULL)
+		goto nvme_wqe_free_wqeq_exit;
+	nvmewqe->context2 = ctxp;
+
+	wqe = &nvmewqe->wqe;
+	memset(wqe, 0, sizeof(union lpfc_wqe));
+
+	/* Words 0 - 2 */
+	wqe->xmit_sequence.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+	wqe->xmit_sequence.bde.tus.f.bdeSize = rspsize;
+	wqe->xmit_sequence.bde.addrLow = le32_to_cpu(putPaddrLow(rspbuf));
+	wqe->xmit_sequence.bde.addrHigh = le32_to_cpu(putPaddrHigh(rspbuf));
+
+	/* Word 3 */
+
+	/* Word 4 */
+
+	/* Word 5 */
+	bf_set(wqe_dfctl, &wqe->xmit_sequence.wge_ctl, 0);
+	bf_set(wqe_ls, &wqe->xmit_sequence.wge_ctl, 1);
+	bf_set(wqe_la, &wqe->xmit_sequence.wge_ctl, 0);
+	bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_DD_SOL_CTL);
+	bf_set(wqe_type, &wqe->xmit_sequence.wge_ctl, FC_TYPE_NVME);
+
+	/* Word 6 */
+	bf_set(wqe_ctxt_tag, &wqe->xmit_sequence.wqe_com,
+	       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
+	bf_set(wqe_xri_tag, &wqe->xmit_sequence.wqe_com, nvmewqe->sli4_xritag);
+
+	/* Word 7 */
+	bf_set(wqe_cmnd, &wqe->xmit_sequence.wqe_com,
+	       CMD_XMIT_SEQUENCE64_WQE);
+	bf_set(wqe_ct, &wqe->xmit_sequence.wqe_com, SLI4_CT_RPI);
+	bf_set(wqe_class, &wqe->xmit_sequence.wqe_com, CLASS3);
+	bf_set(wqe_pu, &wqe->xmit_sequence.wqe_com, 0);
+
+	/* Word 8 */
+	wqe->xmit_sequence.wqe_com.abort_tag = nvmewqe->iotag;
+
+	/* Word 9 */
+	bf_set(wqe_reqtag, &wqe->xmit_sequence.wqe_com, nvmewqe->iotag);
+	/* Needs to be set by caller */
+	bf_set(wqe_rcvoxid, &wqe->xmit_sequence.wqe_com, ctxp->oxid);
+
+	/* Word 10 */
+	bf_set(wqe_dbde, &wqe->xmit_sequence.wqe_com, 1);
+	bf_set(wqe_iod, &wqe->xmit_sequence.wqe_com, LPFC_WQE_IOD_WRITE);
+	bf_set(wqe_lenloc, &wqe->xmit_sequence.wqe_com,
+	       LPFC_WQE_LENLOC_WORD12);
+	bf_set(wqe_ebde_cnt, &wqe->xmit_sequence.wqe_com, 0);
+
+	/* Word 11 */
+	bf_set(wqe_cqid, &wqe->xmit_sequence.wqe_com,
+	       LPFC_WQE_CQ_ID_DEFAULT);
+	bf_set(wqe_cmd_type, &wqe->xmit_sequence.wqe_com,
+	       OTHER_COMMAND);
+
+	/* Word 12 */
+	wqe->xmit_sequence.xmit_len = rspsize;
+
+	nvmewqe->retry = 1;
+	nvmewqe->vport = phba->pport;
+	nvmewqe->drvrTimeout = (phba->fc_ratov * 3) + LPFC_DRVR_TIMEOUT;
+	nvmewqe->iocb_flag |= LPFC_IO_NVME_LS;
+
+	/* Xmit NVME response to remote NPORT <did> */
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
+			"6039 Xmit NVME LS response to remote "
+			"NPORT x%x iotag:x%x oxid:x%x size:x%x\n",
+			ndlp->nlp_DID, nvmewqe->iotag, ctxp->oxid,
+			rspsize);
+	return nvmewqe;
+
+nvme_wqe_free_wqeq_exit:
+	nvmewqe->context2 = NULL;
+	nvmewqe->context3 = NULL;
+	lpfc_sli_release_iocbq(phba, nvmewqe);
+	return NULL;
+}
+
+
+static struct lpfc_iocbq *
+lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
+			struct lpfc_nvmet_rcv_ctx *ctxp)
+{
+	struct nvmefc_tgt_fcp_req *rsp = &ctxp->ctx.fcp_req;
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct sli4_sge *sgl;
+	struct lpfc_nodelist *ndlp;
+	struct lpfc_iocbq *nvmewqe;
+	struct scatterlist *sgel;
+	union lpfc_wqe128 *wqe;
+	uint32_t *txrdy;
+	dma_addr_t physaddr;
+	int i, cnt;
+	int xc = 1;
+
+	if (!lpfc_is_link_up(phba)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6107 lpfc_nvmet_prep_fcp_wqe: link err:"
+				"NPORT x%x oxid:x%x\n", ctxp->sid,
+				ctxp->oxid);
+		return NULL;
+	}
+
+	ndlp = lpfc_findnode_did(phba->pport, ctxp->sid);
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
+	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
+	     (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6108 lpfc_nvmet_prep_fcp_wqe: no ndlp: "
+				"NPORT x%x oxid:x%x\n",
+				ctxp->sid, ctxp->oxid);
+		return NULL;
+	}
+
+	if (rsp->sg_cnt > phba->cfg_sg_seg_cnt) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6109 lpfc_nvmet_prep_fcp_wqe: seg cnt err: "
+				"NPORT x%x oxid:x%x\n",
+				ctxp->sid, ctxp->oxid);
+		return NULL;
+	}
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	nvmewqe = ctxp->wqeq;
+	if (nvmewqe == NULL) {
+		/* Allocate buffer for  command wqe */
+		nvmewqe = ctxp->rqb_buffer->iocbq;
+		if (nvmewqe == NULL) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+					"6110 lpfc_nvmet_prep_fcp_wqe: No "
+					"WQE: NPORT x%x oxid:x%x\n",
+					ctxp->sid, ctxp->oxid);
+			return NULL;
+		}
+		ctxp->wqeq = nvmewqe;
+		xc = 0; /* create new XRI */
+		nvmewqe->sli4_lxritag = NO_XRI;
+		nvmewqe->sli4_xritag = NO_XRI;
+	}
+
+	/* Sanity check */
+	if (((ctxp->state == LPFC_NVMET_STE_RCV) &&
+	    (ctxp->entry_cnt == 1)) ||
+	    ((ctxp->state == LPFC_NVMET_STE_DATA) &&
+	    (ctxp->entry_cnt > 1))) {
+		wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
+	} else {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6111 Wrong state %s: %d  cnt %d\n",
+				__func__, ctxp->state, ctxp->entry_cnt);
+		return NULL;
+	}
+
+	sgl  = (struct sli4_sge *)ctxp->rqb_buffer->sglq->sgl;
+	switch (rsp->op) {
+	case NVMET_FCOP_READDATA:
+	case NVMET_FCOP_READDATA_RSP:
+		/* Words 0 - 2 : The first sg segment */
+		sgel = &rsp->sg[0];
+		physaddr = sg_dma_address(sgel);
+		wqe->fcp_tsend.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+		wqe->fcp_tsend.bde.tus.f.bdeSize = sg_dma_len(sgel);
+		wqe->fcp_tsend.bde.addrLow = cpu_to_le32(putPaddrLow(physaddr));
+		wqe->fcp_tsend.bde.addrHigh =
+			cpu_to_le32(putPaddrHigh(physaddr));
+
+		/* Word 3 */
+		wqe->fcp_tsend.payload_offset_len = 0;
+
+		/* Word 4 */
+		wqe->fcp_tsend.relative_offset = ctxp->offset;
+
+		/* Word 5 */
+
+		/* Word 6 */
+		bf_set(wqe_ctxt_tag, &wqe->fcp_tsend.wqe_com,
+		       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
+		bf_set(wqe_xri_tag, &wqe->fcp_tsend.wqe_com,
+		       nvmewqe->sli4_xritag);
+
+		/* Word 7 */
+		bf_set(wqe_cmnd, &wqe->fcp_tsend.wqe_com, CMD_FCP_TSEND64_WQE);
+
+		/* Word 8 */
+		wqe->fcp_tsend.wqe_com.abort_tag = nvmewqe->iotag;
+
+		/* Word 9 */
+		bf_set(wqe_reqtag, &wqe->fcp_tsend.wqe_com, nvmewqe->iotag);
+		bf_set(wqe_rcvoxid, &wqe->fcp_tsend.wqe_com, ctxp->oxid);
+
+		/* Word 10 */
+		bf_set(wqe_nvme, &wqe->fcp_tsend.wqe_com, 1);
+		bf_set(wqe_dbde, &wqe->fcp_tsend.wqe_com, 1);
+		bf_set(wqe_iod, &wqe->fcp_tsend.wqe_com, LPFC_WQE_IOD_WRITE);
+		bf_set(wqe_lenloc, &wqe->fcp_tsend.wqe_com,
+		       LPFC_WQE_LENLOC_WORD12);
+		bf_set(wqe_ebde_cnt, &wqe->fcp_tsend.wqe_com, 0);
+		bf_set(wqe_xc, &wqe->fcp_tsend.wqe_com, xc);
+		bf_set(wqe_nvme, &wqe->fcp_tsend.wqe_com, 1);
+		if (phba->cfg_nvme_oas)
+			bf_set(wqe_oas, &wqe->fcp_tsend.wqe_com, 1);
+
+		/* Word 11 */
+		bf_set(wqe_cqid, &wqe->fcp_tsend.wqe_com,
+		       LPFC_WQE_CQ_ID_DEFAULT);
+		bf_set(wqe_cmd_type, &wqe->fcp_tsend.wqe_com,
+		       FCP_COMMAND_TSEND);
+
+		/* Word 12 */
+		wqe->fcp_tsend.fcp_data_len = rsp->transfer_length;
+
+		/* Setup 2 SKIP SGEs */
+		sgl->addr_hi = 0;
+		sgl->addr_lo = 0;
+		sgl->word2 = 0;
+		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_SKIP);
+		sgl->word2 = cpu_to_le32(sgl->word2);
+		sgl->sge_len = 0;
+		sgl++;
+		sgl->addr_hi = 0;
+		sgl->addr_lo = 0;
+		sgl->word2 = 0;
+		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_SKIP);
+		sgl->word2 = cpu_to_le32(sgl->word2);
+		sgl->sge_len = 0;
+		sgl++;
+		if (rsp->op == NVMET_FCOP_READDATA_RSP) {
+			atomic_inc(&tgtp->xmt_fcp_read_rsp);
+			bf_set(wqe_ar, &wqe->fcp_tsend.wqe_com, 1);
+			if ((ndlp->nlp_flag & NLP_SUPPRESS_RSP) &&
+			    (rsp->rsplen == 12)) {
+				bf_set(wqe_sup, &wqe->fcp_tsend.wqe_com, 1);
+				bf_set(wqe_wqes, &wqe->fcp_tsend.wqe_com, 0);
+				bf_set(wqe_irsp, &wqe->fcp_tsend.wqe_com, 0);
+				bf_set(wqe_irsplen, &wqe->fcp_tsend.wqe_com, 0);
+			} else {
+				bf_set(wqe_sup, &wqe->fcp_tsend.wqe_com, 0);
+				bf_set(wqe_wqes, &wqe->fcp_tsend.wqe_com, 1);
+				bf_set(wqe_irsp, &wqe->fcp_tsend.wqe_com, 1);
+				bf_set(wqe_irsplen, &wqe->fcp_tsend.wqe_com,
+				       ((rsp->rsplen >> 2) - 1));
+				memcpy(&wqe->words[16], rsp->rspaddr,
+				       rsp->rsplen);
+			}
+		} else {
+			atomic_inc(&tgtp->xmt_fcp_read);
+
+			bf_set(wqe_sup, &wqe->fcp_tsend.wqe_com, 0);
+			bf_set(wqe_wqes, &wqe->fcp_tsend.wqe_com, 0);
+			bf_set(wqe_irsp, &wqe->fcp_tsend.wqe_com, 0);
+			bf_set(wqe_ar, &wqe->fcp_tsend.wqe_com, 0);
+			bf_set(wqe_irsplen, &wqe->fcp_tsend.wqe_com, 0);
+		}
+		ctxp->state = LPFC_NVMET_STE_DATA;
+		break;
+
+	case NVMET_FCOP_WRITEDATA:
+		/* Words 0 - 2 : The first sg segment */
+		txrdy = pci_pool_alloc(phba->txrdy_payload_pool,
+				       GFP_KERNEL, &physaddr);
+		if (!txrdy) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+					"6041 Bad txrdy buffer: oxid x%x\n",
+					ctxp->oxid);
+			return NULL;
+		}
+		ctxp->txrdy = txrdy;
+		ctxp->txrdy_phys = physaddr;
+		wqe->fcp_treceive.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+		wqe->fcp_treceive.bde.tus.f.bdeSize = TXRDY_PAYLOAD_LEN;
+		wqe->fcp_treceive.bde.addrLow =
+			cpu_to_le32(putPaddrLow(physaddr));
+		wqe->fcp_treceive.bde.addrHigh =
+			cpu_to_le32(putPaddrHigh(physaddr));
+
+		/* Word 3 */
+		wqe->fcp_treceive.payload_offset_len = TXRDY_PAYLOAD_LEN;
+
+		/* Word 4 */
+		wqe->fcp_treceive.relative_offset = ctxp->offset;
+
+		/* Word 5 */
+
+		/* Word 6 */
+		bf_set(wqe_ctxt_tag, &wqe->fcp_treceive.wqe_com,
+		       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
+		bf_set(wqe_xri_tag, &wqe->fcp_treceive.wqe_com,
+		       nvmewqe->sli4_xritag);
+
+		/* Word 7 */
+		bf_set(wqe_ar, &wqe->fcp_treceive.wqe_com, 0);
+		bf_set(wqe_cmnd, &wqe->fcp_treceive.wqe_com,
+		       CMD_FCP_TRECEIVE64_WQE);
+
+		/* Word 8 */
+		wqe->fcp_treceive.wqe_com.abort_tag = nvmewqe->iotag;
+
+		/* Word 9 */
+		bf_set(wqe_reqtag, &wqe->fcp_treceive.wqe_com, nvmewqe->iotag);
+		bf_set(wqe_rcvoxid, &wqe->fcp_treceive.wqe_com, ctxp->oxid);
+
+		/* Word 10 */
+		bf_set(wqe_nvme, &wqe->fcp_treceive.wqe_com, 1);
+		bf_set(wqe_dbde, &wqe->fcp_treceive.wqe_com, 1);
+		bf_set(wqe_iod, &wqe->fcp_treceive.wqe_com, LPFC_WQE_IOD_READ);
+		bf_set(wqe_lenloc, &wqe->fcp_treceive.wqe_com,
+		       LPFC_WQE_LENLOC_WORD12);
+		bf_set(wqe_xc, &wqe->fcp_treceive.wqe_com, xc);
+		bf_set(wqe_wqes, &wqe->fcp_treceive.wqe_com, 0);
+		bf_set(wqe_irsp, &wqe->fcp_treceive.wqe_com, 0);
+		bf_set(wqe_irsplen, &wqe->fcp_treceive.wqe_com, 0);
+		bf_set(wqe_nvme, &wqe->fcp_treceive.wqe_com, 1);
+		if (phba->cfg_nvme_oas)
+			bf_set(wqe_oas, &wqe->fcp_treceive.wqe_com, 1);
+
+		/* Word 11 */
+		bf_set(wqe_cqid, &wqe->fcp_treceive.wqe_com,
+		       LPFC_WQE_CQ_ID_DEFAULT);
+		bf_set(wqe_cmd_type, &wqe->fcp_treceive.wqe_com,
+		       FCP_COMMAND_TRECEIVE);
+		bf_set(wqe_sup, &wqe->fcp_tsend.wqe_com, 0);
+
+		/* Word 12 */
+		wqe->fcp_tsend.fcp_data_len = rsp->transfer_length;
+
+		/* Setup 1 TXRDY and 1 SKIP SGE */
+		txrdy[0] = 0;
+		txrdy[1] = cpu_to_be32(rsp->transfer_length);
+		txrdy[2] = 0;
+
+		sgl->addr_hi = putPaddrHigh(physaddr);
+		sgl->addr_lo = putPaddrLow(physaddr);
+		sgl->word2 = 0;
+		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA);
+		sgl->word2 = cpu_to_le32(sgl->word2);
+		sgl->sge_len = cpu_to_le32(TXRDY_PAYLOAD_LEN);
+		sgl++;
+		sgl->addr_hi = 0;
+		sgl->addr_lo = 0;
+		sgl->word2 = 0;
+		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_SKIP);
+		sgl->word2 = cpu_to_le32(sgl->word2);
+		sgl->sge_len = 0;
+		sgl++;
+		ctxp->state = LPFC_NVMET_STE_DATA;
+		atomic_inc(&tgtp->xmt_fcp_write);
+		break;
+
+	case NVMET_FCOP_RSP:
+		/* Words 0 - 2 */
+		sgel = &rsp->sg[0];
+		physaddr = rsp->rspdma;
+		wqe->fcp_trsp.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+		wqe->fcp_trsp.bde.tus.f.bdeSize = rsp->rsplen;
+		wqe->fcp_trsp.bde.addrLow =
+			cpu_to_le32(putPaddrLow(physaddr));
+		wqe->fcp_trsp.bde.addrHigh =
+			cpu_to_le32(putPaddrHigh(physaddr));
+
+		/* Word 3 */
+		wqe->fcp_trsp.response_len = rsp->rsplen;
+
+		/* Word 4 */
+		wqe->fcp_trsp.rsvd_4_5[0] = 0;
+
+
+		/* Word 5 */
+
+		/* Word 6 */
+		bf_set(wqe_ctxt_tag, &wqe->fcp_trsp.wqe_com,
+		       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
+		bf_set(wqe_xri_tag, &wqe->fcp_trsp.wqe_com,
+		       nvmewqe->sli4_xritag);
+
+		/* Word 7 */
+		bf_set(wqe_ag, &wqe->fcp_trsp.wqe_com, 1);
+		bf_set(wqe_cmnd, &wqe->fcp_trsp.wqe_com, CMD_FCP_TRSP64_WQE);
+
+		/* Word 8 */
+		wqe->fcp_trsp.wqe_com.abort_tag = nvmewqe->iotag;
+
+		/* Word 9 */
+		bf_set(wqe_reqtag, &wqe->fcp_trsp.wqe_com, nvmewqe->iotag);
+		bf_set(wqe_rcvoxid, &wqe->fcp_trsp.wqe_com, ctxp->oxid);
+
+		/* Word 10 */
+		bf_set(wqe_nvme, &wqe->fcp_trsp.wqe_com, 1);
+		bf_set(wqe_dbde, &wqe->fcp_trsp.wqe_com, 0);
+		bf_set(wqe_iod, &wqe->fcp_trsp.wqe_com, LPFC_WQE_IOD_WRITE);
+		bf_set(wqe_lenloc, &wqe->fcp_trsp.wqe_com,
+		       LPFC_WQE_LENLOC_WORD3);
+		bf_set(wqe_xc, &wqe->fcp_trsp.wqe_com, xc);
+		bf_set(wqe_nvme, &wqe->fcp_trsp.wqe_com, 1);
+		if (phba->cfg_nvme_oas)
+			bf_set(wqe_oas, &wqe->fcp_trsp.wqe_com, 1);
+
+		/* Word 11 */
+		bf_set(wqe_cqid, &wqe->fcp_trsp.wqe_com,
+		       LPFC_WQE_CQ_ID_DEFAULT);
+		bf_set(wqe_cmd_type, &wqe->fcp_trsp.wqe_com,
+		       FCP_COMMAND_TRSP);
+		bf_set(wqe_sup, &wqe->fcp_tsend.wqe_com, 0);
+		ctxp->state = LPFC_NVMET_STE_RSP;
+
+		if (rsp->rsplen == LPFC_NVMET_SUCCESS_LEN) {
+			/* Good response - all zero's on wire */
+			bf_set(wqe_wqes, &wqe->fcp_trsp.wqe_com, 0);
+			bf_set(wqe_irsp, &wqe->fcp_trsp.wqe_com, 0);
+			bf_set(wqe_irsplen, &wqe->fcp_trsp.wqe_com, 0);
+		} else {
+			bf_set(wqe_wqes, &wqe->fcp_trsp.wqe_com, 1);
+			bf_set(wqe_irsp, &wqe->fcp_trsp.wqe_com, 1);
+			bf_set(wqe_irsplen, &wqe->fcp_trsp.wqe_com,
+			       ((rsp->rsplen >> 2) - 1));
+			memcpy(&wqe->words[16], rsp->rspaddr, rsp->rsplen);
+		}
+
+		/* Use rspbuf, NOT sg list */
+		rsp->sg_cnt = 0;
+		sgl->word2 = 0;
+		atomic_inc(&tgtp->xmt_fcp_rsp);
+		break;
+
+	default:
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+				"6064 Unknown Rsp Op %d\n",
+				rsp->op);
+		return NULL;
+	}
+
+	nvmewqe->retry = 1;
+	nvmewqe->vport = phba->pport;
+	nvmewqe->drvrTimeout = (phba->fc_ratov * 3) + LPFC_DRVR_TIMEOUT;
+	nvmewqe->context1 = ndlp;
+
+	for (i = 0; i < rsp->sg_cnt; i++) {
+		sgel = &rsp->sg[i];
+		physaddr = sg_dma_address(sgel);
+		cnt = sg_dma_len(sgel);
+		sgl->addr_hi = putPaddrHigh(physaddr);
+		sgl->addr_lo = putPaddrLow(physaddr);
+		sgl->word2 = 0;
+		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA);
+		bf_set(lpfc_sli4_sge_offset, sgl, ctxp->offset);
+		if ((i+1) == rsp->sg_cnt)
+			bf_set(lpfc_sli4_sge_last, sgl, 1);
+		sgl->word2 = cpu_to_le32(sgl->word2);
+		sgl->sge_len = cpu_to_le32(cnt);
+		sgl++;
+		ctxp->offset += cnt;
+	}
+	return nvmewqe;
+}
+
+/**
+ * lpfc_nvmet_sol_fcp_abort_cmp - Completion handler for ABTS
+ * @phba: Pointer to HBA context object.
+ * @cmdwqe: Pointer to driver command WQE object.
+ * @wcqe: Pointer to driver response CQE object.
+ *
+ * The function is called from SLI ring event handler with no
+ * lock held. This function is the completion handler for NVME ABTS for FCP cmds
+ * The function frees memory resources used for the NVME commands.
+ **/
+static void
+lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+			     struct lpfc_wcqe_complete *wcqe)
+{
+	struct lpfc_nvmet_rcv_ctx *ctxp;
+	struct lpfc_nvmet_tgtport *tgtp;
+	uint32_t status, result;
+
+	ctxp = cmdwqe->context2;
+	status = bf_get(lpfc_wcqe_c_status, wcqe);
+	result = wcqe->parameter;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	atomic_inc(&tgtp->xmt_abort_cmpl);
+
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+			"6165 Abort cmpl: xri x%x WCQE: %08x %08x %08x %08x\n",
+			ctxp->oxid, wcqe->word0, wcqe->total_data_placed,
+			result, wcqe->word3);
+
+	ctxp->state = LPFC_NVMET_STE_DONE;
+	lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+
+	cmdwqe->context2 = NULL;
+	cmdwqe->context3 = NULL;
+	lpfc_sli_release_iocbq(phba, cmdwqe);
+}
+
+/**
+ * lpfc_nvmet_xmt_fcp_abort_cmp - Completion handler for ABTS
+ * @phba: Pointer to HBA context object.
+ * @cmdwqe: Pointer to driver command WQE object.
+ * @wcqe: Pointer to driver response CQE object.
+ *
+ * The function is called from SLI ring event handler with no
+ * lock held. This function is the completion handler for NVME ABTS for FCP cmds
+ * The function frees memory resources used for the NVME commands.
+ **/
+static void
+lpfc_nvmet_xmt_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+			     struct lpfc_wcqe_complete *wcqe)
+{
+	struct lpfc_nvmet_rcv_ctx *ctxp;
+	struct lpfc_nvmet_tgtport *tgtp;
+	uint32_t status, result;
+
+	ctxp = cmdwqe->context2;
+	status = bf_get(lpfc_wcqe_c_status, wcqe);
+	result = wcqe->parameter;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	atomic_inc(&tgtp->xmt_abort_cmpl);
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6070 Abort cmpl: ctx %p WCQE: %08x %08x %08x %08x\n",
+			ctxp, wcqe->word0, wcqe->total_data_placed,
+			result, wcqe->word3);
+
+	if (ctxp) {
+		/* Sanity check */
+		if (ctxp->state != LPFC_NVMET_STE_ABORT) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+					"6112 ABORT Wrong state:%d oxid x%x\n",
+					ctxp->state, ctxp->oxid);
+		}
+		ctxp->state = LPFC_NVMET_STE_DONE;
+		lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+		cmdwqe->context2 = NULL;
+		cmdwqe->context3 = NULL;
+	}
+}
+
+/**
+ * lpfc_nvmet_xmt_ls_abort_cmp - Completion handler for ABTS
+ * @phba: Pointer to HBA context object.
+ * @cmdwqe: Pointer to driver command WQE object.
+ * @wcqe: Pointer to driver response CQE object.
+ *
+ * The function is called from SLI ring event handler with no
+ * lock held. This function is the completion handler for NVME ABTS for LS cmds
+ * The function frees memory resources used for the NVME commands.
+ **/
+static void
+lpfc_nvmet_xmt_ls_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+			    struct lpfc_wcqe_complete *wcqe)
+{
+	struct lpfc_nvmet_rcv_ctx *ctxp;
+	struct lpfc_nvmet_tgtport *tgtp;
+	uint32_t status, result;
+
+	ctxp = cmdwqe->context2;
+	status = bf_get(lpfc_wcqe_c_status, wcqe);
+	result = wcqe->parameter;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	atomic_inc(&tgtp->xmt_abort_cmpl);
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6083 Abort cmpl: ctx %p WCQE: %08x %08x %08x %08x\n",
+			ctxp, wcqe->word0, wcqe->total_data_placed,
+			result, wcqe->word3);
+
+	if (ctxp) {
+		cmdwqe->context2 = NULL;
+		cmdwqe->context3 = NULL;
+		lpfc_sli_release_iocbq(phba, cmdwqe);
+		kfree(ctxp);
+	} else
+		lpfc_sli_release_iocbq(phba, cmdwqe);
+}
+
+static int
+lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
+			     struct lpfc_nvmet_rcv_ctx *ctxp,
+			     uint32_t sid, uint16_t xri)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct lpfc_iocbq *abts_wqeq;
+	union lpfc_wqe *wqe_abts;
+	struct lpfc_nodelist *ndlp;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6067 %s: Entrypoint: sid %x xri %x\n", __func__,
+			sid, xri);
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+
+	ndlp = lpfc_findnode_did(phba->pport, sid);
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
+	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
+	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
+		atomic_inc(&tgtp->xmt_abort_rsp_error);
+		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+				"6134 Drop ABTS - wrong NDLP state x%x.\n",
+				ndlp->nlp_state);
+
+		/* No failure to an ABTS request. */
+		return 0;
+	}
+
+	abts_wqeq = ctxp->wqeq;
+	wqe_abts = &abts_wqeq->wqe;
+	ctxp->state = LPFC_NVMET_STE_ABORT;
+
+	/*
+	 * Since we zero the whole WQE, we need to ensure we set the WQE fields
+	 * that were initialized in lpfc_sli4_nvmet_alloc.
+	 */
+	memset(wqe_abts, 0, sizeof(union lpfc_wqe));
+
+	/* Word 5 */
+	bf_set(wqe_dfctl, &wqe_abts->xmit_sequence.wge_ctl, 0);
+	bf_set(wqe_ls, &wqe_abts->xmit_sequence.wge_ctl, 1);
+	bf_set(wqe_la, &wqe_abts->xmit_sequence.wge_ctl, 0);
+	bf_set(wqe_rctl, &wqe_abts->xmit_sequence.wge_ctl, FC_RCTL_BA_ABTS);
+	bf_set(wqe_type, &wqe_abts->xmit_sequence.wge_ctl, FC_TYPE_BLS);
+
+	/* Word 6 */
+	bf_set(wqe_ctxt_tag, &wqe_abts->xmit_sequence.wqe_com,
+	       phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]);
+	bf_set(wqe_xri_tag, &wqe_abts->xmit_sequence.wqe_com,
+	       abts_wqeq->sli4_xritag);
+
+	/* Word 7 */
+	bf_set(wqe_cmnd, &wqe_abts->xmit_sequence.wqe_com,
+	       CMD_XMIT_SEQUENCE64_WQE);
+	bf_set(wqe_ct, &wqe_abts->xmit_sequence.wqe_com, SLI4_CT_RPI);
+	bf_set(wqe_class, &wqe_abts->xmit_sequence.wqe_com, CLASS3);
+	bf_set(wqe_pu, &wqe_abts->xmit_sequence.wqe_com, 0);
+
+	/* Word 8 */
+	wqe_abts->xmit_sequence.wqe_com.abort_tag = abts_wqeq->iotag;
+
+	/* Word 9 */
+	bf_set(wqe_reqtag, &wqe_abts->xmit_sequence.wqe_com, abts_wqeq->iotag);
+	/* Needs to be set by caller */
+	bf_set(wqe_rcvoxid, &wqe_abts->xmit_sequence.wqe_com, xri);
+
+	/* Word 10 */
+	bf_set(wqe_dbde, &wqe_abts->xmit_sequence.wqe_com, 1);
+	bf_set(wqe_iod, &wqe_abts->xmit_sequence.wqe_com, LPFC_WQE_IOD_WRITE);
+	bf_set(wqe_lenloc, &wqe_abts->xmit_sequence.wqe_com,
+	       LPFC_WQE_LENLOC_WORD12);
+	bf_set(wqe_ebde_cnt, &wqe_abts->xmit_sequence.wqe_com, 0);
+	bf_set(wqe_qosd, &wqe_abts->xmit_sequence.wqe_com, 0);
+
+	/* Word 11 */
+	bf_set(wqe_cqid, &wqe_abts->xmit_sequence.wqe_com,
+	       LPFC_WQE_CQ_ID_DEFAULT);
+	bf_set(wqe_cmd_type, &wqe_abts->xmit_sequence.wqe_com,
+	       OTHER_COMMAND);
+
+	abts_wqeq->vport = phba->pport;
+	abts_wqeq->context1 = ndlp;
+	abts_wqeq->context2 = ctxp;
+	abts_wqeq->context3 = NULL;
+	abts_wqeq->rsvd2 = 0;
+	/* hba_wqidx should already be setup from command we are aborting */
+	abts_wqeq->iocb.ulpCommand = CMD_XMIT_SEQUENCE64_CR;
+	abts_wqeq->iocb.ulpLe = 1;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+			"6069 Issue ABTS to xri x%x reqtag x%x\n",
+			xri, abts_wqeq->iotag);
+	return 1;
+}
+
+static int
+lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
+			       struct lpfc_nvmet_rcv_ctx *ctxp,
+			       uint32_t sid, uint16_t xri)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct lpfc_iocbq *abts_wqeq;
+	union lpfc_wqe *abts_wqe;
+	struct lpfc_nodelist *ndlp;
+	unsigned long flags;
+	int rc;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	if (!ctxp->wqeq) {
+		ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+		ctxp->wqeq->hba_wqidx = 0;
+	}
+
+	ndlp = lpfc_findnode_did(phba->pport, sid);
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
+	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
+	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
+		atomic_inc(&tgtp->xmt_abort_rsp_error);
+		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+				"6160 Drop ABTS - wrong NDLP state x%x.\n",
+				ndlp->nlp_state);
+
+		/* No failure to an ABTS request. */
+		return 0;
+	}
+
+	/* Issue ABTS for this WQE based on iotag */
+	ctxp->abort_wqeq = lpfc_sli_get_iocbq(phba);
+	if (!ctxp->abort_wqeq) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+				"6161 Abort failed: No wqeqs: "
+				"xri: x%x\n", ctxp->oxid);
+		/* No failure to an ABTS request. */
+		return 0;
+	}
+	abts_wqeq = ctxp->abort_wqeq;
+	abts_wqe = &abts_wqeq->wqe;
+	ctxp->state = LPFC_NVMET_STE_ABORT;
+
+	/* Announce entry to new IO submit field. */
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+			"6162 Abort Request to rport DID x%06x "
+			"for xri x%x x%x\n",
+			ctxp->sid, ctxp->oxid, ctxp->wqeq->sli4_xritag);
+
+	/* If the hba is getting reset, this flag is set.  It is
+	 * cleared when the reset is complete and rings reestablished.
+	 */
+	spin_lock_irqsave(&phba->hbalock, flags);
+	/* driver queued commands are in process of being flushed */
+	if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+				"6163 Driver in reset cleanup - flushing "
+				"NVME Req now. hba_flag x%x oxid x%x\n",
+				phba->hba_flag, ctxp->oxid);
+		lpfc_sli_release_iocbq(phba, abts_wqeq);
+		return 0;
+	}
+
+	/* Outstanding abort is in progress */
+	if (abts_wqeq->iocb_flag & LPFC_DRIVER_ABORTED) {
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+				"6164 Outstanding NVME I/O Abort Request "
+				"still pending on oxid x%x\n",
+				ctxp->oxid);
+		lpfc_sli_release_iocbq(phba, abts_wqeq);
+		return 0;
+	}
+
+	/* Ready - mark outstanding as aborted by driver. */
+	abts_wqeq->iocb_flag |= LPFC_DRIVER_ABORTED;
+
+	/* WQEs are reused.  Clear stale data and set key fields to
+	 * zero like ia, iaab, iaar, xri_tag, and ctxt_tag.
+	 */
+	memset(abts_wqe, 0, sizeof(union lpfc_wqe));
+
+	/* word 3 */
+	bf_set(abort_cmd_criteria, &abts_wqe->abort_cmd, T_XRI_TAG);
+
+	/* word 7 */
+	bf_set(wqe_ct, &abts_wqe->abort_cmd.wqe_com, 0);
+	bf_set(wqe_cmnd, &abts_wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX);
+
+	/* word 8 - tell the FW to abort the IO associated with this
+	 * outstanding exchange ID.
+	 */
+	abts_wqe->abort_cmd.wqe_com.abort_tag = ctxp->wqeq->sli4_xritag;
+
+	/* word 9 - this is the iotag for the abts_wqe completion. */
+	bf_set(wqe_reqtag, &abts_wqe->abort_cmd.wqe_com,
+	       abts_wqeq->iotag);
+
+	/* word 10 */
+	bf_set(wqe_qosd, &abts_wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_lenloc, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE);
+
+	/* word 11 */
+	bf_set(wqe_cmd_type, &abts_wqe->abort_cmd.wqe_com, OTHER_COMMAND);
+	bf_set(wqe_wqec, &abts_wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_cqid, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+
+	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
+	abts_wqeq->hba_wqidx = ctxp->wqeq->hba_wqidx;
+	abts_wqeq->wqe_cmpl = lpfc_nvmet_sol_fcp_abort_cmp;
+	abts_wqeq->iocb_cmpl = 0;
+	abts_wqeq->iocb_flag |= LPFC_IO_NVME;
+	abts_wqeq->context2 = ctxp;
+	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
+	spin_unlock_irqrestore(&phba->hbalock, flags);
+	if (rc == WQE_SUCCESS)
+		return 0;
+
+	lpfc_sli_release_iocbq(phba, abts_wqeq);
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+			"6166 Failed abts issue_wqe with status x%x "
+			"for oxid x%x.\n",
+			rc, ctxp->oxid);
+	return 1;
+}
+
+
+static int
+lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
+				 struct lpfc_nvmet_rcv_ctx *ctxp,
+				 uint32_t sid, uint16_t xri)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct lpfc_iocbq *abts_wqeq;
+	unsigned long flags;
+	int rc;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	if (!ctxp->wqeq) {
+		ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+		ctxp->wqeq->hba_wqidx = 0;
+	}
+
+	rc = lpfc_nvmet_unsol_issue_abort(phba, ctxp, sid, xri);
+	if (rc == 0)
+		goto aerr;
+
+	spin_lock_irqsave(&phba->hbalock, flags);
+	abts_wqeq = ctxp->wqeq;
+	abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_fcp_abort_cmp;
+	abts_wqeq->iocb_cmpl = 0;
+	abts_wqeq->iocb_flag |= LPFC_IO_NVMET;
+	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
+	spin_unlock_irqrestore(&phba->hbalock, flags);
+	if (rc == WQE_SUCCESS) {
+		atomic_inc(&tgtp->xmt_abort_rsp);
+		return 0;
+	}
+
+aerr:
+	lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+	atomic_inc(&tgtp->xmt_abort_rsp_error);
+	lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+			"6135 Failed to Issue ABTS for oxid x%x. Status x%x\n",
+			ctxp->oxid, rc);
+	return 1;
+}
+
+static int
+lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba,
+				struct lpfc_nvmet_rcv_ctx *ctxp,
+				uint32_t sid, uint16_t xri)
+{
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct lpfc_iocbq *abts_wqeq;
+	union lpfc_wqe *wqe_abts;
+	unsigned long flags;
+	int rc;
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	if (!ctxp->wqeq) {
+		/* Issue ABTS for this WQE based on iotag */
+		ctxp->wqeq = lpfc_sli_get_iocbq(phba);
+		if (!ctxp->wqeq) {
+			lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+					"6068 Abort failed: No wqeqs: "
+					"xri: x%x\n", xri);
+			/* No failure to an ABTS request. */
+			kfree(ctxp);
+			return 0;
+		}
+	}
+	abts_wqeq = ctxp->wqeq;
+	wqe_abts = &abts_wqeq->wqe;
+	lpfc_nvmet_unsol_issue_abort(phba, ctxp, sid, xri);
+
+	spin_lock_irqsave(&phba->hbalock, flags);
+	abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_ls_abort_cmp;
+	abts_wqeq->iocb_cmpl = 0;
+	abts_wqeq->iocb_flag |=  LPFC_IO_NVME_LS;
+	rc = lpfc_sli4_issue_wqe(phba, LPFC_ELS_RING, abts_wqeq);
+	spin_unlock_irqrestore(&phba->hbalock, flags);
+	if (rc == WQE_SUCCESS) {
+		atomic_inc(&tgtp->xmt_abort_rsp);
+		return 0;
+	}
+
+	atomic_inc(&tgtp->xmt_abort_rsp_error);
+	abts_wqeq->context2 = NULL;
+	abts_wqeq->context3 = NULL;
+	lpfc_sli_release_iocbq(phba, abts_wqeq);
+	kfree(ctxp);
+	lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+			"6056 Failed to Issue ABTS. Status x%x\n", rc);
+	return 0;
+}
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 72164acb6656..84565f810392 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2518,7 +2518,7 @@ lpfc_complete_unsol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 
 	switch (fch_type) {
 	case FC_TYPE_NVME:
-		/* todo: tgt: forward NVME LS to transport */
+		lpfc_nvmet_unsol_ls_event(phba, pring, saveq);
 		return 1;
 	default:
 		break;
@@ -6867,7 +6867,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 			goto out_destroy_queue;
 		}
 		phba->sli4_hba.nvmet_xri_cnt = rc;
-		/* todo: tgt: create targetport */
+		lpfc_nvmet_create_targetport(phba);
 	} else {
 		/* update host scsi xri-sgl sizes and mappings */
 		rc = lpfc_sli4_scsi_sgl_update(phba);
@@ -13137,7 +13137,9 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 
 		if (fc_hdr->fh_type == FC_TYPE_FCP) {
 			dma_buf->bytes_recv = bf_get(lpfc_rcqe_length,  rcqe);
-			/* todo: tgt: forward cmd iu to transport */
+			lpfc_nvmet_unsol_fcp_event(
+				phba, phba->sli4_hba.els_wq->pring, dma_buf,
+				cq->assoc_qp->isr_timestamp);
 			return false;
 		}
 drop:
-- 
GitLab


From 2b65e18202fd0f109b739dd6717286edca7a2b0d Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:38 -0800
Subject: [PATCH 153/898] scsi: lpfc: NVME Target: Add debugfs support

NVME Target: Add debugfs support

Adds debugfs snippets to cover the new NVME target functionality

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_debugfs.c | 303 ++++++++++++++++++++++++++++-
 drivers/scsi/lpfc/lpfc_nvmet.c   | 317 ++++++++++++++++++++++++++++++-
 drivers/scsi/lpfc/lpfc_nvmet.h   |  13 ++
 3 files changed, 628 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index abc39f605960..f92796d8dc42 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -47,6 +47,7 @@
 #include "lpfc.h"
 #include "lpfc_scsi.h"
 #include "lpfc_nvme.h"
+#include "lpfc_nvmet.h"
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
@@ -543,11 +544,13 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 	int len = 0;
 	int cnt;
 	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+	struct lpfc_hba  *phba = vport->phba;
 	struct lpfc_nodelist *ndlp;
 	unsigned char *statep;
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
 	struct lpfc_nvme_rport *rport;
+	struct lpfc_nvmet_tgtport *tgtp;
 	struct nvme_fc_remote_port *nrport;
 
 	cnt = (LPFC_NODELIST_SIZE / LPFC_NODELIST_ENTRY_SIZE);
@@ -626,6 +629,27 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 	}
 	spin_unlock_irq(shost->host_lock);
 
+	if (phba->nvmet_support && phba->targetport && (vport == phba->pport)) {
+		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+		len += snprintf(buf + len, size - len,
+				"\nNVME Targetport Entry ...\n");
+
+		/* Port state is only one of two values for now. */
+		if (phba->targetport->port_id)
+			statep = "REGISTERED";
+		else
+			statep = "INIT";
+		len += snprintf(buf + len, size - len,
+				"TGT WWNN x%llx WWPN x%llx State %s\n",
+				wwn_to_u64(vport->fc_nodename.u.wwn),
+				wwn_to_u64(vport->fc_portname.u.wwn),
+				statep);
+		len += snprintf(buf + len, size - len,
+				"    Targetport DID x%06x\n",
+				phba->targetport->port_id);
+		goto out_exit;
+	}
+
 	len += snprintf(buf + len, size - len,
 				"\nNVME Lport/Rport Entries ...\n");
 
@@ -718,9 +742,75 @@ static int
 lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 {
 	struct lpfc_hba   *phba = vport->phba;
+	struct lpfc_nvmet_tgtport *tgtp;
 	int len = 0;
 
-	if (phba->nvmet_support == 0) {
+	if (phba->nvmet_support) {
+		if (!phba->targetport)
+			return len;
+		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+		len += snprintf(buf+len, size-len,
+				"\nNVME Targetport Statistics\n");
+
+		len += snprintf(buf+len, size-len,
+				"LS: Rcv %08x Drop %08x Abort %08x\n",
+				atomic_read(&tgtp->rcv_ls_req_in),
+				atomic_read(&tgtp->rcv_ls_req_drop),
+				atomic_read(&tgtp->xmt_ls_abort));
+		if (atomic_read(&tgtp->rcv_ls_req_in) !=
+		    atomic_read(&tgtp->rcv_ls_req_out)) {
+			len += snprintf(buf+len, size-len,
+					"Rcv LS: in %08x != out %08x\n",
+					atomic_read(&tgtp->rcv_ls_req_in),
+					atomic_read(&tgtp->rcv_ls_req_out));
+		}
+
+		len += snprintf(buf+len, size-len,
+				"LS: Xmt %08x Drop %08x Cmpl %08x Err %08x\n",
+				atomic_read(&tgtp->xmt_ls_rsp),
+				atomic_read(&tgtp->xmt_ls_drop),
+				atomic_read(&tgtp->xmt_ls_rsp_cmpl),
+				atomic_read(&tgtp->xmt_ls_rsp_error));
+
+		len += snprintf(buf+len, size-len,
+				"FCP: Rcv %08x Drop %08x\n",
+				atomic_read(&tgtp->rcv_fcp_cmd_in),
+				atomic_read(&tgtp->rcv_fcp_cmd_drop));
+
+		if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
+		    atomic_read(&tgtp->rcv_fcp_cmd_out)) {
+			len += snprintf(buf+len, size-len,
+					"Rcv FCP: in %08x != out %08x\n",
+					atomic_read(&tgtp->rcv_fcp_cmd_in),
+					atomic_read(&tgtp->rcv_fcp_cmd_out));
+		}
+
+		len += snprintf(buf+len, size-len,
+				"FCP Rsp: read %08x readrsp %08x write %08x rsp %08x\n",
+				atomic_read(&tgtp->xmt_fcp_read),
+				atomic_read(&tgtp->xmt_fcp_read_rsp),
+				atomic_read(&tgtp->xmt_fcp_write),
+				atomic_read(&tgtp->xmt_fcp_rsp));
+
+		len += snprintf(buf+len, size-len,
+				"FCP Rsp: abort %08x drop %08x\n",
+				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_drop));
+
+		len += snprintf(buf+len, size-len,
+				"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
+				atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
+				atomic_read(&tgtp->xmt_fcp_rsp_error),
+				atomic_read(&tgtp->xmt_fcp_rsp_drop));
+
+		len += snprintf(buf+len, size-len,
+				"ABORT: Xmt %08x Err %08x Cmpl %08x",
+				atomic_read(&tgtp->xmt_abort_rsp),
+				atomic_read(&tgtp->xmt_abort_rsp_error),
+				atomic_read(&tgtp->xmt_abort_cmpl));
+
+		len +=  snprintf(buf+len, size-len, "\n");
+	} else {
 		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
 			return len;
 
@@ -828,6 +918,121 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			phba->ktime_data_samples));
 		return len;
 	}
+
+	/* NVME Target */
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"ktime %s: Total Samples: %lld %lld\n",
+			(phba->ktime_on ? "Enabled" : "Disabled"),
+			phba->ktime_data_samples,
+			phba->ktime_status_samples);
+	if (phba->ktime_data_samples == 0)
+		return len;
+
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 1: MSI-X ISR Rcv cmd -to- "
+			"cmd pass to NVME Layer\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg1_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg1_min,
+			phba->ktime_seg1_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 2: cmd pass to NVME Layer- "
+			"-to- Driver rcv cmd OP (action)\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg2_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg2_min,
+			phba->ktime_seg2_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 3: Driver rcv cmd OP -to- "
+			"Firmware WQ doorbell: cmd\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg3_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg3_min,
+			phba->ktime_seg3_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 4: Firmware WQ doorbell: cmd "
+			"-to- MSI-X ISR for cmd cmpl\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg4_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg4_min,
+			phba->ktime_seg4_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 5: MSI-X ISR for cmd cmpl "
+			"-to- NVME layer passed cmd done\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg5_total /
+			phba->ktime_data_samples,
+			phba->ktime_seg5_min,
+			phba->ktime_seg5_max);
+
+	if (phba->ktime_status_samples == 0) {
+		len += snprintf(buf + len, PAGE_SIZE-len,
+				"Total: cmd received by MSI-X ISR "
+				"-to- cmd completed on wire\n");
+		len += snprintf(buf + len, PAGE_SIZE-len,
+				"avg:%08lld min:%08lld "
+				"max %08lld\n",
+				phba->ktime_seg10_total /
+				phba->ktime_data_samples,
+				phba->ktime_seg10_min,
+				phba->ktime_seg10_max);
+		return len;
+	}
+
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 6: NVME layer passed cmd done "
+			"-to- Driver rcv rsp status OP\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg6_total /
+			phba->ktime_status_samples,
+			phba->ktime_seg6_min,
+			phba->ktime_seg6_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 7: Driver rcv rsp status OP "
+			"-to- Firmware WQ doorbell: status\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg7_total /
+			phba->ktime_status_samples,
+			phba->ktime_seg7_min,
+			phba->ktime_seg7_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 8: Firmware WQ doorbell: status"
+			" -to- MSI-X ISR for status cmpl\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg8_total /
+			phba->ktime_status_samples,
+			phba->ktime_seg8_min,
+			phba->ktime_seg8_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Segment 9: MSI-X ISR for status cmpl  "
+			"-to- NVME layer passed status done\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg9_total /
+			phba->ktime_status_samples,
+			phba->ktime_seg9_min,
+			phba->ktime_seg9_max);
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"Total: cmd received by MSI-X ISR -to- "
+			"cmd completed on wire\n");
+	len += snprintf(buf + len, PAGE_SIZE-len,
+			"avg:%08lld min:%08lld max %08lld\n",
+			phba->ktime_seg10_total /
+			phba->ktime_status_samples,
+			phba->ktime_seg10_min,
+			phba->ktime_seg10_max);
 	return len;
 }
 
@@ -953,7 +1158,9 @@ lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size)
 	int i;
 	int len = 0;
 	uint32_t tot_xmt = 0;
+	uint32_t tot_rcv = 0;
 	uint32_t tot_cmpl = 0;
+	uint32_t tot_ccmpl = 0;
 
 	if (phba->nvmet_support == 0) {
 		/* NVME Initiator */
@@ -977,6 +1184,33 @@ lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size)
 		return len;
 	}
 
+	/* NVME Target */
+	len += snprintf(buf + len, PAGE_SIZE - len,
+			"CPUcheck %s ",
+			(phba->cpucheck_on & LPFC_CHECK_NVMET_IO ?
+				"IO Enabled - " : "IO Disabled - "));
+	len += snprintf(buf + len, PAGE_SIZE - len,
+			"%s\n",
+			(phba->cpucheck_on & LPFC_CHECK_NVMET_RCV ?
+				"Rcv Enabled\n" : "Rcv Disabled\n"));
+	for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) {
+		if (i >= LPFC_CHECK_CPU_CNT)
+			break;
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"%02d: xmit x%08x ccmpl x%08x "
+				"cmpl x%08x rcv x%08x\n",
+				i, phba->cpucheck_xmt_io[i],
+				phba->cpucheck_ccmpl_io[i],
+				phba->cpucheck_cmpl_io[i],
+				phba->cpucheck_rcv_io[i]);
+		tot_xmt += phba->cpucheck_xmt_io[i];
+		tot_rcv += phba->cpucheck_rcv_io[i];
+		tot_cmpl += phba->cpucheck_cmpl_io[i];
+		tot_ccmpl += phba->cpucheck_ccmpl_io[i];
+	}
+	len += snprintf(buf + len, PAGE_SIZE - len,
+			"tot:xmit x%08x ccmpl x%08x cmpl x%08x rcv x%08x\n",
+			tot_xmt, tot_ccmpl, tot_cmpl, tot_rcv);
 	return len;
 }
 
@@ -1660,6 +1894,65 @@ lpfc_debugfs_nvmestat_open(struct inode *inode, struct file *file)
 	return rc;
 }
 
+static ssize_t
+lpfc_debugfs_nvmestat_write(struct file *file, const char __user *buf,
+			    size_t nbytes, loff_t *ppos)
+{
+	struct lpfc_debug *debug = file->private_data;
+	struct lpfc_vport *vport = (struct lpfc_vport *)debug->i_private;
+	struct lpfc_hba   *phba = vport->phba;
+	struct lpfc_nvmet_tgtport *tgtp;
+	char mybuf[64];
+	char *pbuf;
+
+	if (!phba->targetport)
+		return -ENXIO;
+
+	if (nbytes > 64)
+		nbytes = 64;
+
+	/* Protect copy from user */
+	if (!access_ok(VERIFY_READ, buf, nbytes))
+		return -EFAULT;
+
+	memset(mybuf, 0, sizeof(mybuf));
+
+	if (copy_from_user(mybuf, buf, nbytes))
+		return -EFAULT;
+	pbuf = &mybuf[0];
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	if ((strncmp(pbuf, "reset", strlen("reset")) == 0) ||
+	    (strncmp(pbuf, "zero", strlen("zero")) == 0)) {
+		atomic_set(&tgtp->rcv_ls_req_in, 0);
+		atomic_set(&tgtp->rcv_ls_req_out, 0);
+		atomic_set(&tgtp->rcv_ls_req_drop, 0);
+		atomic_set(&tgtp->xmt_ls_abort, 0);
+		atomic_set(&tgtp->xmt_ls_rsp, 0);
+		atomic_set(&tgtp->xmt_ls_drop, 0);
+		atomic_set(&tgtp->xmt_ls_rsp_error, 0);
+		atomic_set(&tgtp->xmt_ls_rsp_cmpl, 0);
+
+		atomic_set(&tgtp->rcv_fcp_cmd_in, 0);
+		atomic_set(&tgtp->rcv_fcp_cmd_out, 0);
+		atomic_set(&tgtp->rcv_fcp_cmd_drop, 0);
+		atomic_set(&tgtp->xmt_fcp_abort, 0);
+		atomic_set(&tgtp->xmt_fcp_drop, 0);
+		atomic_set(&tgtp->xmt_fcp_read_rsp, 0);
+		atomic_set(&tgtp->xmt_fcp_read, 0);
+		atomic_set(&tgtp->xmt_fcp_write, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp_cmpl, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp_error, 0);
+		atomic_set(&tgtp->xmt_fcp_rsp_drop, 0);
+
+		atomic_set(&tgtp->xmt_abort_rsp, 0);
+		atomic_set(&tgtp->xmt_abort_rsp_error, 0);
+		atomic_set(&tgtp->xmt_abort_cmpl, 0);
+	}
+	return nbytes;
+}
+
 static int
 lpfc_debugfs_nvmektime_open(struct inode *inode, struct file *file)
 {
@@ -1956,7 +2249,10 @@ lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf,
 	pbuf = &mybuf[0];
 
 	if ((strncmp(pbuf, "on", sizeof("on") - 1) == 0)) {
-		phba->cpucheck_on |= LPFC_CHECK_NVME_IO;
+		if (phba->nvmet_support)
+			phba->cpucheck_on |= LPFC_CHECK_NVMET_IO;
+		else
+			phba->cpucheck_on |= LPFC_CHECK_NVME_IO;
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "rcv",
 		   sizeof("rcv") - 1) == 0)) {
@@ -2880,7 +3176,7 @@ lpfc_idiag_cqs_for_eq(struct lpfc_hba *phba, char *pbuffer,
 			return 1;
 	}
 
-	if (phba->cfg_nvmet_mrq > eqidx) {
+	if (eqidx < phba->cfg_nvmet_mrq) {
 		/* NVMET CQset */
 		qp = phba->sli4_hba.nvmet_cqset[eqidx];
 		*len = __lpfc_idiag_print_cq(qp, "NVMET CQset", pbuffer, *len);
@@ -4493,6 +4789,7 @@ static const struct file_operations lpfc_debugfs_op_nvmestat = {
 	.open =         lpfc_debugfs_nvmestat_open,
 	.llseek =       lpfc_debugfs_lseek,
 	.read =         lpfc_debugfs_read,
+	.write =	lpfc_debugfs_nvmestat_write,
 	.release =      lpfc_debugfs_release,
 };
 
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index d4efd86bb156..a476d538360f 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -51,6 +51,7 @@
 #include "lpfc_logmsg.h"
 #include "lpfc_crtn.h"
 #include "lpfc_vport.h"
+#include "lpfc_debugfs.h"
 
 static struct lpfc_iocbq *lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *,
 						 struct lpfc_nvmet_rcv_ctx *,
@@ -103,6 +104,9 @@ lpfc_nvmet_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	ctxp = cmdwqe->context2;
 	rsp = &ctxp->ctx.ls_req;
 
+	lpfc_nvmeio_data(phba, "NVMET LS  CMPL: xri x%x stat x%x result x%x\n",
+			 ctxp->oxid, status, result);
+
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
 			"6038 %s: Entrypoint: ctx %p status %x/%x\n", __func__,
 			ctxp, status, result);
@@ -144,6 +148,170 @@ lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
 	lpfc_rq_buf_free(phba, mp);
 }
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+static void
+lpfc_nvmet_ktime(struct lpfc_hba *phba,
+		 struct lpfc_nvmet_rcv_ctx *ctxp)
+{
+	uint64_t seg1, seg2, seg3, seg4, seg5;
+	uint64_t seg6, seg7, seg8, seg9, seg10;
+
+	if (!phba->ktime_on)
+		return;
+
+	if (!ctxp->ts_isr_cmd || !ctxp->ts_cmd_nvme ||
+	    !ctxp->ts_nvme_data || !ctxp->ts_data_wqput ||
+	    !ctxp->ts_isr_data || !ctxp->ts_data_nvme ||
+	    !ctxp->ts_nvme_status || !ctxp->ts_status_wqput ||
+	    !ctxp->ts_isr_status || !ctxp->ts_status_nvme)
+		return;
+
+	if (ctxp->ts_isr_cmd  > ctxp->ts_cmd_nvme)
+		return;
+	if (ctxp->ts_cmd_nvme > ctxp->ts_nvme_data)
+		return;
+	if (ctxp->ts_nvme_data > ctxp->ts_data_wqput)
+		return;
+	if (ctxp->ts_data_wqput > ctxp->ts_isr_data)
+		return;
+	if (ctxp->ts_isr_data > ctxp->ts_data_nvme)
+		return;
+	if (ctxp->ts_data_nvme > ctxp->ts_nvme_status)
+		return;
+	if (ctxp->ts_nvme_status > ctxp->ts_status_wqput)
+		return;
+	if (ctxp->ts_status_wqput > ctxp->ts_isr_status)
+		return;
+	if (ctxp->ts_isr_status > ctxp->ts_status_nvme)
+		return;
+	/*
+	 * Segment 1 - Time from FCP command received by MSI-X ISR
+	 * to FCP command is passed to NVME Layer.
+	 * Segment 2 - Time from FCP command payload handed
+	 * off to NVME Layer to Driver receives a Command op
+	 * from NVME Layer.
+	 * Segment 3 - Time from Driver receives a Command op
+	 * from NVME Layer to Command is put on WQ.
+	 * Segment 4 - Time from Driver WQ put is done
+	 * to MSI-X ISR for Command cmpl.
+	 * Segment 5 - Time from MSI-X ISR for Command cmpl to
+	 * Command cmpl is passed to NVME Layer.
+	 * Segment 6 - Time from Command cmpl is passed to NVME
+	 * Layer to Driver receives a RSP op from NVME Layer.
+	 * Segment 7 - Time from Driver receives a RSP op from
+	 * NVME Layer to WQ put is done on TRSP FCP Status.
+	 * Segment 8 - Time from Driver WQ put is done on TRSP
+	 * FCP Status to MSI-X ISR for TRSP cmpl.
+	 * Segment 9 - Time from MSI-X ISR for TRSP cmpl to
+	 * TRSP cmpl is passed to NVME Layer.
+	 * Segment 10 - Time from FCP command received by
+	 * MSI-X ISR to command is completed on wire.
+	 * (Segments 1 thru 8) for READDATA / WRITEDATA
+	 * (Segments 1 thru 4) for READDATA_RSP
+	 */
+	seg1 = ctxp->ts_cmd_nvme - ctxp->ts_isr_cmd;
+	seg2 = (ctxp->ts_nvme_data - ctxp->ts_isr_cmd) - seg1;
+	seg3 = (ctxp->ts_data_wqput - ctxp->ts_isr_cmd) -
+		seg1 - seg2;
+	seg4 = (ctxp->ts_isr_data - ctxp->ts_isr_cmd) -
+		seg1 - seg2 - seg3;
+	seg5 = (ctxp->ts_data_nvme - ctxp->ts_isr_cmd) -
+		seg1 - seg2 - seg3 - seg4;
+
+	/* For auto rsp commands seg6 thru seg10 will be 0 */
+	if (ctxp->ts_nvme_status > ctxp->ts_data_nvme) {
+		seg6 = (ctxp->ts_nvme_status -
+			ctxp->ts_isr_cmd) -
+			seg1 - seg2 - seg3 - seg4 - seg5;
+		seg7 = (ctxp->ts_status_wqput -
+			ctxp->ts_isr_cmd) -
+			seg1 - seg2 - seg3 -
+			seg4 - seg5 - seg6;
+		seg8 = (ctxp->ts_isr_status -
+			ctxp->ts_isr_cmd) -
+			seg1 - seg2 - seg3 - seg4 -
+			seg5 - seg6 - seg7;
+		seg9 = (ctxp->ts_status_nvme -
+			ctxp->ts_isr_cmd) -
+			seg1 - seg2 - seg3 - seg4 -
+			seg5 - seg6 - seg7 - seg8;
+		seg10 = (ctxp->ts_isr_status -
+			ctxp->ts_isr_cmd);
+	} else {
+		seg6 =  0;
+		seg7 =  0;
+		seg8 =  0;
+		seg9 =  0;
+		seg10 = (ctxp->ts_isr_data - ctxp->ts_isr_cmd);
+	}
+
+	phba->ktime_seg1_total += seg1;
+	if (seg1 < phba->ktime_seg1_min)
+		phba->ktime_seg1_min = seg1;
+	else if (seg1 > phba->ktime_seg1_max)
+		phba->ktime_seg1_max = seg1;
+
+	phba->ktime_seg2_total += seg2;
+	if (seg2 < phba->ktime_seg2_min)
+		phba->ktime_seg2_min = seg2;
+	else if (seg2 > phba->ktime_seg2_max)
+		phba->ktime_seg2_max = seg2;
+
+	phba->ktime_seg3_total += seg3;
+	if (seg3 < phba->ktime_seg3_min)
+		phba->ktime_seg3_min = seg3;
+	else if (seg3 > phba->ktime_seg3_max)
+		phba->ktime_seg3_max = seg3;
+
+	phba->ktime_seg4_total += seg4;
+	if (seg4 < phba->ktime_seg4_min)
+		phba->ktime_seg4_min = seg4;
+	else if (seg4 > phba->ktime_seg4_max)
+		phba->ktime_seg4_max = seg4;
+
+	phba->ktime_seg5_total += seg5;
+	if (seg5 < phba->ktime_seg5_min)
+		phba->ktime_seg5_min = seg5;
+	else if (seg5 > phba->ktime_seg5_max)
+		phba->ktime_seg5_max = seg5;
+
+	phba->ktime_data_samples++;
+	if (!seg6)
+		goto out;
+
+	phba->ktime_seg6_total += seg6;
+	if (seg6 < phba->ktime_seg6_min)
+		phba->ktime_seg6_min = seg6;
+	else if (seg6 > phba->ktime_seg6_max)
+		phba->ktime_seg6_max = seg6;
+
+	phba->ktime_seg7_total += seg7;
+	if (seg7 < phba->ktime_seg7_min)
+		phba->ktime_seg7_min = seg7;
+	else if (seg7 > phba->ktime_seg7_max)
+		phba->ktime_seg7_max = seg7;
+
+	phba->ktime_seg8_total += seg8;
+	if (seg8 < phba->ktime_seg8_min)
+		phba->ktime_seg8_min = seg8;
+	else if (seg8 > phba->ktime_seg8_max)
+		phba->ktime_seg8_max = seg8;
+
+	phba->ktime_seg9_total += seg9;
+	if (seg9 < phba->ktime_seg9_min)
+		phba->ktime_seg9_min = seg9;
+	else if (seg9 > phba->ktime_seg9_max)
+		phba->ktime_seg9_max = seg9;
+out:
+	phba->ktime_seg10_total += seg10;
+	if (seg10 < phba->ktime_seg10_min)
+		phba->ktime_seg10_min = seg10;
+	else if (seg10 > phba->ktime_seg10_max)
+		phba->ktime_seg10_max = seg10;
+	phba->ktime_status_samples++;
+}
+#endif
+
 /**
  * lpfc_nvmet_xmt_fcp_op_cmp - Completion handler for FCP Response
  * @phba: Pointer to HBA context object.
@@ -162,6 +330,9 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	struct nvmefc_tgt_fcp_req *rsp;
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	uint32_t status, result, op, start_clean;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	uint32_t id;
+#endif
 
 	ctxp = cmdwqe->context2;
 	rsp = &ctxp->ctx.fcp_req;
@@ -174,6 +345,9 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	if (!phba->targetport)
 		goto out;
 
+	lpfc_nvmeio_data(phba, "NVMET FCP CMPL: xri x%x op x%x status x%x\n",
+			 ctxp->oxid, op, status);
+
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	if (status) {
 		rsp->fcp_error = NVME_SC_DATA_XFER_ERROR;
@@ -194,7 +368,44 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 		/* Sanity check */
 		ctxp->state = LPFC_NVMET_STE_DONE;
 		ctxp->entry_cnt++;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		if (phba->ktime_on) {
+			if (rsp->op == NVMET_FCOP_READDATA_RSP) {
+				ctxp->ts_isr_data =
+					cmdwqe->isr_timestamp;
+				ctxp->ts_data_nvme =
+					ktime_get_ns();
+				ctxp->ts_nvme_status =
+					ctxp->ts_data_nvme;
+				ctxp->ts_status_wqput =
+					ctxp->ts_data_nvme;
+				ctxp->ts_isr_status =
+					ctxp->ts_data_nvme;
+				ctxp->ts_status_nvme =
+					ctxp->ts_data_nvme;
+			} else {
+				ctxp->ts_isr_status =
+					cmdwqe->isr_timestamp;
+				ctxp->ts_status_nvme =
+					ktime_get_ns();
+			}
+		}
+		if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
+			id = smp_processor_id();
+			if (ctxp->cpu != id)
+				lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+						"6703 CPU Check cmpl: "
+						"cpu %d expect %d\n",
+						id, ctxp->cpu);
+			if (ctxp->cpu < LPFC_CHECK_CPU_CNT)
+				phba->cpucheck_cmpl_io[id]++;
+		}
+#endif
 		rsp->done(rsp);
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		if (phba->ktime_on)
+			lpfc_nvmet_ktime(phba, ctxp);
+#endif
 		/* Let Abort cmpl repost the context */
 		if (!(ctxp->flag & LPFC_NVMET_ABORT_OP))
 			lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
@@ -203,6 +414,22 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 		start_clean = offsetof(struct lpfc_iocbq, wqe);
 		memset(((char *)cmdwqe) + start_clean, 0,
 		       (sizeof(struct lpfc_iocbq) - start_clean));
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		if (phba->ktime_on) {
+			ctxp->ts_isr_data = cmdwqe->isr_timestamp;
+			ctxp->ts_data_nvme = ktime_get_ns();
+		}
+		if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
+			id = smp_processor_id();
+			if (ctxp->cpu != id)
+				lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+						"6704 CPU Check cmdcmpl: "
+						"cpu %d expect %d\n",
+						id, ctxp->cpu);
+			if (ctxp->cpu < LPFC_CHECK_CPU_CNT)
+				phba->cpucheck_ccmpl_io[id]++;
+		}
+#endif
 		rsp->done(rsp);
 	}
 }
@@ -254,6 +481,9 @@ lpfc_nvmet_xmt_ls_rsp(struct nvmet_fc_target_port *tgtport,
 	nvmewqeq->iocb_cmpl = NULL;
 	nvmewqeq->context2 = ctxp;
 
+	lpfc_nvmeio_data(phba, "NVMET LS  RESP: xri x%x wqidx x%x len x%x\n",
+			 ctxp->oxid, nvmewqeq->hba_wqidx, rsp->rsplen);
+
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_ELS_RING, nvmewqeq);
 	if (rc == WQE_SUCCESS) {
 		/*
@@ -288,12 +518,39 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	struct lpfc_hba *phba = ctxp->phba;
 	struct lpfc_iocbq *nvmewqeq;
 	unsigned long iflags;
-	int rc;
+	int rc, id;
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->ktime_on) {
+		if (rsp->op == NVMET_FCOP_RSP)
+			ctxp->ts_nvme_status = ktime_get_ns();
+		else
+			ctxp->ts_nvme_data = ktime_get_ns();
+	}
+	if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
+		id = smp_processor_id();
+		ctxp->cpu = id;
+		if (id < LPFC_CHECK_CPU_CNT)
+			phba->cpucheck_xmt_io[id]++;
+		if (rsp->hwqid != id) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+					"6705 CPU Check OP: "
+					"cpu %d expect %d\n",
+					id, rsp->hwqid);
+			ctxp->cpu = rsp->hwqid;
+		}
+	}
+#endif
 
 	if (rsp->op == NVMET_FCOP_ABORT) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
 				"6103 Abort op: oxri x%x %d cnt %d\n",
 				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+
+		lpfc_nvmeio_data(phba, "NVMET FCP ABRT: "
+				 "xri x%x state x%x cnt x%x\n",
+				 ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+
 		atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
 		ctxp->entry_cnt++;
 		ctxp->flag |= LPFC_NVMET_ABORT_OP;
@@ -330,12 +587,23 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	nvmewqeq->iocb_flag |=  LPFC_IO_NVMET;
 	ctxp->wqeq->hba_wqidx = rsp->hwqid;
 
+	lpfc_nvmeio_data(phba, "NVMET FCP CMND: xri x%x op x%x len x%x\n",
+			 ctxp->oxid, rsp->op, rsp->rsplen);
+
 	/* For now we take hbalock */
 	spin_lock_irqsave(&phba->hbalock, iflags);
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, nvmewqeq);
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	if (rc == WQE_SUCCESS) {
 		ctxp->flag |= LPFC_NVMET_IO_INP;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		if (!phba->ktime_on)
+			return 0;
+		if (rsp->op == NVMET_FCOP_RSP)
+			ctxp->ts_status_wqput = ktime_get_ns();
+		else
+			ctxp->ts_data_wqput = ktime_get_ns();
+#endif
 		return 0;
 	}
 
@@ -503,6 +771,9 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	if (!nvmebuf || !phba->targetport) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6154 LS Drop IO\n");
+		oxid = 0;
+		size = 0;
+		sid = 0;
 		goto dropit;
 	}
 
@@ -520,6 +791,9 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 				"6155 LS Drop IO x%x: Alloc\n",
 				oxid);
 dropit:
+		lpfc_nvmeio_data(phba, "NVMET LS  DROP: "
+				 "xri x%x sz %d from %06x\n",
+				 oxid, size, sid);
 		if (nvmebuf)
 			lpfc_in_buf_free(phba, &nvmebuf->dbuf);
 		return;
@@ -531,6 +805,9 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	ctxp->wqeq = NULL;
 	ctxp->state = LPFC_NVMET_STE_RCV;
 	ctxp->rqb_buffer = (void *)nvmebuf;
+
+	lpfc_nvmeio_data(phba, "NVMET LS   RCV: xri x%x sz %d from %06x\n",
+			 oxid, size, sid);
 	/*
 	 * The calling sequence should be:
 	 * nvmet_fc_rcv_ls_req -> lpfc_nvmet_xmt_ls_rsp/cmp ->_req->done
@@ -545,10 +822,15 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			"%08x %08x %08x\n", __func__, ctxp, size, rc,
 			*payload, *(payload+1), *(payload+2),
 			*(payload+3), *(payload+4), *(payload+5));
+
 	if (rc == 0) {
 		atomic_inc(&tgtp->rcv_ls_req_out);
 		return;
 	}
+
+	lpfc_nvmeio_data(phba, "NVMET LS  DROP: xri x%x sz %d from %06x\n",
+			 oxid, size, sid);
+
 	atomic_inc(&tgtp->rcv_ls_req_drop);
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 			"6156 LS Drop IO x%x: nvmet_fc_rcv_ls_req %d\n",
@@ -586,11 +868,16 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	struct fc_frame_header *fc_hdr;
 	uint32_t *payload;
 	uint32_t size, oxid, sid, rc;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	uint32_t id;
+#endif
 
-	oxid = 0;
 	if (!nvmebuf || !phba->targetport) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6157 FCP Drop IO\n");
+		oxid = 0;
+		size = 0;
+		sid = 0;
 		goto dropit;
 	}
 
@@ -625,6 +912,30 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	ctxp->entry_cnt = 1;
 	ctxp->flag = 0;
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->ktime_on) {
+		ctxp->ts_isr_cmd = isr_timestamp;
+		ctxp->ts_cmd_nvme = ktime_get_ns();
+		ctxp->ts_nvme_data = 0;
+		ctxp->ts_data_wqput = 0;
+		ctxp->ts_isr_data = 0;
+		ctxp->ts_data_nvme = 0;
+		ctxp->ts_nvme_status = 0;
+		ctxp->ts_status_wqput = 0;
+		ctxp->ts_isr_status = 0;
+		ctxp->ts_status_nvme = 0;
+	}
+
+	if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) {
+		id = smp_processor_id();
+		if (id < LPFC_CHECK_CPU_CNT)
+			phba->cpucheck_rcv_io[id]++;
+	}
+#endif
+
+	lpfc_nvmeio_data(phba, "NVMET FCP  RCV: xri x%x sz %d from %06x\n",
+			 oxid, size, sid);
+
 	atomic_inc(&tgtp->rcv_fcp_cmd_in);
 	/*
 	 * The calling sequence should be:
@@ -645,6 +956,8 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 			"6159 FCP Drop IO x%x: nvmet_fc_rcv_fcp_req x%x\n",
 			ctxp->oxid, rc);
 dropit:
+	lpfc_nvmeio_data(phba, "NVMET FCP DROP: xri x%x sz %d from %06x\n",
+			 oxid, size, sid);
 	if (oxid) {
 		lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, sid, oxid);
 		return;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index f7b6a3f374a4..4aa18d31a5f7 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -98,4 +98,17 @@ struct lpfc_nvmet_rcv_ctx {
 #define LPFC_NVMET_IO_INP		1
 #define LPFC_NVMET_ABORT_OP		2
 	struct rqb_dmabuf *rqb_buffer;
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	uint64_t ts_isr_cmd;
+	uint64_t ts_cmd_nvme;
+	uint64_t ts_nvme_data;
+	uint64_t ts_data_wqput;
+	uint64_t ts_isr_data;
+	uint64_t ts_data_nvme;
+	uint64_t ts_nvme_status;
+	uint64_t ts_status_wqput;
+	uint64_t ts_isr_status;
+	uint64_t ts_status_nvme;
+#endif
 };
-- 
GitLab


From d080abe0a8693c58a4b35b74bab3526d8b554ca3 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:39 -0800
Subject: [PATCH 154/898] scsi: lpfc: Update copyrights

Update copyrights to 2017 for all files touched in this patch set

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/Makefile         | 4 +++-
 drivers/scsi/lpfc/lpfc.h           | 4 +++-
 drivers/scsi/lpfc/lpfc_attr.c      | 4 +++-
 drivers/scsi/lpfc/lpfc_attr.h      | 4 +++-
 drivers/scsi/lpfc/lpfc_bsg.c       | 4 +++-
 drivers/scsi/lpfc/lpfc_bsg.h       | 6 ++++--
 drivers/scsi/lpfc/lpfc_compat.h    | 4 +++-
 drivers/scsi/lpfc/lpfc_crtn.h      | 4 +++-
 drivers/scsi/lpfc/lpfc_ct.c        | 4 +++-
 drivers/scsi/lpfc/lpfc_debugfs.c   | 4 +++-
 drivers/scsi/lpfc/lpfc_debugfs.h   | 4 +++-
 drivers/scsi/lpfc/lpfc_disc.h      | 4 +++-
 drivers/scsi/lpfc/lpfc_els.c       | 4 +++-
 drivers/scsi/lpfc/lpfc_hbadisc.c   | 4 +++-
 drivers/scsi/lpfc/lpfc_hw.h        | 4 +++-
 drivers/scsi/lpfc/lpfc_hw4.h       | 6 ++++--
 drivers/scsi/lpfc/lpfc_ids.h       | 4 +++-
 drivers/scsi/lpfc/lpfc_init.c      | 6 ++++--
 drivers/scsi/lpfc/lpfc_logmsg.h    | 4 +++-
 drivers/scsi/lpfc/lpfc_mbox.c      | 4 +++-
 drivers/scsi/lpfc/lpfc_mem.c       | 4 +++-
 drivers/scsi/lpfc/lpfc_nl.h        | 4 +++-
 drivers/scsi/lpfc/lpfc_nportdisc.c | 4 +++-
 drivers/scsi/lpfc/lpfc_nvme.c      | 4 +++-
 drivers/scsi/lpfc/lpfc_nvme.h      | 4 +++-
 drivers/scsi/lpfc/lpfc_nvmet.c     | 6 ++++--
 drivers/scsi/lpfc/lpfc_nvmet.h     | 4 +++-
 drivers/scsi/lpfc/lpfc_scsi.c      | 4 +++-
 drivers/scsi/lpfc/lpfc_scsi.h      | 4 +++-
 drivers/scsi/lpfc/lpfc_sli.c       | 4 +++-
 drivers/scsi/lpfc/lpfc_sli.h       | 4 +++-
 drivers/scsi/lpfc/lpfc_sli4.h      | 4 +++-
 drivers/scsi/lpfc/lpfc_version.h   | 8 ++++++--
 drivers/scsi/lpfc/lpfc_vport.c     | 4 +++-
 drivers/scsi/lpfc/lpfc_vport.h     | 4 +++-
 35 files changed, 112 insertions(+), 40 deletions(-)

diff --git a/drivers/scsi/lpfc/Makefile b/drivers/scsi/lpfc/Makefile
index 30a6a35abafd..cb6aa802c48e 100644
--- a/drivers/scsi/lpfc/Makefile
+++ b/drivers/scsi/lpfc/Makefile
@@ -1,9 +1,11 @@
 #/*******************************************************************
 # * This file is part of the Emulex Linux Device Driver for         *
 # * Fibre Channel Host Bus Adapters.                                *
+# * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+# * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
 # * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
 # * EMULEX and SLI are trademarks of Emulex.                        *
-# * www.emulex.com                                                  *
+# * www.broadcom.com                                                *
 # *                                                                 *
 # * This program is free software; you can redistribute it and/or   *
 # * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 8a4090c6771c..0bba2e30b4f0 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 700a68f303f3..4114cf4308d0 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_attr.h b/drivers/scsi/lpfc/lpfc_attr.h
index b2bd28e965fa..d56dafcdd563 100644
--- a/drivers/scsi/lpfc/lpfc_attr.h
+++ b/drivers/scsi/lpfc/lpfc_attr.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 55a2270cadfc..18157d2840a3 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2009-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index f2247aa4fa17..e7d95a4e8042 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2010-2015 Emulex.  All rights reserved.                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2010-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_compat.h b/drivers/scsi/lpfc/lpfc_compat.h
index c88e556ea62e..6b32b0ae7506 100644
--- a/drivers/scsi/lpfc/lpfc_compat.h
+++ b/drivers/scsi/lpfc/lpfc_compat.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index f56015b78525..843dd73004da 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 53bdfe421251..c22bb3f887e1 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index f92796d8dc42..599fde4ea8b1 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2007-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index 5312e0f9deb6..c05f56c3023f 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2007-2011 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index e305e97e05a9..f4ff99d95db3 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 1c0ac509e6db..2d26440e6f2f 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 542797bd3134..194a14d5f8a9 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index c2221377e246..15ca21484150 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 0fddb2317875..cfdb068a3bfc 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009-2016 Emulex.  All rights reserved.                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2009-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_ids.h b/drivers/scsi/lpfc/lpfc_ids.h
index 5733feafe25f..0ba3733eb36d 100644
--- a/drivers/scsi/lpfc/lpfc_ids.h
+++ b/drivers/scsi/lpfc/lpfc_ids.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 5eafd0db758d..0ee429d773f3 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
@@ -12117,5 +12119,5 @@ module_init(lpfc_init);
 module_exit(lpfc_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION(LPFC_MODULE_DESC);
-MODULE_AUTHOR("Emulex Corporation - tech.support@emulex.com");
+MODULE_AUTHOR("Broadcom");
 MODULE_VERSION("0:" LPFC_DRIVER_VERSION);
diff --git a/drivers/scsi/lpfc/lpfc_logmsg.h b/drivers/scsi/lpfc/lpfc_logmsg.h
index 3faf7a07bfd4..3b654ad08d1f 100644
--- a/drivers/scsi/lpfc/lpfc_logmsg.h
+++ b/drivers/scsi/lpfc/lpfc_logmsg.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2009 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index 8f4bfdfd9910..a928f5187fa4 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index 2437ec5f4863..c61d8d692ede 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_nl.h b/drivers/scsi/lpfc/lpfc_nl.h
index f2b1bbcb196f..b93e78f671fb 100644
--- a/drivers/scsi/lpfc/lpfc_nl.h
+++ b/drivers/scsi/lpfc/lpfc_nl.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2010 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 0716818f269f..061626bdf701 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -1,9 +1,11 @@
  /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 56b4b94a372e..625b6589a34d 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index 85961c1ddecf..b2fae5e813f8 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index a476d538360f..c421e1738ee9 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
- * Fibre Channsel Host Bus Adapters.                                *
+ * Fibre Channsel Host Bus Adapters.                               *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index 4aa18d31a5f7..ca96f05c1604 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 6ba2b3412337..9d6384af9fce 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index def0c0a5b17e..5da7e15400cb 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 84565f810392..d8d8693040ac 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index f6cea02adc7c..9085306ddd78 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 3bfdff1a4c53..91153c9f6d18 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2009-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 0ee0623a354c..0d9353514071 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
  * modify it under the terms of version 2 of the GNU General       *
@@ -30,4 +32,6 @@
 
 #define LPFC_MODULE_DESC "Emulex LightPulse Fibre Channel SCSI driver " \
 		LPFC_DRIVER_VERSION
-#define LPFC_COPYRIGHT "Copyright(c) 2004-2016 Emulex.  All rights reserved."
+#define LPFC_COPYRIGHT "Copyright (C) 2017 Broadcom. All Rights Reserved. " \
+		"The term \"Broadcom\" refers to Broadcom Limited " \
+		"and/or its subsidiaries."
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index b0d94f2e5b44..c0eeea0694cb 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
diff --git a/drivers/scsi/lpfc/lpfc_vport.h b/drivers/scsi/lpfc/lpfc_vport.h
index 6b2c94eb8134..62295971f66c 100644
--- a/drivers/scsi/lpfc/lpfc_vport.h
+++ b/drivers/scsi/lpfc/lpfc_vport.h
@@ -1,9 +1,11 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
+ * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
+ * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
  * Copyright (C) 2004-2006 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
+ * www.broadcom.com                                                *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
  *                                                                 *
  * This program is free software; you can redistribute it and/or   *
-- 
GitLab


From 693dcc316525d15fcf5a0a8a8e1663985ebdb02c Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Sun, 12 Feb 2017 13:52:40 -0800
Subject: [PATCH 155/898] scsi: lpfc: Update lpfc version to 11.2.0.7

Update lpfc version to 11.2.0.7

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_version.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 0d9353514071..86c6c9b26b82 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.4"
+#define LPFC_DRIVER_VERSION "11.2.0.7"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
-- 
GitLab


From 75d943f3e4222fdd4f907b71bd9d1730412e7ce9 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Wed, 22 Feb 2017 08:20:47 -0800
Subject: [PATCH 156/898] scsi: lpfc: add missing Kconfig NVME dependencies

Add missing Kconfig NVME dependencies.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index d4023bf1e739..255843446e99 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1240,6 +1240,7 @@ config SCSI_LPFC
 	tristate "Emulex LightPulse Fibre Channel Support"
 	depends on PCI && SCSI
 	depends on SCSI_FC_ATTRS
+	depends on NVME_FC && NVME_TARGET_FC
 	select CRC_T10DIF
 	help
           This lpfc driver supports the Emulex LightPulse
-- 
GitLab


From f54f2cb540b53d55a81d620e816810d59be5cb1b Mon Sep 17 00:00:00 2001
From: Michael Hernandez <michael.hernandez@cavium.com>
Date: Wed, 15 Feb 2017 15:37:19 -0800
Subject: [PATCH 157/898] scsi: qla2xxx: Cleaned up queue configuration code.

This patch cleaned up queue configuration code, such that once
initialized, we should not touch msix_count value.  This will prevent
incorrect numbers of MSI-X vectors requested while performing target
mode configuration.

[mkp: fixed Fixes: hash]

Cc: <stable@vger.kernel.org>
Fixes: d74595278f4a ("scsi: qla2xxx: Add multiple queue pair functionality.")
Signed-off-by: Michael Hernandez <michael.hernandez@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_os.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index d01c90c7dd04..8174cee8eb53 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1815,6 +1815,7 @@ qla2x00_iospace_config(struct qla_hw_data *ha)
 
 	/* Determine queue resources */
 	ha->max_req_queues = ha->max_rsp_queues = 1;
+	ha->msix_count = QLA_BASE_VECTORS;
 	if (!ql2xmqsupport || (!IS_QLA25XX(ha) && !IS_QLA81XX(ha)))
 		goto mqiobase_exit;
 
@@ -1842,9 +1843,8 @@ qla2x00_iospace_config(struct qla_hw_data *ha)
 		    "BAR 3 not enabled.\n");
 
 mqiobase_exit:
-	ha->msix_count = ha->max_rsp_queues + 1;
 	ql_dbg_pci(ql_dbg_init, ha->pdev, 0x001c,
-	    "MSIX Count:%d.\n", ha->msix_count);
+	    "MSIX Count: %d.\n", ha->msix_count);
 	return (0);
 
 iospace_error_exit:
@@ -1892,6 +1892,7 @@ qla83xx_iospace_config(struct qla_hw_data *ha)
 	/* 83XX 26XX always use MQ type access for queues
 	 * - mbar 2, a.k.a region 4 */
 	ha->max_req_queues = ha->max_rsp_queues = 1;
+	ha->msix_count = QLA_BASE_VECTORS;
 	ha->mqiobase = ioremap(pci_resource_start(ha->pdev, 4),
 			pci_resource_len(ha->pdev, 4));
 
@@ -1934,14 +1935,8 @@ qla83xx_iospace_config(struct qla_hw_data *ha)
 		    "BAR 1 not enabled.\n");
 
 mqiobase_exit:
-	ha->msix_count = ha->max_rsp_queues + 1;
-	if (QLA_TGT_MODE_ENABLED())
-		ha->msix_count++;
-
-	qlt_83xx_iospace_config(ha);
-
 	ql_dbg_pci(ql_dbg_init, ha->pdev, 0x011f,
-	    "MSIX Count:%d.\n", ha->msix_count);
+	    "MSIX Count: %d.\n", ha->msix_count);
 	return 0;
 
 iospace_error_exit:
-- 
GitLab


From d0d2c68b759bbf678e078fd0c71b5fde65a9392c Mon Sep 17 00:00:00 2001
From: Michael Hernandez <michael.hernandez@cavium.com>
Date: Wed, 15 Feb 2017 15:37:20 -0800
Subject: [PATCH 158/898] scsi: qla2xxx: Fix response queue count for Target
 mode.

Target mode initialization was not calculating response queue values
correctly resulting into one less MSI-X vector.

[mkp: fixed Fixes: hash]

Cc: <stable@vger.kernel.org>
Fixes: 093df73771ba ("scsi: qla2xxx: Fix Target mode handling with Multiqueue changes.")
Signed-off-by: Michael Hernandez <michael.hernandez@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_os.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 8174cee8eb53..71b6b20ae82b 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1916,12 +1916,13 @@ qla83xx_iospace_config(struct qla_hw_data *ha)
 		if (ql2xmqsupport) {
 			/* MB interrupt uses 1 vector */
 			ha->max_req_queues = ha->msix_count - 1;
-			ha->max_rsp_queues = ha->max_req_queues;
 
 			/* ATIOQ needs 1 vector. That's 1 less QPair */
 			if (QLA_TGT_MODE_ENABLED())
 				ha->max_req_queues--;
 
+			ha->max_rsp_queues = ha->max_req_queues;
+
 			/* Queue pairs is the max value minus
 			 * the base queue pair */
 			ha->max_qpairs = ha->max_req_queues - 1;
-- 
GitLab


From 67f2db8792f96d8f7521461635d25f9c80245d80 Mon Sep 17 00:00:00 2001
From: Michael Hernandez <michael.hernandez@cavium.com>
Date: Wed, 15 Feb 2017 15:37:21 -0800
Subject: [PATCH 159/898] scsi: qla2xxx: Fix Regression introduced by
 pci_alloc_irq_vectors_affinity call.

For target mode, we need to increase minimum vectors value by one to
account for ATIO queue.

Following stack trace will be seen

Call Trace:
qla24xx_config_rings+0x15a/0x230 [qla2xxx]
qla2x00_init_rings+0x1a1/0x3a0 [qla2xxx]
qla2x00_restart_isp+0x5c/0x120 [qla2xxx]
qla2x00_abort_isp+0x138/0x430 [qla2xxx]
? __schedule+0x260/0x580
qla2x00_do_dpc+0x3bc/0x920 [qla2xxx]
? qla2x00_relogin+0x290/0x290 [qla2xxx]
? schedule+0x3a/0xa0
? qla2x00_relogin+0x290/0x290 [qla2xxx]
kthread+0x103/0x140
? __kthread_init_worker+0x40/0x40
ret_from_fork+0x29/0x40

RIP: qlt_24xx_config_rings+0x6c/0x90

[mkp: fixed Fixes: hash]

Cc: <stable@vger.kernel.org>
Fixes: 17e5fc58588b ("scsi: qla2xxx: fix MSI-X vector affinity")
Signed-off-by: Michael Hernandez <michael.hernandez@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_isr.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index edc2264db45b..87fc921ce391 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3015,14 +3015,17 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	int i, ret;
 	struct qla_msix_entry *qentry;
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
+	int min_vecs = QLA_BASE_VECTORS;
 	struct irq_affinity desc = {
 		.pre_vectors = QLA_BASE_VECTORS,
 	};
 
-	if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha))
+	if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
 		desc.pre_vectors++;
+		min_vecs++;
+	}
 
-	ret = pci_alloc_irq_vectors_affinity(ha->pdev, QLA_BASE_VECTORS,
+	ret = pci_alloc_irq_vectors_affinity(ha->pdev, min_vecs,
 			ha->msix_count, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
 			&desc);
 
-- 
GitLab


From 61d8658b4a435eac729966cc94cdda077a8df5cd Mon Sep 17 00:00:00 2001
From: "Dupuis, Chad" <chad.dupuis@cavium.com>
Date: Wed, 15 Feb 2017 06:28:23 -0800
Subject: [PATCH 160/898] scsi: qedf: Add QLogic FastLinQ offload FCoE driver
 framework.

The QLogic FastLinQ Driver for FCoE (qedf) is the FCoE specific module
for 41000 Series Converged Network Adapters by QLogic. This patch
consists of following changes:

- MAINTAINERS Makefile and Kconfig changes for qedf
- PCI driver registration
- libfc/fcoe host level initialization
- SCSI host template initialization and callbacks
- Debugfs and log level infrastructure
- Link handling
- Firmware interface structures
- QED core module initialization
- Light L2 interface callbacks
- I/O request initialization
- Firmware I/O completion handling
- Firmware ELS request/response handling
- FIP request/response handled by the driver itself

Signed-off-by: Nilesh Javali <nilesh.javali@cavium.com>
Signed-off-by: Manish Rangankar <manish.rangankar@cavium.com>
Signed-off-by: Saurav Kashyap <saurav.kashyap@cavium.com>
Signed-off-by: Arun Easi <arun.easi@cavium.com>
Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS                      |    6 +
 drivers/scsi/Kconfig             |    1 +
 drivers/scsi/Makefile            |    1 +
 drivers/scsi/qedf/Kconfig        |   11 +
 drivers/scsi/qedf/Makefile       |    5 +
 drivers/scsi/qedf/qedf.h         |  545 +++++
 drivers/scsi/qedf/qedf_attr.c    |  165 ++
 drivers/scsi/qedf/qedf_dbg.c     |  195 ++
 drivers/scsi/qedf/qedf_dbg.h     |  154 ++
 drivers/scsi/qedf/qedf_debugfs.c |  460 ++++
 drivers/scsi/qedf/qedf_els.c     |  949 +++++++++
 drivers/scsi/qedf/qedf_fip.c     |  269 +++
 drivers/scsi/qedf/qedf_hsi.h     |  422 ++++
 drivers/scsi/qedf/qedf_io.c      | 2282 ++++++++++++++++++++
 drivers/scsi/qedf/qedf_main.c    | 3336 ++++++++++++++++++++++++++++++
 drivers/scsi/qedf/qedf_version.h |   15 +
 16 files changed, 8816 insertions(+)
 create mode 100644 drivers/scsi/qedf/Kconfig
 create mode 100644 drivers/scsi/qedf/Makefile
 create mode 100644 drivers/scsi/qedf/qedf.h
 create mode 100644 drivers/scsi/qedf/qedf_attr.c
 create mode 100644 drivers/scsi/qedf/qedf_dbg.c
 create mode 100644 drivers/scsi/qedf/qedf_dbg.h
 create mode 100644 drivers/scsi/qedf/qedf_debugfs.c
 create mode 100644 drivers/scsi/qedf/qedf_els.c
 create mode 100644 drivers/scsi/qedf/qedf_fip.c
 create mode 100644 drivers/scsi/qedf/qedf_hsi.h
 create mode 100644 drivers/scsi/qedf/qedf_io.c
 create mode 100644 drivers/scsi/qedf/qedf_main.c
 create mode 100644 drivers/scsi/qedf/qedf_version.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 545633d6663d..8a0e01477043 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10242,6 +10242,12 @@ L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/qedi/
 
+QLOGIC QL41xxx FCOE DRIVER
+M:	QLogic-Storage-Upstream@cavium.com
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/qedf/
+
 QNX4 FILESYSTEM
 M:	Anders Larsen <al@alarsen.net>
 W:	http://www.alarsen.net/linux/qnx4fs/
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 255843446e99..8aa9bd34123e 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1235,6 +1235,7 @@ config SCSI_QLOGICPTI
 source "drivers/scsi/qla2xxx/Kconfig"
 source "drivers/scsi/qla4xxx/Kconfig"
 source "drivers/scsi/qedi/Kconfig"
+source "drivers/scsi/qedf/Kconfig"
 
 config SCSI_LPFC
 	tristate "Emulex LightPulse Fibre Channel Support"
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 736b77414a4b..fc2855565a51 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_FCOE)		+= fcoe/
 obj-$(CONFIG_FCOE_FNIC)		+= fnic/
 obj-$(CONFIG_SCSI_SNIC)		+= snic/
 obj-$(CONFIG_SCSI_BNX2X_FCOE)	+= libfc/ fcoe/ bnx2fc/
+obj-$(CONFIG_QEDF)		+= qedf/
 obj-$(CONFIG_ISCSI_TCP) 	+= libiscsi.o	libiscsi_tcp.o iscsi_tcp.o
 obj-$(CONFIG_INFINIBAND_ISER) 	+= libiscsi.o
 obj-$(CONFIG_ISCSI_BOOT_SYSFS)	+= iscsi_boot_sysfs.o
diff --git a/drivers/scsi/qedf/Kconfig b/drivers/scsi/qedf/Kconfig
new file mode 100644
index 000000000000..943f5ee45807
--- /dev/null
+++ b/drivers/scsi/qedf/Kconfig
@@ -0,0 +1,11 @@
+config QEDF
+	tristate "QLogic QEDF 25/40/100Gb FCoE Initiator Driver Support"
+	depends on PCI && SCSI
+	depends on QED
+        depends on LIBFC
+        depends on LIBFCOE
+	select QED_LL2
+	select QED_FCOE
+	---help---
+	This driver supports FCoE offload for the QLogic FastLinQ
+	41000 Series Converged Network Adapters.
diff --git a/drivers/scsi/qedf/Makefile b/drivers/scsi/qedf/Makefile
new file mode 100644
index 000000000000..64e9f507ce32
--- /dev/null
+++ b/drivers/scsi/qedf/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_QEDF) := qedf.o
+qedf-y = qedf_dbg.o qedf_main.o qedf_io.o qedf_fip.o \
+	 qedf_attr.o qedf_els.o
+
+qedf-$(CONFIG_DEBUG_FS) += qedf_debugfs.o
diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h
new file mode 100644
index 000000000000..96346a1b1515
--- /dev/null
+++ b/drivers/scsi/qedf/qedf.h
@@ -0,0 +1,545 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#ifndef _QEDFC_H_
+#define _QEDFC_H_
+
+#include <scsi/libfcoe.h>
+#include <scsi/libfc.h>
+#include <scsi/fc/fc_fip.h>
+#include <scsi/fc/fc_fc2.h>
+#include <scsi/scsi_tcq.h>
+#include <scsi/fc_encode.h>
+#include <linux/version.h>
+
+
+/* qedf_hsi.h needs to before included any qed includes */
+#include "qedf_hsi.h"
+
+#include <linux/qed/qed_if.h>
+#include <linux/qed/qed_fcoe_if.h>
+#include <linux/qed/qed_ll2_if.h>
+#include "qedf_version.h"
+#include "qedf_dbg.h"
+
+/* Helpers to extract upper and lower 32-bits of pointer */
+#define U64_HI(val) ((u32)(((u64)(val)) >> 32))
+#define U64_LO(val) ((u32)(((u64)(val)) & 0xffffffff))
+
+#define QEDF_DESCR "QLogic FCoE Offload Driver"
+#define QEDF_MODULE_NAME "qedf"
+
+#define QEDF_MIN_XID		0
+#define QEDF_MAX_SCSI_XID	(NUM_TASKS_PER_CONNECTION - 1)
+#define QEDF_MAX_ELS_XID	4095
+#define QEDF_FLOGI_RETRY_CNT	3
+#define QEDF_RPORT_RETRY_CNT	255
+#define QEDF_MAX_SESSIONS	1024
+#define QEDF_MAX_PAYLOAD	2048
+#define QEDF_MAX_BDS_PER_CMD	256
+#define QEDF_MAX_BD_LEN		0xffff
+#define QEDF_BD_SPLIT_SZ	0x1000
+#define QEDF_PAGE_SIZE		4096
+#define QED_HW_DMA_BOUNDARY     0xfff
+#define QEDF_MAX_SGLEN_FOR_CACHESGL		((1U << 16) - 1)
+#define QEDF_MFS		(QEDF_MAX_PAYLOAD + \
+	sizeof(struct fc_frame_header))
+#define QEDF_MAX_NPIV		64
+#define QEDF_TM_TIMEOUT		10
+#define QEDF_ABORT_TIMEOUT	10
+#define QEDF_CLEANUP_TIMEOUT	10
+#define QEDF_MAX_CDB_LEN	16
+
+#define UPSTREAM_REMOVE		1
+#define UPSTREAM_KEEP		1
+
+struct qedf_mp_req {
+	uint8_t tm_flags;
+
+	uint32_t req_len;
+	void *req_buf;
+	dma_addr_t req_buf_dma;
+	struct fcoe_sge *mp_req_bd;
+	dma_addr_t mp_req_bd_dma;
+	struct fc_frame_header req_fc_hdr;
+
+	uint32_t resp_len;
+	void *resp_buf;
+	dma_addr_t resp_buf_dma;
+	struct fcoe_sge *mp_resp_bd;
+	dma_addr_t mp_resp_bd_dma;
+	struct fc_frame_header resp_fc_hdr;
+};
+
+struct qedf_els_cb_arg {
+	struct qedf_ioreq *aborted_io_req;
+	struct qedf_ioreq *io_req;
+	u8 op; /* Used to keep track of ELS op */
+	uint16_t l2_oxid;
+	u32 offset; /* Used for sequence cleanup */
+	u8 r_ctl; /* Used for sequence cleanup */
+};
+
+enum qedf_ioreq_event {
+	QEDF_IOREQ_EV_ABORT_SUCCESS,
+	QEDF_IOREQ_EV_ABORT_FAILED,
+	QEDF_IOREQ_EV_SEND_RRQ,
+	QEDF_IOREQ_EV_ELS_TMO,
+	QEDF_IOREQ_EV_ELS_ERR_DETECT,
+	QEDF_IOREQ_EV_ELS_FLUSH,
+	QEDF_IOREQ_EV_CLEANUP_SUCCESS,
+	QEDF_IOREQ_EV_CLEANUP_FAILED,
+};
+
+#define FC_GOOD		0
+#define FCOE_FCP_RSP_FLAGS_FCP_RESID_OVER	(0x1<<2)
+#define FCOE_FCP_RSP_FLAGS_FCP_RESID_UNDER	(0x1<<3)
+#define CMD_SCSI_STATUS(Cmnd)			((Cmnd)->SCp.Status)
+#define FCOE_FCP_RSP_FLAGS_FCP_RSP_LEN_VALID	(0x1<<0)
+#define FCOE_FCP_RSP_FLAGS_FCP_SNS_LEN_VALID	(0x1<<1)
+struct qedf_ioreq {
+	struct list_head link;
+	uint16_t xid;
+	struct scsi_cmnd *sc_cmd;
+	bool use_slowpath; /* Use slow SGL for this I/O */
+#define QEDF_SCSI_CMD		1
+#define QEDF_TASK_MGMT_CMD	2
+#define QEDF_ABTS		3
+#define QEDF_ELS		4
+#define QEDF_CLEANUP		5
+#define QEDF_SEQ_CLEANUP	6
+	u8 cmd_type;
+#define QEDF_CMD_OUTSTANDING		0x0
+#define QEDF_CMD_IN_ABORT		0x1
+#define QEDF_CMD_IN_CLEANUP		0x2
+#define QEDF_CMD_SRR_SENT		0x3
+	u8 io_req_flags;
+	struct qedf_rport *fcport;
+	unsigned long flags;
+	enum qedf_ioreq_event event;
+	size_t data_xfer_len;
+	struct kref refcount;
+	struct qedf_cmd_mgr *cmd_mgr;
+	struct io_bdt *bd_tbl;
+	struct delayed_work timeout_work;
+	struct completion tm_done;
+	struct completion abts_done;
+	struct fcoe_task_context *task;
+	int idx;
+/*
+ * Need to allocate enough room for both sense data and FCP response data
+ * which has a max length of 8 bytes according to spec.
+ */
+#define QEDF_SCSI_SENSE_BUFFERSIZE	(SCSI_SENSE_BUFFERSIZE + 8)
+	uint8_t *sense_buffer;
+	dma_addr_t sense_buffer_dma;
+	u32 fcp_resid;
+	u32 fcp_rsp_len;
+	u32 fcp_sns_len;
+	u8 cdb_status;
+	u8 fcp_status;
+	u8 fcp_rsp_code;
+	u8 scsi_comp_flags;
+#define QEDF_MAX_REUSE		0xfff
+	u16 reuse_count;
+	struct qedf_mp_req mp_req;
+	void (*cb_func)(struct qedf_els_cb_arg *cb_arg);
+	struct qedf_els_cb_arg *cb_arg;
+	int fp_idx;
+	unsigned int cpu;
+	unsigned int int_cpu;
+#define QEDF_IOREQ_SLOW_SGE		0
+#define QEDF_IOREQ_SINGLE_SGE		1
+#define QEDF_IOREQ_FAST_SGE		2
+	u8 sge_type;
+	struct delayed_work rrq_work;
+
+	/* Used for sequence level recovery; i.e. REC/SRR */
+	uint32_t rx_buf_off;
+	uint32_t tx_buf_off;
+	uint32_t rx_id;
+	uint32_t task_retry_identifier;
+
+	/*
+	 * Used to tell if we need to return a SCSI command
+	 * during some form of error processing.
+	 */
+	bool return_scsi_cmd_on_abts;
+};
+
+extern struct workqueue_struct *qedf_io_wq;
+
+struct qedf_rport {
+	spinlock_t rport_lock;
+#define QEDF_RPORT_SESSION_READY 1
+#define QEDF_RPORT_UPLOADING_CONNECTION	2
+	unsigned long flags;
+	unsigned long retry_delay_timestamp;
+	struct fc_rport *rport;
+	struct fc_rport_priv *rdata;
+	struct qedf_ctx *qedf;
+	u32 handle; /* Handle from qed */
+	u32 fw_cid; /* fw_cid from qed */
+	void __iomem *p_doorbell;
+	/* Send queue management */
+	atomic_t free_sqes;
+	atomic_t num_active_ios;
+	struct fcoe_wqe *sq;
+	dma_addr_t sq_dma;
+	u16 sq_prod_idx;
+	u16 fw_sq_prod_idx;
+	u16 sq_con_idx;
+	u32 sq_mem_size;
+	void *sq_pbl;
+	dma_addr_t sq_pbl_dma;
+	u32 sq_pbl_size;
+	u32 sid;
+#define	QEDF_RPORT_TYPE_DISK		1
+#define	QEDF_RPORT_TYPE_TAPE		2
+	uint dev_type; /* Disk or tape */
+	struct list_head peers;
+};
+
+/* Used to contain LL2 skb's in ll2_skb_list */
+struct qedf_skb_work {
+	struct work_struct work;
+	struct sk_buff *skb;
+	struct qedf_ctx *qedf;
+};
+
+struct qedf_fastpath {
+#define	QEDF_SB_ID_NULL		0xffff
+	u16		sb_id;
+	struct qed_sb_info	*sb_info;
+	struct qedf_ctx *qedf;
+	/* Keep track of number of completions on this fastpath */
+	unsigned long completions;
+	uint32_t cq_num_entries;
+};
+
+/* Used to pass fastpath information needed to process CQEs */
+struct qedf_io_work {
+	struct work_struct work;
+	struct fcoe_cqe cqe;
+	struct qedf_ctx *qedf;
+	struct fc_frame *fp;
+};
+
+struct qedf_glbl_q_params {
+	u64	hw_p_cq;	/* Completion queue PBL */
+	u64	hw_p_rq;	/* Request queue PBL */
+	u64	hw_p_cmdq;	/* Command queue PBL */
+};
+
+struct global_queue {
+	struct fcoe_cqe *cq;
+	dma_addr_t cq_dma;
+	u32 cq_mem_size;
+	u32 cq_cons_idx; /* Completion queue consumer index */
+	u32 cq_prod_idx;
+
+	void *cq_pbl;
+	dma_addr_t cq_pbl_dma;
+	u32 cq_pbl_size;
+};
+
+/* I/O tracing entry */
+#define QEDF_IO_TRACE_SIZE		2048
+struct qedf_io_log {
+#define QEDF_IO_TRACE_REQ		0
+#define QEDF_IO_TRACE_RSP		1
+	uint8_t direction;
+	uint16_t task_id;
+	uint32_t port_id; /* Remote port fabric ID */
+	int lun;
+	char op; /* SCSI CDB */
+	uint8_t lba[4];
+	unsigned int bufflen; /* SCSI buffer length */
+	unsigned int sg_count; /* Number of SG elements */
+	int result; /* Result passed back to mid-layer */
+	unsigned long jiffies; /* Time stamp when I/O logged */
+	int refcount; /* Reference count for task id */
+	unsigned int req_cpu; /* CPU that the task is queued on */
+	unsigned int int_cpu; /* Interrupt CPU that the task is received on */
+	unsigned int rsp_cpu; /* CPU that task is returned on */
+	u8 sge_type; /* Did we take the slow, single or fast SGE path */
+};
+
+/* Number of entries in BDQ */
+#define QEDF_BDQ_SIZE			256
+#define QEDF_BDQ_BUF_SIZE		2072
+
+/* DMA coherent buffers for BDQ */
+struct qedf_bdq_buf {
+	void *buf_addr;
+	dma_addr_t buf_dma;
+};
+
+/* Main adapter struct */
+struct qedf_ctx {
+	struct qedf_dbg_ctx dbg_ctx;
+	struct fcoe_ctlr ctlr;
+	struct fc_lport *lport;
+	u8 data_src_addr[ETH_ALEN];
+#define QEDF_LINK_DOWN		0
+#define QEDF_LINK_UP		1
+	atomic_t link_state;
+#define QEDF_DCBX_PENDING	0
+#define QEDF_DCBX_DONE		1
+	atomic_t dcbx;
+	uint16_t max_scsi_xid;
+	uint16_t max_els_xid;
+#define QEDF_NULL_VLAN_ID	-1
+#define QEDF_FALLBACK_VLAN	1002
+#define QEDF_DEFAULT_PRIO	3
+	int vlan_id;
+	uint vlan_hw_insert:1;
+	struct qed_dev *cdev;
+	struct qed_dev_fcoe_info dev_info;
+	struct qed_int_info int_info;
+	uint16_t last_command;
+	spinlock_t hba_lock;
+	struct pci_dev *pdev;
+	u64 wwnn;
+	u64 wwpn;
+	u8 __aligned(16) mac[ETH_ALEN];
+	struct list_head fcports;
+	atomic_t num_offloads;
+	unsigned int curr_conn_id;
+	struct workqueue_struct *ll2_recv_wq;
+	struct workqueue_struct *link_update_wq;
+	struct delayed_work link_update;
+	struct delayed_work link_recovery;
+	struct completion flogi_compl;
+	struct completion fipvlan_compl;
+
+	/*
+	 * Used to tell if we're in the window where we are waiting for
+	 * the link to come back up before informting fcoe that the link is
+	 * done.
+	 */
+	atomic_t link_down_tmo_valid;
+#define QEDF_TIMER_INTERVAL		(1 * HZ)
+	struct timer_list timer; /* One second book keeping timer */
+#define QEDF_DRAIN_ACTIVE		1
+#define QEDF_LL2_STARTED		2
+#define QEDF_UNLOADING			3
+#define QEDF_GRCDUMP_CAPTURE		4
+#define QEDF_IN_RECOVERY		5
+#define QEDF_DBG_STOP_IO		6
+	unsigned long flags; /* Miscellaneous state flags */
+	int fipvlan_retries;
+	u8 num_queues;
+	struct global_queue **global_queues;
+	/* Pointer to array of queue structures */
+	struct qedf_glbl_q_params *p_cpuq;
+	/* Physical address of array of queue structures */
+	dma_addr_t hw_p_cpuq;
+
+	struct qedf_bdq_buf bdq[QEDF_BDQ_SIZE];
+	void *bdq_pbl;
+	dma_addr_t bdq_pbl_dma;
+	size_t bdq_pbl_mem_size;
+	void *bdq_pbl_list;
+	dma_addr_t bdq_pbl_list_dma;
+	u8 bdq_pbl_list_num_entries;
+	void __iomem *bdq_primary_prod;
+	void __iomem *bdq_secondary_prod;
+	uint16_t bdq_prod_idx;
+
+	/* Structure for holding all the fastpath for this qedf_ctx */
+	struct qedf_fastpath *fp_array;
+	struct qed_fcoe_tid tasks;
+	struct qedf_cmd_mgr *cmd_mgr;
+	/* Holds the PF parameters we pass to qed to start he FCoE function */
+	struct qed_pf_params pf_params;
+	/* Used to time middle path ELS and TM commands */
+	struct workqueue_struct *timer_work_queue;
+
+#define QEDF_IO_WORK_MIN		64
+	mempool_t *io_mempool;
+	struct workqueue_struct *dpc_wq;
+
+	u32 slow_sge_ios;
+	u32 fast_sge_ios;
+	u32 single_sge_ios;
+
+	uint8_t	*grcdump;
+	uint32_t grcdump_size;
+
+	struct qedf_io_log io_trace_buf[QEDF_IO_TRACE_SIZE];
+	spinlock_t io_trace_lock;
+	uint16_t io_trace_idx;
+
+	bool stop_io_on_error;
+
+	u32 flogi_cnt;
+	u32 flogi_failed;
+
+	/* Used for fc statistics */
+	u64 input_requests;
+	u64 output_requests;
+	u64 control_requests;
+	u64 packet_aborts;
+	u64 alloc_failures;
+};
+
+struct io_bdt {
+	struct qedf_ioreq *io_req;
+	struct fcoe_sge *bd_tbl;
+	dma_addr_t bd_tbl_dma;
+	u16 bd_valid;
+};
+
+struct qedf_cmd_mgr {
+	struct qedf_ctx *qedf;
+	u16 idx;
+	struct io_bdt **io_bdt_pool;
+#define FCOE_PARAMS_NUM_TASKS		4096
+	struct qedf_ioreq cmds[FCOE_PARAMS_NUM_TASKS];
+	spinlock_t lock;
+	atomic_t free_list_cnt;
+};
+
+/* Stolen from qed_cxt_api.h and adapted for qed_fcoe_info
+ * Usage:
+ *
+ * void *ptr;
+ * ptr = qedf_get_task_mem(&qedf->tasks, 128);
+ */
+static inline void *qedf_get_task_mem(struct qed_fcoe_tid *info, u32 tid)
+{
+	return (void *)(info->blocks[tid / info->num_tids_per_block] +
+			(tid % info->num_tids_per_block) * info->size);
+}
+
+static inline void qedf_stop_all_io(struct qedf_ctx *qedf)
+{
+	set_bit(QEDF_DBG_STOP_IO, &qedf->flags);
+}
+
+/*
+ * Externs
+ */
+#define QEDF_DEFAULT_LOG_MASK		0x3CFB6
+extern const struct qed_fcoe_ops *qed_ops;
+extern uint qedf_dump_frames;
+extern uint qedf_io_tracing;
+extern uint qedf_stop_io_on_error;
+extern uint qedf_link_down_tmo;
+#define QEDF_RETRY_DELAY_MAX		20 /* 2 seconds */
+extern bool qedf_retry_delay;
+extern uint qedf_debug;
+
+extern struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf);
+extern void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr);
+extern int qedf_queuecommand(struct Scsi_Host *host,
+	struct scsi_cmnd *sc_cmd);
+extern void qedf_fip_send(struct fcoe_ctlr *fip, struct sk_buff *skb);
+extern void qedf_update_src_mac(struct fc_lport *lport, u8 *addr);
+extern u8 *qedf_get_src_mac(struct fc_lport *lport);
+extern void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb);
+extern void qedf_fcoe_send_vlan_req(struct qedf_ctx *qedf);
+extern void qedf_scsi_completion(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req);
+extern void qedf_process_warning_compl(struct qedf_ctx *qedf,
+	struct fcoe_cqe *cqe, struct qedf_ioreq *io_req);
+extern void qedf_process_error_detect(struct qedf_ctx *qedf,
+	struct fcoe_cqe *cqe, struct qedf_ioreq *io_req);
+extern void qedf_flush_active_ios(struct qedf_rport *fcport, int lun);
+extern void qedf_release_cmd(struct kref *ref);
+extern int qedf_initiate_abts(struct qedf_ioreq *io_req,
+	bool return_scsi_cmd_on_abts);
+extern void qedf_process_abts_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req);
+extern struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport,
+	u8 cmd_type);
+
+extern struct device_attribute *qedf_host_attrs[];
+extern void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
+	unsigned int timer_msec);
+extern int qedf_init_mp_req(struct qedf_ioreq *io_req);
+extern void qedf_init_mp_task(struct qedf_ioreq *io_req,
+	struct fcoe_task_context *task_ctx);
+extern void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid,
+	u32 ptu_invalidate, enum fcoe_task_type req_type, u32 offset);
+extern void qedf_ring_doorbell(struct qedf_rport *fcport);
+extern void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *els_req);
+extern int qedf_send_rrq(struct qedf_ioreq *aborted_io_req);
+extern int qedf_send_adisc(struct qedf_rport *fcport, struct fc_frame *fp);
+extern int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
+	bool return_scsi_cmd_on_abts);
+extern void qedf_process_cleanup_compl(struct qedf_ctx *qedf,
+	struct fcoe_cqe *cqe, struct qedf_ioreq *io_req);
+extern int qedf_initiate_tmf(struct scsi_cmnd *sc_cmd, u8 tm_flags);
+extern void qedf_process_tmf_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req);
+extern void qedf_process_cqe(struct qedf_ctx *qedf, struct fcoe_cqe *cqe);
+extern void qedf_scsi_done(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
+	int result);
+extern void qedf_set_vlan_id(struct qedf_ctx *qedf, int vlan_id);
+extern void qedf_create_sysfs_ctx_attr(struct qedf_ctx *qedf);
+extern void qedf_remove_sysfs_ctx_attr(struct qedf_ctx *qedf);
+extern void qedf_capture_grc_dump(struct qedf_ctx *qedf);
+extern void qedf_wait_for_upload(struct qedf_ctx *qedf);
+extern void qedf_process_unsol_compl(struct qedf_ctx *qedf, uint16_t que_idx,
+	struct fcoe_cqe *cqe);
+extern void qedf_restart_rport(struct qedf_rport *fcport);
+extern int qedf_send_rec(struct qedf_ioreq *orig_io_req);
+extern int qedf_post_io_req(struct qedf_rport *fcport,
+	struct qedf_ioreq *io_req);
+extern void qedf_process_seq_cleanup_compl(struct qedf_ctx *qedf,
+	struct fcoe_cqe *cqe, struct qedf_ioreq *io_req);
+extern int qedf_send_flogi(struct qedf_ctx *qedf);
+extern void qedf_fp_io_handler(struct work_struct *work);
+
+#define FCOE_WORD_TO_BYTE  4
+#define QEDF_MAX_TASK_NUM	0xFFFF
+
+struct fip_vlan {
+	struct ethhdr eth;
+	struct fip_header fip;
+	struct {
+		struct fip_mac_desc mac;
+		struct fip_wwn_desc wwnn;
+	} desc;
+};
+
+/* SQ/CQ Sizes */
+#define GBL_RSVD_TASKS			16
+#define NUM_TASKS_PER_CONNECTION	1024
+#define NUM_RW_TASKS_PER_CONNECTION	512
+#define FCOE_PARAMS_CQ_NUM_ENTRIES	FCOE_PARAMS_NUM_TASKS
+
+#define FCOE_PARAMS_CMDQ_NUM_ENTRIES	FCOE_PARAMS_NUM_TASKS
+#define SQ_NUM_ENTRIES			NUM_TASKS_PER_CONNECTION
+
+#define QEDF_FCOE_PARAMS_GL_RQ_PI              0
+#define QEDF_FCOE_PARAMS_GL_CMD_PI             1
+
+#define QEDF_READ                     (1 << 1)
+#define QEDF_WRITE                    (1 << 0)
+#define MAX_FIBRE_LUNS			0xffffffff
+
+#define QEDF_MAX_NUM_CQS		8
+
+/*
+ * PCI function probe defines
+ */
+/* Probe/remove called during normal PCI probe */
+#define	QEDF_MODE_NORMAL		0
+/* Probe/remove called from qed error recovery */
+#define QEDF_MODE_RECOVERY		1
+
+#define SUPPORTED_25000baseKR_Full    (1<<27)
+#define SUPPORTED_50000baseKR2_Full   (1<<28)
+#define SUPPORTED_100000baseKR4_Full  (1<<29)
+#define SUPPORTED_100000baseCR4_Full  (1<<30)
+
+#endif
diff --git a/drivers/scsi/qedf/qedf_attr.c b/drivers/scsi/qedf/qedf_attr.c
new file mode 100644
index 000000000000..47720611ad2c
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_attr.c
@@ -0,0 +1,165 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#include "qedf.h"
+
+static ssize_t
+qedf_fcoe_mac_show(struct device *dev,
+	struct device_attribute *attr, char *buf)
+{
+	struct fc_lport *lport = shost_priv(class_to_shost(dev));
+	u32 port_id;
+	u8 lport_src_id[3];
+	u8 fcoe_mac[6];
+
+	port_id = fc_host_port_id(lport->host);
+	lport_src_id[2] = (port_id & 0x000000FF);
+	lport_src_id[1] = (port_id & 0x0000FF00) >> 8;
+	lport_src_id[0] = (port_id & 0x00FF0000) >> 16;
+	fc_fcoe_set_mac(fcoe_mac, lport_src_id);
+
+	return scnprintf(buf, PAGE_SIZE, "%pM\n", fcoe_mac);
+}
+
+static DEVICE_ATTR(fcoe_mac, S_IRUGO, qedf_fcoe_mac_show, NULL);
+
+struct device_attribute *qedf_host_attrs[] = {
+	&dev_attr_fcoe_mac,
+	NULL,
+};
+
+extern const struct qed_fcoe_ops *qed_ops;
+
+inline bool qedf_is_vport(struct qedf_ctx *qedf)
+{
+	return (!(qedf->lport->vport == NULL));
+}
+
+/* Get base qedf for physical port from vport */
+static struct qedf_ctx *qedf_get_base_qedf(struct qedf_ctx *qedf)
+{
+	struct fc_lport *lport;
+	struct fc_lport *base_lport;
+
+	if (!(qedf_is_vport(qedf)))
+		return NULL;
+
+	lport = qedf->lport;
+	base_lport = shost_priv(vport_to_shost(lport->vport));
+	return (struct qedf_ctx *)(lport_priv(base_lport));
+}
+
+void qedf_capture_grc_dump(struct qedf_ctx *qedf)
+{
+	struct qedf_ctx *base_qedf;
+
+	/* Make sure we use the base qedf to take the GRC dump */
+	if (qedf_is_vport(qedf))
+		base_qedf = qedf_get_base_qedf(qedf);
+	else
+		base_qedf = qedf;
+
+	if (test_bit(QEDF_GRCDUMP_CAPTURE, &base_qedf->flags)) {
+		QEDF_INFO(&(base_qedf->dbg_ctx), QEDF_LOG_INFO,
+		    "GRC Dump already captured.\n");
+		return;
+	}
+
+
+	qedf_get_grc_dump(base_qedf->cdev, qed_ops->common,
+	    &base_qedf->grcdump, &base_qedf->grcdump_size);
+	QEDF_ERR(&(base_qedf->dbg_ctx), "GRC Dump captured.\n");
+	set_bit(QEDF_GRCDUMP_CAPTURE, &base_qedf->flags);
+	qedf_uevent_emit(base_qedf->lport->host, QEDF_UEVENT_CODE_GRCDUMP,
+	    NULL);
+}
+
+static ssize_t
+qedf_sysfs_read_grcdump(struct file *filep, struct kobject *kobj,
+			struct bin_attribute *ba, char *buf, loff_t off,
+			size_t count)
+{
+	ssize_t ret = 0;
+	struct fc_lport *lport = shost_priv(dev_to_shost(container_of(kobj,
+							struct device, kobj)));
+	struct qedf_ctx *qedf = lport_priv(lport);
+
+	if (test_bit(QEDF_GRCDUMP_CAPTURE, &qedf->flags)) {
+		ret = memory_read_from_buffer(buf, count, &off,
+		    qedf->grcdump, qedf->grcdump_size);
+	} else {
+		QEDF_ERR(&(qedf->dbg_ctx), "GRC Dump not captured!\n");
+	}
+
+	return ret;
+}
+
+static ssize_t
+qedf_sysfs_write_grcdump(struct file *filep, struct kobject *kobj,
+			struct bin_attribute *ba, char *buf, loff_t off,
+			size_t count)
+{
+	struct fc_lport *lport = NULL;
+	struct qedf_ctx *qedf = NULL;
+	long reading;
+	int ret = 0;
+	char msg[40];
+
+	if (off != 0)
+		return ret;
+
+
+	lport = shost_priv(dev_to_shost(container_of(kobj,
+	    struct device, kobj)));
+	qedf = lport_priv(lport);
+
+	buf[1] = 0;
+	ret = kstrtol(buf, 10, &reading);
+	if (ret) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Invalid input, err(%d)\n", ret);
+		return ret;
+	}
+
+	memset(msg, 0, sizeof(msg));
+	switch (reading) {
+	case 0:
+		memset(qedf->grcdump, 0, qedf->grcdump_size);
+		clear_bit(QEDF_GRCDUMP_CAPTURE, &qedf->flags);
+		break;
+	case 1:
+		qedf_capture_grc_dump(qedf);
+		break;
+	}
+
+	return count;
+}
+
+static struct bin_attribute sysfs_grcdump_attr = {
+	.attr = {
+		.name = "grcdump",
+		.mode = S_IRUSR | S_IWUSR,
+	},
+	.size = 0,
+	.read = qedf_sysfs_read_grcdump,
+	.write = qedf_sysfs_write_grcdump,
+};
+
+static struct sysfs_bin_attrs bin_file_entries[] = {
+	{"grcdump", &sysfs_grcdump_attr},
+	{NULL},
+};
+
+void qedf_create_sysfs_ctx_attr(struct qedf_ctx *qedf)
+{
+	qedf_create_sysfs_attr(qedf->lport->host, bin_file_entries);
+}
+
+void qedf_remove_sysfs_ctx_attr(struct qedf_ctx *qedf)
+{
+	qedf_remove_sysfs_attr(qedf->lport->host, bin_file_entries);
+}
diff --git a/drivers/scsi/qedf/qedf_dbg.c b/drivers/scsi/qedf/qedf_dbg.c
new file mode 100644
index 000000000000..e023f5d0dc12
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_dbg.c
@@ -0,0 +1,195 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#include "qedf_dbg.h"
+#include <linux/vmalloc.h>
+
+void
+qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+	      const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (likely(qedf) && likely(qedf->pdev))
+		pr_err("[%s]:[%s:%d]:%d: %pV", dev_name(&(qedf->pdev->dev)),
+			nfunc, line, qedf->host_no, &vaf);
+	else
+		pr_err("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+void
+qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+	       const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedf_debug & QEDF_LOG_WARN))
+		goto ret;
+
+	if (likely(qedf) && likely(qedf->pdev))
+		pr_warn("[%s]:[%s:%d]:%d: %pV", dev_name(&(qedf->pdev->dev)),
+			nfunc, line, qedf->host_no, &vaf);
+	else
+		pr_warn("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+ret:
+	va_end(va);
+}
+
+void
+qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+		 const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedf_debug & QEDF_LOG_NOTICE))
+		goto ret;
+
+	if (likely(qedf) && likely(qedf->pdev))
+		pr_notice("[%s]:[%s:%d]:%d: %pV",
+			  dev_name(&(qedf->pdev->dev)), nfunc, line,
+			  qedf->host_no, &vaf);
+	else
+		pr_notice("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+ret:
+	va_end(va);
+}
+
+void
+qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+	       u32 level, const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedf_debug & level))
+		goto ret;
+
+	if (likely(qedf) && likely(qedf->pdev))
+		pr_info("[%s]:[%s:%d]:%d: %pV", dev_name(&(qedf->pdev->dev)),
+			nfunc, line, qedf->host_no, &vaf);
+	else
+		pr_info("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+ret:
+	va_end(va);
+}
+
+int
+qedf_alloc_grc_dump_buf(u8 **buf, uint32_t len)
+{
+		*buf = vmalloc(len);
+		if (!(*buf))
+			return -ENOMEM;
+
+		memset(*buf, 0, len);
+		return 0;
+}
+
+void
+qedf_free_grc_dump_buf(uint8_t **buf)
+{
+		vfree(*buf);
+		*buf = NULL;
+}
+
+int
+qedf_get_grc_dump(struct qed_dev *cdev, const struct qed_common_ops *common,
+		   u8 **buf, uint32_t *grcsize)
+{
+	if (!*buf)
+		return -EINVAL;
+
+	return common->dbg_grc(cdev, *buf, grcsize);
+}
+
+void
+qedf_uevent_emit(struct Scsi_Host *shost, u32 code, char *msg)
+{
+	char event_string[40];
+	char *envp[] = {event_string, NULL};
+
+	memset(event_string, 0, sizeof(event_string));
+	switch (code) {
+	case QEDF_UEVENT_CODE_GRCDUMP:
+		if (msg)
+			strncpy(event_string, msg, strlen(msg));
+		else
+			sprintf(event_string, "GRCDUMP=%u", shost->host_no);
+		break;
+	default:
+		/* do nothing */
+		break;
+	}
+
+	kobject_uevent_env(&shost->shost_gendev.kobj, KOBJ_CHANGE, envp);
+}
+
+int
+qedf_create_sysfs_attr(struct Scsi_Host *shost, struct sysfs_bin_attrs *iter)
+{
+	int ret = 0;
+
+	for (; iter->name; iter++) {
+		ret = sysfs_create_bin_file(&shost->shost_gendev.kobj,
+					    iter->attr);
+		if (ret)
+			pr_err("Unable to create sysfs %s attr, err(%d).\n",
+			       iter->name, ret);
+	}
+	return ret;
+}
+
+void
+qedf_remove_sysfs_attr(struct Scsi_Host *shost, struct sysfs_bin_attrs *iter)
+{
+	for (; iter->name; iter++)
+		sysfs_remove_bin_file(&shost->shost_gendev.kobj, iter->attr);
+}
diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h
new file mode 100644
index 000000000000..23bd70628a2f
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_dbg.h
@@ -0,0 +1,154 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#ifndef _QEDF_DBG_H_
+#define _QEDF_DBG_H_
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <linux/version.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <scsi/scsi_transport.h>
+#include <linux/fs.h>
+
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/qed_if.h>
+
+extern uint qedf_debug;
+
+/* Debug print level definitions */
+#define QEDF_LOG_DEFAULT	0x1		/* Set default logging mask */
+#define QEDF_LOG_INFO		0x2		/*
+						 * Informational logs,
+						 * MAC address, WWPN, WWNN
+						 */
+#define QEDF_LOG_DISC		0x4		/* Init, discovery, rport */
+#define QEDF_LOG_LL2		0x8		/* LL2, VLAN logs */
+#define QEDF_LOG_CONN		0x10		/* Connection setup, cleanup */
+#define QEDF_LOG_EVT		0x20		/* Events, link, mtu */
+#define QEDF_LOG_TIMER		0x40		/* Timer events */
+#define QEDF_LOG_MP_REQ	0x80		/* Middle Path (MP) logs */
+#define QEDF_LOG_SCSI_TM	0x100		/* SCSI Aborts, Task Mgmt */
+#define QEDF_LOG_UNSOL		0x200		/* unsolicited event logs */
+#define QEDF_LOG_IO		0x400		/* scsi cmd, completion */
+#define QEDF_LOG_MQ		0x800		/* Multi Queue logs */
+#define QEDF_LOG_BSG		0x1000		/* BSG logs */
+#define QEDF_LOG_DEBUGFS	0x2000		/* debugFS logs */
+#define QEDF_LOG_LPORT		0x4000		/* lport logs */
+#define QEDF_LOG_ELS		0x8000		/* ELS logs */
+#define QEDF_LOG_NPIV		0x10000		/* NPIV logs */
+#define QEDF_LOG_SESS		0x20000		/* Conection setup, cleanup */
+#define QEDF_LOG_TID		0x80000         /*
+						 * FW TID context acquire
+						 * free
+						 */
+#define QEDF_TRACK_TID		0x100000        /*
+						 * Track TID state. To be
+						 * enabled only at module load
+						 * and not run-time.
+						 */
+#define QEDF_TRACK_CMD_LIST    0x300000        /*
+						* Track active cmd list nodes,
+						* done with reference to TID,
+						* hence TRACK_TID also enabled.
+						*/
+#define QEDF_LOG_NOTICE	0x40000000	/* Notice logs */
+#define QEDF_LOG_WARN		0x80000000	/* Warning logs */
+
+/* Debug context structure */
+struct qedf_dbg_ctx {
+	unsigned int host_no;
+	struct pci_dev *pdev;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *bdf_dentry;
+#endif
+};
+
+#define QEDF_ERR(pdev, fmt, ...)	\
+		qedf_dbg_err(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDF_WARN(pdev, fmt, ...)	\
+		qedf_dbg_warn(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDF_NOTICE(pdev, fmt, ...)	\
+		qedf_dbg_notice(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDF_INFO(pdev, level, fmt, ...)	\
+		qedf_dbg_info(pdev, __func__, __LINE__, level, fmt,	\
+			      ## __VA_ARGS__)
+
+extern void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+			  const char *fmt, ...);
+extern void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+			   const char *, ...);
+extern void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func,
+			    u32 line, const char *, ...);
+extern void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+			  u32 info, const char *fmt, ...);
+
+/* GRC Dump related defines */
+
+struct Scsi_Host;
+
+#define QEDF_UEVENT_CODE_GRCDUMP 0
+
+struct sysfs_bin_attrs {
+	char *name;
+	struct bin_attribute *attr;
+};
+
+extern int qedf_alloc_grc_dump_buf(uint8_t **buf, uint32_t len);
+extern void qedf_free_grc_dump_buf(uint8_t **buf);
+extern int qedf_get_grc_dump(struct qed_dev *cdev,
+			     const struct qed_common_ops *common, uint8_t **buf,
+			     uint32_t *grcsize);
+extern void qedf_uevent_emit(struct Scsi_Host *shost, u32 code, char *msg);
+extern int qedf_create_sysfs_attr(struct Scsi_Host *shost,
+				   struct sysfs_bin_attrs *iter);
+extern void qedf_remove_sysfs_attr(struct Scsi_Host *shost,
+				    struct sysfs_bin_attrs *iter);
+
+#ifdef CONFIG_DEBUG_FS
+/* DebugFS related code */
+struct qedf_list_of_funcs {
+	char *oper_str;
+	ssize_t (*oper_func)(struct qedf_dbg_ctx *qedf);
+};
+
+struct qedf_debugfs_ops {
+	char *name;
+	struct qedf_list_of_funcs *qedf_funcs;
+};
+
+#define qedf_dbg_fileops(drv, ops) \
+{ \
+	.owner  = THIS_MODULE, \
+	.open   = simple_open, \
+	.read   = drv##_dbg_##ops##_cmd_read, \
+	.write  = drv##_dbg_##ops##_cmd_write \
+}
+
+/* Used for debugfs sequential files */
+#define qedf_dbg_fileops_seq(drv, ops) \
+{ \
+	.owner = THIS_MODULE, \
+	.open = drv##_dbg_##ops##_open, \
+	.read = seq_read, \
+	.llseek = seq_lseek, \
+	.release = single_release, \
+}
+
+extern void qedf_dbg_host_init(struct qedf_dbg_ctx *qedf,
+				struct qedf_debugfs_ops *dops,
+				struct file_operations *fops);
+extern void qedf_dbg_host_exit(struct qedf_dbg_ctx *qedf);
+extern void qedf_dbg_init(char *drv_name);
+extern void qedf_dbg_exit(void);
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* _QEDF_DBG_H_ */
diff --git a/drivers/scsi/qedf/qedf_debugfs.c b/drivers/scsi/qedf/qedf_debugfs.c
new file mode 100644
index 000000000000..cb08b625c594
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_debugfs.c
@@ -0,0 +1,460 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 QLogic Corporation
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+
+#include "qedf.h"
+#include "qedf_dbg.h"
+
+static struct dentry *qedf_dbg_root;
+
+/**
+ * qedf_dbg_host_init - setup the debugfs file for the pf
+ * @pf: the pf that is starting up
+ **/
+void
+qedf_dbg_host_init(struct qedf_dbg_ctx *qedf,
+		    struct qedf_debugfs_ops *dops,
+		    struct file_operations *fops)
+{
+	char host_dirname[32];
+	struct dentry *file_dentry = NULL;
+
+	QEDF_INFO(qedf, QEDF_LOG_DEBUGFS, "Creating debugfs host node\n");
+	/* create pf dir */
+	sprintf(host_dirname, "host%u", qedf->host_no);
+	qedf->bdf_dentry = debugfs_create_dir(host_dirname, qedf_dbg_root);
+	if (!qedf->bdf_dentry)
+		return;
+
+	/* create debugfs files */
+	while (dops) {
+		if (!(dops->name))
+			break;
+
+		file_dentry = debugfs_create_file(dops->name, 0600,
+						  qedf->bdf_dentry, qedf,
+						  fops);
+		if (!file_dentry) {
+			QEDF_INFO(qedf, QEDF_LOG_DEBUGFS,
+				   "Debugfs entry %s creation failed\n",
+				   dops->name);
+			debugfs_remove_recursive(qedf->bdf_dentry);
+			return;
+		}
+		dops++;
+		fops++;
+	}
+}
+
+/**
+ * qedf_dbg_host_exit - clear out the pf's debugfs entries
+ * @pf: the pf that is stopping
+ **/
+void
+qedf_dbg_host_exit(struct qedf_dbg_ctx *qedf)
+{
+	QEDF_INFO(qedf, QEDF_LOG_DEBUGFS, "Destroying debugfs host "
+		   "entry\n");
+	/* remove debugfs  entries of this PF */
+	debugfs_remove_recursive(qedf->bdf_dentry);
+	qedf->bdf_dentry = NULL;
+}
+
+/**
+ * qedf_dbg_init - start up debugfs for the driver
+ **/
+void
+qedf_dbg_init(char *drv_name)
+{
+	QEDF_INFO(NULL, QEDF_LOG_DEBUGFS, "Creating debugfs root node\n");
+
+	/* create qed dir in root of debugfs. NULL means debugfs root */
+	qedf_dbg_root = debugfs_create_dir(drv_name, NULL);
+	if (!qedf_dbg_root)
+		QEDF_INFO(NULL, QEDF_LOG_DEBUGFS, "Init of debugfs "
+			   "failed\n");
+}
+
+/**
+ * qedf_dbg_exit - clean out the driver's debugfs entries
+ **/
+void
+qedf_dbg_exit(void)
+{
+	QEDF_INFO(NULL, QEDF_LOG_DEBUGFS, "Destroying debugfs root "
+		   "entry\n");
+
+	/* remove qed dir in root of debugfs */
+	debugfs_remove_recursive(qedf_dbg_root);
+	qedf_dbg_root = NULL;
+}
+
+struct qedf_debugfs_ops qedf_debugfs_ops[] = {
+	{ "fp_int", NULL },
+	{ "io_trace", NULL },
+	{ "debug", NULL },
+	{ "stop_io_on_error", NULL},
+	{ "driver_stats", NULL},
+	{ "clear_stats", NULL},
+	{ "offload_stats", NULL},
+	/* This must be last */
+	{ NULL, NULL }
+};
+
+DECLARE_PER_CPU(struct qedf_percpu_iothread_s, qedf_percpu_iothreads);
+
+static ssize_t
+qedf_dbg_fp_int_cmd_read(struct file *filp, char __user *buffer, size_t count,
+			 loff_t *ppos)
+{
+	size_t cnt = 0;
+	int id;
+	struct qedf_fastpath *fp = NULL;
+	struct qedf_dbg_ctx *qedf_dbg =
+				(struct qedf_dbg_ctx *)filp->private_data;
+	struct qedf_ctx *qedf = container_of(qedf_dbg,
+	    struct qedf_ctx, dbg_ctx);
+
+	QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "entered\n");
+
+	cnt = sprintf(buffer, "\nFastpath I/O completions\n\n");
+
+	for (id = 0; id < qedf->num_queues; id++) {
+		fp = &(qedf->fp_array[id]);
+		if (fp->sb_id == QEDF_SB_ID_NULL)
+			continue;
+		cnt += sprintf((buffer + cnt), "#%d: %lu\n", id,
+			       fp->completions);
+	}
+
+	cnt = min_t(int, count, cnt - *ppos);
+	*ppos += cnt;
+	return cnt;
+}
+
+static ssize_t
+qedf_dbg_fp_int_cmd_write(struct file *filp, const char __user *buffer,
+			  size_t count, loff_t *ppos)
+{
+	if (!count || *ppos)
+		return 0;
+
+	return count;
+}
+
+static ssize_t
+qedf_dbg_debug_cmd_read(struct file *filp, char __user *buffer, size_t count,
+			loff_t *ppos)
+{
+	int cnt;
+	struct qedf_dbg_ctx *qedf =
+				(struct qedf_dbg_ctx *)filp->private_data;
+
+	QEDF_INFO(qedf, QEDF_LOG_DEBUGFS, "entered\n");
+	cnt = sprintf(buffer, "debug mask = 0x%x\n", qedf_debug);
+
+	cnt = min_t(int, count, cnt - *ppos);
+	*ppos += cnt;
+	return cnt;
+}
+
+static ssize_t
+qedf_dbg_debug_cmd_write(struct file *filp, const char __user *buffer,
+			 size_t count, loff_t *ppos)
+{
+	uint32_t val;
+	void *kern_buf;
+	int rval;
+	struct qedf_dbg_ctx *qedf =
+	    (struct qedf_dbg_ctx *)filp->private_data;
+
+	if (!count || *ppos)
+		return 0;
+
+	kern_buf = memdup_user(buffer, count);
+	if (IS_ERR(kern_buf))
+		return PTR_ERR(kern_buf);
+
+	rval = kstrtouint(kern_buf, 10, &val);
+	kfree(kern_buf);
+	if (rval)
+		return rval;
+
+	if (val == 1)
+		qedf_debug = QEDF_DEFAULT_LOG_MASK;
+	else
+		qedf_debug = val;
+
+	QEDF_INFO(qedf, QEDF_LOG_DEBUGFS, "Setting debug=0x%x.\n", val);
+	return count;
+}
+
+static ssize_t
+qedf_dbg_stop_io_on_error_cmd_read(struct file *filp, char __user *buffer,
+				   size_t count, loff_t *ppos)
+{
+	int cnt;
+	struct qedf_dbg_ctx *qedf_dbg =
+				(struct qedf_dbg_ctx *)filp->private_data;
+	struct qedf_ctx *qedf = container_of(qedf_dbg,
+	    struct qedf_ctx, dbg_ctx);
+
+	QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "entered\n");
+	cnt = sprintf(buffer, "%s\n",
+	    qedf->stop_io_on_error ? "true" : "false");
+
+	cnt = min_t(int, count, cnt - *ppos);
+	*ppos += cnt;
+	return cnt;
+}
+
+static ssize_t
+qedf_dbg_stop_io_on_error_cmd_write(struct file *filp,
+				    const char __user *buffer, size_t count,
+				    loff_t *ppos)
+{
+	void *kern_buf;
+	struct qedf_dbg_ctx *qedf_dbg =
+				(struct qedf_dbg_ctx *)filp->private_data;
+	struct qedf_ctx *qedf = container_of(qedf_dbg, struct qedf_ctx,
+	    dbg_ctx);
+
+	QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "entered\n");
+
+	if (!count || *ppos)
+		return 0;
+
+	kern_buf = memdup_user(buffer, 6);
+	if (IS_ERR(kern_buf))
+		return PTR_ERR(kern_buf);
+
+	if (strncmp(kern_buf, "false", 5) == 0)
+		qedf->stop_io_on_error = false;
+	else if (strncmp(kern_buf, "true", 4) == 0)
+		qedf->stop_io_on_error = true;
+	else if (strncmp(kern_buf, "now", 3) == 0)
+		/* Trigger from user to stop all I/O on this host */
+		set_bit(QEDF_DBG_STOP_IO, &qedf->flags);
+
+	kfree(kern_buf);
+	return count;
+}
+
+static int
+qedf_io_trace_show(struct seq_file *s, void *unused)
+{
+	int i, idx = 0;
+	struct qedf_ctx *qedf = s->private;
+	struct qedf_dbg_ctx *qedf_dbg = &qedf->dbg_ctx;
+	struct qedf_io_log *io_log;
+	unsigned long flags;
+
+	if (!qedf_io_tracing) {
+		seq_puts(s, "I/O tracing not enabled.\n");
+		goto out;
+	}
+
+	QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "entered\n");
+
+	spin_lock_irqsave(&qedf->io_trace_lock, flags);
+	idx = qedf->io_trace_idx;
+	for (i = 0; i < QEDF_IO_TRACE_SIZE; i++) {
+		io_log = &qedf->io_trace_buf[idx];
+		seq_printf(s, "%d:", io_log->direction);
+		seq_printf(s, "0x%x:", io_log->task_id);
+		seq_printf(s, "0x%06x:", io_log->port_id);
+		seq_printf(s, "%d:", io_log->lun);
+		seq_printf(s, "0x%02x:", io_log->op);
+		seq_printf(s, "0x%02x%02x%02x%02x:", io_log->lba[0],
+		    io_log->lba[1], io_log->lba[2], io_log->lba[3]);
+		seq_printf(s, "%d:", io_log->bufflen);
+		seq_printf(s, "%d:", io_log->sg_count);
+		seq_printf(s, "0x%08x:", io_log->result);
+		seq_printf(s, "%lu:", io_log->jiffies);
+		seq_printf(s, "%d:", io_log->refcount);
+		seq_printf(s, "%d:", io_log->req_cpu);
+		seq_printf(s, "%d:", io_log->int_cpu);
+		seq_printf(s, "%d:", io_log->rsp_cpu);
+		seq_printf(s, "%d\n", io_log->sge_type);
+
+		idx++;
+		if (idx == QEDF_IO_TRACE_SIZE)
+			idx = 0;
+	}
+	spin_unlock_irqrestore(&qedf->io_trace_lock, flags);
+
+out:
+	return 0;
+}
+
+static int
+qedf_dbg_io_trace_open(struct inode *inode, struct file *file)
+{
+	struct qedf_dbg_ctx *qedf_dbg = inode->i_private;
+	struct qedf_ctx *qedf = container_of(qedf_dbg,
+	    struct qedf_ctx, dbg_ctx);
+
+	return single_open(file, qedf_io_trace_show, qedf);
+}
+
+static int
+qedf_driver_stats_show(struct seq_file *s, void *unused)
+{
+	struct qedf_ctx *qedf = s->private;
+	struct qedf_rport *fcport;
+	struct fc_rport_priv *rdata;
+
+	seq_printf(s, "cmg_mgr free io_reqs: %d\n",
+	    atomic_read(&qedf->cmd_mgr->free_list_cnt));
+	seq_printf(s, "slow SGEs: %d\n", qedf->slow_sge_ios);
+	seq_printf(s, "single SGEs: %d\n", qedf->single_sge_ios);
+	seq_printf(s, "fast SGEs: %d\n\n", qedf->fast_sge_ios);
+
+	seq_puts(s, "Offloaded ports:\n\n");
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(fcport, &qedf->fcports, peers) {
+		rdata = fcport->rdata;
+		if (rdata == NULL)
+			continue;
+		seq_printf(s, "%06x: free_sqes: %d, num_active_ios: %d\n",
+		    rdata->ids.port_id, atomic_read(&fcport->free_sqes),
+		    atomic_read(&fcport->num_active_ios));
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int
+qedf_dbg_driver_stats_open(struct inode *inode, struct file *file)
+{
+	struct qedf_dbg_ctx *qedf_dbg = inode->i_private;
+	struct qedf_ctx *qedf = container_of(qedf_dbg,
+	    struct qedf_ctx, dbg_ctx);
+
+	return single_open(file, qedf_driver_stats_show, qedf);
+}
+
+static ssize_t
+qedf_dbg_clear_stats_cmd_read(struct file *filp, char __user *buffer,
+				   size_t count, loff_t *ppos)
+{
+	int cnt = 0;
+
+	/* Essentially a read stub */
+	cnt = min_t(int, count, cnt - *ppos);
+	*ppos += cnt;
+	return cnt;
+}
+
+static ssize_t
+qedf_dbg_clear_stats_cmd_write(struct file *filp,
+				    const char __user *buffer, size_t count,
+				    loff_t *ppos)
+{
+	struct qedf_dbg_ctx *qedf_dbg =
+				(struct qedf_dbg_ctx *)filp->private_data;
+	struct qedf_ctx *qedf = container_of(qedf_dbg, struct qedf_ctx,
+	    dbg_ctx);
+
+	QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "Clearing stat counters.\n");
+
+	if (!count || *ppos)
+		return 0;
+
+	/* Clear stat counters exposed by 'stats' node */
+	qedf->slow_sge_ios = 0;
+	qedf->single_sge_ios = 0;
+	qedf->fast_sge_ios = 0;
+
+	return count;
+}
+
+static int
+qedf_offload_stats_show(struct seq_file *s, void *unused)
+{
+	struct qedf_ctx *qedf = s->private;
+	struct qed_fcoe_stats *fw_fcoe_stats;
+
+	fw_fcoe_stats = kmalloc(sizeof(struct qed_fcoe_stats), GFP_KERNEL);
+	if (!fw_fcoe_stats) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Could not allocate memory for "
+		    "fw_fcoe_stats.\n");
+		goto out;
+	}
+
+	/* Query firmware for offload stats */
+	qed_ops->get_stats(qedf->cdev, fw_fcoe_stats);
+
+	seq_printf(s, "fcoe_rx_byte_cnt=%llu\n"
+	    "fcoe_rx_data_pkt_cnt=%llu\n"
+	    "fcoe_rx_xfer_pkt_cnt=%llu\n"
+	    "fcoe_rx_other_pkt_cnt=%llu\n"
+	    "fcoe_silent_drop_pkt_cmdq_full_cnt=%u\n"
+	    "fcoe_silent_drop_pkt_crc_error_cnt=%u\n"
+	    "fcoe_silent_drop_pkt_task_invalid_cnt=%u\n"
+	    "fcoe_silent_drop_total_pkt_cnt=%u\n"
+	    "fcoe_silent_drop_pkt_rq_full_cnt=%u\n"
+	    "fcoe_tx_byte_cnt=%llu\n"
+	    "fcoe_tx_data_pkt_cnt=%llu\n"
+	    "fcoe_tx_xfer_pkt_cnt=%llu\n"
+	    "fcoe_tx_other_pkt_cnt=%llu\n",
+	    fw_fcoe_stats->fcoe_rx_byte_cnt,
+	    fw_fcoe_stats->fcoe_rx_data_pkt_cnt,
+	    fw_fcoe_stats->fcoe_rx_xfer_pkt_cnt,
+	    fw_fcoe_stats->fcoe_rx_other_pkt_cnt,
+	    fw_fcoe_stats->fcoe_silent_drop_pkt_cmdq_full_cnt,
+	    fw_fcoe_stats->fcoe_silent_drop_pkt_crc_error_cnt,
+	    fw_fcoe_stats->fcoe_silent_drop_pkt_task_invalid_cnt,
+	    fw_fcoe_stats->fcoe_silent_drop_total_pkt_cnt,
+	    fw_fcoe_stats->fcoe_silent_drop_pkt_rq_full_cnt,
+	    fw_fcoe_stats->fcoe_tx_byte_cnt,
+	    fw_fcoe_stats->fcoe_tx_data_pkt_cnt,
+	    fw_fcoe_stats->fcoe_tx_xfer_pkt_cnt,
+	    fw_fcoe_stats->fcoe_tx_other_pkt_cnt);
+
+	kfree(fw_fcoe_stats);
+out:
+	return 0;
+}
+
+static int
+qedf_dbg_offload_stats_open(struct inode *inode, struct file *file)
+{
+	struct qedf_dbg_ctx *qedf_dbg = inode->i_private;
+	struct qedf_ctx *qedf = container_of(qedf_dbg,
+	    struct qedf_ctx, dbg_ctx);
+
+	return single_open(file, qedf_offload_stats_show, qedf);
+}
+
+
+const struct file_operations qedf_dbg_fops[] = {
+	qedf_dbg_fileops(qedf, fp_int),
+	qedf_dbg_fileops_seq(qedf, io_trace),
+	qedf_dbg_fileops(qedf, debug),
+	qedf_dbg_fileops(qedf, stop_io_on_error),
+	qedf_dbg_fileops_seq(qedf, driver_stats),
+	qedf_dbg_fileops(qedf, clear_stats),
+	qedf_dbg_fileops_seq(qedf, offload_stats),
+	/* This must be last */
+	{ NULL, NULL },
+};
+
+#else /* CONFIG_DEBUG_FS */
+void qedf_dbg_host_init(struct qedf_dbg_ctx *);
+void qedf_dbg_host_exit(struct qedf_dbg_ctx *);
+void qedf_dbg_init(char *);
+void qedf_dbg_exit(void);
+#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c
new file mode 100644
index 000000000000..78f1c252b649
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_els.c
@@ -0,0 +1,949 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#include "qedf.h"
+
+/* It's assumed that the lock is held when calling this function. */
+static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op,
+	void *data, uint32_t data_len,
+	void (*cb_func)(struct qedf_els_cb_arg *cb_arg),
+	struct qedf_els_cb_arg *cb_arg, uint32_t timer_msec)
+{
+	struct qedf_ctx *qedf = fcport->qedf;
+	struct fc_lport *lport = qedf->lport;
+	struct qedf_ioreq *els_req;
+	struct qedf_mp_req *mp_req;
+	struct fc_frame_header *fc_hdr;
+	struct fcoe_task_context *task;
+	int rc = 0;
+	uint32_t did, sid;
+	uint16_t xid;
+	uint32_t start_time = jiffies / HZ;
+	uint32_t current_time;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending ELS\n");
+
+	rc = fc_remote_port_chkready(fcport->rport);
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "els 0x%x: rport not ready\n", op);
+		rc = -EAGAIN;
+		goto els_err;
+	}
+	if (lport->state != LPORT_ST_READY || !(lport->link_up)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "els 0x%x: link is not ready\n",
+			  op);
+		rc = -EAGAIN;
+		goto els_err;
+	}
+
+	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+		QEDF_ERR(&(qedf->dbg_ctx), "els 0x%x: fcport not ready\n", op);
+		rc = -EINVAL;
+		goto els_err;
+	}
+
+retry_els:
+	els_req = qedf_alloc_cmd(fcport, QEDF_ELS);
+	if (!els_req) {
+		current_time = jiffies / HZ;
+		if ((current_time - start_time) > 10) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+				   "els: Failed els 0x%x\n", op);
+			rc = -ENOMEM;
+			goto els_err;
+		}
+		mdelay(20 * USEC_PER_MSEC);
+		goto retry_els;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "initiate_els els_req = "
+		   "0x%p cb_arg = %p xid = %x\n", els_req, cb_arg,
+		   els_req->xid);
+	els_req->sc_cmd = NULL;
+	els_req->cmd_type = QEDF_ELS;
+	els_req->fcport = fcport;
+	els_req->cb_func = cb_func;
+	cb_arg->io_req = els_req;
+	cb_arg->op = op;
+	els_req->cb_arg = cb_arg;
+	els_req->data_xfer_len = data_len;
+
+	/* Record which cpu this request is associated with */
+	els_req->cpu = smp_processor_id();
+
+	mp_req = (struct qedf_mp_req *)&(els_req->mp_req);
+	rc = qedf_init_mp_req(els_req);
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "ELS MP request init failed\n");
+		kref_put(&els_req->refcount, qedf_release_cmd);
+		goto els_err;
+	} else {
+		rc = 0;
+	}
+
+	/* Fill ELS Payload */
+	if ((op >= ELS_LS_RJT) && (op <= ELS_AUTH_ELS)) {
+		memcpy(mp_req->req_buf, data, data_len);
+	} else {
+		QEDF_ERR(&(qedf->dbg_ctx), "Invalid ELS op 0x%x\n", op);
+		els_req->cb_func = NULL;
+		els_req->cb_arg = NULL;
+		kref_put(&els_req->refcount, qedf_release_cmd);
+		rc = -EINVAL;
+	}
+
+	if (rc)
+		goto els_err;
+
+	/* Fill FC header */
+	fc_hdr = &(mp_req->req_fc_hdr);
+
+	did = fcport->rdata->ids.port_id;
+	sid = fcport->sid;
+
+	__fc_fill_fc_hdr(fc_hdr, FC_RCTL_ELS_REQ, sid, did,
+			   FC_TYPE_ELS, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
+			   FC_FC_SEQ_INIT, 0);
+
+	/* Obtain exchange id */
+	xid = els_req->xid;
+
+	/* Initialize task context for this IO request */
+	task = qedf_get_task_mem(&qedf->tasks, xid);
+	qedf_init_mp_task(els_req, task);
+
+	/* Put timer on original I/O request */
+	if (timer_msec)
+		qedf_cmd_timer_set(qedf, els_req, timer_msec);
+
+	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
+
+	/* Ring doorbell */
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Ringing doorbell for ELS "
+		   "req\n");
+	qedf_ring_doorbell(fcport);
+els_err:
+	return rc;
+}
+
+void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *els_req)
+{
+	struct fcoe_task_context *task_ctx;
+	struct scsi_cmnd *sc_cmd;
+	uint16_t xid;
+	struct fcoe_cqe_midpath_info *mp_info;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Entered with xid = 0x%x"
+		   " cmd_type = %d.\n", els_req->xid, els_req->cmd_type);
+
+	/* Kill the ELS timer */
+	cancel_delayed_work(&els_req->timeout_work);
+
+	xid = els_req->xid;
+	task_ctx = qedf_get_task_mem(&qedf->tasks, xid);
+	sc_cmd = els_req->sc_cmd;
+
+	/* Get ELS response length from CQE */
+	mp_info = &cqe->cqe_info.midpath_info;
+	els_req->mp_req.resp_len = mp_info->data_placement_size;
+
+	/* Parse ELS response */
+	if ((els_req->cb_func) && (els_req->cb_arg)) {
+		els_req->cb_func(els_req->cb_arg);
+		els_req->cb_arg = NULL;
+	}
+
+	kref_put(&els_req->refcount, qedf_release_cmd);
+}
+
+static void qedf_rrq_compl(struct qedf_els_cb_arg *cb_arg)
+{
+	struct qedf_ioreq *orig_io_req;
+	struct qedf_ioreq *rrq_req;
+	struct qedf_ctx *qedf;
+	int refcount;
+
+	rrq_req = cb_arg->io_req;
+	qedf = rrq_req->fcport->qedf;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Entered.\n");
+
+	orig_io_req = cb_arg->aborted_io_req;
+
+	if (!orig_io_req)
+		goto out_free;
+
+	if (rrq_req->event != QEDF_IOREQ_EV_ELS_TMO &&
+	    rrq_req->event != QEDF_IOREQ_EV_ELS_ERR_DETECT)
+		cancel_delayed_work_sync(&orig_io_req->timeout_work);
+
+	refcount = atomic_read(&orig_io_req->refcount.refcount);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "rrq_compl: orig io = %p,"
+		   " orig xid = 0x%x, rrq_xid = 0x%x, refcount=%d\n",
+		   orig_io_req, orig_io_req->xid, rrq_req->xid, refcount);
+
+	/* This should return the aborted io_req to the command pool */
+	if (orig_io_req)
+		kref_put(&orig_io_req->refcount, qedf_release_cmd);
+
+out_free:
+	kfree(cb_arg);
+}
+
+/* Assumes kref is already held by caller */
+int qedf_send_rrq(struct qedf_ioreq *aborted_io_req)
+{
+
+	struct fc_els_rrq rrq;
+	struct qedf_rport *fcport;
+	struct fc_lport *lport;
+	struct qedf_els_cb_arg *cb_arg = NULL;
+	struct qedf_ctx *qedf;
+	uint32_t sid;
+	uint32_t r_a_tov;
+	int rc;
+
+	if (!aborted_io_req) {
+		QEDF_ERR(NULL, "abort_io_req is NULL.\n");
+		return -EINVAL;
+	}
+
+	fcport = aborted_io_req->fcport;
+
+	/* Check that fcport is still offloaded */
+	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+		QEDF_ERR(NULL, "fcport is no longer offloaded.\n");
+		return -EINVAL;
+	}
+
+	if (!fcport->qedf) {
+		QEDF_ERR(NULL, "fcport->qedf is NULL.\n");
+		return -EINVAL;
+	}
+
+	qedf = fcport->qedf;
+	lport = qedf->lport;
+	sid = fcport->sid;
+	r_a_tov = lport->r_a_tov;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending RRQ orig "
+		   "io = %p, orig_xid = 0x%x\n", aborted_io_req,
+		   aborted_io_req->xid);
+	memset(&rrq, 0, sizeof(rrq));
+
+	cb_arg = kzalloc(sizeof(struct qedf_els_cb_arg), GFP_NOIO);
+	if (!cb_arg) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to allocate cb_arg for "
+			  "RRQ\n");
+		rc = -ENOMEM;
+		goto rrq_err;
+	}
+
+	cb_arg->aborted_io_req = aborted_io_req;
+
+	rrq.rrq_cmd = ELS_RRQ;
+	hton24(rrq.rrq_s_id, sid);
+	rrq.rrq_ox_id = htons(aborted_io_req->xid);
+	rrq.rrq_rx_id =
+	    htons(aborted_io_req->task->tstorm_st_context.read_write.rx_id);
+
+	rc = qedf_initiate_els(fcport, ELS_RRQ, &rrq, sizeof(rrq),
+	    qedf_rrq_compl, cb_arg, r_a_tov);
+
+rrq_err:
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "RRQ failed - release orig io "
+			  "req 0x%x\n", aborted_io_req->xid);
+		kfree(cb_arg);
+		kref_put(&aborted_io_req->refcount, qedf_release_cmd);
+	}
+	return rc;
+}
+
+static void qedf_process_l2_frame_compl(struct qedf_rport *fcport,
+					struct fc_frame *fp,
+					u16 l2_oxid)
+{
+	struct fc_lport *lport = fcport->qedf->lport;
+	struct fc_frame_header *fh;
+	u32 crc;
+
+	fh = (struct fc_frame_header *)fc_frame_header_get(fp);
+
+	/* Set the OXID we return to what libfc used */
+	if (l2_oxid != FC_XID_UNKNOWN)
+		fh->fh_ox_id = htons(l2_oxid);
+
+	/* Setup header fields */
+	fh->fh_r_ctl = FC_RCTL_ELS_REP;
+	fh->fh_type = FC_TYPE_ELS;
+	/* Last sequence, end sequence */
+	fh->fh_f_ctl[0] = 0x98;
+	hton24(fh->fh_d_id, lport->port_id);
+	hton24(fh->fh_s_id, fcport->rdata->ids.port_id);
+	fh->fh_rx_id = 0xffff;
+
+	/* Set frame attributes */
+	crc = fcoe_fc_crc(fp);
+	fc_frame_init(fp);
+	fr_dev(fp) = lport;
+	fr_sof(fp) = FC_SOF_I3;
+	fr_eof(fp) = FC_EOF_T;
+	fr_crc(fp) = cpu_to_le32(~crc);
+
+	/* Send completed request to libfc */
+	fc_exch_recv(lport, fp);
+}
+
+/*
+ * In instances where an ELS command times out we may need to restart the
+ * rport by logging out and then logging back in.
+ */
+void qedf_restart_rport(struct qedf_rport *fcport)
+{
+	struct fc_lport *lport;
+	struct fc_rport_priv *rdata;
+	u32 port_id;
+
+	if (!fcport)
+		return;
+
+	rdata = fcport->rdata;
+	if (rdata) {
+		lport = fcport->qedf->lport;
+		port_id = rdata->ids.port_id;
+		QEDF_ERR(&(fcport->qedf->dbg_ctx),
+		    "LOGO port_id=%x.\n", port_id);
+		fc_rport_logoff(rdata);
+		/* Recreate the rport and log back in */
+		rdata = fc_rport_create(lport, port_id);
+		if (rdata)
+			fc_rport_login(rdata);
+	}
+}
+
+static void qedf_l2_els_compl(struct qedf_els_cb_arg *cb_arg)
+{
+	struct qedf_ioreq *els_req;
+	struct qedf_rport *fcport;
+	struct qedf_mp_req *mp_req;
+	struct fc_frame *fp;
+	struct fc_frame_header *fh, *mp_fc_hdr;
+	void *resp_buf, *fc_payload;
+	u32 resp_len;
+	u16 l2_oxid;
+
+	l2_oxid = cb_arg->l2_oxid;
+	els_req = cb_arg->io_req;
+
+	if (!els_req) {
+		QEDF_ERR(NULL, "els_req is NULL.\n");
+		goto free_arg;
+	}
+
+	/*
+	 * If we are flushing the command just free the cb_arg as none of the
+	 * response data will be valid.
+	 */
+	if (els_req->event == QEDF_IOREQ_EV_ELS_FLUSH)
+		goto free_arg;
+
+	fcport = els_req->fcport;
+	mp_req = &(els_req->mp_req);
+	mp_fc_hdr = &(mp_req->resp_fc_hdr);
+	resp_len = mp_req->resp_len;
+	resp_buf = mp_req->resp_buf;
+
+	/*
+	 * If a middle path ELS command times out, don't try to return
+	 * the command but rather do any internal cleanup and then libfc
+	 * timeout the command and clean up its internal resources.
+	 */
+	if (els_req->event == QEDF_IOREQ_EV_ELS_TMO) {
+		/*
+		 * If ADISC times out, libfc will timeout the exchange and then
+		 * try to send a PLOGI which will timeout since the session is
+		 * still offloaded.  Force libfc to logout the session which
+		 * will offload the connection and allow the PLOGI response to
+		 * flow over the LL2 path.
+		 */
+		if (cb_arg->op == ELS_ADISC)
+			qedf_restart_rport(fcport);
+		return;
+	}
+
+	if (sizeof(struct fc_frame_header) + resp_len > QEDF_PAGE_SIZE) {
+		QEDF_ERR(&(fcport->qedf->dbg_ctx), "resp_len is "
+		   "beyond page size.\n");
+		goto free_arg;
+	}
+
+	fp = fc_frame_alloc(fcport->qedf->lport, resp_len);
+	if (!fp) {
+		QEDF_ERR(&(fcport->qedf->dbg_ctx),
+		    "fc_frame_alloc failure.\n");
+		return;
+	}
+
+	/* Copy frame header from firmware into fp */
+	fh = (struct fc_frame_header *)fc_frame_header_get(fp);
+	memcpy(fh, mp_fc_hdr, sizeof(struct fc_frame_header));
+
+	/* Copy payload from firmware into fp */
+	fc_payload = fc_frame_payload_get(fp, resp_len);
+	memcpy(fc_payload, resp_buf, resp_len);
+
+	QEDF_INFO(&(fcport->qedf->dbg_ctx), QEDF_LOG_ELS,
+	    "Completing OX_ID 0x%x back to libfc.\n", l2_oxid);
+	qedf_process_l2_frame_compl(fcport, fp, l2_oxid);
+
+free_arg:
+	kfree(cb_arg);
+}
+
+int qedf_send_adisc(struct qedf_rport *fcport, struct fc_frame *fp)
+{
+	struct fc_els_adisc *adisc;
+	struct fc_frame_header *fh;
+	struct fc_lport *lport = fcport->qedf->lport;
+	struct qedf_els_cb_arg *cb_arg = NULL;
+	struct qedf_ctx *qedf;
+	uint32_t r_a_tov = lport->r_a_tov;
+	int rc;
+
+	qedf = fcport->qedf;
+	fh = fc_frame_header_get(fp);
+
+	cb_arg = kzalloc(sizeof(struct qedf_els_cb_arg), GFP_NOIO);
+	if (!cb_arg) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to allocate cb_arg for "
+			  "ADISC\n");
+		rc = -ENOMEM;
+		goto adisc_err;
+	}
+	cb_arg->l2_oxid = ntohs(fh->fh_ox_id);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+	    "Sending ADISC ox_id=0x%x.\n", cb_arg->l2_oxid);
+
+	adisc = fc_frame_payload_get(fp, sizeof(*adisc));
+
+	rc = qedf_initiate_els(fcport, ELS_ADISC, adisc, sizeof(*adisc),
+	    qedf_l2_els_compl, cb_arg, r_a_tov);
+
+adisc_err:
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "ADISC failed.\n");
+		kfree(cb_arg);
+	}
+	return rc;
+}
+
+static void qedf_srr_compl(struct qedf_els_cb_arg *cb_arg)
+{
+	struct qedf_ioreq *orig_io_req;
+	struct qedf_ioreq *srr_req;
+	struct qedf_mp_req *mp_req;
+	struct fc_frame_header *mp_fc_hdr, *fh;
+	struct fc_frame *fp;
+	void *resp_buf, *fc_payload;
+	u32 resp_len;
+	struct fc_lport *lport;
+	struct qedf_ctx *qedf;
+	int refcount;
+	u8 opcode;
+
+	srr_req = cb_arg->io_req;
+	qedf = srr_req->fcport->qedf;
+	lport = qedf->lport;
+
+	orig_io_req = cb_arg->aborted_io_req;
+
+	if (!orig_io_req)
+		goto out_free;
+
+	clear_bit(QEDF_CMD_SRR_SENT, &orig_io_req->flags);
+
+	if (srr_req->event != QEDF_IOREQ_EV_ELS_TMO &&
+	    srr_req->event != QEDF_IOREQ_EV_ELS_ERR_DETECT)
+		cancel_delayed_work_sync(&orig_io_req->timeout_work);
+
+	refcount = atomic_read(&orig_io_req->refcount.refcount);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Entered: orig_io=%p,"
+		   " orig_io_xid=0x%x, rec_xid=0x%x, refcount=%d\n",
+		   orig_io_req, orig_io_req->xid, srr_req->xid, refcount);
+
+	/* If a SRR times out, simply free resources */
+	if (srr_req->event == QEDF_IOREQ_EV_ELS_TMO)
+		goto out_free;
+
+	/* Normalize response data into struct fc_frame */
+	mp_req = &(srr_req->mp_req);
+	mp_fc_hdr = &(mp_req->resp_fc_hdr);
+	resp_len = mp_req->resp_len;
+	resp_buf = mp_req->resp_buf;
+
+	fp = fc_frame_alloc(lport, resp_len);
+	if (!fp) {
+		QEDF_ERR(&(qedf->dbg_ctx),
+		    "fc_frame_alloc failure.\n");
+		goto out_free;
+	}
+
+	/* Copy frame header from firmware into fp */
+	fh = (struct fc_frame_header *)fc_frame_header_get(fp);
+	memcpy(fh, mp_fc_hdr, sizeof(struct fc_frame_header));
+
+	/* Copy payload from firmware into fp */
+	fc_payload = fc_frame_payload_get(fp, resp_len);
+	memcpy(fc_payload, resp_buf, resp_len);
+
+	opcode = fc_frame_payload_op(fp);
+	switch (opcode) {
+	case ELS_LS_ACC:
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+		    "SRR success.\n");
+		break;
+	case ELS_LS_RJT:
+		QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_ELS,
+		    "SRR rejected.\n");
+		qedf_initiate_abts(orig_io_req, true);
+		break;
+	}
+
+	fc_frame_free(fp);
+out_free:
+	/* Put reference for original command since SRR completed */
+	kref_put(&orig_io_req->refcount, qedf_release_cmd);
+	kfree(cb_arg);
+}
+
+static int qedf_send_srr(struct qedf_ioreq *orig_io_req, u32 offset, u8 r_ctl)
+{
+	struct fcp_srr srr;
+	struct qedf_ctx *qedf;
+	struct qedf_rport *fcport;
+	struct fc_lport *lport;
+	struct qedf_els_cb_arg *cb_arg = NULL;
+	u32 sid, r_a_tov;
+	int rc;
+
+	if (!orig_io_req) {
+		QEDF_ERR(NULL, "orig_io_req is NULL.\n");
+		return -EINVAL;
+	}
+
+	fcport = orig_io_req->fcport;
+
+	/* Check that fcport is still offloaded */
+	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+		QEDF_ERR(NULL, "fcport is no longer offloaded.\n");
+		return -EINVAL;
+	}
+
+	if (!fcport->qedf) {
+		QEDF_ERR(NULL, "fcport->qedf is NULL.\n");
+		return -EINVAL;
+	}
+
+	/* Take reference until SRR command completion */
+	kref_get(&orig_io_req->refcount);
+
+	qedf = fcport->qedf;
+	lport = qedf->lport;
+	sid = fcport->sid;
+	r_a_tov = lport->r_a_tov;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending SRR orig_io=%p, "
+		   "orig_xid=0x%x\n", orig_io_req, orig_io_req->xid);
+	memset(&srr, 0, sizeof(srr));
+
+	cb_arg = kzalloc(sizeof(struct qedf_els_cb_arg), GFP_NOIO);
+	if (!cb_arg) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to allocate cb_arg for "
+			  "SRR\n");
+		rc = -ENOMEM;
+		goto srr_err;
+	}
+
+	cb_arg->aborted_io_req = orig_io_req;
+
+	srr.srr_op = ELS_SRR;
+	srr.srr_ox_id = htons(orig_io_req->xid);
+	srr.srr_rx_id = htons(orig_io_req->rx_id);
+	srr.srr_rel_off = htonl(offset);
+	srr.srr_r_ctl = r_ctl;
+
+	rc = qedf_initiate_els(fcport, ELS_SRR, &srr, sizeof(srr),
+	    qedf_srr_compl, cb_arg, r_a_tov);
+
+srr_err:
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "SRR failed - release orig_io_req"
+			  "=0x%x\n", orig_io_req->xid);
+		kfree(cb_arg);
+		/* If we fail to queue SRR, send ABTS to orig_io */
+		qedf_initiate_abts(orig_io_req, true);
+		kref_put(&orig_io_req->refcount, qedf_release_cmd);
+	} else
+		/* Tell other threads that SRR is in progress */
+		set_bit(QEDF_CMD_SRR_SENT, &orig_io_req->flags);
+
+	return rc;
+}
+
+static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req,
+	u32 offset, u8 r_ctl)
+{
+	struct qedf_rport *fcport;
+	unsigned long flags;
+	struct qedf_els_cb_arg *cb_arg;
+
+	fcport = orig_io_req->fcport;
+
+	QEDF_INFO(&(fcport->qedf->dbg_ctx), QEDF_LOG_ELS,
+	    "Doing sequence cleanup for xid=0x%x offset=%u.\n",
+	    orig_io_req->xid, offset);
+
+	cb_arg = kzalloc(sizeof(struct qedf_els_cb_arg), GFP_NOIO);
+	if (!cb_arg) {
+		QEDF_ERR(&(fcport->qedf->dbg_ctx), "Unable to allocate cb_arg "
+			  "for sequence cleanup\n");
+		return;
+	}
+
+	/* Get reference for cleanup request */
+	kref_get(&orig_io_req->refcount);
+
+	orig_io_req->cmd_type = QEDF_SEQ_CLEANUP;
+	cb_arg->offset = offset;
+	cb_arg->r_ctl = r_ctl;
+	orig_io_req->cb_arg = cb_arg;
+
+	qedf_cmd_timer_set(fcport->qedf, orig_io_req,
+	    QEDF_CLEANUP_TIMEOUT * HZ);
+
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+
+	qedf_add_to_sq(fcport, orig_io_req->xid, 0,
+	    FCOE_TASK_TYPE_SEQUENCE_CLEANUP, offset);
+	qedf_ring_doorbell(fcport);
+
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
+}
+
+void qedf_process_seq_cleanup_compl(struct qedf_ctx *qedf,
+	struct fcoe_cqe *cqe, struct qedf_ioreq *io_req)
+{
+	int rc;
+	struct qedf_els_cb_arg *cb_arg;
+
+	cb_arg = io_req->cb_arg;
+
+	/* If we timed out just free resources */
+	if (io_req->event == QEDF_IOREQ_EV_ELS_TMO || !cqe)
+		goto free;
+
+	/* Kill the timer we put on the request */
+	cancel_delayed_work_sync(&io_req->timeout_work);
+
+	rc = qedf_send_srr(io_req, cb_arg->offset, cb_arg->r_ctl);
+	if (rc)
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to send SRR, I/O will "
+		    "abort, xid=0x%x.\n", io_req->xid);
+free:
+	kfree(cb_arg);
+	kref_put(&io_req->refcount, qedf_release_cmd);
+}
+
+static bool qedf_requeue_io_req(struct qedf_ioreq *orig_io_req)
+{
+	struct qedf_rport *fcport;
+	struct qedf_ioreq *new_io_req;
+	unsigned long flags;
+	bool rc = false;
+
+	fcport = orig_io_req->fcport;
+	if (!fcport) {
+		QEDF_ERR(NULL, "fcport is NULL.\n");
+		goto out;
+	}
+
+	if (!orig_io_req->sc_cmd) {
+		QEDF_ERR(&(fcport->qedf->dbg_ctx), "sc_cmd is NULL for "
+		    "xid=0x%x.\n", orig_io_req->xid);
+		goto out;
+	}
+
+	new_io_req = qedf_alloc_cmd(fcport, QEDF_SCSI_CMD);
+	if (!new_io_req) {
+		QEDF_ERR(&(fcport->qedf->dbg_ctx), "Could not allocate new "
+		    "io_req.\n");
+		goto out;
+	}
+
+	new_io_req->sc_cmd = orig_io_req->sc_cmd;
+
+	/*
+	 * This keeps the sc_cmd struct from being returned to the tape
+	 * driver and being requeued twice. We do need to put a reference
+	 * for the original I/O request since we will not do a SCSI completion
+	 * for it.
+	 */
+	orig_io_req->sc_cmd = NULL;
+	kref_put(&orig_io_req->refcount, qedf_release_cmd);
+
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+
+	/* kref for new command released in qedf_post_io_req on error */
+	if (qedf_post_io_req(fcport, new_io_req)) {
+		QEDF_ERR(&(fcport->qedf->dbg_ctx), "Unable to post io_req\n");
+		/* Return SQE to pool */
+		atomic_inc(&fcport->free_sqes);
+	} else {
+		QEDF_INFO(&(fcport->qedf->dbg_ctx), QEDF_LOG_ELS,
+		    "Reissued SCSI command from  orig_xid=0x%x on "
+		    "new_xid=0x%x.\n", orig_io_req->xid, new_io_req->xid);
+		/*
+		 * Abort the original I/O but do not return SCSI command as
+		 * it has been reissued on another OX_ID.
+		 */
+		spin_unlock_irqrestore(&fcport->rport_lock, flags);
+		qedf_initiate_abts(orig_io_req, false);
+		goto out;
+	}
+
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
+out:
+	return rc;
+}
+
+
+static void qedf_rec_compl(struct qedf_els_cb_arg *cb_arg)
+{
+	struct qedf_ioreq *orig_io_req;
+	struct qedf_ioreq *rec_req;
+	struct qedf_mp_req *mp_req;
+	struct fc_frame_header *mp_fc_hdr, *fh;
+	struct fc_frame *fp;
+	void *resp_buf, *fc_payload;
+	u32 resp_len;
+	struct fc_lport *lport;
+	struct qedf_ctx *qedf;
+	int refcount;
+	enum fc_rctl r_ctl;
+	struct fc_els_ls_rjt *rjt;
+	struct fc_els_rec_acc *acc;
+	u8 opcode;
+	u32 offset, e_stat;
+	struct scsi_cmnd *sc_cmd;
+	bool srr_needed = false;
+
+	rec_req = cb_arg->io_req;
+	qedf = rec_req->fcport->qedf;
+	lport = qedf->lport;
+
+	orig_io_req = cb_arg->aborted_io_req;
+
+	if (!orig_io_req)
+		goto out_free;
+
+	if (rec_req->event != QEDF_IOREQ_EV_ELS_TMO &&
+	    rec_req->event != QEDF_IOREQ_EV_ELS_ERR_DETECT)
+		cancel_delayed_work_sync(&orig_io_req->timeout_work);
+
+	refcount = atomic_read(&orig_io_req->refcount.refcount);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Entered: orig_io=%p,"
+		   " orig_io_xid=0x%x, rec_xid=0x%x, refcount=%d\n",
+		   orig_io_req, orig_io_req->xid, rec_req->xid, refcount);
+
+	/* If a REC times out, free resources */
+	if (rec_req->event == QEDF_IOREQ_EV_ELS_TMO)
+		goto out_free;
+
+	/* Normalize response data into struct fc_frame */
+	mp_req = &(rec_req->mp_req);
+	mp_fc_hdr = &(mp_req->resp_fc_hdr);
+	resp_len = mp_req->resp_len;
+	acc = resp_buf = mp_req->resp_buf;
+
+	fp = fc_frame_alloc(lport, resp_len);
+	if (!fp) {
+		QEDF_ERR(&(qedf->dbg_ctx),
+		    "fc_frame_alloc failure.\n");
+		goto out_free;
+	}
+
+	/* Copy frame header from firmware into fp */
+	fh = (struct fc_frame_header *)fc_frame_header_get(fp);
+	memcpy(fh, mp_fc_hdr, sizeof(struct fc_frame_header));
+
+	/* Copy payload from firmware into fp */
+	fc_payload = fc_frame_payload_get(fp, resp_len);
+	memcpy(fc_payload, resp_buf, resp_len);
+
+	opcode = fc_frame_payload_op(fp);
+	if (opcode == ELS_LS_RJT) {
+		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+		    "Received LS_RJT for REC: er_reason=0x%x, "
+		    "er_explan=0x%x.\n", rjt->er_reason, rjt->er_explan);
+		/*
+		 * The following response(s) mean that we need to reissue the
+		 * request on another exchange.  We need to do this without
+		 * informing the upper layers lest it cause an application
+		 * error.
+		 */
+		if ((rjt->er_reason == ELS_RJT_LOGIC ||
+		    rjt->er_reason == ELS_RJT_UNAB) &&
+		    rjt->er_explan == ELS_EXPL_OXID_RXID) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+			    "Handle CMD LOST case.\n");
+			qedf_requeue_io_req(orig_io_req);
+		}
+	} else if (opcode == ELS_LS_ACC) {
+		offset = ntohl(acc->reca_fc4value);
+		e_stat = ntohl(acc->reca_e_stat);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+		    "Received LS_ACC for REC: offset=0x%x, e_stat=0x%x.\n",
+		    offset, e_stat);
+		if (e_stat & ESB_ST_SEQ_INIT)  {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+			    "Target has the seq init\n");
+			goto out_free_frame;
+		}
+		sc_cmd = orig_io_req->sc_cmd;
+		if (!sc_cmd) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+			    "sc_cmd is NULL for xid=0x%x.\n",
+			    orig_io_req->xid);
+			goto out_free_frame;
+		}
+		/* SCSI write case */
+		if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
+			if (offset == orig_io_req->data_xfer_len) {
+				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+				    "WRITE - response lost.\n");
+				r_ctl = FC_RCTL_DD_CMD_STATUS;
+				srr_needed = true;
+				offset = 0;
+			} else {
+				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+				    "WRITE - XFER_RDY/DATA lost.\n");
+				r_ctl = FC_RCTL_DD_DATA_DESC;
+				/* Use data from warning CQE instead of REC */
+				offset = orig_io_req->tx_buf_off;
+			}
+		/* SCSI read case */
+		} else {
+			if (orig_io_req->rx_buf_off ==
+			    orig_io_req->data_xfer_len) {
+				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+				    "READ - response lost.\n");
+				srr_needed = true;
+				r_ctl = FC_RCTL_DD_CMD_STATUS;
+				offset = 0;
+			} else {
+				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+				    "READ - DATA lost.\n");
+				/*
+				 * For read case we always set the offset to 0
+				 * for sequence recovery task.
+				 */
+				offset = 0;
+				r_ctl = FC_RCTL_DD_SOL_DATA;
+			}
+		}
+
+		if (srr_needed)
+			qedf_send_srr(orig_io_req, offset, r_ctl);
+		else
+			qedf_initiate_seq_cleanup(orig_io_req, offset, r_ctl);
+	}
+
+out_free_frame:
+	fc_frame_free(fp);
+out_free:
+	/* Put reference for original command since REC completed */
+	kref_put(&orig_io_req->refcount, qedf_release_cmd);
+	kfree(cb_arg);
+}
+
+/* Assumes kref is already held by caller */
+int qedf_send_rec(struct qedf_ioreq *orig_io_req)
+{
+
+	struct fc_els_rec rec;
+	struct qedf_rport *fcport;
+	struct fc_lport *lport;
+	struct qedf_els_cb_arg *cb_arg = NULL;
+	struct qedf_ctx *qedf;
+	uint32_t sid;
+	uint32_t r_a_tov;
+	int rc;
+
+	if (!orig_io_req) {
+		QEDF_ERR(NULL, "orig_io_req is NULL.\n");
+		return -EINVAL;
+	}
+
+	fcport = orig_io_req->fcport;
+
+	/* Check that fcport is still offloaded */
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		QEDF_ERR(NULL, "fcport is no longer offloaded.\n");
+		return -EINVAL;
+	}
+
+	if (!fcport->qedf) {
+		QEDF_ERR(NULL, "fcport->qedf is NULL.\n");
+		return -EINVAL;
+	}
+
+	/* Take reference until REC command completion */
+	kref_get(&orig_io_req->refcount);
+
+	qedf = fcport->qedf;
+	lport = qedf->lport;
+	sid = fcport->sid;
+	r_a_tov = lport->r_a_tov;
+
+	memset(&rec, 0, sizeof(rec));
+
+	cb_arg = kzalloc(sizeof(struct qedf_els_cb_arg), GFP_NOIO);
+	if (!cb_arg) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to allocate cb_arg for "
+			  "REC\n");
+		rc = -ENOMEM;
+		goto rec_err;
+	}
+
+	cb_arg->aborted_io_req = orig_io_req;
+
+	rec.rec_cmd = ELS_REC;
+	hton24(rec.rec_s_id, sid);
+	rec.rec_ox_id = htons(orig_io_req->xid);
+	rec.rec_rx_id =
+	    htons(orig_io_req->task->tstorm_st_context.read_write.rx_id);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending REC orig_io=%p, "
+	   "orig_xid=0x%x rx_id=0x%x\n", orig_io_req,
+	   orig_io_req->xid, rec.rec_rx_id);
+	rc = qedf_initiate_els(fcport, ELS_REC, &rec, sizeof(rec),
+	    qedf_rec_compl, cb_arg, r_a_tov);
+
+rec_err:
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "REC failed - release orig_io_req"
+			  "=0x%x\n", orig_io_req->xid);
+		kfree(cb_arg);
+		kref_put(&orig_io_req->refcount, qedf_release_cmd);
+	}
+	return rc;
+}
diff --git a/drivers/scsi/qedf/qedf_fip.c b/drivers/scsi/qedf/qedf_fip.c
new file mode 100644
index 000000000000..868d423380d1
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_fip.c
@@ -0,0 +1,269 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include "qedf.h"
+
+extern const struct qed_fcoe_ops *qed_ops;
+/*
+ * FIP VLAN functions that will eventually move to libfcoe.
+ */
+
+void qedf_fcoe_send_vlan_req(struct qedf_ctx *qedf)
+{
+	struct sk_buff *skb;
+	char *eth_fr;
+	int fr_len;
+	struct fip_vlan *vlan;
+#define MY_FIP_ALL_FCF_MACS        ((__u8[6]) { 1, 0x10, 0x18, 1, 0, 2 })
+	static u8 my_fcoe_all_fcfs[ETH_ALEN] = MY_FIP_ALL_FCF_MACS;
+
+	skb = dev_alloc_skb(sizeof(struct fip_vlan));
+	if (!skb)
+		return;
+
+	fr_len = sizeof(*vlan);
+	eth_fr = (char *)skb->data;
+	vlan = (struct fip_vlan *)eth_fr;
+
+	memset(vlan, 0, sizeof(*vlan));
+	ether_addr_copy(vlan->eth.h_source, qedf->mac);
+	ether_addr_copy(vlan->eth.h_dest, my_fcoe_all_fcfs);
+	vlan->eth.h_proto = htons(ETH_P_FIP);
+
+	vlan->fip.fip_ver = FIP_VER_ENCAPS(FIP_VER);
+	vlan->fip.fip_op = htons(FIP_OP_VLAN);
+	vlan->fip.fip_subcode = FIP_SC_VL_REQ;
+	vlan->fip.fip_dl_len = htons(sizeof(vlan->desc) / FIP_BPW);
+
+	vlan->desc.mac.fd_desc.fip_dtype = FIP_DT_MAC;
+	vlan->desc.mac.fd_desc.fip_dlen = sizeof(vlan->desc.mac) / FIP_BPW;
+	ether_addr_copy(vlan->desc.mac.fd_mac, qedf->mac);
+
+	vlan->desc.wwnn.fd_desc.fip_dtype = FIP_DT_NAME;
+	vlan->desc.wwnn.fd_desc.fip_dlen = sizeof(vlan->desc.wwnn) / FIP_BPW;
+	put_unaligned_be64(qedf->lport->wwnn, &vlan->desc.wwnn.fd_wwn);
+
+	skb_put(skb, sizeof(*vlan));
+	skb->protocol = htons(ETH_P_FIP);
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Sending FIP VLAN "
+		   "request.");
+
+	if (atomic_read(&qedf->link_state) != QEDF_LINK_UP) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Cannot send vlan request "
+		    "because link is not up.\n");
+
+		kfree_skb(skb);
+		return;
+	}
+	qed_ops->ll2->start_xmit(qedf->cdev, skb);
+}
+
+static void qedf_fcoe_process_vlan_resp(struct qedf_ctx *qedf,
+	struct sk_buff *skb)
+{
+	struct fip_header *fiph;
+	struct fip_desc *desc;
+	u16 vid = 0;
+	ssize_t rlen;
+	size_t dlen;
+
+	fiph = (struct fip_header *)(((void *)skb->data) + 2 * ETH_ALEN + 2);
+
+	rlen = ntohs(fiph->fip_dl_len) * 4;
+	desc = (struct fip_desc *)(fiph + 1);
+	while (rlen > 0) {
+		dlen = desc->fip_dlen * FIP_BPW;
+		switch (desc->fip_dtype) {
+		case FIP_DT_VLAN:
+			vid = ntohs(((struct fip_vlan_desc *)desc)->fd_vlan);
+			break;
+		}
+		desc = (struct fip_desc *)((char *)desc + dlen);
+		rlen -= dlen;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "VLAN response, "
+		   "vid=0x%x.\n", vid);
+
+	if (vid > 0 && qedf->vlan_id != vid) {
+		qedf_set_vlan_id(qedf, vid);
+
+		/* Inform waiter that it's ok to call fcoe_ctlr_link up() */
+		complete(&qedf->fipvlan_compl);
+	}
+}
+
+void qedf_fip_send(struct fcoe_ctlr *fip, struct sk_buff *skb)
+{
+	struct qedf_ctx *qedf = container_of(fip, struct qedf_ctx, ctlr);
+	struct ethhdr *eth_hdr;
+	struct vlan_ethhdr *vlan_hdr;
+	struct fip_header *fiph;
+	u16 op, vlan_tci = 0;
+	u8 sub;
+
+	if (!test_bit(QEDF_LL2_STARTED, &qedf->flags)) {
+		QEDF_WARN(&(qedf->dbg_ctx), "LL2 not started\n");
+		kfree_skb(skb);
+		return;
+	}
+
+	fiph = (struct fip_header *) ((void *)skb->data + 2 * ETH_ALEN + 2);
+	eth_hdr = (struct ethhdr *)skb_mac_header(skb);
+	op = ntohs(fiph->fip_op);
+	sub = fiph->fip_subcode;
+
+	if (!qedf->vlan_hw_insert) {
+		vlan_hdr = (struct vlan_ethhdr *)skb_push(skb, sizeof(*vlan_hdr)
+		    - sizeof(*eth_hdr));
+		memcpy(vlan_hdr, eth_hdr, 2 * ETH_ALEN);
+		vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q);
+		vlan_hdr->h_vlan_encapsulated_proto = eth_hdr->h_proto;
+		vlan_hdr->h_vlan_TCI = vlan_tci =  htons(qedf->vlan_id);
+	}
+
+	/* Update eth_hdr since we added a VLAN tag */
+	eth_hdr = (struct ethhdr *)skb_mac_header(skb);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2, "FIP frame send: "
+	    "dest=%pM op=%x sub=%x vlan=%04x.", eth_hdr->h_dest, op, sub,
+	    ntohs(vlan_tci));
+	if (qedf_dump_frames)
+		print_hex_dump(KERN_WARNING, "fip ", DUMP_PREFIX_OFFSET, 16, 1,
+		    skb->data, skb->len, false);
+
+	qed_ops->ll2->start_xmit(qedf->cdev, skb);
+}
+
+/* Process incoming FIP frames. */
+void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
+{
+	struct ethhdr *eth_hdr;
+	struct fip_header *fiph;
+	struct fip_desc *desc;
+	struct fip_mac_desc *mp;
+	struct fip_wwn_desc *wp;
+	struct fip_vn_desc *vp;
+	size_t rlen, dlen;
+	uint32_t cvl_port_id;
+	__u8 cvl_mac[ETH_ALEN];
+	u16 op;
+	u8 sub;
+
+	eth_hdr = (struct ethhdr *)skb_mac_header(skb);
+	fiph = (struct fip_header *) ((void *)skb->data + 2 * ETH_ALEN + 2);
+	op = ntohs(fiph->fip_op);
+	sub = fiph->fip_subcode;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2, "FIP frame received: "
+	    "skb=%p fiph=%p source=%pM op=%x sub=%x", skb, fiph,
+	    eth_hdr->h_source, op, sub);
+	if (qedf_dump_frames)
+		print_hex_dump(KERN_WARNING, "fip ", DUMP_PREFIX_OFFSET, 16, 1,
+		    skb->data, skb->len, false);
+
+	/* Handle FIP VLAN resp in the driver */
+	if (op == FIP_OP_VLAN && sub == FIP_SC_VL_NOTE) {
+		qedf_fcoe_process_vlan_resp(qedf, skb);
+		qedf->vlan_hw_insert = 0;
+		kfree_skb(skb);
+	} else if (op == FIP_OP_CTRL && sub == FIP_SC_CLR_VLINK) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Clear virtual "
+			   "link received.\n");
+
+		/* Check that an FCF has been selected by fcoe */
+		if (qedf->ctlr.sel_fcf == NULL) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "Dropping CVL since FCF has not been selected "
+			    "yet.");
+			return;
+		}
+
+		cvl_port_id = 0;
+		memset(cvl_mac, 0, ETH_ALEN);
+		/*
+		 * We need to loop through the CVL descriptors to determine
+		 * if we want to reset the fcoe link
+		 */
+		rlen = ntohs(fiph->fip_dl_len) * FIP_BPW;
+		desc = (struct fip_desc *)(fiph + 1);
+		while (rlen >= sizeof(*desc)) {
+			dlen = desc->fip_dlen * FIP_BPW;
+			switch (desc->fip_dtype) {
+			case FIP_DT_MAC:
+				mp = (struct fip_mac_desc *)desc;
+				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
+				    "fd_mac=%pM.\n", __func__, mp->fd_mac);
+				ether_addr_copy(cvl_mac, mp->fd_mac);
+				break;
+			case FIP_DT_NAME:
+				wp = (struct fip_wwn_desc *)desc;
+				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
+				    "fc_wwpn=%016llx.\n",
+				    get_unaligned_be64(&wp->fd_wwn));
+				break;
+			case FIP_DT_VN_ID:
+				vp = (struct fip_vn_desc *)desc;
+				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
+				    "fd_fc_id=%x.\n", ntoh24(vp->fd_fc_id));
+				cvl_port_id = ntoh24(vp->fd_fc_id);
+				break;
+			default:
+				/* Ignore anything else */
+				break;
+			}
+			desc = (struct fip_desc *)((char *)desc + dlen);
+			rlen -= dlen;
+		}
+
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
+		    "cvl_port_id=%06x cvl_mac=%pM.\n", cvl_port_id,
+		    cvl_mac);
+		if (cvl_port_id == qedf->lport->port_id &&
+		    ether_addr_equal(cvl_mac,
+		    qedf->ctlr.sel_fcf->fcf_mac)) {
+			fcoe_ctlr_link_down(&qedf->ctlr);
+			qedf_wait_for_upload(qedf);
+			fcoe_ctlr_link_up(&qedf->ctlr);
+		}
+		kfree_skb(skb);
+	} else {
+		/* Everything else is handled by libfcoe */
+		__skb_pull(skb, ETH_HLEN);
+		fcoe_ctlr_recv(&qedf->ctlr, skb);
+	}
+}
+
+void qedf_update_src_mac(struct fc_lport *lport, u8 *addr)
+{
+	struct qedf_ctx *qedf = lport_priv(lport);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+	    "Setting data_src_addr=%pM.\n", addr);
+	ether_addr_copy(qedf->data_src_addr, addr);
+}
+
+u8 *qedf_get_src_mac(struct fc_lport *lport)
+{
+	u8 mac[ETH_ALEN];
+	u8 port_id[3];
+	struct qedf_ctx *qedf = lport_priv(lport);
+
+	/* We need to use the lport port_id to create the data_src_addr */
+	if (is_zero_ether_addr(qedf->data_src_addr)) {
+		hton24(port_id, lport->port_id);
+		fc_fcoe_set_mac(mac, port_id);
+		qedf->ctlr.update_mac(lport, mac);
+	}
+	return qedf->data_src_addr;
+}
diff --git a/drivers/scsi/qedf/qedf_hsi.h b/drivers/scsi/qedf/qedf_hsi.h
new file mode 100644
index 000000000000..dfd65dec2874
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_hsi.h
@@ -0,0 +1,422 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#ifndef __QEDF_HSI__
+#define __QEDF_HSI__
+/*
+ * Add include to common target
+ */
+#include <linux/qed/common_hsi.h>
+
+/*
+ * Add include to common storage target
+ */
+#include <linux/qed/storage_common.h>
+
+/*
+ * Add include to common fcoe target for both eCore and protocol driver
+ */
+#include <linux/qed/fcoe_common.h>
+
+
+/*
+ * FCoE CQ element ABTS information
+ */
+struct fcoe_abts_info {
+	u8 r_ctl /* R_CTL in the ABTS response frame */;
+	u8 reserved0;
+	__le16 rx_id;
+	__le32 reserved2[2];
+	__le32 fc_payload[3] /* ABTS FC payload response frame */;
+};
+
+
+/*
+ * FCoE class type
+ */
+enum fcoe_class_type {
+	FCOE_TASK_CLASS_TYPE_3,
+	FCOE_TASK_CLASS_TYPE_2,
+	MAX_FCOE_CLASS_TYPE
+};
+
+
+/*
+ * FCoE CMDQ element control information
+ */
+struct fcoe_cmdqe_control {
+	__le16 conn_id;
+	u8 num_additional_cmdqes;
+	u8 cmdType;
+	/* true for ABTS request cmdqe. used in Target mode */
+#define FCOE_CMDQE_CONTROL_ABTSREQCMD_MASK  0x1
+#define FCOE_CMDQE_CONTROL_ABTSREQCMD_SHIFT 0
+#define FCOE_CMDQE_CONTROL_RESERVED1_MASK   0x7F
+#define FCOE_CMDQE_CONTROL_RESERVED1_SHIFT  1
+	u8 reserved2[4];
+};
+
+/*
+ * FCoE control + payload CMDQ element
+ */
+struct fcoe_cmdqe {
+	struct fcoe_cmdqe_control hdr;
+	u8 fc_header[24];
+	__le32 fcp_cmd_payload[8];
+};
+
+
+
+/*
+ * FCP RSP flags
+ */
+struct fcoe_fcp_rsp_flags {
+	u8 flags;
+#define FCOE_FCP_RSP_FLAGS_FCP_RSP_LEN_VALID_MASK  0x1
+#define FCOE_FCP_RSP_FLAGS_FCP_RSP_LEN_VALID_SHIFT 0
+#define FCOE_FCP_RSP_FLAGS_FCP_SNS_LEN_VALID_MASK  0x1
+#define FCOE_FCP_RSP_FLAGS_FCP_SNS_LEN_VALID_SHIFT 1
+#define FCOE_FCP_RSP_FLAGS_FCP_RESID_OVER_MASK     0x1
+#define FCOE_FCP_RSP_FLAGS_FCP_RESID_OVER_SHIFT    2
+#define FCOE_FCP_RSP_FLAGS_FCP_RESID_UNDER_MASK    0x1
+#define FCOE_FCP_RSP_FLAGS_FCP_RESID_UNDER_SHIFT   3
+#define FCOE_FCP_RSP_FLAGS_FCP_CONF_REQ_MASK       0x1
+#define FCOE_FCP_RSP_FLAGS_FCP_CONF_REQ_SHIFT      4
+#define FCOE_FCP_RSP_FLAGS_FCP_BIDI_FLAGS_MASK     0x7
+#define FCOE_FCP_RSP_FLAGS_FCP_BIDI_FLAGS_SHIFT    5
+};
+
+/*
+ * FCoE CQ element response information
+ */
+struct fcoe_cqe_rsp_info {
+	struct fcoe_fcp_rsp_flags rsp_flags;
+	u8 scsi_status_code;
+	__le16 retry_delay_timer;
+	__le32 fcp_resid;
+	__le32 fcp_sns_len;
+	__le32 fcp_rsp_len;
+	__le16 rx_id;
+	u8 fw_error_flags;
+#define FCOE_CQE_RSP_INFO_FW_UNDERRUN_MASK  0x1 /* FW detected underrun */
+#define FCOE_CQE_RSP_INFO_FW_UNDERRUN_SHIFT 0
+#define FCOE_CQE_RSP_INFO_RESREVED_MASK     0x7F
+#define FCOE_CQE_RSP_INFO_RESREVED_SHIFT    1
+	u8 reserved;
+	__le32 fw_residual /* Residual bytes calculated by FW */;
+};
+
+/*
+ * FCoE CQ element Target completion information
+ */
+struct fcoe_cqe_target_info {
+	__le16 rx_id;
+	__le16 reserved0;
+	__le32 reserved1[5];
+};
+
+/*
+ * FCoE error/warning reporting entry
+ */
+struct fcoe_err_report_entry {
+	__le32 err_warn_bitmap_lo /* Error bitmap lower 32 bits */;
+	__le32 err_warn_bitmap_hi /* Error bitmap higher 32 bits */;
+	/* Buffer offset the beginning of the Sequence last transmitted */
+	__le32 tx_buf_off;
+	/* Buffer offset from the beginning of the Sequence last received */
+	__le32 rx_buf_off;
+	__le16 rx_id /* RX_ID of the associated task */;
+	__le16 reserved1;
+	__le32 reserved2;
+};
+
+/*
+ * FCoE CQ element middle path information
+ */
+struct fcoe_cqe_midpath_info {
+	__le32 data_placement_size;
+	__le16 rx_id;
+	__le16 reserved0;
+	__le32 reserved1[4];
+};
+
+/*
+ * FCoE CQ element unsolicited information
+ */
+struct fcoe_unsolic_info {
+	/* BD information: Physical address and opaque data */
+	struct scsi_bd bd_info;
+	__le16 conn_id /* Connection ID the frame is associated to */;
+	__le16 pkt_len /* Packet length */;
+	u8 reserved1[4];
+};
+
+/*
+ * FCoE warning reporting entry
+ */
+struct fcoe_warning_report_entry {
+	/* BD information: Physical address and opaque data */
+	struct scsi_bd bd_info;
+	/* Buffer offset the beginning of the Sequence last transmitted */
+	__le32 buf_off;
+	__le16 rx_id /* RX_ID of the associated task */;
+	__le16 reserved1;
+};
+
+/*
+ * FCoE CQ element information
+ */
+union fcoe_cqe_info {
+	struct fcoe_cqe_rsp_info rsp_info /* Response completion information */;
+	/* Target completion information */
+	struct fcoe_cqe_target_info target_info;
+	/* Error completion information */
+	struct fcoe_err_report_entry err_info;
+	struct fcoe_abts_info abts_info /* ABTS completion information */;
+	/* Middle path completion information */
+	struct fcoe_cqe_midpath_info midpath_info;
+	/* Unsolicited packet completion information */
+	struct fcoe_unsolic_info unsolic_info;
+	/* Warning completion information (Rec Tov expiration) */
+	struct fcoe_warning_report_entry warn_info;
+};
+
+/*
+ * FCoE CQ element
+ */
+struct fcoe_cqe {
+	__le32 cqe_data;
+	/* The task identifier (OX_ID) to be completed */
+#define FCOE_CQE_TASK_ID_MASK    0xFFFF
+#define FCOE_CQE_TASK_ID_SHIFT   0
+	/*
+	 * The CQE type: 0x0 Indicating on a pending work request completion.
+	 * 0x1 - Indicating on an unsolicited event notification. use enum
+	 * fcoe_cqe_type  (use enum fcoe_cqe_type)
+	 */
+#define FCOE_CQE_CQE_TYPE_MASK   0xF
+#define FCOE_CQE_CQE_TYPE_SHIFT  16
+#define FCOE_CQE_RESERVED0_MASK  0xFFF
+#define FCOE_CQE_RESERVED0_SHIFT 20
+	__le16 reserved1;
+	__le16 fw_cq_prod;
+	union fcoe_cqe_info cqe_info;
+};
+
+/*
+ * FCoE CQE type
+ */
+enum fcoe_cqe_type {
+	/* solicited response on a R/W or middle-path SQE */
+	FCOE_GOOD_COMPLETION_CQE_TYPE,
+	FCOE_UNSOLIC_CQE_TYPE /* unsolicited packet, RQ consumed */,
+	FCOE_ERROR_DETECTION_CQE_TYPE /* timer expiration, validation error */,
+	FCOE_WARNING_CQE_TYPE /* rec_tov or rr_tov timer expiration */,
+	FCOE_EXCH_CLEANUP_CQE_TYPE /* task cleanup completed */,
+	FCOE_ABTS_CQE_TYPE /* ABTS received and task cleaned */,
+	FCOE_DUMMY_CQE_TYPE /* just increment SQ CONS */,
+	/* Task was completed wight after sending a pkt to the target */
+	FCOE_LOCAL_COMP_CQE_TYPE,
+	MAX_FCOE_CQE_TYPE
+};
+
+
+/*
+ * FCoE device type
+ */
+enum fcoe_device_type {
+	FCOE_TASK_DEV_TYPE_DISK,
+	FCOE_TASK_DEV_TYPE_TAPE,
+	MAX_FCOE_DEVICE_TYPE
+};
+
+
+
+
+/*
+ * FCoE fast path error codes
+ */
+enum fcoe_fp_error_warning_code {
+	FCOE_ERROR_CODE_XFER_OOO_RO /* XFER error codes */,
+	FCOE_ERROR_CODE_XFER_RO_NOT_ALIGNED,
+	FCOE_ERROR_CODE_XFER_NULL_BURST_LEN,
+	FCOE_ERROR_CODE_XFER_RO_GREATER_THAN_DATA2TRNS,
+	FCOE_ERROR_CODE_XFER_INVALID_PAYLOAD_SIZE,
+	FCOE_ERROR_CODE_XFER_TASK_TYPE_NOT_WRITE,
+	FCOE_ERROR_CODE_XFER_PEND_XFER_SET,
+	FCOE_ERROR_CODE_XFER_OPENED_SEQ,
+	FCOE_ERROR_CODE_XFER_FCTL,
+	FCOE_ERROR_CODE_FCP_RSP_BIDI_FLAGS_SET /* FCP RSP error codes */,
+	FCOE_ERROR_CODE_FCP_RSP_INVALID_LENGTH_FIELD,
+	FCOE_ERROR_CODE_FCP_RSP_INVALID_SNS_FIELD,
+	FCOE_ERROR_CODE_FCP_RSP_INVALID_PAYLOAD_SIZE,
+	FCOE_ERROR_CODE_FCP_RSP_PEND_XFER_SET,
+	FCOE_ERROR_CODE_FCP_RSP_OPENED_SEQ,
+	FCOE_ERROR_CODE_FCP_RSP_FCTL,
+	FCOE_ERROR_CODE_FCP_RSP_LAST_SEQ_RESET,
+	FCOE_ERROR_CODE_FCP_RSP_CONF_REQ_NOT_SUPPORTED_YET,
+	FCOE_ERROR_CODE_DATA_OOO_RO /* FCP DATA error codes */,
+	FCOE_ERROR_CODE_DATA_EXCEEDS_DEFINED_MAX_FRAME_SIZE,
+	FCOE_ERROR_CODE_DATA_EXCEEDS_DATA2TRNS,
+	FCOE_ERROR_CODE_DATA_SOFI3_SEQ_ACTIVE_SET,
+	FCOE_ERROR_CODE_DATA_SOFN_SEQ_ACTIVE_RESET,
+	FCOE_ERROR_CODE_DATA_EOFN_END_SEQ_SET,
+	FCOE_ERROR_CODE_DATA_EOFT_END_SEQ_RESET,
+	FCOE_ERROR_CODE_DATA_TASK_TYPE_NOT_READ,
+	FCOE_ERROR_CODE_DATA_FCTL_INITIATIR,
+	FCOE_ERROR_CODE_MIDPATH_INVALID_TYPE /* Middle path error codes */,
+	FCOE_ERROR_CODE_MIDPATH_SOFI3_SEQ_ACTIVE_SET,
+	FCOE_ERROR_CODE_MIDPATH_SOFN_SEQ_ACTIVE_RESET,
+	FCOE_ERROR_CODE_MIDPATH_EOFN_END_SEQ_SET,
+	FCOE_ERROR_CODE_MIDPATH_EOFT_END_SEQ_RESET,
+	FCOE_ERROR_CODE_MIDPATH_REPLY_FCTL,
+	FCOE_ERROR_CODE_MIDPATH_INVALID_REPLY,
+	FCOE_ERROR_CODE_MIDPATH_ELS_REPLY_RCTL,
+	FCOE_ERROR_CODE_COMMON_MIDDLE_FRAME_WITH_PAD /* Common error codes */,
+	FCOE_ERROR_CODE_COMMON_SEQ_INIT_IN_TCE,
+	FCOE_ERROR_CODE_COMMON_FC_HDR_RX_ID_MISMATCH,
+	FCOE_ERROR_CODE_COMMON_INCORRECT_SEQ_CNT,
+	FCOE_ERROR_CODE_COMMON_DATA_FC_HDR_FCP_TYPE_MISMATCH,
+	FCOE_ERROR_CODE_COMMON_DATA_NO_MORE_SGES,
+	FCOE_ERROR_CODE_COMMON_OPTIONAL_FC_HDR,
+	FCOE_ERROR_CODE_COMMON_READ_TCE_OX_ID_TOO_BIG,
+	FCOE_ERROR_CODE_COMMON_DATA_WAS_NOT_TRANSMITTED,
+	FCOE_ERROR_CODE_COMMON_TASK_DDF_RCTL_INFO_FIELD,
+	FCOE_ERROR_CODE_COMMON_TASK_INVALID_RCTL,
+	FCOE_ERROR_CODE_COMMON_TASK_RCTL_GENERAL_MISMATCH,
+	FCOE_ERROR_CODE_E_D_TOV_TIMER_EXPIRATION /* Timer error codes */,
+	FCOE_WARNING_CODE_REC_TOV_TIMER_EXPIRATION /* Timer error codes */,
+	FCOE_ERROR_CODE_RR_TOV_TIMER_EXPIRATION /* Timer error codes */,
+	/* ABTSrsp pckt arrived unexpected */
+	FCOE_ERROR_CODE_ABTS_REPLY_UNEXPECTED,
+	FCOE_ERROR_CODE_TARGET_MODE_FCP_RSP,
+	FCOE_ERROR_CODE_TARGET_MODE_FCP_XFER,
+	FCOE_ERROR_CODE_TARGET_MODE_DATA_TASK_TYPE_NOT_WRITE,
+	FCOE_ERROR_CODE_DATA_FCTL_TARGET,
+	FCOE_ERROR_CODE_TARGET_DATA_SIZE_NO_MATCH_XFER,
+	FCOE_ERROR_CODE_TARGET_DIF_CRC_CHECKSUM_ERROR,
+	FCOE_ERROR_CODE_TARGET_DIF_REF_TAG_ERROR,
+	FCOE_ERROR_CODE_TARGET_DIF_APP_TAG_ERROR,
+	MAX_FCOE_FP_ERROR_WARNING_CODE
+};
+
+
+/*
+ * FCoE RESPQ element
+ */
+struct fcoe_respqe {
+	__le16 ox_id /* OX_ID that is located in the FCP_RSP FC header */;
+	__le16 rx_id /* RX_ID that is located in the FCP_RSP FC header */;
+	__le32 additional_info;
+/* PARAM that is located in the FCP_RSP FC header */
+#define FCOE_RESPQE_PARAM_MASK            0xFFFFFF
+#define FCOE_RESPQE_PARAM_SHIFT           0
+/* Indication whther its Target-auto-rsp mode or not */
+#define FCOE_RESPQE_TARGET_AUTO_RSP_MASK  0xFF
+#define FCOE_RESPQE_TARGET_AUTO_RSP_SHIFT 24
+};
+
+
+/*
+ * FCoE slow path error codes
+ */
+enum fcoe_sp_error_code {
+	/* Error codes for Error Reporting in slow path flows */
+	FCOE_ERROR_CODE_SLOW_PATH_TOO_MANY_FUNCS,
+	FCOE_ERROR_SLOW_PATH_CODE_NO_LICENSE,
+	MAX_FCOE_SP_ERROR_CODE
+};
+
+
+/*
+ * FCoE SQE request type
+ */
+enum fcoe_sqe_request_type {
+	SEND_FCOE_CMD,
+	SEND_FCOE_MIDPATH,
+	SEND_FCOE_ABTS_REQUEST,
+	FCOE_EXCHANGE_CLEANUP,
+	FCOE_SEQUENCE_RECOVERY,
+	SEND_FCOE_XFER_RDY,
+	SEND_FCOE_RSP,
+	SEND_FCOE_RSP_WITH_SENSE_DATA,
+	SEND_FCOE_TARGET_DATA,
+	SEND_FCOE_INITIATOR_DATA,
+	/*
+	 * Xfer Continuation (==1) ready to be sent. Previous XFERs data
+	 * received successfully.
+	 */
+	SEND_FCOE_XFER_CONTINUATION_RDY,
+	SEND_FCOE_TARGET_ABTS_RSP,
+	MAX_FCOE_SQE_REQUEST_TYPE
+};
+
+
+/*
+ * FCoE task TX state
+ */
+enum fcoe_task_tx_state {
+	/* Initiate state after driver has initialized the task */
+	FCOE_TASK_TX_STATE_NORMAL,
+	/* Updated by TX path after complete transmitting unsolicited packet */
+	FCOE_TASK_TX_STATE_UNSOLICITED_COMPLETED,
+	/*
+	 * Updated by TX path after start processing the task requesting the
+	 * cleanup/abort operation
+	 */
+	FCOE_TASK_TX_STATE_CLEAN_REQ,
+	FCOE_TASK_TX_STATE_ABTS /* Updated by TX path during abort procedure */,
+	/* Updated by TX path during exchange cleanup procedure */
+	FCOE_TASK_TX_STATE_EXCLEANUP,
+	/*
+	 * Updated by TX path during exchange cleanup continuation task
+	 * procedure
+	 */
+	FCOE_TASK_TX_STATE_EXCLEANUP_TARGET_WRITE_CONT,
+	/* Updated by TX path during exchange cleanup first xfer procedure */
+	FCOE_TASK_TX_STATE_EXCLEANUP_TARGET_WRITE,
+	/* Updated by TX path during exchange cleanup read task in Target */
+	FCOE_TASK_TX_STATE_EXCLEANUP_TARGET_READ_OR_RSP,
+	/* Updated by TX path during target exchange cleanup procedure */
+	FCOE_TASK_TX_STATE_EXCLEANUP_TARGET_WRITE_LAST_CYCLE,
+	/* Updated by TX path during sequence recovery procedure */
+	FCOE_TASK_TX_STATE_SEQRECOVERY,
+	MAX_FCOE_TASK_TX_STATE
+};
+
+
+/*
+ * FCoE task type
+ */
+enum fcoe_task_type {
+	FCOE_TASK_TYPE_WRITE_INITIATOR,
+	FCOE_TASK_TYPE_READ_INITIATOR,
+	FCOE_TASK_TYPE_MIDPATH,
+	FCOE_TASK_TYPE_UNSOLICITED,
+	FCOE_TASK_TYPE_ABTS,
+	FCOE_TASK_TYPE_EXCHANGE_CLEANUP,
+	FCOE_TASK_TYPE_SEQUENCE_CLEANUP,
+	FCOE_TASK_TYPE_WRITE_TARGET,
+	FCOE_TASK_TYPE_READ_TARGET,
+	FCOE_TASK_TYPE_RSP,
+	FCOE_TASK_TYPE_RSP_SENSE_DATA,
+	FCOE_TASK_TYPE_ABTS_TARGET,
+	FCOE_TASK_TYPE_ENUM_SIZE,
+	MAX_FCOE_TASK_TYPE
+};
+
+struct scsi_glbl_queue_entry {
+	/* Start physical address for the RQ (receive queue) PBL. */
+	struct regpair rq_pbl_addr;
+	/* Start physical address for the CQ (completion queue) PBL. */
+	struct regpair cq_pbl_addr;
+	/* Start physical address for the CMDQ (command queue) PBL. */
+	struct regpair cmdq_pbl_addr;
+};
+
+#endif /* __QEDF_HSI__ */
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
new file mode 100644
index 000000000000..486c045ac8bb
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -0,0 +1,2282 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include "qedf.h"
+#include <scsi/scsi_tcq.h>
+
+void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
+	unsigned int timer_msec)
+{
+	queue_delayed_work(qedf->timer_work_queue, &io_req->timeout_work,
+	    msecs_to_jiffies(timer_msec));
+}
+
+static void qedf_cmd_timeout(struct work_struct *work)
+{
+
+	struct qedf_ioreq *io_req =
+	    container_of(work, struct qedf_ioreq, timeout_work.work);
+	struct qedf_ctx *qedf = io_req->fcport->qedf;
+	struct qedf_rport *fcport = io_req->fcport;
+	u8 op = 0;
+
+	switch (io_req->cmd_type) {
+	case QEDF_ABTS:
+		QEDF_ERR((&qedf->dbg_ctx), "ABTS timeout, xid=0x%x.\n",
+		    io_req->xid);
+		/* Cleanup timed out ABTS */
+		qedf_initiate_cleanup(io_req, true);
+		complete(&io_req->abts_done);
+
+		/*
+		 * Need to call kref_put for reference taken when initiate_abts
+		 * was called since abts_compl won't be called now that we've
+		 * cleaned up the task.
+		 */
+		kref_put(&io_req->refcount, qedf_release_cmd);
+
+		/*
+		 * Now that the original I/O and the ABTS are complete see
+		 * if we need to reconnect to the target.
+		 */
+		qedf_restart_rport(fcport);
+		break;
+	case QEDF_ELS:
+		kref_get(&io_req->refcount);
+		/*
+		 * Don't attempt to clean an ELS timeout as any subseqeunt
+		 * ABTS or cleanup requests just hang.  For now just free
+		 * the resources of the original I/O and the RRQ
+		 */
+		QEDF_ERR(&(qedf->dbg_ctx), "ELS timeout, xid=0x%x.\n",
+			  io_req->xid);
+		io_req->event = QEDF_IOREQ_EV_ELS_TMO;
+		/* Call callback function to complete command */
+		if (io_req->cb_func && io_req->cb_arg) {
+			op = io_req->cb_arg->op;
+			io_req->cb_func(io_req->cb_arg);
+			io_req->cb_arg = NULL;
+		}
+		qedf_initiate_cleanup(io_req, true);
+		kref_put(&io_req->refcount, qedf_release_cmd);
+		break;
+	case QEDF_SEQ_CLEANUP:
+		QEDF_ERR(&(qedf->dbg_ctx), "Sequence cleanup timeout, "
+		    "xid=0x%x.\n", io_req->xid);
+		qedf_initiate_cleanup(io_req, true);
+		io_req->event = QEDF_IOREQ_EV_ELS_TMO;
+		qedf_process_seq_cleanup_compl(qedf, NULL, io_req);
+		break;
+	default:
+		break;
+	}
+}
+
+void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr)
+{
+	struct io_bdt *bdt_info;
+	struct qedf_ctx *qedf = cmgr->qedf;
+	size_t bd_tbl_sz;
+	u16 min_xid = QEDF_MIN_XID;
+	u16 max_xid = (FCOE_PARAMS_NUM_TASKS - 1);
+	int num_ios;
+	int i;
+	struct qedf_ioreq *io_req;
+
+	num_ios = max_xid - min_xid + 1;
+
+	/* Free fcoe_bdt_ctx structures */
+	if (!cmgr->io_bdt_pool)
+		goto free_cmd_pool;
+
+	bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge);
+	for (i = 0; i < num_ios; i++) {
+		bdt_info = cmgr->io_bdt_pool[i];
+		if (bdt_info->bd_tbl) {
+			dma_free_coherent(&qedf->pdev->dev, bd_tbl_sz,
+			    bdt_info->bd_tbl, bdt_info->bd_tbl_dma);
+			bdt_info->bd_tbl = NULL;
+		}
+	}
+
+	/* Destroy io_bdt pool */
+	for (i = 0; i < num_ios; i++) {
+		kfree(cmgr->io_bdt_pool[i]);
+		cmgr->io_bdt_pool[i] = NULL;
+	}
+
+	kfree(cmgr->io_bdt_pool);
+	cmgr->io_bdt_pool = NULL;
+
+free_cmd_pool:
+
+	for (i = 0; i < num_ios; i++) {
+		io_req = &cmgr->cmds[i];
+		/* Make sure we free per command sense buffer */
+		if (io_req->sense_buffer)
+			dma_free_coherent(&qedf->pdev->dev,
+			    QEDF_SCSI_SENSE_BUFFERSIZE, io_req->sense_buffer,
+			    io_req->sense_buffer_dma);
+		cancel_delayed_work_sync(&io_req->rrq_work);
+	}
+
+	/* Free command manager itself */
+	vfree(cmgr);
+}
+
+static void qedf_handle_rrq(struct work_struct *work)
+{
+	struct qedf_ioreq *io_req =
+	    container_of(work, struct qedf_ioreq, rrq_work.work);
+
+	qedf_send_rrq(io_req);
+
+}
+
+struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
+{
+	struct qedf_cmd_mgr *cmgr;
+	struct io_bdt *bdt_info;
+	struct qedf_ioreq *io_req;
+	u16 xid;
+	int i;
+	int num_ios;
+	u16 min_xid = QEDF_MIN_XID;
+	u16 max_xid = (FCOE_PARAMS_NUM_TASKS - 1);
+
+	/* Make sure num_queues is already set before calling this function */
+	if (!qedf->num_queues) {
+		QEDF_ERR(&(qedf->dbg_ctx), "num_queues is not set.\n");
+		return NULL;
+	}
+
+	if (max_xid <= min_xid || max_xid == FC_XID_UNKNOWN) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Invalid min_xid 0x%x and "
+			   "max_xid 0x%x.\n", min_xid, max_xid);
+		return NULL;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "min xid 0x%x, max xid "
+		   "0x%x.\n", min_xid, max_xid);
+
+	num_ios = max_xid - min_xid + 1;
+
+	cmgr = vzalloc(sizeof(struct qedf_cmd_mgr));
+	if (!cmgr) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc cmd mgr.\n");
+		return NULL;
+	}
+
+	cmgr->qedf = qedf;
+	spin_lock_init(&cmgr->lock);
+
+	/*
+	 * Initialize list of qedf_ioreq.
+	 */
+	xid = QEDF_MIN_XID;
+
+	for (i = 0; i < num_ios; i++) {
+		io_req = &cmgr->cmds[i];
+		INIT_DELAYED_WORK(&io_req->timeout_work, qedf_cmd_timeout);
+
+		io_req->xid = xid++;
+
+		INIT_DELAYED_WORK(&io_req->rrq_work, qedf_handle_rrq);
+
+		/* Allocate DMA memory to hold sense buffer */
+		io_req->sense_buffer = dma_alloc_coherent(&qedf->pdev->dev,
+		    QEDF_SCSI_SENSE_BUFFERSIZE, &io_req->sense_buffer_dma,
+		    GFP_KERNEL);
+		if (!io_req->sense_buffer)
+			goto mem_err;
+	}
+
+	/* Allocate pool of io_bdts - one for each qedf_ioreq */
+	cmgr->io_bdt_pool = kmalloc_array(num_ios, sizeof(struct io_bdt *),
+	    GFP_KERNEL);
+
+	if (!cmgr->io_bdt_pool) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc io_bdt_pool.\n");
+		goto mem_err;
+	}
+
+	for (i = 0; i < num_ios; i++) {
+		cmgr->io_bdt_pool[i] = kmalloc(sizeof(struct io_bdt),
+		    GFP_KERNEL);
+		if (!cmgr->io_bdt_pool[i]) {
+			QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
+				   "io_bdt_pool[%d].\n", i);
+			goto mem_err;
+		}
+	}
+
+	for (i = 0; i < num_ios; i++) {
+		bdt_info = cmgr->io_bdt_pool[i];
+		bdt_info->bd_tbl = dma_alloc_coherent(&qedf->pdev->dev,
+		    QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge),
+		    &bdt_info->bd_tbl_dma, GFP_KERNEL);
+		if (!bdt_info->bd_tbl) {
+			QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
+				   "bdt_tbl[%d].\n", i);
+			goto mem_err;
+		}
+	}
+	atomic_set(&cmgr->free_list_cnt, num_ios);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+	    "cmgr->free_list_cnt=%d.\n",
+	    atomic_read(&cmgr->free_list_cnt));
+
+	return cmgr;
+
+mem_err:
+	qedf_cmd_mgr_free(cmgr);
+	return NULL;
+}
+
+struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type)
+{
+	struct qedf_ctx *qedf = fcport->qedf;
+	struct qedf_cmd_mgr *cmd_mgr = qedf->cmd_mgr;
+	struct qedf_ioreq *io_req = NULL;
+	struct io_bdt *bd_tbl;
+	u16 xid;
+	uint32_t free_sqes;
+	int i;
+	unsigned long flags;
+
+	free_sqes = atomic_read(&fcport->free_sqes);
+
+	if (!free_sqes) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Returning NULL, free_sqes=%d.\n ",
+		    free_sqes);
+		goto out_failed;
+	}
+
+	/* Limit the number of outstanding R/W tasks */
+	if ((atomic_read(&fcport->num_active_ios) >=
+	    NUM_RW_TASKS_PER_CONNECTION)) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Returning NULL, num_active_ios=%d.\n",
+		    atomic_read(&fcport->num_active_ios));
+		goto out_failed;
+	}
+
+	/* Limit global TIDs certain tasks */
+	if (atomic_read(&cmd_mgr->free_list_cnt) <= GBL_RSVD_TASKS) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Returning NULL, free_list_cnt=%d.\n",
+		    atomic_read(&cmd_mgr->free_list_cnt));
+		goto out_failed;
+	}
+
+	spin_lock_irqsave(&cmd_mgr->lock, flags);
+	for (i = 0; i < FCOE_PARAMS_NUM_TASKS; i++) {
+		io_req = &cmd_mgr->cmds[cmd_mgr->idx];
+		cmd_mgr->idx++;
+		if (cmd_mgr->idx == FCOE_PARAMS_NUM_TASKS)
+			cmd_mgr->idx = 0;
+
+		/* Check to make sure command was previously freed */
+		if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags))
+			break;
+	}
+
+	if (i == FCOE_PARAMS_NUM_TASKS) {
+		spin_unlock_irqrestore(&cmd_mgr->lock, flags);
+		goto out_failed;
+	}
+
+	set_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+	spin_unlock_irqrestore(&cmd_mgr->lock, flags);
+
+	atomic_inc(&fcport->num_active_ios);
+	atomic_dec(&fcport->free_sqes);
+	xid = io_req->xid;
+	atomic_dec(&cmd_mgr->free_list_cnt);
+
+	io_req->cmd_mgr = cmd_mgr;
+	io_req->fcport = fcport;
+
+	/* Hold the io_req against deletion */
+	kref_init(&io_req->refcount);
+
+	/* Bind io_bdt for this io_req */
+	/* Have a static link between io_req and io_bdt_pool */
+	bd_tbl = io_req->bd_tbl = cmd_mgr->io_bdt_pool[xid];
+	if (bd_tbl == NULL) {
+		QEDF_ERR(&(qedf->dbg_ctx), "bd_tbl is NULL, xid=%x.\n", xid);
+		kref_put(&io_req->refcount, qedf_release_cmd);
+		goto out_failed;
+	}
+	bd_tbl->io_req = io_req;
+	io_req->cmd_type = cmd_type;
+
+	/* Reset sequence offset data */
+	io_req->rx_buf_off = 0;
+	io_req->tx_buf_off = 0;
+	io_req->rx_id = 0xffff; /* No OX_ID */
+
+	return io_req;
+
+out_failed:
+	/* Record failure for stats and return NULL to caller */
+	qedf->alloc_failures++;
+	return NULL;
+}
+
+static void qedf_free_mp_resc(struct qedf_ioreq *io_req)
+{
+	struct qedf_mp_req *mp_req = &(io_req->mp_req);
+	struct qedf_ctx *qedf = io_req->fcport->qedf;
+	uint64_t sz = sizeof(struct fcoe_sge);
+
+	/* clear tm flags */
+	mp_req->tm_flags = 0;
+	if (mp_req->mp_req_bd) {
+		dma_free_coherent(&qedf->pdev->dev, sz,
+		    mp_req->mp_req_bd, mp_req->mp_req_bd_dma);
+		mp_req->mp_req_bd = NULL;
+	}
+	if (mp_req->mp_resp_bd) {
+		dma_free_coherent(&qedf->pdev->dev, sz,
+		    mp_req->mp_resp_bd, mp_req->mp_resp_bd_dma);
+		mp_req->mp_resp_bd = NULL;
+	}
+	if (mp_req->req_buf) {
+		dma_free_coherent(&qedf->pdev->dev, QEDF_PAGE_SIZE,
+		    mp_req->req_buf, mp_req->req_buf_dma);
+		mp_req->req_buf = NULL;
+	}
+	if (mp_req->resp_buf) {
+		dma_free_coherent(&qedf->pdev->dev, QEDF_PAGE_SIZE,
+		    mp_req->resp_buf, mp_req->resp_buf_dma);
+		mp_req->resp_buf = NULL;
+	}
+}
+
+void qedf_release_cmd(struct kref *ref)
+{
+	struct qedf_ioreq *io_req =
+	    container_of(ref, struct qedf_ioreq, refcount);
+	struct qedf_cmd_mgr *cmd_mgr = io_req->cmd_mgr;
+	struct qedf_rport *fcport = io_req->fcport;
+
+	if (io_req->cmd_type == QEDF_ELS ||
+	    io_req->cmd_type == QEDF_TASK_MGMT_CMD)
+		qedf_free_mp_resc(io_req);
+
+	atomic_inc(&cmd_mgr->free_list_cnt);
+	atomic_dec(&fcport->num_active_ios);
+	if (atomic_read(&fcport->num_active_ios) < 0)
+		QEDF_WARN(&(fcport->qedf->dbg_ctx), "active_ios < 0.\n");
+
+	/* Increment task retry identifier now that the request is released */
+	io_req->task_retry_identifier++;
+
+	clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+}
+
+static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
+	int bd_index)
+{
+	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	int frag_size, sg_frags;
+
+	sg_frags = 0;
+	while (sg_len) {
+		if (sg_len > QEDF_BD_SPLIT_SZ)
+			frag_size = QEDF_BD_SPLIT_SZ;
+		else
+			frag_size = sg_len;
+		bd[bd_index + sg_frags].sge_addr.lo = U64_LO(addr);
+		bd[bd_index + sg_frags].sge_addr.hi = U64_HI(addr);
+		bd[bd_index + sg_frags].size = (uint16_t)frag_size;
+
+		addr += (u64)frag_size;
+		sg_frags++;
+		sg_len -= frag_size;
+	}
+	return sg_frags;
+}
+
+static int qedf_map_sg(struct qedf_ioreq *io_req)
+{
+	struct scsi_cmnd *sc = io_req->sc_cmd;
+	struct Scsi_Host *host = sc->device->host;
+	struct fc_lport *lport = shost_priv(host);
+	struct qedf_ctx *qedf = lport_priv(lport);
+	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	struct scatterlist *sg;
+	int byte_count = 0;
+	int sg_count = 0;
+	int bd_count = 0;
+	int sg_frags;
+	unsigned int sg_len;
+	u64 addr, end_addr;
+	int i;
+
+	sg_count = dma_map_sg(&qedf->pdev->dev, scsi_sglist(sc),
+	    scsi_sg_count(sc), sc->sc_data_direction);
+
+	sg = scsi_sglist(sc);
+
+	/*
+	 * New condition to send single SGE as cached-SGL with length less
+	 * than 64k.
+	 */
+	if ((sg_count == 1) && (sg_dma_len(sg) <=
+	    QEDF_MAX_SGLEN_FOR_CACHESGL)) {
+		sg_len = sg_dma_len(sg);
+		addr = (u64)sg_dma_address(sg);
+
+		bd[bd_count].sge_addr.lo = (addr & 0xffffffff);
+		bd[bd_count].sge_addr.hi = (addr >> 32);
+		bd[bd_count].size = (u16)sg_len;
+
+		return ++bd_count;
+	}
+
+	scsi_for_each_sg(sc, sg, sg_count, i) {
+		sg_len = sg_dma_len(sg);
+		addr = (u64)sg_dma_address(sg);
+		end_addr = (u64)(addr + sg_len);
+
+		/*
+		 * First s/g element in the list so check if the end_addr
+		 * is paged aligned. Also check to make sure the length is
+		 * at least page size.
+		 */
+		if ((i == 0) && (sg_count > 1) &&
+		    ((end_addr % QEDF_PAGE_SIZE) ||
+		    sg_len < QEDF_PAGE_SIZE))
+			io_req->use_slowpath = true;
+		/*
+		 * Last s/g element so check if the start address is paged
+		 * aligned.
+		 */
+		else if ((i == (sg_count - 1)) && (sg_count > 1) &&
+		    (addr % QEDF_PAGE_SIZE))
+			io_req->use_slowpath = true;
+		/*
+		 * Intermediate s/g element so check if start and end address
+		 * is page aligned.
+		 */
+		else if ((i != 0) && (i != (sg_count - 1)) &&
+		    ((addr % QEDF_PAGE_SIZE) || (end_addr % QEDF_PAGE_SIZE)))
+			io_req->use_slowpath = true;
+
+		if (sg_len > QEDF_MAX_BD_LEN) {
+			sg_frags = qedf_split_bd(io_req, addr, sg_len,
+			    bd_count);
+		} else {
+			sg_frags = 1;
+			bd[bd_count].sge_addr.lo = U64_LO(addr);
+			bd[bd_count].sge_addr.hi  = U64_HI(addr);
+			bd[bd_count].size = (uint16_t)sg_len;
+		}
+
+		bd_count += sg_frags;
+		byte_count += sg_len;
+	}
+
+	if (byte_count != scsi_bufflen(sc))
+		QEDF_ERR(&(qedf->dbg_ctx), "byte_count = %d != "
+			  "scsi_bufflen = %d, task_id = 0x%x.\n", byte_count,
+			   scsi_bufflen(sc), io_req->xid);
+
+	return bd_count;
+}
+
+static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req)
+{
+	struct scsi_cmnd *sc = io_req->sc_cmd;
+	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	int bd_count;
+
+	if (scsi_sg_count(sc)) {
+		bd_count = qedf_map_sg(io_req);
+		if (bd_count == 0)
+			return -ENOMEM;
+	} else {
+		bd_count = 0;
+		bd[0].sge_addr.lo = bd[0].sge_addr.hi = 0;
+		bd[0].size = 0;
+	}
+	io_req->bd_tbl->bd_valid = bd_count;
+
+	return 0;
+}
+
+static void qedf_build_fcp_cmnd(struct qedf_ioreq *io_req,
+				  struct fcp_cmnd *fcp_cmnd)
+{
+	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
+
+	/* fcp_cmnd is 32 bytes */
+	memset(fcp_cmnd, 0, FCP_CMND_LEN);
+
+	/* 8 bytes: SCSI LUN info */
+	int_to_scsilun(sc_cmd->device->lun,
+			(struct scsi_lun *)&fcp_cmnd->fc_lun);
+
+	/* 4 bytes: flag info */
+	fcp_cmnd->fc_pri_ta = 0;
+	fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags;
+	fcp_cmnd->fc_flags = io_req->io_req_flags;
+	fcp_cmnd->fc_cmdref = 0;
+
+	/* Populate data direction */
+	if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
+		fcp_cmnd->fc_flags |= FCP_CFL_WRDATA;
+	else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE)
+		fcp_cmnd->fc_flags |= FCP_CFL_RDDATA;
+
+	fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
+
+	/* 16 bytes: CDB information */
+	memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
+
+	/* 4 bytes: FCP data length */
+	fcp_cmnd->fc_dl = htonl(io_req->data_xfer_len);
+
+}
+
+static void  qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport,
+	struct qedf_ioreq *io_req, u32 *ptu_invalidate,
+	struct fcoe_task_context *task_ctx)
+{
+	enum fcoe_task_type task_type;
+	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
+	struct io_bdt *bd_tbl = io_req->bd_tbl;
+	union fcoe_data_desc_ctx *data_desc;
+	u32 *fcp_cmnd;
+	u32 tmp_fcp_cmnd[8];
+	int cnt, i;
+	int bd_count;
+	struct qedf_ctx *qedf = fcport->qedf;
+	uint16_t cq_idx = smp_processor_id() % qedf->num_queues;
+	u8 tmp_sgl_mode = 0;
+	u8 mst_sgl_mode = 0;
+
+	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+	io_req->task = task_ctx;
+
+	if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
+		task_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
+	else
+		task_type = FCOE_TASK_TYPE_READ_INITIATOR;
+
+	/* Y Storm context */
+	task_ctx->ystorm_st_context.expect_first_xfer = 1;
+	task_ctx->ystorm_st_context.data_2_trns_rem = io_req->data_xfer_len;
+	/* Check if this is required */
+	task_ctx->ystorm_st_context.ox_id = io_req->xid;
+	task_ctx->ystorm_st_context.task_rety_identifier =
+	    io_req->task_retry_identifier;
+
+	/* T Storm ag context */
+	SET_FIELD(task_ctx->tstorm_ag_context.flags0,
+	    TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, PROTOCOLID_FCOE);
+	task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
+
+	/* T Storm st context */
+	SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
+	    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
+	    1);
+	task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
+
+	task_ctx->tstorm_st_context.read_only.dev_type =
+	    FCOE_TASK_DEV_TYPE_DISK;
+	task_ctx->tstorm_st_context.read_only.conf_supported = 0;
+	task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
+
+	/* Completion queue for response. */
+	task_ctx->tstorm_st_context.read_only.glbl_q_num = cq_idx;
+	task_ctx->tstorm_st_context.read_only.fcp_cmd_trns_size =
+	    io_req->data_xfer_len;
+	task_ctx->tstorm_st_context.read_write.e_d_tov_exp_timeout_val =
+	    lport->e_d_tov;
+
+	task_ctx->ustorm_ag_context.global_cq_num = cq_idx;
+	io_req->fp_idx = cq_idx;
+
+	bd_count = bd_tbl->bd_valid;
+	if (task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) {
+		/* Setup WRITE task */
+		struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
+
+		task_ctx->ystorm_st_context.task_type =
+		    FCOE_TASK_TYPE_WRITE_INITIATOR;
+		data_desc = &task_ctx->ystorm_st_context.data_desc;
+
+		if (io_req->use_slowpath) {
+			SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
+			    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+			    FCOE_SLOW_SGL);
+			data_desc->slow.base_sgl_addr.lo =
+			    U64_LO(bd_tbl->bd_tbl_dma);
+			data_desc->slow.base_sgl_addr.hi =
+			    U64_HI(bd_tbl->bd_tbl_dma);
+			data_desc->slow.remainder_num_sges = bd_count;
+			data_desc->slow.curr_sge_off = 0;
+			data_desc->slow.curr_sgl_index = 0;
+			qedf->slow_sge_ios++;
+			io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+		} else {
+			SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
+			    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+			    (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
+			    FCOE_MUL_FAST_SGES);
+
+			if (bd_count == 1) {
+				data_desc->single_sge.sge_addr.lo =
+				    fcoe_bd_tbl->sge_addr.lo;
+				data_desc->single_sge.sge_addr.hi =
+				    fcoe_bd_tbl->sge_addr.hi;
+				data_desc->single_sge.size =
+				    fcoe_bd_tbl->size;
+				data_desc->single_sge.is_valid_sge = 0;
+				qedf->single_sge_ios++;
+				io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
+			} else {
+				data_desc->fast.sgl_start_addr.lo =
+				    U64_LO(bd_tbl->bd_tbl_dma);
+				data_desc->fast.sgl_start_addr.hi =
+				    U64_HI(bd_tbl->bd_tbl_dma);
+				data_desc->fast.sgl_byte_offset =
+				    data_desc->fast.sgl_start_addr.lo &
+				    (QEDF_PAGE_SIZE - 1);
+				if (data_desc->fast.sgl_byte_offset > 0)
+					QEDF_ERR(&(qedf->dbg_ctx),
+					    "byte_offset=%u for xid=0x%x.\n",
+					    io_req->xid,
+					    data_desc->fast.sgl_byte_offset);
+				data_desc->fast.task_reuse_cnt =
+				    io_req->reuse_count;
+				io_req->reuse_count++;
+				if (io_req->reuse_count == QEDF_MAX_REUSE) {
+					*ptu_invalidate = 1;
+					io_req->reuse_count = 0;
+				}
+				qedf->fast_sge_ios++;
+				io_req->sge_type = QEDF_IOREQ_FAST_SGE;
+			}
+		}
+
+		/* T Storm context */
+		task_ctx->tstorm_st_context.read_only.task_type =
+		    FCOE_TASK_TYPE_WRITE_INITIATOR;
+
+		/* M Storm context */
+		tmp_sgl_mode = GET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
+		    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE);
+		SET_FIELD(task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
+		    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE,
+		    tmp_sgl_mode);
+
+	} else {
+		/* Setup READ task */
+
+		/* M Storm context */
+		struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
+
+		data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
+		task_ctx->mstorm_st_context.fp.data_2_trns_rem =
+		    io_req->data_xfer_len;
+
+		if (io_req->use_slowpath) {
+			SET_FIELD(
+			    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
+			    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
+			    FCOE_SLOW_SGL);
+			data_desc->slow.base_sgl_addr.lo =
+			    U64_LO(bd_tbl->bd_tbl_dma);
+			data_desc->slow.base_sgl_addr.hi =
+			    U64_HI(bd_tbl->bd_tbl_dma);
+			data_desc->slow.remainder_num_sges =
+			    bd_count;
+			data_desc->slow.curr_sge_off = 0;
+			data_desc->slow.curr_sgl_index = 0;
+			qedf->slow_sge_ios++;
+			io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+		} else {
+			SET_FIELD(
+			    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
+			    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
+			    (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
+			    FCOE_MUL_FAST_SGES);
+
+			if (bd_count == 1) {
+				data_desc->single_sge.sge_addr.lo =
+				    fcoe_bd_tbl->sge_addr.lo;
+				data_desc->single_sge.sge_addr.hi =
+				    fcoe_bd_tbl->sge_addr.hi;
+				data_desc->single_sge.size =
+				    fcoe_bd_tbl->size;
+				data_desc->single_sge.is_valid_sge = 0;
+				qedf->single_sge_ios++;
+				io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
+			} else {
+				data_desc->fast.sgl_start_addr.lo =
+				    U64_LO(bd_tbl->bd_tbl_dma);
+				data_desc->fast.sgl_start_addr.hi =
+				    U64_HI(bd_tbl->bd_tbl_dma);
+				data_desc->fast.sgl_byte_offset = 0;
+				data_desc->fast.task_reuse_cnt =
+				    io_req->reuse_count;
+				io_req->reuse_count++;
+				if (io_req->reuse_count == QEDF_MAX_REUSE) {
+					*ptu_invalidate = 1;
+					io_req->reuse_count = 0;
+				}
+				qedf->fast_sge_ios++;
+				io_req->sge_type = QEDF_IOREQ_FAST_SGE;
+			}
+		}
+
+		/* Y Storm context */
+		task_ctx->ystorm_st_context.expect_first_xfer = 0;
+		task_ctx->ystorm_st_context.task_type =
+		    FCOE_TASK_TYPE_READ_INITIATOR;
+
+		/* T Storm context */
+		task_ctx->tstorm_st_context.read_only.task_type =
+		    FCOE_TASK_TYPE_READ_INITIATOR;
+		mst_sgl_mode = GET_FIELD(
+		    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
+		    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE);
+		SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
+		    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE,
+		    mst_sgl_mode);
+	}
+
+	/* fill FCP_CMND IU */
+	fcp_cmnd = (u32 *)task_ctx->ystorm_st_context.tx_info_union.fcp_cmd_payload.opaque;
+	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)&tmp_fcp_cmnd);
+
+	/* Swap fcp_cmnd since FC is big endian */
+	cnt = sizeof(struct fcp_cmnd) / sizeof(u32);
+
+	for (i = 0; i < cnt; i++) {
+		*fcp_cmnd = cpu_to_be32(tmp_fcp_cmnd[i]);
+		fcp_cmnd++;
+	}
+
+	/* M Storm context - Sense buffer */
+	task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
+		U64_LO(io_req->sense_buffer_dma);
+	task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
+		U64_HI(io_req->sense_buffer_dma);
+}
+
+void qedf_init_mp_task(struct qedf_ioreq *io_req,
+	struct fcoe_task_context *task_ctx)
+{
+	struct qedf_mp_req *mp_req = &(io_req->mp_req);
+	struct qedf_rport *fcport = io_req->fcport;
+	struct qedf_ctx *qedf = io_req->fcport->qedf;
+	struct fc_frame_header *fc_hdr;
+	enum fcoe_task_type task_type = 0;
+	union fcoe_data_desc_ctx *data_desc;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Initializing MP task "
+		   "for cmd_type = %d\n", io_req->cmd_type);
+
+	qedf->control_requests++;
+
+	/* Obtain task_type */
+	if ((io_req->cmd_type == QEDF_TASK_MGMT_CMD) ||
+	    (io_req->cmd_type == QEDF_ELS)) {
+		task_type = FCOE_TASK_TYPE_MIDPATH;
+	} else if (io_req->cmd_type == QEDF_ABTS) {
+		task_type = FCOE_TASK_TYPE_ABTS;
+	}
+
+	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+
+	/* Setup the task from io_req for easy reference */
+	io_req->task = task_ctx;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "task type = %d\n",
+		   task_type);
+
+	/* YSTORM only */
+	{
+		/* Initialize YSTORM task context */
+		struct fcoe_tx_mid_path_params *task_fc_hdr =
+		    &task_ctx->ystorm_st_context.tx_info_union.tx_params.mid_path;
+		memset(task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params));
+		task_ctx->ystorm_st_context.task_rety_identifier =
+		    io_req->task_retry_identifier;
+
+		/* Init SGL parameters */
+		if ((task_type == FCOE_TASK_TYPE_MIDPATH) ||
+		    (task_type == FCOE_TASK_TYPE_UNSOLICITED)) {
+			data_desc = &task_ctx->ystorm_st_context.data_desc;
+			data_desc->slow.base_sgl_addr.lo =
+			    U64_LO(mp_req->mp_req_bd_dma);
+			data_desc->slow.base_sgl_addr.hi =
+			    U64_HI(mp_req->mp_req_bd_dma);
+			data_desc->slow.remainder_num_sges = 1;
+			data_desc->slow.curr_sge_off = 0;
+			data_desc->slow.curr_sgl_index = 0;
+		}
+
+		fc_hdr = &(mp_req->req_fc_hdr);
+		if (task_type == FCOE_TASK_TYPE_MIDPATH) {
+			fc_hdr->fh_ox_id = io_req->xid;
+			fc_hdr->fh_rx_id = htons(0xffff);
+		} else if (task_type == FCOE_TASK_TYPE_UNSOLICITED) {
+			fc_hdr->fh_rx_id = io_req->xid;
+		}
+
+		/* Fill FC Header into middle path buffer */
+		task_fc_hdr->parameter = fc_hdr->fh_parm_offset;
+		task_fc_hdr->r_ctl = fc_hdr->fh_r_ctl;
+		task_fc_hdr->type = fc_hdr->fh_type;
+		task_fc_hdr->cs_ctl = fc_hdr->fh_cs_ctl;
+		task_fc_hdr->df_ctl = fc_hdr->fh_df_ctl;
+		task_fc_hdr->rx_id = fc_hdr->fh_rx_id;
+		task_fc_hdr->ox_id = fc_hdr->fh_ox_id;
+
+		task_ctx->ystorm_st_context.data_2_trns_rem =
+		    io_req->data_xfer_len;
+		task_ctx->ystorm_st_context.task_type = task_type;
+	}
+
+	/* TSTORM ONLY */
+	{
+		task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
+		task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
+		/* Always send middle-path repsonses on CQ #0 */
+		task_ctx->tstorm_st_context.read_only.glbl_q_num = 0;
+		io_req->fp_idx = 0;
+		SET_FIELD(task_ctx->tstorm_ag_context.flags0,
+		    TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE,
+		    PROTOCOLID_FCOE);
+		task_ctx->tstorm_st_context.read_only.task_type = task_type;
+		SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
+		    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
+		    1);
+		task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
+	}
+
+	/* MSTORM only */
+	{
+		if (task_type == FCOE_TASK_TYPE_MIDPATH) {
+			/* Initialize task context */
+			data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
+
+			/* Set cache sges address and length */
+			data_desc->slow.base_sgl_addr.lo =
+			    U64_LO(mp_req->mp_resp_bd_dma);
+			data_desc->slow.base_sgl_addr.hi =
+			    U64_HI(mp_req->mp_resp_bd_dma);
+			data_desc->slow.remainder_num_sges = 1;
+			data_desc->slow.curr_sge_off = 0;
+			data_desc->slow.curr_sgl_index = 0;
+
+			/*
+			 * Also need to fil in non-fastpath response address
+			 * for middle path commands.
+			 */
+			task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
+			    U64_LO(mp_req->mp_resp_bd_dma);
+			task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
+			    U64_HI(mp_req->mp_resp_bd_dma);
+		}
+	}
+
+	/* USTORM ONLY */
+	{
+		task_ctx->ustorm_ag_context.global_cq_num = 0;
+	}
+
+	/* I/O stats. Middle path commands always use slow SGEs */
+	qedf->slow_sge_ios++;
+	io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+}
+
+void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, u32 ptu_invalidate,
+	enum fcoe_task_type req_type, u32 offset)
+{
+	struct fcoe_wqe *sqe;
+	uint16_t total_sqe = (fcport->sq_mem_size)/(sizeof(struct fcoe_wqe));
+
+	sqe = &fcport->sq[fcport->sq_prod_idx];
+
+	fcport->sq_prod_idx++;
+	fcport->fw_sq_prod_idx++;
+	if (fcport->sq_prod_idx == total_sqe)
+		fcport->sq_prod_idx = 0;
+
+	switch (req_type) {
+	case FCOE_TASK_TYPE_WRITE_INITIATOR:
+	case FCOE_TASK_TYPE_READ_INITIATOR:
+		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_CMD);
+		if (ptu_invalidate)
+			SET_FIELD(sqe->flags, FCOE_WQE_INVALIDATE_PTU, 1);
+		break;
+	case FCOE_TASK_TYPE_MIDPATH:
+		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_MIDPATH);
+		break;
+	case FCOE_TASK_TYPE_ABTS:
+		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
+		    SEND_FCOE_ABTS_REQUEST);
+		break;
+	case FCOE_TASK_TYPE_EXCHANGE_CLEANUP:
+		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
+		     FCOE_EXCHANGE_CLEANUP);
+		break;
+	case FCOE_TASK_TYPE_SEQUENCE_CLEANUP:
+		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
+		    FCOE_SEQUENCE_RECOVERY);
+		/* NOTE: offset param only used for sequence recovery */
+		sqe->additional_info_union.seq_rec_updated_offset = offset;
+		break;
+	case FCOE_TASK_TYPE_UNSOLICITED:
+		break;
+	default:
+		break;
+	}
+
+	sqe->task_id = xid;
+
+	/* Make sure SQ data is coherent */
+	wmb();
+
+}
+
+void qedf_ring_doorbell(struct qedf_rport *fcport)
+{
+	struct fcoe_db_data dbell = { 0 };
+
+	dbell.agg_flags = 0;
+
+	dbell.params |= DB_DEST_XCM << FCOE_DB_DATA_DEST_SHIFT;
+	dbell.params |= DB_AGG_CMD_SET << FCOE_DB_DATA_AGG_CMD_SHIFT;
+	dbell.params |= DQ_XCM_FCOE_SQ_PROD_CMD <<
+	    FCOE_DB_DATA_AGG_VAL_SEL_SHIFT;
+
+	dbell.sq_prod = fcport->fw_sq_prod_idx;
+	writel(*(u32 *)&dbell, fcport->p_doorbell);
+	/* Make sure SQ index is updated so f/w prcesses requests in order */
+	wmb();
+	mmiowb();
+}
+
+static void qedf_trace_io(struct qedf_rport *fcport, struct qedf_ioreq *io_req,
+			  int8_t direction)
+{
+	struct qedf_ctx *qedf = fcport->qedf;
+	struct qedf_io_log *io_log;
+	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
+	unsigned long flags;
+	uint8_t op;
+
+	spin_lock_irqsave(&qedf->io_trace_lock, flags);
+
+	io_log = &qedf->io_trace_buf[qedf->io_trace_idx];
+	io_log->direction = direction;
+	io_log->task_id = io_req->xid;
+	io_log->port_id = fcport->rdata->ids.port_id;
+	io_log->lun = sc_cmd->device->lun;
+	io_log->op = op = sc_cmd->cmnd[0];
+	io_log->lba[0] = sc_cmd->cmnd[2];
+	io_log->lba[1] = sc_cmd->cmnd[3];
+	io_log->lba[2] = sc_cmd->cmnd[4];
+	io_log->lba[3] = sc_cmd->cmnd[5];
+	io_log->bufflen = scsi_bufflen(sc_cmd);
+	io_log->sg_count = scsi_sg_count(sc_cmd);
+	io_log->result = sc_cmd->result;
+	io_log->jiffies = jiffies;
+	io_log->refcount = atomic_read(&io_req->refcount.refcount);
+
+	if (direction == QEDF_IO_TRACE_REQ) {
+		/* For requests we only care abot the submission CPU */
+		io_log->req_cpu = io_req->cpu;
+		io_log->int_cpu = 0;
+		io_log->rsp_cpu = 0;
+	} else if (direction == QEDF_IO_TRACE_RSP) {
+		io_log->req_cpu = io_req->cpu;
+		io_log->int_cpu = io_req->int_cpu;
+		io_log->rsp_cpu = smp_processor_id();
+	}
+
+	io_log->sge_type = io_req->sge_type;
+
+	qedf->io_trace_idx++;
+	if (qedf->io_trace_idx == QEDF_IO_TRACE_SIZE)
+		qedf->io_trace_idx = 0;
+
+	spin_unlock_irqrestore(&qedf->io_trace_lock, flags);
+}
+
+int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
+{
+	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
+	struct Scsi_Host *host = sc_cmd->device->host;
+	struct fc_lport *lport = shost_priv(host);
+	struct qedf_ctx *qedf = lport_priv(lport);
+	struct fcoe_task_context *task_ctx;
+	u16 xid;
+	enum fcoe_task_type req_type = 0;
+	u32 ptu_invalidate = 0;
+
+	/* Initialize rest of io_req fileds */
+	io_req->data_xfer_len = scsi_bufflen(sc_cmd);
+	sc_cmd->SCp.ptr = (char *)io_req;
+	io_req->use_slowpath = false; /* Assume fast SGL by default */
+
+	/* Record which cpu this request is associated with */
+	io_req->cpu = smp_processor_id();
+
+	if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) {
+		req_type = FCOE_TASK_TYPE_READ_INITIATOR;
+		io_req->io_req_flags = QEDF_READ;
+		qedf->input_requests++;
+	} else if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
+		req_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
+		io_req->io_req_flags = QEDF_WRITE;
+		qedf->output_requests++;
+	} else {
+		io_req->io_req_flags = 0;
+		qedf->control_requests++;
+	}
+
+	xid = io_req->xid;
+
+	/* Build buffer descriptor list for firmware from sg list */
+	if (qedf_build_bd_list_from_sg(io_req)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "BD list creation failed.\n");
+		kref_put(&io_req->refcount, qedf_release_cmd);
+		return -EAGAIN;
+	}
+
+	/* Get the task context */
+	task_ctx = qedf_get_task_mem(&qedf->tasks, xid);
+	if (!task_ctx) {
+		QEDF_WARN(&(qedf->dbg_ctx), "task_ctx is NULL, xid=%d.\n",
+			   xid);
+		kref_put(&io_req->refcount, qedf_release_cmd);
+		return -EINVAL;
+	}
+
+	qedf_init_task(fcport, lport, io_req, &ptu_invalidate, task_ctx);
+
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
+		kref_put(&io_req->refcount, qedf_release_cmd);
+	}
+
+	/* Obtain free SQ entry */
+	qedf_add_to_sq(fcport, xid, ptu_invalidate, req_type, 0);
+
+	/* Ring doorbell */
+	qedf_ring_doorbell(fcport);
+
+	if (qedf_io_tracing && io_req->sc_cmd)
+		qedf_trace_io(fcport, io_req, QEDF_IO_TRACE_REQ);
+
+	return false;
+}
+
+int
+qedf_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc_cmd)
+{
+	struct fc_lport *lport = shost_priv(host);
+	struct qedf_ctx *qedf = lport_priv(lport);
+	struct fc_rport *rport = starget_to_rport(scsi_target(sc_cmd->device));
+	struct fc_rport_libfc_priv *rp = rport->dd_data;
+	struct qedf_rport *fcport = rport->dd_data;
+	struct qedf_ioreq *io_req;
+	int rc = 0;
+	int rval;
+	unsigned long flags = 0;
+
+
+	if (test_bit(QEDF_UNLOADING, &qedf->flags) ||
+	    test_bit(QEDF_DBG_STOP_IO, &qedf->flags)) {
+		sc_cmd->result = DID_NO_CONNECT << 16;
+		sc_cmd->scsi_done(sc_cmd);
+		return 0;
+	}
+
+	rval = fc_remote_port_chkready(rport);
+	if (rval) {
+		sc_cmd->result = rval;
+		sc_cmd->scsi_done(sc_cmd);
+		return 0;
+	}
+
+	/* Retry command if we are doing a qed drain operation */
+	if (test_bit(QEDF_DRAIN_ACTIVE, &qedf->flags)) {
+		rc = SCSI_MLQUEUE_HOST_BUSY;
+		goto exit_qcmd;
+	}
+
+	if (lport->state != LPORT_ST_READY ||
+	    atomic_read(&qedf->link_state) != QEDF_LINK_UP) {
+		rc = SCSI_MLQUEUE_HOST_BUSY;
+		goto exit_qcmd;
+	}
+
+	/* rport and tgt are allocated together, so tgt should be non-NULL */
+	fcport = (struct qedf_rport *)&rp[1];
+
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		/*
+		 * Session is not offloaded yet. Let SCSI-ml retry
+		 * the command.
+		 */
+		rc = SCSI_MLQUEUE_TARGET_BUSY;
+		goto exit_qcmd;
+	}
+	if (fcport->retry_delay_timestamp) {
+		if (time_after(jiffies, fcport->retry_delay_timestamp)) {
+			fcport->retry_delay_timestamp = 0;
+		} else {
+			/* If retry_delay timer is active, flow off the ML */
+			rc = SCSI_MLQUEUE_TARGET_BUSY;
+			goto exit_qcmd;
+		}
+	}
+
+	io_req = qedf_alloc_cmd(fcport, QEDF_SCSI_CMD);
+	if (!io_req) {
+		rc = SCSI_MLQUEUE_HOST_BUSY;
+		goto exit_qcmd;
+	}
+
+	io_req->sc_cmd = sc_cmd;
+
+	/* Take fcport->rport_lock for posting to fcport send queue */
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+	if (qedf_post_io_req(fcport, io_req)) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Unable to post io_req\n");
+		/* Return SQE to pool */
+		atomic_inc(&fcport->free_sqes);
+		rc = SCSI_MLQUEUE_HOST_BUSY;
+	}
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
+
+exit_qcmd:
+	return rc;
+}
+
+static void qedf_parse_fcp_rsp(struct qedf_ioreq *io_req,
+				 struct fcoe_cqe_rsp_info *fcp_rsp)
+{
+	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
+	struct qedf_ctx *qedf = io_req->fcport->qedf;
+	u8 rsp_flags = fcp_rsp->rsp_flags.flags;
+	int fcp_sns_len = 0;
+	int fcp_rsp_len = 0;
+	uint8_t *rsp_info, *sense_data;
+
+	io_req->fcp_status = FC_GOOD;
+	io_req->fcp_resid = 0;
+	if (rsp_flags & (FCOE_FCP_RSP_FLAGS_FCP_RESID_OVER |
+	    FCOE_FCP_RSP_FLAGS_FCP_RESID_UNDER))
+		io_req->fcp_resid = fcp_rsp->fcp_resid;
+
+	io_req->scsi_comp_flags = rsp_flags;
+	CMD_SCSI_STATUS(sc_cmd) = io_req->cdb_status =
+	    fcp_rsp->scsi_status_code;
+
+	if (rsp_flags &
+	    FCOE_FCP_RSP_FLAGS_FCP_RSP_LEN_VALID)
+		fcp_rsp_len = fcp_rsp->fcp_rsp_len;
+
+	if (rsp_flags &
+	    FCOE_FCP_RSP_FLAGS_FCP_SNS_LEN_VALID)
+		fcp_sns_len = fcp_rsp->fcp_sns_len;
+
+	io_req->fcp_rsp_len = fcp_rsp_len;
+	io_req->fcp_sns_len = fcp_sns_len;
+	rsp_info = sense_data = io_req->sense_buffer;
+
+	/* fetch fcp_rsp_code */
+	if ((fcp_rsp_len == 4) || (fcp_rsp_len == 8)) {
+		/* Only for task management function */
+		io_req->fcp_rsp_code = rsp_info[3];
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "fcp_rsp_code = %d\n", io_req->fcp_rsp_code);
+		/* Adjust sense-data location. */
+		sense_data += fcp_rsp_len;
+	}
+
+	if (fcp_sns_len > SCSI_SENSE_BUFFERSIZE) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Truncating sense buffer\n");
+		fcp_sns_len = SCSI_SENSE_BUFFERSIZE;
+	}
+
+	memset(sc_cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
+	if (fcp_sns_len)
+		memcpy(sc_cmd->sense_buffer, sense_data,
+		    fcp_sns_len);
+}
+
+static void qedf_unmap_sg_list(struct qedf_ctx *qedf, struct qedf_ioreq *io_req)
+{
+	struct scsi_cmnd *sc = io_req->sc_cmd;
+
+	if (io_req->bd_tbl->bd_valid && sc && scsi_sg_count(sc)) {
+		dma_unmap_sg(&qedf->pdev->dev, scsi_sglist(sc),
+		    scsi_sg_count(sc), sc->sc_data_direction);
+		io_req->bd_tbl->bd_valid = 0;
+	}
+}
+
+void qedf_scsi_completion(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req)
+{
+	u16 xid, rval;
+	struct fcoe_task_context *task_ctx;
+	struct scsi_cmnd *sc_cmd;
+	struct fcoe_cqe_rsp_info *fcp_rsp;
+	struct qedf_rport *fcport;
+	int refcount;
+	u16 scope, qualifier = 0;
+	u8 fw_residual_flag = 0;
+
+	if (!io_req)
+		return;
+	if (!cqe)
+		return;
+
+	xid = io_req->xid;
+	task_ctx = qedf_get_task_mem(&qedf->tasks, xid);
+	sc_cmd = io_req->sc_cmd;
+	fcp_rsp = &cqe->cqe_info.rsp_info;
+
+	if (!sc_cmd) {
+		QEDF_WARN(&(qedf->dbg_ctx), "sc_cmd is NULL!\n");
+		return;
+	}
+
+	if (!sc_cmd->SCp.ptr) {
+		QEDF_WARN(&(qedf->dbg_ctx), "SCp.ptr is NULL, returned in "
+		    "another context.\n");
+		return;
+	}
+
+	if (!sc_cmd->request) {
+		QEDF_WARN(&(qedf->dbg_ctx), "sc_cmd->request is NULL, "
+		    "sc_cmd=%p.\n", sc_cmd);
+		return;
+	}
+
+	if (!sc_cmd->request->special) {
+		QEDF_WARN(&(qedf->dbg_ctx), "request->special is NULL so "
+		    "request not valid, sc_cmd=%p.\n", sc_cmd);
+		return;
+	}
+
+	if (!sc_cmd->request->q) {
+		QEDF_WARN(&(qedf->dbg_ctx), "request->q is NULL so request "
+		   "is not valid, sc_cmd=%p.\n", sc_cmd);
+		return;
+	}
+
+	fcport = io_req->fcport;
+
+	qedf_parse_fcp_rsp(io_req, fcp_rsp);
+
+	qedf_unmap_sg_list(qedf, io_req);
+
+	/* Check for FCP transport error */
+	if (io_req->fcp_rsp_len > 3 && io_req->fcp_rsp_code) {
+		QEDF_ERR(&(qedf->dbg_ctx),
+		    "FCP I/O protocol failure xid=0x%x fcp_rsp_len=%d "
+		    "fcp_rsp_code=%d.\n", io_req->xid, io_req->fcp_rsp_len,
+		    io_req->fcp_rsp_code);
+		sc_cmd->result = DID_BUS_BUSY << 16;
+		goto out;
+	}
+
+	fw_residual_flag = GET_FIELD(cqe->cqe_info.rsp_info.fw_error_flags,
+	    FCOE_CQE_RSP_INFO_FW_UNDERRUN);
+	if (fw_residual_flag) {
+		QEDF_ERR(&(qedf->dbg_ctx),
+		    "Firmware detected underrun: xid=0x%x fcp_rsp.flags=0x%02x "
+		    "fcp_resid=%d fw_residual=0x%x.\n", io_req->xid,
+		    fcp_rsp->rsp_flags.flags, io_req->fcp_resid,
+		    cqe->cqe_info.rsp_info.fw_residual);
+
+		if (io_req->cdb_status == 0)
+			sc_cmd->result = (DID_ERROR << 16) | io_req->cdb_status;
+		else
+			sc_cmd->result = (DID_OK << 16) | io_req->cdb_status;
+
+		/* Abort the command since we did not get all the data */
+		init_completion(&io_req->abts_done);
+		rval = qedf_initiate_abts(io_req, true);
+		if (rval) {
+			QEDF_ERR(&(qedf->dbg_ctx), "Failed to queue ABTS.\n");
+			sc_cmd->result = (DID_ERROR << 16) | io_req->cdb_status;
+		}
+
+		/*
+		 * Set resid to the whole buffer length so we won't try to resue
+		 * any previously data.
+		 */
+		scsi_set_resid(sc_cmd, scsi_bufflen(sc_cmd));
+		goto out;
+	}
+
+	switch (io_req->fcp_status) {
+	case FC_GOOD:
+		if (io_req->cdb_status == 0) {
+			/* Good I/O completion */
+			sc_cmd->result = DID_OK << 16;
+		} else {
+			refcount = atomic_read(&io_req->refcount.refcount);
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+			    "%d:0:%d:%d xid=0x%0x op=0x%02x "
+			    "lba=%02x%02x%02x%02x cdb_status=%d "
+			    "fcp_resid=0x%x refcount=%d.\n",
+			    qedf->lport->host->host_no, sc_cmd->device->id,
+			    sc_cmd->device->lun, io_req->xid,
+			    sc_cmd->cmnd[0], sc_cmd->cmnd[2], sc_cmd->cmnd[3],
+			    sc_cmd->cmnd[4], sc_cmd->cmnd[5],
+			    io_req->cdb_status, io_req->fcp_resid,
+			    refcount);
+			sc_cmd->result = (DID_OK << 16) | io_req->cdb_status;
+
+			if (io_req->cdb_status == SAM_STAT_TASK_SET_FULL ||
+			    io_req->cdb_status == SAM_STAT_BUSY) {
+				/*
+				 * Check whether we need to set retry_delay at
+				 * all based on retry_delay module parameter
+				 * and the status qualifier.
+				 */
+
+				/* Upper 2 bits */
+				scope = fcp_rsp->retry_delay_timer & 0xC000;
+				/* Lower 14 bits */
+				qualifier = fcp_rsp->retry_delay_timer & 0x3FFF;
+
+				if (qedf_retry_delay &&
+				    scope > 0 && qualifier > 0 &&
+				    qualifier <= 0x3FEF) {
+					/* Check we don't go over the max */
+					if (qualifier > QEDF_RETRY_DELAY_MAX)
+						qualifier =
+						    QEDF_RETRY_DELAY_MAX;
+					fcport->retry_delay_timestamp =
+					    jiffies + (qualifier * HZ / 10);
+				}
+			}
+		}
+		if (io_req->fcp_resid)
+			scsi_set_resid(sc_cmd, io_req->fcp_resid);
+		break;
+	default:
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "fcp_status=%d.\n",
+			   io_req->fcp_status);
+		break;
+	}
+
+out:
+	if (qedf_io_tracing)
+		qedf_trace_io(fcport, io_req, QEDF_IO_TRACE_RSP);
+
+	io_req->sc_cmd = NULL;
+	sc_cmd->SCp.ptr =  NULL;
+	sc_cmd->scsi_done(sc_cmd);
+	kref_put(&io_req->refcount, qedf_release_cmd);
+}
+
+/* Return a SCSI command in some other context besides a normal completion */
+void qedf_scsi_done(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
+	int result)
+{
+	u16 xid;
+	struct scsi_cmnd *sc_cmd;
+	int refcount;
+
+	if (!io_req)
+		return;
+
+	xid = io_req->xid;
+	sc_cmd = io_req->sc_cmd;
+
+	if (!sc_cmd) {
+		QEDF_WARN(&(qedf->dbg_ctx), "sc_cmd is NULL!\n");
+		return;
+	}
+
+	if (!sc_cmd->SCp.ptr) {
+		QEDF_WARN(&(qedf->dbg_ctx), "SCp.ptr is NULL, returned in "
+		    "another context.\n");
+		return;
+	}
+
+	qedf_unmap_sg_list(qedf, io_req);
+
+	sc_cmd->result = result << 16;
+	refcount = atomic_read(&io_req->refcount.refcount);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%d: Completing "
+	    "sc_cmd=%p result=0x%08x op=0x%02x lba=0x%02x%02x%02x%02x, "
+	    "allowed=%d retries=%d refcount=%d.\n",
+	    qedf->lport->host->host_no, sc_cmd->device->id,
+	    sc_cmd->device->lun, sc_cmd, sc_cmd->result, sc_cmd->cmnd[0],
+	    sc_cmd->cmnd[2], sc_cmd->cmnd[3], sc_cmd->cmnd[4],
+	    sc_cmd->cmnd[5], sc_cmd->allowed, sc_cmd->retries,
+	    refcount);
+
+	/*
+	 * Set resid to the whole buffer length so we won't try to resue any
+	 * previously read data
+	 */
+	scsi_set_resid(sc_cmd, scsi_bufflen(sc_cmd));
+
+	if (qedf_io_tracing)
+		qedf_trace_io(io_req->fcport, io_req, QEDF_IO_TRACE_RSP);
+
+	io_req->sc_cmd = NULL;
+	sc_cmd->SCp.ptr = NULL;
+	sc_cmd->scsi_done(sc_cmd);
+	kref_put(&io_req->refcount, qedf_release_cmd);
+}
+
+/*
+ * Handle warning type CQE completions. This is mainly used for REC timer
+ * popping.
+ */
+void qedf_process_warning_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req)
+{
+	int rval, i;
+	struct qedf_rport *fcport = io_req->fcport;
+	u64 err_warn_bit_map;
+	u8 err_warn = 0xff;
+
+	if (!cqe)
+		return;
+
+	QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx), "Warning CQE, "
+		  "xid=0x%x\n", io_req->xid);
+	QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx),
+		  "err_warn_bitmap=%08x:%08x\n",
+		  le32_to_cpu(cqe->cqe_info.err_info.err_warn_bitmap_hi),
+		  le32_to_cpu(cqe->cqe_info.err_info.err_warn_bitmap_lo));
+	QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx), "tx_buff_off=%08x, "
+		  "rx_buff_off=%08x, rx_id=%04x\n",
+		  le32_to_cpu(cqe->cqe_info.err_info.tx_buf_off),
+		  le32_to_cpu(cqe->cqe_info.err_info.rx_buf_off),
+		  le32_to_cpu(cqe->cqe_info.err_info.rx_id));
+
+	/* Normalize the error bitmap value to an just an unsigned int */
+	err_warn_bit_map = (u64)
+	    ((u64)cqe->cqe_info.err_info.err_warn_bitmap_hi << 32) |
+	    (u64)cqe->cqe_info.err_info.err_warn_bitmap_lo;
+	for (i = 0; i < 64; i++) {
+		if (err_warn_bit_map & (u64)((u64)1 << i)) {
+			err_warn = i;
+			break;
+		}
+	}
+
+	/* Check if REC TOV expired if this is a tape device */
+	if (fcport->dev_type == QEDF_RPORT_TYPE_TAPE) {
+		if (err_warn ==
+		    FCOE_WARNING_CODE_REC_TOV_TIMER_EXPIRATION) {
+			QEDF_ERR(&(qedf->dbg_ctx), "REC timer expired.\n");
+			if (!test_bit(QEDF_CMD_SRR_SENT, &io_req->flags)) {
+				io_req->rx_buf_off =
+				    cqe->cqe_info.err_info.rx_buf_off;
+				io_req->tx_buf_off =
+				    cqe->cqe_info.err_info.tx_buf_off;
+				io_req->rx_id = cqe->cqe_info.err_info.rx_id;
+				rval = qedf_send_rec(io_req);
+				/*
+				 * We only want to abort the io_req if we
+				 * can't queue the REC command as we want to
+				 * keep the exchange open for recovery.
+				 */
+				if (rval)
+					goto send_abort;
+			}
+			return;
+		}
+	}
+
+send_abort:
+	init_completion(&io_req->abts_done);
+	rval = qedf_initiate_abts(io_req, true);
+	if (rval)
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed to queue ABTS.\n");
+}
+
+/* Cleanup a command when we receive an error detection completion */
+void qedf_process_error_detect(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req)
+{
+	int rval;
+
+	if (!cqe)
+		return;
+
+	QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx), "Error detection CQE, "
+		  "xid=0x%x\n", io_req->xid);
+	QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx),
+		  "err_warn_bitmap=%08x:%08x\n",
+		  le32_to_cpu(cqe->cqe_info.err_info.err_warn_bitmap_hi),
+		  le32_to_cpu(cqe->cqe_info.err_info.err_warn_bitmap_lo));
+	QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx), "tx_buff_off=%08x, "
+		  "rx_buff_off=%08x, rx_id=%04x\n",
+		  le32_to_cpu(cqe->cqe_info.err_info.tx_buf_off),
+		  le32_to_cpu(cqe->cqe_info.err_info.rx_buf_off),
+		  le32_to_cpu(cqe->cqe_info.err_info.rx_id));
+
+	if (qedf->stop_io_on_error) {
+		qedf_stop_all_io(qedf);
+		return;
+	}
+
+	init_completion(&io_req->abts_done);
+	rval = qedf_initiate_abts(io_req, true);
+	if (rval)
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed to queue ABTS.\n");
+}
+
+static void qedf_flush_els_req(struct qedf_ctx *qedf,
+	struct qedf_ioreq *els_req)
+{
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+	    "Flushing ELS request xid=0x%x refcount=%d.\n", els_req->xid,
+	    atomic_read(&els_req->refcount.refcount));
+
+	/*
+	 * Need to distinguish this from a timeout when calling the
+	 * els_req->cb_func.
+	 */
+	els_req->event = QEDF_IOREQ_EV_ELS_FLUSH;
+
+	/* Cancel the timer */
+	cancel_delayed_work_sync(&els_req->timeout_work);
+
+	/* Call callback function to complete command */
+	if (els_req->cb_func && els_req->cb_arg) {
+		els_req->cb_func(els_req->cb_arg);
+		els_req->cb_arg = NULL;
+	}
+
+	/* Release kref for original initiate_els */
+	kref_put(&els_req->refcount, qedf_release_cmd);
+}
+
+/* A value of -1 for lun is a wild card that means flush all
+ * active SCSI I/Os for the target.
+ */
+void qedf_flush_active_ios(struct qedf_rport *fcport, int lun)
+{
+	struct qedf_ioreq *io_req;
+	struct qedf_ctx *qedf;
+	struct qedf_cmd_mgr *cmd_mgr;
+	int i, rc;
+
+	if (!fcport)
+		return;
+
+	qedf = fcport->qedf;
+	cmd_mgr = qedf->cmd_mgr;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "Flush active i/o's.\n");
+
+	for (i = 0; i < FCOE_PARAMS_NUM_TASKS; i++) {
+		io_req = &cmd_mgr->cmds[i];
+
+		if (!io_req)
+			continue;
+		if (io_req->fcport != fcport)
+			continue;
+		if (io_req->cmd_type == QEDF_ELS) {
+			rc = kref_get_unless_zero(&io_req->refcount);
+			if (!rc) {
+				QEDF_ERR(&(qedf->dbg_ctx),
+				    "Could not get kref for io_req=0x%p.\n",
+				    io_req);
+				continue;
+			}
+			qedf_flush_els_req(qedf, io_req);
+			/*
+			 * Release the kref and go back to the top of the
+			 * loop.
+			 */
+			goto free_cmd;
+		}
+
+		if (!io_req->sc_cmd)
+			continue;
+		if (lun > 0) {
+			if (io_req->sc_cmd->device->lun !=
+			    (u64)lun)
+				continue;
+		}
+
+		/*
+		 * Use kref_get_unless_zero in the unlikely case the command
+		 * we're about to flush was completed in the normal SCSI path
+		 */
+		rc = kref_get_unless_zero(&io_req->refcount);
+		if (!rc) {
+			QEDF_ERR(&(qedf->dbg_ctx), "Could not get kref for "
+			    "io_req=0x%p\n", io_req);
+			continue;
+		}
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Cleanup xid=0x%x.\n", io_req->xid);
+
+		/* Cleanup task and return I/O mid-layer */
+		qedf_initiate_cleanup(io_req, true);
+
+free_cmd:
+		kref_put(&io_req->refcount, qedf_release_cmd);
+	}
+}
+
+/*
+ * Initiate a ABTS middle path command. Note that we don't have to initialize
+ * the task context for an ABTS task.
+ */
+int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
+{
+	struct fc_lport *lport;
+	struct qedf_rport *fcport = io_req->fcport;
+	struct fc_rport_priv *rdata = fcport->rdata;
+	struct qedf_ctx *qedf = fcport->qedf;
+	u16 xid;
+	u32 r_a_tov = 0;
+	int rc = 0;
+	unsigned long flags;
+
+	r_a_tov = rdata->r_a_tov;
+	lport = qedf->lport;
+
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "tgt not offloaded\n");
+		rc = 1;
+		goto abts_err;
+	}
+
+	if (lport->state != LPORT_ST_READY || !(lport->link_up)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "link is not ready\n");
+		rc = 1;
+		goto abts_err;
+	}
+
+	if (atomic_read(&qedf->link_down_tmo_valid) > 0) {
+		QEDF_ERR(&(qedf->dbg_ctx), "link_down_tmo active.\n");
+		rc = 1;
+		goto abts_err;
+	}
+
+	/* Ensure room on SQ */
+	if (!atomic_read(&fcport->free_sqes)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "No SQ entries available\n");
+		rc = 1;
+		goto abts_err;
+	}
+
+
+	kref_get(&io_req->refcount);
+
+	xid = io_req->xid;
+	qedf->control_requests++;
+	qedf->packet_aborts++;
+
+	/* Set the return CPU to be the same as the request one */
+	io_req->cpu = smp_processor_id();
+
+	/* Set the command type to abort */
+	io_req->cmd_type = QEDF_ABTS;
+	io_req->return_scsi_cmd_on_abts = return_scsi_cmd_on_abts;
+
+	set_bit(QEDF_CMD_IN_ABORT, &io_req->flags);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, "ABTS io_req xid = "
+		   "0x%x\n", xid);
+
+	qedf_cmd_timer_set(qedf, io_req, QEDF_ABORT_TIMEOUT * HZ);
+
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+
+	/* Add ABTS to send queue */
+	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_ABTS, 0);
+
+	/* Ring doorbell */
+	qedf_ring_doorbell(fcport);
+
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
+
+	return rc;
+abts_err:
+	/*
+	 * If the ABTS task fails to queue then we need to cleanup the
+	 * task at the firmware.
+	 */
+	qedf_initiate_cleanup(io_req, return_scsi_cmd_on_abts);
+	return rc;
+}
+
+void qedf_process_abts_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req)
+{
+	uint32_t r_ctl;
+	uint16_t xid;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, "Entered with xid = "
+		   "0x%x cmd_type = %d\n", io_req->xid, io_req->cmd_type);
+
+	cancel_delayed_work(&io_req->timeout_work);
+
+	xid = io_req->xid;
+	r_ctl = cqe->cqe_info.abts_info.r_ctl;
+
+	switch (r_ctl) {
+	case FC_RCTL_BA_ACC:
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM,
+		    "ABTS response - ACC Send RRQ after R_A_TOV\n");
+		io_req->event = QEDF_IOREQ_EV_ABORT_SUCCESS;
+		/*
+		 * Dont release this cmd yet. It will be relesed
+		 * after we get RRQ response
+		 */
+		kref_get(&io_req->refcount);
+		queue_delayed_work(qedf->dpc_wq, &io_req->rrq_work,
+		    msecs_to_jiffies(qedf->lport->r_a_tov));
+		break;
+	/* For error cases let the cleanup return the command */
+	case FC_RCTL_BA_RJT:
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM,
+		   "ABTS response - RJT\n");
+		io_req->event = QEDF_IOREQ_EV_ABORT_FAILED;
+		break;
+	default:
+		QEDF_ERR(&(qedf->dbg_ctx), "Unknown ABTS response\n");
+		break;
+	}
+
+	clear_bit(QEDF_CMD_IN_ABORT, &io_req->flags);
+
+	if (io_req->sc_cmd) {
+		if (io_req->return_scsi_cmd_on_abts)
+			qedf_scsi_done(qedf, io_req, DID_ERROR);
+	}
+
+	/* Notify eh_abort handler that ABTS is complete */
+	complete(&io_req->abts_done);
+
+	kref_put(&io_req->refcount, qedf_release_cmd);
+}
+
+int qedf_init_mp_req(struct qedf_ioreq *io_req)
+{
+	struct qedf_mp_req *mp_req;
+	struct fcoe_sge *mp_req_bd;
+	struct fcoe_sge *mp_resp_bd;
+	struct qedf_ctx *qedf = io_req->fcport->qedf;
+	dma_addr_t addr;
+	uint64_t sz;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_MP_REQ, "Entered.\n");
+
+	mp_req = (struct qedf_mp_req *)&(io_req->mp_req);
+	memset(mp_req, 0, sizeof(struct qedf_mp_req));
+
+	if (io_req->cmd_type != QEDF_ELS) {
+		mp_req->req_len = sizeof(struct fcp_cmnd);
+		io_req->data_xfer_len = mp_req->req_len;
+	} else
+		mp_req->req_len = io_req->data_xfer_len;
+
+	mp_req->req_buf = dma_alloc_coherent(&qedf->pdev->dev, QEDF_PAGE_SIZE,
+	    &mp_req->req_buf_dma, GFP_KERNEL);
+	if (!mp_req->req_buf) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to alloc MP req buffer\n");
+		qedf_free_mp_resc(io_req);
+		return -ENOMEM;
+	}
+
+	mp_req->resp_buf = dma_alloc_coherent(&qedf->pdev->dev,
+	    QEDF_PAGE_SIZE, &mp_req->resp_buf_dma, GFP_KERNEL);
+	if (!mp_req->resp_buf) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to alloc TM resp "
+			  "buffer\n");
+		qedf_free_mp_resc(io_req);
+		return -ENOMEM;
+	}
+
+	/* Allocate and map mp_req_bd and mp_resp_bd */
+	sz = sizeof(struct fcoe_sge);
+	mp_req->mp_req_bd = dma_alloc_coherent(&qedf->pdev->dev, sz,
+	    &mp_req->mp_req_bd_dma, GFP_KERNEL);
+	if (!mp_req->mp_req_bd) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to alloc MP req bd\n");
+		qedf_free_mp_resc(io_req);
+		return -ENOMEM;
+	}
+
+	mp_req->mp_resp_bd = dma_alloc_coherent(&qedf->pdev->dev, sz,
+	    &mp_req->mp_resp_bd_dma, GFP_KERNEL);
+	if (!mp_req->mp_resp_bd) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to alloc MP resp bd\n");
+		qedf_free_mp_resc(io_req);
+		return -ENOMEM;
+	}
+
+	/* Fill bd table */
+	addr = mp_req->req_buf_dma;
+	mp_req_bd = mp_req->mp_req_bd;
+	mp_req_bd->sge_addr.lo = U64_LO(addr);
+	mp_req_bd->sge_addr.hi = U64_HI(addr);
+	mp_req_bd->size = QEDF_PAGE_SIZE;
+
+	/*
+	 * MP buffer is either a task mgmt command or an ELS.
+	 * So the assumption is that it consumes a single bd
+	 * entry in the bd table
+	 */
+	mp_resp_bd = mp_req->mp_resp_bd;
+	addr = mp_req->resp_buf_dma;
+	mp_resp_bd->sge_addr.lo = U64_LO(addr);
+	mp_resp_bd->sge_addr.hi = U64_HI(addr);
+	mp_resp_bd->size = QEDF_PAGE_SIZE;
+
+	return 0;
+}
+
+/*
+ * Last ditch effort to clear the port if it's stuck. Used only after a
+ * cleanup task times out.
+ */
+static void qedf_drain_request(struct qedf_ctx *qedf)
+{
+	if (test_bit(QEDF_DRAIN_ACTIVE, &qedf->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "MCP drain already active.\n");
+		return;
+	}
+
+	/* Set bit to return all queuecommand requests as busy */
+	set_bit(QEDF_DRAIN_ACTIVE, &qedf->flags);
+
+	/* Call qed drain request for function. Should be synchronous */
+	qed_ops->common->drain(qedf->cdev);
+
+	/* Settle time for CQEs to be returned */
+	msleep(100);
+
+	/* Unplug and continue */
+	clear_bit(QEDF_DRAIN_ACTIVE, &qedf->flags);
+}
+
+/*
+ * Returns SUCCESS if the cleanup task does not timeout, otherwise return
+ * FAILURE.
+ */
+int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
+	bool return_scsi_cmd_on_abts)
+{
+	struct qedf_rport *fcport;
+	struct qedf_ctx *qedf;
+	uint16_t xid;
+	struct fcoe_task_context *task;
+	int tmo = 0;
+	int rc = SUCCESS;
+	unsigned long flags;
+
+	fcport = io_req->fcport;
+	if (!fcport) {
+		QEDF_ERR(NULL, "fcport is NULL.\n");
+		return SUCCESS;
+	}
+
+	qedf = fcport->qedf;
+	if (!qedf) {
+		QEDF_ERR(NULL, "qedf is NULL.\n");
+		return SUCCESS;
+	}
+
+	if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags) ||
+	    test_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "io_req xid=0x%x already in "
+			  "cleanup processing or already completed.\n",
+			  io_req->xid);
+		return SUCCESS;
+	}
+
+	/* Ensure room on SQ */
+	if (!atomic_read(&fcport->free_sqes)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "No SQ entries available\n");
+		return FAILED;
+	}
+
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "Entered xid=0x%x\n",
+	    io_req->xid);
+
+	/* Cleanup cmds re-use the same TID as the original I/O */
+	xid = io_req->xid;
+	io_req->cmd_type = QEDF_CLEANUP;
+	io_req->return_scsi_cmd_on_abts = return_scsi_cmd_on_abts;
+
+	/* Set the return CPU to be the same as the request one */
+	io_req->cpu = smp_processor_id();
+
+	set_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
+
+	task = qedf_get_task_mem(&qedf->tasks, xid);
+
+	init_completion(&io_req->tm_done);
+
+	/* Obtain free SQ entry */
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_EXCHANGE_CLEANUP, 0);
+
+	/* Ring doorbell */
+	qedf_ring_doorbell(fcport);
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
+
+	tmo = wait_for_completion_timeout(&io_req->tm_done,
+	    QEDF_CLEANUP_TIMEOUT * HZ);
+
+	if (!tmo) {
+		rc = FAILED;
+		/* Timeout case */
+		QEDF_ERR(&(qedf->dbg_ctx), "Cleanup command timeout, "
+			  "xid=%x.\n", io_req->xid);
+		clear_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
+		/* Issue a drain request if cleanup task times out */
+		QEDF_ERR(&(qedf->dbg_ctx), "Issuing MCP drain request.\n");
+		qedf_drain_request(qedf);
+	}
+
+	if (io_req->sc_cmd) {
+		if (io_req->return_scsi_cmd_on_abts)
+			qedf_scsi_done(qedf, io_req, DID_ERROR);
+	}
+
+	if (rc == SUCCESS)
+		io_req->event = QEDF_IOREQ_EV_CLEANUP_SUCCESS;
+	else
+		io_req->event = QEDF_IOREQ_EV_CLEANUP_FAILED;
+
+	return rc;
+}
+
+void qedf_process_cleanup_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req)
+{
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "Entered xid = 0x%x\n",
+		   io_req->xid);
+
+	clear_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
+
+	/* Complete so we can finish cleaning up the I/O */
+	complete(&io_req->tm_done);
+}
+
+static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
+	uint8_t tm_flags)
+{
+	struct qedf_ioreq *io_req;
+	struct qedf_mp_req *tm_req;
+	struct fcoe_task_context *task;
+	struct fc_frame_header *fc_hdr;
+	struct fcp_cmnd *fcp_cmnd;
+	struct qedf_ctx *qedf = fcport->qedf;
+	int rc = 0;
+	uint16_t xid;
+	uint32_t sid, did;
+	int tmo = 0;
+	unsigned long flags;
+
+	if (!sc_cmd) {
+		QEDF_ERR(&(qedf->dbg_ctx), "invalid arg\n");
+		return FAILED;
+	}
+
+	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+		QEDF_ERR(&(qedf->dbg_ctx), "fcport not offloaded\n");
+		rc = FAILED;
+		return FAILED;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, "portid = 0x%x "
+		   "tm_flags = %d\n", fcport->rdata->ids.port_id, tm_flags);
+
+	io_req = qedf_alloc_cmd(fcport, QEDF_TASK_MGMT_CMD);
+	if (!io_req) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed TMF");
+		rc = -EAGAIN;
+		goto reset_tmf_err;
+	}
+
+	/* Initialize rest of io_req fields */
+	io_req->sc_cmd = sc_cmd;
+	io_req->fcport = fcport;
+	io_req->cmd_type = QEDF_TASK_MGMT_CMD;
+
+	/* Set the return CPU to be the same as the request one */
+	io_req->cpu = smp_processor_id();
+
+	tm_req = (struct qedf_mp_req *)&(io_req->mp_req);
+
+	rc = qedf_init_mp_req(io_req);
+	if (rc == FAILED) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Task mgmt MP request init "
+			  "failed\n");
+		kref_put(&io_req->refcount, qedf_release_cmd);
+		goto reset_tmf_err;
+	}
+
+	/* Set TM flags */
+	io_req->io_req_flags = 0;
+	tm_req->tm_flags = tm_flags;
+
+	/* Default is to return a SCSI command when an error occurs */
+	io_req->return_scsi_cmd_on_abts = true;
+
+	/* Fill FCP_CMND */
+	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tm_req->req_buf);
+	fcp_cmnd = (struct fcp_cmnd *)tm_req->req_buf;
+	memset(fcp_cmnd->fc_cdb, 0, FCP_CMND_LEN);
+	fcp_cmnd->fc_dl = 0;
+
+	/* Fill FC header */
+	fc_hdr = &(tm_req->req_fc_hdr);
+	sid = fcport->sid;
+	did = fcport->rdata->ids.port_id;
+	__fc_fill_fc_hdr(fc_hdr, FC_RCTL_DD_UNSOL_CMD, sid, did,
+			   FC_TYPE_FCP, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
+			   FC_FC_SEQ_INIT, 0);
+	/* Obtain exchange id */
+	xid = io_req->xid;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, "TMF io_req xid = "
+		   "0x%x\n", xid);
+
+	/* Initialize task context for this IO request */
+	task = qedf_get_task_mem(&qedf->tasks, xid);
+	qedf_init_mp_task(io_req, task);
+
+	init_completion(&io_req->tm_done);
+
+	/* Obtain free SQ entry */
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
+
+	/* Ring doorbell */
+	qedf_ring_doorbell(fcport);
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
+
+	tmo = wait_for_completion_timeout(&io_req->tm_done,
+	    QEDF_TM_TIMEOUT * HZ);
+
+	if (!tmo) {
+		rc = FAILED;
+		QEDF_ERR(&(qedf->dbg_ctx), "wait for tm_cmpl timeout!\n");
+	} else {
+		/* Check TMF response code */
+		if (io_req->fcp_rsp_code == 0)
+			rc = SUCCESS;
+		else
+			rc = FAILED;
+	}
+
+	if (tm_flags == FCP_TMF_LUN_RESET)
+		qedf_flush_active_ios(fcport, (int)sc_cmd->device->lun);
+	else
+		qedf_flush_active_ios(fcport, -1);
+
+	kref_put(&io_req->refcount, qedf_release_cmd);
+
+	if (rc != SUCCESS) {
+		QEDF_ERR(&(qedf->dbg_ctx), "task mgmt command failed...\n");
+		rc = FAILED;
+	} else {
+		QEDF_ERR(&(qedf->dbg_ctx), "task mgmt command success...\n");
+		rc = SUCCESS;
+	}
+reset_tmf_err:
+	return rc;
+}
+
+int qedf_initiate_tmf(struct scsi_cmnd *sc_cmd, u8 tm_flags)
+{
+	struct fc_rport *rport = starget_to_rport(scsi_target(sc_cmd->device));
+	struct fc_rport_libfc_priv *rp = rport->dd_data;
+	struct qedf_rport *fcport = (struct qedf_rport *)&rp[1];
+	struct qedf_ctx *qedf;
+	struct fc_lport *lport;
+	int rc = SUCCESS;
+	int rval;
+
+	rval = fc_remote_port_chkready(rport);
+
+	if (rval) {
+		QEDF_ERR(NULL, "device_reset rport not ready\n");
+		rc = FAILED;
+		goto tmf_err;
+	}
+
+	if (fcport == NULL) {
+		QEDF_ERR(NULL, "device_reset: rport is NULL\n");
+		rc = FAILED;
+		goto tmf_err;
+	}
+
+	qedf = fcport->qedf;
+	lport = qedf->lport;
+
+	if (test_bit(QEDF_UNLOADING, &qedf->flags) ||
+	    test_bit(QEDF_DBG_STOP_IO, &qedf->flags)) {
+		rc = SUCCESS;
+		goto tmf_err;
+	}
+
+	if (lport->state != LPORT_ST_READY || !(lport->link_up)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "link is not ready\n");
+		rc = FAILED;
+		goto tmf_err;
+	}
+
+	rc = qedf_execute_tmf(fcport, sc_cmd, tm_flags);
+
+tmf_err:
+	return rc;
+}
+
+void qedf_process_tmf_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
+	struct qedf_ioreq *io_req)
+{
+	struct fcoe_cqe_rsp_info *fcp_rsp;
+	struct fcoe_cqe_midpath_info *mp_info;
+
+
+	/* Get TMF response length from CQE */
+	mp_info = &cqe->cqe_info.midpath_info;
+	io_req->mp_req.resp_len = mp_info->data_placement_size;
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM,
+	    "Response len is %d.\n", io_req->mp_req.resp_len);
+
+	fcp_rsp = &cqe->cqe_info.rsp_info;
+	qedf_parse_fcp_rsp(io_req, fcp_rsp);
+
+	io_req->sc_cmd = NULL;
+	complete(&io_req->tm_done);
+}
+
+void qedf_process_unsol_compl(struct qedf_ctx *qedf, uint16_t que_idx,
+	struct fcoe_cqe *cqe)
+{
+	unsigned long flags;
+	uint16_t tmp;
+	uint16_t pktlen = cqe->cqe_info.unsolic_info.pkt_len;
+	u32 payload_len, crc;
+	struct fc_frame_header *fh;
+	struct fc_frame *fp;
+	struct qedf_io_work *io_work;
+	u32 bdq_idx;
+	void *bdq_addr;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_UNSOL,
+	    "address.hi=%x address.lo=%x opaque_data.hi=%x "
+	    "opaque_data.lo=%x bdq_prod_idx=%u len=%u.\n",
+	    le32_to_cpu(cqe->cqe_info.unsolic_info.bd_info.address.hi),
+	    le32_to_cpu(cqe->cqe_info.unsolic_info.bd_info.address.lo),
+	    le32_to_cpu(cqe->cqe_info.unsolic_info.bd_info.opaque.hi),
+	    le32_to_cpu(cqe->cqe_info.unsolic_info.bd_info.opaque.lo),
+	    qedf->bdq_prod_idx, pktlen);
+
+	bdq_idx = le32_to_cpu(cqe->cqe_info.unsolic_info.bd_info.opaque.lo);
+	if (bdq_idx >= QEDF_BDQ_SIZE) {
+		QEDF_ERR(&(qedf->dbg_ctx), "bdq_idx is out of range %d.\n",
+		    bdq_idx);
+		goto increment_prod;
+	}
+
+	bdq_addr = qedf->bdq[bdq_idx].buf_addr;
+	if (!bdq_addr) {
+		QEDF_ERR(&(qedf->dbg_ctx), "bdq_addr is NULL, dropping "
+		    "unsolicited packet.\n");
+		goto increment_prod;
+	}
+
+	if (qedf_dump_frames) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_UNSOL,
+		    "BDQ frame is at addr=%p.\n", bdq_addr);
+		print_hex_dump(KERN_WARNING, "bdq ", DUMP_PREFIX_OFFSET, 16, 1,
+		    (void *)bdq_addr, pktlen, false);
+	}
+
+	/* Allocate frame */
+	payload_len = pktlen - sizeof(struct fc_frame_header);
+	fp = fc_frame_alloc(qedf->lport, payload_len);
+	if (!fp) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Could not allocate fp.\n");
+		goto increment_prod;
+	}
+
+	/* Copy data from BDQ buffer into fc_frame struct */
+	fh = (struct fc_frame_header *)fc_frame_header_get(fp);
+	memcpy(fh, (void *)bdq_addr, pktlen);
+
+	/* Initialize the frame so libfc sees it as a valid frame */
+	crc = fcoe_fc_crc(fp);
+	fc_frame_init(fp);
+	fr_dev(fp) = qedf->lport;
+	fr_sof(fp) = FC_SOF_I3;
+	fr_eof(fp) = FC_EOF_T;
+	fr_crc(fp) = cpu_to_le32(~crc);
+
+	/*
+	 * We need to return the frame back up to libfc in a non-atomic
+	 * context
+	 */
+	io_work = mempool_alloc(qedf->io_mempool, GFP_ATOMIC);
+	if (!io_work) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Could not allocate "
+			   "work for I/O completion.\n");
+		fc_frame_free(fp);
+		goto increment_prod;
+	}
+	memset(io_work, 0, sizeof(struct qedf_io_work));
+
+	INIT_WORK(&io_work->work, qedf_fp_io_handler);
+
+	/* Copy contents of CQE for deferred processing */
+	memcpy(&io_work->cqe, cqe, sizeof(struct fcoe_cqe));
+
+	io_work->qedf = qedf;
+	io_work->fp = fp;
+
+	queue_work_on(smp_processor_id(), qedf_io_wq, &io_work->work);
+increment_prod:
+	spin_lock_irqsave(&qedf->hba_lock, flags);
+
+	/* Increment producer to let f/w know we've handled the frame */
+	qedf->bdq_prod_idx++;
+
+	/* Producer index wraps at uint16_t boundary */
+	if (qedf->bdq_prod_idx == 0xffff)
+		qedf->bdq_prod_idx = 0;
+
+	writew(qedf->bdq_prod_idx, qedf->bdq_primary_prod);
+	tmp = readw(qedf->bdq_primary_prod);
+	writew(qedf->bdq_prod_idx, qedf->bdq_secondary_prod);
+	tmp = readw(qedf->bdq_secondary_prod);
+
+	spin_unlock_irqrestore(&qedf->hba_lock, flags);
+}
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
new file mode 100644
index 000000000000..d9d7a86b5f8b
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -0,0 +1,3336 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/highmem.h>
+#include <linux/crc32.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/kthread.h>
+#include <scsi/libfc.h>
+#include <scsi/scsi_host.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/cpu.h>
+#include "qedf.h"
+
+const struct qed_fcoe_ops *qed_ops;
+
+static int qedf_probe(struct pci_dev *pdev, const struct pci_device_id *id);
+static void qedf_remove(struct pci_dev *pdev);
+
+extern struct qedf_debugfs_ops qedf_debugfs_ops;
+extern struct file_operations qedf_dbg_fops;
+
+/*
+ * Driver module parameters.
+ */
+static unsigned int qedf_dev_loss_tmo = 60;
+module_param_named(dev_loss_tmo, qedf_dev_loss_tmo, int, S_IRUGO);
+MODULE_PARM_DESC(dev_loss_tmo,  " dev_loss_tmo setting for attached "
+	"remote ports (default 60)");
+
+uint qedf_debug = QEDF_LOG_INFO;
+module_param_named(debug, qedf_debug, uint, S_IRUGO);
+MODULE_PARM_DESC(qedf_debug, " Debug mask. Pass '1' to enable default debugging"
+	" mask");
+
+static uint qedf_fipvlan_retries = 30;
+module_param_named(fipvlan_retries, qedf_fipvlan_retries, int, S_IRUGO);
+MODULE_PARM_DESC(fipvlan_retries, " Number of FIP VLAN requests to attempt "
+	"before giving up (default 30)");
+
+static uint qedf_fallback_vlan = QEDF_FALLBACK_VLAN;
+module_param_named(fallback_vlan, qedf_fallback_vlan, int, S_IRUGO);
+MODULE_PARM_DESC(fallback_vlan, " VLAN ID to try if fip vlan request fails "
+	"(default 1002).");
+
+static uint qedf_default_prio = QEDF_DEFAULT_PRIO;
+module_param_named(default_prio, qedf_default_prio, int, S_IRUGO);
+MODULE_PARM_DESC(default_prio, " Default 802.1q priority for FIP and FCoE"
+	" traffic (default 3).");
+
+uint qedf_dump_frames;
+module_param_named(dump_frames, qedf_dump_frames, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dump_frames, " Print the skb data of FIP and FCoE frames "
+	"(default off)");
+
+static uint qedf_queue_depth;
+module_param_named(queue_depth, qedf_queue_depth, int, S_IRUGO);
+MODULE_PARM_DESC(queue_depth, " Sets the queue depth for all LUNs discovered "
+	"by the qedf driver. Default is 0 (use OS default).");
+
+uint qedf_io_tracing;
+module_param_named(io_tracing, qedf_io_tracing, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(io_tracing, " Enable logging of SCSI requests/completions "
+	"into trace buffer. (default off).");
+
+static uint qedf_max_lun = MAX_FIBRE_LUNS;
+module_param_named(max_lun, qedf_max_lun, int, S_IRUGO);
+MODULE_PARM_DESC(max_lun, " Sets the maximum luns per target that the driver "
+	"supports. (default 0xffffffff)");
+
+uint qedf_link_down_tmo;
+module_param_named(link_down_tmo, qedf_link_down_tmo, int, S_IRUGO);
+MODULE_PARM_DESC(link_down_tmo, " Delays informing the fcoe transport that the "
+	"link is down by N seconds.");
+
+bool qedf_retry_delay;
+module_param_named(retry_delay, qedf_retry_delay, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(retry_delay, " Enable/disable handling of FCP_RSP IU retry "
+	"delay handling (default off).");
+
+static uint qedf_dp_module;
+module_param_named(dp_module, qedf_dp_module, uint, S_IRUGO);
+MODULE_PARM_DESC(dp_module, " bit flags control for verbose printk passed "
+	"qed module during probe.");
+
+static uint qedf_dp_level;
+module_param_named(dp_level, qedf_dp_level, uint, S_IRUGO);
+MODULE_PARM_DESC(dp_level, " printk verbosity control passed to qed module  "
+	"during probe (0-3: 0 more verbose).");
+
+struct workqueue_struct *qedf_io_wq;
+
+static struct fcoe_percpu_s qedf_global;
+static DEFINE_SPINLOCK(qedf_global_lock);
+
+static struct kmem_cache *qedf_io_work_cache;
+
+void qedf_set_vlan_id(struct qedf_ctx *qedf, int vlan_id)
+{
+	qedf->vlan_id = vlan_id;
+	qedf->vlan_id |= qedf_default_prio << VLAN_PRIO_SHIFT;
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Setting vlan_id=%04x "
+		   "prio=%d.\n", vlan_id, qedf_default_prio);
+}
+
+/* Returns true if we have a valid vlan, false otherwise */
+static bool qedf_initiate_fipvlan_req(struct qedf_ctx *qedf)
+{
+	int rc;
+
+	if (atomic_read(&qedf->link_state) != QEDF_LINK_UP) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Link not up.\n");
+		return  false;
+	}
+
+	while (qedf->fipvlan_retries--) {
+		if (qedf->vlan_id > 0)
+			return true;
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			   "Retry %d.\n", qedf->fipvlan_retries);
+		init_completion(&qedf->fipvlan_compl);
+		qedf_fcoe_send_vlan_req(qedf);
+		rc = wait_for_completion_timeout(&qedf->fipvlan_compl,
+		    1 * HZ);
+		if (rc > 0) {
+			fcoe_ctlr_link_up(&qedf->ctlr);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static void qedf_handle_link_update(struct work_struct *work)
+{
+	struct qedf_ctx *qedf =
+	    container_of(work, struct qedf_ctx, link_update.work);
+	int rc;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Entered.\n");
+
+	if (atomic_read(&qedf->link_state) == QEDF_LINK_UP) {
+		rc = qedf_initiate_fipvlan_req(qedf);
+		if (rc)
+			return;
+		/*
+		 * If we get here then we never received a repsonse to our
+		 * fip vlan request so set the vlan_id to the default and
+		 * tell FCoE that the link is up
+		 */
+		QEDF_WARN(&(qedf->dbg_ctx), "Did not receive FIP VLAN "
+			   "response, falling back to default VLAN %d.\n",
+			   qedf_fallback_vlan);
+		qedf_set_vlan_id(qedf, QEDF_FALLBACK_VLAN);
+
+		/*
+		 * Zero out data_src_addr so we'll update it with the new
+		 * lport port_id
+		 */
+		eth_zero_addr(qedf->data_src_addr);
+		fcoe_ctlr_link_up(&qedf->ctlr);
+	} else if (atomic_read(&qedf->link_state) == QEDF_LINK_DOWN) {
+		/*
+		 * If we hit here and link_down_tmo_valid is still 1 it means
+		 * that link_down_tmo timed out so set it to 0 to make sure any
+		 * other readers have accurate state.
+		 */
+		atomic_set(&qedf->link_down_tmo_valid, 0);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+		    "Calling fcoe_ctlr_link_down().\n");
+		fcoe_ctlr_link_down(&qedf->ctlr);
+		qedf_wait_for_upload(qedf);
+		/* Reset the number of FIP VLAN retries */
+		qedf->fipvlan_retries = qedf_fipvlan_retries;
+	}
+}
+
+static void qedf_flogi_resp(struct fc_seq *seq, struct fc_frame *fp,
+	void *arg)
+{
+	struct fc_exch *exch = fc_seq_exch(seq);
+	struct fc_lport *lport = exch->lp;
+	struct qedf_ctx *qedf = lport_priv(lport);
+
+	if (!qedf) {
+		QEDF_ERR(NULL, "qedf is NULL.\n");
+		return;
+	}
+
+	/*
+	 * If ERR_PTR is set then don't try to stat anything as it will cause
+	 * a crash when we access fp.
+	 */
+	if (IS_ERR(fp)) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+		    "fp has IS_ERR() set.\n");
+		goto skip_stat;
+	}
+
+	/* Log stats for FLOGI reject */
+	if (fc_frame_payload_op(fp) == ELS_LS_RJT)
+		qedf->flogi_failed++;
+
+	/* Complete flogi_compl so we can proceed to sending ADISCs */
+	complete(&qedf->flogi_compl);
+
+skip_stat:
+	/* Report response to libfc */
+	fc_lport_flogi_resp(seq, fp, lport);
+}
+
+static struct fc_seq *qedf_elsct_send(struct fc_lport *lport, u32 did,
+	struct fc_frame *fp, unsigned int op,
+	void (*resp)(struct fc_seq *,
+	struct fc_frame *,
+	void *),
+	void *arg, u32 timeout)
+{
+	struct qedf_ctx *qedf = lport_priv(lport);
+
+	/*
+	 * Intercept FLOGI for statistic purposes. Note we use the resp
+	 * callback to tell if this is really a flogi.
+	 */
+	if (resp == fc_lport_flogi_resp) {
+		qedf->flogi_cnt++;
+		return fc_elsct_send(lport, did, fp, op, qedf_flogi_resp,
+		    arg, timeout);
+	}
+
+	return fc_elsct_send(lport, did, fp, op, resp, arg, timeout);
+}
+
+int qedf_send_flogi(struct qedf_ctx *qedf)
+{
+	struct fc_lport *lport;
+	struct fc_frame *fp;
+
+	lport = qedf->lport;
+
+	if (!lport->tt.elsct_send)
+		return -EINVAL;
+
+	fp = fc_frame_alloc(lport, sizeof(struct fc_els_flogi));
+	if (!fp) {
+		QEDF_ERR(&(qedf->dbg_ctx), "fc_frame_alloc failed.\n");
+		return -ENOMEM;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS,
+	    "Sending FLOGI to reestablish session with switch.\n");
+	lport->tt.elsct_send(lport, FC_FID_FLOGI, fp,
+	    ELS_FLOGI, qedf_flogi_resp, lport, lport->r_a_tov);
+
+	init_completion(&qedf->flogi_compl);
+
+	return 0;
+}
+
+struct qedf_tmp_rdata_item {
+	struct fc_rport_priv *rdata;
+	struct list_head list;
+};
+
+/*
+ * This function is called if link_down_tmo is in use.  If we get a link up and
+ * link_down_tmo has not expired then use just FLOGI/ADISC to recover our
+ * sessions with targets.  Otherwise, just call fcoe_ctlr_link_up().
+ */
+static void qedf_link_recovery(struct work_struct *work)
+{
+	struct qedf_ctx *qedf =
+	    container_of(work, struct qedf_ctx, link_recovery.work);
+	struct qedf_rport *fcport;
+	struct fc_rport_priv *rdata;
+	struct qedf_tmp_rdata_item *rdata_item, *tmp_rdata_item;
+	bool rc;
+	int retries = 30;
+	int rval, i;
+	struct list_head rdata_login_list;
+
+	INIT_LIST_HEAD(&rdata_login_list);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+	    "Link down tmo did not expire.\n");
+
+	/*
+	 * Essentially reset the fcoe_ctlr here without affecting the state
+	 * of the libfc structs.
+	 */
+	qedf->ctlr.state = FIP_ST_LINK_WAIT;
+	fcoe_ctlr_link_down(&qedf->ctlr);
+
+	/*
+	 * Bring the link up before we send the fipvlan request so libfcoe
+	 * can select a new fcf in parallel
+	 */
+	fcoe_ctlr_link_up(&qedf->ctlr);
+
+	/* Since the link when down and up to verify which vlan we're on */
+	qedf->fipvlan_retries = qedf_fipvlan_retries;
+	rc = qedf_initiate_fipvlan_req(qedf);
+	if (!rc)
+		return;
+
+	/*
+	 * We need to wait for an FCF to be selected due to the
+	 * fcoe_ctlr_link_up other the FLOGI will be rejected.
+	 */
+	while (retries > 0) {
+		if (qedf->ctlr.sel_fcf) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "FCF reselected, proceeding with FLOGI.\n");
+			break;
+		}
+		msleep(500);
+		retries--;
+	}
+
+	if (retries < 1) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Exhausted retries waiting for "
+		    "FCF selection.\n");
+		return;
+	}
+
+	rval = qedf_send_flogi(qedf);
+	if (rval)
+		return;
+
+	/* Wait for FLOGI completion before proceeding with sending ADISCs */
+	i = wait_for_completion_timeout(&qedf->flogi_compl,
+	    qedf->lport->r_a_tov);
+	if (i == 0) {
+		QEDF_ERR(&(qedf->dbg_ctx), "FLOGI timed out.\n");
+		return;
+	}
+
+	/*
+	 * Call lport->tt.rport_login which will cause libfc to send an
+	 * ADISC since the rport is in state ready.
+	 */
+	rcu_read_lock();
+	list_for_each_entry_rcu(fcport, &qedf->fcports, peers) {
+		rdata = fcport->rdata;
+		if (rdata == NULL)
+			continue;
+		rdata_item = kzalloc(sizeof(struct qedf_tmp_rdata_item),
+		    GFP_ATOMIC);
+		if (!rdata_item)
+			continue;
+		if (kref_get_unless_zero(&rdata->kref)) {
+			rdata_item->rdata = rdata;
+			list_add(&rdata_item->list, &rdata_login_list);
+		} else
+			kfree(rdata_item);
+	}
+	rcu_read_unlock();
+	/*
+	 * Do the fc_rport_login outside of the rcu lock so we don't take a
+	 * mutex in an atomic context.
+	 */
+	list_for_each_entry_safe(rdata_item, tmp_rdata_item, &rdata_login_list,
+	    list) {
+		list_del(&rdata_item->list);
+		fc_rport_login(rdata_item->rdata);
+		kref_put(&rdata_item->rdata->kref, fc_rport_destroy);
+		kfree(rdata_item);
+	}
+}
+
+static void qedf_update_link_speed(struct qedf_ctx *qedf,
+	struct qed_link_output *link)
+{
+	struct fc_lport *lport = qedf->lport;
+
+	lport->link_speed = FC_PORTSPEED_UNKNOWN;
+	lport->link_supported_speeds = FC_PORTSPEED_UNKNOWN;
+
+	/* Set fc_host link speed */
+	switch (link->speed) {
+	case 10000:
+		lport->link_speed = FC_PORTSPEED_10GBIT;
+		break;
+	case 25000:
+		lport->link_speed = FC_PORTSPEED_25GBIT;
+		break;
+	case 40000:
+		lport->link_speed = FC_PORTSPEED_40GBIT;
+		break;
+	case 50000:
+		lport->link_speed = FC_PORTSPEED_50GBIT;
+		break;
+	case 100000:
+		lport->link_speed = FC_PORTSPEED_100GBIT;
+		break;
+	default:
+		lport->link_speed = FC_PORTSPEED_UNKNOWN;
+		break;
+	}
+
+	/*
+	 * Set supported link speed by querying the supported
+	 * capabilities of the link.
+	 */
+	if (link->supported_caps & SUPPORTED_10000baseKR_Full)
+		lport->link_supported_speeds |= FC_PORTSPEED_10GBIT;
+	if (link->supported_caps & SUPPORTED_25000baseKR_Full)
+		lport->link_supported_speeds |= FC_PORTSPEED_25GBIT;
+	if (link->supported_caps & SUPPORTED_40000baseLR4_Full)
+		lport->link_supported_speeds |= FC_PORTSPEED_40GBIT;
+	if (link->supported_caps & SUPPORTED_50000baseKR2_Full)
+		lport->link_supported_speeds |= FC_PORTSPEED_50GBIT;
+	if (link->supported_caps & SUPPORTED_100000baseKR4_Full)
+		lport->link_supported_speeds |= FC_PORTSPEED_100GBIT;
+	fc_host_supported_speeds(lport->host) = lport->link_supported_speeds;
+}
+
+static void qedf_link_update(void *dev, struct qed_link_output *link)
+{
+	struct qedf_ctx *qedf = (struct qedf_ctx *)dev;
+
+	if (link->link_up) {
+		QEDF_ERR(&(qedf->dbg_ctx), "LINK UP (%d GB/s).\n",
+		    link->speed / 1000);
+
+		/* Cancel any pending link down work */
+		cancel_delayed_work(&qedf->link_update);
+
+		atomic_set(&qedf->link_state, QEDF_LINK_UP);
+		qedf_update_link_speed(qedf, link);
+
+		if (atomic_read(&qedf->dcbx) == QEDF_DCBX_DONE) {
+			QEDF_ERR(&(qedf->dbg_ctx), "DCBx done.\n");
+			if (atomic_read(&qedf->link_down_tmo_valid) > 0)
+				queue_delayed_work(qedf->link_update_wq,
+				    &qedf->link_recovery, 0);
+			else
+				queue_delayed_work(qedf->link_update_wq,
+				    &qedf->link_update, 0);
+			atomic_set(&qedf->link_down_tmo_valid, 0);
+		}
+
+	} else {
+		QEDF_ERR(&(qedf->dbg_ctx), "LINK DOWN.\n");
+
+		atomic_set(&qedf->link_state, QEDF_LINK_DOWN);
+		atomic_set(&qedf->dcbx, QEDF_DCBX_PENDING);
+		/*
+		 * Flag that we're waiting for the link to come back up before
+		 * informing the fcoe layer of the event.
+		 */
+		if (qedf_link_down_tmo > 0) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "Starting link down tmo.\n");
+			atomic_set(&qedf->link_down_tmo_valid, 1);
+		}
+		qedf->vlan_id  = 0;
+		qedf_update_link_speed(qedf, link);
+		queue_delayed_work(qedf->link_update_wq, &qedf->link_update,
+		    qedf_link_down_tmo * HZ);
+	}
+}
+
+
+static void qedf_dcbx_handler(void *dev, struct qed_dcbx_get *get, u32 mib_type)
+{
+	struct qedf_ctx *qedf = (struct qedf_ctx *)dev;
+
+	QEDF_ERR(&(qedf->dbg_ctx), "DCBx event valid=%d enabled=%d fcoe "
+	    "prio=%d.\n", get->operational.valid, get->operational.enabled,
+	    get->operational.app_prio.fcoe);
+
+	if (get->operational.enabled && get->operational.valid) {
+		/* If DCBX was already negotiated on link up then just exit */
+		if (atomic_read(&qedf->dcbx) == QEDF_DCBX_DONE) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "DCBX already set on link up.\n");
+			return;
+		}
+
+		atomic_set(&qedf->dcbx, QEDF_DCBX_DONE);
+
+		if (atomic_read(&qedf->link_state) == QEDF_LINK_UP) {
+			if (atomic_read(&qedf->link_down_tmo_valid) > 0)
+				queue_delayed_work(qedf->link_update_wq,
+				    &qedf->link_recovery, 0);
+			else
+				queue_delayed_work(qedf->link_update_wq,
+				    &qedf->link_update, 0);
+			atomic_set(&qedf->link_down_tmo_valid, 0);
+		}
+	}
+
+}
+
+static u32 qedf_get_login_failures(void *cookie)
+{
+	struct qedf_ctx *qedf;
+
+	qedf = (struct qedf_ctx *)cookie;
+	return qedf->flogi_failed;
+}
+
+static struct qed_fcoe_cb_ops qedf_cb_ops = {
+	{
+		.link_update = qedf_link_update,
+		.dcbx_aen = qedf_dcbx_handler,
+	}
+};
+
+/*
+ * Various transport templates.
+ */
+
+static struct scsi_transport_template *qedf_fc_transport_template;
+static struct scsi_transport_template *qedf_fc_vport_transport_template;
+
+/*
+ * SCSI EH handlers
+ */
+static int qedf_eh_abort(struct scsi_cmnd *sc_cmd)
+{
+	struct fc_rport *rport = starget_to_rport(scsi_target(sc_cmd->device));
+	struct fc_rport_libfc_priv *rp = rport->dd_data;
+	struct qedf_rport *fcport;
+	struct fc_lport *lport;
+	struct qedf_ctx *qedf;
+	struct qedf_ioreq *io_req;
+	int rc = FAILED;
+	int rval;
+
+	if (fc_remote_port_chkready(rport)) {
+		QEDF_ERR(NULL, "rport not ready\n");
+		goto out;
+	}
+
+	lport = shost_priv(sc_cmd->device->host);
+	qedf = (struct qedf_ctx *)lport_priv(lport);
+
+	if ((lport->state != LPORT_ST_READY) || !(lport->link_up)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "link not ready.\n");
+		goto out;
+	}
+
+	fcport = (struct qedf_rport *)&rp[1];
+
+	io_req = (struct qedf_ioreq *)sc_cmd->SCp.ptr;
+	if (!io_req) {
+		QEDF_ERR(&(qedf->dbg_ctx), "io_req is NULL.\n");
+		rc = SUCCESS;
+		goto out;
+	}
+
+	if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags) ||
+	    test_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags) ||
+	    test_bit(QEDF_CMD_IN_ABORT, &io_req->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "io_req xid=0x%x already in "
+			  "cleanup or abort processing or already "
+			  "completed.\n", io_req->xid);
+		rc = SUCCESS;
+		goto out;
+	}
+
+	QEDF_ERR(&(qedf->dbg_ctx), "Aborting io_req sc_cmd=%p xid=0x%x "
+		  "fp_idx=%d.\n", sc_cmd, io_req->xid, io_req->fp_idx);
+
+	if (qedf->stop_io_on_error) {
+		qedf_stop_all_io(qedf);
+		rc = SUCCESS;
+		goto out;
+	}
+
+	init_completion(&io_req->abts_done);
+	rval = qedf_initiate_abts(io_req, true);
+	if (rval) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed to queue ABTS.\n");
+		goto out;
+	}
+
+	wait_for_completion(&io_req->abts_done);
+
+	if (io_req->event == QEDF_IOREQ_EV_ABORT_SUCCESS ||
+	    io_req->event == QEDF_IOREQ_EV_ABORT_FAILED ||
+	    io_req->event == QEDF_IOREQ_EV_CLEANUP_SUCCESS) {
+		/*
+		 * If we get a reponse to the abort this is success from
+		 * the perspective that all references to the command have
+		 * been removed from the driver and firmware
+		 */
+		rc = SUCCESS;
+	} else {
+		/* If the abort and cleanup failed then return a failure */
+		rc = FAILED;
+	}
+
+	if (rc == SUCCESS)
+		QEDF_ERR(&(qedf->dbg_ctx), "ABTS succeeded, xid=0x%x.\n",
+			  io_req->xid);
+	else
+		QEDF_ERR(&(qedf->dbg_ctx), "ABTS failed, xid=0x%x.\n",
+			  io_req->xid);
+
+out:
+	return rc;
+}
+
+static int qedf_eh_target_reset(struct scsi_cmnd *sc_cmd)
+{
+	QEDF_ERR(NULL, "TARGET RESET Issued...");
+	return qedf_initiate_tmf(sc_cmd, FCP_TMF_TGT_RESET);
+}
+
+static int qedf_eh_device_reset(struct scsi_cmnd *sc_cmd)
+{
+	QEDF_ERR(NULL, "LUN RESET Issued...\n");
+	return qedf_initiate_tmf(sc_cmd, FCP_TMF_LUN_RESET);
+}
+
+void qedf_wait_for_upload(struct qedf_ctx *qedf)
+{
+	while (1) {
+		if (atomic_read(&qedf->num_offloads))
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "Waiting for all uploads to complete.\n");
+		else
+			break;
+		msleep(500);
+	}
+}
+
+/* Reset the host by gracefully logging out and then logging back in */
+static int qedf_eh_host_reset(struct scsi_cmnd *sc_cmd)
+{
+	struct fc_lport *lport;
+	struct qedf_ctx *qedf;
+
+	lport = shost_priv(sc_cmd->device->host);
+
+	if (lport->vport) {
+		QEDF_ERR(NULL, "Cannot issue host reset on NPIV port.\n");
+		return SUCCESS;
+	}
+
+	qedf = (struct qedf_ctx *)lport_priv(lport);
+
+	if (atomic_read(&qedf->link_state) == QEDF_LINK_DOWN ||
+	    test_bit(QEDF_UNLOADING, &qedf->flags) ||
+	    test_bit(QEDF_DBG_STOP_IO, &qedf->flags))
+		return FAILED;
+
+	QEDF_ERR(&(qedf->dbg_ctx), "HOST RESET Issued...");
+
+	/* For host reset, essentially do a soft link up/down */
+	atomic_set(&qedf->link_state, QEDF_LINK_DOWN);
+	atomic_set(&qedf->dcbx, QEDF_DCBX_PENDING);
+	queue_delayed_work(qedf->link_update_wq, &qedf->link_update,
+	    0);
+	qedf_wait_for_upload(qedf);
+	atomic_set(&qedf->link_state, QEDF_LINK_UP);
+	qedf->vlan_id  = 0;
+	queue_delayed_work(qedf->link_update_wq, &qedf->link_update,
+	    0);
+
+	return SUCCESS;
+}
+
+static int qedf_slave_configure(struct scsi_device *sdev)
+{
+	if (qedf_queue_depth) {
+		scsi_change_queue_depth(sdev, qedf_queue_depth);
+	}
+
+	return 0;
+}
+
+static struct scsi_host_template qedf_host_template = {
+	.module 	= THIS_MODULE,
+	.name 		= QEDF_MODULE_NAME,
+	.this_id 	= -1,
+	.cmd_per_lun 	= 3,
+	.use_clustering = ENABLE_CLUSTERING,
+	.max_sectors 	= 0xffff,
+	.queuecommand 	= qedf_queuecommand,
+	.shost_attrs	= qedf_host_attrs,
+	.eh_abort_handler	= qedf_eh_abort,
+	.eh_device_reset_handler = qedf_eh_device_reset, /* lun reset */
+	.eh_target_reset_handler = qedf_eh_target_reset, /* target reset */
+	.eh_host_reset_handler  = qedf_eh_host_reset,
+	.slave_configure	= qedf_slave_configure,
+	.dma_boundary = QED_HW_DMA_BOUNDARY,
+	.sg_tablesize = QEDF_MAX_BDS_PER_CMD,
+	.can_queue = FCOE_PARAMS_NUM_TASKS,
+};
+
+static int qedf_get_paged_crc_eof(struct sk_buff *skb, int tlen)
+{
+	int rc;
+
+	spin_lock(&qedf_global_lock);
+	rc = fcoe_get_paged_crc_eof(skb, tlen, &qedf_global);
+	spin_unlock(&qedf_global_lock);
+
+	return rc;
+}
+
+static struct qedf_rport *qedf_fcport_lookup(struct qedf_ctx *qedf, u32 port_id)
+{
+	struct qedf_rport *fcport;
+	struct fc_rport_priv *rdata;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(fcport, &qedf->fcports, peers) {
+		rdata = fcport->rdata;
+		if (rdata == NULL)
+			continue;
+		if (rdata->ids.port_id == port_id) {
+			rcu_read_unlock();
+			return fcport;
+		}
+	}
+	rcu_read_unlock();
+
+	/* Return NULL to caller to let them know fcport was not found */
+	return NULL;
+}
+
+/* Transmits an ELS frame over an offloaded session */
+static int qedf_xmit_l2_frame(struct qedf_rport *fcport, struct fc_frame *fp)
+{
+	struct fc_frame_header *fh;
+	int rc = 0;
+
+	fh = fc_frame_header_get(fp);
+	if ((fh->fh_type == FC_TYPE_ELS) &&
+	    (fh->fh_r_ctl == FC_RCTL_ELS_REQ)) {
+		switch (fc_frame_payload_op(fp)) {
+		case ELS_ADISC:
+			qedf_send_adisc(fcport, fp);
+			rc = 1;
+			break;
+		}
+	}
+
+	return rc;
+}
+
+/**
+ * qedf_xmit - qedf FCoE frame transmit function
+ *
+ */
+static int qedf_xmit(struct fc_lport *lport, struct fc_frame *fp)
+{
+	struct fc_lport		*base_lport;
+	struct qedf_ctx		*qedf;
+	struct ethhdr		*eh;
+	struct fcoe_crc_eof	*cp;
+	struct sk_buff		*skb;
+	struct fc_frame_header	*fh;
+	struct fcoe_hdr		*hp;
+	u8			sof, eof;
+	u32			crc;
+	unsigned int		hlen, tlen, elen;
+	int			wlen;
+	struct fc_stats		*stats;
+	struct fc_lport *tmp_lport;
+	struct fc_lport *vn_port = NULL;
+	struct qedf_rport *fcport;
+	int rc;
+	u16 vlan_tci = 0;
+
+	qedf = (struct qedf_ctx *)lport_priv(lport);
+
+	fh = fc_frame_header_get(fp);
+	skb = fp_skb(fp);
+
+	/* Filter out traffic to other NPIV ports on the same host */
+	if (lport->vport)
+		base_lport = shost_priv(vport_to_shost(lport->vport));
+	else
+		base_lport = lport;
+
+	/* Flag if the destination is the base port */
+	if (base_lport->port_id == ntoh24(fh->fh_d_id)) {
+		vn_port = base_lport;
+	} else {
+		/* Got through the list of vports attached to the base_lport
+		 * and see if we have a match with the destination address.
+		 */
+		list_for_each_entry(tmp_lport, &base_lport->vports, list) {
+			if (tmp_lport->port_id == ntoh24(fh->fh_d_id)) {
+				vn_port = tmp_lport;
+				break;
+			}
+		}
+	}
+	if (vn_port && ntoh24(fh->fh_d_id) != FC_FID_FLOGI) {
+		struct fc_rport_priv *rdata = NULL;
+
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
+		    "Dropping FCoE frame to %06x.\n", ntoh24(fh->fh_d_id));
+		kfree_skb(skb);
+		rdata = fc_rport_lookup(lport, ntoh24(fh->fh_d_id));
+		if (rdata)
+			rdata->retries = lport->max_rport_retry_count;
+		return -EINVAL;
+	}
+	/* End NPIV filtering */
+
+	if (!qedf->ctlr.sel_fcf) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	if (!test_bit(QEDF_LL2_STARTED, &qedf->flags)) {
+		QEDF_WARN(&(qedf->dbg_ctx), "LL2 not started\n");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	if (atomic_read(&qedf->link_state) != QEDF_LINK_UP) {
+		QEDF_WARN(&(qedf->dbg_ctx), "qedf link down\n");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	if (unlikely(fh->fh_r_ctl == FC_RCTL_ELS_REQ)) {
+		if (fcoe_ctlr_els_send(&qedf->ctlr, lport, skb))
+			return 0;
+	}
+
+	/* Check to see if this needs to be sent on an offloaded session */
+	fcport = qedf_fcport_lookup(qedf, ntoh24(fh->fh_d_id));
+
+	if (fcport && test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		rc = qedf_xmit_l2_frame(fcport, fp);
+		/*
+		 * If the frame was successfully sent over the middle path
+		 * then do not try to also send it over the LL2 path
+		 */
+		if (rc)
+			return 0;
+	}
+
+	sof = fr_sof(fp);
+	eof = fr_eof(fp);
+
+	elen = sizeof(struct ethhdr);
+	hlen = sizeof(struct fcoe_hdr);
+	tlen = sizeof(struct fcoe_crc_eof);
+	wlen = (skb->len - tlen + sizeof(crc)) / FCOE_WORD_TO_BYTE;
+
+	skb->ip_summed = CHECKSUM_NONE;
+	crc = fcoe_fc_crc(fp);
+
+	/* copy port crc and eof to the skb buff */
+	if (skb_is_nonlinear(skb)) {
+		skb_frag_t *frag;
+
+		if (qedf_get_paged_crc_eof(skb, tlen)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		frag = &skb_shinfo(skb)->frags[skb_shinfo(skb)->nr_frags - 1];
+		cp = kmap_atomic(skb_frag_page(frag)) + frag->page_offset;
+	} else {
+		cp = (struct fcoe_crc_eof *)skb_put(skb, tlen);
+	}
+
+	memset(cp, 0, sizeof(*cp));
+	cp->fcoe_eof = eof;
+	cp->fcoe_crc32 = cpu_to_le32(~crc);
+	if (skb_is_nonlinear(skb)) {
+		kunmap_atomic(cp);
+		cp = NULL;
+	}
+
+
+	/* adjust skb network/transport offsets to match mac/fcoe/port */
+	skb_push(skb, elen + hlen);
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb->mac_len = elen;
+	skb->protocol = htons(ETH_P_FCOE);
+
+	__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), qedf->vlan_id);
+
+	/* fill up mac and fcoe headers */
+	eh = eth_hdr(skb);
+	eh->h_proto = htons(ETH_P_FCOE);
+	if (qedf->ctlr.map_dest)
+		fc_fcoe_set_mac(eh->h_dest, fh->fh_d_id);
+	else
+		/* insert GW address */
+		ether_addr_copy(eh->h_dest, qedf->ctlr.dest_addr);
+
+	/* Set the source MAC address */
+	fc_fcoe_set_mac(eh->h_source, fh->fh_s_id);
+
+	hp = (struct fcoe_hdr *)(eh + 1);
+	memset(hp, 0, sizeof(*hp));
+	if (FC_FCOE_VER)
+		FC_FCOE_ENCAPS_VER(hp, FC_FCOE_VER);
+	hp->fcoe_sof = sof;
+
+	/*update tx stats */
+	stats = per_cpu_ptr(lport->stats, get_cpu());
+	stats->TxFrames++;
+	stats->TxWords += wlen;
+	put_cpu();
+
+	/* Get VLAN ID from skb for printing purposes */
+	__vlan_hwaccel_get_tag(skb, &vlan_tci);
+
+	/* send down to lld */
+	fr_dev(fp) = lport;
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2, "FCoE frame send: "
+	    "src=%06x dest=%06x r_ctl=%x type=%x vlan=%04x.\n",
+	    ntoh24(fh->fh_s_id), ntoh24(fh->fh_d_id), fh->fh_r_ctl, fh->fh_type,
+	    vlan_tci);
+	if (qedf_dump_frames)
+		print_hex_dump(KERN_WARNING, "fcoe: ", DUMP_PREFIX_OFFSET, 16,
+		    1, skb->data, skb->len, false);
+	qed_ops->ll2->start_xmit(qedf->cdev, skb);
+
+	return 0;
+}
+
+static int qedf_alloc_sq(struct qedf_ctx *qedf, struct qedf_rport *fcport)
+{
+	int rval = 0;
+	u32 *pbl;
+	dma_addr_t page;
+	int num_pages;
+
+	/* Calculate appropriate queue and PBL sizes */
+	fcport->sq_mem_size = SQ_NUM_ENTRIES * sizeof(struct fcoe_wqe);
+	fcport->sq_mem_size = ALIGN(fcport->sq_mem_size, QEDF_PAGE_SIZE);
+	fcport->sq_pbl_size = (fcport->sq_mem_size / QEDF_PAGE_SIZE) *
+	    sizeof(void *);
+	fcport->sq_pbl_size = fcport->sq_pbl_size + QEDF_PAGE_SIZE;
+
+	fcport->sq = dma_alloc_coherent(&qedf->pdev->dev, fcport->sq_mem_size,
+	    &fcport->sq_dma, GFP_KERNEL);
+	if (!fcport->sq) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Could not allocate send "
+			   "queue.\n");
+		rval = 1;
+		goto out;
+	}
+	memset(fcport->sq, 0, fcport->sq_mem_size);
+
+	fcport->sq_pbl = dma_alloc_coherent(&qedf->pdev->dev,
+	    fcport->sq_pbl_size, &fcport->sq_pbl_dma, GFP_KERNEL);
+	if (!fcport->sq_pbl) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Could not allocate send "
+			   "queue PBL.\n");
+		rval = 1;
+		goto out_free_sq;
+	}
+	memset(fcport->sq_pbl, 0, fcport->sq_pbl_size);
+
+	/* Create PBL */
+	num_pages = fcport->sq_mem_size / QEDF_PAGE_SIZE;
+	page = fcport->sq_dma;
+	pbl = (u32 *)fcport->sq_pbl;
+
+	while (num_pages--) {
+		*pbl = U64_LO(page);
+		pbl++;
+		*pbl = U64_HI(page);
+		pbl++;
+		page += QEDF_PAGE_SIZE;
+	}
+
+	return rval;
+
+out_free_sq:
+	dma_free_coherent(&qedf->pdev->dev, fcport->sq_mem_size, fcport->sq,
+	    fcport->sq_dma);
+out:
+	return rval;
+}
+
+static void qedf_free_sq(struct qedf_ctx *qedf, struct qedf_rport *fcport)
+{
+	if (fcport->sq_pbl)
+		dma_free_coherent(&qedf->pdev->dev, fcport->sq_pbl_size,
+		    fcport->sq_pbl, fcport->sq_pbl_dma);
+	if (fcport->sq)
+		dma_free_coherent(&qedf->pdev->dev, fcport->sq_mem_size,
+		    fcport->sq, fcport->sq_dma);
+}
+
+static int qedf_offload_connection(struct qedf_ctx *qedf,
+	struct qedf_rport *fcport)
+{
+	struct qed_fcoe_params_offload conn_info;
+	u32 port_id;
+	u8 lport_src_id[3];
+	int rval;
+	uint16_t total_sqe = (fcport->sq_mem_size / sizeof(struct fcoe_wqe));
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_CONN, "Offloading connection "
+		   "portid=%06x.\n", fcport->rdata->ids.port_id);
+	rval = qed_ops->acquire_conn(qedf->cdev, &fcport->handle,
+	    &fcport->fw_cid, &fcport->p_doorbell);
+	if (rval) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Could not acquire connection "
+			   "for portid=%06x.\n", fcport->rdata->ids.port_id);
+		rval = 1; /* For some reason qed returns 0 on failure here */
+		goto out;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_CONN, "portid=%06x "
+		   "fw_cid=%08x handle=%d.\n", fcport->rdata->ids.port_id,
+		   fcport->fw_cid, fcport->handle);
+
+	memset(&conn_info, 0, sizeof(struct qed_fcoe_params_offload));
+
+	/* Fill in the offload connection info */
+	conn_info.sq_pbl_addr = fcport->sq_pbl_dma;
+
+	conn_info.sq_curr_page_addr = (dma_addr_t)(*(u64 *)fcport->sq_pbl);
+	conn_info.sq_next_page_addr =
+	    (dma_addr_t)(*(u64 *)(fcport->sq_pbl + 8));
+
+	/* Need to use our FCoE MAC for the offload session */
+	port_id = fc_host_port_id(qedf->lport->host);
+	lport_src_id[2] = (port_id & 0x000000FF);
+	lport_src_id[1] = (port_id & 0x0000FF00) >> 8;
+	lport_src_id[0] = (port_id & 0x00FF0000) >> 16;
+	fc_fcoe_set_mac(conn_info.src_mac, lport_src_id);
+
+	ether_addr_copy(conn_info.dst_mac, qedf->ctlr.dest_addr);
+
+	conn_info.tx_max_fc_pay_len = fcport->rdata->maxframe_size;
+	conn_info.e_d_tov_timer_val = qedf->lport->e_d_tov / 20;
+	conn_info.rec_tov_timer_val = 3; /* I think this is what E3 was */
+	conn_info.rx_max_fc_pay_len = fcport->rdata->maxframe_size;
+
+	/* Set VLAN data */
+	conn_info.vlan_tag = qedf->vlan_id <<
+	    FCOE_CONN_OFFLOAD_RAMROD_DATA_VLAN_ID_SHIFT;
+	conn_info.vlan_tag |=
+	    qedf_default_prio << FCOE_CONN_OFFLOAD_RAMROD_DATA_PRIORITY_SHIFT;
+	conn_info.flags |= (FCOE_CONN_OFFLOAD_RAMROD_DATA_B_VLAN_FLAG_MASK <<
+	    FCOE_CONN_OFFLOAD_RAMROD_DATA_B_VLAN_FLAG_SHIFT);
+
+	/* Set host port source id */
+	port_id = fc_host_port_id(qedf->lport->host);
+	fcport->sid = port_id;
+	conn_info.s_id.addr_hi = (port_id & 0x000000FF);
+	conn_info.s_id.addr_mid = (port_id & 0x0000FF00) >> 8;
+	conn_info.s_id.addr_lo = (port_id & 0x00FF0000) >> 16;
+
+	conn_info.max_conc_seqs_c3 = fcport->rdata->max_seq;
+
+	/* Set remote port destination id */
+	port_id = fcport->rdata->rport->port_id;
+	conn_info.d_id.addr_hi = (port_id & 0x000000FF);
+	conn_info.d_id.addr_mid = (port_id & 0x0000FF00) >> 8;
+	conn_info.d_id.addr_lo = (port_id & 0x00FF0000) >> 16;
+
+	conn_info.def_q_idx = 0; /* Default index for send queue? */
+
+	/* Set FC-TAPE specific flags if needed */
+	if (fcport->dev_type == QEDF_RPORT_TYPE_TAPE) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_CONN,
+		    "Enable CONF, REC for portid=%06x.\n",
+		    fcport->rdata->ids.port_id);
+		conn_info.flags |= 1 <<
+		    FCOE_CONN_OFFLOAD_RAMROD_DATA_B_CONF_REQ_SHIFT;
+		conn_info.flags |=
+		    ((fcport->rdata->sp_features & FC_SP_FT_SEQC) ? 1 : 0) <<
+		    FCOE_CONN_OFFLOAD_RAMROD_DATA_B_REC_VALID_SHIFT;
+	}
+
+	rval = qed_ops->offload_conn(qedf->cdev, fcport->handle, &conn_info);
+	if (rval) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Could not offload connection "
+			   "for portid=%06x.\n", fcport->rdata->ids.port_id);
+		goto out_free_conn;
+	} else
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_CONN, "Offload "
+			   "succeeded portid=%06x total_sqe=%d.\n",
+			   fcport->rdata->ids.port_id, total_sqe);
+
+	spin_lock_init(&fcport->rport_lock);
+	atomic_set(&fcport->free_sqes, total_sqe);
+	return 0;
+out_free_conn:
+	qed_ops->release_conn(qedf->cdev, fcport->handle);
+out:
+	return rval;
+}
+
+#define QEDF_TERM_BUFF_SIZE		10
+static void qedf_upload_connection(struct qedf_ctx *qedf,
+	struct qedf_rport *fcport)
+{
+	void *term_params;
+	dma_addr_t term_params_dma;
+
+	/* Term params needs to be a DMA coherent buffer as qed shared the
+	 * physical DMA address with the firmware. The buffer may be used in
+	 * the receive path so we may eventually have to move this.
+	 */
+	term_params = dma_alloc_coherent(&qedf->pdev->dev, QEDF_TERM_BUFF_SIZE,
+		&term_params_dma, GFP_KERNEL);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_CONN, "Uploading connection "
+		   "port_id=%06x.\n", fcport->rdata->ids.port_id);
+
+	qed_ops->destroy_conn(qedf->cdev, fcport->handle, term_params_dma);
+	qed_ops->release_conn(qedf->cdev, fcport->handle);
+
+	dma_free_coherent(&qedf->pdev->dev, QEDF_TERM_BUFF_SIZE, term_params,
+	    term_params_dma);
+}
+
+static void qedf_cleanup_fcport(struct qedf_ctx *qedf,
+	struct qedf_rport *fcport)
+{
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_CONN, "Cleaning up portid=%06x.\n",
+	    fcport->rdata->ids.port_id);
+
+	/* Flush any remaining i/o's before we upload the connection */
+	qedf_flush_active_ios(fcport, -1);
+
+	if (test_and_clear_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))
+		qedf_upload_connection(qedf, fcport);
+	qedf_free_sq(qedf, fcport);
+	fcport->rdata = NULL;
+	fcport->qedf = NULL;
+}
+
+/**
+ * This event_callback is called after successful completion of libfc
+ * initiated target login. qedf can proceed with initiating the session
+ * establishment.
+ */
+static void qedf_rport_event_handler(struct fc_lport *lport,
+				struct fc_rport_priv *rdata,
+				enum fc_rport_event event)
+{
+	struct qedf_ctx *qedf = lport_priv(lport);
+	struct fc_rport *rport = rdata->rport;
+	struct fc_rport_libfc_priv *rp;
+	struct qedf_rport *fcport;
+	u32 port_id;
+	int rval;
+	unsigned long flags;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "event = %d, "
+		   "port_id = 0x%x\n", event, rdata->ids.port_id);
+
+	switch (event) {
+	case RPORT_EV_READY:
+		if (!rport) {
+			QEDF_WARN(&(qedf->dbg_ctx), "rport is NULL.\n");
+			break;
+		}
+
+		rp = rport->dd_data;
+		fcport = (struct qedf_rport *)&rp[1];
+		fcport->qedf = qedf;
+
+		if (atomic_read(&qedf->num_offloads) >= QEDF_MAX_SESSIONS) {
+			QEDF_ERR(&(qedf->dbg_ctx), "Not offloading "
+			    "portid=0x%x as max number of offloaded sessions "
+			    "reached.\n", rdata->ids.port_id);
+			return;
+		}
+
+		/*
+		 * Don't try to offload the session again. Can happen when we
+		 * get an ADISC
+		 */
+		if (test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+			QEDF_WARN(&(qedf->dbg_ctx), "Session already "
+				   "offloaded, portid=0x%x.\n",
+				   rdata->ids.port_id);
+			return;
+		}
+
+		if (rport->port_id == FC_FID_DIR_SERV) {
+			/*
+			 * qedf_rport structure doesn't exist for
+			 * directory server.
+			 * We should not come here, as lport will
+			 * take care of fabric login
+			 */
+			QEDF_WARN(&(qedf->dbg_ctx), "rport struct does not "
+			    "exist for dir server port_id=%x\n",
+			    rdata->ids.port_id);
+			break;
+		}
+
+		if (rdata->spp_type != FC_TYPE_FCP) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "Not offlading since since spp type isn't FCP\n");
+			break;
+		}
+		if (!(rdata->ids.roles & FC_RPORT_ROLE_FCP_TARGET)) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "Not FCP target so not offloading\n");
+			break;
+		}
+
+		fcport->rdata = rdata;
+		fcport->rport = rport;
+
+		rval = qedf_alloc_sq(qedf, fcport);
+		if (rval) {
+			qedf_cleanup_fcport(qedf, fcport);
+			break;
+		}
+
+		/* Set device type */
+		if (rdata->flags & FC_RP_FLAGS_RETRY &&
+		    rdata->ids.roles & FC_RPORT_ROLE_FCP_TARGET &&
+		    !(rdata->ids.roles & FC_RPORT_ROLE_FCP_INITIATOR)) {
+			fcport->dev_type = QEDF_RPORT_TYPE_TAPE;
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "portid=%06x is a TAPE device.\n",
+			    rdata->ids.port_id);
+		} else {
+			fcport->dev_type = QEDF_RPORT_TYPE_DISK;
+		}
+
+		rval = qedf_offload_connection(qedf, fcport);
+		if (rval) {
+			qedf_cleanup_fcport(qedf, fcport);
+			break;
+		}
+
+		/* Add fcport to list of qedf_ctx list of offloaded ports */
+		spin_lock_irqsave(&qedf->hba_lock, flags);
+		list_add_rcu(&fcport->peers, &qedf->fcports);
+		spin_unlock_irqrestore(&qedf->hba_lock, flags);
+
+		/*
+		 * Set the session ready bit to let everyone know that this
+		 * connection is ready for I/O
+		 */
+		set_bit(QEDF_RPORT_SESSION_READY, &fcport->flags);
+		atomic_inc(&qedf->num_offloads);
+
+		break;
+	case RPORT_EV_LOGO:
+	case RPORT_EV_FAILED:
+	case RPORT_EV_STOP:
+		port_id = rdata->ids.port_id;
+		if (port_id == FC_FID_DIR_SERV)
+			break;
+
+		if (!rport) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "port_id=%x - rport notcreated Yet!!\n", port_id);
+			break;
+		}
+		rp = rport->dd_data;
+		/*
+		 * Perform session upload. Note that rdata->peers is already
+		 * removed from disc->rports list before we get this event.
+		 */
+		fcport = (struct qedf_rport *)&rp[1];
+
+		/* Only free this fcport if it is offloaded already */
+		if (test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+			set_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags);
+			qedf_cleanup_fcport(qedf, fcport);
+
+			/*
+			 * Remove fcport to list of qedf_ctx list of offloaded
+			 * ports
+			 */
+			spin_lock_irqsave(&qedf->hba_lock, flags);
+			list_del_rcu(&fcport->peers);
+			spin_unlock_irqrestore(&qedf->hba_lock, flags);
+
+			clear_bit(QEDF_RPORT_UPLOADING_CONNECTION,
+			    &fcport->flags);
+			atomic_dec(&qedf->num_offloads);
+		}
+
+		break;
+
+	case RPORT_EV_NONE:
+		break;
+	}
+}
+
+static void qedf_abort_io(struct fc_lport *lport)
+{
+	/* NO-OP but need to fill in the template */
+}
+
+static void qedf_fcp_cleanup(struct fc_lport *lport)
+{
+	/*
+	 * NO-OP but need to fill in template to prevent a NULL
+	 * function pointer dereference during link down. I/Os
+	 * will be flushed when port is uploaded.
+	 */
+}
+
+static struct libfc_function_template qedf_lport_template = {
+	.frame_send		= qedf_xmit,
+	.fcp_abort_io		= qedf_abort_io,
+	.fcp_cleanup		= qedf_fcp_cleanup,
+	.rport_event_callback	= qedf_rport_event_handler,
+	.elsct_send		= qedf_elsct_send,
+};
+
+static void qedf_fcoe_ctlr_setup(struct qedf_ctx *qedf)
+{
+	fcoe_ctlr_init(&qedf->ctlr, FIP_ST_AUTO);
+
+	qedf->ctlr.send = qedf_fip_send;
+	qedf->ctlr.update_mac = qedf_update_src_mac;
+	qedf->ctlr.get_src_addr = qedf_get_src_mac;
+	ether_addr_copy(qedf->ctlr.ctl_src_addr, qedf->mac);
+}
+
+static int qedf_lport_setup(struct qedf_ctx *qedf)
+{
+	struct fc_lport *lport = qedf->lport;
+
+	lport->link_up = 0;
+	lport->max_retry_count = QEDF_FLOGI_RETRY_CNT;
+	lport->max_rport_retry_count = QEDF_RPORT_RETRY_CNT;
+	lport->service_params = (FCP_SPPF_INIT_FCN | FCP_SPPF_RD_XRDY_DIS |
+	    FCP_SPPF_RETRY | FCP_SPPF_CONF_COMPL);
+	lport->boot_time = jiffies;
+	lport->e_d_tov = 2 * 1000;
+	lport->r_a_tov = 10 * 1000;
+
+	/* Set NPIV support */
+	lport->does_npiv = 1;
+	fc_host_max_npiv_vports(lport->host) = QEDF_MAX_NPIV;
+
+	fc_set_wwnn(lport, qedf->wwnn);
+	fc_set_wwpn(lport, qedf->wwpn);
+
+	fcoe_libfc_config(lport, &qedf->ctlr, &qedf_lport_template, 0);
+
+	/* Allocate the exchange manager */
+	fc_exch_mgr_alloc(lport, FC_CLASS_3, qedf->max_scsi_xid + 1,
+	    qedf->max_els_xid, NULL);
+
+	if (fc_lport_init_stats(lport))
+		return -ENOMEM;
+
+	/* Finish lport config */
+	fc_lport_config(lport);
+
+	/* Set max frame size */
+	fc_set_mfs(lport, QEDF_MFS);
+	fc_host_maxframe_size(lport->host) = lport->mfs;
+
+	/* Set default dev_loss_tmo based on module parameter */
+	fc_host_dev_loss_tmo(lport->host) = qedf_dev_loss_tmo;
+
+	/* Set symbolic node name */
+	snprintf(fc_host_symbolic_name(lport->host), 256,
+	    "QLogic %s v%s", QEDF_MODULE_NAME, QEDF_VERSION);
+
+	return 0;
+}
+
+/*
+ * NPIV functions
+ */
+
+static int qedf_vport_libfc_config(struct fc_vport *vport,
+	struct fc_lport *lport)
+{
+	lport->link_up = 0;
+	lport->qfull = 0;
+	lport->max_retry_count = QEDF_FLOGI_RETRY_CNT;
+	lport->max_rport_retry_count = QEDF_RPORT_RETRY_CNT;
+	lport->service_params = (FCP_SPPF_INIT_FCN | FCP_SPPF_RD_XRDY_DIS |
+	    FCP_SPPF_RETRY | FCP_SPPF_CONF_COMPL);
+	lport->boot_time = jiffies;
+	lport->e_d_tov = 2 * 1000;
+	lport->r_a_tov = 10 * 1000;
+	lport->does_npiv = 1; /* Temporary until we add NPIV support */
+
+	/* Allocate stats for vport */
+	if (fc_lport_init_stats(lport))
+		return -ENOMEM;
+
+	/* Finish lport config */
+	fc_lport_config(lport);
+
+	/* offload related configuration */
+	lport->crc_offload = 0;
+	lport->seq_offload = 0;
+	lport->lro_enabled = 0;
+	lport->lro_xid = 0;
+	lport->lso_max = 0;
+
+	return 0;
+}
+
+static int qedf_vport_create(struct fc_vport *vport, bool disabled)
+{
+	struct Scsi_Host *shost = vport_to_shost(vport);
+	struct fc_lport *n_port = shost_priv(shost);
+	struct fc_lport *vn_port;
+	struct qedf_ctx *base_qedf = lport_priv(n_port);
+	struct qedf_ctx *vport_qedf;
+
+	char buf[32];
+	int rc = 0;
+
+	rc = fcoe_validate_vport_create(vport);
+	if (rc) {
+		fcoe_wwn_to_str(vport->port_name, buf, sizeof(buf));
+		QEDF_WARN(&(base_qedf->dbg_ctx), "Failed to create vport, "
+			   "WWPN (0x%s) already exists.\n", buf);
+		goto err1;
+	}
+
+	if (atomic_read(&base_qedf->link_state) != QEDF_LINK_UP) {
+		QEDF_WARN(&(base_qedf->dbg_ctx), "Cannot create vport "
+			   "because link is not up.\n");
+		rc = -EIO;
+		goto err1;
+	}
+
+	vn_port = libfc_vport_create(vport, sizeof(struct qedf_ctx));
+	if (!vn_port) {
+		QEDF_WARN(&(base_qedf->dbg_ctx), "Could not create lport "
+			   "for vport.\n");
+		rc = -ENOMEM;
+		goto err1;
+	}
+
+	fcoe_wwn_to_str(vport->port_name, buf, sizeof(buf));
+	QEDF_ERR(&(base_qedf->dbg_ctx), "Creating NPIV port, WWPN=%s.\n",
+	    buf);
+
+	/* Copy some fields from base_qedf */
+	vport_qedf = lport_priv(vn_port);
+	memcpy(vport_qedf, base_qedf, sizeof(struct qedf_ctx));
+
+	/* Set qedf data specific to this vport */
+	vport_qedf->lport = vn_port;
+	/* Use same hba_lock as base_qedf */
+	vport_qedf->hba_lock = base_qedf->hba_lock;
+	vport_qedf->pdev = base_qedf->pdev;
+	vport_qedf->cmd_mgr = base_qedf->cmd_mgr;
+	init_completion(&vport_qedf->flogi_compl);
+	INIT_LIST_HEAD(&vport_qedf->fcports);
+
+	rc = qedf_vport_libfc_config(vport, vn_port);
+	if (rc) {
+		QEDF_ERR(&(base_qedf->dbg_ctx), "Could not allocate memory "
+		    "for lport stats.\n");
+		goto err2;
+	}
+
+	fc_set_wwnn(vn_port, vport->node_name);
+	fc_set_wwpn(vn_port, vport->port_name);
+	vport_qedf->wwnn = vn_port->wwnn;
+	vport_qedf->wwpn = vn_port->wwpn;
+
+	vn_port->host->transportt = qedf_fc_vport_transport_template;
+	vn_port->host->can_queue = QEDF_MAX_ELS_XID;
+	vn_port->host->max_lun = qedf_max_lun;
+	vn_port->host->sg_tablesize = QEDF_MAX_BDS_PER_CMD;
+	vn_port->host->max_cmd_len = QEDF_MAX_CDB_LEN;
+
+	rc = scsi_add_host(vn_port->host, &vport->dev);
+	if (rc) {
+		QEDF_WARN(&(base_qedf->dbg_ctx), "Error adding Scsi_Host.\n");
+		goto err2;
+	}
+
+	/* Set default dev_loss_tmo based on module parameter */
+	fc_host_dev_loss_tmo(vn_port->host) = qedf_dev_loss_tmo;
+
+	/* Init libfc stuffs */
+	memcpy(&vn_port->tt, &qedf_lport_template,
+		sizeof(qedf_lport_template));
+	fc_exch_init(vn_port);
+	fc_elsct_init(vn_port);
+	fc_lport_init(vn_port);
+	fc_disc_init(vn_port);
+	fc_disc_config(vn_port, vn_port);
+
+
+	/* Allocate the exchange manager */
+	shost = vport_to_shost(vport);
+	n_port = shost_priv(shost);
+	fc_exch_mgr_list_clone(n_port, vn_port);
+
+	/* Set max frame size */
+	fc_set_mfs(vn_port, QEDF_MFS);
+
+	fc_host_port_type(vn_port->host) = FC_PORTTYPE_UNKNOWN;
+
+	if (disabled) {
+		fc_vport_set_state(vport, FC_VPORT_DISABLED);
+	} else {
+		vn_port->boot_time = jiffies;
+		fc_fabric_login(vn_port);
+		fc_vport_setlink(vn_port);
+	}
+
+	QEDF_INFO(&(base_qedf->dbg_ctx), QEDF_LOG_NPIV, "vn_port=%p.\n",
+		   vn_port);
+
+	/* Set up debug context for vport */
+	vport_qedf->dbg_ctx.host_no = vn_port->host->host_no;
+	vport_qedf->dbg_ctx.pdev = base_qedf->pdev;
+
+err2:
+	scsi_host_put(vn_port->host);
+err1:
+	return rc;
+}
+
+static int qedf_vport_destroy(struct fc_vport *vport)
+{
+	struct Scsi_Host *shost = vport_to_shost(vport);
+	struct fc_lport *n_port = shost_priv(shost);
+	struct fc_lport *vn_port = vport->dd_data;
+
+	mutex_lock(&n_port->lp_mutex);
+	list_del(&vn_port->list);
+	mutex_unlock(&n_port->lp_mutex);
+
+	fc_fabric_logoff(vn_port);
+	fc_lport_destroy(vn_port);
+
+	/* Detach from scsi-ml */
+	fc_remove_host(vn_port->host);
+	scsi_remove_host(vn_port->host);
+
+	/*
+	 * Only try to release the exchange manager if the vn_port
+	 * configuration is complete.
+	 */
+	if (vn_port->state == LPORT_ST_READY)
+		fc_exch_mgr_free(vn_port);
+
+	/* Free memory used by statistical counters */
+	fc_lport_free_stats(vn_port);
+
+	/* Release Scsi_Host */
+	if (vn_port->host)
+		scsi_host_put(vn_port->host);
+
+	return 0;
+}
+
+static int qedf_vport_disable(struct fc_vport *vport, bool disable)
+{
+	struct fc_lport *lport = vport->dd_data;
+
+	if (disable) {
+		fc_vport_set_state(vport, FC_VPORT_DISABLED);
+		fc_fabric_logoff(lport);
+	} else {
+		lport->boot_time = jiffies;
+		fc_fabric_login(lport);
+		fc_vport_setlink(lport);
+	}
+	return 0;
+}
+
+/*
+ * During removal we need to wait for all the vports associated with a port
+ * to be destroyed so we avoid a race condition where libfc is still trying
+ * to reap vports while the driver remove function has already reaped the
+ * driver contexts associated with the physical port.
+ */
+static void qedf_wait_for_vport_destroy(struct qedf_ctx *qedf)
+{
+	struct fc_host_attrs *fc_host = shost_to_fc_host(qedf->lport->host);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_NPIV,
+	    "Entered.\n");
+	while (fc_host->npiv_vports_inuse > 0) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_NPIV,
+		    "Waiting for all vports to be reaped.\n");
+		msleep(1000);
+	}
+}
+
+/**
+ * qedf_fcoe_reset - Resets the fcoe
+ *
+ * @shost: shost the reset is from
+ *
+ * Returns: always 0
+ */
+static int qedf_fcoe_reset(struct Scsi_Host *shost)
+{
+	struct fc_lport *lport = shost_priv(shost);
+
+	fc_fabric_logoff(lport);
+	fc_fabric_login(lport);
+	return 0;
+}
+
+static struct fc_host_statistics *qedf_fc_get_host_stats(struct Scsi_Host
+	*shost)
+{
+	struct fc_host_statistics *qedf_stats;
+	struct fc_lport *lport = shost_priv(shost);
+	struct qedf_ctx *qedf = lport_priv(lport);
+	struct qed_fcoe_stats *fw_fcoe_stats;
+
+	qedf_stats = fc_get_host_stats(shost);
+
+	/* We don't collect offload stats for specific NPIV ports */
+	if (lport->vport)
+		goto out;
+
+	fw_fcoe_stats = kmalloc(sizeof(struct qed_fcoe_stats), GFP_KERNEL);
+	if (!fw_fcoe_stats) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Could not allocate memory for "
+		    "fw_fcoe_stats.\n");
+		goto out;
+	}
+
+	/* Query firmware for offload stats */
+	qed_ops->get_stats(qedf->cdev, fw_fcoe_stats);
+
+	/*
+	 * The expectation is that we add our offload stats to the stats
+	 * being maintained by libfc each time the fc_get_host_status callback
+	 * is invoked. The additions are not carried over for each call to
+	 * the fc_get_host_stats callback.
+	 */
+	qedf_stats->tx_frames += fw_fcoe_stats->fcoe_tx_data_pkt_cnt +
+	    fw_fcoe_stats->fcoe_tx_xfer_pkt_cnt +
+	    fw_fcoe_stats->fcoe_tx_other_pkt_cnt;
+	qedf_stats->rx_frames += fw_fcoe_stats->fcoe_rx_data_pkt_cnt +
+	    fw_fcoe_stats->fcoe_rx_xfer_pkt_cnt +
+	    fw_fcoe_stats->fcoe_rx_other_pkt_cnt;
+	qedf_stats->fcp_input_megabytes +=
+	    do_div(fw_fcoe_stats->fcoe_rx_byte_cnt, 1000000);
+	qedf_stats->fcp_output_megabytes +=
+	    do_div(fw_fcoe_stats->fcoe_tx_byte_cnt, 1000000);
+	qedf_stats->rx_words += fw_fcoe_stats->fcoe_rx_byte_cnt / 4;
+	qedf_stats->tx_words += fw_fcoe_stats->fcoe_tx_byte_cnt / 4;
+	qedf_stats->invalid_crc_count +=
+	    fw_fcoe_stats->fcoe_silent_drop_pkt_crc_error_cnt;
+	qedf_stats->dumped_frames =
+	    fw_fcoe_stats->fcoe_silent_drop_total_pkt_cnt;
+	qedf_stats->error_frames +=
+	    fw_fcoe_stats->fcoe_silent_drop_total_pkt_cnt;
+	qedf_stats->fcp_input_requests += qedf->input_requests;
+	qedf_stats->fcp_output_requests += qedf->output_requests;
+	qedf_stats->fcp_control_requests += qedf->control_requests;
+	qedf_stats->fcp_packet_aborts += qedf->packet_aborts;
+	qedf_stats->fcp_frame_alloc_failures += qedf->alloc_failures;
+
+	kfree(fw_fcoe_stats);
+out:
+	return qedf_stats;
+}
+
+static struct fc_function_template qedf_fc_transport_fn = {
+	.show_host_node_name = 1,
+	.show_host_port_name = 1,
+	.show_host_supported_classes = 1,
+	.show_host_supported_fc4s = 1,
+	.show_host_active_fc4s = 1,
+	.show_host_maxframe_size = 1,
+
+	.show_host_port_id = 1,
+	.show_host_supported_speeds = 1,
+	.get_host_speed = fc_get_host_speed,
+	.show_host_speed = 1,
+	.show_host_port_type = 1,
+	.get_host_port_state = fc_get_host_port_state,
+	.show_host_port_state = 1,
+	.show_host_symbolic_name = 1,
+
+	/*
+	 * Tell FC transport to allocate enough space to store the backpointer
+	 * for the associate qedf_rport struct.
+	 */
+	.dd_fcrport_size = (sizeof(struct fc_rport_libfc_priv) +
+				sizeof(struct qedf_rport)),
+	.show_rport_maxframe_size = 1,
+	.show_rport_supported_classes = 1,
+	.show_host_fabric_name = 1,
+	.show_starget_node_name = 1,
+	.show_starget_port_name = 1,
+	.show_starget_port_id = 1,
+	.set_rport_dev_loss_tmo = fc_set_rport_loss_tmo,
+	.show_rport_dev_loss_tmo = 1,
+	.get_fc_host_stats = qedf_fc_get_host_stats,
+	.issue_fc_host_lip = qedf_fcoe_reset,
+	.vport_create = qedf_vport_create,
+	.vport_delete = qedf_vport_destroy,
+	.vport_disable = qedf_vport_disable,
+	.bsg_request = fc_lport_bsg_request,
+};
+
+static struct fc_function_template qedf_fc_vport_transport_fn = {
+	.show_host_node_name = 1,
+	.show_host_port_name = 1,
+	.show_host_supported_classes = 1,
+	.show_host_supported_fc4s = 1,
+	.show_host_active_fc4s = 1,
+	.show_host_maxframe_size = 1,
+	.show_host_port_id = 1,
+	.show_host_supported_speeds = 1,
+	.get_host_speed = fc_get_host_speed,
+	.show_host_speed = 1,
+	.show_host_port_type = 1,
+	.get_host_port_state = fc_get_host_port_state,
+	.show_host_port_state = 1,
+	.show_host_symbolic_name = 1,
+	.dd_fcrport_size = (sizeof(struct fc_rport_libfc_priv) +
+				sizeof(struct qedf_rport)),
+	.show_rport_maxframe_size = 1,
+	.show_rport_supported_classes = 1,
+	.show_host_fabric_name = 1,
+	.show_starget_node_name = 1,
+	.show_starget_port_name = 1,
+	.show_starget_port_id = 1,
+	.set_rport_dev_loss_tmo = fc_set_rport_loss_tmo,
+	.show_rport_dev_loss_tmo = 1,
+	.get_fc_host_stats = fc_get_host_stats,
+	.issue_fc_host_lip = qedf_fcoe_reset,
+	.bsg_request = fc_lport_bsg_request,
+};
+
+static bool qedf_fp_has_work(struct qedf_fastpath *fp)
+{
+	struct qedf_ctx *qedf = fp->qedf;
+	struct global_queue *que;
+	struct qed_sb_info *sb_info = fp->sb_info;
+	struct status_block *sb = sb_info->sb_virt;
+	u16 prod_idx;
+
+	/* Get the pointer to the global CQ this completion is on */
+	que = qedf->global_queues[fp->sb_id];
+
+	/* Be sure all responses have been written to PI */
+	rmb();
+
+	/* Get the current firmware producer index */
+	prod_idx = sb->pi_array[QEDF_FCOE_PARAMS_GL_RQ_PI];
+
+	return (que->cq_prod_idx != prod_idx);
+}
+
+/*
+ * Interrupt handler code.
+ */
+
+/* Process completion queue and copy CQE contents for deferred processesing
+ *
+ * Return true if we should wake the I/O thread, false if not.
+ */
+static bool qedf_process_completions(struct qedf_fastpath *fp)
+{
+	struct qedf_ctx *qedf = fp->qedf;
+	struct qed_sb_info *sb_info = fp->sb_info;
+	struct status_block *sb = sb_info->sb_virt;
+	struct global_queue *que;
+	u16 prod_idx;
+	struct fcoe_cqe *cqe;
+	struct qedf_io_work *io_work;
+	int num_handled = 0;
+	unsigned int cpu;
+	struct qedf_ioreq *io_req = NULL;
+	u16 xid;
+	u16 new_cqes;
+	u32 comp_type;
+
+	/* Get the current firmware producer index */
+	prod_idx = sb->pi_array[QEDF_FCOE_PARAMS_GL_RQ_PI];
+
+	/* Get the pointer to the global CQ this completion is on */
+	que = qedf->global_queues[fp->sb_id];
+
+	/* Calculate the amount of new elements since last processing */
+	new_cqes = (prod_idx >= que->cq_prod_idx) ?
+	    (prod_idx - que->cq_prod_idx) :
+	    0x10000 - que->cq_prod_idx + prod_idx;
+
+	/* Save producer index */
+	que->cq_prod_idx = prod_idx;
+
+	while (new_cqes) {
+		fp->completions++;
+		num_handled++;
+		cqe = &que->cq[que->cq_cons_idx];
+
+		comp_type = (cqe->cqe_data >> FCOE_CQE_CQE_TYPE_SHIFT) &
+		    FCOE_CQE_CQE_TYPE_MASK;
+
+		/*
+		 * Process unsolicited CQEs directly in the interrupt handler
+		 * sine we need the fastpath ID
+		 */
+		if (comp_type == FCOE_UNSOLIC_CQE_TYPE) {
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_UNSOL,
+			   "Unsolicated CQE.\n");
+			qedf_process_unsol_compl(qedf, fp->sb_id, cqe);
+			/*
+			 * Don't add a work list item.  Increment consumer
+			 * consumer index and move on.
+			 */
+			goto inc_idx;
+		}
+
+		xid = cqe->cqe_data & FCOE_CQE_TASK_ID_MASK;
+		io_req = &qedf->cmd_mgr->cmds[xid];
+
+		/*
+		 * Figure out which percpu thread we should queue this I/O
+		 * on.
+		 */
+		if (!io_req)
+			/* If there is not io_req assocated with this CQE
+			 * just queue it on CPU 0
+			 */
+			cpu = 0;
+		else {
+			cpu = io_req->cpu;
+			io_req->int_cpu = smp_processor_id();
+		}
+
+		io_work = mempool_alloc(qedf->io_mempool, GFP_ATOMIC);
+		if (!io_work) {
+			QEDF_WARN(&(qedf->dbg_ctx), "Could not allocate "
+				   "work for I/O completion.\n");
+			continue;
+		}
+		memset(io_work, 0, sizeof(struct qedf_io_work));
+
+		INIT_WORK(&io_work->work, qedf_fp_io_handler);
+
+		/* Copy contents of CQE for deferred processing */
+		memcpy(&io_work->cqe, cqe, sizeof(struct fcoe_cqe));
+
+		io_work->qedf = fp->qedf;
+		io_work->fp = NULL; /* Only used for unsolicited frames */
+
+		queue_work_on(cpu, qedf_io_wq, &io_work->work);
+
+inc_idx:
+		que->cq_cons_idx++;
+		if (que->cq_cons_idx == fp->cq_num_entries)
+			que->cq_cons_idx = 0;
+		new_cqes--;
+	}
+
+	return true;
+}
+
+
+/* MSI-X fastpath handler code */
+static irqreturn_t qedf_msix_handler(int irq, void *dev_id)
+{
+	struct qedf_fastpath *fp = dev_id;
+
+	if (!fp) {
+		QEDF_ERR(NULL, "fp is null.\n");
+		return IRQ_HANDLED;
+	}
+	if (!fp->sb_info) {
+		QEDF_ERR(NULL, "fp->sb_info in null.");
+		return IRQ_HANDLED;
+	}
+
+	/*
+	 * Disable interrupts for this status block while we process new
+	 * completions
+	 */
+	qed_sb_ack(fp->sb_info, IGU_INT_DISABLE, 0 /*do not update*/);
+
+	while (1) {
+		qedf_process_completions(fp);
+
+		if (qedf_fp_has_work(fp) == 0) {
+			/* Update the sb information */
+			qed_sb_update_sb_idx(fp->sb_info);
+
+			/* Check for more work */
+			rmb();
+
+			if (qedf_fp_has_work(fp) == 0) {
+				/* Re-enable interrupts */
+				qed_sb_ack(fp->sb_info, IGU_INT_ENABLE, 1);
+				return IRQ_HANDLED;
+			}
+		}
+	}
+
+	/* Do we ever want to break out of above loop? */
+	return IRQ_HANDLED;
+}
+
+/* simd handler for MSI/INTa */
+static void qedf_simd_int_handler(void *cookie)
+{
+	/* Cookie is qedf_ctx struct */
+	struct qedf_ctx *qedf = (struct qedf_ctx *)cookie;
+
+	QEDF_WARN(&(qedf->dbg_ctx), "qedf=%p.\n", qedf);
+}
+
+#define QEDF_SIMD_HANDLER_NUM		0
+static void qedf_sync_free_irqs(struct qedf_ctx *qedf)
+{
+	int i;
+
+	if (qedf->int_info.msix_cnt) {
+		for (i = 0; i < qedf->int_info.used_cnt; i++) {
+			synchronize_irq(qedf->int_info.msix[i].vector);
+			irq_set_affinity_hint(qedf->int_info.msix[i].vector,
+			    NULL);
+			irq_set_affinity_notifier(qedf->int_info.msix[i].vector,
+			    NULL);
+			free_irq(qedf->int_info.msix[i].vector,
+			    &qedf->fp_array[i]);
+		}
+	} else
+		qed_ops->common->simd_handler_clean(qedf->cdev,
+		    QEDF_SIMD_HANDLER_NUM);
+
+	qedf->int_info.used_cnt = 0;
+	qed_ops->common->set_fp_int(qedf->cdev, 0);
+}
+
+static int qedf_request_msix_irq(struct qedf_ctx *qedf)
+{
+	int i, rc, cpu;
+
+	cpu = cpumask_first(cpu_online_mask);
+	for (i = 0; i < qedf->num_queues; i++) {
+		rc = request_irq(qedf->int_info.msix[i].vector,
+		    qedf_msix_handler, 0, "qedf", &qedf->fp_array[i]);
+
+		if (rc) {
+			QEDF_WARN(&(qedf->dbg_ctx), "request_irq failed.\n");
+			qedf_sync_free_irqs(qedf);
+			return rc;
+		}
+
+		qedf->int_info.used_cnt++;
+		rc = irq_set_affinity_hint(qedf->int_info.msix[i].vector,
+		    get_cpu_mask(cpu));
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	}
+
+	return 0;
+}
+
+static int qedf_setup_int(struct qedf_ctx *qedf)
+{
+	int rc = 0;
+
+	/*
+	 * Learn interrupt configuration
+	 */
+	rc = qed_ops->common->set_fp_int(qedf->cdev, num_online_cpus());
+
+	rc  = qed_ops->common->get_fp_int(qedf->cdev, &qedf->int_info);
+	if (rc)
+		return 0;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Number of msix_cnt = "
+		   "0x%x num of cpus = 0x%x\n", qedf->int_info.msix_cnt,
+		   num_online_cpus());
+
+	if (qedf->int_info.msix_cnt)
+		return qedf_request_msix_irq(qedf);
+
+	qed_ops->common->simd_handler_config(qedf->cdev, &qedf,
+	    QEDF_SIMD_HANDLER_NUM, qedf_simd_int_handler);
+	qedf->int_info.used_cnt = 1;
+
+	return 0;
+}
+
+/* Main function for libfc frame reception */
+static void qedf_recv_frame(struct qedf_ctx *qedf,
+	struct sk_buff *skb)
+{
+	u32 fr_len;
+	struct fc_lport *lport;
+	struct fc_frame_header *fh;
+	struct fcoe_crc_eof crc_eof;
+	struct fc_frame *fp;
+	u8 *mac = NULL;
+	u8 *dest_mac = NULL;
+	struct fcoe_hdr *hp;
+	struct qedf_rport *fcport;
+
+	lport = qedf->lport;
+	if (lport == NULL || lport->state == LPORT_ST_DISABLED) {
+		QEDF_WARN(NULL, "Invalid lport struct or lport disabled.\n");
+		kfree_skb(skb);
+		return;
+	}
+
+	if (skb_is_nonlinear(skb))
+		skb_linearize(skb);
+	mac = eth_hdr(skb)->h_source;
+	dest_mac = eth_hdr(skb)->h_dest;
+
+	/* Pull the header */
+	hp = (struct fcoe_hdr *)skb->data;
+	fh = (struct fc_frame_header *) skb_transport_header(skb);
+	skb_pull(skb, sizeof(struct fcoe_hdr));
+	fr_len = skb->len - sizeof(struct fcoe_crc_eof);
+
+	fp = (struct fc_frame *)skb;
+	fc_frame_init(fp);
+	fr_dev(fp) = lport;
+	fr_sof(fp) = hp->fcoe_sof;
+	if (skb_copy_bits(skb, fr_len, &crc_eof, sizeof(crc_eof))) {
+		kfree_skb(skb);
+		return;
+	}
+	fr_eof(fp) = crc_eof.fcoe_eof;
+	fr_crc(fp) = crc_eof.fcoe_crc32;
+	if (pskb_trim(skb, fr_len)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	fh = fc_frame_header_get(fp);
+
+	if (fh->fh_r_ctl == FC_RCTL_DD_SOL_DATA &&
+	    fh->fh_type == FC_TYPE_FCP) {
+		/* Drop FCP data. We dont this in L2 path */
+		kfree_skb(skb);
+		return;
+	}
+	if (fh->fh_r_ctl == FC_RCTL_ELS_REQ &&
+	    fh->fh_type == FC_TYPE_ELS) {
+		switch (fc_frame_payload_op(fp)) {
+		case ELS_LOGO:
+			if (ntoh24(fh->fh_s_id) == FC_FID_FLOGI) {
+				/* drop non-FIP LOGO */
+				kfree_skb(skb);
+				return;
+			}
+			break;
+		}
+	}
+
+	if (fh->fh_r_ctl == FC_RCTL_BA_ABTS) {
+		/* Drop incoming ABTS */
+		kfree_skb(skb);
+		return;
+	}
+
+	/*
+	 * If a connection is uploading, drop incoming FCoE frames as there
+	 * is a small window where we could try to return a frame while libfc
+	 * is trying to clean things up.
+	 */
+
+	/* Get fcport associated with d_id if it exists */
+	fcport = qedf_fcport_lookup(qedf, ntoh24(fh->fh_d_id));
+
+	if (fcport && test_bit(QEDF_RPORT_UPLOADING_CONNECTION,
+	    &fcport->flags)) {
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
+		    "Connection uploading, dropping fp=%p.\n", fp);
+		kfree_skb(skb);
+		return;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2, "FCoE frame receive: "
+	    "skb=%p fp=%p src=%06x dest=%06x r_ctl=%x fh_type=%x.\n", skb, fp,
+	    ntoh24(fh->fh_s_id), ntoh24(fh->fh_d_id), fh->fh_r_ctl,
+	    fh->fh_type);
+	if (qedf_dump_frames)
+		print_hex_dump(KERN_WARNING, "fcoe: ", DUMP_PREFIX_OFFSET, 16,
+		    1, skb->data, skb->len, false);
+	fc_exch_recv(lport, fp);
+}
+
+static void qedf_ll2_process_skb(struct work_struct *work)
+{
+	struct qedf_skb_work *skb_work =
+	    container_of(work, struct qedf_skb_work, work);
+	struct qedf_ctx *qedf = skb_work->qedf;
+	struct sk_buff *skb = skb_work->skb;
+	struct ethhdr *eh;
+
+	if (!qedf) {
+		QEDF_ERR(NULL, "qedf is NULL\n");
+		goto err_out;
+	}
+
+	eh = (struct ethhdr *)skb->data;
+
+	/* Undo VLAN encapsulation */
+	if (eh->h_proto == htons(ETH_P_8021Q)) {
+		memmove((u8 *)eh + VLAN_HLEN, eh, ETH_ALEN * 2);
+		eh = (struct ethhdr *)skb_pull(skb, VLAN_HLEN);
+		skb_reset_mac_header(skb);
+	}
+
+	/*
+	 * Process either a FIP frame or FCoE frame based on the
+	 * protocol value.  If it's not either just drop the
+	 * frame.
+	 */
+	if (eh->h_proto == htons(ETH_P_FIP)) {
+		qedf_fip_recv(qedf, skb);
+		goto out;
+	} else if (eh->h_proto == htons(ETH_P_FCOE)) {
+		__skb_pull(skb, ETH_HLEN);
+		qedf_recv_frame(qedf, skb);
+		goto out;
+	} else
+		goto err_out;
+
+err_out:
+	kfree_skb(skb);
+out:
+	kfree(skb_work);
+	return;
+}
+
+static int qedf_ll2_rx(void *cookie, struct sk_buff *skb,
+	u32 arg1, u32 arg2)
+{
+	struct qedf_ctx *qedf = (struct qedf_ctx *)cookie;
+	struct qedf_skb_work *skb_work;
+
+	skb_work = kzalloc(sizeof(struct qedf_skb_work), GFP_ATOMIC);
+	if (!skb_work) {
+		QEDF_WARN(&(qedf->dbg_ctx), "Could not allocate skb_work so "
+			   "dropping frame.\n");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	INIT_WORK(&skb_work->work, qedf_ll2_process_skb);
+	skb_work->skb = skb;
+	skb_work->qedf = qedf;
+	queue_work(qedf->ll2_recv_wq, &skb_work->work);
+
+	return 0;
+}
+
+static struct qed_ll2_cb_ops qedf_ll2_cb_ops = {
+	.rx_cb = qedf_ll2_rx,
+	.tx_cb = NULL,
+};
+
+/* Main thread to process I/O completions */
+void qedf_fp_io_handler(struct work_struct *work)
+{
+	struct qedf_io_work *io_work =
+	    container_of(work, struct qedf_io_work, work);
+	u32 comp_type;
+
+	/*
+	 * Deferred part of unsolicited CQE sends
+	 * frame to libfc.
+	 */
+	comp_type = (io_work->cqe.cqe_data >>
+	    FCOE_CQE_CQE_TYPE_SHIFT) &
+	    FCOE_CQE_CQE_TYPE_MASK;
+	if (comp_type == FCOE_UNSOLIC_CQE_TYPE &&
+	    io_work->fp)
+		fc_exch_recv(io_work->qedf->lport, io_work->fp);
+	else
+		qedf_process_cqe(io_work->qedf, &io_work->cqe);
+
+	kfree(io_work);
+}
+
+static int qedf_alloc_and_init_sb(struct qedf_ctx *qedf,
+	struct qed_sb_info *sb_info, u16 sb_id)
+{
+	struct status_block *sb_virt;
+	dma_addr_t sb_phys;
+	int ret;
+
+	sb_virt = dma_alloc_coherent(&qedf->pdev->dev,
+	    sizeof(struct status_block), &sb_phys, GFP_KERNEL);
+
+	if (!sb_virt) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Status block allocation failed "
+			  "for id = %d.\n", sb_id);
+		return -ENOMEM;
+	}
+
+	ret = qed_ops->common->sb_init(qedf->cdev, sb_info, sb_virt, sb_phys,
+	    sb_id, QED_SB_TYPE_STORAGE);
+
+	if (ret) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Status block initialization "
+			  "failed for id = %d.\n", sb_id);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void qedf_free_sb(struct qedf_ctx *qedf, struct qed_sb_info *sb_info)
+{
+	if (sb_info->sb_virt)
+		dma_free_coherent(&qedf->pdev->dev, sizeof(*sb_info->sb_virt),
+		    (void *)sb_info->sb_virt, sb_info->sb_phys);
+}
+
+static void qedf_destroy_sb(struct qedf_ctx *qedf)
+{
+	int id;
+	struct qedf_fastpath *fp = NULL;
+
+	for (id = 0; id < qedf->num_queues; id++) {
+		fp = &(qedf->fp_array[id]);
+		if (fp->sb_id == QEDF_SB_ID_NULL)
+			break;
+		qedf_free_sb(qedf, fp->sb_info);
+		kfree(fp->sb_info);
+	}
+	kfree(qedf->fp_array);
+}
+
+static int qedf_prepare_sb(struct qedf_ctx *qedf)
+{
+	int id;
+	struct qedf_fastpath *fp;
+	int ret;
+
+	qedf->fp_array =
+	    kcalloc(qedf->num_queues, sizeof(struct qedf_fastpath),
+		GFP_KERNEL);
+
+	if (!qedf->fp_array) {
+		QEDF_ERR(&(qedf->dbg_ctx), "fastpath array allocation "
+			  "failed.\n");
+		return -ENOMEM;
+	}
+
+	for (id = 0; id < qedf->num_queues; id++) {
+		fp = &(qedf->fp_array[id]);
+		fp->sb_id = QEDF_SB_ID_NULL;
+		fp->sb_info = kcalloc(1, sizeof(*fp->sb_info), GFP_KERNEL);
+		if (!fp->sb_info) {
+			QEDF_ERR(&(qedf->dbg_ctx), "SB info struct "
+				  "allocation failed.\n");
+			goto err;
+		}
+		ret = qedf_alloc_and_init_sb(qedf, fp->sb_info, id);
+		if (ret) {
+			QEDF_ERR(&(qedf->dbg_ctx), "SB allocation and "
+				  "initialization failed.\n");
+			goto err;
+		}
+		fp->sb_id = id;
+		fp->qedf = qedf;
+		fp->cq_num_entries =
+		    qedf->global_queues[id]->cq_mem_size /
+		    sizeof(struct fcoe_cqe);
+	}
+err:
+	return 0;
+}
+
+void qedf_process_cqe(struct qedf_ctx *qedf, struct fcoe_cqe *cqe)
+{
+	u16 xid;
+	struct qedf_ioreq *io_req;
+	struct qedf_rport *fcport;
+	u32 comp_type;
+
+	comp_type = (cqe->cqe_data >> FCOE_CQE_CQE_TYPE_SHIFT) &
+	    FCOE_CQE_CQE_TYPE_MASK;
+
+	xid = cqe->cqe_data & FCOE_CQE_TASK_ID_MASK;
+	io_req = &qedf->cmd_mgr->cmds[xid];
+
+	/* Completion not for a valid I/O anymore so just return */
+	if (!io_req)
+		return;
+
+	fcport = io_req->fcport;
+
+	if (fcport == NULL) {
+		QEDF_ERR(&(qedf->dbg_ctx), "fcport is NULL.\n");
+		return;
+	}
+
+	/*
+	 * Check that fcport is offloaded.  If it isn't then the spinlock
+	 * isn't valid and shouldn't be taken. We should just return.
+	 */
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
+		return;
+	}
+
+
+	switch (comp_type) {
+	case FCOE_GOOD_COMPLETION_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		switch (io_req->cmd_type) {
+		case QEDF_SCSI_CMD:
+			qedf_scsi_completion(qedf, cqe, io_req);
+			break;
+		case QEDF_ELS:
+			qedf_process_els_compl(qedf, cqe, io_req);
+			break;
+		case QEDF_TASK_MGMT_CMD:
+			qedf_process_tmf_compl(qedf, cqe, io_req);
+			break;
+		case QEDF_SEQ_CLEANUP:
+			qedf_process_seq_cleanup_compl(qedf, cqe, io_req);
+			break;
+		}
+		break;
+	case FCOE_ERROR_DETECTION_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Error detect CQE.\n");
+		qedf_process_error_detect(qedf, cqe, io_req);
+		break;
+	case FCOE_EXCH_CLEANUP_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Cleanup CQE.\n");
+		qedf_process_cleanup_compl(qedf, cqe, io_req);
+		break;
+	case FCOE_ABTS_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Abort CQE.\n");
+		qedf_process_abts_compl(qedf, cqe, io_req);
+		break;
+	case FCOE_DUMMY_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Dummy CQE.\n");
+		break;
+	case FCOE_LOCAL_COMP_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Local completion CQE.\n");
+		break;
+	case FCOE_WARNING_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Warning CQE.\n");
+		qedf_process_warning_compl(qedf, cqe, io_req);
+		break;
+	case MAX_FCOE_CQE_TYPE:
+		atomic_inc(&fcport->free_sqes);
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Max FCoE CQE.\n");
+		break;
+	default:
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
+		    "Default CQE.\n");
+		break;
+	}
+}
+
+static void qedf_free_bdq(struct qedf_ctx *qedf)
+{
+	int i;
+
+	if (qedf->bdq_pbl_list)
+		dma_free_coherent(&qedf->pdev->dev, QEDF_PAGE_SIZE,
+		    qedf->bdq_pbl_list, qedf->bdq_pbl_list_dma);
+
+	if (qedf->bdq_pbl)
+		dma_free_coherent(&qedf->pdev->dev, qedf->bdq_pbl_mem_size,
+		    qedf->bdq_pbl, qedf->bdq_pbl_dma);
+
+	for (i = 0; i < QEDF_BDQ_SIZE; i++) {
+		if (qedf->bdq[i].buf_addr) {
+			dma_free_coherent(&qedf->pdev->dev, QEDF_BDQ_BUF_SIZE,
+			    qedf->bdq[i].buf_addr, qedf->bdq[i].buf_dma);
+		}
+	}
+}
+
+static void qedf_free_global_queues(struct qedf_ctx *qedf)
+{
+	int i;
+	struct global_queue **gl = qedf->global_queues;
+
+	for (i = 0; i < qedf->num_queues; i++) {
+		if (!gl[i])
+			continue;
+
+		if (gl[i]->cq)
+			dma_free_coherent(&qedf->pdev->dev,
+			    gl[i]->cq_mem_size, gl[i]->cq, gl[i]->cq_dma);
+		if (gl[i]->cq_pbl)
+			dma_free_coherent(&qedf->pdev->dev, gl[i]->cq_pbl_size,
+			    gl[i]->cq_pbl, gl[i]->cq_pbl_dma);
+
+		kfree(gl[i]);
+	}
+
+	qedf_free_bdq(qedf);
+}
+
+static int qedf_alloc_bdq(struct qedf_ctx *qedf)
+{
+	int i;
+	struct scsi_bd *pbl;
+	u64 *list;
+	dma_addr_t page;
+
+	/* Alloc dma memory for BDQ buffers */
+	for (i = 0; i < QEDF_BDQ_SIZE; i++) {
+		qedf->bdq[i].buf_addr = dma_alloc_coherent(&qedf->pdev->dev,
+		    QEDF_BDQ_BUF_SIZE, &qedf->bdq[i].buf_dma, GFP_KERNEL);
+		if (!qedf->bdq[i].buf_addr) {
+			QEDF_ERR(&(qedf->dbg_ctx), "Could not allocate BDQ "
+			    "buffer %d.\n", i);
+			return -ENOMEM;
+		}
+	}
+
+	/* Alloc dma memory for BDQ page buffer list */
+	qedf->bdq_pbl_mem_size =
+	    QEDF_BDQ_SIZE * sizeof(struct scsi_bd);
+	qedf->bdq_pbl_mem_size =
+	    ALIGN(qedf->bdq_pbl_mem_size, QEDF_PAGE_SIZE);
+
+	qedf->bdq_pbl = dma_alloc_coherent(&qedf->pdev->dev,
+	    qedf->bdq_pbl_mem_size, &qedf->bdq_pbl_dma, GFP_KERNEL);
+	if (!qedf->bdq_pbl) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Could not allocate BDQ PBL.\n");
+		return -ENOMEM;
+	}
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+	    "BDQ PBL addr=0x%p dma=0x%llx.\n", qedf->bdq_pbl,
+	    qedf->bdq_pbl_dma);
+
+	/*
+	 * Populate BDQ PBL with physical and virtual address of individual
+	 * BDQ buffers
+	 */
+	pbl = (struct scsi_bd *)qedf->bdq_pbl;
+	for (i = 0; i < QEDF_BDQ_SIZE; i++) {
+		pbl->address.hi = cpu_to_le32(U64_HI(qedf->bdq[i].buf_dma));
+		pbl->address.lo = cpu_to_le32(U64_LO(qedf->bdq[i].buf_dma));
+		pbl->opaque.hi = 0;
+		/* Opaque lo data is an index into the BDQ array */
+		pbl->opaque.lo = cpu_to_le32(i);
+		pbl++;
+	}
+
+	/* Allocate list of PBL pages */
+	qedf->bdq_pbl_list = dma_alloc_coherent(&qedf->pdev->dev,
+	    QEDF_PAGE_SIZE, &qedf->bdq_pbl_list_dma, GFP_KERNEL);
+	if (!qedf->bdq_pbl_list) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Could not allocate list of PBL "
+		    "pages.\n");
+		return -ENOMEM;
+	}
+	memset(qedf->bdq_pbl_list, 0, QEDF_PAGE_SIZE);
+
+	/*
+	 * Now populate PBL list with pages that contain pointers to the
+	 * individual buffers.
+	 */
+	qedf->bdq_pbl_list_num_entries = qedf->bdq_pbl_mem_size /
+	    QEDF_PAGE_SIZE;
+	list = (u64 *)qedf->bdq_pbl_list;
+	page = qedf->bdq_pbl_list_dma;
+	for (i = 0; i < qedf->bdq_pbl_list_num_entries; i++) {
+		*list = qedf->bdq_pbl_dma;
+		list++;
+		page += QEDF_PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+static int qedf_alloc_global_queues(struct qedf_ctx *qedf)
+{
+	u32 *list;
+	int i;
+	int status = 0, rc;
+	u32 *pbl;
+	dma_addr_t page;
+	int num_pages;
+
+	/* Allocate and map CQs, RQs */
+	/*
+	 * Number of global queues (CQ / RQ). This should
+	 * be <= number of available MSIX vectors for the PF
+	 */
+	if (!qedf->num_queues) {
+		QEDF_ERR(&(qedf->dbg_ctx), "No MSI-X vectors available!\n");
+		return 1;
+	}
+
+	/*
+	 * Make sure we allocated the PBL that will contain the physical
+	 * addresses of our queues
+	 */
+	if (!qedf->p_cpuq) {
+		status = 1;
+		goto mem_alloc_failure;
+	}
+
+	qedf->global_queues = kzalloc((sizeof(struct global_queue *)
+	    * qedf->num_queues), GFP_KERNEL);
+	if (!qedf->global_queues) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Unable to allocate global "
+			  "queues array ptr memory\n");
+		return -ENOMEM;
+	}
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+		   "qedf->global_queues=%p.\n", qedf->global_queues);
+
+	/* Allocate DMA coherent buffers for BDQ */
+	rc = qedf_alloc_bdq(qedf);
+	if (rc)
+		goto mem_alloc_failure;
+
+	/* Allocate a CQ and an associated PBL for each MSI-X vector */
+	for (i = 0; i < qedf->num_queues; i++) {
+		qedf->global_queues[i] = kzalloc(sizeof(struct global_queue),
+		    GFP_KERNEL);
+		if (!qedf->global_queues[i]) {
+			QEDF_WARN(&(qedf->dbg_ctx), "Unable to allocation "
+				   "global queue %d.\n", i);
+			goto mem_alloc_failure;
+		}
+
+		qedf->global_queues[i]->cq_mem_size =
+		    FCOE_PARAMS_CQ_NUM_ENTRIES * sizeof(struct fcoe_cqe);
+		qedf->global_queues[i]->cq_mem_size =
+		    ALIGN(qedf->global_queues[i]->cq_mem_size, QEDF_PAGE_SIZE);
+
+		qedf->global_queues[i]->cq_pbl_size =
+		    (qedf->global_queues[i]->cq_mem_size /
+		    PAGE_SIZE) * sizeof(void *);
+		qedf->global_queues[i]->cq_pbl_size =
+		    ALIGN(qedf->global_queues[i]->cq_pbl_size, QEDF_PAGE_SIZE);
+
+		qedf->global_queues[i]->cq =
+		    dma_alloc_coherent(&qedf->pdev->dev,
+			qedf->global_queues[i]->cq_mem_size,
+			&qedf->global_queues[i]->cq_dma, GFP_KERNEL);
+
+		if (!qedf->global_queues[i]->cq) {
+			QEDF_WARN(&(qedf->dbg_ctx), "Could not allocate "
+				   "cq.\n");
+			status = -ENOMEM;
+			goto mem_alloc_failure;
+		}
+		memset(qedf->global_queues[i]->cq, 0,
+		    qedf->global_queues[i]->cq_mem_size);
+
+		qedf->global_queues[i]->cq_pbl =
+		    dma_alloc_coherent(&qedf->pdev->dev,
+			qedf->global_queues[i]->cq_pbl_size,
+			&qedf->global_queues[i]->cq_pbl_dma, GFP_KERNEL);
+
+		if (!qedf->global_queues[i]->cq_pbl) {
+			QEDF_WARN(&(qedf->dbg_ctx), "Could not allocate "
+				   "cq PBL.\n");
+			status = -ENOMEM;
+			goto mem_alloc_failure;
+		}
+		memset(qedf->global_queues[i]->cq_pbl, 0,
+		    qedf->global_queues[i]->cq_pbl_size);
+
+		/* Create PBL */
+		num_pages = qedf->global_queues[i]->cq_mem_size /
+		    QEDF_PAGE_SIZE;
+		page = qedf->global_queues[i]->cq_dma;
+		pbl = (u32 *)qedf->global_queues[i]->cq_pbl;
+
+		while (num_pages--) {
+			*pbl = U64_LO(page);
+			pbl++;
+			*pbl = U64_HI(page);
+			pbl++;
+			page += QEDF_PAGE_SIZE;
+		}
+		/* Set the initial consumer index for cq */
+		qedf->global_queues[i]->cq_cons_idx = 0;
+	}
+
+	list = (u32 *)qedf->p_cpuq;
+
+	/*
+	 * The list is built as follows: CQ#0 PBL pointer, RQ#0 PBL pointer,
+	 * CQ#1 PBL pointer, RQ#1 PBL pointer, etc.  Each PBL pointer points
+	 * to the physical address which contains an array of pointers to
+	 * the physical addresses of the specific queue pages.
+	 */
+	for (i = 0; i < qedf->num_queues; i++) {
+		*list = U64_LO(qedf->global_queues[i]->cq_pbl_dma);
+		list++;
+		*list = U64_HI(qedf->global_queues[i]->cq_pbl_dma);
+		list++;
+		*list = U64_LO(0);
+		list++;
+		*list = U64_HI(0);
+		list++;
+	}
+
+	return 0;
+
+mem_alloc_failure:
+	qedf_free_global_queues(qedf);
+	return status;
+}
+
+static int qedf_set_fcoe_pf_param(struct qedf_ctx *qedf)
+{
+	u8 sq_num_pbl_pages;
+	u32 sq_mem_size;
+	u32 cq_mem_size;
+	u32 cq_num_entries;
+	int rval;
+
+	/*
+	 * The number of completion queues/fastpath interrupts/status blocks
+	 * we allocation is the minimum off:
+	 *
+	 * Number of CPUs
+	 * Number of MSI-X vectors
+	 * Max number allocated in hardware (QEDF_MAX_NUM_CQS)
+	 */
+	qedf->num_queues = min((unsigned int)QEDF_MAX_NUM_CQS,
+	    num_online_cpus());
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Number of CQs is %d.\n",
+		   qedf->num_queues);
+
+	qedf->p_cpuq = pci_alloc_consistent(qedf->pdev,
+	    qedf->num_queues * sizeof(struct qedf_glbl_q_params),
+	    &qedf->hw_p_cpuq);
+
+	if (!qedf->p_cpuq) {
+		QEDF_ERR(&(qedf->dbg_ctx), "pci_alloc_consistent failed.\n");
+		return 1;
+	}
+
+	rval = qedf_alloc_global_queues(qedf);
+	if (rval) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Global queue allocation "
+			  "failed.\n");
+		return 1;
+	}
+
+	/* Calculate SQ PBL size in the same manner as in qedf_sq_alloc() */
+	sq_mem_size = SQ_NUM_ENTRIES * sizeof(struct fcoe_wqe);
+	sq_mem_size = ALIGN(sq_mem_size, QEDF_PAGE_SIZE);
+	sq_num_pbl_pages = (sq_mem_size / QEDF_PAGE_SIZE);
+
+	/* Calculate CQ num entries */
+	cq_mem_size = FCOE_PARAMS_CQ_NUM_ENTRIES * sizeof(struct fcoe_cqe);
+	cq_mem_size = ALIGN(cq_mem_size, QEDF_PAGE_SIZE);
+	cq_num_entries = cq_mem_size / sizeof(struct fcoe_cqe);
+
+	memset(&(qedf->pf_params), 0,
+	    sizeof(qedf->pf_params));
+
+	/* Setup the value for fcoe PF */
+	qedf->pf_params.fcoe_pf_params.num_cons = QEDF_MAX_SESSIONS;
+	qedf->pf_params.fcoe_pf_params.num_tasks = FCOE_PARAMS_NUM_TASKS;
+	qedf->pf_params.fcoe_pf_params.glbl_q_params_addr =
+	    (u64)qedf->hw_p_cpuq;
+	qedf->pf_params.fcoe_pf_params.sq_num_pbl_pages = sq_num_pbl_pages;
+
+	qedf->pf_params.fcoe_pf_params.rq_buffer_log_size = 0;
+
+	qedf->pf_params.fcoe_pf_params.cq_num_entries = cq_num_entries;
+	qedf->pf_params.fcoe_pf_params.num_cqs = qedf->num_queues;
+
+	/* log_page_size: 12 for 4KB pages */
+	qedf->pf_params.fcoe_pf_params.log_page_size = ilog2(QEDF_PAGE_SIZE);
+
+	qedf->pf_params.fcoe_pf_params.mtu = 9000;
+	qedf->pf_params.fcoe_pf_params.gl_rq_pi = QEDF_FCOE_PARAMS_GL_RQ_PI;
+	qedf->pf_params.fcoe_pf_params.gl_cmd_pi = QEDF_FCOE_PARAMS_GL_CMD_PI;
+
+	/* BDQ address and size */
+	qedf->pf_params.fcoe_pf_params.bdq_pbl_base_addr[0] =
+	    qedf->bdq_pbl_list_dma;
+	qedf->pf_params.fcoe_pf_params.bdq_pbl_num_entries[0] =
+	    qedf->bdq_pbl_list_num_entries;
+	qedf->pf_params.fcoe_pf_params.rq_buffer_size = QEDF_BDQ_BUF_SIZE;
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+	    "bdq_list=%p bdq_pbl_list_dma=%llx bdq_pbl_list_entries=%d.\n",
+	    qedf->bdq_pbl_list,
+	    qedf->pf_params.fcoe_pf_params.bdq_pbl_base_addr[0],
+	    qedf->pf_params.fcoe_pf_params.bdq_pbl_num_entries[0]);
+
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+	    "cq_num_entries=%d.\n",
+	    qedf->pf_params.fcoe_pf_params.cq_num_entries);
+
+	return 0;
+}
+
+/* Free DMA coherent memory for array of queue pointers we pass to qed */
+static void qedf_free_fcoe_pf_param(struct qedf_ctx *qedf)
+{
+	size_t size = 0;
+
+	if (qedf->p_cpuq) {
+		size = qedf->num_queues * sizeof(struct qedf_glbl_q_params);
+		pci_free_consistent(qedf->pdev, size, qedf->p_cpuq,
+		    qedf->hw_p_cpuq);
+	}
+
+	qedf_free_global_queues(qedf);
+
+	if (qedf->global_queues)
+		kfree(qedf->global_queues);
+}
+
+/*
+ * PCI driver functions
+ */
+
+static const struct pci_device_id qedf_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x165c) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x8080) },
+	{0}
+};
+MODULE_DEVICE_TABLE(pci, qedf_pci_tbl);
+
+static struct pci_driver qedf_pci_driver = {
+	.name = QEDF_MODULE_NAME,
+	.id_table = qedf_pci_tbl,
+	.probe = qedf_probe,
+	.remove = qedf_remove,
+};
+
+static int __qedf_probe(struct pci_dev *pdev, int mode)
+{
+	int rc = -EINVAL;
+	struct fc_lport *lport;
+	struct qedf_ctx *qedf;
+	struct Scsi_Host *host;
+	bool is_vf = false;
+	struct qed_ll2_params params;
+	char host_buf[20];
+	struct qed_link_params link_params;
+	int status;
+	void *task_start, *task_end;
+	struct qed_slowpath_params slowpath_params;
+	struct qed_probe_params qed_params;
+	u16 tmp;
+
+	/*
+	 * When doing error recovery we didn't reap the lport so don't try
+	 * to reallocate it.
+	 */
+	if (mode != QEDF_MODE_RECOVERY) {
+		lport = libfc_host_alloc(&qedf_host_template,
+		    sizeof(struct qedf_ctx));
+
+		if (!lport) {
+			QEDF_ERR(NULL, "Could not allocate lport.\n");
+			rc = -ENOMEM;
+			goto err0;
+		}
+
+		/* Initialize qedf_ctx */
+		qedf = lport_priv(lport);
+		qedf->lport = lport;
+		qedf->ctlr.lp = lport;
+		qedf->pdev = pdev;
+		qedf->dbg_ctx.pdev = pdev;
+		qedf->dbg_ctx.host_no = lport->host->host_no;
+		spin_lock_init(&qedf->hba_lock);
+		INIT_LIST_HEAD(&qedf->fcports);
+		qedf->curr_conn_id = QEDF_MAX_SESSIONS - 1;
+		atomic_set(&qedf->num_offloads, 0);
+		qedf->stop_io_on_error = false;
+		pci_set_drvdata(pdev, qedf);
+
+		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_INFO,
+		   "QLogic FastLinQ FCoE Module qedf %s, "
+		   "FW %d.%d.%d.%d\n", QEDF_VERSION,
+		   FW_MAJOR_VERSION, FW_MINOR_VERSION, FW_REVISION_VERSION,
+		   FW_ENGINEERING_VERSION);
+	} else {
+		/* Init pointers during recovery */
+		qedf = pci_get_drvdata(pdev);
+		lport = qedf->lport;
+	}
+
+	host = lport->host;
+
+	/* Allocate mempool for qedf_io_work structs */
+	qedf->io_mempool = mempool_create_slab_pool(QEDF_IO_WORK_MIN,
+	    qedf_io_work_cache);
+	if (qedf->io_mempool == NULL) {
+		QEDF_ERR(&(qedf->dbg_ctx), "qedf->io_mempool is NULL.\n");
+		goto err1;
+	}
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_INFO, "qedf->io_mempool=%p.\n",
+	    qedf->io_mempool);
+
+	sprintf(host_buf, "qedf_%u_link",
+	    qedf->lport->host->host_no);
+	qedf->link_update_wq = create_singlethread_workqueue(host_buf);
+	INIT_DELAYED_WORK(&qedf->link_update, qedf_handle_link_update);
+	INIT_DELAYED_WORK(&qedf->link_recovery, qedf_link_recovery);
+
+	qedf->fipvlan_retries = qedf_fipvlan_retries;
+
+	/*
+	 * Common probe. Takes care of basic hardware init and pci_*
+	 * functions.
+	 */
+	memset(&qed_params, 0, sizeof(qed_params));
+	qed_params.protocol = QED_PROTOCOL_FCOE;
+	qed_params.dp_module = qedf_dp_module;
+	qed_params.dp_level = qedf_dp_level;
+	qed_params.is_vf = is_vf;
+	qedf->cdev = qed_ops->common->probe(pdev, &qed_params);
+	if (!qedf->cdev) {
+		rc = -ENODEV;
+		goto err1;
+	}
+
+	/* queue allocation code should come here
+	 * order should be
+	 * 	slowpath_start
+	 * 	status block allocation
+	 *	interrupt registration (to get min number of queues)
+	 *	set_fcoe_pf_param
+	 *	qed_sp_fcoe_func_start
+	 */
+	rc = qedf_set_fcoe_pf_param(qedf);
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Cannot set fcoe pf param.\n");
+		goto err2;
+	}
+	qed_ops->common->update_pf_params(qedf->cdev, &qedf->pf_params);
+
+	/* Learn information crucial for qedf to progress */
+	rc = qed_ops->fill_dev_info(qedf->cdev, &qedf->dev_info);
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed to dev info.\n");
+		goto err1;
+	}
+
+	/* Record BDQ producer doorbell addresses */
+	qedf->bdq_primary_prod = qedf->dev_info.primary_dbq_rq_addr;
+	qedf->bdq_secondary_prod = qedf->dev_info.secondary_bdq_rq_addr;
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+	    "BDQ primary_prod=%p secondary_prod=%p.\n", qedf->bdq_primary_prod,
+	    qedf->bdq_secondary_prod);
+
+	qed_ops->register_ops(qedf->cdev, &qedf_cb_ops, qedf);
+
+	rc = qedf_prepare_sb(qedf);
+	if (rc) {
+
+		QEDF_ERR(&(qedf->dbg_ctx), "Cannot start slowpath.\n");
+		goto err2;
+	}
+
+	/* Start the Slowpath-process */
+	slowpath_params.int_mode = QED_INT_MODE_MSIX;
+	slowpath_params.drv_major = QEDF_DRIVER_MAJOR_VER;
+	slowpath_params.drv_minor = QEDF_DRIVER_MINOR_VER;
+	slowpath_params.drv_rev = QEDF_DRIVER_REV_VER;
+	slowpath_params.drv_eng = QEDF_DRIVER_ENG_VER;
+	memcpy(slowpath_params.name, "qedf", QED_DRV_VER_STR_SIZE);
+	rc = qed_ops->common->slowpath_start(qedf->cdev, &slowpath_params);
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Cannot start slowpath.\n");
+		goto err2;
+	}
+
+	/*
+	 * update_pf_params needs to be called before and after slowpath
+	 * start
+	 */
+	qed_ops->common->update_pf_params(qedf->cdev, &qedf->pf_params);
+
+	/* Setup interrupts */
+	rc = qedf_setup_int(qedf);
+	if (rc)
+		goto err3;
+
+	rc = qed_ops->start(qedf->cdev, &qedf->tasks);
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Cannot start FCoE function.\n");
+		goto err4;
+	}
+	task_start = qedf_get_task_mem(&qedf->tasks, 0);
+	task_end = qedf_get_task_mem(&qedf->tasks, MAX_TID_BLOCKS_FCOE - 1);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Task context start=%p, "
+		   "end=%p block_size=%u.\n", task_start, task_end,
+		   qedf->tasks.size);
+
+	/*
+	 * We need to write the number of BDs in the BDQ we've preallocated so
+	 * the f/w will do a prefetch and we'll get an unsolicited CQE when a
+	 * packet arrives.
+	 */
+	qedf->bdq_prod_idx = QEDF_BDQ_SIZE;
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+	    "Writing %d to primary and secondary BDQ doorbell registers.\n",
+	    qedf->bdq_prod_idx);
+	writew(qedf->bdq_prod_idx, qedf->bdq_primary_prod);
+	tmp = readw(qedf->bdq_primary_prod);
+	writew(qedf->bdq_prod_idx, qedf->bdq_secondary_prod);
+	tmp = readw(qedf->bdq_secondary_prod);
+
+	qed_ops->common->set_power_state(qedf->cdev, PCI_D0);
+
+	/* Now that the dev_info struct has been filled in set the MAC
+	 * address
+	 */
+	ether_addr_copy(qedf->mac, qedf->dev_info.common.hw_mac);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "MAC address is %pM.\n",
+		   qedf->mac);
+
+	/* Set the WWNN and WWPN based on the MAC address */
+	qedf->wwnn = fcoe_wwn_from_mac(qedf->mac, 1, 0);
+	qedf->wwpn = fcoe_wwn_from_mac(qedf->mac, 2, 0);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,  "WWNN=%016llx "
+		   "WWPN=%016llx.\n", qedf->wwnn, qedf->wwpn);
+
+	sprintf(host_buf, "host_%d", host->host_no);
+	qed_ops->common->set_id(qedf->cdev, host_buf, QEDF_VERSION);
+
+
+	/* Set xid max values */
+	qedf->max_scsi_xid = QEDF_MAX_SCSI_XID;
+	qedf->max_els_xid = QEDF_MAX_ELS_XID;
+
+	/* Allocate cmd mgr */
+	qedf->cmd_mgr = qedf_cmd_mgr_alloc(qedf);
+	if (!qedf->cmd_mgr) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed to allocate cmd mgr.\n");
+		goto err5;
+	}
+
+	if (mode != QEDF_MODE_RECOVERY) {
+		host->transportt = qedf_fc_transport_template;
+		host->can_queue = QEDF_MAX_ELS_XID;
+		host->max_lun = qedf_max_lun;
+		host->max_cmd_len = QEDF_MAX_CDB_LEN;
+		rc = scsi_add_host(host, &pdev->dev);
+		if (rc)
+			goto err6;
+	}
+
+	memset(&params, 0, sizeof(params));
+	params.mtu = 9000;
+	ether_addr_copy(params.ll2_mac_address, qedf->mac);
+
+	/* Start LL2 processing thread */
+	snprintf(host_buf, 20, "qedf_%d_ll2", host->host_no);
+	qedf->ll2_recv_wq =
+		create_singlethread_workqueue(host_buf);
+	if (!qedf->ll2_recv_wq) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed to LL2 workqueue.\n");
+		goto err7;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedf_dbg_host_init(&(qedf->dbg_ctx), &qedf_debugfs_ops,
+			    &qedf_dbg_fops);
+#endif
+
+	/* Start LL2 */
+	qed_ops->ll2->register_cb_ops(qedf->cdev, &qedf_ll2_cb_ops, qedf);
+	rc = qed_ops->ll2->start(qedf->cdev, &params);
+	if (rc) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Could not start Light L2.\n");
+		goto err7;
+	}
+	set_bit(QEDF_LL2_STARTED, &qedf->flags);
+
+	/* hw will be insterting vlan tag*/
+	qedf->vlan_hw_insert = 1;
+	qedf->vlan_id = 0;
+
+	/*
+	 * No need to setup fcoe_ctlr or fc_lport objects during recovery since
+	 * they were not reaped during the unload process.
+	 */
+	if (mode != QEDF_MODE_RECOVERY) {
+		/* Setup imbedded fcoe controller */
+		qedf_fcoe_ctlr_setup(qedf);
+
+		/* Setup lport */
+		rc = qedf_lport_setup(qedf);
+		if (rc) {
+			QEDF_ERR(&(qedf->dbg_ctx),
+			    "qedf_lport_setup failed.\n");
+			goto err7;
+		}
+	}
+
+	sprintf(host_buf, "qedf_%u_timer", qedf->lport->host->host_no);
+	qedf->timer_work_queue =
+		create_singlethread_workqueue(host_buf);
+	if (!qedf->timer_work_queue) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Failed to start timer "
+			  "workqueue.\n");
+		goto err7;
+	}
+
+	/* DPC workqueue is not reaped during recovery unload */
+	if (mode != QEDF_MODE_RECOVERY) {
+		sprintf(host_buf, "qedf_%u_dpc",
+		    qedf->lport->host->host_no);
+		qedf->dpc_wq = create_singlethread_workqueue(host_buf);
+	}
+
+	/*
+	 * GRC dump and sysfs parameters are not reaped during the recovery
+	 * unload process.
+	 */
+	if (mode != QEDF_MODE_RECOVERY) {
+		qedf->grcdump_size = qed_ops->common->dbg_grc_size(qedf->cdev);
+		if (qedf->grcdump_size) {
+			rc = qedf_alloc_grc_dump_buf(&qedf->grcdump,
+			    qedf->grcdump_size);
+			if (rc) {
+				QEDF_ERR(&(qedf->dbg_ctx),
+				    "GRC Dump buffer alloc failed.\n");
+				qedf->grcdump = NULL;
+			}
+
+			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+			    "grcdump: addr=%p, size=%u.\n",
+			    qedf->grcdump, qedf->grcdump_size);
+		}
+		qedf_create_sysfs_ctx_attr(qedf);
+
+		/* Initialize I/O tracing for this adapter */
+		spin_lock_init(&qedf->io_trace_lock);
+		qedf->io_trace_idx = 0;
+	}
+
+	init_completion(&qedf->flogi_compl);
+
+	memset(&link_params, 0, sizeof(struct qed_link_params));
+	link_params.link_up = true;
+	status = qed_ops->common->set_link(qedf->cdev, &link_params);
+	if (status)
+		QEDF_WARN(&(qedf->dbg_ctx), "set_link failed.\n");
+
+	/* Start/restart discovery */
+	if (mode == QEDF_MODE_RECOVERY)
+		fcoe_ctlr_link_up(&qedf->ctlr);
+	else
+		fc_fabric_login(lport);
+
+	/* All good */
+	return 0;
+
+err7:
+	if (qedf->ll2_recv_wq)
+		destroy_workqueue(qedf->ll2_recv_wq);
+	fc_remove_host(qedf->lport->host);
+	scsi_remove_host(qedf->lport->host);
+#ifdef CONFIG_DEBUG_FS
+	qedf_dbg_host_exit(&(qedf->dbg_ctx));
+#endif
+err6:
+	qedf_cmd_mgr_free(qedf->cmd_mgr);
+err5:
+	qed_ops->stop(qedf->cdev);
+err4:
+	qedf_free_fcoe_pf_param(qedf);
+	qedf_sync_free_irqs(qedf);
+err3:
+	qed_ops->common->slowpath_stop(qedf->cdev);
+err2:
+	qed_ops->common->remove(qedf->cdev);
+err1:
+	scsi_host_put(lport->host);
+err0:
+	return rc;
+}
+
+static int qedf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	return __qedf_probe(pdev, QEDF_MODE_NORMAL);
+}
+
+static void __qedf_remove(struct pci_dev *pdev, int mode)
+{
+	struct qedf_ctx *qedf;
+
+	if (!pdev) {
+		QEDF_ERR(NULL, "pdev is NULL.\n");
+		return;
+	}
+
+	qedf = pci_get_drvdata(pdev);
+
+	/*
+	 * Prevent race where we're in board disable work and then try to
+	 * rmmod the module.
+	 */
+	if (test_bit(QEDF_UNLOADING, &qedf->flags)) {
+		QEDF_ERR(&qedf->dbg_ctx, "Already removing PCI function.\n");
+		return;
+	}
+
+	if (mode != QEDF_MODE_RECOVERY)
+		set_bit(QEDF_UNLOADING, &qedf->flags);
+
+	/* Logoff the fabric to upload all connections */
+	if (mode == QEDF_MODE_RECOVERY)
+		fcoe_ctlr_link_down(&qedf->ctlr);
+	else
+		fc_fabric_logoff(qedf->lport);
+	qedf_wait_for_upload(qedf);
+
+#ifdef CONFIG_DEBUG_FS
+	qedf_dbg_host_exit(&(qedf->dbg_ctx));
+#endif
+
+	/* Stop any link update handling */
+	cancel_delayed_work_sync(&qedf->link_update);
+	destroy_workqueue(qedf->link_update_wq);
+	qedf->link_update_wq = NULL;
+
+	if (qedf->timer_work_queue)
+		destroy_workqueue(qedf->timer_work_queue);
+
+	/* Stop Light L2 */
+	clear_bit(QEDF_LL2_STARTED, &qedf->flags);
+	qed_ops->ll2->stop(qedf->cdev);
+	if (qedf->ll2_recv_wq)
+		destroy_workqueue(qedf->ll2_recv_wq);
+
+	/* Stop fastpath */
+	qedf_sync_free_irqs(qedf);
+	qedf_destroy_sb(qedf);
+
+	/*
+	 * During recovery don't destroy OS constructs that represent the
+	 * physical port.
+	 */
+	if (mode != QEDF_MODE_RECOVERY) {
+		qedf_free_grc_dump_buf(&qedf->grcdump);
+		qedf_remove_sysfs_ctx_attr(qedf);
+
+		/* Remove all SCSI/libfc/libfcoe structures */
+		fcoe_ctlr_destroy(&qedf->ctlr);
+		fc_lport_destroy(qedf->lport);
+		fc_remove_host(qedf->lport->host);
+		scsi_remove_host(qedf->lport->host);
+	}
+
+	qedf_cmd_mgr_free(qedf->cmd_mgr);
+
+	if (mode != QEDF_MODE_RECOVERY) {
+		fc_exch_mgr_free(qedf->lport);
+		fc_lport_free_stats(qedf->lport);
+
+		/* Wait for all vports to be reaped */
+		qedf_wait_for_vport_destroy(qedf);
+	}
+
+	/*
+	 * Now that all connections have been uploaded we can stop the
+	 * rest of the qed operations
+	 */
+	qed_ops->stop(qedf->cdev);
+
+	if (mode != QEDF_MODE_RECOVERY) {
+		if (qedf->dpc_wq) {
+			/* Stop general DPC handling */
+			destroy_workqueue(qedf->dpc_wq);
+			qedf->dpc_wq = NULL;
+		}
+	}
+
+	/* Final shutdown for the board */
+	qedf_free_fcoe_pf_param(qedf);
+	if (mode != QEDF_MODE_RECOVERY) {
+		qed_ops->common->set_power_state(qedf->cdev, PCI_D0);
+		pci_set_drvdata(pdev, NULL);
+	}
+	qed_ops->common->slowpath_stop(qedf->cdev);
+	qed_ops->common->remove(qedf->cdev);
+
+	mempool_destroy(qedf->io_mempool);
+
+	/* Only reap the Scsi_host on a real removal */
+	if (mode != QEDF_MODE_RECOVERY)
+		scsi_host_put(qedf->lport->host);
+}
+
+static void qedf_remove(struct pci_dev *pdev)
+{
+	/* Check to make sure this function wasn't already disabled */
+	if (!atomic_read(&pdev->enable_cnt))
+		return;
+
+	__qedf_remove(pdev, QEDF_MODE_NORMAL);
+}
+
+/*
+ * Module Init/Remove
+ */
+
+static int __init qedf_init(void)
+{
+	int ret;
+
+	/* If debug=1 passed, set the default log mask */
+	if (qedf_debug == QEDF_LOG_DEFAULT)
+		qedf_debug = QEDF_DEFAULT_LOG_MASK;
+
+	/* Print driver banner */
+	QEDF_INFO(NULL, QEDF_LOG_INFO, "%s v%s.\n", QEDF_DESCR,
+		   QEDF_VERSION);
+
+	/* Create kmem_cache for qedf_io_work structs */
+	qedf_io_work_cache = kmem_cache_create("qedf_io_work_cache",
+	    sizeof(struct qedf_io_work), 0, SLAB_HWCACHE_ALIGN, NULL);
+	if (qedf_io_work_cache == NULL) {
+		QEDF_ERR(NULL, "qedf_io_work_cache is NULL.\n");
+		goto err1;
+	}
+	QEDF_INFO(NULL, QEDF_LOG_DISC, "qedf_io_work_cache=%p.\n",
+	    qedf_io_work_cache);
+
+	qed_ops = qed_get_fcoe_ops();
+	if (!qed_ops) {
+		QEDF_ERR(NULL, "Failed to get qed fcoe operations\n");
+		goto err1;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedf_dbg_init("qedf");
+#endif
+
+	qedf_fc_transport_template =
+	    fc_attach_transport(&qedf_fc_transport_fn);
+	if (!qedf_fc_transport_template) {
+		QEDF_ERR(NULL, "Could not register with FC transport\n");
+		goto err2;
+	}
+
+	qedf_fc_vport_transport_template =
+		fc_attach_transport(&qedf_fc_vport_transport_fn);
+	if (!qedf_fc_vport_transport_template) {
+		QEDF_ERR(NULL, "Could not register vport template with FC "
+			  "transport\n");
+		goto err3;
+	}
+
+	qedf_io_wq = create_workqueue("qedf_io_wq");
+	if (!qedf_io_wq) {
+		QEDF_ERR(NULL, "Could not create qedf_io_wq.\n");
+		goto err4;
+	}
+
+	qedf_cb_ops.get_login_failures = qedf_get_login_failures;
+
+	ret = pci_register_driver(&qedf_pci_driver);
+	if (ret) {
+		QEDF_ERR(NULL, "Failed to register driver\n");
+		goto err5;
+	}
+
+	return 0;
+
+err5:
+	destroy_workqueue(qedf_io_wq);
+err4:
+	fc_release_transport(qedf_fc_vport_transport_template);
+err3:
+	fc_release_transport(qedf_fc_transport_template);
+err2:
+#ifdef CONFIG_DEBUG_FS
+	qedf_dbg_exit();
+#endif
+	qed_put_fcoe_ops();
+err1:
+	return -EINVAL;
+}
+
+static void __exit qedf_cleanup(void)
+{
+	pci_unregister_driver(&qedf_pci_driver);
+
+	destroy_workqueue(qedf_io_wq);
+
+	fc_release_transport(qedf_fc_vport_transport_template);
+	fc_release_transport(qedf_fc_transport_template);
+#ifdef CONFIG_DEBUG_FS
+	qedf_dbg_exit();
+#endif
+	qed_put_fcoe_ops();
+
+	kmem_cache_destroy(qedf_io_work_cache);
+}
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("QLogic QEDF 25/40/50/100Gb FCoE Driver");
+MODULE_AUTHOR("QLogic Corporation");
+MODULE_VERSION(QEDF_VERSION);
+module_init(qedf_init);
+module_exit(qedf_cleanup);
diff --git a/drivers/scsi/qedf/qedf_version.h b/drivers/scsi/qedf/qedf_version.h
new file mode 100644
index 000000000000..4ae5f537a440
--- /dev/null
+++ b/drivers/scsi/qedf/qedf_version.h
@@ -0,0 +1,15 @@
+/*
+ *  QLogic FCoE Offload Driver
+ *  Copyright (c) 2016 Cavium Inc.
+ *
+ *  This software is available under the terms of the GNU General Public License
+ *  (GPL) Version 2, available from the file COPYING in the main directory of
+ *  this source tree.
+ */
+
+#define QEDF_VERSION		"8.10.7.0"
+#define QEDF_DRIVER_MAJOR_VER		8
+#define QEDF_DRIVER_MINOR_VER		10
+#define QEDF_DRIVER_REV_VER		7
+#define QEDF_DRIVER_ENG_VER		0
+
-- 
GitLab


From 8bfcd1bf867d5fae67ecc553b44d7a29ab66013c Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 8 Feb 2017 16:24:24 +0000
Subject: [PATCH 161/898] scsi: sd: make sd_devt_release() static

Fixes the following sparse warning:

drivers/scsi/sd.c:3087:6: warning:
 symbol 'sd_devt_release' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index cb6e68dd6df0..b9b32f5811e0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3084,7 +3084,7 @@ struct sd_devt {
 	struct disk_devt disk_devt;
 };
 
-void sd_devt_release(struct disk_devt *disk_devt)
+static void sd_devt_release(struct disk_devt *disk_devt)
 {
 	struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt,
 			disk_devt);
-- 
GitLab


From f170396c14243d307e2f479af142fd7356b3bd2a Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Feb 2017 19:38:54 +0000
Subject: [PATCH 162/898] scsi: fix memory leak of sdpk on when gd fails to
 allocate

On an allocation failure of gd, the current exit path is via
out_free_devt which leaves sdpk still allocated and hence it gets
leaked. Fix this by correcting the order of resource free'ing with a
change in the error exit path labels.

Detected by CoverityScan, CID#1399519 ("Resource Leak")

Fixes: 0dba1314d4f81115dc ("scsi, block: fix duplicate bdi name registration crashes")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index b9b32f5811e0..8e4f4f72ea64 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3213,10 +3213,10 @@ static int sd_probe(struct device *dev)
 	sd_devt = NULL;
  out_put:
 	put_disk(gd);
- out_free:
-	kfree(sdkp);
  out_free_devt:
 	kfree(sd_devt);
+ out_free:
+	kfree(sdkp);
  out:
 	scsi_autopm_put_device(sdp);
 	return error;
-- 
GitLab


From 4d7d39a18b8b81511f0b893b7d2203790bf8a58b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 21 Feb 2017 21:46:37 +0300
Subject: [PATCH 163/898] scsi: scsi_dh_emc: return success in
 clariion_std_inquiry()

We accidentally return an uninitialized variable on success.

Fixes: b6ff1b14cdf4 ("[SCSI] scsi_dh: Update EMC handler")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/device_handler/scsi_dh_emc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 4a7679f6c73d..f1578832ec7a 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -358,7 +358,7 @@ static int clariion_prep_fn(struct scsi_device *sdev, struct request *req)
 static int clariion_std_inquiry(struct scsi_device *sdev,
 				struct clariion_dh_data *csdev)
 {
-	int err;
+	int err = SCSI_DH_OK;
 	char *sp_model;
 
 	sp_model = parse_sp_model(sdev, sdev->inquiry);
-- 
GitLab


From 148cff67b401e2229c076c0ea418712654be77e4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Feb 2017 20:15:55 +0100
Subject: [PATCH 164/898] scsi: always zero sshdr in scsi_normalize_sense

This gives us a clear state even if a command didn't return sense data.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c
index b1383a71400e..a75673bb82b3 100644
--- a/drivers/scsi/scsi_common.c
+++ b/drivers/scsi/scsi_common.c
@@ -137,11 +137,11 @@ EXPORT_SYMBOL(int_to_scsilun);
 bool scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
 			  struct scsi_sense_hdr *sshdr)
 {
+	memset(sshdr, 0, sizeof(struct scsi_sense_hdr));
+
 	if (!sense_buffer || !sb_len)
 		return false;
 
-	memset(sshdr, 0, sizeof(struct scsi_sense_hdr));
-
 	sshdr->response_code = (sense_buffer[0] & 0x7f);
 
 	if (!scsi_sense_valid(sshdr))
-- 
GitLab


From 6fa2b8f9e3ae8dd770d8fa264825f86b146381c8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Feb 2017 20:15:56 +0100
Subject: [PATCH 165/898] scsi: sd: improve TUR handling in sd_check_events

Remove bogus evaluations of retval and sshdr when the device is offline,
and fix a possible NULL pointer dereference by allocating the 8 byte
sized sense header on stack.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 8e4f4f72ea64..be535d4215c4 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1425,7 +1425,6 @@ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
 {
 	struct scsi_disk *sdkp = scsi_disk_get(disk);
 	struct scsi_device *sdp;
-	struct scsi_sense_hdr *sshdr = NULL;
 	int retval;
 
 	if (!sdkp)
@@ -1454,22 +1453,21 @@ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
 	 * by sd_spinup_disk() from sd_revalidate_disk(), which happens whenever
 	 * sd_revalidate() is called.
 	 */
-	retval = -ENODEV;
-
 	if (scsi_block_when_processing_errors(sdp)) {
-		sshdr  = kzalloc(sizeof(*sshdr), GFP_KERNEL);
+		struct scsi_sense_hdr sshdr = { 0, };
+
 		retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, SD_MAX_RETRIES,
-					      sshdr);
-	}
+					      &sshdr);
 
-	/* failed to execute TUR, assume media not present */
-	if (host_byte(retval)) {
-		set_media_not_present(sdkp);
-		goto out;
-	}
+		/* failed to execute TUR, assume media not present */
+		if (host_byte(retval)) {
+			set_media_not_present(sdkp);
+			goto out;
+		}
 
-	if (media_not_present(sdkp, sshdr))
-		goto out;
+		if (media_not_present(sdkp, &sshdr))
+			goto out;
+	}
 
 	/*
 	 * For removable scsi disk we have to recognise the presence
@@ -1485,7 +1483,6 @@ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
 	 *	Medium present state has changed in either direction.
 	 *	Device has indicated UNIT_ATTENTION.
 	 */
-	kfree(sshdr);
 	retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0;
 	sdp->changed = 0;
 	scsi_disk_put(sdkp);
-- 
GitLab


From 74a78ebda4fa5c5ae87fc501152863ee31c17da4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Feb 2017 20:15:57 +0100
Subject: [PATCH 166/898] scsi: make the sense header argument to
 scsi_test_unit_ready mandatory

It's a tiny structure that can be allocated on the stack, don't
complicate the code by making it optional.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/osd/osd_uld.c |  3 ++-
 drivers/scsi/scsi_ioctl.c  |  3 ++-
 drivers/scsi/scsi_lib.c    | 14 ++------------
 3 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/osd/osd_uld.c b/drivers/scsi/osd/osd_uld.c
index 243eab3d10d0..e0ce5d2fd14d 100644
--- a/drivers/scsi/osd/osd_uld.c
+++ b/drivers/scsi/osd/osd_uld.c
@@ -372,6 +372,7 @@ EXPORT_SYMBOL(osduld_device_same);
 static int __detect_osd(struct osd_uld_device *oud)
 {
 	struct scsi_device *scsi_device = oud->od.scsi_device;
+	struct scsi_sense_hdr sense_hdr;
 	char caps[OSD_CAP_LEN];
 	int error;
 
@@ -380,7 +381,7 @@ static int __detect_osd(struct osd_uld_device *oud)
 	 */
 	OSD_DEBUG("start scsi_test_unit_ready %p %p %p\n",
 			oud, scsi_device, scsi_device->request_queue);
-	error = scsi_test_unit_ready(scsi_device, 10*HZ, 5, NULL);
+	error = scsi_test_unit_ready(scsi_device, 10*HZ, 5, &sense_hdr);
 	if (error)
 		OSD_ERR("warning: scsi_test_unit_ready failed\n");
 
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 8b8c814df5c7..b6bf3f29a12a 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -199,6 +199,7 @@ static int scsi_ioctl_get_pci(struct scsi_device *sdev, void __user *arg)
 int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	char scsi_cmd[MAX_COMMAND_SIZE];
+	struct scsi_sense_hdr sense_hdr;
 
 	/* Check for deprecated ioctls ... all the ioctls which don't
 	 * follow the new unique numbering scheme are deprecated */
@@ -243,7 +244,7 @@ int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 		return scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW);
 	case SCSI_IOCTL_TEST_UNIT_READY:
 		return scsi_test_unit_ready(sdev, IOCTL_NORMAL_TIMEOUT,
-					    NORMAL_RETRIES, NULL);
+					    NORMAL_RETRIES, &sense_hdr);
 	case SCSI_IOCTL_START_UNIT:
 		scsi_cmd[0] = START_STOP;
 		scsi_cmd[1] = 0;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 39b2d727f033..a3c7ec1795c9 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2520,28 +2520,20 @@ EXPORT_SYMBOL(scsi_mode_sense);
  *	@sdev:	scsi device to change the state of.
  *	@timeout: command timeout
  *	@retries: number of retries before failing
- *	@sshdr_external: Optional pointer to struct scsi_sense_hdr for
- *		returning sense. Make sure that this is cleared before passing
- *		in.
+ *	@sshdr: outpout pointer for decoded sense information.
  *
  *	Returns zero if unsuccessful or an error if TUR failed.  For
  *	removable media, UNIT_ATTENTION sets ->changed flag.
  **/
 int
 scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries,
-		     struct scsi_sense_hdr *sshdr_external)
+		     struct scsi_sense_hdr *sshdr)
 {
 	char cmd[] = {
 		TEST_UNIT_READY, 0, 0, 0, 0, 0,
 	};
-	struct scsi_sense_hdr *sshdr;
 	int result;
 
-	if (!sshdr_external)
-		sshdr = kzalloc(sizeof(*sshdr), GFP_KERNEL);
-	else
-		sshdr = sshdr_external;
-
 	/* try to eat the UNIT_ATTENTION if there are enough retries */
 	do {
 		result = scsi_execute_req(sdev, cmd, DMA_NONE, NULL, 0, sshdr,
@@ -2552,8 +2544,6 @@ scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries,
 	} while (scsi_sense_valid(sshdr) &&
 		 sshdr->sense_key == UNIT_ATTENTION && --retries);
 
-	if (!sshdr_external)
-		kfree(sshdr);
 	return result;
 }
 EXPORT_SYMBOL(scsi_test_unit_ready);
-- 
GitLab


From 3949e2f04262495f6c8795b148aa26dffccba646 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 14 Feb 2017 20:15:58 +0100
Subject: [PATCH 167/898] scsi: simplify scsi_execute_req_flags

Add a sshdr argument to __scsi_execute so that we can decode the sense
data directly into the sense header instead of needing a copy of it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 27 +++++++++------------------
 1 file changed, 9 insertions(+), 18 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index a3c7ec1795c9..5f661486cf6e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -215,8 +215,9 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 
 static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
-		 unsigned char *sense, int timeout, int retries, u64 flags,
-		 req_flags_t rq_flags, int *resid)
+		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
+		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
+		 int *resid)
 {
 	struct request *req;
 	struct scsi_request *rq;
@@ -259,6 +260,8 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		*resid = rq->resid_len;
 	if (sense && rq->sense_len)
 		memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
+	if (sshdr)
+		scsi_normalize_sense(rq->sense, rq->sense_len, sshdr);
 	ret = req->errors;
  out:
 	blk_put_request(req);
@@ -288,7 +291,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int *resid)
 {
 	return __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,
-			timeout, retries, flags, 0, resid);
+			NULL, timeout, retries, flags, 0, resid);
 }
 EXPORT_SYMBOL(scsi_execute);
 
@@ -297,21 +300,9 @@ int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
 		     struct scsi_sense_hdr *sshdr, int timeout, int retries,
 		     int *resid, u64 flags, req_flags_t rq_flags)
 {
-	char *sense = NULL;
-	int result;
-	
-	if (sshdr) {
-		sense = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-		if (!sense)
-			return DRIVER_ERROR << 24;
-	}
-	result = __scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
-			      sense, timeout, retries, flags, rq_flags, resid);
-	if (sshdr)
-		scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, sshdr);
-
-	kfree(sense);
-	return result;
+	return __scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
+			      NULL, sshdr, timeout, retries, flags, rq_flags,
+			      resid);
 }
 EXPORT_SYMBOL(scsi_execute_req_flags);
 
-- 
GitLab


From a33fc7a0482a40068c022aefcefd50f9f0f44f87 Mon Sep 17 00:00:00 2001
From: Min He <min.he@intel.com>
Date: Fri, 17 Feb 2017 16:42:38 +0800
Subject: [PATCH 168/898] drm/i915/gvt: enter failsafe mode when guest requires
 more resources

Windows guest will notitfy GVT-g to request more resources through g2v
interface, when its resources are not enough.
This patch is to handle this case and let vgpu enter failsafe mode to
avoid too many error messages.

Signed-off-by: Min He <min.he@intel.com>
Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gvt.h      | 1 +
 drivers/gpu/drm/i915/gvt/handlers.c | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 48ef0771d772..a41b322d8957 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -453,6 +453,7 @@ struct intel_gvt_ops {
 
 enum {
 	GVT_FAILSAFE_UNSUPPORTED_GUEST,
+	GVT_FAILSAFE_INSUFFICIENT_RESOURCE,
 };
 
 #include "mpt.h"
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index fd7e789a72c3..e1a382645112 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -157,6 +157,8 @@ static void enter_failsafe_mode(struct intel_vgpu *vgpu, int reason)
 	case GVT_FAILSAFE_UNSUPPORTED_GUEST:
 		pr_err("Detected your guest driver doesn't support GVT-g.\n");
 		break;
+	case GVT_FAILSAFE_INSUFFICIENT_RESOURCE:
+		pr_err("Graphics resource is not enough for the guest\n");
 	default:
 		break;
 	}
@@ -1106,6 +1108,9 @@ static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	case _vgtif_reg(execlist_context_descriptor_lo):
 	case _vgtif_reg(execlist_context_descriptor_hi):
 		break;
+	case _vgtif_reg(rsv5[0])..._vgtif_reg(rsv5[3]):
+		enter_failsafe_mode(vgpu, GVT_FAILSAFE_INSUFFICIENT_RESOURCE);
+		break;
 	default:
 		gvt_err("invalid pvinfo write offset %x bytes %x data %x\n",
 				offset, bytes, data);
-- 
GitLab


From 9272f73f79bd780502134f227fa52fd280ecda17 Mon Sep 17 00:00:00 2001
From: Chuanxiao Dong <chuanxiao.dong@intel.com>
Date: Fri, 17 Feb 2017 19:29:52 +0800
Subject: [PATCH 169/898] drm/i915/gvt: add a NULL pointer check to avoid
 kernel panic

Due to the request replay, context switch interrupt may come after
gvt free the workload thus can cause a kernel NULL pointer kernel
panic. This patch will add a simple check to avoid this for a short
term.

From long term, gvt workload lifecycle doesn't match with i915 request
and need to find a proper way to manage this.

v4: simplify the NULL pointer check.
v5: add unlikely to optimize.

Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/scheduler.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index d6b6d0efdd1a..e355a82ccabd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -139,6 +139,9 @@ static int shadow_context_status_change(struct notifier_block *nb,
 	struct intel_vgpu_workload *workload =
 		scheduler->current_workload[req->engine->id];
 
+	if (unlikely(!workload))
+		return NOTIFY_OK;
+
 	switch (action) {
 	case INTEL_CONTEXT_SCHEDULE_IN:
 		intel_gvt_load_render_mmio(workload->vgpu,
-- 
GitLab


From 593e59b4b941910e4f7ba87d3c02d63e38e960d0 Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Mon, 20 Feb 2017 15:51:13 +0800
Subject: [PATCH 170/898] drm/i915/gvt: fix unhandled mmio warnings

some registers were missing or treated as BDW only. This patch is to fix it
avoid unhandled mmio wanrings

v2: update commit message according to zhenyu's comment

Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index e1a382645112..e1abece853d4 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1519,6 +1519,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
 	MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK, NULL, NULL);
 	MMIO_DFH(CACHE_MODE_1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(CACHE_MODE_0, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(0x2124, D_ALL, F_MODE_MASK, NULL, NULL);
 
 	MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK, NULL, NULL);
 	MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK, NULL, NULL);
@@ -2390,9 +2392,9 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW);
-	MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW);
-	MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW);
+	MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW_PLUS);
+	MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW_PLUS);
+	MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW_PLUS);
 
 	MMIO_D(WM_MISC, D_BDW);
 	MMIO_D(BDW_EDP_PSR_BASE, D_BDW);
@@ -2406,7 +2408,7 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(GEN8_EU_DISABLE1, D_BDW_PLUS);
 	MMIO_D(GEN8_EU_DISABLE2, D_BDW_PLUS);
 
-	MMIO_D(0xfdc, D_BDW);
+	MMIO_D(0xfdc, D_BDW_PLUS);
 	MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(GEN7_ROW_CHICKEN2, D_BDW_PLUS);
 	MMIO_D(GEN8_UCGCTL6, D_BDW_PLUS);
@@ -2423,6 +2425,10 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(0x24d8, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x24dc, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 
+	MMIO_D(0x22040, D_BDW_PLUS);
+	MMIO_D(0x44484, D_BDW_PLUS);
+	MMIO_D(0x4448c, D_BDW_PLUS);
+
 	MMIO_D(0x83a4, D_BDW);
 	MMIO_D(GEN8_L3_LRA_1_GPGPU, D_BDW_PLUS);
 
@@ -2668,6 +2674,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_PLANE_KEYMSK_1(PIPE_C), D_SKL);
 
 	MMIO_D(0x44500, D_SKL);
+	MMIO_D(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS);
 	return 0;
 }
 
-- 
GitLab


From d8e9b2b9097c117880dc22933239d05199c60b96 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 20 Feb 2017 14:58:25 +0100
Subject: [PATCH 171/898] drm/i915/gvt: Fix superfluous newline in
 GVT_DISPLAY_READY env var

send_display_send_uevent() sends two environment variable, and the
first one GVT_DISPLAY_READY is set including a new line at the end of
the string; that is obviously superfluous and wrong -- at least, it
*looks* so when you only read the code.

However, it doesn't appear in the actual output by a (supposedly
unexpected) trick.  The code uses snprintf() and truncates the string
in size 20 bytes.  This makes the string as GVT_DISPLAY_READY=0 or
...=1 including the trailing NUL-letter.  That is, the '\n' found in
the format string is always cut off as a result.

Although the code gives the correct result, it is confusing.  This
patch addresses it, just removing the superfluous '\n' from the format
string for avoiding further confusion.  If the argument "ready" were
not a  bool, the size 20 should be corrected as well.  But it's a
bool, so we can leave the magic number 20 as is for now.

FWIW, the bug was spotted by a new GCC7 warning:
  drivers/gpu/drm/i915/gvt/handlers.c: In function 'pvinfo_mmio_write':
  drivers/gpu/drm/i915/gvt/handlers.c:1042:34: error: 'snprintf' output truncated before the last format character [-Werror=format-truncation=]
    snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d\n", ready);
                                    ^~~~~~~~~~~~~~~~~~~~~~~~
  drivers/gpu/drm/i915/gvt/handlers.c:1042:2: note: 'snprintf' output 21 bytes into a destination of size 20
    snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d\n", ready);
    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Fixes: 04d348ae3f0a ("drm/i915/gvt: vGPU display virtualization")
Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1025903
Reported-by: Richard Biener <rguenther@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index e1abece853d4..a1880424ad32 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1069,7 +1069,7 @@ static int send_display_ready_uevent(struct intel_vgpu *vgpu, int ready)
 	char vmid_str[20];
 	char display_ready_str[20];
 
-	snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d\n", ready);
+	snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d", ready);
 	env[0] = display_ready_str;
 
 	snprintf(vmid_str, 20, "VMID=%d", vgpu->id);
-- 
GitLab


From 4c4b22abb3d405c5c194b02255eecc1a9eff42cf Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Tue, 21 Feb 2017 09:39:00 +0800
Subject: [PATCH 172/898] drm/i915/gvt: add more registers to context
 save/restore list

the value of those registers should be applied to hardware on
context restoring

Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/render.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/render.c b/drivers/gpu/drm/i915/gvt/render.c
index 2b3a642284b6..73f052a4f424 100644
--- a/drivers/gpu/drm/i915/gvt/render.c
+++ b/drivers/gpu/drm/i915/gvt/render.c
@@ -53,6 +53,14 @@ static struct render_mmio gen8_render_mmio_list[] = {
 	{RCS, _MMIO(0x24d4), 0, false},
 	{RCS, _MMIO(0x24d8), 0, false},
 	{RCS, _MMIO(0x24dc), 0, false},
+	{RCS, _MMIO(0x24e0), 0, false},
+	{RCS, _MMIO(0x24e4), 0, false},
+	{RCS, _MMIO(0x24e8), 0, false},
+	{RCS, _MMIO(0x24ec), 0, false},
+	{RCS, _MMIO(0x24f0), 0, false},
+	{RCS, _MMIO(0x24f4), 0, false},
+	{RCS, _MMIO(0x24f8), 0, false},
+	{RCS, _MMIO(0x24fc), 0, false},
 	{RCS, _MMIO(0x7004), 0xffff, true},
 	{RCS, _MMIO(0x7008), 0xffff, true},
 	{RCS, _MMIO(0x7000), 0xffff, true},
@@ -76,6 +84,14 @@ static struct render_mmio gen9_render_mmio_list[] = {
 	{RCS, _MMIO(0x24d4), 0, false},
 	{RCS, _MMIO(0x24d8), 0, false},
 	{RCS, _MMIO(0x24dc), 0, false},
+	{RCS, _MMIO(0x24e0), 0, false},
+	{RCS, _MMIO(0x24e4), 0, false},
+	{RCS, _MMIO(0x24e8), 0, false},
+	{RCS, _MMIO(0x24ec), 0, false},
+	{RCS, _MMIO(0x24f0), 0, false},
+	{RCS, _MMIO(0x24f4), 0, false},
+	{RCS, _MMIO(0x24f8), 0, false},
+	{RCS, _MMIO(0x24fc), 0, false},
 	{RCS, _MMIO(0x7004), 0xffff, true},
 	{RCS, _MMIO(0x7008), 0xffff, true},
 	{RCS, _MMIO(0x7000), 0xffff, true},
-- 
GitLab


From e6cedfea6b8dcb205f75ea632570f52d2ffd1251 Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Tue, 21 Feb 2017 10:38:53 +0800
Subject: [PATCH 173/898] drm/i915/gvt: force-nopriv register handling

add a whitelist to check the content of force-nonpriv registers

v3:
per He Min's comment, modify in_whitelist()'s return type to bool, and use
negative value as the return value for failure for force_nonpriv_write().

v2:
1. split a big patch into two smaller ones per zhenyu's comment.
this patch is the mmio handling part for force-nopriv registers

2. per zhenyu's comment, combine all non-priv registers into a single
MMIO_DFH entry

Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 74 +++++++++++++++++++++++++++--
 1 file changed, 70 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index a1880424ad32..af0c0d1ec9a8 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -398,6 +398,74 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	return 0;
 }
 
+/* ascendingly sorted */
+static i915_reg_t force_nonpriv_white_list[] = {
+	GEN9_CS_DEBUG_MODE1, //_MMIO(0x20ec)
+	GEN9_CTX_PREEMPT_REG,//_MMIO(0x2248)
+	GEN8_CS_CHICKEN1,//_MMIO(0x2580)
+	_MMIO(0x2690),
+	_MMIO(0x2694),
+	_MMIO(0x2698),
+	_MMIO(0x4de0),
+	_MMIO(0x4de4),
+	_MMIO(0x4dfc),
+	GEN7_COMMON_SLICE_CHICKEN1,//_MMIO(0x7010)
+	_MMIO(0x7014),
+	HDC_CHICKEN0,//_MMIO(0x7300)
+	GEN8_HDC_CHICKEN1,//_MMIO(0x7304)
+	_MMIO(0x7700),
+	_MMIO(0x7704),
+	_MMIO(0x7708),
+	_MMIO(0x770c),
+	_MMIO(0xb110),
+	GEN8_L3SQCREG4,//_MMIO(0xb118)
+	_MMIO(0xe100),
+	_MMIO(0xe18c),
+	_MMIO(0xe48c),
+	_MMIO(0xe5f4),
+};
+
+/* a simple bsearch */
+static inline bool in_whitelist(unsigned int reg)
+{
+	int left = 0, right = ARRAY_SIZE(force_nonpriv_white_list);
+	i915_reg_t *array = force_nonpriv_white_list;
+
+	while (left < right) {
+		int mid = (left + right)/2;
+
+		if (reg > array[mid].reg)
+			left = mid + 1;
+		else if (reg < array[mid].reg)
+			right = mid;
+		else
+			return true;
+	}
+	return false;
+}
+
+static int force_nonpriv_write(struct intel_vgpu *vgpu,
+	unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 reg_nonpriv = *(u32 *)p_data;
+	int ret = -EINVAL;
+
+	if ((bytes != 4) || ((offset & (bytes - 1)) != 0)) {
+		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV offset %x(%dB)\n",
+			vgpu->id, offset, bytes);
+		return ret;
+	}
+
+	if (in_whitelist(reg_nonpriv)) {
+		ret = intel_vgpu_default_mmio_write(vgpu, offset, p_data,
+			bytes);
+	} else {
+		gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x\n",
+			vgpu->id, reg_nonpriv);
+	}
+	return ret;
+}
+
 static int ddi_buf_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
@@ -2420,10 +2488,8 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0xb10c, D_BDW);
 	MMIO_D(0xb110, D_BDW);
 
-	MMIO_DFH(0x24d0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x24d4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x24d8, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x24dc, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_F(0x24d0, 48, F_CMD_ACCESS, 0, 0, D_BDW_PLUS,
+		NULL, force_nonpriv_write);
 
 	MMIO_D(0x22040, D_BDW_PLUS);
 	MMIO_D(0x44484, D_BDW_PLUS);
-- 
GitLab


From 187447a106fc9caca45f10413845678d3666556c Mon Sep 17 00:00:00 2001
From: Pei Zhang <pei.zhang@intel.com>
Date: Tue, 21 Feb 2017 21:58:14 +0800
Subject: [PATCH 174/898] drm/i915/gvt: add cmd_access to
 GEN7_HALF_SLICE_CHICKEN1

Linux guest is using this MMIO in lri command. Add cmd_access flag
for this mmio in gvt to avoid error log.

v2: change the mmio address to its macro name

Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index af0c0d1ec9a8..bfe12ddb0210 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1607,7 +1607,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x243c, D_ALL);
 	MMIO_DFH(0x7018, D_ALL, F_MODE_MASK, NULL, NULL);
 	MMIO_DFH(HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0xe100, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(GEN7_HALF_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
 	/* display */
 	MMIO_F(0x60220, 0x20, 0, 0, 0, D_ALL, NULL, NULL);
-- 
GitLab


From ec162aa84c9057e196f3a844c0a8d569f5095e6c Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Tue, 21 Feb 2017 14:00:37 +0800
Subject: [PATCH 175/898] drm/i915/gvt: set default value to 0 for unhandled
 mmio regs

for a handled mmio reg,  its default value is read from hardware, while
for an unhandled mmio regs,  its default value would be random if not
explicitly set to 0

Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/firmware.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c
index 1cb29b2d7dc6..933a7c211a1c 100644
--- a/drivers/gpu/drm/i915/gvt/firmware.c
+++ b/drivers/gpu/drm/i915/gvt/firmware.c
@@ -80,7 +80,7 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt)
 	int ret;
 
 	size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1;
-	firmware = vmalloc(size);
+	firmware = vzalloc(size);
 	if (!firmware)
 		return -ENOMEM;
 
-- 
GitLab


From bab059304314e127cf4a5330c6bd5a71fd27c022 Mon Sep 17 00:00:00 2001
From: "Zhao, Xinda" <xinda.zhao@intel.com>
Date: Tue, 21 Feb 2017 15:07:31 +0800
Subject: [PATCH 176/898] drm/i915/gvt: decrease priority of output msg for
 untracked mmio

When untracked mmio is visited, too many log info will be printed out,
it may confuse the user, but most of the time, it is not the urgent case,
so use gvt_dbg_mmio() instead.

Signed-off-by: Zhao, Xinda <xinda.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/mmio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 99abb01fa9eb..60b698cb8365 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -298,7 +298,7 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 
 	mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
 	if (!mmio && !vgpu->mmio.disable_warn_untrack)
-		gvt_err("vgpu%d: write untracked MMIO %x len %d val %x\n",
+		gvt_dbg_mmio("vgpu%d: write untracked MMIO %x len %d val %x\n",
 				vgpu->id, offset, bytes, *(u32 *)p_data);
 
 	if (!intel_gvt_mmio_is_unalign(gvt, offset)) {
-- 
GitLab


From da9cc8de22aa6bd6ed51c406432d599ab520a6e3 Mon Sep 17 00:00:00 2001
From: Ping Gao <ping.a.gao@intel.com>
Date: Tue, 21 Feb 2017 15:52:56 +0800
Subject: [PATCH 177/898] drm/i915/gvt: clear the vGPU reset logic

Releasing shadow PPGTT pages is not enough when vGPU reset, the
guest page table tracking data should has same life-cycle with
all the shadow PPGTT pages; Otherwise there is no chance to
re-shadow the PPGTT pages without free the guest page table
tracking data.

This patch clear the PPGTT reset logic and make the vGPU reset in
working order.

v2: refactor some logic to avoid code duplicated.
v3: remove useless macro and add comments from Christophe.
v4: keep reset logic in reset function.

Signed-off-by: Ping Gao <ping.a.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 35 ++++++++++++++++++++++++----------
 1 file changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 28c92346db0e..b5c833287d39 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -2015,6 +2015,22 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
 	return create_scratch_page_tree(vgpu);
 }
 
+static void intel_vgpu_free_mm(struct intel_vgpu *vgpu, int type)
+{
+	struct list_head *pos, *n;
+	struct intel_vgpu_mm *mm;
+
+	list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) {
+		mm = container_of(pos, struct intel_vgpu_mm, list);
+		if (mm->type == type) {
+			vgpu->gvt->gtt.mm_free_page_table(mm);
+			list_del(&mm->list);
+			list_del(&mm->lru_list);
+			kfree(mm);
+		}
+	}
+}
+
 /**
  * intel_vgpu_clean_gtt - clean up per-vGPU graphics memory virulization
  * @vgpu: a vGPU
@@ -2027,19 +2043,11 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
  */
 void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu)
 {
-	struct list_head *pos, *n;
-	struct intel_vgpu_mm *mm;
-
 	ppgtt_free_all_shadow_page(vgpu);
 	release_scratch_page_tree(vgpu);
 
-	list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) {
-		mm = container_of(pos, struct intel_vgpu_mm, list);
-		vgpu->gvt->gtt.mm_free_page_table(mm);
-		list_del(&mm->list);
-		list_del(&mm->lru_list);
-		kfree(mm);
-	}
+	intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT);
+	intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_GGTT);
 }
 
 static void clean_spt_oos(struct intel_gvt *gvt)
@@ -2322,6 +2330,13 @@ void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr)
 	int i;
 
 	ppgtt_free_all_shadow_page(vgpu);
+
+	/* Shadow pages are only created when there is no page
+	 * table tracking data, so remove page tracking data after
+	 * removing the shadow pages.
+	 */
+	intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT);
+
 	if (!dmlr)
 		return;
 
-- 
GitLab


From d8a355be0b2b5613f7b34aee1394369d45d50586 Mon Sep 17 00:00:00 2001
From: Weinan Li <weinan.z.li@intel.com>
Date: Wed, 22 Feb 2017 11:03:24 +0800
Subject: [PATCH 178/898] drm/i915/gvt: refine pcode write emulation

In GVT-g we always emulate as pcode read/write success and ready for access
anytime, since we don't touch real physical registers here.

Add 'SKL_PCODE_CDCLK_CONTROL' write emulation, without it will cause
skl_set_cdclk fail in guest.

Signed-off-by: Weinan Li <weinan.z.li@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index bfe12ddb0210..f89b183488e9 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1315,6 +1315,9 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 		else
 			*data0 = 0x61514b3d;
 		break;
+	case SKL_PCODE_CDCLK_CONTROL:
+		*data0 = SKL_CDCLK_READY_FOR_CHANGE;
+		break;
 	case 0x5:
 		*data0 |= 0x1;
 		break;
@@ -1322,8 +1325,13 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 
 	gvt_dbg_core("VM(%d) write %x to mailbox, return data0 %x\n",
 		     vgpu->id, value, *data0);
-
-	value &= ~(1 << 31);
+	/**
+	 * PCODE_READY clear means ready for pcode read/write,
+	 * PCODE_ERROR_MASK clear means no error happened. In GVT-g we
+	 * always emulate as pcode read/write success and ready for access
+	 * anytime, since we don't touch real physical registers here.
+	 */
+	value &= ~(GEN6_PCODE_READY | GEN6_PCODE_ERROR_MASK);
 	return intel_vgpu_default_mmio_write(vgpu, offset, &value, bytes);
 }
 
-- 
GitLab


From 7c28135c77414327523b89bfc3f13096e095f5ac Mon Sep 17 00:00:00 2001
From: "Zhao, Xinda" <xinda.zhao@intel.com>
Date: Tue, 21 Feb 2017 15:54:56 +0800
Subject: [PATCH 179/898] drm/i915/gvt: remove unnecessary error msg from gtt
 write

The guest VM may initialize the whole GTT table during boot up,
so the warning msg in emulate_gtt_mmio_write is not necessary, it is
the expected behavior and it may confuse the user if error msg is
printed out, so remove the msg from emulate_gtt_mmio_write(),

Signed-off-by: Zhao, Xinda <xinda.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index b5c833287d39..6a5ff23ded90 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1825,11 +1825,8 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	gma = g_gtt_index << GTT_PAGE_SHIFT;
 
 	/* the VM may configure the whole GM space when ballooning is used */
-	if (WARN_ONCE(!vgpu_gmadr_is_valid(vgpu, gma),
-				"vgpu%d: found oob ggtt write, offset %x\n",
-				vgpu->id, off)) {
+	if (!vgpu_gmadr_is_valid(vgpu, gma))
 		return 0;
-	}
 
 	ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index);
 
-- 
GitLab


From 191020b670f84f5e2edfaa906c3801df20485610 Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Thu, 23 Feb 2017 14:46:23 +0800
Subject: [PATCH 180/898] drm/i915/gvt: adjust to fixed vGPU types

Previous vGPU type create tried to determine vGPU type name e.g _1, _2
based on the number of mdev devices can be created, but different type
might have very different resource size depending on physical device.
We need to split type name vs. actual mdev resource and create fixed
vGPU type with determined size for consistence.

With this we'd like to fix vGPU types for _1, _2, _4 and _8 now, each
type has fixed defined resource size. Available mdev instances that could
be created is determined by physical resource, and user should query
for that before creating.

Cc: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gvt.h  |  1 -
 drivers/gpu/drm/i915/gvt/vgpu.c | 58 +++++++++++++++++++--------------
 2 files changed, 34 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index a41b322d8957..faff044c6434 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -212,7 +212,6 @@ struct intel_gvt_opregion {
 #define NR_MAX_INTEL_VGPU_TYPES 20
 struct intel_vgpu_type {
 	char name[16];
-	unsigned int max_instance;
 	unsigned int avail_instance;
 	unsigned int low_gm_size;
 	unsigned int high_gm_size;
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index dcfcce1dc00e..c27c13c3cc48 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -64,6 +64,19 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 	WARN_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE);
 }
 
+static struct {
+	unsigned int low_mm;
+	unsigned int high_mm;
+	unsigned int fence;
+	char *name;
+} vgpu_types[] = {
+/* Fixed vGPU type table */
+	{ MB_TO_BYTES(64), MB_TO_BYTES(512), 4, "8" },
+	{ MB_TO_BYTES(128), MB_TO_BYTES(512), 4, "4" },
+	{ MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, "2" },
+	{ MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, "1" },
+};
+
 /**
  * intel_gvt_init_vgpu_types - initialize vGPU type list
  * @gvt : GVT device
@@ -78,9 +91,8 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 	unsigned int min_low;
 
 	/* vGPU type name is defined as GVTg_Vx_y which contains
-	 * physical GPU generation type and 'y' means maximum vGPU
-	 * instances user can create on one physical GPU for this
-	 * type.
+	 * physical GPU generation type (e.g V4 as BDW server, V5 as
+	 * SKL server).
 	 *
 	 * Depend on physical SKU resource, might see vGPU types like
 	 * GVTg_V4_8, GVTg_V4_4, GVTg_V4_2, etc. We can create
@@ -92,7 +104,7 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 	 */
 	low_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE;
 	high_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE;
-	num_types = 4;
+	num_types = sizeof(vgpu_types) / sizeof(vgpu_types[0]);
 
 	gvt->types = kzalloc(num_types * sizeof(struct intel_vgpu_type),
 			     GFP_KERNEL);
@@ -101,25 +113,24 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 
 	min_low = MB_TO_BYTES(32);
 	for (i = 0; i < num_types; ++i) {
-		if (low_avail / min_low == 0)
+		if (low_avail / vgpu_types[i].low_mm == 0)
 			break;
-		gvt->types[i].low_gm_size = min_low;
-		gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U));
-		gvt->types[i].fence = 4;
-		gvt->types[i].max_instance = min(low_avail / min_low,
-						 high_avail / gvt->types[i].high_gm_size);
-		gvt->types[i].avail_instance = gvt->types[i].max_instance;
+
+		gvt->types[i].low_gm_size = vgpu_types[i].low_mm;
+		gvt->types[i].high_gm_size = vgpu_types[i].high_mm;
+		gvt->types[i].fence = vgpu_types[i].fence;
+		gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm,
+						   high_avail / vgpu_types[i].high_mm);
 
 		if (IS_GEN8(gvt->dev_priv))
-			sprintf(gvt->types[i].name, "GVTg_V4_%u",
-						gvt->types[i].max_instance);
+			sprintf(gvt->types[i].name, "GVTg_V4_%s",
+						vgpu_types[i].name);
 		else if (IS_GEN9(gvt->dev_priv))
-			sprintf(gvt->types[i].name, "GVTg_V5_%u",
-						gvt->types[i].max_instance);
+			sprintf(gvt->types[i].name, "GVTg_V5_%s",
+						vgpu_types[i].name);
 
-		min_low <<= 1;
-		gvt_dbg_core("type[%d]: %s max %u avail %u low %u high %u fence %u\n",
-			     i, gvt->types[i].name, gvt->types[i].max_instance,
+		gvt_dbg_core("type[%d]: %s avail %u low %u high %u fence %u\n",
+			     i, gvt->types[i].name,
 			     gvt->types[i].avail_instance,
 			     gvt->types[i].low_gm_size,
 			     gvt->types[i].high_gm_size, gvt->types[i].fence);
@@ -138,7 +149,7 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt)
 {
 	int i;
 	unsigned int low_gm_avail, high_gm_avail, fence_avail;
-	unsigned int low_gm_min, high_gm_min, fence_min, total_min;
+	unsigned int low_gm_min, high_gm_min, fence_min;
 
 	/* Need to depend on maxium hw resource size but keep on
 	 * static config for now.
@@ -154,12 +165,11 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt)
 		low_gm_min = low_gm_avail / gvt->types[i].low_gm_size;
 		high_gm_min = high_gm_avail / gvt->types[i].high_gm_size;
 		fence_min = fence_avail / gvt->types[i].fence;
-		total_min = min(min(low_gm_min, high_gm_min), fence_min);
-		gvt->types[i].avail_instance = min(gvt->types[i].max_instance,
-						   total_min);
+		gvt->types[i].avail_instance = min(min(low_gm_min, high_gm_min),
+						   fence_min);
 
-		gvt_dbg_core("update type[%d]: %s max %u avail %u low %u high %u fence %u\n",
-		       i, gvt->types[i].name, gvt->types[i].max_instance,
+		gvt_dbg_core("update type[%d]: %s avail %u low %u high %u fence %u\n",
+		       i, gvt->types[i].name,
 		       gvt->types[i].avail_instance, gvt->types[i].low_gm_size,
 		       gvt->types[i].high_gm_size, gvt->types[i].fence);
 	}
-- 
GitLab


From 1f8728b7adc4c2b351cda886a6916087595c9125 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 17 Feb 2017 10:55:23 +0100
Subject: [PATCH 181/898] PM / Domains: Move genpd_power_off() above
 genpd_power_on()

Following changes in genpd_power_on() makes it invoke genpd_power_off().
To enable these changes and avoiding to declare genpd_power_off(), let's
move its implementation above genpd_power_on(). In this way, following
changes should become easier to review.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 162 ++++++++++++++++++------------------
 1 file changed, 81 insertions(+), 81 deletions(-)

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 3a75fb1b4126..3dc44f216067 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -273,6 +273,87 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 	queue_work(pm_wq, &genpd->power_off_work);
 }
 
+/**
+ * genpd_power_off - Remove power from a given PM domain.
+ * @genpd: PM domain to power down.
+ * @is_async: PM domain is powered down from a scheduled work
+ *
+ * If all of the @genpd's devices have been suspended and all of its subdomains
+ * have been powered down, remove power from @genpd.
+ */
+static int genpd_power_off(struct generic_pm_domain *genpd, bool is_async)
+{
+	struct pm_domain_data *pdd;
+	struct gpd_link *link;
+	unsigned int not_suspended = 0;
+
+	/*
+	 * Do not try to power off the domain in the following situations:
+	 * (1) The domain is already in the "power off" state.
+	 * (2) System suspend is in progress.
+	 */
+	if (genpd->status == GPD_STATE_POWER_OFF
+	    || genpd->prepared_count > 0)
+		return 0;
+
+	if (atomic_read(&genpd->sd_count) > 0)
+		return -EBUSY;
+
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		enum pm_qos_flags_status stat;
+
+		stat = dev_pm_qos_flags(pdd->dev,
+					PM_QOS_FLAG_NO_POWER_OFF
+						| PM_QOS_FLAG_REMOTE_WAKEUP);
+		if (stat > PM_QOS_FLAGS_NONE)
+			return -EBUSY;
+
+		/*
+		 * Do not allow PM domain to be powered off, when an IRQ safe
+		 * device is part of a non-IRQ safe domain.
+		 */
+		if (!pm_runtime_suspended(pdd->dev) ||
+			irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd))
+			not_suspended++;
+	}
+
+	if (not_suspended > 1 || (not_suspended == 1 && is_async))
+		return -EBUSY;
+
+	if (genpd->gov && genpd->gov->power_down_ok) {
+		if (!genpd->gov->power_down_ok(&genpd->domain))
+			return -EAGAIN;
+	}
+
+	if (genpd->power_off) {
+		int ret;
+
+		if (atomic_read(&genpd->sd_count) > 0)
+			return -EBUSY;
+
+		/*
+		 * If sd_count > 0 at this point, one of the subdomains hasn't
+		 * managed to call genpd_power_on() for the master yet after
+		 * incrementing it.  In that case genpd_power_on() will wait
+		 * for us to drop the lock, so we can call .power_off() and let
+		 * the genpd_power_on() restore power for us (this shouldn't
+		 * happen very often).
+		 */
+		ret = _genpd_power_off(genpd, true);
+		if (ret)
+			return ret;
+	}
+
+	genpd->status = GPD_STATE_POWER_OFF;
+
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		genpd_sd_counter_dec(link->master);
+		genpd_queue_power_off_work(link->master);
+	}
+
+	return 0;
+}
+
 /**
  * genpd_power_on - Restore power to a given PM domain and its masters.
  * @genpd: PM domain to power up.
@@ -367,87 +448,6 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-/**
- * genpd_power_off - Remove power from a given PM domain.
- * @genpd: PM domain to power down.
- * @is_async: PM domain is powered down from a scheduled work
- *
- * If all of the @genpd's devices have been suspended and all of its subdomains
- * have been powered down, remove power from @genpd.
- */
-static int genpd_power_off(struct generic_pm_domain *genpd, bool is_async)
-{
-	struct pm_domain_data *pdd;
-	struct gpd_link *link;
-	unsigned int not_suspended = 0;
-
-	/*
-	 * Do not try to power off the domain in the following situations:
-	 * (1) The domain is already in the "power off" state.
-	 * (2) System suspend is in progress.
-	 */
-	if (genpd->status == GPD_STATE_POWER_OFF
-	    || genpd->prepared_count > 0)
-		return 0;
-
-	if (atomic_read(&genpd->sd_count) > 0)
-		return -EBUSY;
-
-	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
-		enum pm_qos_flags_status stat;
-
-		stat = dev_pm_qos_flags(pdd->dev,
-					PM_QOS_FLAG_NO_POWER_OFF
-						| PM_QOS_FLAG_REMOTE_WAKEUP);
-		if (stat > PM_QOS_FLAGS_NONE)
-			return -EBUSY;
-
-		/*
-		 * Do not allow PM domain to be powered off, when an IRQ safe
-		 * device is part of a non-IRQ safe domain.
-		 */
-		if (!pm_runtime_suspended(pdd->dev) ||
-			irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd))
-			not_suspended++;
-	}
-
-	if (not_suspended > 1 || (not_suspended == 1 && is_async))
-		return -EBUSY;
-
-	if (genpd->gov && genpd->gov->power_down_ok) {
-		if (!genpd->gov->power_down_ok(&genpd->domain))
-			return -EAGAIN;
-	}
-
-	if (genpd->power_off) {
-		int ret;
-
-		if (atomic_read(&genpd->sd_count) > 0)
-			return -EBUSY;
-
-		/*
-		 * If sd_count > 0 at this point, one of the subdomains hasn't
-		 * managed to call genpd_power_on() for the master yet after
-		 * incrementing it.  In that case genpd_power_on() will wait
-		 * for us to drop the lock, so we can call .power_off() and let
-		 * the genpd_power_on() restore power for us (this shouldn't
-		 * happen very often).
-		 */
-		ret = _genpd_power_off(genpd, true);
-		if (ret)
-			return ret;
-	}
-
-	genpd->status = GPD_STATE_POWER_OFF;
-
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_dec(link->master);
-		genpd_queue_power_off_work(link->master);
-	}
-
-	return 0;
-}
-
 /**
  * genpd_power_off_work_fn - Power off PM domain whose subdomain count is 0.
  * @work: Work structure used for scheduling the execution of this function.
-- 
GitLab


From 3c64649d1cf9f32fd16491e69ccc16385e0ef421 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 17 Feb 2017 10:55:24 +0100
Subject: [PATCH 182/898] PM / Domains: Rename is_async to one_dev_on for
 genpd_power_off()

The parameter name is_async, for genpd_power_off() gives a poor description
of its purpose. To clarify, let's rename it to one_dev_on and update the
documentation of it in the function header.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 3dc44f216067..179bb269a58f 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -276,12 +276,15 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 /**
  * genpd_power_off - Remove power from a given PM domain.
  * @genpd: PM domain to power down.
- * @is_async: PM domain is powered down from a scheduled work
+ * @one_dev_on: If invoked from genpd's ->runtime_suspend|resume() callback, the
+ * RPM status of the releated device is in an intermediate state, not yet turned
+ * into RPM_SUSPENDED. This means genpd_power_off() must allow one device to not
+ * be RPM_SUSPENDED, while it tries to power off the PM domain.
  *
  * If all of the @genpd's devices have been suspended and all of its subdomains
  * have been powered down, remove power from @genpd.
  */
-static int genpd_power_off(struct generic_pm_domain *genpd, bool is_async)
+static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on)
 {
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
@@ -317,7 +320,7 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool is_async)
 			not_suspended++;
 	}
 
-	if (not_suspended > 1 || (not_suspended == 1 && is_async))
+	if (not_suspended > 1 || (not_suspended == 1 && !one_dev_on))
 		return -EBUSY;
 
 	if (genpd->gov && genpd->gov->power_down_ok) {
@@ -459,7 +462,7 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
 	genpd_lock(genpd);
-	genpd_power_off(genpd, true);
+	genpd_power_off(genpd, false);
 	genpd_unlock(genpd);
 }
 
@@ -578,7 +581,7 @@ static int genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	genpd_lock(genpd);
-	genpd_power_off(genpd, false);
+	genpd_power_off(genpd, true);
 	genpd_unlock(genpd);
 
 	return 0;
@@ -658,7 +661,7 @@ static int genpd_runtime_resume(struct device *dev)
 	if (!pm_runtime_is_irq_safe(dev) ||
 		(pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) {
 		genpd_lock(genpd);
-		genpd_power_off(genpd, 0);
+		genpd_power_off(genpd, true);
 		genpd_unlock(genpd);
 	}
 
-- 
GitLab


From 2da835452a0875866ca55d23126c77b9372f0015 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 17 Feb 2017 10:55:25 +0100
Subject: [PATCH 183/898] PM / Domains: Power off masters immediately in the
 power off sequence

Once a subdomain is powered off, genpd queues a power off work for each of
the subdomain's corresponding masters, thus postponing the masters to be
powered off to a later point.

When genpd used intermediate power off states, which was removed in
commit ba2bbfbf6307 ("PM / Domains: Remove intermediate states from the
power off sequence"), this behaviour made sense, but now it simply doesn't.

Genpd can easily try to power off the masters in the same context as the
subdomain, of course by acquiring/releasing the lock. Then, let's convert
to this behaviour, as it avoids unnecessary works from being queued.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 179bb269a58f..e697dec9d25b 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -284,7 +284,8 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
  * If all of the @genpd's devices have been suspended and all of its subdomains
  * have been powered down, remove power from @genpd.
  */
-static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on)
+static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
+			   unsigned int depth)
 {
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
@@ -351,7 +352,9 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on)
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_dec(link->master);
-		genpd_queue_power_off_work(link->master);
+		genpd_lock_nested(link->master, depth + 1);
+		genpd_power_off(link->master, false, depth + 1);
+		genpd_unlock(link->master);
 	}
 
 	return 0;
@@ -405,7 +408,9 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 					&genpd->slave_links,
 					slave_node) {
 		genpd_sd_counter_dec(link->master);
-		genpd_queue_power_off_work(link->master);
+		genpd_lock_nested(link->master, depth + 1);
+		genpd_power_off(link->master, false, depth + 1);
+		genpd_unlock(link->master);
 	}
 
 	return ret;
@@ -462,7 +467,7 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
 	genpd_lock(genpd);
-	genpd_power_off(genpd, false);
+	genpd_power_off(genpd, false, 0);
 	genpd_unlock(genpd);
 }
 
@@ -581,7 +586,7 @@ static int genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	genpd_lock(genpd);
-	genpd_power_off(genpd, true);
+	genpd_power_off(genpd, true, 0);
 	genpd_unlock(genpd);
 
 	return 0;
@@ -661,7 +666,7 @@ static int genpd_runtime_resume(struct device *dev)
 	if (!pm_runtime_is_irq_safe(dev) ||
 		(pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) {
 		genpd_lock(genpd);
-		genpd_power_off(genpd, true);
+		genpd_power_off(genpd, true, 0);
 		genpd_unlock(genpd);
 	}
 
-- 
GitLab


From 76aaf87b4cdc7f7115a32e4fda88310d42ce7fde Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Feb 2017 16:02:36 +0100
Subject: [PATCH 184/898] scsi: merge __scsi_execute into scsi_execute

All but one caller want the decoded sense header, so offer the existing
__scsi_execute helper as the public scsi_execute API to simply the
callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-scsi.c         | 12 +++-----
 drivers/scsi/cxlflash/superpipe.c |  8 ++----
 drivers/scsi/cxlflash/vlun.c      |  4 +--
 drivers/scsi/scsi_lib.c           | 48 ++++++++++++++-----------------
 drivers/scsi/scsi_transport_spi.c | 24 +++++++---------
 drivers/scsi/sr_ioctl.c           | 19 ++----------
 include/scsi/scsi_device.h        |  5 ++--
 7 files changed, 46 insertions(+), 74 deletions(-)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 12d3a66600a3..1ac70744ae7b 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -600,6 +600,7 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	u8 args[4], *argbuf = NULL, *sensebuf = NULL;
 	int argsize = 0;
 	enum dma_data_direction data_dir;
+	struct scsi_sense_hdr sshdr;
 	int cmd_result;
 
 	if (arg == NULL)
@@ -648,7 +649,7 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	/* Good values for timeout and retries?  Values below
 	   from scsi_ioctl_send_command() for default case... */
 	cmd_result = scsi_execute(scsidev, scsi_cmd, data_dir, argbuf, argsize,
-				  sensebuf, (10*HZ), 5, 0, NULL);
+				  sensebuf, &sshdr, (10*HZ), 5, 0, 0, NULL);
 
 	if (driver_byte(cmd_result) == DRIVER_SENSE) {/* sense data available */
 		u8 *desc = sensebuf + 8;
@@ -657,9 +658,6 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 		/* If we set cc then ATA pass-through will cause a
 		 * check condition even if no error. Filter that. */
 		if (cmd_result & SAM_STAT_CHECK_CONDITION) {
-			struct scsi_sense_hdr sshdr;
-			scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE,
-					     &sshdr);
 			if (sshdr.sense_key == RECOVERED_ERROR &&
 			    sshdr.asc == 0 && sshdr.ascq == 0x1d)
 				cmd_result &= ~SAM_STAT_CHECK_CONDITION;
@@ -707,6 +705,7 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	int rc = 0;
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
 	u8 args[7], *sensebuf = NULL;
+	struct scsi_sense_hdr sshdr;
 	int cmd_result;
 
 	if (arg == NULL)
@@ -734,7 +733,7 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	/* Good values for timeout and retries?  Values below
 	   from scsi_ioctl_send_command() for default case... */
 	cmd_result = scsi_execute(scsidev, scsi_cmd, DMA_NONE, NULL, 0,
-				sensebuf, (10*HZ), 5, 0, NULL);
+				sensebuf, &sshdr, (10*HZ), 5, 0, 0, NULL);
 
 	if (driver_byte(cmd_result) == DRIVER_SENSE) {/* sense data available */
 		u8 *desc = sensebuf + 8;
@@ -743,9 +742,6 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 		/* If we set cc then ATA pass-through will cause a
 		 * check condition even if no error. Filter that. */
 		if (cmd_result & SAM_STAT_CHECK_CONDITION) {
-			struct scsi_sense_hdr sshdr;
-			scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE,
-						&sshdr);
 			if (sshdr.sense_key == RECOVERED_ERROR &&
 			    sshdr.asc == 0 && sshdr.ascq == 0x1d)
 				cmd_result &= ~SAM_STAT_CHECK_CONDITION;
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index 90869cee2b20..5b812ed87f22 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -305,6 +305,7 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct glun_info *gli = lli->parent;
+	struct scsi_sense_hdr sshdr;
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
 	u8 *sense_buf = NULL;
@@ -332,7 +333,8 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	/* Drop the ioctl read semahpore across lengthy call */
 	up_read(&cfg->ioctl_rwsem);
 	result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
-			      CMD_BUFSIZE, sense_buf, to, CMD_RETRIES, 0, NULL);
+			      CMD_BUFSIZE, sense_buf, &sshdr, to, CMD_RETRIES,
+			      0, 0, NULL);
 	down_read(&cfg->ioctl_rwsem);
 	rc = check_state(cfg);
 	if (rc) {
@@ -345,10 +347,6 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	if (driver_byte(result) == DRIVER_SENSE) {
 		result &= ~(0xFF<<24); /* DRIVER_SENSE is not an error */
 		if (result & SAM_STAT_CHECK_CONDITION) {
-			struct scsi_sense_hdr sshdr;
-
-			scsi_normalize_sense(sense_buf, SCSI_SENSE_BUFFERSIZE,
-					    &sshdr);
 			switch (sshdr.sense_key) {
 			case NO_SENSE:
 			case RECOVERED_ERROR:
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index 8fcc804dbef9..7aa06ef229fd 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -453,8 +453,8 @@ static int write_same16(struct scsi_device *sdev,
 		/* Drop the ioctl read semahpore across lengthy call */
 		up_read(&cfg->ioctl_rwsem);
 		result = scsi_execute(sdev, scsi_cmd, DMA_TO_DEVICE, cmd_buf,
-				      CMD_BUFSIZE, sense_buf, to, CMD_RETRIES,
-				      0, NULL);
+				      CMD_BUFSIZE, sense_buf, NULL, to,
+				      CMD_RETRIES, 0, 0, NULL);
 		down_read(&cfg->ioctl_rwsem);
 		rc = check_state(cfg);
 		if (rc) {
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 5f661486cf6e..b0cb3e0713f3 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -213,7 +213,26 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 	__scsi_queue_insert(cmd, reason, 1);
 }
 
-static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+
+/**
+ * scsi_execute - insert request and wait for the result
+ * @sdev:	scsi device
+ * @cmd:	scsi command
+ * @data_direction: data direction
+ * @buffer:	data buffer
+ * @bufflen:	len of buffer
+ * @sense:	optional sense buffer
+ * @sshdr:	optional decoded sense header
+ * @timeout:	request timeout in seconds
+ * @retries:	number of times to retry request
+ * @flags:	flags for ->cmd_flags
+ * @rq_flags:	flags for ->rq_flags
+ * @resid:	optional residual length
+ *
+ * returns the req->errors value which is the scsi_cmnd result
+ * field.
+ */
+int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
 		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
@@ -268,31 +287,6 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	return ret;
 }
-
-/**
- * scsi_execute - insert request and wait for the result
- * @sdev:	scsi device
- * @cmd:	scsi command
- * @data_direction: data direction
- * @buffer:	data buffer
- * @bufflen:	len of buffer
- * @sense:	optional sense buffer
- * @timeout:	request timeout in seconds
- * @retries:	number of times to retry request
- * @flags:	or into request flags;
- * @resid:	optional residual length
- *
- * returns the req->errors value which is the scsi_cmnd result
- * field.
- */
-int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
-		 int data_direction, void *buffer, unsigned bufflen,
-		 unsigned char *sense, int timeout, int retries, u64 flags,
-		 int *resid)
-{
-	return __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,
-			NULL, timeout, retries, flags, 0, resid);
-}
 EXPORT_SYMBOL(scsi_execute);
 
 int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
@@ -300,7 +294,7 @@ int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
 		     struct scsi_sense_hdr *sshdr, int timeout, int retries,
 		     int *resid, u64 flags, req_flags_t rq_flags)
 {
-	return __scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
+	return scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
 			      NULL, sshdr, timeout, retries, flags, rq_flags,
 			      resid);
 }
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index 319868f3f674..d0219e36080c 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -123,25 +123,21 @@ static int spi_execute(struct scsi_device *sdev, const void *cmd,
 {
 	int i, result;
 	unsigned char sense[SCSI_SENSE_BUFFERSIZE];
+	struct scsi_sense_hdr sshdr_tmp;
+
+	if (!sshdr)
+		sshdr = &sshdr_tmp;
 
 	for(i = 0; i < DV_RETRIES; i++) {
-		result = scsi_execute(sdev, cmd, dir, buffer, bufflen,
-				      sense, DV_TIMEOUT, /* retries */ 1,
+		result = scsi_execute(sdev, cmd, dir, buffer, bufflen, sense,
+				      sshdr, DV_TIMEOUT, /* retries */ 1,
 				      REQ_FAILFAST_DEV |
 				      REQ_FAILFAST_TRANSPORT |
 				      REQ_FAILFAST_DRIVER,
-				      NULL);
-		if (driver_byte(result) & DRIVER_SENSE) {
-			struct scsi_sense_hdr sshdr_tmp;
-			if (!sshdr)
-				sshdr = &sshdr_tmp;
-
-			if (scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE,
-						 sshdr)
-			    && sshdr->sense_key == UNIT_ATTENTION)
-				continue;
-		}
-		break;
+				      0, NULL);
+		if (!(driver_byte(result) & DRIVER_SENSE) ||
+		    sshdr->sense_key != UNIT_ATTENTION)
+			break;
 	}
 	return result;
 }
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index dfffdf63e44c..4610c8c5693f 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -187,30 +187,19 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	struct scsi_device *SDev;
 	struct scsi_sense_hdr sshdr;
 	int result, err = 0, retries = 0;
-	struct request_sense *sense = cgc->sense;
 
 	SDev = cd->device;
 
-	if (!sense) {
-		sense = kmalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-		if (!sense) {
-			err = -ENOMEM;
-			goto out;
-		}
-	}
-
       retry:
 	if (!scsi_block_when_processing_errors(SDev)) {
 		err = -ENODEV;
 		goto out;
 	}
 
-	memset(sense, 0, sizeof(*sense));
 	result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
-			      cgc->buffer, cgc->buflen, (char *)sense,
-			      cgc->timeout, IOCTL_RETRIES, 0, NULL);
-
-	scsi_normalize_sense((char *)sense, sizeof(*sense), &sshdr);
+			      cgc->buffer, cgc->buflen,
+			      (unsigned char *)cgc->sense, &sshdr,
+			      cgc->timeout, IOCTL_RETRIES, 0, 0, NULL);
 
 	/* Minimal error checking.  Ignore cases we know about, and report the rest. */
 	if (driver_byte(result) != 0) {
@@ -261,8 +250,6 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 
 	/* Wake up a process waiting for device */
       out:
-	if (!cgc->sense)
-		kfree(sense);
 	cgc->stat = err;
 	return err;
 }
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index be41c76ddd48..cb4c8c889da0 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -410,8 +410,9 @@ extern int scsi_is_target_device(const struct device *);
 extern void scsi_sanitize_inquiry_string(unsigned char *s, int len);
 extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
-			unsigned char *sense, int timeout, int retries,
-			u64 flags, int *resid);
+			unsigned char *sense, struct scsi_sense_hdr *sshdr,
+			int timeout, int retries, u64 flags,
+			req_flags_t rq_flags, int *resid);
 extern int scsi_execute_req_flags(struct scsi_device *sdev,
 	const unsigned char *cmd, int data_direction, void *buffer,
 	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,
-- 
GitLab


From fcbfffe2c5cbec0c1721b2261c316b961ad50208 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 23 Feb 2017 16:02:37 +0100
Subject: [PATCH 185/898] scsi: remove scsi_execute_req_flags

And switch all callers to use scsi_execute instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/device_handler/scsi_dh_alua.c  | 16 ++++++----------
 drivers/scsi/device_handler/scsi_dh_emc.c   |  7 +++----
 drivers/scsi/device_handler/scsi_dh_hp_sw.c | 10 ++++------
 drivers/scsi/device_handler/scsi_dh_rdac.c  |  7 +++----
 drivers/scsi/scsi_lib.c                     | 11 -----------
 drivers/scsi/sd.c                           |  9 ++++-----
 drivers/scsi/ufs/ufshcd.c                   | 10 +++++-----
 include/scsi/scsi_device.h                  |  8 ++------
 8 files changed, 27 insertions(+), 51 deletions(-)

diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index d704752b6332..48e200102221 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -151,11 +151,9 @@ static int submit_rtpg(struct scsi_device *sdev, unsigned char *buff,
 		cdb[1] = MI_REPORT_TARGET_PGS;
 	put_unaligned_be32(bufflen, &cdb[6]);
 
-	return scsi_execute_req_flags(sdev, cdb, DMA_FROM_DEVICE,
-				      buff, bufflen, sshdr,
-				      ALUA_FAILOVER_TIMEOUT * HZ,
-				      ALUA_FAILOVER_RETRIES, NULL,
-				      req_flags, 0);
+	return scsi_execute(sdev, cdb, DMA_FROM_DEVICE, buff, bufflen, NULL,
+			sshdr, ALUA_FAILOVER_TIMEOUT * HZ,
+			ALUA_FAILOVER_RETRIES, req_flags, 0, NULL);
 }
 
 /*
@@ -185,11 +183,9 @@ static int submit_stpg(struct scsi_device *sdev, int group_id,
 	cdb[1] = MO_SET_TARGET_PGS;
 	put_unaligned_be32(stpg_len, &cdb[6]);
 
-	return scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
-				      stpg_data, stpg_len,
-				      sshdr, ALUA_FAILOVER_TIMEOUT * HZ,
-				      ALUA_FAILOVER_RETRIES, NULL,
-				      req_flags, 0);
+	return scsi_execute(sdev, cdb, DMA_TO_DEVICE, stpg_data, stpg_len, NULL,
+			sshdr, ALUA_FAILOVER_TIMEOUT * HZ,
+			ALUA_FAILOVER_RETRIES, req_flags, 0, NULL);
 }
 
 static struct alua_port_group *alua_find_get_pg(char *id_str, size_t id_size,
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index f1578832ec7a..8654e940e1a8 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -276,10 +276,9 @@ static int send_trespass_cmd(struct scsi_device *sdev,
 	BUG_ON((len > CLARIION_BUFFER_SIZE));
 	memcpy(csdev->buffer, page22, len);
 
-	err = scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
-				     csdev->buffer, len, &sshdr,
-				     CLARIION_TIMEOUT * HZ, CLARIION_RETRIES,
-				     NULL, req_flags, 0);
+	err = scsi_execute(sdev, cdb, DMA_TO_DEVICE, csdev->buffer, len, NULL,
+			&sshdr, CLARIION_TIMEOUT * HZ, CLARIION_RETRIES,
+			req_flags, 0, NULL);
 	if (err) {
 		if (scsi_sense_valid(&sshdr))
 			res = trespass_endio(sdev, &sshdr);
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index be43c940636d..62d314e07d11 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -100,9 +100,8 @@ static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 		REQ_FAILFAST_DRIVER;
 
 retry:
-	res = scsi_execute_req_flags(sdev, cmd, DMA_NONE, NULL, 0, &sshdr,
-				     HP_SW_TIMEOUT, HP_SW_RETRIES,
-				     NULL, req_flags, 0);
+	res = scsi_execute(sdev, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+			HP_SW_TIMEOUT, HP_SW_RETRIES, req_flags, 0, NULL);
 	if (res) {
 		if (scsi_sense_valid(&sshdr))
 			ret = tur_done(sdev, h, &sshdr);
@@ -139,9 +138,8 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *h)
 		REQ_FAILFAST_DRIVER;
 
 retry:
-	res = scsi_execute_req_flags(sdev, cmd, DMA_NONE, NULL, 0, &sshdr,
-				     HP_SW_TIMEOUT, HP_SW_RETRIES,
-				     NULL, req_flags, 0);
+	res = scsi_execute(sdev, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+			HP_SW_TIMEOUT, HP_SW_RETRIES, req_flags, 0, NULL);
 	if (res) {
 		if (!scsi_sense_valid(&sshdr)) {
 			sdev_printk(KERN_WARNING, sdev,
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index b64eaae8533d..3cbab8710e58 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -555,10 +555,9 @@ static void send_mode_select(struct work_struct *work)
 		(char *) h->ctlr->array_name, h->ctlr->index,
 		(retry_cnt == RDAC_RETRY_COUNT) ? "queueing" : "retrying");
 
-	if (scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
-				   &h->ctlr->mode_select, data_size, &sshdr,
-				   RDAC_TIMEOUT * HZ,
-				   RDAC_RETRIES, NULL, req_flags, 0)) {
+	if (scsi_execute(sdev, cdb, DMA_TO_DEVICE, &h->ctlr->mode_select,
+			data_size, NULL, &sshdr, RDAC_TIMEOUT * HZ,
+			RDAC_RETRIES, req_flags, 0, NULL)) {
 		err = mode_select_handle_sense(sdev, &sshdr);
 		if (err == SCSI_DH_RETRY && retry_cnt--)
 			goto retry;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b0cb3e0713f3..f5e45a252485 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -289,17 +289,6 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 }
 EXPORT_SYMBOL(scsi_execute);
 
-int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
-		     int data_direction, void *buffer, unsigned bufflen,
-		     struct scsi_sense_hdr *sshdr, int timeout, int retries,
-		     int *resid, u64 flags, req_flags_t rq_flags)
-{
-	return scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
-			      NULL, sshdr, timeout, retries, flags, rq_flags,
-			      resid);
-}
-EXPORT_SYMBOL(scsi_execute_req_flags);
-
 /*
  * Function:    scsi_init_cmd_errh()
  *
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index be535d4215c4..c7839f6c35cc 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1508,9 +1508,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
 		 * Leave the rest of the command zero to indicate
 		 * flush everything.
 		 */
-		res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0,
-					     &sshdr, timeout, SD_MAX_RETRIES,
-					     NULL, 0, RQF_PM);
+		res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+				timeout, SD_MAX_RETRIES, 0, RQF_PM, NULL);
 		if (res == 0)
 			break;
 	}
@@ -3296,8 +3295,8 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
 	if (!scsi_device_online(sdp))
 		return -ENODEV;
 
-	res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
-			       SD_TIMEOUT, SD_MAX_RETRIES, NULL, 0, RQF_PM);
+	res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+			SD_TIMEOUT, SD_MAX_RETRIES, 0, RQF_PM, NULL);
 	if (res) {
 		sd_print_result(sdkp, "Start/Stop Unit failed", res);
 		if (driver_byte(res) & DRIVER_SENSE)
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 8b721f431dd0..dc6efbd1be8e 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -6915,9 +6915,9 @@ ufshcd_send_request_sense(struct ufs_hba *hba, struct scsi_device *sdp)
 		goto out;
 	}
 
-	ret = scsi_execute_req_flags(sdp, cmd, DMA_FROM_DEVICE, buffer,
-				UFSHCD_REQ_SENSE_SIZE, NULL,
-				msecs_to_jiffies(1000), 3, NULL, 0, RQF_PM);
+	ret = scsi_execute(sdp, cmd, DMA_FROM_DEVICE, buffer,
+			UFSHCD_REQ_SENSE_SIZE, NULL, NULL,
+			msecs_to_jiffies(1000), 3, 0, RQF_PM, NULL);
 	if (ret)
 		pr_err("%s: failed with err %d\n", __func__, ret);
 
@@ -6982,8 +6982,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	 * callbacks hence set the RQF_PM flag so that it doesn't resume the
 	 * already suspended childs.
 	 */
-	ret = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
-				     START_STOP_TIMEOUT, 0, NULL, 0, RQF_PM);
+	ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+			START_STOP_TIMEOUT, 0, 0, RQF_PM, NULL);
 	if (ret) {
 		sdev_printk(KERN_WARNING, sdp,
 			    "START_STOP failed for power mode: %d, result %x\n",
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index cb4c8c889da0..6f22b39f1b0c 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -413,17 +413,13 @@ extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			unsigned char *sense, struct scsi_sense_hdr *sshdr,
 			int timeout, int retries, u64 flags,
 			req_flags_t rq_flags, int *resid);
-extern int scsi_execute_req_flags(struct scsi_device *sdev,
-	const unsigned char *cmd, int data_direction, void *buffer,
-	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,
-	int retries, int *resid, u64 flags, req_flags_t rq_flags);
 static inline int scsi_execute_req(struct scsi_device *sdev,
 	const unsigned char *cmd, int data_direction, void *buffer,
 	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,
 	int retries, int *resid)
 {
-	return scsi_execute_req_flags(sdev, cmd, data_direction, buffer,
-		bufflen, sshdr, timeout, retries, resid, 0, 0);
+	return scsi_execute(sdev, cmd, data_direction, buffer,
+		bufflen, NULL, sshdr, timeout, retries,  0, 0, resid);
 }
 extern void sdev_disable_disk_events(struct scsi_device *sdev);
 extern void sdev_enable_disk_events(struct scsi_device *sdev);
-- 
GitLab


From 1afca6b5f31616d330fb64a0c87060640a75ff6a Mon Sep 17 00:00:00 2001
From: "Dupuis, Chad" <chad.dupuis@cavium.com>
Date: Thu, 23 Feb 2017 07:01:03 -0800
Subject: [PATCH 186/898] scsi: qedf: fixup compilation warning about atomic_t
 usage

Based on an original patch by Hannes Reinecke.

The driver didn't follow the atomic_t vs refcount_t change, and anyway
one should be using kref_read() instead of accessing the counter inside
an kref.

Fixes: 61d8658b4a435e ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.)
Cc: Hannes Reinecke <hare@suse.de>
Cc: Nilesh Javali <nilesh.javali@cavium.com>
Signed-off-by: Dupuis, Chad <chad.dupuis@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedf/qedf_els.c | 6 +++---
 drivers/scsi/qedf/qedf_io.c  | 8 ++++----
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c
index 78f1c252b649..59f3e5c73a13 100644
--- a/drivers/scsi/qedf/qedf_els.c
+++ b/drivers/scsi/qedf/qedf_els.c
@@ -183,7 +183,7 @@ static void qedf_rrq_compl(struct qedf_els_cb_arg *cb_arg)
 	    rrq_req->event != QEDF_IOREQ_EV_ELS_ERR_DETECT)
 		cancel_delayed_work_sync(&orig_io_req->timeout_work);
 
-	refcount = atomic_read(&orig_io_req->refcount.refcount);
+	refcount = kref_read(&orig_io_req->refcount);
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "rrq_compl: orig io = %p,"
 		   " orig xid = 0x%x, rrq_xid = 0x%x, refcount=%d\n",
 		   orig_io_req, orig_io_req->xid, rrq_req->xid, refcount);
@@ -474,7 +474,7 @@ static void qedf_srr_compl(struct qedf_els_cb_arg *cb_arg)
 	    srr_req->event != QEDF_IOREQ_EV_ELS_ERR_DETECT)
 		cancel_delayed_work_sync(&orig_io_req->timeout_work);
 
-	refcount = atomic_read(&orig_io_req->refcount.refcount);
+	refcount = kref_read(&orig_io_req->refcount);
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Entered: orig_io=%p,"
 		   " orig_io_xid=0x%x, rec_xid=0x%x, refcount=%d\n",
 		   orig_io_req, orig_io_req->xid, srr_req->xid, refcount);
@@ -758,7 +758,7 @@ static void qedf_rec_compl(struct qedf_els_cb_arg *cb_arg)
 	    rec_req->event != QEDF_IOREQ_EV_ELS_ERR_DETECT)
 		cancel_delayed_work_sync(&orig_io_req->timeout_work);
 
-	refcount = atomic_read(&orig_io_req->refcount.refcount);
+	refcount = kref_read(&orig_io_req->refcount);
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Entered: orig_io=%p,"
 		   " orig_io_xid=0x%x, rec_xid=0x%x, refcount=%d\n",
 		   orig_io_req, orig_io_req->xid, rec_req->xid, refcount);
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
index 486c045ac8bb..ee0dcf9d3aba 100644
--- a/drivers/scsi/qedf/qedf_io.c
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -998,7 +998,7 @@ static void qedf_trace_io(struct qedf_rport *fcport, struct qedf_ioreq *io_req,
 	io_log->sg_count = scsi_sg_count(sc_cmd);
 	io_log->result = sc_cmd->result;
 	io_log->jiffies = jiffies;
-	io_log->refcount = atomic_read(&io_req->refcount.refcount);
+	io_log->refcount = kref_read(&io_req->refcount);
 
 	if (direction == QEDF_IO_TRACE_REQ) {
 		/* For requests we only care abot the submission CPU */
@@ -1340,7 +1340,7 @@ void qedf_scsi_completion(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 			/* Good I/O completion */
 			sc_cmd->result = DID_OK << 16;
 		} else {
-			refcount = atomic_read(&io_req->refcount.refcount);
+			refcount = kref_read(&io_req->refcount);
 			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
 			    "%d:0:%d:%d xid=0x%0x op=0x%02x "
 			    "lba=%02x%02x%02x%02x cdb_status=%d "
@@ -1425,7 +1425,7 @@ void qedf_scsi_done(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
 	qedf_unmap_sg_list(qedf, io_req);
 
 	sc_cmd->result = result << 16;
-	refcount = atomic_read(&io_req->refcount.refcount);
+	refcount = kref_read(&io_req->refcount);
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%d: Completing "
 	    "sc_cmd=%p result=0x%08x op=0x%02x lba=0x%02x%02x%02x%02x, "
 	    "allowed=%d retries=%d refcount=%d.\n",
@@ -1556,7 +1556,7 @@ static void qedf_flush_els_req(struct qedf_ctx *qedf,
 {
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
 	    "Flushing ELS request xid=0x%x refcount=%d.\n", els_req->xid,
-	    atomic_read(&els_req->refcount.refcount));
+	    kref_read(&els_req->refcount));
 
 	/*
 	 * Need to distinguish this from a timeout when calling the
-- 
GitLab


From 8cc311167c22f9365304b2b20225df2d881c8843 Mon Sep 17 00:00:00 2001
From: Andrzej Hajda <a.hajda@samsung.com>
Date: Mon, 20 Feb 2017 19:57:57 +0100
Subject: [PATCH 187/898] PM / OPP: fix off-by-one bug in
 dev_pm_opp_get_max_volt_latency loop

Reading array at given index before checking if index is valid results in
illegal memory access.

The bug was detected using KASAN framework.

Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 91ec3232d630..dae61720b314 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -231,7 +231,8 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 	 * The caller needs to ensure that opp_table (and hence the regulator)
 	 * isn't freed, while we are executing this routine.
 	 */
-	for (i = 0; reg = regulators[i], i < count; i++) {
+	for (i = 0; i < count; i++) {
+		reg = regulators[i];
 		ret = regulator_set_voltage_time(reg, uV[i].min, uV[i].max);
 		if (ret > 0)
 			latency_ns += ret * 1000;
-- 
GitLab


From 1d55abc0e98a0bf35f3af80665aac564e3b30572 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 22 Feb 2017 11:31:41 +0100
Subject: [PATCH 188/898] scsi: mpt3sas: switch to pci_alloc_irq_vectors

Cleanup the MSI-X handling allowing us to use the PCI-layer provided
vector allocation.

Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 105 +++++++++++++---------------
 drivers/scsi/mpt3sas/mpt3sas_base.h |   2 -
 2 files changed, 48 insertions(+), 59 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index a3fe1fb55c17..5b7aec5d575a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1148,7 +1148,7 @@ mpt3sas_base_sync_reply_irqs(struct MPT3SAS_ADAPTER *ioc)
 		/* TMs are on msix_index == 0 */
 		if (reply_q->msix_index == 0)
 			continue;
-		synchronize_irq(reply_q->vector);
+		synchronize_irq(pci_irq_vector(ioc->pdev, reply_q->msix_index));
 	}
 }
 
@@ -1837,11 +1837,8 @@ _base_free_irq(struct MPT3SAS_ADAPTER *ioc)
 
 	list_for_each_entry_safe(reply_q, next, &ioc->reply_queue_list, list) {
 		list_del(&reply_q->list);
-		if (smp_affinity_enable) {
-			irq_set_affinity_hint(reply_q->vector, NULL);
-			free_cpumask_var(reply_q->affinity_hint);
-		}
-		free_irq(reply_q->vector, reply_q);
+		free_irq(pci_irq_vector(ioc->pdev, reply_q->msix_index),
+			 reply_q);
 		kfree(reply_q);
 	}
 }
@@ -1850,13 +1847,13 @@ _base_free_irq(struct MPT3SAS_ADAPTER *ioc)
  * _base_request_irq - request irq
  * @ioc: per adapter object
  * @index: msix index into vector table
- * @vector: irq vector
  *
  * Inserting respective reply_queue into the list.
  */
 static int
-_base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index, u32 vector)
+_base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index)
 {
+	struct pci_dev *pdev = ioc->pdev;
 	struct adapter_reply_queue *reply_q;
 	int r;
 
@@ -1868,14 +1865,6 @@ _base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index, u32 vector)
 	}
 	reply_q->ioc = ioc;
 	reply_q->msix_index = index;
-	reply_q->vector = vector;
-
-	if (smp_affinity_enable) {
-		if (!zalloc_cpumask_var(&reply_q->affinity_hint, GFP_KERNEL)) {
-			kfree(reply_q);
-			return -ENOMEM;
-		}
-	}
 
 	atomic_set(&reply_q->busy, 0);
 	if (ioc->msix_enable)
@@ -1884,12 +1873,11 @@ _base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index, u32 vector)
 	else
 		snprintf(reply_q->name, MPT_NAME_LENGTH, "%s%d",
 		    ioc->driver_name, ioc->id);
-	r = request_irq(vector, _base_interrupt, IRQF_SHARED, reply_q->name,
-	    reply_q);
+	r = request_irq(pci_irq_vector(pdev, index), _base_interrupt,
+			IRQF_SHARED, reply_q->name, reply_q);
 	if (r) {
 		pr_err(MPT3SAS_FMT "unable to allocate interrupt %d!\n",
-		    reply_q->name, vector);
-		free_cpumask_var(reply_q->affinity_hint);
+		       reply_q->name, pci_irq_vector(pdev, index));
 		kfree(reply_q);
 		return -EBUSY;
 	}
@@ -1925,6 +1913,21 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
 	if (!nr_msix)
 		return;
 
+	if (smp_affinity_enable) {
+		list_for_each_entry(reply_q, &ioc->reply_queue_list, list) {
+			const cpumask_t *mask = pci_irq_get_affinity(ioc->pdev,
+							reply_q->msix_index);
+			if (!mask) {
+				pr_warn(MPT3SAS_FMT "no affinity for msi %x\n",
+					ioc->name, reply_q->msix_index);
+				continue;
+			}
+
+			for_each_cpu(cpu, mask)
+				ioc->cpu_msix_table[cpu] = reply_q->msix_index;
+		}
+		return;
+	}
 	cpu = cpumask_first(cpu_online_mask);
 
 	list_for_each_entry(reply_q, &ioc->reply_queue_list, list) {
@@ -1938,18 +1941,9 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
 			group++;
 
 		for (i = 0 ; i < group ; i++) {
-			ioc->cpu_msix_table[cpu] = index;
-			if (smp_affinity_enable)
-				cpumask_or(reply_q->affinity_hint,
-				   reply_q->affinity_hint, get_cpu_mask(cpu));
+			ioc->cpu_msix_table[cpu] = reply_q->msix_index;
 			cpu = cpumask_next(cpu, cpu_online_mask);
 		}
-		if (smp_affinity_enable)
-			if (irq_set_affinity_hint(reply_q->vector,
-					   reply_q->affinity_hint))
-				dinitprintk(ioc, pr_info(MPT3SAS_FMT
-				 "Err setting affinity hint to irq vector %d\n",
-				 ioc->name, reply_q->vector));
 		index++;
 	}
 }
@@ -1976,10 +1970,10 @@ _base_disable_msix(struct MPT3SAS_ADAPTER *ioc)
 static int
 _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 {
-	struct msix_entry *entries, *a;
 	int r;
 	int i, local_max_msix_vectors;
 	u8 try_msix = 0;
+	unsigned int irq_flags = PCI_IRQ_MSIX;
 
 	if (msix_disable == -1 || msix_disable == 0)
 		try_msix = 1;
@@ -1991,7 +1985,7 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 		goto try_ioapic;
 
 	ioc->reply_queue_count = min_t(int, ioc->cpu_count,
-	    ioc->msix_vector_count);
+		ioc->msix_vector_count);
 
 	printk(MPT3SAS_FMT "MSI-X vectors supported: %d, no of cores"
 	  ": %d, max_msix_vectors: %d\n", ioc->name, ioc->msix_vector_count,
@@ -2002,56 +1996,51 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 	else
 		local_max_msix_vectors = max_msix_vectors;
 
-	if (local_max_msix_vectors > 0) {
+	if (local_max_msix_vectors > 0)
 		ioc->reply_queue_count = min_t(int, local_max_msix_vectors,
 			ioc->reply_queue_count);
-		ioc->msix_vector_count = ioc->reply_queue_count;
-	} else if (local_max_msix_vectors == 0)
+	else if (local_max_msix_vectors == 0)
 		goto try_ioapic;
 
 	if (ioc->msix_vector_count < ioc->cpu_count)
 		smp_affinity_enable = 0;
 
-	entries = kcalloc(ioc->reply_queue_count, sizeof(struct msix_entry),
-	    GFP_KERNEL);
-	if (!entries) {
-		dfailprintk(ioc, pr_info(MPT3SAS_FMT
-			"kcalloc failed @ at %s:%d/%s() !!!\n",
-			ioc->name, __FILE__, __LINE__, __func__));
-		goto try_ioapic;
-	}
+	if (smp_affinity_enable)
+		irq_flags |= PCI_IRQ_AFFINITY;
 
-	for (i = 0, a = entries; i < ioc->reply_queue_count; i++, a++)
-		a->entry = i;
-
-	r = pci_enable_msix_exact(ioc->pdev, entries, ioc->reply_queue_count);
-	if (r) {
+	r = pci_alloc_irq_vectors(ioc->pdev, 1, ioc->reply_queue_count,
+				  irq_flags);
+	if (r < 0) {
 		dfailprintk(ioc, pr_info(MPT3SAS_FMT
-			"pci_enable_msix_exact failed (r=%d) !!!\n",
+			"pci_alloc_irq_vectors failed (r=%d) !!!\n",
 			ioc->name, r));
-		kfree(entries);
 		goto try_ioapic;
 	}
 
 	ioc->msix_enable = 1;
-	for (i = 0, a = entries; i < ioc->reply_queue_count; i++, a++) {
-		r = _base_request_irq(ioc, i, a->vector);
+	ioc->reply_queue_count = r;
+	for (i = 0; i < ioc->reply_queue_count; i++) {
+		r = _base_request_irq(ioc, i);
 		if (r) {
 			_base_free_irq(ioc);
 			_base_disable_msix(ioc);
-			kfree(entries);
 			goto try_ioapic;
 		}
 	}
 
-	kfree(entries);
 	return 0;
 
 /* failback to io_apic interrupt routing */
  try_ioapic:
 
 	ioc->reply_queue_count = 1;
-	r = _base_request_irq(ioc, 0, ioc->pdev->irq);
+	r = pci_alloc_irq_vectors(ioc->pdev, 1, 1, PCI_IRQ_LEGACY);
+	if (r < 0) {
+		dfailprintk(ioc, pr_info(MPT3SAS_FMT
+			"pci_alloc_irq_vector(legacy) failed (r=%d) !!!\n",
+			ioc->name, r));
+	} else
+		r = _base_request_irq(ioc, 0);
 
 	return r;
 }
@@ -2222,7 +2211,8 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 	list_for_each_entry(reply_q, &ioc->reply_queue_list, list)
 		pr_info(MPT3SAS_FMT "%s: IRQ %d\n",
 		    reply_q->name,  ((ioc->msix_enable) ? "PCI-MSI-X enabled" :
-		    "IO-APIC enabled"), reply_q->vector);
+		    "IO-APIC enabled"),
+		    pci_irq_vector(ioc->pdev, reply_q->msix_index));
 
 	pr_info(MPT3SAS_FMT "iomem(0x%016llx), mapped(0x%p), size(%d)\n",
 	    ioc->name, (unsigned long long)chip_phys, ioc->chip, memap_sz);
@@ -5357,7 +5347,8 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		    sizeof(resource_size_t *), GFP_KERNEL);
 		if (!ioc->reply_post_host_index) {
 			dfailprintk(ioc, pr_info(MPT3SAS_FMT "allocation "
-				"for cpu_msix_table failed!!!\n", ioc->name));
+				"for reply_post_host_index failed!!!\n",
+				ioc->name));
 			r = -ENOMEM;
 			goto out_free_resources;
 		}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 4ab634fc27df..7fe7e6ed595b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -731,12 +731,10 @@ struct _event_ack_list {
 struct adapter_reply_queue {
 	struct MPT3SAS_ADAPTER	*ioc;
 	u8			msix_index;
-	unsigned int		vector;
 	u32			reply_post_host_index;
 	Mpi2ReplyDescriptorsUnion_t *reply_post_free;
 	char			name[MPT_NAME_LENGTH];
 	atomic_t		busy;
-	cpumask_var_t		affinity_hint;
 	struct list_head	list;
 };
 
-- 
GitLab


From 17b4eaf475684bd12aeecf358a7ea6e3bec871a5 Mon Sep 17 00:00:00 2001
From: Tang Yuantian <Yuantian.Tang@nxp.com>
Date: Tue, 21 Feb 2017 14:51:24 +0800
Subject: [PATCH 189/898] cpufreq: qoriq: clean up unused code

This snip code is not needed anymore since its user
get_hard_smp_processor_id() has been removed.

Signed-off-by: Tang Yuantian <yuantian.tang@nxp.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/qoriq-cpufreq.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index a6fefac8afe4..bfec1bcd3835 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -23,10 +23,6 @@
 #include <linux/slab.h>
 #include <linux/smp.h>
 
-#if !defined(CONFIG_ARM)
-#include <asm/smp.h>	/* for get_hard_smp_processor_id() in UP configs */
-#endif
-
 /**
  * struct cpu_data
  * @pclk: the parent clock of cpu
-- 
GitLab


From a56e574067c20d01d8fc74863fa187dd66da7b94 Mon Sep 17 00:00:00 2001
From: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Date: Wed, 22 Feb 2017 07:23:13 -0800
Subject: [PATCH 190/898] scsi: aacraid: Fixed expander hotplug for SMART
 family

Current driver Hotplug processing code skips over Enclosure channel,
therefore any addition/removal of expander enclosure is not processed.
Additionally device addition code relies on older device type, which
prevents the hotplug of adapter expanders.

Fixed by removing code that skips over Enclosure channels and using the
latest device type for addition or removal or enclosure expanders.

Fixes: 6223a39fe6fbbeef (scsi: aacraid: Added support for hotplug)
Signed-off-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: Dave Carroll <david.carroll@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index a2ea70d8a13a..1994c7445b54 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1908,9 +1908,6 @@ static void aac_resolve_luns(struct aac_dev *dev)
 	for (bus = 0; bus < AAC_MAX_BUSES; bus++) {
 		for (target = 0; target < AAC_MAX_TARGETS; target++) {
 
-			if (aac_phys_to_logical(bus) == ENCLOSURE_CHANNEL)
-				continue;
-
 			if (bus == CONTAINER_CHANNEL)
 				channel = CONTAINER_CHANNEL;
 			else
@@ -1922,7 +1919,7 @@ static void aac_resolve_luns(struct aac_dev *dev)
 			sdev = scsi_device_lookup(dev->scsi_host_ptr, channel,
 					target, 0);
 
-			if (!sdev && devtype)
+			if (!sdev && new_devtype)
 				scsi_add_device(dev->scsi_host_ptr, channel,
 						target, 0);
 			else if (sdev && new_devtype != devtype)
-- 
GitLab


From 35bfa99e81f45079728f6b2ac553dabb0bc62c7d Mon Sep 17 00:00:00 2001
From: Christophe Jaillet <christophe.jaillet@wanadoo.fr>
Date: Tue, 21 Feb 2017 21:41:53 +0100
Subject: [PATCH 191/898] PM / runtime: Fix some typos

Signed-off-by: Christophe Jaillet <christophe.jaillet@wanadoo.fr>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/runtime_pm.txt | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 4870980e967e..64546eb9a16a 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -100,7 +100,7 @@ knows what to do to handle the device).
   * If the suspend callback returns an error code different from -EBUSY and
     -EAGAIN, the PM core regards this as a fatal error and will refuse to run
     the helper functions described in Section 4 for the device until its status
-    is directly set to  either'active', or 'suspended' (the PM core provides
+    is directly set to  either 'active', or 'suspended' (the PM core provides
     special helper functions for this purpose).
 
 In particular, if the driver requires remote wakeup capability (i.e. hardware
@@ -217,7 +217,7 @@ defined in include/linux/pm.h:
       one to complete
 
   spinlock_t lock;
-    - lock used for synchronisation
+    - lock used for synchronization
 
   atomic_t usage_count;
     - the usage counter of the device
@@ -565,7 +565,7 @@ appropriate to ensure that the device is not put back to sleep during the
 probe. This can happen with systems such as the network device layer.
 
 It may be desirable to suspend the device once ->probe() has finished.
-Therefore the driver core uses the asyncronous pm_request_idle() to submit a
+Therefore the driver core uses the asynchronous pm_request_idle() to submit a
 request to execute the subsystem-level idle callback for the device at that
 time.  A driver that makes use of the runtime autosuspend feature, may want to
 update the last busy mark before returning from ->probe().
-- 
GitLab


From d08d1b27fe2a7f6923952613f5fab56ae47a6f5b Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 22 Feb 2017 13:58:52 +0530
Subject: [PATCH 192/898] PM / QoS: Remove global notifiers

They were never used in the kernel, so get rid of them.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/pm_qos_interface.txt | 13 +-----
 drivers/base/power/qos.c                 | 50 ++----------------------
 include/linux/pm_qos.h                   |  8 ----
 3 files changed, 5 insertions(+), 66 deletions(-)

diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index 129f7c0e1483..21d2d48f87a2 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -163,8 +163,7 @@ of flags and remove sysfs attributes pm_qos_no_power_off and pm_qos_remote_wakeu
 under the device's power directory.
 
 Notification mechanisms:
-The per-device PM QoS framework has 2 different and distinct notification trees:
-a per-device notification tree and a global notification tree.
+The per-device PM QoS framework has a per-device notification tree.
 
 int dev_pm_qos_add_notifier(device, notifier):
 Adds a notification callback function for the device.
@@ -174,16 +173,6 @@ is changed (for resume latency device PM QoS only).
 int dev_pm_qos_remove_notifier(device, notifier):
 Removes the notification callback function for the device.
 
-int dev_pm_qos_add_global_notifier(notifier):
-Adds a notification callback function in the global notification tree of the
-framework.
-The callback is called when the aggregated value for any device is changed
-(for resume latency device PM QoS only).
-
-int dev_pm_qos_remove_global_notifier(notifier):
-Removes the notification callback function from the global notification tree
-of the framework.
-
 
 Active state latency tolerance
 
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index d888d9869b6a..271bec73185e 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -17,12 +17,9 @@
  *
  * This QoS design is best effort based. Dependents register their QoS needs.
  * Watchers register to keep track of the current QoS needs of the system.
- * Watchers can register different types of notification callbacks:
- *  . a per-device notification callback using the dev_pm_qos_*_notifier API.
- *    The notification chain data is stored in the per-device constraint
- *    data struct.
- *  . a system-wide notification callback using the dev_pm_qos_*_global_notifier
- *    API. The notification chain data is stored in a static variable.
+ * Watchers can register a per-device notification callback using the
+ * dev_pm_qos_*_notifier API. The notification chain data is stored in the
+ * per-device constraint data struct.
  *
  * Note about the per-device constraint data struct allocation:
  * . The per-device constraints data struct ptr is tored into the device
@@ -49,8 +46,6 @@
 static DEFINE_MUTEX(dev_pm_qos_mtx);
 static DEFINE_MUTEX(dev_pm_qos_sysfs_mtx);
 
-static BLOCKING_NOTIFIER_HEAD(dev_pm_notifiers);
-
 /**
  * __dev_pm_qos_flags - Check PM QoS flags for a given device.
  * @dev: Device to check the PM QoS flags for.
@@ -135,8 +130,7 @@ s32 dev_pm_qos_read_value(struct device *dev)
  * @value: Value to assign to the QoS request.
  *
  * Internal function to update the constraints list using the PM QoS core
- * code and if needed call the per-device and the global notification
- * callbacks
+ * code and if needed call the per-device callbacks.
  */
 static int apply_constraint(struct dev_pm_qos_request *req,
 			    enum pm_qos_req_action action, s32 value)
@@ -148,12 +142,6 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 	case DEV_PM_QOS_RESUME_LATENCY:
 		ret = pm_qos_update_target(&qos->resume_latency,
 					   &req->data.pnode, action, value);
-		if (ret) {
-			value = pm_qos_read_value(&qos->resume_latency);
-			blocking_notifier_call_chain(&dev_pm_notifiers,
-						     (unsigned long)value,
-						     req);
-		}
 		break;
 	case DEV_PM_QOS_LATENCY_TOLERANCE:
 		ret = pm_qos_update_target(&qos->latency_tolerance,
@@ -535,36 +523,6 @@ int dev_pm_qos_remove_notifier(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier);
 
-/**
- * dev_pm_qos_add_global_notifier - sets notification entry for changes to
- * target value of the PM QoS constraints for any device
- *
- * @notifier: notifier block managed by caller.
- *
- * Will register the notifier into a notification chain that gets called
- * upon changes to the target value for any device.
- */
-int dev_pm_qos_add_global_notifier(struct notifier_block *notifier)
-{
-	return blocking_notifier_chain_register(&dev_pm_notifiers, notifier);
-}
-EXPORT_SYMBOL_GPL(dev_pm_qos_add_global_notifier);
-
-/**
- * dev_pm_qos_remove_global_notifier - deletes notification for changes to
- * target value of PM QoS constraints for any device
- *
- * @notifier: notifier block to be removed.
- *
- * Will remove the notifier from the notification chain that gets called
- * upon changes to the target value for any device.
- */
-int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier)
-{
-	return blocking_notifier_chain_unregister(&dev_pm_notifiers, notifier);
-}
-EXPORT_SYMBOL_GPL(dev_pm_qos_remove_global_notifier);
-
 /**
  * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor.
  * @dev: Device whose ancestor to add the request for.
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index d4d34791e463..3e2547d6e207 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -146,8 +146,6 @@ int dev_pm_qos_add_notifier(struct device *dev,
 			    struct notifier_block *notifier);
 int dev_pm_qos_remove_notifier(struct device *dev,
 			       struct notifier_block *notifier);
-int dev_pm_qos_add_global_notifier(struct notifier_block *notifier);
-int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier);
 void dev_pm_qos_constraints_init(struct device *dev);
 void dev_pm_qos_constraints_destroy(struct device *dev);
 int dev_pm_qos_add_ancestor_request(struct device *dev,
@@ -199,12 +197,6 @@ static inline int dev_pm_qos_add_notifier(struct device *dev,
 static inline int dev_pm_qos_remove_notifier(struct device *dev,
 					     struct notifier_block *notifier)
 			{ return 0; }
-static inline int dev_pm_qos_add_global_notifier(
-					struct notifier_block *notifier)
-			{ return 0; }
-static inline int dev_pm_qos_remove_global_notifier(
-					struct notifier_block *notifier)
-			{ return 0; }
 static inline void dev_pm_qos_constraints_init(struct device *dev)
 {
 	dev->power.power_state = PMSG_ON;
-- 
GitLab


From 669a311b6ecc4eeb367a269bdd5f4e143caddb9c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 23 Feb 2017 10:57:23 +0000
Subject: [PATCH 193/898] scsi: qla2xxx: fix spelling mistake: "seperator" ->
 "separator"

Trivial fix to spelling mistake in pr_err message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/tcm_qla2xxx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 3084983c1287..fbbe5abd6ddb 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1738,7 +1738,7 @@ static struct se_wwn *tcm_qla2xxx_npiv_make_lport(
 
 	p = strchr(tmp, '@');
 	if (!p) {
-		pr_err("Unable to locate NPIV '@' seperator\n");
+		pr_err("Unable to locate NPIV '@' separator\n");
 		return ERR_PTR(-EINVAL);
 	}
 	*p++ = '\0';
-- 
GitLab


From ebe73647fb3895b75544cecdb6766a517fbf03d6 Mon Sep 17 00:00:00 2001
From: Don Brace <don.brace@microsemi.com>
Date: Thu, 23 Feb 2017 08:57:20 -0600
Subject: [PATCH 194/898] scsi: cciss: correct check map error.

Remove device driver failed to check map error messages

Reported-by: Johnny Bieren <jbieren@redhat.com>
Tested-by: Johnny Bieren <jbieren@redhat.com>
Reviewed-by: Scott Teel <scott.teel@microsemi.com>
Signed-off-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/block/cciss.c | 32 ++++++++++++++++++++++++++++----
 1 file changed, 28 insertions(+), 4 deletions(-)

diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 27d613795653..8e1a4554951c 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -348,7 +348,7 @@ static void cciss_unmap_sg_chain_block(ctlr_info_t *h, CommandList_struct *c)
 	pci_unmap_single(h->pdev, temp64.val, chain_sg->Len, PCI_DMA_TODEVICE);
 }
 
-static void cciss_map_sg_chain_block(ctlr_info_t *h, CommandList_struct *c,
+static int cciss_map_sg_chain_block(ctlr_info_t *h, CommandList_struct *c,
 	SGDescriptor_struct *chain_block, int len)
 {
 	SGDescriptor_struct *chain_sg;
@@ -359,8 +359,16 @@ static void cciss_map_sg_chain_block(ctlr_info_t *h, CommandList_struct *c,
 	chain_sg->Len = len;
 	temp64.val = pci_map_single(h->pdev, chain_block, len,
 				PCI_DMA_TODEVICE);
+	if (dma_mapping_error(&h->pdev->dev, temp64.val)) {
+		dev_warn(&h->pdev->dev,
+			"%s: error mapping chain block for DMA\n",
+			__func__);
+		return -1;
+	}
 	chain_sg->Addr.lower = temp64.val32.lower;
 	chain_sg->Addr.upper = temp64.val32.upper;
+
+	return 0;
 }
 
 #include "cciss_scsi.c"		/* For SCSI tape support */
@@ -3369,15 +3377,31 @@ static void do_cciss_request(struct request_queue *q)
 		temp64.val = (__u64) pci_map_page(h->pdev, sg_page(&tmp_sg[i]),
 						tmp_sg[i].offset,
 						tmp_sg[i].length, dir);
+		if (dma_mapping_error(&h->pdev->dev, temp64.val)) {
+			dev_warn(&h->pdev->dev,
+				"%s: error mapping page for DMA\n", __func__);
+			creq->errors = make_status_bytes(SAM_STAT_GOOD,
+							0, DRIVER_OK,
+							DID_SOFT_ERROR);
+			cmd_free(h, c);
+			return;
+		}
 		curr_sg[sg_index].Addr.lower = temp64.val32.lower;
 		curr_sg[sg_index].Addr.upper = temp64.val32.upper;
 		curr_sg[sg_index].Ext = 0;  /* we are not chaining */
 		++sg_index;
 	}
-	if (chained)
-		cciss_map_sg_chain_block(h, c, h->cmd_sg_list[c->cmdindex],
+	if (chained) {
+		if (cciss_map_sg_chain_block(h, c, h->cmd_sg_list[c->cmdindex],
 			(seg - (h->max_cmd_sgentries - 1)) *
-				sizeof(SGDescriptor_struct));
+				sizeof(SGDescriptor_struct))) {
+			creq->errors = make_status_bytes(SAM_STAT_GOOD,
+							0, DRIVER_OK,
+							DID_SOFT_ERROR);
+			cmd_free(h, c);
+			return;
+		}
+	}
 
 	/* track how many SG entries we are using */
 	if (seg > h->maxSG)
-- 
GitLab


From 2559a1ef688f933835912c731bed2254146a9b04 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Feb 2017 09:08:02 +1100
Subject: [PATCH 195/898] scsi: mac_scsi: Fix MAC_SCSI=m option when SCSI=m

The mac_scsi driver still gets disabled when SCSI=m. This should have
been fixed back when I enabled the tristate but I didn't see the bug.

Fixes: 6e9ae6d560e1 ("[PATCH] mac_scsi: Add module option to Kconfig")
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 8aa9bd34123e..230043c1c90f 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1480,7 +1480,7 @@ config ATARI_SCSI
 
 config MAC_SCSI
 	tristate "Macintosh NCR5380 SCSI"
-	depends on MAC && SCSI=y
+	depends on MAC && SCSI
 	select SCSI_SPI_ATTRS
 	help
 	  This is the NCR 5380 SCSI controller included on most of the 68030
-- 
GitLab


From 4dd9920d991745c4a16f53a8f615f706fbe4b3f7 Mon Sep 17 00:00:00 2001
From: Robbie Ko <robbieko@synology.com>
Date: Thu, 5 Jan 2017 16:24:55 +0800
Subject: [PATCH 196/898] Btrfs: send, fix failure to rename top level inode
 due to name collision

Under certain situations, an incremental send operation can fail due to a
premature attempt to create a new top level inode (a direct child of the
subvolume/snapshot root) whose name collides with another inode that was
removed from the send snapshot.

Consider the following example scenario.

Parent snapshot:

  .                 (ino 256, gen 8)
  |---- a1/         (ino 257, gen 9)
  |---- a2/         (ino 258, gen 9)

Send snapshot:

  .                 (ino 256, gen 3)
  |---- a2/         (ino 257, gen 7)

In this scenario, when receiving the incremental send stream, the btrfs
receive command fails like this (ran in verbose mode, -vv argument):

  rmdir a1
  mkfile o257-7-0
  rename o257-7-0 -> a2
  ERROR: rename o257-7-0 -> a2 failed: Is a directory

What happens when computing the incremental send stream is:

1) An operation to remove the directory with inode number 257 and
   generation 9 is issued.

2) An operation to create the inode with number 257 and generation 7 is
   issued. This creates the inode with an orphanized name of "o257-7-0".

3) An operation rename the new inode 257 to its final name, "a2", is
   issued. This is incorrect because inode 258, which has the same name
   and it's a child of the same parent (root inode 256), was not yet
   processed and therefore no rmdir operation for it was yet issued.
   The rename operation is issued because we fail to detect that the
   name of the new inode 257 collides with inode 258, because their
   parent, a subvolume/snapshot root (inode 256) has a different
   generation in both snapshots.

So fix this by ignoring the generation value of a parent directory that
matches a root inode (number 256) when we are checking if the name of the
inode currently being processed collides with the name of some other
inode that was not yet processed.

We can achieve this scenario of different inodes with the same number but
different generation values either by mounting a filesystem with the inode
cache option (-o inode_cache) or by creating and sending snapshots across
different filesystems, like in the following example:

  $ mkfs.btrfs -f /dev/sdb
  $ mount /dev/sdb /mnt
  $ mkdir /mnt/a1
  $ mkdir /mnt/a2
  $ btrfs subvolume snapshot -r /mnt /mnt/snap1
  $ btrfs send /mnt/snap1 -f /tmp/1.snap
  $ umount /mnt

  $ mkfs.btrfs -f /dev/sdc
  $ mount /dev/sdc /mnt
  $ touch /mnt/a2
  $ btrfs subvolume snapshot -r /mnt /mnt/snap2
  $ btrfs receive /mnt -f /tmp/1.snap
  # Take note that once the filesystem is created, its current
  # generation has value 7 so the inode from the second snapshot has
  # a generation value of 7. And after receiving the first snapshot
  # the filesystem is at a generation value of 10, because the call to
  # create the second snapshot bumps the generation to 8 (the snapshot
  # creation ioctl does a transaction commit), the receive command calls
  # the snapshot creation ioctl to create the first snapshot, which bumps
  # the filesystem's generation to 9, and finally when the receive
  # operation finishes it calls an ioctl to transition the first snapshot
  # (snap1) from RW mode to RO mode, which does another transaction commit
  # and bumps the filesystem's generation to 10.
  $ rm -f /tmp/1.snap
  $ btrfs send /mnt/snap1 -f /tmp/1.snap
  $ btrfs send -p /mnt/snap1 /mnt/snap2 -f /tmp/2.snap
  $ umount /mnt

  $ mkfs.btrfs -f /dev/sdd
  $ mount /dev/sdd /mnt
  $ btrfs receive /mnt /tmp/1.snap
  # Receive of snapshot snap2 used to fail.
  $ btrfs receive /mnt /tmp/2.snap

Signed-off-by: Robbie Ko <robbieko@synology.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
[Rewrote changelog to be more precise and clear]
Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/send.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index d145ce804620..2ae32c4f7dd7 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1681,6 +1681,9 @@ static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen)
 {
 	int ret;
 
+	if (ino == BTRFS_FIRST_FREE_OBJECTID)
+		return 1;
+
 	ret = get_cur_inode_state(sctx, ino, gen);
 	if (ret < 0)
 		goto out;
@@ -1866,7 +1869,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	 * not deleted and then re-created, if it was then we have no overwrite
 	 * and we can just unlink this entry.
 	 */
-	if (sctx->parent_root) {
+	if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) {
 		ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL,
 				     NULL, NULL, NULL);
 		if (ret < 0 && ret != -ENOENT)
-- 
GitLab


From fe9c798dbf4c78322549068255f611e4038a5b28 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 11 Jan 2017 02:15:39 +0000
Subject: [PATCH 197/898] Btrfs: incremental send, do not delay rename when
 parent inode is new

When we are checking if we need to delay the rename operation for an
inode we not checking if a parent inode that exists in the send and
parent snapshots is really the same inode or not, that is, we are not
comparing the generation number of the parent inode in the send and
parent snapshots. Not only this results in unnecessarily delaying a
rename operation but also can later on make us generate an incorrect
name for a new inode in the send snapshot that has the same number
as another inode in the parent snapshot but a different generation.

Here follows an example where this happens.

Parent snapshot:

 .                                                  (ino 256, gen 3)
 |--- dir258/                                       (ino 258, gen 7)
 |       |--- dir257/                               (ino 257, gen 7)
 |
 |--- dir259/                                       (ino 259, gen 7)

Send snapshot:

 .                                                  (ino 256, gen 3)
 |--- file258                                       (ino 258, gen 10)
 |
 |--- new_dir259/                                   (ino 259, gen 10)
          |--- dir257/                              (ino 257, gen 7)

The following steps happen when computing the incremental send stream:

1) When processing inode 257, its new parent is created using its orphan
   name (o257-21-0), and the rename operation for inode 257 is delayed
   because its new parent (inode 259) was not yet processed - this
   decision to delay the rename operation does not make much sense
   because the inode 259 in the send snapshot is a new inode, it's not
   the same as inode 259 in the parent snapshot.

2) When processing inode 258 we end up delaying its rmdir operation,
   because inode 257 was not yet renamed (moved away from the directory
   inode 258 represents). We also create the new inode 258 using its
   orphan name "o258-10-0", then rename it to its final name of "file258"
   and then issue a truncate operation for it. However this truncate
   operation contains an incorrect name, which corresponds to the orphan
   name and not to the final name, which makes the receiver fail. This
   happens because when we attempt to compute the inode's current name
   we verify that there's another inode with the same number (258) that
   has its rmdir operation pending and because of that we generate an
   orphan name for the new inode 258 (we do this in the function
   get_cur_path()).

Fix this by not delayed the rename operation of an inode if it has parents
with the same number but different generations in both snapshots.

The following steps reproduce this example scenario.

 $ mkfs.btrfs -f /dev/sdb
 $ mount /dev/sdb /mnt
 $ mkdir /mnt/dir257
 $ mkdir /mnt/dir258
 $ mkdir /mnt/dir259
 $ mv /mnt/dir257 /mnt/dir258/dir257
 $ btrfs subvolume snapshot -r /mnt /mnt/snap1

 $ mv /mnt/dir258/dir257 /mnt/dir257
 $ rmdir /mnt/dir258
 $ rmdir /mnt/dir259

 # Remount the filesystem so that the next created inodes will have the
 # numbers 258 and 259. This is because when a filesystem is mounted,
 # btrfs sets the subvolume's inode counter to a value corresponding to
 # the highest inode number in the subvolume plus 1. This inode counter
 # is used to assign a unique number to each new inode and it's
 # incremented by 1 after very inode creation.
 # Note: we unmount and then mount instead of doing a mount with
 # "-o remount" because otherwise the inode counter remains at value 260.
 $ umount /mnt
 $ mount /dev/sdb /mnt
 $ touch /mnt/file258
 $ mkdir /mnt/new_dir259
 $ mv /mnt/dir257 /mnt/new_dir259/dir257
 $ btrfs subvolume snapshot -r /mnt /mnt/snap2

 $ btrfs send /mnt/snap1 -f /tmp/1.snap
 $ btrfs send -p /mnt/snap1 /mnt/snap2 -f /tmp/2.snap

 $ umount /mnt
 $ mkfs.btrfs -f /dev/sdc
 $ mount /dev/sdc /mnt
 $ btrfs receive /mnt -f /tmo/1.snap
 $ btrfs receive /mnt -f /tmo/2.snap -vv
 receiving snapshot mysnap2 uuid=e059b6d1-7f55-f140-8d7c-9a3039d23c97, ctransid=10 parent_uuid=77e98cb6-8762-814f-9e05-e8ba877fc0b0, parent_ctransid=7
 utimes
 mkdir o259-10-0
 rename dir258 -> o258-7-0
 utimes
 mkfile o258-10-0
 rename o258-10-0 -> file258
 utimes
 truncate o258-10-0 size=0
 ERROR: truncate o258-10-0 failed: No such file or directory

Reported-by: Robbie Ko <robbieko@synology.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/send.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 2ae32c4f7dd7..2742324514e4 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3559,6 +3559,7 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 {
 	int ret = 0;
 	u64 ino = parent_ref->dir;
+	u64 ino_gen = parent_ref->dir_gen;
 	u64 parent_ino_before, parent_ino_after;
 	struct fs_path *path_before = NULL;
 	struct fs_path *path_after = NULL;
@@ -3579,6 +3580,8 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 	 * at get_cur_path()).
 	 */
 	while (ino > BTRFS_FIRST_FREE_OBJECTID) {
+		u64 parent_ino_after_gen;
+
 		if (is_waiting_for_move(sctx, ino)) {
 			/*
 			 * If the current inode is an ancestor of ino in the
@@ -3601,7 +3604,7 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 		fs_path_reset(path_after);
 
 		ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
-				    NULL, path_after);
+				    &parent_ino_after_gen, path_after);
 		if (ret < 0)
 			goto out;
 		ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before,
@@ -3618,10 +3621,20 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 		if (ino > sctx->cur_ino &&
 		    (parent_ino_before != parent_ino_after || len1 != len2 ||
 		     memcmp(path_before->start, path_after->start, len1))) {
-			ret = 1;
-			break;
+			u64 parent_ino_gen;
+
+			ret = get_inode_info(sctx->parent_root, ino, NULL,
+					     &parent_ino_gen, NULL, NULL, NULL,
+					     NULL);
+			if (ret < 0)
+				goto out;
+			if (ino_gen == parent_ino_gen) {
+				ret = 1;
+				break;
+			}
 		}
 		ino = parent_ino_after;
+		ino_gen = parent_ino_after_gen;
 	}
 
 out:
-- 
GitLab


From 0191410158840d6176de3267daa4604ad6a773fb Mon Sep 17 00:00:00 2001
From: Robbie Ko <robbieko@synology.com>
Date: Thu, 5 Jan 2017 16:24:58 +0800
Subject: [PATCH 198/898] Btrfs: incremental send, do not issue invalid rmdir
 operations

When both the parent and send snapshots have a directory inode with the
same number but different generations (therefore they are different
inodes) and both have an entry with the same name, an incremental send
stream will contain an invalid rmdir operation that refers to the
orphanized name of the inode from the parent snapshot.

The following example scenario shows how this happens.

Parent snapshot:

 .
 |---- d259_old/               (ino 259, gen 9)
 |         |---- d1/           (ino 258, gen 9)
 |
 |---- f                       (ino 257, gen 9)

Send snapshot:

 .
 |---- d258/                   (ino 258, gen 7)
 |---- d259/                   (ino 259, gen 7)
         |---- d1/             (ino 257, gen 7)

When the kernel is processing inode 258 it notices that in both snapshots
there is an inode numbered 259 that is a parent of an inode 258. However
it ignores the fact that the inodes numbered 259 have different generations
in both snapshots, which means they are effectively different inodes.
Then it checks that both inodes 259 have a dentry named "d1" and because
of that it issues a rmdir operation with orphanized name of the inode 258
from the parent snapshot. This happens at send.c:process_record_refs(),
which calls send.c:did_overwrite_first_ref() that returns true and because
of that later on at process_recorded_refs() such rmdir operation is issued
because the inode being currently processed (258) is a directory and it
was deleted in the send snapshot (and replaced with another inode that has
the same number and is a directory too).
Fix this issue by comparing the generations of parent directory inodes
that have the same number and make send.c:did_overwrite_first_ref() when
the generations are different.

The following steps reproduce the problem.

 $ mkfs.btrfs -f /dev/sdb
 $ mount /dev/sdb /mnt
 $ touch /mnt/f
 $ mkdir /mnt/d1
 $ mkdir /mnt/d259_old
 $ mv /mnt/d1 /mnt/d259_old/d1
 $ btrfs subvolume snapshot -r /mnt /mnt/snap1
 $ btrfs send /mnt/snap1 -f /tmp/1.snap
 $ umount /mnt

 $ mkfs.btrfs -f /dev/sdc
 $ mount /dev/sdc /mnt
 $ mkdir /mnt/d1
 $ mkdir /mnt/dir258
 $ mkdir /mnt/dir259
 $ mv /mnt/d1 /mnt/dir259/d1
 $ btrfs subvolume snapshot -r /mnt /mnt/snap2
 $ btrfs receive /mnt/ -f /tmp/1.snap
 # Take note that once the filesystem is created, its current
 # generation has value 7 so the inodes from the second snapshot all have
 # a generation value of 7. And after receiving the first snapshot
 # the filesystem is at a generation value of 10, because the call to
 # create the second snapshot bumps the generation to 8 (the snapshot
 # creation ioctl does a transaction commit), the receive command calls
 # the snapshot creation ioctl to create the first snapshot, which bumps
 # the filesystem's generation to 9, and finally when the receive
 # operation finishes it calls an ioctl to transition the first snapshot
 # (snap1) from RW mode to RO mode, which does another transaction commit
 # and bumps the filesystem's generation to 10. This means all the inodes
 # in the first snapshot (snap1) have a generation value of 9.
 $ rm -f /tmp/1.snap
 $ btrfs send /mnt/snap1 -f /tmp/1.snap
 $ btrfs send -p /mnt/snap1 /mnt/snap2 -f /tmp/2.snap
 $ umount /mnt

 $ mkfs.btrfs -f /dev/sdd
 $ mount /dev/sdd /mnt
 $ btrfs receive /mnt -f /tmp/1.snap
 $ btrfs receive -vv /mnt -f /tmp/2.snap
 receiving snapshot mysnap2 uuid=9c03962f-f620-0047-9f98-32e5a87116d9, ctransid=7 parent_uuid=d17a6e3f-14e5-df4f-be39-a7951a5399aa, parent_ctransid=9
 utimes
 unlink f
 mkdir o257-7-0
 mkdir o259-7-0
 rename o257-7-0 -> o259-7-0/d1
 chown o259-7-0/d1 - uid=0, gid=0
 chmod o259-7-0/d1 - mode=0755
 utimes o259-7-0/d1
 rmdir o258-9-0
 ERROR: rmdir o258-9-0 failed: No such file or directory

Signed-off-by: Robbie Ko <robbieko@synology.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
[Rewrote changelog to be more precise and clear]
Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/send.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 2742324514e4..712922ea64d2 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1937,6 +1937,19 @@ static int did_overwrite_ref(struct send_ctx *sctx,
 	if (ret <= 0)
 		goto out;
 
+	if (dir != BTRFS_FIRST_FREE_OBJECTID) {
+		ret = get_inode_info(sctx->send_root, dir, NULL, &gen, NULL,
+				     NULL, NULL, NULL);
+		if (ret < 0 && ret != -ENOENT)
+			goto out;
+		if (ret) {
+			ret = 0;
+			goto out;
+		}
+		if (gen != dir_gen)
+			goto out;
+	}
+
 	/* check if the ref was overwritten by another ref */
 	ret = lookup_dir_item_inode(sctx->send_root, dir, name, name_len,
 			&ow_inode, &other_type);
-- 
GitLab


From 6f546216e9f9e95d6783547ce6113eb13e2daa54 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 28 Jan 2017 01:47:56 +0000
Subject: [PATCH 199/898] Btrfs: bulk delete checksum items in the same leaf

Very often we have the checksums for an extent spread in multiple items
in the checksums tree, and currently the algorithm to delete them starts
by looking for them one by one and then deleting them one by one, which
is not optimal since each deletion involves shifting all the other items
in the leaf and when the leaf reaches some low threshold, to move items
off the leaf into its left and right neighbor leafs. Also, after each
item deletion we release our search path and start a new search for other
checksums items.

So optimize this by deleting in bulk all the items in the same leaf that
contain checksums for the extent being freed.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
---
 fs/btrfs/file-item.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index f7b9a92ad56d..e35df48b4383 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -643,7 +643,33 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 
 		/* delete the entire item, it is inside our range */
 		if (key.offset >= bytenr && csum_end <= end_byte) {
-			ret = btrfs_del_item(trans, root, path);
+			int del_nr = 1;
+
+			/*
+			 * Check how many csum items preceding this one in this
+			 * leaf correspond to our range and then delete them all
+			 * at once.
+			 */
+			if (key.offset > bytenr && path->slots[0] > 0) {
+				int slot = path->slots[0] - 1;
+
+				while (slot >= 0) {
+					struct btrfs_key pk;
+
+					btrfs_item_key_to_cpu(leaf, &pk, slot);
+					if (pk.offset < bytenr ||
+					    pk.type != BTRFS_EXTENT_CSUM_KEY ||
+					    pk.objectid !=
+					    BTRFS_EXTENT_CSUM_OBJECTID)
+						break;
+					path->slots[0] = slot;
+					del_nr++;
+					key.offset = pk.offset;
+					slot--;
+				}
+			}
+			ret = btrfs_del_items(trans, root, path,
+					      path->slots[0], del_nr);
 			if (ret)
 				goto out;
 			if (key.offset == bytenr)
-- 
GitLab


From 91e1f56a8b3c94cb5ac9ce12b806134dc33c1eeb Mon Sep 17 00:00:00 2001
From: Robbie Ko <robbieko@synology.com>
Date: Fri, 7 Oct 2016 10:01:29 +0800
Subject: [PATCH 200/898] Btrfs: fix leak of subvolume writers counter

When falling back from a nocow write to a regular cow write, we were
leaking the subvolume writers counter in 2 situations, preventing
snapshot creation from ever completing in the future, as it waits
for that counter to go down to zero before the snapshot creation
starts.

Signed-off-by: Robbie Ko <robbieko@synology.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
[Improved changelog and subject]
Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/inode.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c38391e948d9..4efe9d82944c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1331,10 +1331,16 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 			 * either valid or do not exist.
 			 */
 			if (csum_exist_in_range(fs_info, disk_bytenr,
-						num_bytes))
+						num_bytes)) {
+				if (!nolock)
+					btrfs_end_write_no_snapshoting(root);
 				goto out_check;
-			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
+			}
+			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) {
+				if (!nolock)
+					btrfs_end_write_no_snapshoting(root);
 				goto out_check;
+			}
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
-- 
GitLab


From 3168021cf9b4906f7bd9871770235f14c5a17715 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 1 Feb 2017 14:58:02 +0000
Subject: [PATCH 201/898] Btrfs: do not create explicit holes when replaying
 log tree if NO_HOLES enabled

We log holes explicitly by using file extent items, however when replaying
a log tree, if a logged file extent item corresponds to a hole and the
NO_HOLES feature is enabled we do not need to copy the file extent item
into the fs/subvolume tree, as the absence of such file extent items is
the purpose of the NO_HOLES feature. So skip the copying of file extent
items representing holes when the NO_HOLES feature is enabled.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/tree-log.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 3806853cde08..3cc972330ab3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -673,6 +673,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		unsigned long dest_offset;
 		struct btrfs_key ins;
 
+		if (btrfs_file_extent_disk_bytenr(eb, item) == 0 &&
+		    btrfs_fs_incompat(fs_info, NO_HOLES))
+			goto update_inode;
+
 		ret = btrfs_insert_empty_item(trans, root, path, key,
 					      sizeof(*item));
 		if (ret)
@@ -825,6 +829,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	}
 
 	inode_add_bytes(inode, nbytes);
+update_inode:
 	ret = btrfs_update_inode(trans, root, inode);
 out:
 	if (inode)
-- 
GitLab


From 5cdd7db6c5c9d33dc66ecdd81aa8020276c7d140 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 1 Feb 2017 22:39:50 +0000
Subject: [PATCH 202/898] Btrfs: fix assertion failure when freeing block
 groups at close_ctree()

At close_ctree() we free the block groups and then only after we wait for
any running worker kthreads to finish and shutdown the workqueues. This
behaviour is racy and it triggers an assertion failure when freeing block
groups because while we are doing it we can have for example a block group
caching kthread running, and in that case the block group's reference
count can still be greater than 1 by the time we assert its reference count
is 1, leading to an assertion failure:

[19041.198004] assertion failed: atomic_read(&block_group->count) == 1, file: fs/btrfs/extent-tree.c, line: 9799
[19041.200584] ------------[ cut here ]------------
[19041.201692] kernel BUG at fs/btrfs/ctree.h:3418!
[19041.202830] invalid opcode: 0000 [#1] PREEMPT SMP
[19041.203929] Modules linked in: btrfs xor raid6_pq dm_flakey dm_mod crc32c_generic ppdev sg psmouse acpi_cpufreq pcspkr parport_pc evdev tpm_tis parport tpm_tis_core i2c_piix4 i2c_core tpm serio_raw processor button loop autofs4 ext4 crc16 jbd2 mbcache sr_mod cdrom sd_mod ata_generic virtio_scsi ata_piix virtio_pci libata virtio_ring virtio e1000 scsi_mod floppy [last unloaded: btrfs]
[19041.208082] CPU: 6 PID: 29051 Comm: umount Not tainted 4.9.0-rc7-btrfs-next-36+ #1
[19041.208082] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014
[19041.208082] task: ffff88015f028980 task.stack: ffffc9000ad34000
[19041.208082] RIP: 0010:[<ffffffffa03e319e>]  [<ffffffffa03e319e>] assfail.constprop.41+0x1c/0x1e [btrfs]
[19041.208082] RSP: 0018:ffffc9000ad37d60  EFLAGS: 00010286
[19041.208082] RAX: 0000000000000061 RBX: ffff88015ecb4000 RCX: 0000000000000001
[19041.208082] RDX: ffff88023f392fb8 RSI: ffffffff817ef7ba RDI: 00000000ffffffff
[19041.208082] RBP: ffffc9000ad37d60 R08: 0000000000000001 R09: 0000000000000000
[19041.208082] R10: ffffc9000ad37cb0 R11: ffffffff82f2b66d R12: ffff88023431d170
[19041.208082] R13: ffff88015ecb40c0 R14: ffff88023431d000 R15: ffff88015ecb4100
[19041.208082] FS:  00007f44f3d42840(0000) GS:ffff88023f380000(0000) knlGS:0000000000000000
[19041.208082] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[19041.208082] CR2: 00007f65d623b000 CR3: 00000002166f2000 CR4: 00000000000006e0
[19041.208082] Stack:
[19041.208082]  ffffc9000ad37d98 ffffffffa035989f ffff88015ecb4000 ffff88015ecb5630
[19041.208082]  ffff88014f6be000 0000000000000000 00007ffcf0ba6a10 ffffc9000ad37df8
[19041.208082]  ffffffffa0368cd4 ffff88014e9658e0 ffffc9000ad37e08 ffffffff811a634d
[19041.208082] Call Trace:
[19041.208082]  [<ffffffffa035989f>] btrfs_free_block_groups+0x17f/0x392 [btrfs]
[19041.208082]  [<ffffffffa0368cd4>] close_ctree+0x1c5/0x2e1 [btrfs]
[19041.208082]  [<ffffffff811a634d>] ? evict_inodes+0x132/0x141
[19041.208082]  [<ffffffffa034356d>] btrfs_put_super+0x15/0x17 [btrfs]
[19041.208082]  [<ffffffff8118fc32>] generic_shutdown_super+0x6a/0xeb
[19041.208082]  [<ffffffff8119004f>] kill_anon_super+0x12/0x1c
[19041.208082]  [<ffffffffa0343370>] btrfs_kill_super+0x16/0x21 [btrfs]
[19041.208082]  [<ffffffff8118fad1>] deactivate_locked_super+0x3b/0x68
[19041.208082]  [<ffffffff8118fb34>] deactivate_super+0x36/0x39
[19041.208082]  [<ffffffff811a9946>] cleanup_mnt+0x58/0x76
[19041.208082]  [<ffffffff811a99a2>] __cleanup_mnt+0x12/0x14
[19041.208082]  [<ffffffff81071573>] task_work_run+0x6f/0x95
[19041.208082]  [<ffffffff81001897>] prepare_exit_to_usermode+0xa3/0xc1
[19041.208082]  [<ffffffff81001a23>] syscall_return_slowpath+0x16e/0x1d2
[19041.208082]  [<ffffffff814c607d>] entry_SYSCALL_64_fastpath+0xab/0xad
[19041.208082] Code: c7 ae a0 3e a0 48 89 e5 e8 4e 74 d4 e0 0f 0b 55 89 f1 48 c7 c2 0b a4 3e a0 48 89 fe 48 c7 c7 a4 a6 3e a0 48 89 e5 e8 30 74 d4 e0 <0f> 0b 55 31 d2 48 89 e5 e8 d5 b9 f7 ff 5d c3 48 63 f6 55 31 c9
[19041.208082] RIP  [<ffffffffa03e319e>] assfail.constprop.41+0x1c/0x1e [btrfs]
[19041.208082]  RSP <ffffc9000ad37d60>
[19041.279264] ---[ end trace 23330586f16f064d ]---

This started happening as of kernel 4.8, since commit f3bca8028bd9
("Btrfs: add ASSERT for block group's memory leak") introduced these
assertions.

So fix this by freeing the block groups only after waiting for all
worker kthreads to complete and shutdown the workqueues.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
---
 fs/btrfs/disk-io.c     | 6 +++---
 fs/btrfs/extent-tree.c | 9 ++++++---
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2b06f557c176..d0e61d58b121 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3261,7 +3261,6 @@ int open_ctree(struct super_block *sb,
 
 fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
-	btrfs_free_block_groups(fs_info);
 
 fail_tree_roots:
 	free_root_pointers(fs_info, 1);
@@ -3269,6 +3268,7 @@ int open_ctree(struct super_block *sb,
 
 fail_sb_buffer:
 	btrfs_stop_all_workers(fs_info);
+	btrfs_free_block_groups(fs_info);
 fail_alloc:
 fail_iput:
 	btrfs_mapping_tree_free(&fs_info->mapping_tree);
@@ -3977,8 +3977,6 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 
 	btrfs_put_block_group_cache(fs_info);
 
-	btrfs_free_block_groups(fs_info);
-
 	/*
 	 * we must make sure there is not any read request to
 	 * submit after we stopping all workers.
@@ -3986,6 +3984,8 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
+	btrfs_free_block_groups(fs_info);
+
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	free_root_pointers(fs_info, 1);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c35b96633554..438c7312de33 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9740,6 +9740,11 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 	}
 }
 
+/*
+ * Must be called only after stopping all workers, since we could have block
+ * group caching kthreads running, and therefore they could race with us if we
+ * freed the block groups before stopping them.
+ */
 int btrfs_free_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_block_group_cache *block_group;
@@ -9779,9 +9784,6 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		list_del(&block_group->list);
 		up_write(&block_group->space_info->groups_sem);
 
-		if (block_group->cached == BTRFS_CACHE_STARTED)
-			wait_block_group_cache_done(block_group);
-
 		/*
 		 * We haven't cached this block group, which means we could
 		 * possibly have excluded extents on this block group.
@@ -9791,6 +9793,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 			free_excluded_extents(info, block_group);
 
 		btrfs_remove_free_space_cache(block_group);
+		ASSERT(block_group->cached != BTRFS_CACHE_STARTED);
 		ASSERT(list_empty(&block_group->dirty_list));
 		ASSERT(list_empty(&block_group->io_list));
 		ASSERT(list_empty(&block_group->bg_list));
-- 
GitLab


From a9b9477db2937934e469db800317ec3ef7e81b51 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 4 Feb 2017 17:12:00 +0000
Subject: [PATCH 203/898] Btrfs: fix use-after-free due to wrong order of
 destroying work queues

Before we destroy all work queues (and wait for their tasks to complete)
we were destroying the work queues used for metadata I/O operations, which
can result in a use-after-free problem because most tasks from all work
queues do metadata I/O operations. For example, the tasks from the caching
workers work queue (fs_info->caching_workers), which is destroyed only
after the work queue used for metadata reads (fs_info->endio_meta_workers)
is destroyed, do metadata reads, which result in attempts to queue tasks
into the later work queue, triggering a use-after-free with a trace like
the following:

[23114.613543] general protection fault: 0000 [#1] PREEMPT SMP
[23114.614442] Modules linked in: dm_thin_pool dm_persistent_data dm_bio_prison dm_bufio libcrc32c btrfs xor raid6_pq dm_flakey dm_mod crc32c_generic
acpi_cpufreq tpm_tis tpm_tis_core tpm ppdev parport_pc parport i2c_piix4 processor sg evdev i2c_core psmouse pcspkr serio_raw button loop autofs4 ext4 crc16
jbd2 mbcache sr_mod cdrom sd_mod ata_generic virtio_scsi ata_piix virtio_pci libata virtio_ring virtio e1000 scsi_mod floppy [last unloaded: scsi_debug]
[23114.616932] CPU: 9 PID: 4537 Comm: kworker/u32:8 Not tainted 4.9.0-rc7-btrfs-next-36+ #1
[23114.616932] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014
[23114.616932] Workqueue: btrfs-cache btrfs_cache_helper [btrfs]
[23114.616932] task: ffff880221d45780 task.stack: ffffc9000bc50000
[23114.616932] RIP: 0010:[<ffffffffa037c1bf>]  [<ffffffffa037c1bf>] btrfs_queue_work+0x2c/0x190 [btrfs]
[23114.616932] RSP: 0018:ffff88023f443d60  EFLAGS: 00010246
[23114.616932] RAX: 0000000000000000 RBX: 6b6b6b6b6b6b6b6b RCX: 0000000000000102
[23114.616932] RDX: ffffffffa0419000 RSI: ffff88011df534f0 RDI: ffff880101f01c00
[23114.616932] RBP: ffff88023f443d80 R08: 00000000000f7000 R09: 000000000000ffff
[23114.616932] R10: ffff88023f443d48 R11: 0000000000001000 R12: ffff88011df534f0
[23114.616932] R13: ffff880135963868 R14: 0000000000001000 R15: 0000000000001000
[23114.616932] FS:  0000000000000000(0000) GS:ffff88023f440000(0000) knlGS:0000000000000000
[23114.616932] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[23114.616932] CR2: 00007f0fb9f8e520 CR3: 0000000001a0b000 CR4: 00000000000006e0
[23114.616932] Stack:
[23114.616932]  ffff880101f01c00 ffff88011df534f0 ffff880135963868 0000000000001000
[23114.616932]  ffff88023f443da0 ffffffffa03470af ffff880149b37200 ffff880135963868
[23114.616932]  ffff88023f443db8 ffffffff8125293c ffff880149b37200 ffff88023f443de0
[23114.616932] Call Trace:
[23114.616932]  <IRQ> [23114.616932]  [<ffffffffa03470af>] end_workqueue_bio+0xd5/0xda [btrfs]
[23114.616932]  [<ffffffff8125293c>] bio_endio+0x54/0x57
[23114.616932]  [<ffffffffa0377929>] btrfs_end_bio+0xf7/0x106 [btrfs]
[23114.616932]  [<ffffffff8125293c>] bio_endio+0x54/0x57
[23114.616932]  [<ffffffff8125955f>] blk_update_request+0x21a/0x30f
[23114.616932]  [<ffffffffa0022316>] scsi_end_request+0x31/0x182 [scsi_mod]
[23114.616932]  [<ffffffffa00235fc>] scsi_io_completion+0x1ce/0x4c8 [scsi_mod]
[23114.616932]  [<ffffffffa001ba9d>] scsi_finish_command+0x104/0x10d [scsi_mod]
[23114.616932]  [<ffffffffa002311f>] scsi_softirq_done+0x101/0x10a [scsi_mod]
[23114.616932]  [<ffffffff8125fbd9>] blk_done_softirq+0x82/0x8d
[23114.616932]  [<ffffffff814c8a4b>] __do_softirq+0x1ab/0x412
[23114.616932]  [<ffffffff8105b01d>] irq_exit+0x49/0x99
[23114.616932]  [<ffffffff81035135>] smp_call_function_single_interrupt+0x24/0x26
[23114.616932]  [<ffffffff814c7ec9>] call_function_single_interrupt+0x89/0x90
[23114.616932]  <EOI> [23114.616932]  [<ffffffffa0023262>] ? scsi_request_fn+0x13a/0x2a1 [scsi_mod]
[23114.616932]  [<ffffffff814c5966>] ? _raw_spin_unlock_irq+0x2c/0x4a
[23114.616932]  [<ffffffff814c596c>] ? _raw_spin_unlock_irq+0x32/0x4a
[23114.616932]  [<ffffffff814c5966>] ? _raw_spin_unlock_irq+0x2c/0x4a
[23114.616932]  [<ffffffffa0023262>] scsi_request_fn+0x13a/0x2a1 [scsi_mod]
[23114.616932]  [<ffffffff8125590e>] __blk_run_queue_uncond+0x22/0x2b
[23114.616932]  [<ffffffff81255930>] __blk_run_queue+0x19/0x1b
[23114.616932]  [<ffffffff8125ab01>] blk_queue_bio+0x268/0x282
[23114.616932]  [<ffffffff81258f44>] generic_make_request+0xbd/0x160
[23114.616932]  [<ffffffff812590e7>] submit_bio+0x100/0x11d
[23114.616932]  [<ffffffff81298603>] ? __this_cpu_preempt_check+0x13/0x15
[23114.616932]  [<ffffffff812a1805>] ? __percpu_counter_add+0x8e/0xa7
[23114.616932]  [<ffffffffa03bfd47>] btrfsic_submit_bio+0x1a/0x1d [btrfs]
[23114.616932]  [<ffffffffa0377db2>] btrfs_map_bio+0x1f4/0x26d [btrfs]
[23114.616932]  [<ffffffffa0348a33>] btree_submit_bio_hook+0x74/0xbf [btrfs]
[23114.616932]  [<ffffffffa03489bf>] ? btrfs_wq_submit_bio+0x160/0x160 [btrfs]
[23114.616932]  [<ffffffffa03697a9>] submit_one_bio+0x6b/0x89 [btrfs]
[23114.616932]  [<ffffffffa036f5be>] read_extent_buffer_pages+0x170/0x1ec [btrfs]
[23114.616932]  [<ffffffffa03471fa>] ? free_root_pointers+0x64/0x64 [btrfs]
[23114.616932]  [<ffffffffa0348adf>] readahead_tree_block+0x3f/0x4c [btrfs]
[23114.616932]  [<ffffffffa032e115>] read_block_for_search.isra.20+0x1ce/0x23d [btrfs]
[23114.616932]  [<ffffffffa032fab8>] btrfs_search_slot+0x65f/0x774 [btrfs]
[23114.616932]  [<ffffffffa036eff1>] ? free_extent_buffer+0x73/0x7e [btrfs]
[23114.616932]  [<ffffffffa0331ba4>] btrfs_next_old_leaf+0xa1/0x33c [btrfs]
[23114.616932]  [<ffffffffa0331e4f>] btrfs_next_leaf+0x10/0x12 [btrfs]
[23114.616932]  [<ffffffffa0336aa6>] caching_thread+0x22d/0x416 [btrfs]
[23114.616932]  [<ffffffffa037bce9>] btrfs_scrubparity_helper+0x187/0x3b6 [btrfs]
[23114.616932]  [<ffffffffa037c036>] btrfs_cache_helper+0xe/0x10 [btrfs]
[23114.616932]  [<ffffffff8106cf96>] process_one_work+0x273/0x4e4
[23114.616932]  [<ffffffff8106d6db>] worker_thread+0x1eb/0x2ca
[23114.616932]  [<ffffffff8106d4f0>] ? rescuer_thread+0x2b6/0x2b6
[23114.616932]  [<ffffffff81072a81>] kthread+0xd5/0xdd
[23114.616932]  [<ffffffff810729ac>] ? __kthread_unpark+0x5a/0x5a
[23114.616932]  [<ffffffff814c6257>] ret_from_fork+0x27/0x40
[23114.616932] Code: 1f 44 00 00 55 48 89 e5 41 56 41 55 41 54 53 49 89 f4 48 8b 46 70 a8 04 74 09 48 8b 5f 08 48 85 db 75 03 48 8b 1f 49 89 5c 24 68 <83> 7b
64 ff 74 04 f0 ff 43 58 49 83 7c 24 08 00 74 2c 4c 8d 6b
[23114.616932] RIP  [<ffffffffa037c1bf>] btrfs_queue_work+0x2c/0x190 [btrfs]
[23114.616932]  RSP <ffff88023f443d60>
[23114.689493] ---[ end trace 6e48b6bc707ca34b ]---
[23114.690166] Kernel panic - not syncing: Fatal exception in interrupt
[23114.691283] Kernel Offset: disabled
[23114.691918] ---[ end Kernel panic - not syncing: Fatal exception in interrupt

The following diagram shows the sequence of operations that lead to the
use-after-free problem from the above trace:

        CPU 1                               CPU 2                                     CPU 3

                                       caching_thread()
 close_ctree()
   btrfs_stop_all_workers()
     btrfs_destroy_workqueue(
      fs_info->endio_meta_workers)

                                         btrfs_search_slot()
                                          read_block_for_search()
                                           readahead_tree_block()
                                            read_extent_buffer_pages()
                                             submit_one_bio()
                                              btree_submit_bio_hook()
                                               btrfs_bio_wq_end_io()
                                                --> sets the bio's
                                                    bi_end_io callback
                                                    to end_workqueue_bio()
                                               --> bio is submitted
                                                                                  bio completes
                                                                                  and its bi_end_io callback
                                                                                  is invoked
                                                                                   --> end_workqueue_bio()
                                                                                       --> attempts to queue
                                                                                           a task on fs_info->endio_meta_workers

     btrfs_destroy_workqueue(
      fs_info->caching_workers)

So fix this by destroying the queues used for metadata I/O tasks only
after destroying all the other queues.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
---
 fs/btrfs/disk-io.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d0e61d58b121..32a9ec11888d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2205,11 +2205,9 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->delalloc_workers);
 	btrfs_destroy_workqueue(fs_info->workers);
 	btrfs_destroy_workqueue(fs_info->endio_workers);
-	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
 	btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
 	btrfs_destroy_workqueue(fs_info->endio_repair_workers);
 	btrfs_destroy_workqueue(fs_info->rmw_workers);
-	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
 	btrfs_destroy_workqueue(fs_info->submit_workers);
@@ -2219,6 +2217,13 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->flush_workers);
 	btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
 	btrfs_destroy_workqueue(fs_info->extent_workers);
+	/*
+	 * Now that all other work queues are destroyed, we can safely destroy
+	 * the queues used for metadata I/O, since tasks from those other work
+	 * queues can do metadata I/O operations.
+	 */
+	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
+	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
 }
 
 static void free_root_extent_buffers(struct btrfs_root *root)
-- 
GitLab


From 82bfb2e7b645c8f228dc3b6d3b27b0b10125ca4f Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 14 Feb 2017 17:56:32 +0000
Subject: [PATCH 204/898] Btrfs: incremental send, fix unnecessary hole writes
 for sparse files

When using the NO_HOLES feature, during an incremental send we often issue
write operations for holes when we should not, because that range is already
a hole in the destination snapshot. While that does not change the contents
of the file at the receiver, it avoids preservation of file holes, leading
to wasted disk space and extra IO during send/receive.

A couple examples where the holes are not preserved follows.

 $ mkfs.btrfs -O no-holes -f /dev/sdb
 $ mount /dev/sdb /mnt
 $ xfs_io -f -c "pwrite -S 0xaa 0 4K" /mnt/foo
 $ xfs_io -f -c "pwrite -S 0xaa 0 4K" -c "pwrite -S 0xbb 1028K 4K" /mnt/bar
 $ btrfs subvolume snapshot -r /mnt /mnt/snap1

 # Now add one new extent to our first test file, increasing its size and
 # leaving a 1Mb hole between the first extent and this new extent.
 $ xfs_io -c "pwrite -S 0xbb 1028K 4K" /mnt/foo

 # Now overwrite the last extent of our second test file.
 $ xfs_io -c "pwrite -S 0xcc 1028K 4K" /mnt/bar

 $ btrfs subvolume snapshot -r /mnt /mnt/snap2

 $ xfs_io -r -c "fiemap -v" /mnt/snap2/foo
 /mnt/snap2/foo:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..7]:          25088..25095         8 0x2000
   1: [8..2055]:       hole              2048
   2: [2056..2063]:    24576..24583         8 0x2001

 $ xfs_io -r -c "fiemap -v" /mnt/snap2/bar
 /mnt/snap2/bar:
 EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
   0: [0..7]:          25096..25103         8 0x2000
   1: [8..2055]:       hole              2048
   2: [2056..2063]:    24584..24591         8 0x2001

  $ btrfs send /mnt/snap1 -f /tmp/1.snap
  $ btrfs send -p /mnt/snap1 /mnt/snap2 -f /tmp/2.snap

  $ umount /mnt
  # It's not relevant to enable no-holes in the new filesystem.
  $ mkfs.btrfs -O no-holes -f /dev/sdc
  $ mount /dev/sdc /mnt
  $ btrfs receive /mnt -f /tmp/1.snap
  $ btrfs receive /mnt -f /tmp/2.snap

  $ xfs_io -r -c "fiemap -v" /mnt/snap2/foo
  /mnt/snap2/foo:
  EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
    0: [0..7]:          24576..24583         8 0x2000
    1: [8..2063]:       25624..27679      2056   0x1

  $ xfs_io -r -c "fiemap -v" /mnt/snap2/bar
  /mnt/snap2/bar:
  EXT: FILE-OFFSET      BLOCK-RANGE      TOTAL FLAGS
    0: [0..7]:          24584..24591         8 0x2000
    1: [8..2063]:       27680..29735      2056   0x1

The holes do not exist in the second filesystem and they were replaced
with extents filled with the byte 0x00, making each file take 1032Kb of
space instead of 8Kb.

So fix this by not issuing the write operations consisting of buffers
filled with the byte 0x00 when the destination snapshot already has a
hole for the respective range.

A test case for fstests will follow soon.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/send.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 86 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 712922ea64d2..456c8901489b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5306,6 +5306,81 @@ static int get_last_extent(struct send_ctx *sctx, u64 offset)
 	return ret;
 }
 
+static int range_is_hole_in_parent(struct send_ctx *sctx,
+				   const u64 start,
+				   const u64 end)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_root *root = sctx->parent_root;
+	u64 search_start = start;
+	int ret;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = sctx->cur_ino;
+	key.type = BTRFS_EXTENT_DATA_KEY;
+	key.offset = search_start;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0 && path->slots[0] > 0)
+		path->slots[0]--;
+
+	while (search_start < end) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+		struct btrfs_file_extent_item *fi;
+		u64 extent_end;
+
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid < sctx->cur_ino ||
+		    key.type < BTRFS_EXTENT_DATA_KEY)
+			goto next;
+		if (key.objectid > sctx->cur_ino ||
+		    key.type > BTRFS_EXTENT_DATA_KEY ||
+		    key.offset >= end)
+			break;
+
+		fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+		if (btrfs_file_extent_type(leaf, fi) ==
+		    BTRFS_FILE_EXTENT_INLINE) {
+			u64 size = btrfs_file_extent_inline_len(leaf, slot, fi);
+
+			extent_end = ALIGN(key.offset + size,
+					   root->fs_info->sectorsize);
+		} else {
+			extent_end = key.offset +
+				btrfs_file_extent_num_bytes(leaf, fi);
+		}
+		if (extent_end <= start)
+			goto next;
+		if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) {
+			search_start = extent_end;
+			goto next;
+		}
+		ret = 0;
+		goto out;
+next:
+		path->slots[0]++;
+	}
+	ret = 1;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			   struct btrfs_key *key)
 {
@@ -5350,8 +5425,17 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			return ret;
 	}
 
-	if (sctx->cur_inode_last_extent < key->offset)
-		ret = send_hole(sctx, key->offset);
+	if (sctx->cur_inode_last_extent < key->offset) {
+		ret = range_is_hole_in_parent(sctx,
+					      sctx->cur_inode_last_extent,
+					      key->offset);
+		if (ret < 0)
+			return ret;
+		else if (ret == 0)
+			ret = send_hole(sctx, key->offset);
+		else
+			ret = 0;
+	}
 	sctx->cur_inode_last_extent = extent_end;
 	return ret;
 }
-- 
GitLab


From 76b42abbf7488121c4f9f1ea5941123306e25d99 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 14 Feb 2017 16:56:01 +0000
Subject: [PATCH 205/898] Btrfs: fix data loss after truncate when using the
 no-holes feature

If we have a file with an implicit hole (NO_HOLES feature enabled) that
has an extent following the hole, delayed writes against regions of the
file behind the hole happened before but were not yet flushed and then
we truncate the file to a smaller size that lies inside the hole, we
end up persisting a wrong disk_i_size value for our inode that leads to
data loss after umounting and mounting again the filesystem or after
the inode is evicted and loaded again.

This happens because at inode.c:btrfs_truncate_inode_items() we end up
setting last_size to the offset of the extent that we deleted and that
followed the hole. We then pass that value to btrfs_ordered_update_i_size()
which updates the inode's disk_i_size to a value smaller then the offset
of the buffered (delayed) writes.

Example reproducer:

 $ mkfs.btrfs -f /dev/sdb
 $ mount /dev/sdb /mnt

 $ xfs_io -f -c "pwrite -S 0x01 0K 32K" /mnt/foo
 $ xfs_io -d -c "pwrite -S 0x02 -b 32K 64K 32K" /mnt/foo
 $ xfs_io -c "truncate 60K" /mnt/foo
   --> inode's disk_i_size updated to 0

 $ md5sum /mnt/foo
 3c5ca3c3ab42f4b04d7e7eb0b0d4d806  /mnt/foo

 $ umount /dev/sdb
 $ mount /dev/sdb /mnt

 $ md5sum /mnt/foo
 d41d8cd98f00b204e9800998ecf8427e  /mnt/foo
   --> Empty file, all data lost!

Cc: <stable@vger.kernel.org>  # 3.14+
Fixes: 16e7549f045d ("Btrfs: incompatible format change to remove hole extents")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
---
 fs/btrfs/inode.c | 19 ++++++-------------
 1 file changed, 6 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4efe9d82944c..70df45192424 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4418,19 +4418,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size) {
-				/*
-				 * With NO_HOLES mode, for the following mapping
-				 *
-				 * [0-4k][hole][8k-12k]
-				 *
-				 * if truncating isize down to 6k, it ends up
-				 * isize being 8k.
-				 */
-				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
-					last_size = new_size;
+			if (item_end < new_size)
 				break;
-			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else
@@ -4613,8 +4602,12 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			btrfs_abort_transaction(trans, ret);
 	}
 error:
-	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+		ASSERT(last_size >= new_size);
+		if (!err && last_size > new_size)
+			last_size = new_size;
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
+	}
 
 	btrfs_free_path(path);
 
-- 
GitLab


From 263d3995c93c6020576f6c93506412a0b9d1e932 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 17 Feb 2017 18:43:57 +0000
Subject: [PATCH 206/898] Btrfs: try harder to migrate items to left sibling
 before splitting a leaf

Before attempting to split a leaf we try to migrate items from the leaf to
its right and left siblings. We start by trying to move items into the
rigth sibling and, if the new item is meant to be inserted at the end of
our leaf, we try to free from our leaf an amount of bytes equal to the
number of bytes used by the new item, by setting the variable space_needed
to the byte size of that new item. However if we fail to move enough items
to the right sibling due to lack of space in that sibling, we then try
to move items into the left sibling, and in that case we try to free
an amount equal to the size of the new item from our leaf, when we need
only to free an amount corresponding to the size of the new item minus
the current free space of our leaf. So make sure that before we try to
move items to the left sibling we do set the variable space_needed with
a value corresponding to the new item's size minus the leaf's current
free space.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
---
 fs/btrfs/ctree.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 1192bc7d2ee7..1fb60ee77b4a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -4159,6 +4159,9 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans,
 
 	/* try to push all the items before our slot into the next leaf */
 	slot = path->slots[0];
+	space_needed = data_size;
+	if (slot > 0)
+		space_needed -= btrfs_leaf_free_space(fs_info, path->nodes[0]);
 	ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot);
 	if (ret < 0)
 		return ret;
@@ -4214,6 +4217,10 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 		if (wret < 0)
 			return wret;
 		if (wret) {
+			space_needed = data_size;
+			if (slot > 0)
+				space_needed -= btrfs_leaf_free_space(fs_info,
+								      l);
 			wret = push_leaf_left(trans, root, path, space_needed,
 					      space_needed, 0, (u32)-1);
 			if (wret < 0)
-- 
GitLab


From bca5609fcc401b0055a3c01ecc33c5f6fb67af7b Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Fri, 24 Feb 2017 10:58:20 +0800
Subject: [PATCH 207/898] drm/i915/gvt: Add more edid definition support

We'll need to apply different resolution for vgpu types, so this
adds more EDID types definition.

v2: fix typo for actual 1920x1200 resolution

Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/display.c | 112 +++++++++++++++++++----------
 drivers/gpu/drm/i915/gvt/display.h |   6 ++
 2 files changed, 80 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8fde880c39..d346e43656f7 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -83,44 +83,80 @@ static int pipe_is_enabled(struct intel_vgpu *vgpu, int pipe)
 	return 0;
 }
 
+static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = {
+	{
+/* EDID with 1024x768 as its resolution */
+		/*Header*/
+		0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+		/* Vendor & Product Identification */
+		0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
+		/* Version & Revision */
+		0x01, 0x04,
+		/* Basic Display Parameters & Features */
+		0xa5, 0x34, 0x20, 0x78, 0x23,
+		/* Color Characteristics */
+		0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
+		/* Established Timings: maximum resolution is 1024x768 */
+		0x21, 0x08, 0x00,
+		/* Standard Timings. All invalid */
+		0x00, 0xc0, 0x00, 0xc0, 0x00, 0x40, 0x00, 0x80, 0x00, 0x00,
+		0x00, 0x40, 0x00, 0x00, 0x00, 0x01,
+		/* 18 Byte Data Blocks 1: invalid */
+		0x00, 0x00, 0x80, 0xa0, 0x70, 0xb0,
+		0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
+		/* 18 Byte Data Blocks 2: invalid */
+		0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
+		0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+		/* 18 Byte Data Blocks 3: invalid */
+		0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
+		0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
+		/* 18 Byte Data Blocks 4: invalid */
+		0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
+		0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
+		/* Extension Block Count */
+		0x00,
+		/* Checksum */
+		0xef,
+	},
+	{
 /* EDID with 1920x1200 as its resolution */
-static unsigned char virtual_dp_monitor_edid[] = {
-	/*Header*/
-	0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
-	/* Vendor & Product Identification */
-	0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
-	/* Version & Revision */
-	0x01, 0x04,
-	/* Basic Display Parameters & Features */
-	0xa5, 0x34, 0x20, 0x78, 0x23,
-	/* Color Characteristics */
-	0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
-	/* Established Timings: maximum resolution is 1024x768 */
-	0x21, 0x08, 0x00,
-	/*
-	 * Standard Timings.
-	 * below new resolutions can be supported:
-	 * 1920x1080, 1280x720, 1280x960, 1280x1024,
-	 * 1440x900, 1600x1200, 1680x1050
-	 */
-	0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00,
-	0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01,
-	/* 18 Byte Data Blocks 1: max resolution is 1920x1200 */
-	0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0,
-	0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
-	/* 18 Byte Data Blocks 2: invalid */
-	0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
-	0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-	/* 18 Byte Data Blocks 3: invalid */
-	0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
-	0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
-	/* 18 Byte Data Blocks 4: invalid */
-	0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
-	0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
-	/* Extension Block Count */
-	0x00,
-	/* Checksum */
-	0x45,
+		/*Header*/
+		0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+		/* Vendor & Product Identification */
+		0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
+		/* Version & Revision */
+		0x01, 0x04,
+		/* Basic Display Parameters & Features */
+		0xa5, 0x34, 0x20, 0x78, 0x23,
+		/* Color Characteristics */
+		0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
+		/* Established Timings: maximum resolution is 1024x768 */
+		0x21, 0x08, 0x00,
+		/*
+		 * Standard Timings.
+		 * below new resolutions can be supported:
+		 * 1920x1080, 1280x720, 1280x960, 1280x1024,
+		 * 1440x900, 1600x1200, 1680x1050
+		 */
+		0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00,
+		0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01,
+		/* 18 Byte Data Blocks 1: max resolution is 1920x1200 */
+		0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0,
+		0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
+		/* 18 Byte Data Blocks 2: invalid */
+		0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
+		0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+		/* 18 Byte Data Blocks 3: invalid */
+		0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
+		0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
+		/* 18 Byte Data Blocks 4: invalid */
+		0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
+		0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
+		/* Extension Block Count */
+		0x00,
+		/* Checksum */
+		0x45,
+	},
 };
 
 #define DPCD_HEADER_SIZE        0xb
@@ -189,7 +225,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
 		return -ENOMEM;
 	}
 
-	memcpy(port->edid->edid_block, virtual_dp_monitor_edid,
+	memcpy(port->edid->edid_block, virtual_dp_monitor_edid[GVT_EDID_1920_1200],
 			EDID_SIZE);
 	port->edid->data_valid = true;
 
diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h
index 8b234ea961f6..84f160bb7bc2 100644
--- a/drivers/gpu/drm/i915/gvt/display.h
+++ b/drivers/gpu/drm/i915/gvt/display.h
@@ -154,6 +154,12 @@ struct intel_vgpu_port {
 	int type;
 };
 
+enum intel_vgpu_edid {
+	GVT_EDID_1024_768,
+	GVT_EDID_1920_1200,
+	GVT_EDID_NUM,
+};
+
 void intel_gvt_emulate_vblank(struct intel_gvt *gvt);
 void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt);
 
-- 
GitLab


From d1a513be1f0a25f094e1577d059b9aebaa279bb2 Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Fri, 24 Feb 2017 10:58:21 +0800
Subject: [PATCH 208/898] drm/i915/gvt: add resolution definition for vGPU type

This assigns resolution definition for each vGPU type. For smaller
resource type we should limit max resolution, so e.g limit to 1024x768
for 64M type, others are still default to 1920x1200.

v2: Fix for actual 1920x1200 resolution

Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/display.c | 15 ++++++++++-----
 drivers/gpu/drm/i915/gvt/display.h | 14 +++++++++++++-
 drivers/gpu/drm/i915/gvt/gvt.h     |  2 ++
 drivers/gpu/drm/i915/gvt/kvmgt.c   |  8 ++++----
 drivers/gpu/drm/i915/gvt/vgpu.c    | 18 +++++++++++-------
 5 files changed, 40 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index d346e43656f7..43e02e038375 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -211,10 +211,13 @@ static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num)
 }
 
 static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
-		int type)
+				    int type, unsigned int resolution)
 {
 	struct intel_vgpu_port *port = intel_vgpu_port(vgpu, port_num);
 
+	if (WARN_ON(resolution >= GVT_EDID_NUM))
+		return -EINVAL;
+
 	port->edid = kzalloc(sizeof(*(port->edid)), GFP_KERNEL);
 	if (!port->edid)
 		return -ENOMEM;
@@ -225,7 +228,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
 		return -ENOMEM;
 	}
 
-	memcpy(port->edid->edid_block, virtual_dp_monitor_edid[GVT_EDID_1920_1200],
+	memcpy(port->edid->edid_block, virtual_dp_monitor_edid[resolution],
 			EDID_SIZE);
 	port->edid->data_valid = true;
 
@@ -358,16 +361,18 @@ void intel_vgpu_clean_display(struct intel_vgpu *vgpu)
  * Zero on success, negative error code if failed.
  *
  */
-int intel_vgpu_init_display(struct intel_vgpu *vgpu)
+int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
 	intel_vgpu_init_i2c_edid(vgpu);
 
 	if (IS_SKYLAKE(dev_priv))
-		return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D);
+		return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D,
+						resolution);
 	else
-		return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B);
+		return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B,
+						resolution);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h
index 84f160bb7bc2..d73de22102e2 100644
--- a/drivers/gpu/drm/i915/gvt/display.h
+++ b/drivers/gpu/drm/i915/gvt/display.h
@@ -160,10 +160,22 @@ enum intel_vgpu_edid {
 	GVT_EDID_NUM,
 };
 
+static inline char *vgpu_edid_str(enum intel_vgpu_edid id)
+{
+	switch (id) {
+	case GVT_EDID_1024_768:
+		return "1024x768";
+	case GVT_EDID_1920_1200:
+		return "1920x1200";
+	default:
+		return "";
+	}
+}
+
 void intel_gvt_emulate_vblank(struct intel_gvt *gvt);
 void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt);
 
-int intel_vgpu_init_display(struct intel_vgpu *vgpu);
+int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution);
 void intel_vgpu_reset_display(struct intel_vgpu *vgpu);
 void intel_vgpu_clean_display(struct intel_vgpu *vgpu);
 
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index faff044c6434..23791920ced1 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -216,6 +216,7 @@ struct intel_vgpu_type {
 	unsigned int low_gm_size;
 	unsigned int high_gm_size;
 	unsigned int fence;
+	enum intel_vgpu_edid resolution;
 };
 
 struct intel_gvt {
@@ -318,6 +319,7 @@ struct intel_vgpu_creation_params {
 	__u64 low_gm_sz;  /* in MB */
 	__u64 high_gm_sz; /* in MB */
 	__u64 fence_sz;
+	__u64 resolution;
 	__s32 primary;
 	__u64 vgpu_id;
 };
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 10c3a4b95a92..182914c22ac5 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -295,10 +295,10 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev,
 		return 0;
 
 	return sprintf(buf, "low_gm_size: %dMB\nhigh_gm_size: %dMB\n"
-				"fence: %d\n",
-				BYTES_TO_MB(type->low_gm_size),
-				BYTES_TO_MB(type->high_gm_size),
-				type->fence);
+		       "fence: %d\nresolution: %s\n",
+		       BYTES_TO_MB(type->low_gm_size),
+		       BYTES_TO_MB(type->high_gm_size),
+		       type->fence, vgpu_edid_str(type->resolution));
 }
 
 static MDEV_TYPE_ATTR_RO(available_instance);
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index c27c13c3cc48..41cfa5ccae84 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -68,13 +68,14 @@ static struct {
 	unsigned int low_mm;
 	unsigned int high_mm;
 	unsigned int fence;
+	enum intel_vgpu_edid edid;
 	char *name;
 } vgpu_types[] = {
 /* Fixed vGPU type table */
-	{ MB_TO_BYTES(64), MB_TO_BYTES(512), 4, "8" },
-	{ MB_TO_BYTES(128), MB_TO_BYTES(512), 4, "4" },
-	{ MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, "2" },
-	{ MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, "1" },
+	{ MB_TO_BYTES(64), MB_TO_BYTES(512), 4, GVT_EDID_1024_768, "8" },
+	{ MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" },
+	{ MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" },
+	{ MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" },
 };
 
 /**
@@ -119,6 +120,7 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 		gvt->types[i].low_gm_size = vgpu_types[i].low_mm;
 		gvt->types[i].high_gm_size = vgpu_types[i].high_mm;
 		gvt->types[i].fence = vgpu_types[i].fence;
+		gvt->types[i].resolution = vgpu_types[i].edid;
 		gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm,
 						   high_avail / vgpu_types[i].high_mm);
 
@@ -129,11 +131,12 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 			sprintf(gvt->types[i].name, "GVTg_V5_%s",
 						vgpu_types[i].name);
 
-		gvt_dbg_core("type[%d]: %s avail %u low %u high %u fence %u\n",
+		gvt_dbg_core("type[%d]: %s avail %u low %u high %u fence %u res %s\n",
 			     i, gvt->types[i].name,
 			     gvt->types[i].avail_instance,
 			     gvt->types[i].low_gm_size,
-			     gvt->types[i].high_gm_size, gvt->types[i].fence);
+			     gvt->types[i].high_gm_size, gvt->types[i].fence,
+			     vgpu_edid_str(gvt->types[i].resolution));
 	}
 
 	gvt->num_types = i;
@@ -258,7 +261,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_detach_hypervisor_vgpu;
 
-	ret = intel_vgpu_init_display(vgpu);
+	ret = intel_vgpu_init_display(vgpu, param->resolution);
 	if (ret)
 		goto out_clean_gtt;
 
@@ -322,6 +325,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	param.low_gm_sz = type->low_gm_size;
 	param.high_gm_sz = type->high_gm_size;
 	param.fence_sz = type->fence;
+	param.resolution = type->resolution;
 
 	/* XXX current param based on MB */
 	param.low_gm_sz = BYTES_TO_MB(param.low_gm_sz);
-- 
GitLab


From 8bcd7c188bc479bea866d286a7dc0af9734c3c64 Mon Sep 17 00:00:00 2001
From: Weinan Li <weinan.z.li@intel.com>
Date: Fri, 24 Feb 2017 17:07:38 +0800
Subject: [PATCH 209/898] drm/i915/gvt: fix pcode mailbox write emulation of
 BDW

Add pcode mailbox write emulation in gvt for BDW, reuse emulation code of
Skylake.

V2: refine comments, remove duplication defination of 0x138124, add
IS_SKYLAKE() check for Skylake only pcode commands.

Signed-off-by: Weinan Li <weinan.z.li@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 33 ++++++++++++++++-------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index f89b183488e9..ebbe74072dc3 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1304,21 +1304,24 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 	u32 *data0 = &vgpu_vreg(vgpu, GEN6_PCODE_DATA);
 
 	switch (cmd) {
-	case 0x6:
-		/**
-		 * "Read memory latency" command on gen9.
-		 * Below memory latency values are read
-		 * from skylake platform.
-		 */
-		if (!*data0)
-			*data0 = 0x1e1a1100;
-		else
-			*data0 = 0x61514b3d;
+	case GEN9_PCODE_READ_MEM_LATENCY:
+		if (IS_SKYLAKE(vgpu->gvt->dev_priv)) {
+			/**
+			 * "Read memory latency" command on gen9.
+			 * Below memory latency values are read
+			 * from skylake platform.
+			 */
+			if (!*data0)
+				*data0 = 0x1e1a1100;
+			else
+				*data0 = 0x61514b3d;
+		}
 		break;
 	case SKL_PCODE_CDCLK_CONTROL:
-		*data0 = SKL_CDCLK_READY_FOR_CHANGE;
+		if (IS_SKYLAKE(vgpu->gvt->dev_priv))
+			*data0 = SKL_CDCLK_READY_FOR_CHANGE;
 		break;
-	case 0x5:
+	case GEN6_PCODE_READ_RC6VIDS:
 		*data0 |= 0x1;
 		break;
 	}
@@ -2202,7 +2205,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_F(0x4f000, 0x90, 0, 0, 0, D_ALL, NULL, NULL);
 
-	MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_SKL);
+	MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_BDW);
 	MMIO_D(GEN6_PCODE_DATA, D_ALL);
 	MMIO_D(0x13812c, D_ALL);
 	MMIO_DH(GEN7_ERR_INT, D_ALL, NULL, NULL);
@@ -2281,7 +2284,6 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x1a054, D_ALL);
 
 	MMIO_D(0x44070, D_ALL);
-
 	MMIO_D(0x215c, D_HSW_PLUS);
 	MMIO_DFH(0x2178, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x217c, D_ALL, F_CMD_ACCESS, NULL, NULL);
@@ -2453,6 +2455,8 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(GEN7_MISCCPCTL, D_BDW_PLUS);
 	MMIO_D(0x1c054, D_BDW_PLUS);
 
+	MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
+
 	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
 	MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
 
@@ -2544,7 +2548,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(HSW_PWR_WELL_BIOS, D_SKL);
 	MMIO_DH(HSW_PWR_WELL_DRIVER, D_SKL, NULL, skl_power_well_ctl_write);
 
-	MMIO_DH(GEN6_PCODE_MAILBOX, D_SKL, NULL, mailbox_write);
 	MMIO_D(0xa210, D_SKL_PLUS);
 	MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
 	MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
-- 
GitLab


From 41bfab35b3d0e0a85ed0c12d7bafd7484e96ca78 Mon Sep 17 00:00:00 2001
From: Pei Zhang <pei.zhang@intel.com>
Date: Fri, 24 Feb 2017 16:03:28 +0800
Subject: [PATCH 210/898] drm/i915/gvt: add some new MMIOs to cmd_access white
 list

Guest is now acces some MMIOs (0x215c, RING_INSTPM) through command which
is not originally in gvt's white list. This cause huge error log printed in
gvt.
This patch addes these MMIOs to the white list.

V2. change the commit message content.
V3. remove duplicate defination of 0x20c0.
V4. refine code style.

Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Weinan Li <weinan.z.li@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index ebbe74072dc3..57b4d538f370 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1589,7 +1589,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 #undef RING_REG
 
 	MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+			NULL, NULL);
 	MMIO_RING_DFH(RING_TIMESTAMP, D_ALL, F_CMD_ACCESS,
 			ring_timestamp_mmio_read, NULL);
 	MMIO_RING_DFH(RING_TIMESTAMP_UDW, D_ALL, F_CMD_ACCESS,
@@ -2284,7 +2285,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x1a054, D_ALL);
 
 	MMIO_D(0x44070, D_ALL);
-	MMIO_D(0x215c, D_HSW_PLUS);
+	MMIO_DFH(0x215c, D_HSW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x2178, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x217c, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x12178, D_ALL, F_CMD_ACCESS, NULL, NULL);
-- 
GitLab


From c0464062bfea9cd2ef6643d93429eafe8f6c2a4a Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sat, 25 Feb 2017 02:08:12 -0800
Subject: [PATCH 211/898] PCI: dwc: Fix crashes seen due to missing assignments

Fix the following crash, seen in dwc/pci-imx6.

  Unable to handle kernel NULL pointer dereference at virtual address 00000070
  pgd = c0004000
  [00000070] *pgd=00000000
  Internal error: Oops: 805 [#1] SMP ARM
  Modules linked in:
  CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.10.0-09686-g9e31489 #1
  Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree)
  task: cb850000 task.stack: cb84e000
  PC is at imx6_pcie_probe+0x2f4/0x414
  ...

While at it, fix the same problem in various drivers instead of waiting for
individual crash reports.

The change in the imx6 driver was tested with qemu. The changes in other
drivers are based on code inspection and have been compile tested only.

Fixes: 442ec4c04d12 ("PCI: dwc: all: Split struct pcie_port into host-only and core structures")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Vivek Gautam <vivek.gautam@codeaurora.org>  # designware-plat
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/pci/dwc/pci-exynos.c           | 1 +
 drivers/pci/dwc/pci-imx6.c             | 1 +
 drivers/pci/dwc/pci-keystone.c         | 2 ++
 drivers/pci/dwc/pci-layerscape.c       | 2 ++
 drivers/pci/dwc/pcie-armada8k.c        | 2 ++
 drivers/pci/dwc/pcie-artpec6.c         | 2 ++
 drivers/pci/dwc/pcie-designware-plat.c | 2 ++
 drivers/pci/dwc/pcie-hisi.c            | 2 ++
 drivers/pci/dwc/pcie-qcom.c            | 2 ++
 drivers/pci/dwc/pcie-spear13xx.c       | 2 ++
 10 files changed, 18 insertions(+)

diff --git a/drivers/pci/dwc/pci-exynos.c b/drivers/pci/dwc/pci-exynos.c
index 001c91a945aa..993b650ef275 100644
--- a/drivers/pci/dwc/pci-exynos.c
+++ b/drivers/pci/dwc/pci-exynos.c
@@ -668,6 +668,7 @@ static int __init exynos_pcie_probe(struct platform_device *pdev)
 	pci->dev = dev;
 	pci->ops = &dw_pcie_ops;
 
+	ep->pci = pci;
 	ep->ops = (const struct exynos_pcie_ops *)
 		of_device_get_match_data(dev);
 
diff --git a/drivers/pci/dwc/pci-imx6.c b/drivers/pci/dwc/pci-imx6.c
index 3ab6761db9e8..801e46cd266d 100644
--- a/drivers/pci/dwc/pci-imx6.c
+++ b/drivers/pci/dwc/pci-imx6.c
@@ -605,6 +605,7 @@ static int __init imx6_pcie_probe(struct platform_device *pdev)
 	pci->dev = dev;
 	pci->ops = &dw_pcie_ops;
 
+	imx6_pcie->pci = pci;
 	imx6_pcie->variant =
 		(enum imx6_pcie_variants)of_device_get_match_data(dev);
 
diff --git a/drivers/pci/dwc/pci-keystone.c b/drivers/pci/dwc/pci-keystone.c
index 8dc66409182d..fcc9723bad6e 100644
--- a/drivers/pci/dwc/pci-keystone.c
+++ b/drivers/pci/dwc/pci-keystone.c
@@ -401,6 +401,8 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
 	pci->dev = dev;
 	pci->ops = &dw_pcie_ops;
 
+	ks_pcie->pci = pci;
+
 	/* initialize SerDes Phy if present */
 	phy = devm_phy_get(dev, "pcie-phy");
 	if (PTR_ERR_OR_ZERO(phy) == -EPROBE_DEFER)
diff --git a/drivers/pci/dwc/pci-layerscape.c b/drivers/pci/dwc/pci-layerscape.c
index 175c09e3a932..c32e392a0ae6 100644
--- a/drivers/pci/dwc/pci-layerscape.c
+++ b/drivers/pci/dwc/pci-layerscape.c
@@ -280,6 +280,8 @@ static int __init ls_pcie_probe(struct platform_device *pdev)
 	pci->dev = dev;
 	pci->ops = pcie->drvdata->dw_pcie_ops;
 
+	pcie->pci = pci;
+
 	dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	pci->dbi_base = devm_ioremap_resource(dev, dbi_base);
 	if (IS_ERR(pci->dbi_base))
diff --git a/drivers/pci/dwc/pcie-armada8k.c b/drivers/pci/dwc/pcie-armada8k.c
index 66bac6fbfa9f..f110e3b24a26 100644
--- a/drivers/pci/dwc/pcie-armada8k.c
+++ b/drivers/pci/dwc/pcie-armada8k.c
@@ -220,6 +220,8 @@ static int armada8k_pcie_probe(struct platform_device *pdev)
 	pci->dev = dev;
 	pci->ops = &dw_pcie_ops;
 
+	pcie->pci = pci;
+
 	pcie->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(pcie->clk))
 		return PTR_ERR(pcie->clk);
diff --git a/drivers/pci/dwc/pcie-artpec6.c b/drivers/pci/dwc/pcie-artpec6.c
index 59ecc9e66436..fcd3ef845883 100644
--- a/drivers/pci/dwc/pcie-artpec6.c
+++ b/drivers/pci/dwc/pcie-artpec6.c
@@ -253,6 +253,8 @@ static int artpec6_pcie_probe(struct platform_device *pdev)
 
 	pci->dev = dev;
 
+	artpec6_pcie->pci = pci;
+
 	dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
 	pci->dbi_base = devm_ioremap_resource(dev, dbi_base);
 	if (IS_ERR(pci->dbi_base))
diff --git a/drivers/pci/dwc/pcie-designware-plat.c b/drivers/pci/dwc/pcie-designware-plat.c
index 65250f63515c..b6c832ba39dd 100644
--- a/drivers/pci/dwc/pcie-designware-plat.c
+++ b/drivers/pci/dwc/pcie-designware-plat.c
@@ -104,6 +104,8 @@ static int dw_plat_pcie_probe(struct platform_device *pdev)
 
 	pci->dev = dev;
 
+	dw_plat_pcie->pci = pci;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	pci->dbi_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(pci->dbi_base))
diff --git a/drivers/pci/dwc/pcie-hisi.c b/drivers/pci/dwc/pcie-hisi.c
index e3e4fedd9f68..fd66a3199db7 100644
--- a/drivers/pci/dwc/pcie-hisi.c
+++ b/drivers/pci/dwc/pcie-hisi.c
@@ -284,6 +284,8 @@ static int hisi_pcie_probe(struct platform_device *pdev)
 
 	driver = dev->driver;
 
+	hisi_pcie->pci = pci;
+
 	hisi_pcie->soc_ops = of_device_get_match_data(dev);
 
 	hisi_pcie->subctrl =
diff --git a/drivers/pci/dwc/pcie-qcom.c b/drivers/pci/dwc/pcie-qcom.c
index e36abe0d9d6f..67eb7f5926dd 100644
--- a/drivers/pci/dwc/pcie-qcom.c
+++ b/drivers/pci/dwc/pcie-qcom.c
@@ -686,6 +686,8 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 	pci->ops = &dw_pcie_ops;
 	pp = &pci->pp;
 
+	pcie->pci = pci;
+
 	pcie->ops = (struct qcom_pcie_ops *)of_device_get_match_data(dev);
 
 	pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_LOW);
diff --git a/drivers/pci/dwc/pcie-spear13xx.c b/drivers/pci/dwc/pcie-spear13xx.c
index 348f9c5e0433..eaa4ea8e2ea4 100644
--- a/drivers/pci/dwc/pcie-spear13xx.c
+++ b/drivers/pci/dwc/pcie-spear13xx.c
@@ -247,6 +247,8 @@ static int spear13xx_pcie_probe(struct platform_device *pdev)
 	pci->dev = dev;
 	pci->ops = &dw_pcie_ops;
 
+	spear13xx_pcie->pci = pci;
+
 	spear13xx_pcie->phy = devm_phy_get(dev, "pcie-phy");
 	if (IS_ERR(spear13xx_pcie->phy)) {
 		ret = PTR_ERR(spear13xx_pcie->phy);
-- 
GitLab


From ca1c39ef76376b67303d01f94fe98bb68bb3861a Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 21 Feb 2017 07:34:00 +0100
Subject: [PATCH 212/898] iio: adc: xilinx: Fix error handling

Reorder error handling labels in order to match the way resources have
been allocated.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/adc/xilinx-xadc-core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index 0a6beb3d99cb..56cf5907a5f0 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -1208,7 +1208,7 @@ static int xadc_probe(struct platform_device *pdev)
 
 	ret = xadc->ops->setup(pdev, indio_dev, irq);
 	if (ret)
-		goto err_free_samplerate_trigger;
+		goto err_clk_disable_unprepare;
 
 	ret = request_irq(irq, xadc->ops->interrupt_handler, 0,
 			dev_name(&pdev->dev), indio_dev);
@@ -1268,6 +1268,8 @@ static int xadc_probe(struct platform_device *pdev)
 
 err_free_irq:
 	free_irq(irq, indio_dev);
+err_clk_disable_unprepare:
+	clk_disable_unprepare(xadc->clk);
 err_free_samplerate_trigger:
 	if (xadc->ops->flags & XADC_FLAGS_BUFFERED)
 		iio_trigger_free(xadc->samplerate_trigger);
@@ -1277,8 +1279,6 @@ static int xadc_probe(struct platform_device *pdev)
 err_triggered_buffer_cleanup:
 	if (xadc->ops->flags & XADC_FLAGS_BUFFERED)
 		iio_triggered_buffer_cleanup(indio_dev);
-err_clk_disable_unprepare:
-	clk_disable_unprepare(xadc->clk);
 err_device_free:
 	kfree(indio_dev->channels);
 
-- 
GitLab


From 99cde44edfa06b5f910c1704cb15d36310a56545 Mon Sep 17 00:00:00 2001
From: Arvind Yadav <arvind.yadav.cs@gmail.com>
Date: Tue, 17 Jan 2017 13:35:03 +0530
Subject: [PATCH 213/898] parisc: eisa: Remove coding style errors

This patch removes coding style errors in the eisa driver.

Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/parisc/eisa.c | 104 +++++++++++++++++++++---------------------
 1 file changed, 52 insertions(+), 52 deletions(-)

diff --git a/drivers/parisc/eisa.c b/drivers/parisc/eisa.c
index 103095bbe8c0..59edee911f7d 100644
--- a/drivers/parisc/eisa.c
+++ b/drivers/parisc/eisa.c
@@ -14,16 +14,16 @@
  * Wax ASIC also includes a PS/2 and RS-232 controller, but those are
  * dealt with elsewhere; this file is concerned only with the EISA portions
  * of Wax.
- * 
- * 
+ *
+ *
  * HINT:
  * -----
  * To allow an ISA card to work properly in the EISA slot you need to
- * set an edge trigger level. This may be done on the palo command line 
- * by adding the kernel parameter "eisa_irq_edge=n,n2,[...]]", with 
+ * set an edge trigger level. This may be done on the palo command line
+ * by adding the kernel parameter "eisa_irq_edge=n,n2,[...]]", with
  * n and n2 as the irq levels you want to use.
- * 
- * Example: "eisa_irq_edge=10,11" allows ISA cards to operate at 
+ *
+ * Example: "eisa_irq_edge=10,11" allows ISA cards to operate at
  * irq levels 10 and 11.
  */
 
@@ -46,9 +46,9 @@
 #include <asm/eisa_eeprom.h>
 
 #if 0
-#define EISA_DBG(msg, arg... ) printk(KERN_DEBUG "eisa: " msg , ## arg )
+#define EISA_DBG(msg, arg...) printk(KERN_DEBUG "eisa: " msg, ## arg)
 #else
-#define EISA_DBG(msg, arg... )  
+#define EISA_DBG(msg, arg...)
 #endif
 
 #define SNAKES_EEPROM_BASE_ADDR 0xF0810400
@@ -108,7 +108,7 @@ void eisa_out8(unsigned char data, unsigned short port)
 
 void eisa_out16(unsigned short data, unsigned short port)
 {
-	if (EISA_bus)	
+	if (EISA_bus)
 		gsc_writew(cpu_to_le16(data), eisa_permute(port));
 }
 
@@ -135,9 +135,9 @@ static int master_mask;
 static int slave_mask;
 
 /* the trig level can be set with the
- * eisa_irq_edge=n,n,n commandline parameter 
- * We should really read this from the EEPROM 
- * in the furure. 
+ * eisa_irq_edge=n,n,n commandline parameter
+ * We should really read this from the EEPROM
+ * in the furure.
  */
 /* irq 13,8,2,1,0 must be edge */
 static unsigned int eisa_irq_level __read_mostly; /* default to edge triggered */
@@ -170,7 +170,7 @@ static void eisa_unmask_irq(struct irq_data *d)
 	unsigned int irq = d->irq;
 	unsigned long flags;
 	EISA_DBG("enable irq %d\n", irq);
-		
+
 	spin_lock_irqsave(&eisa_irq_lock, flags);
         if (irq & 8) {
 		slave_mask &= ~(1 << (irq&7));
@@ -194,7 +194,7 @@ static irqreturn_t eisa_irq(int wax_irq, void *intr_dev)
 {
 	int irq = gsc_readb(0xfc01f000); /* EISA supports 16 irqs */
 	unsigned long flags;
-        
+
 	spin_lock_irqsave(&eisa_irq_lock, flags);
 	/* read IRR command */
 	eisa_out8(0x0a, 0x20);
@@ -202,31 +202,31 @@ static irqreturn_t eisa_irq(int wax_irq, void *intr_dev)
 
 	EISA_DBG("irq IAR %02x 8259-1 irr %02x 8259-2 irr %02x\n",
 		   irq, eisa_in8(0x20), eisa_in8(0xa0));
-   
+
 	/* read ISR command */
 	eisa_out8(0x0a, 0x20);
 	eisa_out8(0x0a, 0xa0);
 	EISA_DBG("irq 8259-1 isr %02x imr %02x 8259-2 isr %02x imr %02x\n",
 		 eisa_in8(0x20), eisa_in8(0x21), eisa_in8(0xa0), eisa_in8(0xa1));
-	
+
 	irq &= 0xf;
-	
+
 	/* mask irq and write eoi */
 	if (irq & 8) {
 		slave_mask |= (1 << (irq&7));
 		eisa_out8(slave_mask, 0xa1);
 		eisa_out8(0x60 | (irq&7),0xa0);/* 'Specific EOI' to slave */
-		eisa_out8(0x62,0x20);	/* 'Specific EOI' to master-IRQ2 */
-		
+		eisa_out8(0x62, 0x20);	/* 'Specific EOI' to master-IRQ2 */
+
 	} else {
 		master_mask |= (1 << (irq&7));
 		eisa_out8(master_mask, 0x21);
-		eisa_out8(0x60|irq,0x20);	/* 'Specific EOI' to master */
+		eisa_out8(0x60|irq, 0x20);	/* 'Specific EOI' to master */
 	}
 	spin_unlock_irqrestore(&eisa_irq_lock, flags);
 
 	generic_handle_irq(irq);
-   
+
 	spin_lock_irqsave(&eisa_irq_lock, flags);
 	/* unmask */
         if (irq & 8) {
@@ -254,44 +254,44 @@ static struct irqaction irq2_action = {
 static void init_eisa_pic(void)
 {
 	unsigned long flags;
-	
+
 	spin_lock_irqsave(&eisa_irq_lock, flags);
 
 	eisa_out8(0xff, 0x21); /* mask during init */
 	eisa_out8(0xff, 0xa1); /* mask during init */
-	
+
 	/* master pic */
-	eisa_out8(0x11,0x20); /* ICW1 */   
-	eisa_out8(0x00,0x21); /* ICW2 */   
-	eisa_out8(0x04,0x21); /* ICW3 */   
-	eisa_out8(0x01,0x21); /* ICW4 */   
-	eisa_out8(0x40,0x20); /* OCW2 */   
-	
+	eisa_out8(0x11, 0x20); /* ICW1 */
+	eisa_out8(0x00, 0x21); /* ICW2 */
+	eisa_out8(0x04, 0x21); /* ICW3 */
+	eisa_out8(0x01, 0x21); /* ICW4 */
+	eisa_out8(0x40, 0x20); /* OCW2 */
+
 	/* slave pic */
-	eisa_out8(0x11,0xa0); /* ICW1 */   
-	eisa_out8(0x08,0xa1); /* ICW2 */   
-        eisa_out8(0x02,0xa1); /* ICW3 */   
-	eisa_out8(0x01,0xa1); /* ICW4 */   
-	eisa_out8(0x40,0xa0); /* OCW2 */   
-        
+	eisa_out8(0x11, 0xa0); /* ICW1 */
+	eisa_out8(0x08, 0xa1); /* ICW2 */
+	eisa_out8(0x02, 0xa1); /* ICW3 */
+	eisa_out8(0x01, 0xa1); /* ICW4 */
+	eisa_out8(0x40, 0xa0); /* OCW2 */
+
 	udelay(100);
-	
-	slave_mask = 0xff; 
-	master_mask = 0xfb; 
+
+	slave_mask = 0xff;
+	master_mask = 0xfb;
 	eisa_out8(slave_mask, 0xa1); /* OCW1 */
 	eisa_out8(master_mask, 0x21); /* OCW1 */
-	
+
 	/* setup trig level */
 	EISA_DBG("EISA edge/level %04x\n", eisa_irq_level);
-	
+
 	eisa_out8(eisa_irq_level&0xff, 0x4d0); /* Set all irq's to edge  */
-	eisa_out8((eisa_irq_level >> 8) & 0xff, 0x4d1); 
-	
+	eisa_out8((eisa_irq_level >> 8) & 0xff, 0x4d1);
+
 	EISA_DBG("pic0 mask %02x\n", eisa_in8(0x21));
 	EISA_DBG("pic1 mask %02x\n", eisa_in8(0xa1));
 	EISA_DBG("pic0 edge/level %02x\n", eisa_in8(0x4d0));
 	EISA_DBG("pic1 edge/level %02x\n", eisa_in8(0x4d1));
-	
+
 	spin_unlock_irqrestore(&eisa_irq_lock, flags);
 }
 
@@ -305,7 +305,7 @@ static int __init eisa_probe(struct parisc_device *dev)
 
 	char *name = is_mongoose(dev) ? "Mongoose" : "Wax";
 
-	printk(KERN_INFO "%s EISA Adapter found at 0x%08lx\n", 
+	printk(KERN_INFO "%s EISA Adapter found at 0x%08lx\n",
 		name, (unsigned long)dev->hpa.start);
 
 	eisa_dev.hba.dev = dev;
@@ -336,14 +336,14 @@ static int __init eisa_probe(struct parisc_device *dev)
 		printk(KERN_ERR "EISA: request_irq failed!\n");
 		return result;
 	}
-	
+
 	/* Reserve IRQ2 */
 	setup_irq(2, &irq2_action);
 	for (i = 0; i < 16; i++) {
 		irq_set_chip_and_handler(i, &eisa_interrupt_type,
 					 handle_simple_irq);
 	}
-	
+
 	EISA_bus = 1;
 
 	if (dev->num_addrs) {
@@ -375,7 +375,7 @@ static int __init eisa_probe(struct parisc_device *dev)
 			return -1;
 		}
 	}
-	
+
 	return 0;
 }
 
@@ -404,7 +404,7 @@ void eisa_make_irq_level(int num)
 {
 	if (eisa_irq_configured& (1<<num)) {
 		printk(KERN_WARNING
-		       "IRQ %d polarity configured twice (last to level)\n", 
+		       "IRQ %d polarity configured twice (last to level)\n",
 		       num);
 	}
 	eisa_irq_level |= (1<<num); /* set the corresponding bit */
@@ -414,7 +414,7 @@ void eisa_make_irq_level(int num)
 void eisa_make_irq_edge(int num)
 {
 	if (eisa_irq_configured& (1<<num)) {
-		printk(KERN_WARNING 
+		printk(KERN_WARNING
 		       "IRQ %d polarity configured twice (last to edge)\n",
 		       num);
 	}
@@ -430,18 +430,18 @@ static int __init eisa_irq_setup(char *str)
 	EISA_DBG("IRQ setup\n");
 	while (cur != NULL) {
 		char *pe;
-		
+
 		val = (int) simple_strtoul(cur, &pe, 0);
 		if (val > 15 || val < 0) {
 			printk(KERN_ERR "eisa: EISA irq value are 0-15\n");
 			continue;
 		}
-		if (val == 2) { 
+		if (val == 2) {
 			val = 9;
 		}
 		eisa_make_irq_edge(val); /* clear the corresponding bit */
 		EISA_DBG("setting IRQ %d to edge-triggered mode\n", val);
-		
+
 		if ((cur = strchr(cur, ','))) {
 			cur++;
 		} else {
-- 
GitLab


From af640d17ecee1f82a949b580cc4a3e8f29c377b9 Mon Sep 17 00:00:00 2001
From: Arvind Yadav <arvind.yadav.cs@gmail.com>
Date: Wed, 18 Jan 2017 13:41:31 +0530
Subject: [PATCH 214/898] parisc: eisa: Fix resource leaks in error paths

Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/parisc/eisa.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/parisc/eisa.c b/drivers/parisc/eisa.c
index 59edee911f7d..7e2f6d5a6aaf 100644
--- a/drivers/parisc/eisa.c
+++ b/drivers/parisc/eisa.c
@@ -334,7 +334,7 @@ static int __init eisa_probe(struct parisc_device *dev)
 	result = request_irq(dev->irq, eisa_irq, IRQF_SHARED, "EISA", &eisa_dev);
 	if (result) {
 		printk(KERN_ERR "EISA: request_irq failed!\n");
-		return result;
+		goto error_release;
 	}
 
 	/* Reserve IRQ2 */
@@ -358,6 +358,11 @@ static int __init eisa_probe(struct parisc_device *dev)
 		}
 	}
 	eisa_eeprom_addr = ioremap_nocache(eisa_dev.eeprom_addr, HPEE_MAX_LENGTH);
+	if (!eisa_eeprom_addr) {
+		result = -ENOMEM;
+		printk(KERN_ERR "EISA: ioremap_nocache failed!\n");
+		goto error_free_irq;
+	}
 	result = eisa_enumerator(eisa_dev.eeprom_addr, &eisa_dev.hba.io_space,
 			&eisa_dev.hba.lmmio_space);
 	init_eisa_pic();
@@ -372,11 +377,20 @@ static int __init eisa_probe(struct parisc_device *dev)
 		eisa_dev.root.dma_mask = 0xffffffff; /* wild guess */
 		if (eisa_root_register (&eisa_dev.root)) {
 			printk(KERN_ERR "EISA: Failed to register EISA root\n");
-			return -1;
+			result = -ENOMEM;
+			goto error_iounmap;
 		}
 	}
 
 	return 0;
+
+error_iounmap:
+	iounmap(eisa_eeprom_addr);
+error_free_irq:
+	free_irq(dev->irq, &eisa_dev);
+error_release:
+	release_resource(&eisa_dev.hba.io_space);
+	return result;
 }
 
 static const struct parisc_device_id eisa_tbl[] = {
-- 
GitLab


From 09b871ffd4d8ddc005a9480fb69ff1897caaeb1f Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Sun, 29 Jan 2017 18:19:33 +0100
Subject: [PATCH 215/898] parisc: Define access_ok() as macro

Define access_ok() as macro instead of static function. This fixes build
warnings in code where the second parameter is given as unsigned long.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/uaccess.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 9a2aee1b90fc..fb4382c28259 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -32,11 +32,7 @@
  * that put_user is the same as __put_user, etc.
  */
 
-static inline long access_ok(int type, const void __user * addr,
-		unsigned long size)
-{
-	return 1;
-}
+#define access_ok(type, uaddr, size) (1)
 
 #define put_user __put_user
 #define get_user __get_user
-- 
GitLab


From e28f701b21ee4b4eb716e4717fa2aa78c28a8523 Mon Sep 17 00:00:00 2001
From: Arvind Yadav <arvind.yadav.cs@gmail.com>
Date: Thu, 2 Feb 2017 18:52:34 +0530
Subject: [PATCH 216/898] parisc: ccio-dma: Handle return NULL error from
 ioremap_nocache

Fix error paths and return -ENOMEM instead of '1'.

Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/parisc/ccio-dma.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 553ef8a5d588..b0558e2451b5 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -1539,7 +1539,7 @@ static int __init ccio_probe(struct parisc_device *dev)
 	ioc = kzalloc(sizeof(struct ioc), GFP_KERNEL);
 	if (ioc == NULL) {
 		printk(KERN_ERR MODULE_NAME ": memory allocation failure\n");
-		return 1;
+		return -ENOMEM;
 	}
 
 	ioc->name = dev->id.hversion == U2_IOA_RUNWAY ? "U2" : "UTurn";
@@ -1554,6 +1554,10 @@ static int __init ccio_probe(struct parisc_device *dev)
 
 	ioc->hw_path = dev->hw_path;
 	ioc->ioc_regs = ioremap_nocache(dev->hpa.start, 4096);
+	if (!ioc->ioc_regs) {
+		kfree(ioc);
+		return -ENOMEM;
+	}
 	ccio_ioc_init(ioc);
 	ccio_init_resources(ioc);
 	hppa_dma_ops = &ccio_ops;
-- 
GitLab


From 8351badf349b22b47c9696f54656db65d7834e42 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 8 Feb 2017 10:20:35 +0300
Subject: [PATCH 217/898] parisc: fix a printk

We want to do a pr_cont() here and not a pr_warn().

Fixes: b391667eb45a ("parisc: Report trap type as human readable string")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/mm/fault.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 1a0b4f63f0e9..c3f8d34a11cf 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -238,8 +238,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long code,
 		vma ? ',':'\n');
 
 	if (vma)
-		pr_warn(KERN_CONT " vm_start = 0x%08lx, vm_end = 0x%08lx\n",
-				vma->vm_start, vma->vm_end);
+		pr_cont(" vm_start = 0x%08lx, vm_end = 0x%08lx\n",
+			vma->vm_start, vma->vm_end);
 
 	show_regs(regs);
 }
-- 
GitLab


From ef470a60e10eb12635d7b84c9502cea3028d44e8 Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Mon, 20 Feb 2017 14:02:46 -0500
Subject: [PATCH 218/898] parisc: Remove flush_user_dcache_range and
 flush_user_icache_range

The functions flush_user_dcache_range() and flush_user_icache_range()
are only used by the parisc signal handling code.  This code only needs
to flush a couple of lines, so the threshold check is unnecessary
overhead.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/cacheflush.h |  2 --
 arch/parisc/kernel/cache.c           | 18 ------------------
 arch/parisc/kernel/signal.c          | 13 +++++++------
 3 files changed, 7 insertions(+), 26 deletions(-)

diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 7bd69bd43a01..19c9c3c5f267 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -27,8 +27,6 @@ void flush_user_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_page_asm(void *);
 void flush_kernel_icache_page(void *);
-void flush_user_dcache_range(unsigned long, unsigned long);
-void flush_user_icache_range(unsigned long, unsigned long);
 
 /* Cache flush operations */
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 977f0a4f5ecf..20b013cbd297 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -573,24 +573,6 @@ void flush_cache_mm(struct mm_struct *mm)
 	}
 }
 
-void
-flush_user_dcache_range(unsigned long start, unsigned long end)
-{
-	if ((end - start) < parisc_cache_flush_threshold)
-		flush_user_dcache_range_asm(start,end);
-	else
-		flush_data_cache();
-}
-
-void
-flush_user_icache_range(unsigned long start, unsigned long end)
-{
-	if ((end - start) < parisc_cache_flush_threshold)
-		flush_user_icache_range_asm(start,end);
-	else
-		flush_instruction_cache();
-}
-
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index e58925ac64d1..f6aaca27ac4e 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -232,6 +232,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs,
 	struct rt_sigframe __user *frame;
 	unsigned long rp, usp;
 	unsigned long haddr, sigframe_size;
+	unsigned long start, end;
 	int err = 0;
 #ifdef CONFIG_64BIT
 	struct compat_rt_sigframe __user * compat_frame;
@@ -299,10 +300,10 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs,
 	}
 #endif
 
-	flush_user_dcache_range((unsigned long) &frame->tramp[0],
-			   (unsigned long) &frame->tramp[TRAMP_SIZE]);
-	flush_user_icache_range((unsigned long) &frame->tramp[0],
-			   (unsigned long) &frame->tramp[TRAMP_SIZE]);
+	start = (unsigned long) &frame->tramp[0];
+	end = (unsigned long) &frame->tramp[TRAMP_SIZE];
+	flush_user_dcache_range_asm(start, end);
+	flush_user_icache_range_asm(start, end);
 
 	/* TRAMP Words 0-4, Length 5 = SIGRESTARTBLOCK_TRAMP
 	 * TRAMP Words 5-9, Length 4 = SIGRETURN_TRAMP
@@ -548,8 +549,8 @@ insert_restart_trampoline(struct pt_regs *regs)
 		WARN_ON(err);
 
 		/* flush data/instruction cache for new insns */
-		flush_user_dcache_range(start, end);
-		flush_user_icache_range(start, end);
+		flush_user_dcache_range_asm(start, end);
+		flush_user_icache_range_asm(start, end);
 
 		regs->gr[31] = regs->gr[30] + 8;
 		return;
-- 
GitLab


From 678a3bd1b3de6d2ebf604e7d708bc8150bb667e9 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 9 Feb 2017 22:22:13 -0500
Subject: [PATCH 219/898] tools/power turbostat: fix bugs in --add option

When --add was used more than once, overflowed buffers
caused some counters to be stored on top of others,
corrupting the results.  Simplify the code by simply
reserving space for up to 16 added counters per each
cpu, core, package.

Per-cpu added counters were being printed only per-core.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 88 ++++++++++++++++-----------
 1 file changed, 52 insertions(+), 36 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index f13f61b065c6..c7fadf0faa4b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -154,6 +154,7 @@ char *progname;
 
 cpu_set_t *cpu_present_set, *cpu_affinity_set;
 size_t cpu_present_setsize, cpu_affinity_setsize;
+#define MAX_ADDED_COUNTERS 16
 
 struct thread_data {
 	unsigned long long tsc;
@@ -166,7 +167,7 @@ struct thread_data {
 	unsigned int flags;
 #define CPU_IS_FIRST_THREAD_IN_CORE	0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
-	unsigned long long counter[1];
+	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *thread_even, *thread_odd;
 
 struct core_data {
@@ -175,7 +176,7 @@ struct core_data {
 	unsigned long long c7;
 	unsigned int core_temp_c;
 	unsigned int core_id;
-	unsigned long long counter[1];
+	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *core_even, *core_odd;
 
 struct pkg_data {
@@ -200,7 +201,7 @@ struct pkg_data {
 	unsigned int rapl_pkg_perf_status;	/* MSR_PKG_PERF_STATUS */
 	unsigned int rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
 	unsigned int pkg_temp_c;
-	unsigned long long counter[1];
+	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *package_even, *package_odd;
 
 #define ODD_COUNTERS thread_odd, core_odd, package_odd
@@ -228,9 +229,9 @@ struct msr_counter {
 };
 
 struct sys_counters {
-	unsigned int thread_counter_bytes;
-	unsigned int core_counter_bytes;
-	unsigned int package_counter_bytes;
+	unsigned int added_thread_counters;
+	unsigned int added_core_counters;
+	unsigned int added_package_counters;
 	struct msr_counter *tp;
 	struct msr_counter *cp;
 	struct msr_counter *pp;
@@ -374,12 +375,6 @@ void print_header(void)
 
 	if (do_nhm_cstates)
 		outp += sprintf(outp, "\tCPU%%c1");
-	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "\tCPU%%c3");
-	if (do_nhm_cstates)
-		outp += sprintf(outp, "\tCPU%%c6");
-	if (do_snb_cstates)
-		outp += sprintf(outp, "\tCPU%%c7");
 
 	for (mp = sys.tp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
@@ -392,6 +387,14 @@ void print_header(void)
 		}
 	}
 
+	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
+		outp += sprintf(outp, "\tCPU%%c3");
+	if (do_nhm_cstates)
+		outp += sprintf(outp, "\tCPU%%c6");
+	if (do_snb_cstates)
+		outp += sprintf(outp, "\tCPU%%c7");
+
+
 	if (do_dts)
 		outp += sprintf(outp, "\tCoreTmp");
 
@@ -635,20 +638,11 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (do_smi)
 		outp += sprintf(outp, "\t%d", t->smi_count);
 
+	/* C1 */
 	if (do_nhm_cstates)
 		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc);
 
-	/* print per-core data only for 1st thread in core */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
-		goto done;
-
-	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc);
-	if (do_nhm_cstates)
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc);
-	if (do_snb_cstates)
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
-
+	/* Added counters */
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
@@ -656,12 +650,23 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "\t0x%016llx", t->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
-			outp += sprintf(outp, "\t%8lld", t->counter[i]);
+			outp += sprintf(outp, "\t%lld", t->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
 			outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/t->tsc);
 		}
 	}
 
+	/* print per-core data only for 1st thread in core */
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+		goto done;
+
+	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc);
+	if (do_nhm_cstates)
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc);
+	if (do_snb_cstates)
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
+
 
 	if (do_dts)
 		outp += sprintf(outp, "\t%d", c->core_temp_c);
@@ -673,7 +678,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "\t0x%016llx", c->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
-			outp += sprintf(outp, "\t%8lld", c->counter[i]);
+			outp += sprintf(outp, "\t%lld", c->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
 			outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/t->tsc);
 		}
@@ -770,7 +775,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "\t0x%016llx", p->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
-			outp += sprintf(outp, "\t%8lld", p->counter[i]);
+			outp += sprintf(outp, "\t%lld", p->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
 			outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/t->tsc);
 		}
@@ -1036,7 +1041,6 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	p->gfx_rc6_ms = 0;
 	p->gfx_mhz = 0;
-
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
 		t->counter[i] = 0;
 
@@ -3662,7 +3666,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
 	int i;
 
 	*t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
-		topo.num_packages, sizeof(struct thread_data) + sys.thread_counter_bytes);
+		topo.num_packages, sizeof(struct thread_data));
 	if (*t == NULL)
 		goto error;
 
@@ -3671,14 +3675,14 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
 		(*t)[i].cpu_id = -1;
 
 	*c = calloc(topo.num_cores_per_pkg * topo.num_packages,
-		sizeof(struct core_data) + sys.core_counter_bytes);
+		sizeof(struct core_data));
 	if (*c == NULL)
 		goto error;
 
 	for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
 		(*c)[i].core_id = -1;
 
-	*p = calloc(topo.num_packages, sizeof(struct pkg_data) + sys.package_counter_bytes);
+	*p = calloc(topo.num_packages, sizeof(struct pkg_data));
 	if (*p == NULL)
 		goto error;
 
@@ -3901,24 +3905,36 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width,
 	switch (scope) {
 
 	case SCOPE_CPU:
-		sys.thread_counter_bytes += 64;
 		msrp->next = sys.tp;
 		sys.tp = msrp;
-		sys.thread_counter_bytes += sizeof(unsigned long long);
+		sys.added_thread_counters++;
+		if (sys.added_thread_counters > MAX_ADDED_COUNTERS) {
+			fprintf(stderr, "exceeded max %d added thread counters\n",
+				MAX_ADDED_COUNTERS);
+			exit(-1);
+		}
 		break;
 
 	case SCOPE_CORE:
-		sys.core_counter_bytes += 64;
 		msrp->next = sys.cp;
 		sys.cp = msrp;
-		sys.core_counter_bytes += sizeof(unsigned long long);
+		sys.added_core_counters++;
+		if (sys.added_core_counters > MAX_ADDED_COUNTERS) {
+			fprintf(stderr, "exceeded max %d added core counters\n",
+				MAX_ADDED_COUNTERS);
+			exit(-1);
+		}
 		break;
 
 	case SCOPE_PACKAGE:
-		sys.package_counter_bytes += 64;
 		msrp->next = sys.pp;
 		sys.pp = msrp;
-		sys.package_counter_bytes += sizeof(unsigned long long);
+		sys.added_package_counters++;
+		if (sys.added_package_counters > MAX_ADDED_COUNTERS) {
+			fprintf(stderr, "exceeded max %d added package counters\n",
+				MAX_ADDED_COUNTERS);
+			exit(-1);
+		}
 		break;
 	}
 
-- 
GitLab


From 812db3f77b9a3f6ed59baf7a0d5c3fd8ec8ef86a Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 10 Feb 2017 00:25:41 -0500
Subject: [PATCH 220/898] tools/power turbostat: Add --show and --hide
 parameters

Add the "--show" and "--hide" cmdline parameters.

By default, turbostat shows all columns.

turbostat --hide counter_list
will continue showing all columns, except for those listed.

turbostat --show counter_list
will show _only_ the listed columns

These features work for built-in counters, and have no effect
on columns added with the --add parameter.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.8 |   4 +
 tools/power/x86/turbostat/turbostat.c | 463 +++++++++++++++++++-------
 2 files changed, 347 insertions(+), 120 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 03cb639b292e..e8fb1e02d121 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -47,6 +47,10 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 		default: delta
 .fi
 .PP
+\fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.
+.PP
+\fB--show column\fP show only the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.
+.PP
 \fB--Dump\fP displays the raw counter values.
 .PP
 \fB--debug\fP displays additional system configuration information.  Invoking this parameter
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index c7fadf0faa4b..fff280b50af0 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -52,7 +52,6 @@ unsigned int debug;
 unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int dump_only;
-unsigned int do_nhm_cstates;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
 unsigned int do_pc2;
@@ -72,24 +71,17 @@ unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
 unsigned int do_nhm_platform_info;
 unsigned int aperf_mperf_multiplier = 1;
-int do_irq = 1;
-int do_smi;
 double bclk;
 double base_hz;
 unsigned int has_base_hz;
 double tsc_tweak = 1.0;
-unsigned int show_pkg;
-unsigned int show_core;
-unsigned int show_cpu;
 unsigned int show_pkg_only;
 unsigned int show_core_only;
 char *output_buffer, *outp;
 unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
-unsigned int do_gfx_rc6_ms;
 unsigned long long  gfx_cur_rc6_ms;
-unsigned int do_gfx_mhz;
 unsigned int gfx_cur_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
@@ -226,6 +218,9 @@ struct msr_counter {
 	enum counter_type type;
 	enum counter_format format;
 	struct msr_counter *next;
+	unsigned int flags;
+#define	FLAGS_HIDE	(1 << 0)
+#define	FLAGS_SHOW	(1 << 1)
 };
 
 struct sys_counters {
@@ -341,39 +336,153 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 }
 
 /*
- * Example Format w/ field column widths:
- *
- *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 ThreadC CoreTmp  CoreCnt PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt PkgCnt
- * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
+ * Each string in this array is compared in --show and --hide cmdline.
+ * Thus, strings that are proper sub-sets must follow their more specific peers.
  */
+struct msr_counter bic[] = {
+	{ 0x0, "Package" },
+	{ 0x0, "Avg_MHz" },
+	{ 0x0, "Bzy_MHz" },
+	{ 0x0, "TSC_MHz" },
+	{ 0x0, "IRQ" },
+	{ 0x0, "SMI", 32, 0, FORMAT_DELTA, NULL},
+	{ 0x0, "Busy%" },
+	{ 0x0, "CPU%c1" },
+	{ 0x0, "CPU%c3" },
+	{ 0x0, "CPU%c6" },
+	{ 0x0, "CPU%c7" },
+	{ 0x0, "ThreadC" },
+	{ 0x0, "CoreTmp" },
+	{ 0x0, "CoreCnt" },
+	{ 0x0, "PkgTmp" },
+	{ 0x0, "GFX%rc6" },
+	{ 0x0, "GFXMHz" },
+	{ 0x0, "Pkg%pc2" },
+	{ 0x0, "Pkg%pc3" },
+	{ 0x0, "Pkg%pc6" },
+	{ 0x0, "Pkg%pc7" },
+	{ 0x0, "PkgWatt" },
+	{ 0x0, "CorWatt" },
+	{ 0x0, "GFXWatt" },
+	{ 0x0, "PkgCnt" },
+	{ 0x0, "RAMWatt" },
+	{ 0x0, "PKG_%" },
+	{ 0x0, "RAM_%" },
+	{ 0x0, "Pkg_J" },
+	{ 0x0, "Cor_J" },
+	{ 0x0, "GFX_J" },
+	{ 0x0, "RAM_J" },
+	{ 0x0, "Core" },
+	{ 0x0, "CPU" },
+};
+
+#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
+#define	BIC_Package	(1ULL << 0)
+#define	BIC_Avg_MHz	(1ULL << 1)
+#define	BIC_Bzy_MHz	(1ULL << 2)
+#define	BIC_TSC_MHz	(1ULL << 3)
+#define	BIC_IRQ		(1ULL << 4)
+#define	BIC_SMI		(1ULL << 5)
+#define	BIC_Busy	(1ULL << 6)
+#define	BIC_CPU_c1	(1ULL << 7)
+#define	BIC_CPU_c3	(1ULL << 8)
+#define	BIC_CPU_c6	(1ULL << 9)
+#define	BIC_CPU_c7	(1ULL << 10)
+#define	BIC_ThreadC	(1ULL << 11)
+#define	BIC_CoreTmp	(1ULL << 12)
+#define	BIC_CoreCnt	(1ULL << 13)
+#define	BIC_PkgTmp	(1ULL << 14)
+#define	BIC_GFX_rc6	(1ULL << 15)
+#define	BIC_GFXMHz	(1ULL << 16)
+#define	BIC_Pkgpc2	(1ULL << 17)
+#define	BIC_Pkgpc3	(1ULL << 18)
+#define	BIC_Pkgpc6	(1ULL << 19)
+#define	BIC_Pkgpc7	(1ULL << 20)
+#define	BIC_PkgWatt	(1ULL << 21)
+#define	BIC_CorWatt	(1ULL << 22)
+#define	BIC_GFXWatt	(1ULL << 23)
+#define	BIC_PkgCnt	(1ULL << 24)
+#define	BIC_RAMWatt	(1ULL << 27)
+#define	BIC_PKG__	(1ULL << 28)
+#define	BIC_RAM__	(1ULL << 29)
+#define	BIC_Pkg_J	(1ULL << 30)
+#define	BIC_Cor_J	(1ULL << 31)
+#define	BIC_GFX_J	(1ULL << 30)
+#define	BIC_RAM_J	(1ULL << 31)
+#define	BIC_Core	(1ULL << 32)
+#define	BIC_CPU		(1ULL << 33)
+
+unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
+unsigned long long bic_present;
+
+#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
+
+/*
+ * bic_lookup
+ * for all the strings in comma separate name_list,
+ * set the approprate bit in return value.
+ */
+unsigned long long bic_lookup(char *name_list)
+{
+	int i;
+	unsigned long long retval = 0;
+
+	while (name_list) {
+		char *comma;
+
+		comma = strchr(name_list, ',');
+
+		if (comma)
+			*comma = '\0';
+
+		for (i = 0; i < MAX_BIC; ++i) {
+			if (!strcmp(name_list, bic[i].name)) {
+				retval |= (1ULL << i);
+				break;
+			}
+		}
+		if (i == MAX_BIC) {
+			fprintf(stderr, "Invalid counter name: %s\n", name_list);
+			exit(-1);
+		}
+
+		name_list = comma;
+		if (name_list)
+			name_list++;
+
+	}
+	return retval;
+}
 
 void print_header(void)
 {
 	struct msr_counter *mp;
 
-	if (show_pkg)
+	if (DO_BIC(BIC_Package))
 		outp += sprintf(outp, "\tPackage");
-	if (show_core)
+	if (DO_BIC(BIC_Core))
 		outp += sprintf(outp, "\tCore");
-	if (show_cpu)
+	if (DO_BIC(BIC_CPU))
 		outp += sprintf(outp, "\tCPU");
-	if (has_aperf)
+	if (DO_BIC(BIC_Avg_MHz))
 		outp += sprintf(outp, "\tAvg_MHz");
-	if (has_aperf)
+	if (DO_BIC(BIC_Busy))
 		outp += sprintf(outp, "\tBusy%%");
-	if (has_aperf)
+	if (DO_BIC(BIC_Bzy_MHz))
 		outp += sprintf(outp, "\tBzy_MHz");
-	outp += sprintf(outp, "\tTSC_MHz");
+	if (DO_BIC(BIC_TSC_MHz))
+		outp += sprintf(outp, "\tTSC_MHz");
 
 	if (!debug)
 		goto done;
 
-	if (do_irq)
+	if (DO_BIC(BIC_IRQ))
 		outp += sprintf(outp, "\tIRQ");
-	if (do_smi)
+	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "\tSMI");
 
-	if (do_nhm_cstates)
+	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "\tCPU%%c1");
 
 	for (mp = sys.tp; mp; mp = mp->next) {
@@ -387,15 +496,15 @@ void print_header(void)
 		}
 	}
 
-	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
+	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
 		outp += sprintf(outp, "\tCPU%%c3");
-	if (do_nhm_cstates)
+	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "\tCPU%%c6");
-	if (do_snb_cstates)
+	if (DO_BIC(BIC_CPU_c7))
 		outp += sprintf(outp, "\tCPU%%c7");
 
 
-	if (do_dts)
+	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "\tCoreTmp");
 
 	for (mp = sys.cp; mp; mp = mp->next) {
@@ -409,13 +518,13 @@ void print_header(void)
 		}
 	}
 
-	if (do_ptm)
+	if (DO_BIC(BIC_PkgTmp))
 		outp += sprintf(outp, "\tPkgTmp");
 
-	if (do_gfx_rc6_ms)
+	if (DO_BIC(BIC_GFX_rc6))
 		outp += sprintf(outp, "\tGFX%%rc6");
 
-	if (do_gfx_mhz)
+	if (DO_BIC(BIC_GFXMHz))
 		outp += sprintf(outp, "\tGFXMHz");
 
 	if (do_skl_residency) {
@@ -440,30 +549,30 @@ void print_header(void)
 	}
 
 	if (do_rapl && !rapl_joules) {
-		if (do_rapl & RAPL_PKG)
+		if (DO_BIC(BIC_PkgWatt))
 			outp += sprintf(outp, "\tPkgWatt");
-		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
+		if (DO_BIC(BIC_CorWatt))
 			outp += sprintf(outp, "\tCorWatt");
-		if (do_rapl & RAPL_GFX)
+		if (DO_BIC(BIC_GFXWatt))
 			outp += sprintf(outp, "\tGFXWatt");
-		if (do_rapl & RAPL_DRAM)
+		if (DO_BIC(BIC_RAMWatt))
 			outp += sprintf(outp, "\tRAMWatt");
-		if (do_rapl & RAPL_PKG_PERF_STATUS)
+		if (DO_BIC(BIC_PKG__))
 			outp += sprintf(outp, "\tPKG_%%");
-		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+		if (DO_BIC(BIC_RAM__))
 			outp += sprintf(outp, "\tRAM_%%");
 	} else if (do_rapl && rapl_joules) {
-		if (do_rapl & RAPL_PKG)
+		if (DO_BIC(BIC_Pkg_J))
 			outp += sprintf(outp, "\tPkg_J");
-		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
+		if (DO_BIC(BIC_Cor_J))
 			outp += sprintf(outp, "\tCor_J");
-		if (do_rapl & RAPL_GFX)
+		if (DO_BIC(BIC_GFX_J))
 			outp += sprintf(outp, "\tGFX_J");
-		if (do_rapl & RAPL_DRAM)
+		if (DO_BIC(BIC_RAM_J))
 			outp += sprintf(outp, "\tRAM_J");
-		if (do_rapl & RAPL_PKG_PERF_STATUS)
+		if (DO_BIC(BIC_PKG__))
 			outp += sprintf(outp, "\tPKG_%%");
-		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+		if (DO_BIC(BIC_RAM__))
 			outp += sprintf(outp, "\tRAM_%%");
 	}
 	for (mp = sys.pp; mp; mp = mp->next) {
@@ -497,9 +606,9 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "mperf: %016llX\n", t->mperf);
 		outp += sprintf(outp, "c1: %016llX\n", t->c1);
 
-		if (do_irq)
+		if (DO_BIC(BIC_IRQ))
 			outp += sprintf(outp, "IRQ: %08X\n", t->irq_count);
-		if (do_smi)
+		if (DO_BIC(BIC_SMI))
 			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
 
 		for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
@@ -583,40 +692,37 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	/* topo columns, print blanks on 1st (average) line */
 	if (t == &average.threads) {
-		if (show_pkg)
+		if (DO_BIC(BIC_Package))
 			outp += sprintf(outp, "\t-");
-		if (show_core)
+		if (DO_BIC(BIC_Core))
 			outp += sprintf(outp, "\t-");
-		if (show_cpu)
+		if (DO_BIC(BIC_CPU))
 			outp += sprintf(outp, "\t-");
 	} else {
-		if (show_pkg) {
+		if (DO_BIC(BIC_Package)) {
 			if (p)
 				outp += sprintf(outp, "\t%d", p->package_id);
 			else
 				outp += sprintf(outp, "\t-");
 		}
-		if (show_core) {
+		if (DO_BIC(BIC_Core)) {
 			if (c)
 				outp += sprintf(outp, "\t%d", c->core_id);
 			else
 				outp += sprintf(outp, "\t-");
 		}
-		if (show_cpu)
+		if (DO_BIC(BIC_CPU))
 			outp += sprintf(outp, "\t%d", t->cpu_id);
 	}
 
-	/* Avg_MHz */
-	if (has_aperf)
+	if (DO_BIC(BIC_Avg_MHz))
 		outp += sprintf(outp, "\t%.0f",
 			1.0 / units * t->aperf / interval_float);
 
-	/* Busy% */
-	if (has_aperf)
+	if (DO_BIC(BIC_Busy))
 		outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
 
-	/* Bzy_MHz */
-	if (has_aperf) {
+	if (DO_BIC(BIC_Bzy_MHz)) {
 		if (has_base_hz)
 			outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf);
 		else
@@ -624,22 +730,22 @@ int format_counters(struct thread_data *t, struct core_data *c,
 				1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
 	}
 
-	/* TSC_MHz */
-	outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
+	if (DO_BIC(BIC_TSC_MHz))
+		outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
 
 	if (!debug)
 		goto done;
 
 	/* IRQ */
-	if (do_irq)
+	if (DO_BIC(BIC_IRQ))
 		outp += sprintf(outp, "\t%d", t->irq_count);
 
 	/* SMI */
-	if (do_smi)
+	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "\t%d", t->smi_count);
 
 	/* C1 */
-	if (do_nhm_cstates)
+	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc);
 
 	/* Added counters */
@@ -660,15 +766,14 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
+	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
 		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc);
-	if (do_nhm_cstates)
+	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc);
-	if (do_snb_cstates)
+	if (DO_BIC(BIC_CPU_c7))
 		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
 
-
-	if (do_dts)
+	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "\t%d", c->core_temp_c);
 
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
@@ -689,11 +794,11 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		goto done;
 
 	/* PkgTmp */
-	if (do_ptm)
+	if (DO_BIC(BIC_PkgTmp))
 		outp += sprintf(outp, "\t%d", p->pkg_temp_c);
 
 	/* GFXrc6 */
-	if (do_gfx_rc6_ms) {
+	if (DO_BIC(BIC_GFX_rc6)) {
 		if (p->gfx_rc6_ms == -1) {	/* detect GFX counter reset */
 			outp += sprintf(outp, "\t**.**");
 		} else {
@@ -703,7 +808,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	}
 
 	/* GFXMHz */
-	if (do_gfx_mhz)
+	if (DO_BIC(BIC_GFXMHz))
 		outp += sprintf(outp, "\t%d", p->gfx_mhz);
 
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
@@ -737,37 +842,27 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	else
 		fmt8 = "%6.0f**";
 
-	if (do_rapl && !rapl_joules) {
-		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float);
-		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
-			outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float);
-		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
-		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units / interval_float);
-		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
-		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-	} else if (do_rapl && rapl_joules) {
-		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, fmt8,
-					p->energy_pkg * rapl_energy_units);
-		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, fmt8,
-					p->energy_cores * rapl_energy_units);
-		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, fmt8,
-					p->energy_gfx * rapl_energy_units);
-		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, fmt8,
-					p->energy_dram * rapl_dram_energy_units);
-		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
-		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-	}
+	if (DO_BIC(BIC_PkgWatt))
+		outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float);
+	if (DO_BIC(BIC_CorWatt))
+		outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float);
+	if (DO_BIC(BIC_GFXWatt))
+		outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
+	if (DO_BIC(BIC_RAMWatt))
+		outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units / interval_float);
+	if (DO_BIC(BIC_Pkg_J))
+		outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units);
+	if (DO_BIC(BIC_Cor_J))
+		outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units);
+	if (DO_BIC(BIC_GFX_J))
+		outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units);
+	if (DO_BIC(BIC_RAM_J))
+		outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units);
+	if (DO_BIC(BIC_PKG__))
+		outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+	if (DO_BIC(BIC_RAM__))
+		outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
@@ -921,7 +1016,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 
 	old->c1 = new->c1 - old->c1;
 
-	if (has_aperf) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
 		if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
 			old->aperf = new->aperf - old->aperf;
 			old->mperf = new->mperf - old->mperf;
@@ -957,10 +1052,10 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 		old->mperf = 1;	/* divide by 0 protection */
 	}
 
-	if (do_irq)
+	if (DO_BIC(BIC_IRQ))
 		old->irq_count = new->irq_count - old->irq_count;
 
-	if (do_smi)
+	if (DO_BIC(BIC_SMI))
 		old->smi_count = new->smi_count - old->smi_count;
 
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
@@ -1217,7 +1312,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 retry:
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
-	if (has_aperf) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
 		unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
 
 		/*
@@ -1273,9 +1368,9 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		t->mperf = t->mperf * aperf_mperf_multiplier;
 	}
 
-	if (do_irq)
+	if (DO_BIC(BIC_IRQ))
 		t->irq_count = irqs_per_cpu[cpu];
-	if (do_smi) {
+	if (DO_BIC(BIC_SMI)) {
 		if (get_msr(cpu, MSR_SMI_COUNT, &msr))
 			return -5;
 		t->smi_count = msr & 0xFFFFFFFF;
@@ -1296,12 +1391,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
 
-	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) {
+	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) {
 		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
 			return -6;
 	}
 
-	if (do_nhm_cstates && !do_knl_cstates) {
+	if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) {
 		if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
 			return -7;
 	} else if (do_knl_cstates) {
@@ -1309,11 +1404,11 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -7;
 	}
 
-	if (do_snb_cstates)
+	if (DO_BIC(BIC_CPU_c7))
 		if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7))
 			return -8;
 
-	if (do_dts) {
+	if (DO_BIC(BIC_CoreTmp)) {
 		if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
 			return -9;
 		c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
@@ -1388,16 +1483,16 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -16;
 		p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
 	}
-	if (do_ptm) {
+	if (DO_BIC(BIC_PkgTmp)) {
 		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
 			return -17;
 		p->pkg_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
 
-	if (do_gfx_rc6_ms)
+	if (DO_BIC(BIC_GFX_rc6))
 		p->gfx_rc6_ms = gfx_cur_rc6_ms;
 
-	if (do_gfx_mhz)
+	if (DO_BIC(BIC_GFXMHz))
 		p->gfx_mhz = gfx_cur_mhz;
 
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
@@ -2155,10 +2250,10 @@ int snapshot_proc_sysfs_files(void)
 	if (snapshot_proc_interrupts())
 		return 1;
 
-	if (do_gfx_rc6_ms)
+	if (DO_BIC(BIC_GFX_rc6))
 		snapshot_gfx_rc6_ms();
 
-	if (do_gfx_mhz)
+	if (DO_BIC(BIC_GFXMHz))
 		snapshot_gfx_mhz();
 
 	return 0;
@@ -2794,15 +2889,39 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
 	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+			BIC_PRESENT(BIC_GFX_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+			BIC_PRESENT(BIC_GFXWatt);
+		}
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
+		if (rapl_joules)
+			BIC_PRESENT(BIC_Pkg_J);
+		else
+			BIC_PRESENT(BIC_PkgWatt);
 		break;
 	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
 	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		BIC_PRESENT(BIC_PKG__);
+		BIC_PRESENT(BIC_RAM__);
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+			BIC_PRESENT(BIC_RAM_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+			BIC_PRESENT(BIC_RAMWatt);
+		}
 		break;
 	case INTEL_FAM6_HASWELL_X:	/* HSX */
 	case INTEL_FAM6_BROADWELL_X:	/* BDX */
@@ -2811,17 +2930,55 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
 	case INTEL_FAM6_XEON_PHI_KNM:
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		BIC_PRESENT(BIC_PKG__);
+		BIC_PRESENT(BIC_RAM__);
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_RAM_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_RAMWatt);
+		}
 		break;
 	case INTEL_FAM6_SANDYBRIDGE_X:
 	case INTEL_FAM6_IVYBRIDGE_X:
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		BIC_PRESENT(BIC_PKG__);
+		BIC_PRESENT(BIC_RAM__);
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+			BIC_PRESENT(BIC_RAM_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+			BIC_PRESENT(BIC_RAMWatt);
+		}
 		break;
 	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
 	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
 		do_rapl = RAPL_PKG | RAPL_CORES;
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+		}
 		break;
 	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
+		BIC_PRESENT(BIC_PKG__);
+		BIC_PRESENT(BIC_RAM__);
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+			BIC_PRESENT(BIC_RAM_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+			BIC_PRESENT(BIC_RAMWatt);
+		}
 		break;
 	default:
 		return;
@@ -3398,8 +3555,17 @@ void process_cpuid()
 
 	__cpuid(0x6, eax, ebx, ecx, edx);
 	has_aperf = ecx & (1 << 0);
+	if (has_aperf) {
+		BIC_PRESENT(BIC_Avg_MHz);
+		BIC_PRESENT(BIC_Busy);
+		BIC_PRESENT(BIC_Bzy_MHz);
+	}
 	do_dts = eax & (1 << 0);
+	if (do_dts)
+		BIC_PRESENT(BIC_CoreTmp);
 	do_ptm = eax & (1 << 6);
+	if (do_ptm)
+		BIC_PRESENT(BIC_PkgTmp);
 	has_hwp = eax & (1 << 7);
 	has_hwp_notify = eax & (1 << 8);
 	has_hwp_activity_window = eax & (1 << 9);
@@ -3497,8 +3663,21 @@ void process_cpuid()
 	if (has_aperf)
 		aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
 
-	do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
+	BIC_PRESENT(BIC_IRQ);
+	BIC_PRESENT(BIC_TSC_MHz);
+
+	if (probe_nhm_msrs(family, model)) {
+		do_nhm_platform_info = 1;
+		BIC_PRESENT(BIC_CPU_c1);
+		BIC_PRESENT(BIC_CPU_c3);
+		BIC_PRESENT(BIC_CPU_c6);
+		BIC_PRESENT(BIC_SMI);
+	}
 	do_snb_cstates = has_snb_msrs(family, model);
+
+	if (do_snb_cstates)
+		BIC_PRESENT(BIC_CPU_c7);
+
 	do_irtl_snb = has_snb_msrs(family, model);
 	do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
 	do_pc3 = (pkg_cstate_limit >= PCL__3);
@@ -3522,9 +3701,11 @@ void process_cpuid()
 	if (has_skl_msrs(family, model))
 		calculate_tsc_tweak();
 
-	do_gfx_rc6_ms = !access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK);
+	if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
+		BIC_PRESENT(BIC_GFX_rc6);
 
-	do_gfx_mhz = !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK);
+	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+		BIC_PRESENT(BIC_GFXMHz);
 
 	return;
 }
@@ -3583,7 +3764,7 @@ void topology_probe()
 	topo.max_cpu_num = 0;
 	for_all_proc_cpus(count_cpus);
 	if (!summary_only && topo.num_cpus > 1)
-		show_cpu = 1;
+		BIC_PRESENT(BIC_CPU);
 
 	if (debug > 1)
 		fprintf(outf, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
@@ -3644,14 +3825,14 @@ void topology_probe()
 		fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
 			max_core_id, topo.num_cores_per_pkg);
 	if (debug && !summary_only && topo.num_cores_per_pkg > 1)
-		show_core = 1;
+		BIC_PRESENT(BIC_Core);
 
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
 		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
 			max_package_id, topo.num_packages);
 	if (debug && !summary_only && topo.num_packages > 1)
-		show_pkg = 1;
+		BIC_PRESENT(BIC_Package);
 
 	topo.num_threads_per_core = max_siblings;
 	if (debug > 1)
@@ -4045,6 +4226,40 @@ void parse_add_command(char *add_command)
 		exit(1);
 	}
 }
+/*
+ * HIDE_LIST - hide this list of counters, show the rest [default]
+ * SHOW_LIST - show this list of counters, hide the rest
+ */
+enum show_hide_mode { SHOW_LIST, HIDE_LIST } global_show_hide_mode = HIDE_LIST;
+
+int shown;
+/*
+ * parse_show_hide() - process cmdline to set default counter action
+ */
+void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
+{
+	/*
+	 * --show: show only those specified
+	 *  The 1st invocation will clear and replace the enabled mask
+	 *  subsequent invocations can add to it.
+	 */
+	if (new_mode == SHOW_LIST) {
+		if (shown == 0)
+			bic_enabled = bic_lookup(optarg);
+		else
+			bic_enabled |= bic_lookup(optarg);
+		shown = 1;
+
+		return;
+	}
+
+	/*
+	 * --hide: do not show those specified
+	 *  multiple invocations simply clear more bits in enabled mask
+	 */
+	bic_enabled &= ~bic_lookup(optarg);
+}
+
 void cmdline(int argc, char **argv)
 {
 	int opt;
@@ -4055,10 +4270,12 @@ void cmdline(int argc, char **argv)
 		{"debug",	no_argument,		0, 'd'},
 		{"interval",	required_argument,	0, 'i'},
 		{"help",	no_argument,		0, 'h'},
+		{"hide",	required_argument,	0, 'H'},	// meh, -h taken by --help
 		{"Joules",	no_argument,		0, 'J'},
 		{"out",		required_argument,	0, 'o'},
 		{"Package",	no_argument,		0, 'p'},
 		{"processor",	no_argument,		0, 'p'},
+		{"show",	required_argument,	0, 's'},
 		{"Summary",	no_argument,		0, 'S'},
 		{"TCC",		required_argument,	0, 'T'},
 		{"version",	no_argument,		0, 'v' },
@@ -4079,6 +4296,9 @@ void cmdline(int argc, char **argv)
 		case 'd':
 			debug++;
 			break;
+		case 'H':
+			parse_show_hide(optarg, HIDE_LIST);
+			break;
 		case 'h':
 		default:
 			help();
@@ -4109,6 +4329,9 @@ void cmdline(int argc, char **argv)
 		case 'p':
 			show_core_only++;
 			break;
+		case 's':
+			parse_show_hide(optarg, SHOW_LIST);
+			break;
 		case 'S':
 			summary_only++;
 			break;
-- 
GitLab


From cf4cbe5314884c3123fe4ca137e9d750b6e2b8c9 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sun, 1 Jan 2017 13:08:33 -0500
Subject: [PATCH 221/898] tools/power turbostat: BYT does not have
 MSR_MISC_PWR_MGMT

and so --debug fails with:

turbostat: msr 1 offset 0x1aa read failed: Input/output error

It seems that baytrail, and airmont do not have this MSR.
It is included in subsequent Goldmont Atom.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index fff280b50af0..fdf0273465fa 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -70,6 +70,7 @@ unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
 unsigned int do_nhm_platform_info;
+unsigned int no_MSR_MISC_PWR_MGMT;
 unsigned int aperf_mperf_multiplier = 1;
 double bclk;
 double base_hz;
@@ -330,7 +331,7 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 	retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset);
 
 	if (retval != sizeof *msr)
-		err(-1, "msr %d offset 0x%llx read failed", cpu, (unsigned long long)offset);
+		err(-1, "cpu%d: msr offset 0x%llx read failed", cpu, (unsigned long long)offset);
 
 	return 0;
 }
@@ -2384,6 +2385,8 @@ void check_permissions()
  * MSR_PLATFORM_INFO               0x000000ce
  * MSR_NHM_SNB_PKG_CST_CFG_CTL     0x000000e2
  *
+ * MSR_MISC_PWR_MGMT               0x000001aa
+ *
  * MSR_PKG_C3_RESIDENCY            0x000003f8
  * MSR_PKG_C6_RESIDENCY            0x000003f9
  * MSR_CORE_C3_RESIDENCY           0x000003fc
@@ -2440,11 +2443,13 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		pkg_cstate_limits = skx_pkg_cstate_limits;
 		break;
 	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+		no_MSR_MISC_PWR_MGMT = 1;
 	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
 		pkg_cstate_limits = slv_pkg_cstate_limits;
 		break;
 	case INTEL_FAM6_ATOM_AIRMONT:	/* AMT */
 		pkg_cstate_limits = amt_pkg_cstate_limits;
+		no_MSR_MISC_PWR_MGMT = 1;
 		break;
 	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI */
 	case INTEL_FAM6_XEON_PHI_KNM:
@@ -3481,6 +3486,9 @@ void decode_misc_pwr_mgmt_msr(void)
 	if (!do_nhm_platform_info)
 		return;
 
+	if (no_MSR_MISC_PWR_MGMT)
+		return;
+
 	if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
 		fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB %sable-OOB)\n",
 			base_cpu, msr,
@@ -4061,7 +4069,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 4.16 24 Dec 2016"
+	fprintf(outf, "turbostat version 4.17 1 Jan 2017"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
-- 
GitLab


From 71616c8e936a6dd541f0627d7bf4ff09971d8ccb Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Jan 2017 22:37:48 -0500
Subject: [PATCH 222/898] tools/power turbostat: decode Baytrail CC6 and MC6
 demotion configuration

with --debug, see:

cpu0: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x00000000 (DISable-CC6-Demotion)
cpu0: MSR_MC6_DEMOTION_POLICY_CONFIG: 0x00000000 (DISable-MC6-Demotion)

Note that the hardware default is to enable demotion,
and Linux started clearing these registers in 3.17.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 42 +++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index fdf0273465fa..1b762f67e3e2 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3262,6 +3262,27 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	return 0;
 }
 
+/*
+ * SLV client has supporet for unique MSRs:
+ *
+ * MSR_CC6_DEMOTION_POLICY_CONFIG
+ * MSR_MC6_DEMOTION_POLICY_CONFIG
+ */
+
+int has_slv_msrs(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_MERRIFIELD:
+	case INTEL_FAM6_ATOM_MOOREFIELD:
+		return 1;
+	}
+	return 0;
+}
+
 /*
  * HSW adds support for additional MSRs:
  *
@@ -3496,6 +3517,24 @@ void decode_misc_pwr_mgmt_msr(void)
 			msr & (1 << 1) ? "EN" : "DIS",
 			msr & (1 << 8) ? "EN" : "DIS");
 }
+/*
+ * Decode MSR_CC6_DEMOTION_POLICY_CONFIG, MSR_MC6_DEMOTION_POLICY_CONFIG
+ *
+ * This MSRs are present on Silvermont processors,
+ * Intel Atom processor E3000 series (Baytrail), and friends.
+ */
+void decode_c6_demotion_policy_msr(void)
+{
+	unsigned long long msr;
+
+	if (!get_msr(base_cpu, MSR_CC6_DEMOTION_POLICY_CONFIG, &msr))
+		fprintf(outf, "cpu%d: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-CC6-Demotion)\n",
+			base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
+
+	if (!get_msr(base_cpu, MSR_MC6_DEMOTION_POLICY_CONFIG, &msr))
+		fprintf(outf, "cpu%d: MSR_MC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-MC6-Demotion)\n",
+			base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
+}
 
 void process_cpuid()
 {
@@ -3700,6 +3739,9 @@ void process_cpuid()
 	if (debug)
 		decode_misc_pwr_mgmt_msr();
 
+	if (debug && has_slv_msrs(family, model))
+		decode_c6_demotion_policy_msr();
+
 	rapl_probe(family, model);
 	perf_limit_reasons_probe(family, model);
 
-- 
GitLab


From 8f6196c192f6393823e632bfb927ff1572369875 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Jan 2017 22:40:23 -0500
Subject: [PATCH 223/898] tools/power turbostat: Baytrail: remove debug line in
 quiet mode

Without --debug, a debug line was printed on Baytrail:

SLM BCLK: 83.3 Mhz

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 1b762f67e3e2..9b35c9bb0489 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3388,7 +3388,8 @@ double slm_bclk(void)
 	}
 	freq = slm_freq_table[i];
 
-	fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
+	if (debug)
+		fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
 
 	return freq;
 }
-- 
GitLab


From f2642888476d7faefa9695bbebb2abbaeb3685d8 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Jan 2017 23:13:15 -0500
Subject: [PATCH 224/898] tools/power turbostat: update
 MSR_PKG_CST_CONFIG_CONTROL decoding

AMT value 0 is unlimited, not PC0

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9b35c9bb0489..aedfaddbad30 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1534,7 +1534,7 @@ int nhm_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV,
 int snb_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCL__8, PCL__9, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-- 
GitLab


From dc7ffefdcc28a45214aa707fdc3df6a5e611ba09 Mon Sep 17 00:00:00 2001
From: Oleg Drokin <green@linuxhacker.ru>
Date: Sun, 19 Feb 2017 16:35:59 -0500
Subject: [PATCH 225/898] staging/lustre/lnet: Fix allocation size for
 sv_cpt_data

This is unbreaking another of those "stealth" janitor
patches that got in and subtly broke some things.

sv_cpt_data is a pointer to pointer, so need to
dereference it twice to allocate the correct structure size.

Fixes: 9899cb68c6c2 ("Staging: lustre: rpc: Use sizeof type *pointer instead of sizeof type.")
CC: Sandhya Bankar <bankarsandhya512@gmail.com>
Cc: stable <stable@vger.kernel.org> # 4.7+
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/lustre/lnet/selftest/rpc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/lustre/lnet/selftest/rpc.c b/drivers/staging/lustre/lnet/selftest/rpc.c
index 92cd4113cf75..87fe366f8f70 100644
--- a/drivers/staging/lustre/lnet/selftest/rpc.c
+++ b/drivers/staging/lustre/lnet/selftest/rpc.c
@@ -255,7 +255,7 @@ srpc_service_init(struct srpc_service *svc)
 	svc->sv_shuttingdown = 0;
 
 	svc->sv_cpt_data = cfs_percpt_alloc(lnet_cpt_table(),
-					    sizeof(*svc->sv_cpt_data));
+					    sizeof(**svc->sv_cpt_data));
 	if (!svc->sv_cpt_data)
 		return -ENOMEM;
 
-- 
GitLab


From f4082c6f28a8e77dcb694c6f23de9e533251051d Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sat, 18 Feb 2017 02:20:36 +0300
Subject: [PATCH 226/898] staging: bcm2835/mmal-vchiq: unlock on error in
 buffer_from_host()

We should unlock before returning on this error path.

Fixes: 7b3ad5abf027 ("staging: Import the BCM2835 MMAL-based V4L2 camera driver.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/media/platform/bcm2835/mmal-vchiq.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/media/platform/bcm2835/mmal-vchiq.c b/drivers/staging/media/platform/bcm2835/mmal-vchiq.c
index f0639ee6c8b9..fdfb6a620a43 100644
--- a/drivers/staging/media/platform/bcm2835/mmal-vchiq.c
+++ b/drivers/staging/media/platform/bcm2835/mmal-vchiq.c
@@ -397,8 +397,10 @@ buffer_from_host(struct vchiq_mmal_instance *instance,
 
 	/* get context */
 	msg_context = get_msg_context(instance);
-	if (msg_context == NULL)
-		return -ENOMEM;
+	if (!msg_context) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
 
 	/* store bulk message context for when data arrives */
 	msg_context->u.bulk.instance = instance;
@@ -454,6 +456,7 @@ buffer_from_host(struct vchiq_mmal_instance *instance,
 
 	vchi_service_release(instance->handle);
 
+unlock:
 	mutex_unlock(&instance->bulk_mutex);
 
 	return ret;
-- 
GitLab


From 6cf1bf636a067eb308cb3a8322b9d6b1844a075d Mon Sep 17 00:00:00 2001
From: Michael Zoran <mzoran@crowfest.net>
Date: Sat, 18 Feb 2017 03:22:01 -0800
Subject: [PATCH 227/898] staging: vchiq_2835_arm: Make cache-line-size a
 required DT property

The original github source allowed for the cache-line-size property
to be missing.  Since recent firmwares also require this property,
it makes sense to always require it in the driver as well.

If the cache-line-size property is missing, then the driver probe
should fail as no dev since the kernel and dt may be out of sync.
The fix is to add a check for the return value of of_property_read_u32.

Changes V2:
	1. Add error message if cache-line-size is missing.
	2. Simple check for non-zero return value from
	   of_property_read_u32.

Signed-off-by: Michael Zoran <mzoran@crowfest.net>
Acked-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../vc04_services/interface/vchiq_arm/vchiq_2835_arm.c    | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
index e6241fb5cfa6..3aeffcb9c87e 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
@@ -121,8 +121,14 @@ int vchiq_platform_init(struct platform_device *pdev, VCHIQ_STATE_T *state)
 	if (err < 0)
 		return err;
 
-	(void)of_property_read_u32(dev->of_node, "cache-line-size",
+	err = of_property_read_u32(dev->of_node, "cache-line-size",
 				   &g_cache_line_size);
+
+	if (err) {
+		dev_err(dev, "Missing cache-line-size property\n");
+		return -ENODEV;
+	}
+
 	g_fragments_size = 2 * g_cache_line_size;
 
 	/* Allocate space for the channels in coherent memory */
-- 
GitLab


From bd4e2d2907fa23a11d46217064ecf80470ddae10 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Wed, 22 Feb 2017 22:06:32 -0800
Subject: [PATCH 228/898] target: Fix NULL dereference during LUN lookup +
 active I/O shutdown

When transport_clear_lun_ref() is shutting down a se_lun via
configfs with new I/O in-flight, it's possible to trigger a
NULL pointer dereference in transport_lookup_cmd_lun() due
to the fact percpu_ref_get() doesn't do any __PERCPU_REF_DEAD
checking before incrementing lun->lun_ref.count after
lun->lun_ref has switched to atomic_t mode.

This results in a NULL pointer dereference as LUN shutdown
code in core_tpg_remove_lun() continues running after the
existing ->release() -> core_tpg_lun_ref_release() callback
completes, and clears the RCU protected se_lun->lun_se_dev
pointer.

During the OOPs, the state of lun->lun_ref in the process
which triggered the NULL pointer dereference looks like
the following on v4.1.y stable code:

struct se_lun {
  lun_link_magic = 4294932337,
  lun_status = TRANSPORT_LUN_STATUS_FREE,

  .....

  lun_se_dev = 0x0,
  lun_sep = 0x0,

  .....

  lun_ref = {
    count = {
      counter = 1
    },
    percpu_count_ptr = 3,
    release = 0xffffffffa02fa1e0 <core_tpg_lun_ref_release>,
    confirm_switch = 0x0,
    force_atomic = false,
    rcu = {
      next = 0xffff88154fa1a5d0,
      func = 0xffffffff8137c4c0 <percpu_ref_switch_to_atomic_rcu>
    }
  }
}

To address this bug, use percpu_ref_tryget_live() to ensure
once __PERCPU_REF_DEAD is visable on all CPUs and ->lun_ref
has switched to atomic_t, all new I/Os will fail to obtain
a new lun->lun_ref reference.

Also use an explicit percpu_ref_kill_and_confirm() callback
to block on ->lun_ref_comp to allow the first stage and
associated RCU grace period to complete, and then block on
->lun_ref_shutdown waiting for the final percpu_ref_put()
to drop the last reference via transport_lun_remove_cmd()
before continuing with core_tpg_remove_lun() shutdown.

Reported-by: Rob Millner <rlm@daterainc.com>
Tested-by: Rob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Tested-by: Vaibhav Tandon <vst@datera.io>
Cc: Vaibhav Tandon <vst@datera.io>
Tested-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c    | 10 +++++++--
 drivers/target/target_core_tpg.c       |  3 ++-
 drivers/target/target_core_transport.c | 31 +++++++++++++++++++++++++-
 include/target/target_core_base.h      |  1 +
 4 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index cb7047d66afc..c754ae33bf7b 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -78,12 +78,16 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 					&deve->read_bytes);
 
 		se_lun = rcu_dereference(deve->se_lun);
+
+		if (!percpu_ref_tryget_live(&se_lun->lun_ref)) {
+			se_lun = NULL;
+			goto out_unlock;
+		}
+
 		se_cmd->se_lun = rcu_dereference(deve->se_lun);
 		se_cmd->pr_res_key = deve->pr_res_key;
 		se_cmd->orig_fe_lun = unpacked_lun;
 		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
-
-		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
 
 		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
@@ -97,6 +101,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 			goto ref_dev;
 		}
 	}
+out_unlock:
 	rcu_read_unlock();
 
 	if (!se_lun) {
@@ -815,6 +820,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	xcopy_lun = &dev->xcopy_lun;
 	rcu_assign_pointer(xcopy_lun->lun_se_dev, dev);
 	init_completion(&xcopy_lun->lun_ref_comp);
+	init_completion(&xcopy_lun->lun_shutdown_comp);
 	INIT_LIST_HEAD(&xcopy_lun->lun_deve_list);
 	INIT_LIST_HEAD(&xcopy_lun->lun_dev_link);
 	mutex_init(&xcopy_lun->lun_tg_pt_md_mutex);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index d99752c6cd60..2744251178ad 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -445,7 +445,7 @@ static void core_tpg_lun_ref_release(struct percpu_ref *ref)
 {
 	struct se_lun *lun = container_of(ref, struct se_lun, lun_ref);
 
-	complete(&lun->lun_ref_comp);
+	complete(&lun->lun_shutdown_comp);
 }
 
 int core_tpg_register(
@@ -571,6 +571,7 @@ struct se_lun *core_tpg_alloc_lun(
 	lun->lun_link_magic = SE_LUN_LINK_MAGIC;
 	atomic_set(&lun->lun_acl_count, 0);
 	init_completion(&lun->lun_ref_comp);
+	init_completion(&lun->lun_shutdown_comp);
 	INIT_LIST_HEAD(&lun->lun_deve_list);
 	INIT_LIST_HEAD(&lun->lun_dev_link);
 	atomic_set(&lun->lun_tg_pt_secondary_offline, 0);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index efb9e6f38201..434d9d693989 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2700,10 +2700,39 @@ void target_wait_for_sess_cmds(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(target_wait_for_sess_cmds);
 
+static void target_lun_confirm(struct percpu_ref *ref)
+{
+	struct se_lun *lun = container_of(ref, struct se_lun, lun_ref);
+
+	complete(&lun->lun_ref_comp);
+}
+
 void transport_clear_lun_ref(struct se_lun *lun)
 {
-	percpu_ref_kill(&lun->lun_ref);
+	/*
+	 * Mark the percpu-ref as DEAD, switch to atomic_t mode, drop
+	 * the initial reference and schedule confirm kill to be
+	 * executed after one full RCU grace period has completed.
+	 */
+	percpu_ref_kill_and_confirm(&lun->lun_ref, target_lun_confirm);
+	/*
+	 * The first completion waits for percpu_ref_switch_to_atomic_rcu()
+	 * to call target_lun_confirm after lun->lun_ref has been marked
+	 * as __PERCPU_REF_DEAD on all CPUs, and switches to atomic_t
+	 * mode so that percpu_ref_tryget_live() lookup of lun->lun_ref
+	 * fails for all new incoming I/O.
+	 */
 	wait_for_completion(&lun->lun_ref_comp);
+	/*
+	 * The second completion waits for percpu_ref_put_many() to
+	 * invoke ->release() after lun->lun_ref has switched to
+	 * atomic_t mode, and lun->lun_ref.count has reached zero.
+	 *
+	 * At this point all target-core lun->lun_ref references have
+	 * been dropped via transport_lun_remove_cmd(), and it's safe
+	 * to proceed with the remaining LUN shutdown.
+	 */
+	wait_for_completion(&lun->lun_shutdown_comp);
 }
 
 static bool
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index d7336f3c6b60..16d3be8395be 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -730,6 +730,7 @@ struct se_lun {
 	struct config_group	lun_group;
 	struct se_port_stat_grps port_stat_grps;
 	struct completion	lun_ref_comp;
+	struct completion	lun_shutdown_comp;
 	struct percpu_ref	lun_ref;
 	struct list_head	lun_dev_link;
 	struct hlist_node	link;
-- 
GitLab


From 17c61ad66f2e09a9014ab2d4e1f04c8294427db1 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 23 Feb 2017 21:26:31 -0800
Subject: [PATCH 229/898] iscsi-target: Fix early login failure statistics
 misses

Due to the long standing checks in iscsit_snmp_get_tiqn()
that assume conn->sess->tpg dereference of tpg->tpg_tiqn
for iscsit_collect_login_stats() usage, some of the early
login failure cases like ISCSI_LOGIN_STATUS_TGT_FORBIDDEN
where not getting incremented, due to sess->tpg assignment
happening later in iscsi_login_zero_tsih_s2().

Instead, use the earlier conn->tpg assignment done by
iscsi_target_locate_portal() -> iscsit_get_tpg_from_np()
so the existing counters are incremented correctly for
the various early login failure cases.

Also, go ahead and drop the old rate limiting check in
iscsit_collect_login_stats(), so we get the true number
of failed login attempts in the existing statistics.

Reported-by: Ryan Stiles <ras@datera.io>
Cc: Ryan Stiles <ras@datera.io>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target_util.c | 38 ++----------------------
 1 file changed, 2 insertions(+), 36 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index f46eadffec07..cc5958882431 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1378,33 +1378,6 @@ int tx_data(
 	return iscsit_do_tx_data(conn, &c);
 }
 
-static bool sockaddr_equal(struct sockaddr_storage *x, struct sockaddr_storage *y)
-{
-	switch (x->ss_family) {
-	case AF_INET: {
-		struct sockaddr_in *sinx = (struct sockaddr_in *)x;
-		struct sockaddr_in *siny = (struct sockaddr_in *)y;
-		if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr)
-			return false;
-		if (sinx->sin_port != siny->sin_port)
-			return false;
-		break;
-	}
-	case AF_INET6: {
-		struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x;
-		struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y;
-		if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr))
-			return false;
-		if (sinx->sin6_port != siny->sin6_port)
-			return false;
-		break;
-	}
-	default:
-		return false;
-	}
-	return true;
-}
-
 void iscsit_collect_login_stats(
 	struct iscsi_conn *conn,
 	u8 status_class,
@@ -1421,13 +1394,6 @@ void iscsit_collect_login_stats(
 	ls = &tiqn->login_stats;
 
 	spin_lock(&ls->lock);
-	if (sockaddr_equal(&conn->login_sockaddr, &ls->last_intr_fail_sockaddr) &&
-	    ((get_jiffies_64() - ls->last_fail_time) < 10)) {
-		/* We already have the failure info for this login */
-		spin_unlock(&ls->lock);
-		return;
-	}
-
 	if (status_class == ISCSI_STATUS_CLS_SUCCESS)
 		ls->accepts++;
 	else if (status_class == ISCSI_STATUS_CLS_REDIRECT) {
@@ -1472,10 +1438,10 @@ struct iscsi_tiqn *iscsit_snmp_get_tiqn(struct iscsi_conn *conn)
 {
 	struct iscsi_portal_group *tpg;
 
-	if (!conn || !conn->sess)
+	if (!conn)
 		return NULL;
 
-	tpg = conn->sess->tpg;
+	tpg = conn->tpg;
 	if (!tpg)
 		return NULL;
 
-- 
GitLab


From c87ba9c49c1fa86261448b09c5f1b2223bf7efd9 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@daterainc.com>
Date: Thu, 19 Jan 2017 15:45:57 -0800
Subject: [PATCH 230/898] target: Add counters for ABORT_TASK success + failure

This patch introduces two counters for ABORT_TASK success +
failure under:

   /sys/kernel/config/target/core/$HBA/$DEV/statistics/scsi_tgt_dev/

that are useful for diagnosing various backend device latency
and front fabric issues.

Normally when folks see alot of aborts_complete happening,
it means the backend device I/O completion latency is high,
and not returning completions fast enough before host side
timeouts trigger.

And normally when folks see alot of aborts_no_task, it means
completions are being posted by target-core into fabric driver
code, but the responses aren't making it back to the host.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_stat.c | 18 ++++++++++++++++++
 drivers/target/target_core_tmr.c  |  2 ++
 include/target/target_core_base.h |  2 ++
 3 files changed, 22 insertions(+)

diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index be380e4acfcd..8038255b21e8 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -158,12 +158,28 @@ static ssize_t target_stat_tgt_resets_show(struct config_item *item,
 			atomic_long_read(&to_stat_tgt_dev(item)->num_resets));
 }
 
+static ssize_t target_stat_tgt_aborts_complete_show(struct config_item *item,
+		char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%lu\n",
+			atomic_long_read(&to_stat_tgt_dev(item)->aborts_complete));
+}
+
+static ssize_t target_stat_tgt_aborts_no_task_show(struct config_item *item,
+		char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%lu\n",
+			atomic_long_read(&to_stat_tgt_dev(item)->aborts_no_task));
+}
+
 CONFIGFS_ATTR_RO(target_stat_tgt_, inst);
 CONFIGFS_ATTR_RO(target_stat_tgt_, indx);
 CONFIGFS_ATTR_RO(target_stat_tgt_, num_lus);
 CONFIGFS_ATTR_RO(target_stat_tgt_, status);
 CONFIGFS_ATTR_RO(target_stat_tgt_, non_access_lus);
 CONFIGFS_ATTR_RO(target_stat_tgt_, resets);
+CONFIGFS_ATTR_RO(target_stat_tgt_, aborts_complete);
+CONFIGFS_ATTR_RO(target_stat_tgt_, aborts_no_task);
 
 static struct configfs_attribute *target_stat_scsi_tgt_dev_attrs[] = {
 	&target_stat_tgt_attr_inst,
@@ -172,6 +188,8 @@ static struct configfs_attribute *target_stat_scsi_tgt_dev_attrs[] = {
 	&target_stat_tgt_attr_status,
 	&target_stat_tgt_attr_non_access_lus,
 	&target_stat_tgt_attr_resets,
+	&target_stat_tgt_attr_aborts_complete,
+	&target_stat_tgt_attr_aborts_no_task,
 	NULL,
 };
 
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index a806d9bca3d2..dce1e1b47316 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -190,6 +190,7 @@ void core_tmr_abort_task(
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
 				" ref_tag: %llu\n", ref_tag);
 		tmr->response = TMR_FUNCTION_COMPLETE;
+		atomic_long_inc(&dev->aborts_complete);
 		return;
 	}
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
@@ -197,6 +198,7 @@ void core_tmr_abort_task(
 	printk("ABORT_TASK: Sending TMR_TASK_DOES_NOT_EXIST for ref_tag: %lld\n",
 			tmr->ref_task_tag);
 	tmr->response = TMR_TASK_DOES_NOT_EXIST;
+	atomic_long_inc(&dev->aborts_no_task);
 }
 
 static void core_tmr_drain_tmr_list(
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 16d3be8395be..49ce5bc9912f 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -766,6 +766,8 @@ struct se_device {
 	u32			dev_index;
 	u64			creation_time;
 	atomic_long_t		num_resets;
+	atomic_long_t		aborts_complete;
+	atomic_long_t		aborts_no_task;
 	atomic_long_t		num_cmds;
 	atomic_long_t		read_bytes;
 	atomic_long_t		write_bytes;
-- 
GitLab


From 9bd829041b704e5e501ad5f5a9374a63426763fd Mon Sep 17 00:00:00 2001
From: George Cherian <george.cherian@cavium.com>
Date: Wed, 15 Feb 2017 12:42:19 +0000
Subject: [PATCH 231/898] crypto: cavium - Fix couple of static checker errors

Fix the following smatch errors
cptvf_reqmanager.c:333 do_post_process() warn: variable dereferenced
before check 'cptvf'
cptvf_main.c:825 cptvf_remove() error: we previously assumed 'cptvf'
could be null

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: George Cherian <george.cherian@cavium.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/cavium/cpt/cptvf_main.c       | 4 +++-
 drivers/crypto/cavium/cpt/cptvf_reqmanager.c | 4 ++--
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/crypto/cavium/cpt/cptvf_main.c b/drivers/crypto/cavium/cpt/cptvf_main.c
index aac2966ff8d9..e50872e666d6 100644
--- a/drivers/crypto/cavium/cpt/cptvf_main.c
+++ b/drivers/crypto/cavium/cpt/cptvf_main.c
@@ -815,8 +815,10 @@ static void cptvf_remove(struct pci_dev *pdev)
 {
 	struct cpt_vf *cptvf = pci_get_drvdata(pdev);
 
-	if (!cptvf)
+	if (!cptvf) {
 		dev_err(&pdev->dev, "Invalid CPT-VF device\n");
+		return;
+	}
 
 	/* Convey DOWN to PF */
 	if (cptvf_send_vf_down(cptvf)) {
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
index 7f57f30f8863..169e66231bcf 100644
--- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -330,8 +330,8 @@ void do_post_process(struct cpt_vf *cptvf, struct cpt_info_buffer *info)
 {
 	struct pci_dev *pdev = cptvf->pdev;
 
-	if (!info || !cptvf) {
-		dev_err(&pdev->dev, "Input params are incorrect for post processing\n");
+	if (!info) {
+		dev_err(&pdev->dev, "incorrect cpt_info_buffer for post processing\n");
 		return;
 	}
 
-- 
GitLab


From d80388eca1b476125755a811676f76f138bbbe28 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 17 Feb 2017 15:57:43 +0000
Subject: [PATCH 232/898] crypto: cavium - fix leak on curr if curr->head fails
 to be allocated

The exit path when curr->head cannot be allocated fails to kfree the
earlier allocated curr.  Fix this by kfree'ing it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/cavium/cpt/cptvf_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/crypto/cavium/cpt/cptvf_main.c b/drivers/crypto/cavium/cpt/cptvf_main.c
index e50872e666d6..6ffc740c7431 100644
--- a/drivers/crypto/cavium/cpt/cptvf_main.c
+++ b/drivers/crypto/cavium/cpt/cptvf_main.c
@@ -242,6 +242,7 @@ static int alloc_command_queues(struct cpt_vf *cptvf,
 			if (!curr->head) {
 				dev_err(&pdev->dev, "Command Q (%d) chunk (%d) allocation failed\n",
 					i, queue->nchunks);
+				kfree(curr);
 				goto cmd_qfail;
 			}
 
-- 
GitLab


From f7f9482e370981ebeeeac30bbdb9960807e332ee Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 24 Feb 2017 11:27:38 +0100
Subject: [PATCH 233/898] crypto: atmel - CRYPTO_DEV_ATMEL_TDES and
 CRYPTO_DEV_ATMEL_SHA should depend on HAS_DMA

If NO_DMA=y:

    ERROR: "bad_dma_ops" [drivers/crypto/atmel-tdes.ko] undefined!
    ERROR: "bad_dma_ops" [drivers/crypto/atmel-sha.ko] undefined!

Add dependencies on HAS_DMA to fix this.

Fixes: ceb4afb3086ab08f ("crypto: atmel - refine Kconfig dependencies")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 2cac445b02fd..69f7fc0dc84d 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -445,6 +445,7 @@ config CRYPTO_DEV_ATMEL_AES
 
 config CRYPTO_DEV_ATMEL_TDES
 	tristate "Support for Atmel DES/TDES hw accelerator"
+	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_DES
 	select CRYPTO_BLKCIPHER
@@ -458,6 +459,7 @@ config CRYPTO_DEV_ATMEL_TDES
 
 config CRYPTO_DEV_ATMEL_SHA
 	tristate "Support for Atmel SHA hw accelerator"
+	depends on HAS_DMA
 	depends on ARCH_AT91 || COMPILE_TEST
 	select CRYPTO_HASH
 	help
-- 
GitLab


From c884b36816c131906038cdac4773f6c84a5bf3ee Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 24 Feb 2017 11:27:39 +0100
Subject: [PATCH 234/898] crypto: atmel - CRYPTO_DEV_MEDIATEK should depend on
 HAS_DMA

If NO_DMA=y:

    ERROR: "bad_dma_ops" [drivers/crypto/mediatek/mtk-crypto.ko] undefined!

Add a dependency on HAS_DMA to fix this.

Fixes: 7dee9f618790d0b7 ("crypto: mediatek - remove ARM dependencies")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 69f7fc0dc84d..a7ff6e5d0ba9 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -571,6 +571,7 @@ config CRYPTO_DEV_ROCKCHIP
 
 config CRYPTO_DEV_MEDIATEK
 	tristate "MediaTek's EIP97 Cryptographic Engine driver"
+	depends on HAS_DMA
 	depends on (ARM && ARCH_MEDIATEK) || COMPILE_TEST
 	select CRYPTO_AES
 	select CRYPTO_AEAD
-- 
GitLab


From 016df0abc56ec06d0c63c5318ef53e40738dea8b Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sun, 26 Feb 2017 12:22:35 +0800
Subject: [PATCH 235/898] crypto: api - Add crypto_requires_off helper

This patch adds crypto_requires_off which is an extension of
crypto_requires_sync for similar bits such as NEED_FALLBACK.

Cc: stable@vger.kernel.org #4.10
Suggested-by: Marcelo Cerri <marcelo.cerri@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/algapi.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index ebe4ded0c55d..436c4c2683c7 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -360,13 +360,18 @@ static inline struct crypto_alg *crypto_get_attr_alg(struct rtattr **tb,
 	return crypto_attr_alg(tb[1], type, mask);
 }
 
+static inline int crypto_requires_off(u32 type, u32 mask, u32 off)
+{
+	return (type ^ off) & mask & off;
+}
+
 /*
  * Returns CRYPTO_ALG_ASYNC if type/mask requires the use of sync algorithms.
  * Otherwise returns zero.
  */
 static inline int crypto_requires_sync(u32 type, u32 mask)
 {
-	return (type ^ CRYPTO_ALG_ASYNC) & mask & CRYPTO_ALG_ASYNC;
+	return crypto_requires_off(type, mask, CRYPTO_ALG_ASYNC);
 }
 
 noinline unsigned long __crypto_memneq(const void *a, const void *b, size_t size);
-- 
GitLab


From 89027579bc6c2febbcc9c2f9d5069adf71539e4b Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sun, 26 Feb 2017 12:24:10 +0800
Subject: [PATCH 236/898] crypto: xts - Propagate NEED_FALLBACK bit

When we're used as a fallback algorithm, we should propagate
the NEED_FALLBACK bit when searching for the underlying ECB mode.

This just happens to fix a hang too because otherwise the search
may end up loading the same module that triggered this XTS creation.

Cc: stable@vger.kernel.org #4.10
Fixes: f1c131b45410 ("crypto: xts - Convert to skcipher")
Reported-by: Harald Freudenberger <freude@linux.vnet.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/xts.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/crypto/xts.c b/crypto/xts.c
index 410a2e299085..baeb34dd8582 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -463,6 +463,7 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	struct xts_instance_ctx *ctx;
 	struct skcipher_alg *alg;
 	const char *cipher_name;
+	u32 mask;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
@@ -483,18 +484,19 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	ctx = skcipher_instance_ctx(inst);
 
 	crypto_set_skcipher_spawn(&ctx->spawn, skcipher_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->spawn, cipher_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+
+	mask = crypto_requires_off(algt->type, algt->mask,
+				   CRYPTO_ALG_NEED_FALLBACK |
+				   CRYPTO_ALG_ASYNC);
+
+	err = crypto_grab_skcipher(&ctx->spawn, cipher_name, 0, mask);
 	if (err == -ENOENT) {
 		err = -ENAMETOOLONG;
 		if (snprintf(ctx->name, CRYPTO_MAX_ALG_NAME, "ecb(%s)",
 			     cipher_name) >= CRYPTO_MAX_ALG_NAME)
 			goto err_free_inst;
 
-		err = crypto_grab_skcipher(&ctx->spawn, ctx->name, 0,
-					   crypto_requires_sync(algt->type,
-								algt->mask));
+		err = crypto_grab_skcipher(&ctx->spawn, ctx->name, 0, mask);
 	}
 
 	if (err)
-- 
GitLab


From 0328edc77d4f35014b35f32b46be0a7e16aae74f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 20 Feb 2017 08:59:16 +0100
Subject: [PATCH 237/898] mac80211: fix packet statistics for fast-RX

When adding per-CPU statistics, which added statistics back
to mac80211 for the fast-RX path, I evidently forgot to add
the "stats->packets++" line. The reason for that is likely
that I didn't see it since it's done in defragmentation for
the regular RX path.

Add the missing line to properly count received packets in
the fast-RX case.

Fixes: c9c5962b56c1 ("mac80211: enable collecting station statistics per-CPU")
Reported-by: Oren Givon <oren.givon@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 50ca3828b124..a8443d8bc233 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3880,6 +3880,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 	stats->last_rate = sta_stats_encode_rate(status);
 
 	stats->fragments++;
+	stats->packets++;
 
 	if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) {
 		stats->last_signal = status->signal;
-- 
GitLab


From a9e9200d8661c1a0be8c39f93deb383dc940de35 Mon Sep 17 00:00:00 2001
From: Matt Chen <matt.chen@intel.com>
Date: Sun, 22 Jan 2017 02:16:58 +0800
Subject: [PATCH 238/898] mac80211: flush delayed work when entering suspend

The issue was found when entering suspend and resume.
It triggers a warning in:
mac80211/key.c: ieee80211_enable_keys()
...
WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
             sdata->crypto_tx_tailroom_pending_dec);
...

It points out sdata->crypto_tx_tailroom_pending_dec isn't cleaned up successfully
in a delayed_work during suspend. Add a flush_delayed_work to fix it.

Cc: stable@vger.kernel.org
Signed-off-by: Matt Chen <matt.chen@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/pm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 28a3a0957c9e..76a8bcd8ef11 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -168,6 +168,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 			break;
 		}
 
+		flush_delayed_work(&sdata->dec_tailroom_needed_wk);
 		drv_remove_interface(local, sdata);
 	}
 
-- 
GitLab


From b7540d8f25c8034de7e4163fc23ac457bf057731 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 6 Feb 2017 15:28:42 +0200
Subject: [PATCH 239/898] mac80211: don't reorder frames with SN smaller than
 SSN

When RX aggregation starts, transmitter may continue send frames
with SN smaller than SSN until the AddBA response is received.
However, the reorder buffer is already initialized at this point,
which will cause the drop of such frames as duplicates since the
head SN of the reorder buffer is set to the SSN, which is bigger.

Cc: stable@vger.kernel.org
Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/agg-rx.c   |  1 +
 net/mac80211/rx.c       | 14 +++++++++++++-
 net/mac80211/sta_info.h |  6 ++++--
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 3b5fd4188f2a..58ad23a44109 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -398,6 +398,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 	tid_agg_rx->timeout = timeout;
 	tid_agg_rx->stored_mpdu_num = 0;
 	tid_agg_rx->auto_seq = auto_seq;
+	tid_agg_rx->started = false;
 	tid_agg_rx->reorder_buf_filtered = 0;
 	status = WLAN_STATUS_SUCCESS;
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index a8443d8bc233..28cc494a774d 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4,7 +4,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
+ * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -1034,6 +1034,18 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata
 	buf_size = tid_agg_rx->buf_size;
 	head_seq_num = tid_agg_rx->head_seq_num;
 
+	/*
+	 * If the current MPDU's SN is smaller than the SSN, it shouldn't
+	 * be reordered.
+	 */
+	if (unlikely(!tid_agg_rx->started)) {
+		if (ieee80211_sn_less(mpdu_seq_num, head_seq_num)) {
+			ret = false;
+			goto out;
+		}
+		tid_agg_rx->started = true;
+	}
+
 	/* frame with out of date sequence number */
 	if (ieee80211_sn_less(mpdu_seq_num, head_seq_num)) {
 		dev_kfree_skb(skb);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index dd06ef0b8861..15599c70a38f 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -189,6 +189,7 @@ struct tid_ampdu_tx {
  * @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and
  *	and ssn.
  * @removed: this session is removed (but might have been found due to RCU)
+ * @started: this session has started (head ssn or higher was received)
  *
  * This structure's lifetime is managed by RCU, assignments to
  * the array holding it must hold the aggregation mutex.
@@ -212,8 +213,9 @@ struct tid_ampdu_rx {
 	u16 ssn;
 	u16 buf_size;
 	u16 timeout;
-	bool auto_seq;
-	bool removed;
+	u8 auto_seq:1,
+	   removed:1,
+	   started:1;
 };
 
 /**
-- 
GitLab


From 8fbcfeb8a9cc803464d6c166e7991913711c612c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 25 Feb 2017 10:27:37 +0000
Subject: [PATCH 240/898] mac80211_hwsim: Replace bogus hrtimer clockid

mac80211_hwsim initializes a hrtimer with clockid
CLOCK_MONOTONIC_RAW. That's not supported.

Use CLOCK_MONOTONIC instead.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 1620a5d2757d..0889fc81ce9e 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2671,7 +2671,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	tasklet_hrtimer_init(&data->beacon_timer,
 			     mac80211_hwsim_beacon,
-			     CLOCK_MONOTONIC_RAW, HRTIMER_MODE_ABS);
+			     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	spin_lock_bh(&hwsim_radio_lock);
 	list_add_tail(&data->list, &hwsim_radios);
-- 
GitLab


From 890030d3c425f49abaa4acf60e20f288b599f980 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 22 Feb 2017 16:16:07 +0100
Subject: [PATCH 241/898] mac80211: don't handle filtered frames within a BA
 session

When running a BA session, the driver (or the hardware) already takes
care of retransmitting failed frames, since it has to keep the receiver
reorder window in sync.

Adding another layer of retransmit around that does not improve
anything. In fact, it can only lead to some strong reordering with huge
latency.

Cc: stable@vger.kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/status.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index a3af6e1bfd98..05ccd55b5d83 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -51,7 +51,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local,
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	int ac;
 
-	if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) {
+	if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER |
+			   IEEE80211_TX_CTL_AMPDU)) {
 		ieee80211_free_txskb(&local->hw, skb);
 		return;
 	}
-- 
GitLab


From d98937f4ea713d21e0fcc345919f86c877dd8d6f Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 20 Feb 2017 14:24:36 +0100
Subject: [PATCH 242/898] mac80211: fix power saving clients handling in
 iwlwifi

iwlwifi now supports RSS and can't let mac80211 track the
PS state based on the Rx frames since they can come out of
order. iwlwifi is now advertising AP_LINK_PS, and uses
explicit notifications to teach mac80211 about the PS state
of the stations and the PS poll / uAPSD trigger frames
coming our way from the peers.

Because of that, the TIM stopped being maintained in
mac80211. I tried to fix this in commit c68df2e7be0c
("mac80211: allow using AP_LINK_PS with mac80211-generated TIM IE")
but that was later reverted by Felix in commit 6c18a6b4e799
("Revert "mac80211: allow using AP_LINK_PS with mac80211-generated TIM IE")
since it broke drivers that do not implement set_tim.

Since none of the drivers that set AP_LINK_PS have the
set_tim() handler set besides iwlwifi, I can bail out in
__sta_info_recalc_tim if AP_LINK_PS AND .set_tim is not
implemented.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 4774e663a411..8bb99d299cda 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -688,7 +688,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending)
 	}
 
 	/* No need to do anything if the driver does all */
-	if (ieee80211_hw_check(&local->hw, AP_LINK_PS))
+	if (ieee80211_hw_check(&local->hw, AP_LINK_PS) && !local->ops->set_tim)
 		return;
 
 	if (sta->dead)
-- 
GitLab


From 2595d259b667114431501bae51b45d6656b987d1 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 20 Feb 2017 14:24:39 +0100
Subject: [PATCH 243/898] mac80211: shorten debug message

Tracing is limited to 100 characters and this message passes
the limit when there are a few buffered frames. Shorten it.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 8bb99d299cda..3323a2fb289b 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1264,7 +1264,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	sta_info_recalc_tim(sta);
 
 	ps_dbg(sdata,
-	       "STA %pM aid %d sending %d filtered/%d PS frames since STA not sleeping anymore\n",
+	       "STA %pM aid %d sending %d filtered/%d PS frames since STA woke up\n",
 	       sta->sta.addr, sta->sta.aid, filtered, buffered);
 
 	ieee80211_check_fast_xmit(sta);
-- 
GitLab


From 09e0a2fe102208cbaf39510b8b04dd524d7d2935 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 20 Feb 2017 14:24:38 +0100
Subject: [PATCH 244/898] mac80211: fix typo in debug print

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/agg-rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 58ad23a44109..4456559cb056 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -85,7 +85,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
 	ht_dbg(sta->sdata,
 	       "Rx BA session stop requested for %pM tid %u %s reason: %d\n",
 	       sta->sta.addr, tid,
-	       initiator == WLAN_BACK_RECIPIENT ? "recipient" : "inititator",
+	       initiator == WLAN_BACK_RECIPIENT ? "recipient" : "initiator",
 	       (int)reason);
 
 	if (drv_ampdu_action(local, sta->sdata, &params))
-- 
GitLab


From d825adb48cf9bf9e3f5cb1d927e2827f8c2abee4 Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Sun, 26 Feb 2017 16:15:21 +0900
Subject: [PATCH 245/898] xenbus: Remove duplicate inclusion of linux/init.h

This patch remove duplicate inclusion of linux/init.h in
xenbus_dev_frontend.c.
Confirm successfully compile after remove the line.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
---
 drivers/xen/xenbus/xenbus_dev_frontend.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 4d343eed08f5..1f4733b80c87 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -55,7 +55,6 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/miscdevice.h>
-#include <linux/init.h>
 
 #include <xen/xenbus.h>
 #include <xen/xen.h>
-- 
GitLab


From 6dbf5cea05a7098a69f294c96b6d76f08562cae5 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 24 Feb 2017 13:25:14 +0100
Subject: [PATCH 246/898] cpuidle: menu: Avoid taking spinlock for accessing
 QoS values

After commit 9908859acaa9 (cpuidle/menu: add per CPU PM QoS resume
latency consideration) the cpuidle menu governor calls
dev_pm_qos_read_value() on CPU devices to read the current resume
latency QoS constraint values for them.  That function takes a spinlock
to prevent the device's power.qos pointer from becoming NULL during
the access which is a problem for the RT patchset where spinlocks are
converted into mutexes and the idle loop stops working.

However, it is not even necessary for the menu governor to take
that spinlock, because the power.qos pointer accessed under it
cannot be modified during the access anyway.

For this reason, introduce a "raw" routine for accessing device
QoS resume latency constraints without locking and use it in the
menu governor.

Fixes: 9908859acaa9 (cpuidle/menu: add per CPU PM QoS resume latency consideration)
Acked-by: Alex Shi <alex.shi@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/qos.c         | 3 +--
 drivers/cpuidle/governors/menu.c | 2 +-
 include/linux/pm_qos.h           | 7 +++++++
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 58fcc758334e..73142d086240 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -108,8 +108,7 @@ s32 __dev_pm_qos_read_value(struct device *dev)
 {
 	lockdep_assert_held(&dev->power.lock);
 
-	return IS_ERR_OR_NULL(dev->power.qos) ?
-		0 : pm_qos_read_value(&dev->power.qos->resume_latency);
+	return dev_pm_qos_raw_read_value(dev);
 }
 
 /**
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 8d6d25c38c02..6d6f46e79d94 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -287,7 +287,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	unsigned int interactivity_req;
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
-	int resume_latency = dev_pm_qos_read_value(device);
+	int resume_latency = dev_pm_qos_raw_read_value(device);
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 0f65d36c2a75..5aba9f47899d 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -173,6 +173,12 @@ static inline s32 dev_pm_qos_requested_flags(struct device *dev)
 {
 	return dev->power.qos->flags_req->data.flr.flags;
 }
+
+static inline s32 dev_pm_qos_raw_read_value(struct device *dev)
+{
+	return IS_ERR_OR_NULL(dev->power.qos) ?
+		0 : pm_qos_read_value(&dev->power.qos->resume_latency);
+}
 #else
 static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev,
 							  s32 mask)
@@ -237,6 +243,7 @@ static inline void dev_pm_qos_hide_latency_tolerance(struct device *dev) {}
 
 static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; }
 static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; }
+static inline s32 dev_pm_qos_raw_read_value(struct device *dev) { return 0; }
 #endif
 
 #endif
-- 
GitLab


From 81d45bdf89135cd26dc7535c14a45db6cdd647fa Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 24 Feb 2017 00:25:28 +0100
Subject: [PATCH 247/898] PM / hibernate: Untangle power_down()

The power_down() routine in the core hibernation code is not exactly
straightforward (to put it lightly), so clean it up to make it avoid
invoking itself recursively, among other things.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/hibernate.c | 35 ++++++++++++++++-------------------
 1 file changed, 16 insertions(+), 19 deletions(-)

diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index b26dbc48c75b..f251b4d32913 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -608,6 +608,22 @@ static void power_down(void)
 {
 #ifdef CONFIG_SUSPEND
 	int error;
+
+	if (hibernation_mode == HIBERNATION_SUSPEND) {
+		error = suspend_devices_and_enter(PM_SUSPEND_MEM);
+		if (error) {
+			hibernation_mode = hibernation_ops ?
+						HIBERNATION_PLATFORM :
+						HIBERNATION_SHUTDOWN;
+		} else {
+			/* Restore swap signature. */
+			error = swsusp_unmark();
+			if (error)
+				pr_err("PM: Swap will be unusable! Try swapon -a.\n");
+
+			return;
+		}
+	}
 #endif
 
 	switch (hibernation_mode) {
@@ -620,25 +636,6 @@ static void power_down(void)
 		if (pm_power_off)
 			kernel_power_off();
 		break;
-#ifdef CONFIG_SUSPEND
-	case HIBERNATION_SUSPEND:
-		error = suspend_devices_and_enter(PM_SUSPEND_MEM);
-		if (error) {
-			if (hibernation_ops)
-				hibernation_mode = HIBERNATION_PLATFORM;
-			else
-				hibernation_mode = HIBERNATION_SHUTDOWN;
-			power_down();
-		}
-		/*
-		 * Restore swap signature.
-		 */
-		error = swsusp_unmark();
-		if (error)
-			printk(KERN_ERR "PM: Swap will be unusable! "
-			                "Try swapon -a.\n");
-		return;
-#endif
 	}
 	kernel_halt();
 	/*
-- 
GitLab


From 2872de1382a7c888fa69532eda25aa7342dfe748 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 24 Feb 2017 00:26:15 +0100
Subject: [PATCH 248/898] PM / hibernate: Define pr_fmt() and use pr_*()
 instead of printk()

Define a pr_fmt() for hibernate.c and convert all of the explicit
printk() calls into corresponding pr_*() so that they use the
pr_fmt() format.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/hibernate.c | 60 +++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 31 deletions(-)

diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f251b4d32913..8951d0d04810 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -10,6 +10,8 @@
  * This file is released under the GPLv2.
  */
 
+#define pr_fmt(fmt) "PM: " fmt
+
 #include <linux/export.h>
 #include <linux/suspend.h>
 #include <linux/syscalls.h>
@@ -104,7 +106,7 @@ EXPORT_SYMBOL(system_entering_hibernation);
 #ifdef CONFIG_PM_DEBUG
 static void hibernation_debug_sleep(void)
 {
-	printk(KERN_INFO "hibernation debug: Waiting for 5 seconds.\n");
+	pr_info("hibernation debug: Waiting for 5 seconds.\n");
 	mdelay(5000);
 }
 
@@ -250,10 +252,9 @@ void swsusp_show_speed(ktime_t start, ktime_t stop,
 		centisecs = 1;	/* avoid div-by-zero */
 	k = nr_pages * (PAGE_SIZE / 1024);
 	kps = (k * 100) / centisecs;
-	printk(KERN_INFO "PM: %s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n",
-			msg, k,
-			centisecs / 100, centisecs % 100,
-			kps / 1000, (kps % 1000) / 10);
+	pr_info("%s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n",
+		msg, k, centisecs / 100, centisecs % 100, kps / 1000,
+		(kps % 1000) / 10);
 }
 
 /**
@@ -271,8 +272,7 @@ static int create_image(int platform_mode)
 
 	error = dpm_suspend_end(PMSG_FREEZE);
 	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to power down, "
-			"aborting hibernation\n");
+		pr_err("Some devices failed to power down, aborting hibernation\n");
 		return error;
 	}
 
@@ -288,8 +288,7 @@ static int create_image(int platform_mode)
 
 	error = syscore_suspend();
 	if (error) {
-		printk(KERN_ERR "PM: Some system devices failed to power down, "
-			"aborting hibernation\n");
+		pr_err("Some system devices failed to power down, aborting hibernation\n");
 		goto Enable_irqs;
 	}
 
@@ -304,8 +303,8 @@ static int create_image(int platform_mode)
 	restore_processor_state();
 	trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
 	if (error)
-		printk(KERN_ERR "PM: Error %d creating hibernation image\n",
-			error);
+		pr_err("Error %d creating hibernation image\n", error);
+
 	if (!in_suspend) {
 		events_check_enabled = false;
 		clear_free_pages();
@@ -432,8 +431,7 @@ static int resume_target_kernel(bool platform_mode)
 
 	error = dpm_suspend_end(PMSG_QUIESCE);
 	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to power down, "
-			"aborting resume\n");
+		pr_err("Some devices failed to power down, aborting resume\n");
 		return error;
 	}
 
@@ -619,7 +617,7 @@ static void power_down(void)
 			/* Restore swap signature. */
 			error = swsusp_unmark();
 			if (error)
-				pr_err("PM: Swap will be unusable! Try swapon -a.\n");
+				pr_err("Swap will be unusable! Try swapon -a.\n");
 
 			return;
 		}
@@ -642,7 +640,7 @@ static void power_down(void)
 	 * Valid image is on the disk, if we continue we risk serious data
 	 * corruption after resume.
 	 */
-	printk(KERN_CRIT "PM: Please power down manually\n");
+	pr_crit("Power down manually\n");
 	while (1)
 		cpu_relax();
 }
@@ -652,7 +650,7 @@ static int load_image_and_restore(void)
 	int error;
 	unsigned int flags;
 
-	pr_debug("PM: Loading hibernation image.\n");
+	pr_debug("Loading hibernation image.\n");
 
 	lock_device_hotplug();
 	error = create_basic_memory_bitmaps();
@@ -664,7 +662,7 @@ static int load_image_and_restore(void)
 	if (!error)
 		hibernation_restore(flags & SF_PLATFORM_MODE);
 
-	printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n");
+	pr_err("Failed to load hibernation image, recovering.\n");
 	swsusp_free();
 	free_basic_memory_bitmaps();
  Unlock:
@@ -682,7 +680,7 @@ int hibernate(void)
 	bool snapshot_test = false;
 
 	if (!hibernation_available()) {
-		pr_debug("PM: Hibernation not available.\n");
+		pr_debug("Hibernation not available.\n");
 		return -EPERM;
 	}
 
@@ -700,9 +698,9 @@ int hibernate(void)
 		goto Exit;
 	}
 
-	printk(KERN_INFO "PM: Syncing filesystems ... ");
+	pr_info("Syncing filesystems ... \n");
 	sys_sync();
-	printk("done.\n");
+	pr_info("done.\n");
 
 	error = freeze_processes();
 	if (error)
@@ -728,7 +726,7 @@ int hibernate(void)
 		else
 		        flags |= SF_CRC32_MODE;
 
-		pr_debug("PM: writing image.\n");
+		pr_debug("Writing image.\n");
 		error = swsusp_write(flags);
 		swsusp_free();
 		if (!error) {
@@ -740,7 +738,7 @@ int hibernate(void)
 		in_suspend = 0;
 		pm_restore_gfp_mask();
 	} else {
-		pr_debug("PM: Image restored successfully.\n");
+		pr_debug("Image restored successfully.\n");
 	}
 
  Free_bitmaps:
@@ -748,7 +746,7 @@ int hibernate(void)
  Thaw:
 	unlock_device_hotplug();
 	if (snapshot_test) {
-		pr_debug("PM: Checking hibernation image\n");
+		pr_debug("Checking hibernation image\n");
 		error = swsusp_check();
 		if (!error)
 			error = load_image_and_restore();
@@ -812,10 +810,10 @@ static int software_resume(void)
 		goto Unlock;
 	}
 
-	pr_debug("PM: Checking hibernation image partition %s\n", resume_file);
+	pr_debug("Checking hibernation image partition %s\n", resume_file);
 
 	if (resume_delay) {
-		printk(KERN_INFO "Waiting %dsec before reading resume device...\n",
+		pr_info("Waiting %dsec before reading resume device ...\n",
 			resume_delay);
 		ssleep(resume_delay);
 	}
@@ -854,10 +852,10 @@ static int software_resume(void)
 	}
 
  Check_image:
-	pr_debug("PM: Hibernation image partition %d:%d present\n",
+	pr_debug("Hibernation image partition %d:%d present\n",
 		MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device));
 
-	pr_debug("PM: Looking for hibernation image.\n");
+	pr_debug("Looking for hibernation image.\n");
 	error = swsusp_check();
 	if (error)
 		goto Unlock;
@@ -876,7 +874,7 @@ static int software_resume(void)
 		goto Close_Finish;
 	}
 
-	pr_debug("PM: Preparing processes for restore.\n");
+	pr_debug("Preparing processes for restore.\n");
 	error = freeze_processes();
 	if (error)
 		goto Close_Finish;
@@ -889,7 +887,7 @@ static int software_resume(void)
 	/* For success case, the suspend path will release the lock */
  Unlock:
 	mutex_unlock(&pm_mutex);
-	pr_debug("PM: Hibernation image not present or could not be loaded.\n");
+	pr_debug("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
 	swsusp_close(FMODE_READ);
@@ -1013,7 +1011,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 		error = -EINVAL;
 
 	if (!error)
-		pr_debug("PM: Hibernation mode set to '%s'\n",
+		pr_debug("Hibernation mode set to '%s'\n",
 			 hibernation_modes[mode]);
 	unlock_system_sleep();
 	return error ? error : n;
@@ -1049,7 +1047,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
 	lock_system_sleep();
 	swsusp_resume_device = res;
 	unlock_system_sleep();
-	printk(KERN_INFO "PM: Starting manual resume from disk\n");
+	pr_info("Starting manual resume from disk\n");
 	noresume = 0;
 	software_resume();
 	return n;
-- 
GitLab


From 51be7a9a261ce18c520fb3928b168feb77522745 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 12 Jan 2017 23:36:32 +0200
Subject: [PATCH 249/898] virtio_mmio: expose header to userspace

It's handy for userspace emulators like QEMU.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_mmio.c           | 2 +-
 include/uapi/linux/Kbuild              | 1 +
 include/{ => uapi}/linux/virtio_mmio.h | 0
 3 files changed, 2 insertions(+), 1 deletion(-)
 rename include/{ => uapi}/linux/virtio_mmio.h (100%)

diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index c71fde5fe835..08357d70a891 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -70,7 +70,7 @@
 #include <linux/spinlock.h>
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
-#include <linux/virtio_mmio.h>
+#include <uapi/linux/virtio_mmio.h>
 #include <linux/virtio_ring.h>
 
 
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index f330ba4547cf..718fa73310e1 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -458,6 +458,7 @@ header-y += virtio_console.h
 header-y += virtio_gpu.h
 header-y += virtio_ids.h
 header-y += virtio_input.h
+header-y += virtio_mmio.h
 header-y += virtio_net.h
 header-y += virtio_pci.h
 header-y += virtio_ring.h
diff --git a/include/linux/virtio_mmio.h b/include/uapi/linux/virtio_mmio.h
similarity index 100%
rename from include/linux/virtio_mmio.h
rename to include/uapi/linux/virtio_mmio.h
-- 
GitLab


From 3a150df945b7408c27cad2c01a1638e8b14ac562 Mon Sep 17 00:00:00 2001
From: Chunyu Hu <chuhu@redhat.com>
Date: Wed, 22 Feb 2017 08:29:26 +0800
Subject: [PATCH 250/898] tracing: Fix code comment for ftrace_ops_get_func()

There is no function 'ftrace_ops_recurs_func' existing in the current code,
it was renamed to ftrace_ops_assist_func() in commit c68c0fa29341
("ftrace: Have ftrace_ops_get_func() handle RCU and PER_CPU flags too").
Update the comment to the correct function name.

Link: http://lkml.kernel.org/r/1487723366-14463-1-git-send-email-chuhu@redhat.com

Signed-off-by: Chunyu Hu <chuhu@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0c0609326391..fd84f2e30b6d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5487,7 +5487,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
  * Normally the mcount trampoline will call the ops->func, but there
  * are times that it should not. For example, if the ops does not
  * have its own recursion protection, then it should call the
- * ftrace_ops_recurs_func() instead.
+ * ftrace_ops_assist_func() instead.
  *
  * Returns the function that the trampoline should call for @ops.
  */
-- 
GitLab


From ff4dd73dd2b4806419f8ff65cbce11d5019548d0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 27 Feb 2017 17:15:28 +0100
Subject: [PATCH 251/898] mac80211_hwsim: check HWSIM_ATTR_RADIO_NAME length

Unfortunately, the nla policy was defined to have HWSIM_ATTR_RADIO_NAME
as an NLA_STRING, rather than NLA_NUL_STRING, so we can't use it as a
NUL-terminated string in the kernel.

Rather than break the API, kasprintf() the string to a new buffer to
guarantee NUL termination.

Reported-by: Andrew Zaborowski <andrew.zaborowski@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 28 ++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 0889fc81ce9e..50c219fb1a52 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3056,6 +3056,7 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2,
 static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 {
 	struct hwsim_new_radio_params param = { 0 };
+	const char *hwname = NULL;
 
 	param.reg_strict = info->attrs[HWSIM_ATTR_REG_STRICT_REG];
 	param.p2p_device = info->attrs[HWSIM_ATTR_SUPPORT_P2P_DEVICE];
@@ -3069,8 +3070,14 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	if (info->attrs[HWSIM_ATTR_NO_VIF])
 		param.no_vif = true;
 
-	if (info->attrs[HWSIM_ATTR_RADIO_NAME])
-		param.hwname = nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]);
+	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
+		hwname = kasprintf(GFP_KERNEL, "%.*s",
+				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		if (!hwname)
+			return -ENOMEM;
+		param.hwname = hwname;
+	}
 
 	if (info->attrs[HWSIM_ATTR_USE_CHANCTX])
 		param.use_chanctx = true;
@@ -3098,11 +3105,15 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	s64 idx = -1;
 	const char *hwname = NULL;
 
-	if (info->attrs[HWSIM_ATTR_RADIO_ID])
+	if (info->attrs[HWSIM_ATTR_RADIO_ID]) {
 		idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]);
-	else if (info->attrs[HWSIM_ATTR_RADIO_NAME])
-		hwname = (void *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]);
-	else
+	} else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
+		hwname = kasprintf(GFP_KERNEL, "%.*s",
+				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		if (!hwname)
+			return -ENOMEM;
+	} else
 		return -EINVAL;
 
 	spin_lock_bh(&hwsim_radio_lock);
@@ -3111,7 +3122,8 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 			if (data->idx != idx)
 				continue;
 		} else {
-			if (strcmp(hwname, wiphy_name(data->hw->wiphy)))
+			if (!hwname ||
+			    strcmp(hwname, wiphy_name(data->hw->wiphy)))
 				continue;
 		}
 
@@ -3122,10 +3134,12 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 		spin_unlock_bh(&hwsim_radio_lock);
 		mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy),
 					 info);
+		kfree(hwname);
 		return 0;
 	}
 	spin_unlock_bh(&hwsim_radio_lock);
 
+	kfree(hwname);
 	return -ENODEV;
 }
 
-- 
GitLab


From e3b56cdd4351f0e227d4d847eeadff4c82aef1b9 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 7 Feb 2017 15:49:50 +0800
Subject: [PATCH 252/898] vhost: try avoiding avail index access when getting
 descriptor

If last avail idx is not equal to cached avail idx, we're sure there's
still available buffers in the virtqueue so there's no need to re-read
avail idx. So let's skip this to avoid unnecessary userspace memory
access and memory barrier. Pktgen test show about 3% improvement on rx
pps.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 39 +++++++++++++++++++++++----------------
 1 file changed, 23 insertions(+), 16 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 8f99fe08de02..1f7e4e4e6f8e 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1930,25 +1930,32 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 
 	/* Check it isn't doing very strange things with descriptor numbers. */
 	last_avail_idx = vq->last_avail_idx;
-	if (unlikely(vhost_get_user(vq, avail_idx, &vq->avail->idx))) {
-		vq_err(vq, "Failed to access avail idx at %p\n",
-		       &vq->avail->idx);
-		return -EFAULT;
-	}
-	vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
 
-	if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
-		vq_err(vq, "Guest moved used index from %u to %u",
-		       last_avail_idx, vq->avail_idx);
-		return -EFAULT;
-	}
+	if (vq->avail_idx == vq->last_avail_idx) {
+		if (unlikely(vhost_get_user(vq, avail_idx, &vq->avail->idx))) {
+			vq_err(vq, "Failed to access avail idx at %p\n",
+				&vq->avail->idx);
+			return -EFAULT;
+		}
+		vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
 
-	/* If there's nothing new since last we looked, return invalid. */
-	if (vq->avail_idx == last_avail_idx)
-		return vq->num;
+		if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
+			vq_err(vq, "Guest moved used index from %u to %u",
+				last_avail_idx, vq->avail_idx);
+			return -EFAULT;
+		}
+
+		/* If there's nothing new since last we looked, return
+		 * invalid.
+		 */
+		if (vq->avail_idx == last_avail_idx)
+			return vq->num;
 
-	/* Only get avail ring entries after they have been exposed by guest. */
-	smp_rmb();
+		/* Only get avail ring entries after they have been
+		 * exposed by guest.
+		 */
+		smp_rmb();
+	}
 
 	/* Grab the next descriptor number they're advertising, and increment
 	 * the index we've seen. */
-- 
GitLab


From 5c34d002dcc7a6dd665a19d098b4f4cd5501ba1a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:18 +0100
Subject: [PATCH 253/898] virtio_pci: remove struct virtio_pci_vq_info

We don't really need struct virtio_pci_vq_info, as most field in there
are redundant:

 - the vq backpointer is not strictly neede to start with
 - the entry in the vqs list is not needed - the generic virtqueue already
   has list, we only need to check if it has a callback to get the same
   semantics
 - we can use a simple array to look up the MSI-X vec if needed.
 - That simple array now also duoble serves to replace the per_vq_vectors
   flag

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 117 +++++++++--------------------
 drivers/virtio/virtio_pci_common.h |  25 +-----
 drivers/virtio/virtio_pci_legacy.c |   6 +-
 drivers/virtio/virtio_pci_modern.c |   6 +-
 4 files changed, 39 insertions(+), 115 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 186cbab327b8..a33767318cbf 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -62,16 +62,13 @@ static irqreturn_t vp_config_changed(int irq, void *opaque)
 static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
 {
 	struct virtio_pci_device *vp_dev = opaque;
-	struct virtio_pci_vq_info *info;
 	irqreturn_t ret = IRQ_NONE;
-	unsigned long flags;
+	struct virtqueue *vq;
 
-	spin_lock_irqsave(&vp_dev->lock, flags);
-	list_for_each_entry(info, &vp_dev->virtqueues, node) {
-		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+	list_for_each_entry(vq, &vp_dev->vdev.vqs, list) {
+		if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED)
 			ret = IRQ_HANDLED;
 	}
-	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
 	return ret;
 }
@@ -167,55 +164,6 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
 	return err;
 }
 
-static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
-				     void (*callback)(struct virtqueue *vq),
-				     const char *name,
-				     u16 msix_vec)
-{
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
-	struct virtqueue *vq;
-	unsigned long flags;
-
-	/* fill out our structure that represents an active queue */
-	if (!info)
-		return ERR_PTR(-ENOMEM);
-
-	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, msix_vec);
-	if (IS_ERR(vq))
-		goto out_info;
-
-	info->vq = vq;
-	if (callback) {
-		spin_lock_irqsave(&vp_dev->lock, flags);
-		list_add(&info->node, &vp_dev->virtqueues);
-		spin_unlock_irqrestore(&vp_dev->lock, flags);
-	} else {
-		INIT_LIST_HEAD(&info->node);
-	}
-
-	vp_dev->vqs[index] = info;
-	return vq;
-
-out_info:
-	kfree(info);
-	return vq;
-}
-
-static void vp_del_vq(struct virtqueue *vq)
-{
-	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
-	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
-	unsigned long flags;
-
-	spin_lock_irqsave(&vp_dev->lock, flags);
-	list_del(&info->node);
-	spin_unlock_irqrestore(&vp_dev->lock, flags);
-
-	vp_dev->del_vq(info);
-	kfree(info);
-}
-
 /* the config->del_vqs() implementation */
 void vp_del_vqs(struct virtio_device *vdev)
 {
@@ -224,16 +172,15 @@ void vp_del_vqs(struct virtio_device *vdev)
 	int i;
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
-		if (vp_dev->per_vq_vectors) {
-			int v = vp_dev->vqs[vq->index]->msix_vector;
+		if (vp_dev->msix_vector_map) {
+			int v = vp_dev->msix_vector_map[vq->index];
 
 			if (v != VIRTIO_MSI_NO_VECTOR)
 				free_irq(pci_irq_vector(vp_dev->pci_dev, v),
 					vq);
 		}
-		vp_del_vq(vq);
+		vp_dev->del_vq(vq);
 	}
-	vp_dev->per_vq_vectors = false;
 
 	if (vp_dev->intx_enabled) {
 		free_irq(vp_dev->pci_dev->irq, vp_dev);
@@ -261,8 +208,8 @@ void vp_del_vqs(struct virtio_device *vdev)
 	vp_dev->msix_names = NULL;
 	kfree(vp_dev->msix_affinity_masks);
 	vp_dev->msix_affinity_masks = NULL;
-	kfree(vp_dev->vqs);
-	vp_dev->vqs = NULL;
+	kfree(vp_dev->msix_vector_map);
+	vp_dev->msix_vector_map = NULL;
 }
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
@@ -275,10 +222,6 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 	u16 msix_vec;
 	int i, err, nvectors, allocated_vectors;
 
-	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
-	if (!vp_dev->vqs)
-		return -ENOMEM;
-
 	if (per_vq_vectors) {
 		/* Best option: one for change interrupt, one per vq. */
 		nvectors = 1;
@@ -294,7 +237,13 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 	if (err)
 		goto error_find;
 
-	vp_dev->per_vq_vectors = per_vq_vectors;
+	if (per_vq_vectors) {
+		vp_dev->msix_vector_map = kmalloc_array(nvqs,
+				sizeof(*vp_dev->msix_vector_map), GFP_KERNEL);
+		if (!vp_dev->msix_vector_map)
+			goto error_find;
+	}
+
 	allocated_vectors = vp_dev->msix_used_vectors;
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
@@ -304,19 +253,25 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 
 		if (!callbacks[i])
 			msix_vec = VIRTIO_MSI_NO_VECTOR;
-		else if (vp_dev->per_vq_vectors)
+		else if (per_vq_vectors)
 			msix_vec = allocated_vectors++;
 		else
 			msix_vec = VP_MSIX_VQ_VECTOR;
-		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
+		vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
+				msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto error_find;
 		}
 
-		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
+		if (!per_vq_vectors)
 			continue;
 
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
+			continue;
+		}
+
 		/* allocate per-vq irq if available and necessary */
 		snprintf(vp_dev->msix_names[msix_vec],
 			 sizeof *vp_dev->msix_names,
@@ -326,8 +281,12 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 				  vring_interrupt, 0,
 				  vp_dev->msix_names[msix_vec],
 				  vqs[i]);
-		if (err)
+		if (err) {
+			/* don't free this irq on error */
+			vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
 			goto error_find;
+		}
+		vp_dev->msix_vector_map[i] = msix_vec;
 	}
 	return 0;
 
@@ -343,23 +302,18 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i, err;
 
-	vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
-	if (!vp_dev->vqs)
-		return -ENOMEM;
-
 	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vp_dev);
 	if (err)
 		goto out_del_vqs;
 
 	vp_dev->intx_enabled = 1;
-	vp_dev->per_vq_vectors = false;
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
 			continue;
 		}
-		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+		vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
 				VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
@@ -409,16 +363,15 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 {
 	struct virtio_device *vdev = vq->vdev;
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
-	struct cpumask *mask;
-	unsigned int irq;
 
 	if (!vq->callback)
 		return -EINVAL;
 
 	if (vp_dev->msix_enabled) {
-		mask = vp_dev->msix_affinity_masks[info->msix_vector];
-		irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
+		int vec = vp_dev->msix_vector_map[vq->index];
+		struct cpumask *mask = vp_dev->msix_affinity_masks[vec];
+		unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec);
+
 		if (cpu == -1)
 			irq_set_affinity_hint(irq, NULL);
 		else {
@@ -498,8 +451,6 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	vp_dev->vdev.dev.parent = &pci_dev->dev;
 	vp_dev->vdev.dev.release = virtio_pci_release_dev;
 	vp_dev->pci_dev = pci_dev;
-	INIT_LIST_HEAD(&vp_dev->virtqueues);
-	spin_lock_init(&vp_dev->lock);
 
 	/* enable the device */
 	rc = pci_enable_device(pci_dev);
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index b2f666250ae0..2038887bdf23 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -31,17 +31,6 @@
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 
-struct virtio_pci_vq_info {
-	/* the actual virtqueue */
-	struct virtqueue *vq;
-
-	/* the list node for the virtqueues list */
-	struct list_head node;
-
-	/* MSI-X vector (or none) */
-	unsigned msix_vector;
-};
-
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -75,13 +64,6 @@ struct virtio_pci_device {
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
 
-	/* a list of queues so we can dispatch IRQs */
-	spinlock_t lock;
-	struct list_head virtqueues;
-
-	/* array of all queues for house-keeping */
-	struct virtio_pci_vq_info **vqs;
-
 	/* MSI-X support */
 	int msix_enabled;
 	int intx_enabled;
@@ -94,16 +76,15 @@ struct virtio_pci_device {
 	/* Vectors allocated, excluding per-vq vectors if any */
 	unsigned msix_used_vectors;
 
-	/* Whether we have vector per vq */
-	bool per_vq_vectors;
+	/* Map of per-VQ MSI-X vectors, may be NULL */
+	unsigned *msix_vector_map;
 
 	struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
-				      struct virtio_pci_vq_info *info,
 				      unsigned idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
 				      u16 msix_vec);
-	void (*del_vq)(struct virtio_pci_vq_info *info);
+	void (*del_vq)(struct virtqueue *vq);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
 };
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 6d9e5173d5fa..47292dad0ff9 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -112,7 +112,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
-				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -130,8 +129,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
 		return ERR_PTR(-ENOENT);
 
-	info->msix_vector = msix_vec;
-
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
@@ -162,9 +159,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	return ERR_PTR(err);
 }
 
-static void del_vq(struct virtio_pci_vq_info *info)
+static void del_vq(struct virtqueue *vq)
 {
-	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 4bf7ab375894..00e6fc1df407 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -293,7 +293,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
-				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -323,8 +322,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	/* get offset of notification word for this vq */
 	off = vp_ioread16(&cfg->queue_notify_off);
 
-	info->msix_vector = msix_vec;
-
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
@@ -409,9 +406,8 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	return 0;
 }
 
-static void del_vq(struct virtio_pci_vq_info *info)
+static void del_vq(struct virtqueue *vq)
 {
-	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	vp_iowrite16(vq->index, &vp_dev->common->queue_select);
-- 
GitLab


From 07ec51480b5eb1233f8c1b0f5d7a7c8d1247c507 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:19 +0100
Subject: [PATCH 254/898] virtio_pci: use shared interrupts for virtqueues

This lets IRQ layer handle dispatching IRQs to separate handlers for the
case where we don't have per-VQ MSI-X vectors, and allows us to greatly
simplify the code based on the assumption that we always have interrupt
vector 0 (legacy INTx or config interrupt for MSI-X) available, and
any other interrupt is request/freed throught the VQ, even if the
actual interrupt line might be shared in some cases.

This allows removing a great deal of variables keeping track of the
interrupt state in struct virtio_pci_device, as we can now simply walk the
list of VQs and deal with per-VQ interrupt handlers there, and only treat
vector 0 special.

Additionally clean up the VQ allocation code to properly unwind on error
instead of having a single global cleanup label, which is error prone,
and in this case also leads to more code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 235 +++++++++++++----------------
 drivers/virtio/virtio_pci_common.h |  16 +-
 2 files changed, 106 insertions(+), 145 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index a33767318cbf..274dc1ff09c0 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -33,10 +33,8 @@ void vp_synchronize_vectors(struct virtio_device *vdev)
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i;
 
-	if (vp_dev->intx_enabled)
-		synchronize_irq(vp_dev->pci_dev->irq);
-
-	for (i = 0; i < vp_dev->msix_vectors; ++i)
+	synchronize_irq(pci_irq_vector(vp_dev->pci_dev, 0));
+	for (i = 1; i < vp_dev->msix_vectors; i++)
 		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
 }
 
@@ -99,77 +97,10 @@ static irqreturn_t vp_interrupt(int irq, void *opaque)
 	return vp_vring_interrupt(irq, opaque);
 }
 
-static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
-				   bool per_vq_vectors)
-{
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-	const char *name = dev_name(&vp_dev->vdev.dev);
-	unsigned i, v;
-	int err = -ENOMEM;
-
-	vp_dev->msix_vectors = nvectors;
-
-	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
-				     GFP_KERNEL);
-	if (!vp_dev->msix_names)
-		goto error;
-	vp_dev->msix_affinity_masks
-		= kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
-			  GFP_KERNEL);
-	if (!vp_dev->msix_affinity_masks)
-		goto error;
-	for (i = 0; i < nvectors; ++i)
-		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
-					GFP_KERNEL))
-			goto error;
-
-	err = pci_alloc_irq_vectors(vp_dev->pci_dev, nvectors, nvectors,
-			PCI_IRQ_MSIX);
-	if (err < 0)
-		goto error;
-	vp_dev->msix_enabled = 1;
-
-	/* Set the vector used for configuration */
-	v = vp_dev->msix_used_vectors;
-	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
-		 "%s-config", name);
-	err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
-			  vp_config_changed, 0, vp_dev->msix_names[v],
-			  vp_dev);
-	if (err)
-		goto error;
-	++vp_dev->msix_used_vectors;
-
-	v = vp_dev->config_vector(vp_dev, v);
-	/* Verify we had enough resources to assign the vector */
-	if (v == VIRTIO_MSI_NO_VECTOR) {
-		err = -EBUSY;
-		goto error;
-	}
-
-	if (!per_vq_vectors) {
-		/* Shared vector for all VQs */
-		v = vp_dev->msix_used_vectors;
-		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
-			 "%s-virtqueues", name);
-		err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
-				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
-				  vp_dev);
-		if (err)
-			goto error;
-		++vp_dev->msix_used_vectors;
-	}
-	return 0;
-error:
-	return err;
-}
-
-/* the config->del_vqs() implementation */
-void vp_del_vqs(struct virtio_device *vdev)
+static void vp_remove_vqs(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtqueue *vq, *n;
-	int i;
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
 		if (vp_dev->msix_vector_map) {
@@ -181,35 +112,33 @@ void vp_del_vqs(struct virtio_device *vdev)
 		}
 		vp_dev->del_vq(vq);
 	}
+}
 
-	if (vp_dev->intx_enabled) {
-		free_irq(vp_dev->pci_dev->irq, vp_dev);
-		vp_dev->intx_enabled = 0;
-	}
+/* the config->del_vqs() implementation */
+void vp_del_vqs(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
 
-	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
-		free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
+	if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs)))
+		return;
 
-	for (i = 0; i < vp_dev->msix_vectors; i++)
-		if (vp_dev->msix_affinity_masks[i])
-			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+	vp_remove_vqs(vdev);
 
 	if (vp_dev->msix_enabled) {
+		for (i = 0; i < vp_dev->msix_vectors; i++)
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+
 		/* Disable the vector used for configuration */
 		vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
 
-		pci_free_irq_vectors(vp_dev->pci_dev);
-		vp_dev->msix_enabled = 0;
+		kfree(vp_dev->msix_affinity_masks);
+		kfree(vp_dev->msix_names);
+		kfree(vp_dev->msix_vector_map);
 	}
 
-	vp_dev->msix_vectors = 0;
-	vp_dev->msix_used_vectors = 0;
-	kfree(vp_dev->msix_names);
-	vp_dev->msix_names = NULL;
-	kfree(vp_dev->msix_affinity_masks);
-	vp_dev->msix_affinity_masks = NULL;
-	kfree(vp_dev->msix_vector_map);
-	vp_dev->msix_vector_map = NULL;
+	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
+	pci_free_irq_vectors(vp_dev->pci_dev);
 }
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
@@ -219,79 +148,122 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 			      bool per_vq_vectors)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	const char *name = dev_name(&vp_dev->vdev.dev);
+	int i, err = -ENOMEM, allocated_vectors, nvectors;
 	u16 msix_vec;
-	int i, err, nvectors, allocated_vectors;
+
+	nvectors = 1;
+	for (i = 0; i < nvqs; i++)
+		if (callbacks[i])
+			nvectors++;
 
 	if (per_vq_vectors) {
-		/* Best option: one for change interrupt, one per vq. */
-		nvectors = 1;
-		for (i = 0; i < nvqs; ++i)
-			if (callbacks[i])
-				++nvectors;
+		err = pci_alloc_irq_vectors(vp_dev->pci_dev, nvectors, nvectors,
+				PCI_IRQ_MSIX);
 	} else {
-		/* Second best: one for change, shared for all vqs. */
-		nvectors = 2;
+		err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2,
+				PCI_IRQ_MSIX);
 	}
+	if (err < 0)
+		return err;
 
-	err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
+	vp_dev->msix_vectors = nvectors;
+	vp_dev->msix_names = kmalloc_array(nvectors,
+			sizeof(*vp_dev->msix_names), GFP_KERNEL);
+	if (!vp_dev->msix_names)
+		goto out_free_irq_vectors;
+
+	vp_dev->msix_affinity_masks = kcalloc(nvectors,
+			sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL);
+	if (!vp_dev->msix_affinity_masks)
+		goto out_free_msix_names;
+
+	for (i = 0; i < nvectors; ++i) {
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+				GFP_KERNEL))
+			goto out_free_msix_affinity_masks;
+	}
+
+	/* Set the vector used for configuration */
+	snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names),
+		 "%s-config", name);
+	err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed,
+			0, vp_dev->msix_names[0], vp_dev);
 	if (err)
-		goto error_find;
+		goto out_free_irq_vectors;
 
-	if (per_vq_vectors) {
-		vp_dev->msix_vector_map = kmalloc_array(nvqs,
-				sizeof(*vp_dev->msix_vector_map), GFP_KERNEL);
-		if (!vp_dev->msix_vector_map)
-			goto error_find;
+	/* Verify we had enough resources to assign the vector */
+	if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) {
+		err = -EBUSY;
+		goto out_free_config_irq;
 	}
 
-	allocated_vectors = vp_dev->msix_used_vectors;
+	vp_dev->msix_vector_map = kmalloc_array(nvqs,
+			sizeof(*vp_dev->msix_vector_map), GFP_KERNEL);
+	if (!vp_dev->msix_vector_map)
+		goto out_disable_config_irq;
+
+	allocated_vectors = 1; /* vector 0 is the config interrupt */
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
 			continue;
 		}
 
-		if (!callbacks[i])
-			msix_vec = VIRTIO_MSI_NO_VECTOR;
-		else if (per_vq_vectors)
-			msix_vec = allocated_vectors++;
+		if (callbacks[i])
+			msix_vec = allocated_vectors;
 		else
-			msix_vec = VP_MSIX_VQ_VECTOR;
+			msix_vec = VIRTIO_MSI_NO_VECTOR;
+
 		vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
 				msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
-			goto error_find;
+			goto out_remove_vqs;
 		}
 
-		if (!per_vq_vectors)
-			continue;
-
 		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
 			vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
 			continue;
 		}
 
-		/* allocate per-vq irq if available and necessary */
-		snprintf(vp_dev->msix_names[msix_vec],
-			 sizeof *vp_dev->msix_names,
-			 "%s-%s",
+		snprintf(vp_dev->msix_names[i + 1],
+			 sizeof(*vp_dev->msix_names), "%s-%s",
 			 dev_name(&vp_dev->vdev.dev), names[i]);
 		err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
-				  vring_interrupt, 0,
-				  vp_dev->msix_names[msix_vec],
-				  vqs[i]);
+				  vring_interrupt, IRQF_SHARED,
+				  vp_dev->msix_names[i + 1], vqs[i]);
 		if (err) {
 			/* don't free this irq on error */
 			vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
-			goto error_find;
+			goto out_remove_vqs;
 		}
 		vp_dev->msix_vector_map[i] = msix_vec;
+
+		if (per_vq_vectors)
+			allocated_vectors++;
 	}
+
+	vp_dev->msix_enabled = 1;
 	return 0;
 
-error_find:
-	vp_del_vqs(vdev);
+out_remove_vqs:
+	vp_remove_vqs(vdev);
+	kfree(vp_dev->msix_vector_map);
+out_disable_config_irq:
+	vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
+out_free_config_irq:
+	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
+out_free_msix_affinity_masks:
+	for (i = 0; i < nvectors; i++) {
+		if (vp_dev->msix_affinity_masks[i])
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+	}
+	kfree(vp_dev->msix_affinity_masks);
+out_free_msix_names:
+	kfree(vp_dev->msix_names);
+out_free_irq_vectors:
+	pci_free_irq_vectors(vp_dev->pci_dev);
 	return err;
 }
 
@@ -305,9 +277,8 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vp_dev);
 	if (err)
-		goto out_del_vqs;
+		return err;
 
-	vp_dev->intx_enabled = 1;
 	for (i = 0; i < nvqs; ++i) {
 		if (!names[i]) {
 			vqs[i] = NULL;
@@ -317,13 +288,15 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 				VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
-			goto out_del_vqs;
+			goto out_remove_vqs;
 		}
 	}
 
 	return 0;
-out_del_vqs:
-	vp_del_vqs(vdev);
+
+out_remove_vqs:
+	vp_remove_vqs(vdev);
+	free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
 	return err;
 }
 
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 2038887bdf23..85593867e712 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -66,16 +66,12 @@ struct virtio_pci_device {
 
 	/* MSI-X support */
 	int msix_enabled;
-	int intx_enabled;
 	cpumask_var_t *msix_affinity_masks;
 	/* Name strings for interrupts. This size should be enough,
 	 * and I'm too lazy to allocate each name separately. */
 	char (*msix_names)[256];
-	/* Number of available vectors */
-	unsigned msix_vectors;
-	/* Vectors allocated, excluding per-vq vectors if any */
-	unsigned msix_used_vectors;
-
+	/* Total Number of MSI-X vectors (including per-VQ ones). */
+	int msix_vectors;
 	/* Map of per-VQ MSI-X vectors, may be NULL */
 	unsigned *msix_vector_map;
 
@@ -89,14 +85,6 @@ struct virtio_pci_device {
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
 };
 
-/* Constants for MSI-X */
-/* Use first vector for configuration changes, second and the rest for
- * virtqueues Thus, we need at least 2 vectors for MSI. */
-enum {
-	VP_MSIX_CONFIG_VECTOR = 0,
-	VP_MSIX_VQ_VECTOR = 1,
-};
-
 /* Convert a generic virtio device to our structure */
 static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
 {
-- 
GitLab


From 53a020c661741f3b87ad3ac6fa545088aaebac9b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:20 +0100
Subject: [PATCH 255/898] virtio_pci: don't duplicate the msix_enable flag in
 struct pci_dev

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 5 ++---
 drivers/virtio/virtio_pci_common.h | 2 --
 drivers/virtio/virtio_pci_legacy.c | 2 +-
 drivers/virtio/virtio_pci_modern.c | 2 +-
 include/uapi/linux/virtio_pci.h    | 2 +-
 5 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 274dc1ff09c0..b83053082875 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -125,7 +125,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 
 	vp_remove_vqs(vdev);
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		for (i = 0; i < vp_dev->msix_vectors; i++)
 			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
 
@@ -244,7 +244,6 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 			allocated_vectors++;
 	}
 
-	vp_dev->msix_enabled = 1;
 	return 0;
 
 out_remove_vqs:
@@ -340,7 +339,7 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 	if (!vq->callback)
 		return -EINVAL;
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		int vec = vp_dev->msix_vector_map[vq->index];
 		struct cpumask *mask = vp_dev->msix_affinity_masks[vec];
 		unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec);
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 85593867e712..217ca876eed7 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -64,8 +64,6 @@ struct virtio_pci_device {
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
 
-	/* MSI-X support */
-	int msix_enabled;
 	cpumask_var_t *msix_affinity_masks;
 	/* Name strings for interrupts. This size should be enough,
 	 * and I'm too lazy to allocate each name separately. */
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 47292dad0ff9..2ab6aee51bf6 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -165,7 +165,7 @@ static void del_vq(struct virtqueue *vq)
 
 	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
 			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
 		/* Flush the write out to device */
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 00e6fc1df407..e5ce31091953 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -412,7 +412,7 @@ static void del_vq(struct virtqueue *vq)
 
 	vp_iowrite16(vq->index, &vp_dev->common->queue_select);
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
 			     &vp_dev->common->queue_msix_vector);
 		/* Flush the write out to device */
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 90007a1abcab..15b4385a2be1 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -79,7 +79,7 @@
  * configuration space */
 #define VIRTIO_PCI_CONFIG_OFF(msix_enabled)	((msix_enabled) ? 24 : 20)
 /* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */
-#define VIRTIO_PCI_CONFIG(dev)	VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled)
+#define VIRTIO_PCI_CONFIG(dev)	VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled)
 
 /* Virtio ABI version, this must match exactly */
 #define VIRTIO_PCI_ABI_VERSION		0
-- 
GitLab


From 52a61516125fa9a21b3bdf4f90928308e2e5573f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:21 +0100
Subject: [PATCH 256/898] virtio_pci: simplify MSI-X setup

Try to grab the MSI-X vectors early and fall back to the shared one
before doing lots of allocations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 35 +++++++++++++++---------------
 1 file changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index b83053082875..822f8e5dcee4 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -142,14 +142,13 @@ void vp_del_vqs(struct virtio_device *vdev)
 }
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
-			      struct virtqueue *vqs[],
-			      vq_callback_t *callbacks[],
-			      const char * const names[],
-			      bool per_vq_vectors)
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[])
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	const char *name = dev_name(&vp_dev->vdev.dev);
 	int i, err = -ENOMEM, allocated_vectors, nvectors;
+	bool shared = false;
 	u16 msix_vec;
 
 	nvectors = 1;
@@ -157,12 +156,16 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 		if (callbacks[i])
 			nvectors++;
 
-	if (per_vq_vectors) {
-		err = pci_alloc_irq_vectors(vp_dev->pci_dev, nvectors, nvectors,
-				PCI_IRQ_MSIX);
-	} else {
+	/* Try one vector per queue first. */
+	err = pci_alloc_irq_vectors(vp_dev->pci_dev, nvectors, nvectors,
+			PCI_IRQ_MSIX);
+	if (err < 0) {
+		/* Fallback to one vector for config, one shared for queues. */
+		shared = true;
 		err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2,
 				PCI_IRQ_MSIX);
+		if (err < 0)
+			return err;
 	}
 	if (err < 0)
 		return err;
@@ -190,7 +193,7 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 	err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed,
 			0, vp_dev->msix_names[0], vp_dev);
 	if (err)
-		goto out_free_irq_vectors;
+		goto out_free_msix_affinity_masks;
 
 	/* Verify we had enough resources to assign the vector */
 	if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) {
@@ -240,7 +243,11 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 		}
 		vp_dev->msix_vector_map[i] = msix_vec;
 
-		if (per_vq_vectors)
+		/*
+		 * Use a different vector for each queue if they are available,
+		 * else share the same vector for all VQs.
+		 */
+		if (!shared)
 			allocated_vectors++;
 	}
 
@@ -307,15 +314,9 @@ int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 {
 	int err;
 
-	/* Try MSI-X with one vector per queue. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true);
-	if (!err)
-		return 0;
-	/* Fallback: MSI-X with one vector for config, one shared for queues. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names);
 	if (!err)
 		return 0;
-	/* Finally fall back to regular interrupts. */
 	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
 }
 
-- 
GitLab


From fb5e31d970ce8b4941f03ed765d7dbefc39f22d9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:22 +0100
Subject: [PATCH 257/898] virtio: allow drivers to request IRQ affinity when
 creating VQs

Add a struct irq_affinity pointer to the find_vqs methods, which if set
is used to tell the PCI layer to create the MSI-X vectors for our I/O
virtqueues with the proper affinity from the start.  Compared to after
the fact affinity hints this gives us an instantly working setup and
allows to allocate the irq descritors node-local and avoid interconnect
traffic.  Last but not least this will allow blk-mq queues are created
based on the interrupt affinity for storage drivers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/block/virtio_blk.c                 |  3 ++-
 drivers/char/virtio_console.c              |  2 +-
 drivers/crypto/virtio/virtio_crypto_core.c |  2 +-
 drivers/gpu/drm/virtio/virtgpu_kms.c       |  2 +-
 drivers/misc/mic/vop/vop_main.c            |  2 +-
 drivers/net/caif/caif_virtio.c             |  3 ++-
 drivers/net/virtio_net.c                   |  2 +-
 drivers/remoteproc/remoteproc_virtio.c     |  3 ++-
 drivers/rpmsg/virtio_rpmsg_bus.c           |  2 +-
 drivers/s390/virtio/kvm_virtio.c           |  3 ++-
 drivers/s390/virtio/virtio_ccw.c           |  3 ++-
 drivers/scsi/virtio_scsi.c                 |  3 ++-
 drivers/virtio/virtio_balloon.c            |  3 ++-
 drivers/virtio/virtio_input.c              |  3 ++-
 drivers/virtio/virtio_mmio.c               |  3 ++-
 drivers/virtio/virtio_pci_common.c         | 19 ++++++++++++-------
 drivers/virtio/virtio_pci_common.h         |  5 ++---
 drivers/virtio/virtio_pci_modern.c         |  7 +++----
 include/linux/virtio_config.h              |  9 +++++----
 net/vmw_vsock/virtio_transport.c           |  3 ++-
 20 files changed, 48 insertions(+), 34 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 10332c24f961..c54118bdc67d 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -411,7 +411,8 @@ static int init_vq(struct virtio_blk *vblk)
 	}
 
 	/* Discover virtqueues and write information to configuration.  */
-	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
+	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
+			NULL);
 	if (err)
 		goto out;
 
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 17857beb4892..6266c0568e1d 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1939,7 +1939,7 @@ static int init_vqs(struct ports_device *portdev)
 	/* Find the queues. */
 	err = portdev->vdev->config->find_vqs(portdev->vdev, nr_queues, vqs,
 					      io_callbacks,
-					      (const char **)io_names);
+					      (const char **)io_names, NULL);
 	if (err)
 		goto free;
 
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index fe70ec823b27..0aa2f045543b 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -119,7 +119,7 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi)
 	}
 
 	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names);
+					 names, NULL);
 	if (ret)
 		goto err_find;
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c
index 1235519853f4..e975fa5b0a32 100644
--- a/drivers/gpu/drm/virtio/virtgpu_kms.c
+++ b/drivers/gpu/drm/virtio/virtgpu_kms.c
@@ -172,7 +172,7 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags)
 		 vgdev->has_virgl_3d ? "enabled" : "not available");
 
 	ret = vgdev->vdev->config->find_vqs(vgdev->vdev, 2, vqs,
-					    callbacks, names);
+					    callbacks, names, NULL);
 	if (ret) {
 		DRM_ERROR("failed to find virt queues\n");
 		goto err_vqs;
diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c
index 1a2b67f3183d..c2e29d7f0de8 100644
--- a/drivers/misc/mic/vop/vop_main.c
+++ b/drivers/misc/mic/vop/vop_main.c
@@ -374,7 +374,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev,
 static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
 			struct virtqueue *vqs[],
 			vq_callback_t *callbacks[],
-			const char * const names[])
+			const char * const names[], struct irq_affinity *desc)
 {
 	struct _vop_vdev *vdev = to_vopvdev(dev);
 	struct vop_device *vpdev = vdev->vpdev;
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index b306210b02b7..bc0eb47eccee 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -679,7 +679,8 @@ static int cfv_probe(struct virtio_device *vdev)
 		goto err;
 
 	/* Get the TX virtio ring. This is a "guest side vring". */
-	err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names);
+	err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names,
+			NULL);
 	if (err)
 		goto err;
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 765c2d6358da..9be74c2dfb22 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2003,7 +2003,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	}
 
 	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names);
+					 names, NULL);
 	if (ret)
 		goto err_find;
 
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index 364411fb7734..0142cc3f0c91 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -137,7 +137,8 @@ static void rproc_virtio_del_vqs(struct virtio_device *vdev)
 static int rproc_virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				 struct virtqueue *vqs[],
 				 vq_callback_t *callbacks[],
-				 const char * const names[])
+				 const char * const names[],
+				 struct irq_affinity *desc)
 {
 	int i, ret;
 
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 3090b0d3072f..5e66e081027e 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -869,7 +869,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
 	init_waitqueue_head(&vrp->sendq);
 
 	/* We expect two virtqueues, rx and tx (and in this order) */
-	err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names);
+	err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names, NULL);
 	if (err)
 		goto free_vrp;
 
diff --git a/drivers/s390/virtio/kvm_virtio.c b/drivers/s390/virtio/kvm_virtio.c
index 5e5c11f37b24..2ce0b3eb2efe 100644
--- a/drivers/s390/virtio/kvm_virtio.c
+++ b/drivers/s390/virtio/kvm_virtio.c
@@ -255,7 +255,8 @@ static void kvm_del_vqs(struct virtio_device *vdev)
 static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			struct virtqueue *vqs[],
 			vq_callback_t *callbacks[],
-			const char * const names[])
+			const char * const names[],
+			struct irq_affinity *desc)
 {
 	struct kvm_device *kdev = to_kvmdev(vdev);
 	int i;
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 070c4da95f48..304d3b3cbfd3 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -628,7 +628,8 @@ static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev,
 static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			       struct virtqueue *vqs[],
 			       vq_callback_t *callbacks[],
-			       const char * const names[])
+			       const char * const names[],
+			       struct irq_affinity *desc)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
 	unsigned long *indicatorp = NULL;
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index c680d7641311..c9c5ea0611e9 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -941,7 +941,8 @@ static int virtscsi_init(struct virtio_device *vdev,
 	}
 
 	/* Discover virtqueues and write information to configuration.  */
-	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
+	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
+			NULL);
 	if (err)
 		goto out;
 
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 181793f07852..36c9c8fcb7f8 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -413,7 +413,8 @@ static int init_vqs(struct virtio_balloon *vb)
 	 * optionally stat.
 	 */
 	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names);
+	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names,
+			NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index 350a2a5a49db..79f1293cda93 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -173,7 +173,8 @@ static int virtinput_init_vqs(struct virtio_input *vi)
 	static const char * const names[] = { "events", "status" };
 	int err;
 
-	err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names);
+	err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names,
+			NULL);
 	if (err)
 		return err;
 	vi->evt = vqs[0];
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 08357d70a891..78343b8f9034 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -446,7 +446,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
-		       const char * const names[])
+		       const char * const names[],
+		       struct irq_affinity *desc)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 822f8e5dcee4..7902e920fc73 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -143,22 +143,28 @@ void vp_del_vqs(struct virtio_device *vdev)
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[])
+		const char * const names[], struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	const char *name = dev_name(&vp_dev->vdev.dev);
 	int i, err = -ENOMEM, allocated_vectors, nvectors;
+	unsigned flags = PCI_IRQ_MSIX;
 	bool shared = false;
 	u16 msix_vec;
 
+	if (desc) {
+		flags |= PCI_IRQ_AFFINITY;
+		desc->pre_vectors++; /* virtio config vector */
+	}
+
 	nvectors = 1;
 	for (i = 0; i < nvqs; i++)
 		if (callbacks[i])
 			nvectors++;
 
 	/* Try one vector per queue first. */
-	err = pci_alloc_irq_vectors(vp_dev->pci_dev, nvectors, nvectors,
-			PCI_IRQ_MSIX);
+	err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
+			nvectors, flags, desc);
 	if (err < 0) {
 		/* Fallback to one vector for config, one shared for queues. */
 		shared = true;
@@ -308,13 +314,12 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-		struct virtqueue *vqs[],
-		vq_callback_t *callbacks[],
-		const char * const names[])
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc)
 {
 	int err;
 
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc);
 	if (!err)
 		return 0;
 	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 217ca876eed7..a6ad9ec6baef 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -97,9 +97,8 @@ bool vp_notify(struct virtqueue *vq);
 void vp_del_vqs(struct virtio_device *vdev);
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-		       struct virtqueue *vqs[],
-		       vq_callback_t *callbacks[],
-		       const char * const names[]);
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc);
 const char *vp_bus_name(struct virtio_device *vdev);
 
 /* Setup the affinity for a virtqueue:
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index e5ce31091953..a7a0981e441c 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -384,13 +384,12 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 }
 
 static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-			      struct virtqueue *vqs[],
-			      vq_callback_t *callbacks[],
-			      const char * const names[])
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtqueue *vq;
-	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names);
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, desc);
 
 	if (rc)
 		return rc;
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 26c155bb639b..2ebe506fe41a 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -7,6 +7,8 @@
 #include <linux/virtio_byteorder.h>
 #include <uapi/linux/virtio_config.h>
 
+struct irq_affinity;
+
 /**
  * virtio_config_ops - operations for configuring a virtio device
  * @get: read the value of a configuration field
@@ -68,9 +70,8 @@ struct virtio_config_ops {
 	void (*set_status)(struct virtio_device *vdev, u8 status);
 	void (*reset)(struct virtio_device *vdev);
 	int (*find_vqs)(struct virtio_device *, unsigned nvqs,
-			struct virtqueue *vqs[],
-			vq_callback_t *callbacks[],
-			const char * const names[]);
+			struct virtqueue *vqs[], vq_callback_t *callbacks[],
+			const char * const names[], struct irq_affinity *desc);
 	void (*del_vqs)(struct virtio_device *);
 	u64 (*get_features)(struct virtio_device *vdev);
 	int (*finalize_features)(struct virtio_device *vdev);
@@ -169,7 +170,7 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 	vq_callback_t *callbacks[] = { c };
 	const char *names[] = { n };
 	struct virtqueue *vq;
-	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names);
+	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 	return vq;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 6788264acc63..9d24c0e958b1 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -532,7 +532,8 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 	vsock->vdev = vdev;
 
 	ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX,
-					    vsock->vqs, callbacks, names);
+					    vsock->vqs, callbacks, names,
+					    NULL);
 	if (ret < 0)
 		goto out;
 
-- 
GitLab


From bbaba479563910aaa51e59bb9027a09e396d3a3c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:23 +0100
Subject: [PATCH 258/898] virtio: provide a method to get the IRQ affinity mask
 for a virtqueue

This basically passed up the pci_irq_get_affinity information through
virtio through an optional get_vq_affinity method.  It is only implemented
by the PCI backend for now, and only when we use per-virtqueue IRQs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 11 +++++++++++
 drivers/virtio/virtio_pci_common.h |  2 ++
 drivers/virtio/virtio_pci_legacy.c |  1 +
 drivers/virtio/virtio_pci_modern.c |  2 ++
 include/linux/virtio_config.h      |  3 +++
 5 files changed, 19 insertions(+)

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 7902e920fc73..df548a6fb844 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -361,6 +361,17 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 	return 0;
 }
 
+const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	unsigned int *map = vp_dev->msix_vector_map;
+
+	if (!map || map[index] == VIRTIO_MSI_NO_VECTOR)
+		return NULL;
+
+	return pci_irq_get_affinity(vp_dev->pci_dev, map[index]);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int virtio_pci_freeze(struct device *dev)
 {
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index a6ad9ec6baef..ac8c9d788964 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -108,6 +108,8 @@ const char *vp_bus_name(struct virtio_device *vdev);
  */
 int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
 
+const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index);
+
 #if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
 int virtio_pci_legacy_probe(struct virtio_pci_device *);
 void virtio_pci_legacy_remove(struct virtio_pci_device *);
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 2ab6aee51bf6..f7362c5fe18a 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -190,6 +190,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 /* the PCI probing function */
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index a7a0981e441c..7bc3004b840e 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -437,6 +437,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -452,6 +453,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 /**
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 2ebe506fe41a..8355bab175e1 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -58,6 +58,7 @@ struct irq_affinity;
  *      This returns a pointer to the bus name a la pci_name from which
  *      the caller can then copy.
  * @set_vq_affinity: set the affinity for a virtqueue.
+ * @get_vq_affinity: get the affinity for a virtqueue (optional).
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
@@ -77,6 +78,8 @@ struct virtio_config_ops {
 	int (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
 	int (*set_vq_affinity)(struct virtqueue *vq, int cpu);
+	const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev,
+			int index);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
-- 
GitLab


From 73473427bb551686e4b68ecd99bfd27e6635286a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:24 +0100
Subject: [PATCH 259/898] blk-mq: provide a default queue mapping for virtio
 device

Similar to the PCI version, just calling into virtio instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 block/Kconfig                 |  5 ++++
 block/Makefile                |  1 +
 block/blk-mq-virtio.c         | 54 +++++++++++++++++++++++++++++++++++
 include/linux/blk-mq-virtio.h | 10 +++++++
 4 files changed, 70 insertions(+)
 create mode 100644 block/blk-mq-virtio.c
 create mode 100644 include/linux/blk-mq-virtio.h

diff --git a/block/Kconfig b/block/Kconfig
index 8bf114a3858a..3523b4f0cd8b 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -165,4 +165,9 @@ config BLK_MQ_PCI
 	depends on BLOCK && PCI
 	default y
 
+config BLK_MQ_VIRTIO
+	bool
+	depends on BLOCK && VIRTIO
+	default y
+
 source block/Kconfig.iosched
diff --git a/block/Makefile b/block/Makefile
index a827f988c4e6..60691949d28d 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -23,5 +23,6 @@ obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
+obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c
new file mode 100644
index 000000000000..c3afbca11299
--- /dev/null
+++ b/block/blk-mq-virtio.c
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2016 Christoph Hellwig.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/device.h>
+#include <linux/blk-mq.h>
+#include <linux/blk-mq-virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/module.h>
+#include "blk-mq.h"
+
+/**
+ * blk_mq_virtio_map_queues - provide a default queue mapping for virtio device
+ * @set:	tagset to provide the mapping for
+ * @vdev:	virtio device associated with @set.
+ * @first_vec:	first interrupt vectors to use for queues (usually 0)
+ *
+ * This function assumes the virtio device @vdev has at least as many available
+ * interrupt vetors as @set has queues.  It will then queuery the vector
+ * corresponding to each queue for it's affinity mask and built queue mapping
+ * that maps a queue to the CPUs that have irq affinity for the corresponding
+ * vector.
+ */
+int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
+		struct virtio_device *vdev, int first_vec)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	if (!vdev->config->get_vq_affinity)
+		goto fallback;
+
+	for (queue = 0; queue < set->nr_hw_queues; queue++) {
+		mask = vdev->config->get_vq_affinity(vdev, first_vec + queue);
+		if (!mask)
+			goto fallback;
+
+		for_each_cpu(cpu, mask)
+			set->mq_map[cpu] = queue;
+	}
+
+	return 0;
+fallback:
+	return blk_mq_map_queues(set);
+}
+EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues);
diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h
new file mode 100644
index 000000000000..b1ef6e14744f
--- /dev/null
+++ b/include/linux/blk-mq-virtio.h
@@ -0,0 +1,10 @@
+#ifndef _LINUX_BLK_MQ_VIRTIO_H
+#define _LINUX_BLK_MQ_VIRTIO_H
+
+struct blk_mq_tag_set;
+struct virtio_device;
+
+int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
+		struct virtio_device *vdev, int first_vec);
+
+#endif /* _LINUX_BLK_MQ_VIRTIO_H */
-- 
GitLab


From ad71473d9c43725c917fc5a86d54ceb7001ee28c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:25 +0100
Subject: [PATCH 260/898] virtio_blk: use virtio IRQ affinity

Use automatic IRQ affinity assignment in the virtio layer if available,
and build the blk-mq queues based on it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/block/virtio_blk.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c54118bdc67d..1028dfeb5a7f 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -5,6 +5,7 @@
 #include <linux/hdreg.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/interrupt.h>
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
@@ -12,6 +13,7 @@
 #include <scsi/scsi_cmnd.h>
 #include <linux/idr.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-mq-virtio.h>
 #include <linux/numa.h>
 
 #define PART_BITS 4
@@ -385,6 +387,7 @@ static int init_vq(struct virtio_blk *vblk)
 	struct virtqueue **vqs;
 	unsigned short num_vqs;
 	struct virtio_device *vdev = vblk->vdev;
+	struct irq_affinity desc = { 0, };
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ,
 				   struct virtio_blk_config, num_queues,
@@ -412,7 +415,7 @@ static int init_vq(struct virtio_blk *vblk)
 
 	/* Discover virtqueues and write information to configuration.  */
 	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
-			NULL);
+			&desc);
 	if (err)
 		goto out;
 
@@ -543,10 +546,18 @@ static int virtblk_init_request(void *data, struct request *rq,
 	return 0;
 }
 
+static int virtblk_map_queues(struct blk_mq_tag_set *set)
+{
+	struct virtio_blk *vblk = set->driver_data;
+
+	return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
+}
+
 static struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.complete	= virtblk_request_done,
 	.init_request	= virtblk_init_request,
+	.map_queues	= virtblk_map_queues,
 };
 
 static unsigned int virtblk_queue_depth;
-- 
GitLab


From 0d9f0a52c8b9f7a003fe1650b7d5fb8518efabe0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Feb 2017 18:15:26 +0100
Subject: [PATCH 261/898] virtio_scsi: use virtio IRQ affinity

Use automatic IRQ affinity assignment in the virtio layer if available,
and build the blk-mq queues based on it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/scsi/virtio_scsi.c | 126 ++++---------------------------------
 include/linux/cpuhotplug.h |   1 -
 2 files changed, 12 insertions(+), 115 deletions(-)

diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index c9c5ea0611e9..939c47df73fa 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/mempool.h>
+#include <linux/interrupt.h>
 #include <linux/virtio.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
@@ -29,6 +30,7 @@
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_tcq.h>
 #include <linux/seqlock.h>
+#include <linux/blk-mq-virtio.h>
 
 #define VIRTIO_SCSI_MEMPOOL_SZ 64
 #define VIRTIO_SCSI_EVENT_LEN 8
@@ -108,7 +110,6 @@ struct virtio_scsi {
 	bool affinity_hint_set;
 
 	struct hlist_node node;
-	struct hlist_node node_dead;
 
 	/* Protected by event_vq lock */
 	bool stop_events;
@@ -118,7 +119,6 @@ struct virtio_scsi {
 	struct virtio_scsi_vq req_vqs[];
 };
 
-static enum cpuhp_state virtioscsi_online;
 static struct kmem_cache *virtscsi_cmd_cache;
 static mempool_t *virtscsi_cmd_pool;
 
@@ -766,6 +766,13 @@ static void virtscsi_target_destroy(struct scsi_target *starget)
 	kfree(tgt);
 }
 
+static int virtscsi_map_queues(struct Scsi_Host *shost)
+{
+	struct virtio_scsi *vscsi = shost_priv(shost);
+
+	return blk_mq_virtio_map_queues(&shost->tag_set, vscsi->vdev, 2);
+}
+
 static struct scsi_host_template virtscsi_host_template_single = {
 	.module = THIS_MODULE,
 	.name = "Virtio SCSI HBA",
@@ -801,6 +808,7 @@ static struct scsi_host_template virtscsi_host_template_multi = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.target_alloc = virtscsi_target_alloc,
 	.target_destroy = virtscsi_target_destroy,
+	.map_queues = virtscsi_map_queues,
 	.track_queue_depth = 1,
 };
 
@@ -817,80 +825,6 @@ static struct scsi_host_template virtscsi_host_template_multi = {
 		virtio_cwrite(vdev, struct virtio_scsi_config, fld, &__val); \
 	} while(0)
 
-static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
-{
-	int i;
-	int cpu;
-
-	/* In multiqueue mode, when the number of cpu is equal
-	 * to the number of request queues, we let the qeueues
-	 * to be private to one cpu by setting the affinity hint
-	 * to eliminate the contention.
-	 */
-	if ((vscsi->num_queues == 1 ||
-	     vscsi->num_queues != num_online_cpus()) && affinity) {
-		if (vscsi->affinity_hint_set)
-			affinity = false;
-		else
-			return;
-	}
-
-	if (affinity) {
-		i = 0;
-		for_each_online_cpu(cpu) {
-			virtqueue_set_affinity(vscsi->req_vqs[i].vq, cpu);
-			i++;
-		}
-
-		vscsi->affinity_hint_set = true;
-	} else {
-		for (i = 0; i < vscsi->num_queues; i++) {
-			if (!vscsi->req_vqs[i].vq)
-				continue;
-
-			virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1);
-		}
-
-		vscsi->affinity_hint_set = false;
-	}
-}
-
-static void virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
-{
-	get_online_cpus();
-	__virtscsi_set_affinity(vscsi, affinity);
-	put_online_cpus();
-}
-
-static int virtscsi_cpu_online(unsigned int cpu, struct hlist_node *node)
-{
-	struct virtio_scsi *vscsi = hlist_entry_safe(node, struct virtio_scsi,
-						     node);
-	__virtscsi_set_affinity(vscsi, true);
-	return 0;
-}
-
-static int virtscsi_cpu_notif_add(struct virtio_scsi *vi)
-{
-	int ret;
-
-	ret = cpuhp_state_add_instance(virtioscsi_online, &vi->node);
-	if (ret)
-		return ret;
-
-	ret = cpuhp_state_add_instance(CPUHP_VIRT_SCSI_DEAD, &vi->node_dead);
-	if (ret)
-		cpuhp_state_remove_instance(virtioscsi_online, &vi->node);
-	return ret;
-}
-
-static void virtscsi_cpu_notif_remove(struct virtio_scsi *vi)
-{
-	cpuhp_state_remove_instance_nocalls(virtioscsi_online, &vi->node);
-	cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_SCSI_DEAD,
-					    &vi->node_dead);
-}
-
 static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
 			     struct virtqueue *vq)
 {
@@ -900,14 +834,8 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
 
 static void virtscsi_remove_vqs(struct virtio_device *vdev)
 {
-	struct Scsi_Host *sh = virtio_scsi_host(vdev);
-	struct virtio_scsi *vscsi = shost_priv(sh);
-
-	virtscsi_set_affinity(vscsi, false);
-
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
-
 	vdev->config->del_vqs(vdev);
 }
 
@@ -920,6 +848,7 @@ static int virtscsi_init(struct virtio_device *vdev,
 	vq_callback_t **callbacks;
 	const char **names;
 	struct virtqueue **vqs;
+	struct irq_affinity desc = { .pre_vectors = 2 };
 
 	num_vqs = vscsi->num_queues + VIRTIO_SCSI_VQ_BASE;
 	vqs = kmalloc(num_vqs * sizeof(struct virtqueue *), GFP_KERNEL);
@@ -942,7 +871,7 @@ static int virtscsi_init(struct virtio_device *vdev,
 
 	/* Discover virtqueues and write information to configuration.  */
 	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
-			NULL);
+			&desc);
 	if (err)
 		goto out;
 
@@ -1008,10 +937,6 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	if (err)
 		goto virtscsi_init_failed;
 
-	err = virtscsi_cpu_notif_add(vscsi);
-	if (err)
-		goto scsi_add_host_failed;
-
 	cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1;
 	shost->cmd_per_lun = min_t(u32, cmd_per_lun, shost->can_queue);
 	shost->max_sectors = virtscsi_config_get(vdev, max_sectors) ?: 0xFFFF;
@@ -1066,9 +991,6 @@ static void virtscsi_remove(struct virtio_device *vdev)
 		virtscsi_cancel_event_work(vscsi);
 
 	scsi_remove_host(shost);
-
-	virtscsi_cpu_notif_remove(vscsi);
-
 	virtscsi_remove_vqs(vdev);
 	scsi_host_put(shost);
 }
@@ -1076,10 +998,6 @@ static void virtscsi_remove(struct virtio_device *vdev)
 #ifdef CONFIG_PM_SLEEP
 static int virtscsi_freeze(struct virtio_device *vdev)
 {
-	struct Scsi_Host *sh = virtio_scsi_host(vdev);
-	struct virtio_scsi *vscsi = shost_priv(sh);
-
-	virtscsi_cpu_notif_remove(vscsi);
 	virtscsi_remove_vqs(vdev);
 	return 0;
 }
@@ -1094,11 +1012,6 @@ static int virtscsi_restore(struct virtio_device *vdev)
 	if (err)
 		return err;
 
-	err = virtscsi_cpu_notif_add(vscsi);
-	if (err) {
-		vdev->config->del_vqs(vdev);
-		return err;
-	}
 	virtio_device_ready(vdev);
 
 	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
@@ -1153,16 +1066,6 @@ static int __init init(void)
 		pr_err("mempool_create() for virtscsi_cmd_pool failed\n");
 		goto error;
 	}
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
-				      "scsi/virtio:online",
-				      virtscsi_cpu_online, NULL);
-	if (ret < 0)
-		goto error;
-	virtioscsi_online = ret;
-	ret = cpuhp_setup_state_multi(CPUHP_VIRT_SCSI_DEAD, "scsi/virtio:dead",
-				      NULL, virtscsi_cpu_online);
-	if (ret)
-		goto error;
 	ret = register_virtio_driver(&virtio_scsi_driver);
 	if (ret < 0)
 		goto error;
@@ -1178,17 +1081,12 @@ static int __init init(void)
 		kmem_cache_destroy(virtscsi_cmd_cache);
 		virtscsi_cmd_cache = NULL;
 	}
-	if (virtioscsi_online)
-		cpuhp_remove_multi_state(virtioscsi_online);
-	cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD);
 	return ret;
 }
 
 static void __exit fini(void)
 {
 	unregister_virtio_driver(&virtio_scsi_driver);
-	cpuhp_remove_multi_state(virtioscsi_online);
-	cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD);
 	mempool_destroy(virtscsi_cmd_pool);
 	kmem_cache_destroy(virtscsi_cmd_cache);
 }
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 921acaaa1601..01aea80a503e 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -26,7 +26,6 @@ enum cpuhp_state {
 	CPUHP_ARM_OMAP_WAKE_DEAD,
 	CPUHP_IRQ_POLL_DEAD,
 	CPUHP_BLOCK_SOFTIRQ_DEAD,
-	CPUHP_VIRT_SCSI_DEAD,
 	CPUHP_ACPI_CPUDRV_DEAD,
 	CPUHP_S390_PFAULT_DEAD,
 	CPUHP_BLK_MQ_DEAD,
-- 
GitLab


From 41139ac3cd76c6dff8286102a8ac62933c680463 Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Mon, 20 Feb 2017 09:12:58 +0800
Subject: [PATCH 262/898] ACPI: APEI: Fix BERT resources conflict with ACPI NVS
 area

It was reported that on some machines, there is overlap between ACPI
NVS area and BERT address range.  This appears reasonable because BERT
contents need to be non-volatile across reboot.  But this will cause
resources conflict in current Linux kernel implementation because the
ACPI NVS area is marked as busy.  The resource conflict is fixed via
excluding the ACPI NVS area when requesting IO resources for BERT.
When accessing the BERT contents, the whole BERT address range will be
ioremapped and accessed.

Reported-and-tested-by: Hans Kristian Rosbach <hansr@raskesider.no>
Signed-off-by: Ying Huang <ying.huang@intel.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/bert.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c
index a05b5c0cf181..12771fcf0417 100644
--- a/drivers/acpi/apei/bert.c
+++ b/drivers/acpi/apei/bert.c
@@ -97,6 +97,7 @@ static int __init bert_check_table(struct acpi_table_bert *bert_tab)
 
 static int __init bert_init(void)
 {
+	struct apei_resources bert_resources;
 	struct acpi_bert_region *boot_error_region;
 	struct acpi_table_bert *bert_tab;
 	unsigned int region_len;
@@ -127,13 +128,14 @@ static int __init bert_init(void)
 	}
 
 	region_len = bert_tab->region_length;
-	if (!request_mem_region(bert_tab->address, region_len, "APEI BERT")) {
-		pr_err("Can't request iomem region <%016llx-%016llx>.\n",
-		       (unsigned long long)bert_tab->address,
-		       (unsigned long long)bert_tab->address + region_len - 1);
-		return -EIO;
-	}
-
+	apei_resources_init(&bert_resources);
+	rc = apei_resources_add(&bert_resources, bert_tab->address,
+				region_len, true);
+	if (rc)
+		return rc;
+	rc = apei_resources_request(&bert_resources, "APEI BERT");
+	if (rc)
+		goto out_fini;
 	boot_error_region = ioremap_cache(bert_tab->address, region_len);
 	if (boot_error_region) {
 		bert_print_all(boot_error_region, region_len);
@@ -142,7 +144,9 @@ static int __init bert_init(void)
 		rc = -ENOMEM;
 	}
 
-	release_mem_region(bert_tab->address, region_len);
+	apei_resources_release(&bert_resources);
+out_fini:
+	apei_resources_fini(&bert_resources);
 
 	return rc;
 }
-- 
GitLab


From dcc235279a52d49023d4f1af7c3ed468a97015ae Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 27 Feb 2017 21:29:03 +0100
Subject: [PATCH 263/898] gcc-plugins: fix sancov_plugin for gcc-5
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The name of the local variable was inadvertantly changed from
sancov_plugin_pass_info to sancov_pass_info:

scripts/gcc-plugins/sancov_plugin.c: In function ‘int plugin_init(plugin_name_args*, plugin_gcc_version*)’:
scripts/gcc-plugins/sancov_plugin.c:136:67: error: ‘sancov_plugin_pass_info’ was not declared in this scope

This changes the conditional reference to this variable as well.

Fixes: 5a45a4c5c3f5 ("gcc-plugins: consolidate on PASS_INFO macro")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 scripts/gcc-plugins/sancov_plugin.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c
index 9b0b5cbc5b89..0f98634c20a0 100644
--- a/scripts/gcc-plugins/sancov_plugin.c
+++ b/scripts/gcc-plugins/sancov_plugin.c
@@ -133,7 +133,7 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gc
 #if BUILDING_GCC_VERSION < 6000
 	register_callback(plugin_name, PLUGIN_START_UNIT, &sancov_start_unit, NULL);
 	register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, (void *)&gt_ggc_r_gt_sancov);
-	register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_plugin_pass_info);
+	register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_pass_info);
 #endif
 
 	return 0;
-- 
GitLab


From 90ec7c9dff07d676c0b9b499286b931005c6b051 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 27 Feb 2017 21:31:43 +0100
Subject: [PATCH 264/898] scsi: lpfc: use div_u64 for 64-bit division

The new debugfs output causes a link error on 32-bit architectures:

ERROR: "__aeabi_uldivmod" [drivers/scsi/lpfc/lpfc.ko] undefined!

This code is not performance critical, so we can simply use div_u64().

[mkp: fixed up whitespace]

Fixes: bd2cdd5e400f ("scsi: lpfc: NVME Initiator: Add debugfs support")
Fixes: 2b65e18202fd ("scsi: lpfc: NVME Target: Add debugfs support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_debugfs.c | 64 ++++++++++++++++----------------
 1 file changed, 32 insertions(+), 32 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 599fde4ea8b1..9f4798e9d938 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -873,8 +873,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 		len += snprintf(
 			buf + len, PAGE_SIZE - len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg1_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg1_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg1_min,
 			phba->ktime_seg1_max);
 		len += snprintf(
@@ -884,8 +884,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 		len += snprintf(
 			buf + len, PAGE_SIZE - len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg2_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg2_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg2_min,
 			phba->ktime_seg2_max);
 		len += snprintf(
@@ -895,8 +895,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 		len += snprintf(
 			buf + len, PAGE_SIZE - len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg3_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg3_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg3_min,
 			phba->ktime_seg3_max);
 		len += snprintf(
@@ -906,17 +906,17 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 		len += snprintf(
 			buf + len, PAGE_SIZE - len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg4_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg4_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg4_min,
 			phba->ktime_seg4_max);
 		len += snprintf(
 			buf + len, PAGE_SIZE - len,
 			"Total IO avg time: %08lld\n",
-			((phba->ktime_seg1_total +
+			div_u64(phba->ktime_seg1_total +
 			phba->ktime_seg2_total  +
 			phba->ktime_seg3_total +
-			phba->ktime_seg4_total) /
+			phba->ktime_seg4_total,
 			phba->ktime_data_samples));
 		return len;
 	}
@@ -935,8 +935,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"cmd pass to NVME Layer\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg1_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg1_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg1_min,
 			phba->ktime_seg1_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -944,8 +944,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"-to- Driver rcv cmd OP (action)\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg2_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg2_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg2_min,
 			phba->ktime_seg2_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -953,8 +953,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"Firmware WQ doorbell: cmd\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg3_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg3_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg3_min,
 			phba->ktime_seg3_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -962,8 +962,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"-to- MSI-X ISR for cmd cmpl\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg4_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg4_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg4_min,
 			phba->ktime_seg4_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -971,8 +971,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"-to- NVME layer passed cmd done\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg5_total /
-			phba->ktime_data_samples,
+			div_u64(phba->ktime_seg5_total,
+				phba->ktime_data_samples),
 			phba->ktime_seg5_min,
 			phba->ktime_seg5_max);
 
@@ -983,8 +983,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 		len += snprintf(buf + len, PAGE_SIZE-len,
 				"avg:%08lld min:%08lld "
 				"max %08lld\n",
-				phba->ktime_seg10_total /
-				phba->ktime_data_samples,
+				div_u64(phba->ktime_seg10_total,
+					phba->ktime_data_samples),
 				phba->ktime_seg10_min,
 				phba->ktime_seg10_max);
 		return len;
@@ -995,8 +995,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"-to- Driver rcv rsp status OP\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg6_total /
-			phba->ktime_status_samples,
+			div_u64(phba->ktime_seg6_total,
+				phba->ktime_status_samples),
 			phba->ktime_seg6_min,
 			phba->ktime_seg6_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -1004,8 +1004,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"-to- Firmware WQ doorbell: status\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg7_total /
-			phba->ktime_status_samples,
+			div_u64(phba->ktime_seg7_total,
+				phba->ktime_status_samples),
 			phba->ktime_seg7_min,
 			phba->ktime_seg7_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -1013,8 +1013,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			" -to- MSI-X ISR for status cmpl\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg8_total /
-			phba->ktime_status_samples,
+			div_u64(phba->ktime_seg8_total,
+				phba->ktime_status_samples),
 			phba->ktime_seg8_min,
 			phba->ktime_seg8_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -1022,8 +1022,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"-to- NVME layer passed status done\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg9_total /
-			phba->ktime_status_samples,
+			div_u64(phba->ktime_seg9_total,
+				phba->ktime_status_samples),
 			phba->ktime_seg9_min,
 			phba->ktime_seg9_max);
 	len += snprintf(buf + len, PAGE_SIZE-len,
@@ -1031,8 +1031,8 @@ lpfc_debugfs_nvmektime_data(struct lpfc_vport *vport, char *buf, int size)
 			"cmd completed on wire\n");
 	len += snprintf(buf + len, PAGE_SIZE-len,
 			"avg:%08lld min:%08lld max %08lld\n",
-			phba->ktime_seg10_total /
-			phba->ktime_status_samples,
+			div_u64(phba->ktime_seg10_total,
+				phba->ktime_status_samples),
 			phba->ktime_seg10_min,
 			phba->ktime_seg10_max);
 	return len;
-- 
GitLab


From 825c6abbc316f496cd2b66e1fa72892cf4b49a9f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 27 Feb 2017 21:37:12 +0100
Subject: [PATCH 265/898] scsi: lpfc: use proper format string for dma_addr_t

dma_addr_t may be either u32 or u64, depending on the kernel configuration,
and we get a warning for the 32-bit case:

drivers/scsi/lpfc/lpfc_nvme.c: In function 'lpfc_nvme_ls_req':
drivers/scsi/lpfc/lpfc_logmsg.h:52:52: error: format '%llu' expects argument of type 'long long unsigned int', but argument 11 has type 'dma_addr_t {aka unsigned int}' [-Werror=format=]
drivers/scsi/lpfc/lpfc_logmsg.h:52:52: error: format '%llu' expects argument of type 'long long unsigned int', but argument 12 has type 'dma_addr_t {aka unsigned int}' [-Werror=format=]
drivers/scsi/lpfc/lpfc_nvme.c: In function 'lpfc_nvme_ls_abort':
drivers/scsi/lpfc/lpfc_logmsg.h:52:52: error: format '%llu' expects argument of type 'long long unsigned int', but argument 11 has type 'dma_addr_t {aka unsigned int}' [-Werror=format=]
drivers/scsi/lpfc/lpfc_logmsg.h:52:52: error: format '%llu' expects argument of type 'long long unsigned int', but argument 12 has type 'dma_addr_t {aka unsigned int}' [-Werror=format=]

printk has a special "%pad" format string that passes the dma address by
reference to solve this problem.

Fixes: 01649561a8b4 ("scsi: lpfc: NVME Initiator: bind to nvme_fc api")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_nvme.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 625b6589a34d..609a908ea9db 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -457,11 +457,11 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 	/* Expand print to include key fields. */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 			 "6051 ENTER.  lport %p, rport %p lsreq%p rqstlen:%d "
-			 "rsplen:%d %llux %llux\n",
+			 "rsplen:%d %pad %pad\n",
 			 pnvme_lport, pnvme_rport,
 			 pnvme_lsreq, pnvme_lsreq->rqstlen,
-			 pnvme_lsreq->rsplen, pnvme_lsreq->rqstdma,
-			 pnvme_lsreq->rspdma);
+			 pnvme_lsreq->rsplen, &pnvme_lsreq->rqstdma,
+			 &pnvme_lsreq->rspdma);
 
 	vport->phba->fc4NvmeLsRequests++;
 
@@ -527,11 +527,11 @@ lpfc_nvme_ls_abort(struct nvme_fc_local_port *pnvme_lport,
 	/* Expand print to include key fields. */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS,
 			 "6040 ENTER.  lport %p, rport %p lsreq %p rqstlen:%d "
-			 "rsplen:%d %llux %llux\n",
+			 "rsplen:%d %pad %pad\n",
 			 pnvme_lport, pnvme_rport,
 			 pnvme_lsreq, pnvme_lsreq->rqstlen,
-			 pnvme_lsreq->rsplen, pnvme_lsreq->rqstdma,
-			 pnvme_lsreq->rspdma);
+			 pnvme_lsreq->rsplen, &pnvme_lsreq->rqstdma,
+			 &pnvme_lsreq->rspdma);
 
 	/*
 	 * Lock the ELS ring txcmplq and build a local list of all ELS IOs
-- 
GitLab


From fbdab3e7fd547e1ce558db1521659707bdf02cc6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 24 Feb 2017 14:43:30 +0000
Subject: [PATCH 266/898] scsi: aacraid: remove redundant zero check on ret

The check for ret being zero is redundant as a few statements earlier we
break out of the while loop if ret is non-zero.  Thus we can remove the
zero check and also the dead-code non-zero case too.

Detected by CoverityScan, CID#1411632 ("Logically Dead Code")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Dave Carroll <david.carroll@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 1994c7445b54..a3ad04293487 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -2508,8 +2508,7 @@ int aac_command_thread(void *data)
 			 && (now.tv_usec > (1000000 / HZ)))
 				difference = (((1000000 - now.tv_usec) * HZ)
 				  + 500000) / 1000000;
-			else if (ret == 0) {
-
+			else {
 				if (now.tv_usec > 500000)
 					++now.tv_sec;
 
@@ -2520,9 +2519,6 @@ int aac_command_thread(void *data)
 					ret = aac_send_hosttime(dev, &now);
 
 				difference = (long)(unsigned)update_interval*HZ;
-			} else {
-				/* retry shortly */
-				difference = 10 * HZ;
 			}
 			next_jiffies = jiffies + difference;
 			if (time_before(next_check_jiffies,next_jiffies))
-- 
GitLab


From 42a70abddd90374518057e989f5b7289b7b535d8 Mon Sep 17 00:00:00 2001
From: "Dupuis, Chad" <chad.dupuis@cavium.com>
Date: Fri, 24 Feb 2017 00:31:56 -0800
Subject: [PATCH 267/898] scsi: qedi: Fix memory leak in tmf response
 processing.

Signed-off-by: Manish Rangankar <manish.rangankar@cavium.com>
Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedi/qedi_fw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index b1d3904ae8fd..c9f0ef4e11b3 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -165,10 +165,9 @@ static void qedi_tmf_resp_work(struct work_struct *work)
 	iscsi_block_session(session->cls_session);
 	rval = qedi_cleanup_all_io(qedi, qedi_conn, qedi_cmd->task, true);
 	if (rval) {
-		clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
 		qedi_clear_task_idx(qedi, qedi_cmd->task_id);
 		iscsi_unblock_session(session->cls_session);
-		return;
+		goto exit_tmf_resp;
 	}
 
 	iscsi_unblock_session(session->cls_session);
@@ -177,6 +176,8 @@ static void qedi_tmf_resp_work(struct work_struct *work)
 	spin_lock(&session->back_lock);
 	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr, NULL, 0);
 	spin_unlock(&session->back_lock);
+
+exit_tmf_resp:
 	kfree(resp_hdr_ptr);
 	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
 }
-- 
GitLab


From 19d19e960598161be92a7e4828eb7706c6410ce6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 27 Feb 2017 09:38:11 +0100
Subject: [PATCH 268/898] mac80211: use driver-indicated transmitter STA only
 for data frames
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When I originally introduced using the driver-indicated station as an
optimisation to avoid the hashtable lookup/iteration, of course it
wasn't intended to really functionally change anything.

I neglected, however, to take into account VLAN interfaces, which have
the property that management and data frames are handled differently:
data frames go directly to the station and the VLAN while management
frames continue to be processed over the underlying/associated AP-type
interface. As a consequence, when a driver used this optimisation for
management frames and the user enabled VLANs, my change broke things
since any management frames, particularly disassoc/deauth, were missed
by hostapd.

Fix this by restoring the original code path for non-data frames, they
aren't critical for performance to begin with.

This fixes https://bugzilla.kernel.org/show_bug.cgi?id=194713.

Big thanks goes to Jarek who bisected the issue and provided a very
detailed bug report, including the crucial information that he was
using VLANs in his configuration.

Cc: stable@vger.kernel.org
Fixes: 771e846bea9e ("mac80211: allow passing transmitter station on RX")
Reported-and-tested-by: Jarek Kamiński <jarek@freeside.be>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 28cc494a774d..e48724a6725e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4086,15 +4086,17 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
 		     ieee80211_is_beacon(hdr->frame_control)))
 		ieee80211_scan_rx(local, skb);
 
-	if (pubsta) {
-		rx.sta = container_of(pubsta, struct sta_info, sta);
-		rx.sdata = rx.sta->sdata;
-		if (ieee80211_prepare_and_rx_handle(&rx, skb, true))
-			return;
-		goto out;
-	} else if (ieee80211_is_data(fc)) {
+	if (ieee80211_is_data(fc)) {
 		struct sta_info *sta, *prev_sta;
 
+		if (pubsta) {
+			rx.sta = container_of(pubsta, struct sta_info, sta);
+			rx.sdata = rx.sta->sdata;
+			if (ieee80211_prepare_and_rx_handle(&rx, skb, true))
+				return;
+			goto out;
+		}
+
 		prev_sta = NULL;
 
 		for_each_sta_info(local, hdr->addr2, sta, tmp) {
-- 
GitLab


From 3b30460c5b0ed762be75a004e924ec3f8711e032 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 27 Feb 2017 15:30:56 +0000
Subject: [PATCH 269/898] crypto: ccm - move cbcmac input off the stack

Commit f15f05b0a5de ("crypto: ccm - switch to separate cbcmac driver")
refactored the CCM driver to allow separate implementations of the
underlying MAC to be provided by a platform. However, in doing so, it
moved some data from the linear region to the stack, which violates the
SG constraints when the stack is virtually mapped.

So move idata/odata back to the request ctx struct, of which we can
reasonably expect that it has been allocated using kmalloc() et al.

Reported-by: Johannes Berg <johannes@sipsolutions.net>
Fixes: f15f05b0a5de ("crypto: ccm - switch to separate cbcmac driver")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ccm.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/crypto/ccm.c b/crypto/ccm.c
index 442848807a52..1ce37ae0ce56 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -45,6 +45,7 @@ struct crypto_rfc4309_req_ctx {
 
 struct crypto_ccm_req_priv_ctx {
 	u8 odata[16];
+	u8 idata[16];
 	u8 auth_tag[16];
 	u32 flags;
 	struct scatterlist src[3];
@@ -183,8 +184,8 @@ static int crypto_ccm_auth(struct aead_request *req, struct scatterlist *plain,
 	AHASH_REQUEST_ON_STACK(ahreq, ctx->mac);
 	unsigned int assoclen = req->assoclen;
 	struct scatterlist sg[3];
-	u8 odata[16];
-	u8 idata[16];
+	u8 *odata = pctx->odata;
+	u8 *idata = pctx->idata;
 	int ilen, err;
 
 	/* format control data for input */
-- 
GitLab


From d0a0b78de4a641ff0924687bfd5a9698f1a97f7a Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:30 +0200
Subject: [PATCH 270/898] btrfs: Make btrfs_log_all_parents take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 3806853cde08..cf45b264cff3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5287,15 +5287,15 @@ static int log_new_dir_dentries(struct btrfs_trans_handle *trans,
 }
 
 static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
-				 struct inode *inode,
+				 struct btrfs_inode *inode,
 				 struct btrfs_log_ctx *ctx)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_key key;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	const u64 ino = btrfs_ino(BTRFS_I(inode));
+	struct btrfs_root *root = inode->root;
+	const u64 ino = btrfs_ino(inode);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -5506,7 +5506,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * and has a link count of 2.
 	 */
 	if (BTRFS_I(inode)->last_unlink_trans > last_committed) {
-		ret = btrfs_log_all_parents(trans, orig_inode, ctx);
+		ret = btrfs_log_all_parents(trans, BTRFS_I(orig_inode), ctx);
 		if (ret)
 			goto end_trans;
 	}
-- 
GitLab


From 8e7611cf38765f1bf1324ed1190f1f8e76ab9546 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:31 +0200
Subject: [PATCH 271/898] btrfs: Make btrfs_insert_dir_item take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 2 +-
 fs/btrfs/dir-item.c    | 6 +++---
 fs/btrfs/inode.c       | 2 +-
 fs/btrfs/ioctl.c       | 2 +-
 fs/btrfs/transaction.c | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ad23a73ac7e7..97f84a80b479 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2982,7 +2982,7 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
 			  const char *name, int name_len);
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, const char *name,
-			  int name_len, struct inode *dir,
+			  int name_len, struct btrfs_inode *dir,
 			  struct btrfs_key *location, u8 type, u64 index);
 struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
 					     struct btrfs_root *root,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 724504a2d7ac..b13d9536d4de 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -120,7 +120,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
  */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 			  *root, const char *name, int name_len,
-			  struct inode *dir, struct btrfs_key *location,
+			  struct btrfs_inode *dir, struct btrfs_key *location,
 			  u8 type, u64 index)
 {
 	int ret = 0;
@@ -133,7 +133,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 	struct btrfs_disk_key disk_key;
 	u32 data_size;
 
-	key.objectid = btrfs_ino(BTRFS_I(dir));
+	key.objectid = btrfs_ino(dir);
 	key.type = BTRFS_DIR_ITEM_KEY;
 	key.offset = btrfs_name_hash(name, name_len);
 
@@ -174,7 +174,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 	btrfs_release_path(path);
 
 	ret2 = btrfs_insert_delayed_dir_index(trans, root->fs_info, name,
-			name_len, BTRFS_I(dir), &disk_key, type, index);
+			name_len, dir, &disk_key, type, index);
 out_free:
 	btrfs_free_path(path);
 	if (ret)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c38391e948d9..a23391b52ab1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6276,7 +6276,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		return ret;
 
 	ret = btrfs_insert_dir_item(trans, root, name, name_len,
-				    parent_inode, &key,
+				    BTRFS_I(parent_inode), &key,
 				    btrfs_inode_type(inode), index);
 	if (ret == -EEXIST || ret == -EOVERFLOW)
 		goto fail_dir_item;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d8539979b44f..a55361d9554d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -587,7 +587,7 @@ static noinline int create_subvol(struct inode *dir,
 	}
 
 	ret = btrfs_insert_dir_item(trans, root,
-				    name, namelen, dir, &key,
+				    name, namelen, BTRFS_I(dir), &key,
 				    BTRFS_FT_DIR, index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6b3e0fc2fe7a..294563216dd3 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1644,7 +1644,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				    dentry->d_name.name, dentry->d_name.len,
-				    parent_inode, &key,
+				    BTRFS_I(parent_inode), &key,
 				    BTRFS_FT_DIR, index);
 	/* We have check then name at the beginning, so it is impossible. */
 	BUG_ON(ret == -EEXIST || ret == -EOVERFLOW);
-- 
GitLab


From 4c570655f4f95609e9f682a36647f84b54b8a721 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:32 +0200
Subject: [PATCH 272/898] btrfs: make btrfs_set_inode_index_count take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a23391b52ab1..226b5a9fdf0d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5978,15 +5978,15 @@ static int btrfs_update_time(struct inode *inode, struct timespec *now,
  * and then set the in-memory index_cnt variable to reflect
  * free sequence numbers
  */
-static int btrfs_set_inode_index_count(struct inode *inode)
+static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	struct btrfs_key key, found_key;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	int ret;
 
-	key.objectid = btrfs_ino(BTRFS_I(inode));
+	key.objectid = btrfs_ino(inode);
 	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = (u64)-1;
 
@@ -6009,7 +6009,7 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 	 * else has to start at 2
 	 */
 	if (path->slots[0] == 0) {
-		BTRFS_I(inode)->index_cnt = 2;
+		inode->index_cnt = 2;
 		goto out;
 	}
 
@@ -6018,13 +6018,13 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 
-	if (found_key.objectid != btrfs_ino(BTRFS_I(inode)) ||
+	if (found_key.objectid != btrfs_ino(inode) ||
 	    found_key.type != BTRFS_DIR_INDEX_KEY) {
-		BTRFS_I(inode)->index_cnt = 2;
+		inode->index_cnt = 2;
 		goto out;
 	}
 
-	BTRFS_I(inode)->index_cnt = found_key.offset + 1;
+	inode->index_cnt = found_key.offset + 1;
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -6041,7 +6041,7 @@ int btrfs_set_inode_index(struct inode *dir, u64 *index)
 	if (BTRFS_I(dir)->index_cnt == (u64)-1) {
 		ret = btrfs_inode_delayed_dir_index_count(BTRFS_I(dir));
 		if (ret) {
-			ret = btrfs_set_inode_index_count(dir);
+			ret = btrfs_set_inode_index_count(BTRFS_I(dir));
 			if (ret)
 				return ret;
 		}
-- 
GitLab


From 877574e2548bbfd792b0b1200d4b46eef54c05f5 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:33 +0200
Subject: [PATCH 273/898] btrfs: Make btrfs_set_inode_index take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c       | 22 +++++++++++-----------
 fs/btrfs/ioctl.c       |  2 +-
 fs/btrfs/transaction.c |  2 +-
 3 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 226b5a9fdf0d..d4ba1c4235de 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6034,21 +6034,21 @@ static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
  * helper to find a free sequence number in a given directory.  This current
  * code is very simple, later versions will do smarter things in the btree
  */
-int btrfs_set_inode_index(struct inode *dir, u64 *index)
+int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index)
 {
 	int ret = 0;
 
-	if (BTRFS_I(dir)->index_cnt == (u64)-1) {
-		ret = btrfs_inode_delayed_dir_index_count(BTRFS_I(dir));
+	if (dir->index_cnt == (u64)-1) {
+		ret = btrfs_inode_delayed_dir_index_count(dir);
 		if (ret) {
-			ret = btrfs_set_inode_index_count(BTRFS_I(dir));
+			ret = btrfs_set_inode_index_count(dir);
 			if (ret)
 				return ret;
 		}
 	}
 
-	*index = BTRFS_I(dir)->index_cnt;
-	BTRFS_I(dir)->index_cnt++;
+	*index = dir->index_cnt;
+	dir->index_cnt++;
 
 	return ret;
 }
@@ -6109,7 +6109,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	if (dir && name) {
 		trace_btrfs_inode_request(dir);
 
-		ret = btrfs_set_inode_index(dir, index);
+		ret = btrfs_set_inode_index(BTRFS_I(dir), index);
 		if (ret) {
 			btrfs_free_path(path);
 			iput(inode);
@@ -6490,7 +6490,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	if (inode->i_nlink >= BTRFS_LINK_MAX)
 		return -EMLINK;
 
-	err = btrfs_set_inode_index(dir, &index);
+	err = btrfs_set_inode_index(BTRFS_I(dir), &index);
 	if (err)
 		goto fail;
 
@@ -9480,10 +9480,10 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	 * We need to find a free sequence number both in the source and
 	 * in the destination directory for the exchange.
 	 */
-	ret = btrfs_set_inode_index(new_dir, &old_idx);
+	ret = btrfs_set_inode_index(BTRFS_I(new_dir), &old_idx);
 	if (ret)
 		goto out_fail;
-	ret = btrfs_set_inode_index(old_dir, &new_idx);
+	ret = btrfs_set_inode_index(BTRFS_I(old_dir), &new_idx);
 	if (ret)
 		goto out_fail;
 
@@ -9791,7 +9791,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (dest != root)
 		btrfs_record_root_in_trans(trans, dest);
 
-	ret = btrfs_set_inode_index(new_dir, &index);
+	ret = btrfs_set_inode_index(BTRFS_I(new_dir), &index);
 	if (ret)
 		goto out_fail;
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a55361d9554d..628d1b180cee 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -580,7 +580,7 @@ static noinline int create_subvol(struct inode *dir,
 	/*
 	 * insert the directory item
 	 */
-	ret = btrfs_set_inode_index(dir, &index);
+	ret = btrfs_set_inode_index(BTRFS_I(dir), &index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 294563216dd3..05c2bbff2a28 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1505,7 +1505,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	/*
 	 * insert the directory item
 	 */
-	ret = btrfs_set_inode_index(parent_inode, &index);
+	ret = btrfs_set_inode_index(BTRFS_I(parent_inode), &index);
 	BUG_ON(ret); /* -ENOMEM */
 
 	/* check if there is a file/dir which has the same name. */
-- 
GitLab


From 6ef06d27903d9c15505dc1a3ccf424f5018562f7 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:34 +0200
Subject: [PATCH 274/898] btrfs: Make btrfs_i_size_write take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h      |  6 +++---
 fs/btrfs/delayed-inode.c    |  2 +-
 fs/btrfs/free-space-cache.c |  2 +-
 fs/btrfs/inode.c            | 19 +++++++++----------
 fs/btrfs/ioctl.c            |  4 ++--
 fs/btrfs/transaction.c      |  2 +-
 fs/btrfs/tree-log.c         |  2 +-
 7 files changed, 18 insertions(+), 19 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 819a6d27218a..46d117b77bd2 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -237,10 +237,10 @@ static inline u64 btrfs_ino(struct btrfs_inode *inode)
 	return ino;
 }
 
-static inline void btrfs_i_size_write(struct inode *inode, u64 size)
+static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size)
 {
-	i_size_write(inode, size);
-	BTRFS_I(inode)->disk_i_size = size;
+	i_size_write(&inode->vfs_inode, size);
+	inode->disk_i_size = size;
 }
 
 static inline bool btrfs_is_free_space_inode(struct inode *inode)
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index f7a6ee5ccc80..1aff676f0e5b 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1790,7 +1790,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 
 	i_uid_write(inode, btrfs_stack_inode_uid(inode_item));
 	i_gid_write(inode, btrfs_stack_inode_gid(inode_item));
-	btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
+	btrfs_i_size_write(BTRFS_I(inode), btrfs_stack_inode_size(inode_item));
 	inode->i_mode = btrfs_stack_inode_mode(inode_item);
 	set_nlink(inode, btrfs_stack_inode_nlink(inode_item));
 	inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 1a131f7d6c1b..c0f313cbbbf2 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -260,7 +260,7 @@ int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
 		btrfs_free_path(path);
 	}
 
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 	truncate_pagecache(inode, 0);
 
 	/*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d4ba1c4235de..4e9407a014d9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3617,7 +3617,7 @@ static int btrfs_read_locked_inode(struct inode *inode)
 	set_nlink(inode, btrfs_inode_nlink(leaf, inode_item));
 	i_uid_write(inode, btrfs_inode_uid(leaf, inode_item));
 	i_gid_write(inode, btrfs_inode_gid(leaf, inode_item));
-	btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
+	btrfs_i_size_write(BTRFS_I(inode), btrfs_inode_size(leaf, inode_item));
 
 	inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime);
 	inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime);
@@ -3988,8 +3988,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	btrfs_i_size_write(&dir->vfs_inode,
-			dir->vfs_inode.i_size - name_len * 2);
+	btrfs_i_size_write(dir, dir->vfs_inode.i_size - name_len * 2);
 	inode_inc_iversion(&inode->vfs_inode);
 	inode_inc_iversion(&dir->vfs_inode);
 	inode->vfs_inode.i_ctime = dir->vfs_inode.i_mtime =
@@ -4137,7 +4136,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
+	btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name_len * 2);
 	inode_inc_iversion(dir);
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ret = btrfs_update_inode_fallback(trans, root, dir);
@@ -4184,7 +4183,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 			BTRFS_I(d_inode(dentry)), dentry->d_name.name,
 			dentry->d_name.len);
 	if (!err) {
-		btrfs_i_size_write(inode, 0);
+		btrfs_i_size_write(BTRFS_I(inode), 0);
 		/*
 		 * Propagate the last_unlink_trans value of the deleted dir to
 		 * its parent directory. This is to prevent an unrecoverable
@@ -5221,7 +5220,7 @@ void btrfs_evict_inode(struct inode *inode)
 	rsv->failfast = 1;
 	global_rsv = &fs_info->global_block_rsv;
 
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 
 	/*
 	 * This is a bit simpler than btrfs_truncate since we've already
@@ -6285,7 +6284,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	btrfs_i_size_write(parent_inode, parent_inode->i_size +
+	btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size +
 			   name_len * 2);
 	inode_inc_iversion(parent_inode);
 	parent_inode->i_mtime = parent_inode->i_ctime =
@@ -6589,7 +6588,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (err)
 		goto out_fail_inode;
 
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
 		goto out_fail_inode;
@@ -9205,7 +9204,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 	inode->i_fop = &btrfs_dir_file_operations;
 
 	set_nlink(inode, 1);
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 	unlock_new_inode(inode);
 
 	err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
@@ -10232,7 +10231,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &btrfs_symlink_aops;
 	inode_set_bytes(inode, name_len);
-	btrfs_i_size_write(inode, name_len);
+	btrfs_i_size_write(BTRFS_I(inode), name_len);
 	err = btrfs_update_inode(trans, root, inode);
 	/*
 	 * Last step, add directory indexes for our symlink inode. This is the
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 628d1b180cee..86f993c958ba 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -594,7 +594,7 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
-	btrfs_i_size_write(dir, dir->i_size + namelen * 2);
+	btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2);
 	ret = btrfs_update_inode(trans, root, dir);
 	BUG_ON(ret);
 
@@ -3298,7 +3298,7 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 	if (endoff > destoff + olen)
 		endoff = destoff + olen;
 	if (endoff > inode->i_size)
-		btrfs_i_size_write(inode, endoff);
+		btrfs_i_size_write(BTRFS_I(inode), endoff);
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret) {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 05c2bbff2a28..61b807de3e16 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1653,7 +1653,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	btrfs_i_size_write(parent_inode, parent_inode->i_size +
+	btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size +
 					 dentry->d_name.len * 2);
 	parent_inode->i_mtime = parent_inode->i_ctime =
 		current_time(parent_inode);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index cf45b264cff3..071f64944711 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1780,7 +1780,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 out:
 	btrfs_release_path(path);
 	if (!ret && update_size) {
-		btrfs_i_size_write(dir, dir->i_size + name_len * 2);
+		btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name_len * 2);
 		ret = btrfs_update_inode(trans, root, dir);
 	}
 	kfree(name);
-- 
GitLab


From 70ddc553b5522b96e65a162be1cecba532630841 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:35 +0200
Subject: [PATCH 275/898] btrfs: make btrfs_is_free_space_inode take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h |  8 ++++----
 fs/btrfs/ctree.h       |  2 +-
 fs/btrfs/extent-tree.c |  4 ++--
 fs/btrfs/file-item.c   |  2 +-
 fs/btrfs/inode.c       | 23 ++++++++++++-----------
 5 files changed, 20 insertions(+), 19 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 46d117b77bd2..36eca5464e1b 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -243,14 +243,14 @@ static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size)
 	inode->disk_i_size = size;
 }
 
-static inline bool btrfs_is_free_space_inode(struct inode *inode)
+static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 
 	if (root == root->fs_info->tree_root &&
-	    btrfs_ino(BTRFS_I(inode)) != BTRFS_BTREE_INODE_OBJECTID)
+	    btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID)
 		return true;
-	if (BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID)
+	if (inode->location.objectid == BTRFS_FREE_INO_OBJECTID)
 		return true;
 	return false;
 }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 97f84a80b479..8ab0ce65a218 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3123,7 +3123,7 @@ static inline void btrfs_force_ra(struct address_space *mapping,
 }
 
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
-int btrfs_set_inode_index(struct inode *dir, u64 *index);
+int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root,
 		       struct btrfs_inode *dir, struct btrfs_inode *inode,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c35b96633554..b8a172e65619 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4148,7 +4148,7 @@ int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
 	/* make sure bytes are sectorsize aligned */
 	bytes = ALIGN(bytes, fs_info->sectorsize);
 
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		need_commit = 0;
 		ASSERT(current->journal_info);
 	}
@@ -5947,7 +5947,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	 * If we have a transaction open (can happen if we call truncate_block
 	 * from truncate), then we need FLUSH_LIMIT so we don't deadlock.
 	 */
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		flush = BTRFS_RESERVE_NO_FLUSH;
 		delalloc_lock = false;
 	} else if (current->journal_info) {
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index f7b9a92ad56d..a8a0dd217084 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -214,7 +214,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	 * read from the commit root and sidestep a nasty deadlock
 	 * between reading the free space cache and updating the csum tree.
 	 */
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		path->search_commit_root = 1;
 		path->skip_locking = 1;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4e9407a014d9..a465a927395e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -933,7 +933,7 @@ static noinline int cow_file_range(struct inode *inode,
 	struct extent_map *em;
 	int ret = 0;
 
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		WARN_ON_ONCE(1);
 		ret = -EINVAL;
 		goto out_unlock;
@@ -1231,7 +1231,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 		return -ENOMEM;
 	}
 
-	nolock = btrfs_is_free_space_inode(inode);
+	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
 
 	cow_start = (u64)-1;
 	cur_offset = start;
@@ -1670,7 +1670,7 @@ static void btrfs_set_bit_hook(struct inode *inode,
 	if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
 		u64 len = state->end + 1 - state->start;
-		bool do_list = !btrfs_is_free_space_inode(inode);
+		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
 
 		if (*bits & EXTENT_FIRST_DELALLOC) {
 			*bits &= ~EXTENT_FIRST_DELALLOC;
@@ -1720,7 +1720,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 	 */
 	if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
-		bool do_list = !btrfs_is_free_space_inode(inode);
+		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
 
 		if (*bits & EXTENT_FIRST_DELALLOC) {
 			*bits &= ~EXTENT_FIRST_DELALLOC;
@@ -1854,7 +1854,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
-	if (btrfs_is_free_space_inode(inode))
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
 
 	if (bio_op(bio) != REQ_OP_WRITE) {
@@ -2793,7 +2793,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	bool nolock;
 	bool truncated = false;
 
-	nolock = btrfs_is_free_space_inode(inode);
+	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
 
 	if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
 		ret = -EIO;
@@ -2993,7 +2993,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 					    end - start + 1, uptodate))
 		return 0;
 
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		wq = fs_info->endio_freespace_worker;
 		func = btrfs_freespace_write_helper;
 	} else {
@@ -3865,7 +3865,7 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	 * The data relocation inode should also be directly updated
 	 * without delay
 	 */
-	if (!btrfs_is_free_space_inode(inode)
+	if (!btrfs_is_free_space_inode(BTRFS_I(inode))
 	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
 	    && !test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
 		btrfs_update_root_times(trans, root);
@@ -4319,7 +4319,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	 * for non-free space inodes and ref cows, we want to back off from
 	 * time to time
 	 */
-	if (!btrfs_is_free_space_inode(inode) &&
+	if (!btrfs_is_free_space_inode(BTRFS_I(inode)) &&
 	    test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		be_nice = 1;
 
@@ -5180,7 +5180,7 @@ void btrfs_evict_inode(struct inode *inode)
 	if (inode->i_nlink &&
 	    ((btrfs_root_refs(&root->root_item) != 0 &&
 	      root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) ||
-	     btrfs_is_free_space_inode(inode)))
+	     btrfs_is_free_space_inode(BTRFS_I(inode))))
 		goto no_delete;
 
 	if (is_bad_inode(inode)) {
@@ -5897,7 +5897,8 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
 		return 0;
 
-	if (btrfs_fs_closing(root->fs_info) && btrfs_is_free_space_inode(inode))
+	if (btrfs_fs_closing(root->fs_info) &&
+			btrfs_is_free_space_inode(BTRFS_I(inode)))
 		nolock = true;
 
 	if (wbc->sync_mode == WB_SYNC_ALL) {
-- 
GitLab


From 04f4f916531adc7d2ca6fdb16a68b6f2ff2a8a3b Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:36 +0200
Subject: [PATCH 276/898] btrfs: make btrfs_alloc_data_chunk_ondemand take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 2 +-
 fs/btrfs/extent-tree.c | 8 ++++----
 fs/btrfs/file.c        | 3 ++-
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8ab0ce65a218..76e661d00822 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2687,7 +2687,7 @@ enum btrfs_flush_state {
 };
 
 int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
-int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes);
+int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
 void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b8a172e65619..c17493ee2d9d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4135,10 +4135,10 @@ static u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
 		(may_use_included ? s_info->bytes_may_use : 0);
 }
 
-int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
+int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
 {
 	struct btrfs_space_info *data_sinfo;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 used;
 	int ret = 0;
@@ -4148,7 +4148,7 @@ int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
 	/* make sure bytes are sectorsize aligned */
 	bytes = ALIGN(bytes, fs_info->sectorsize);
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(inode)) {
 		need_commit = 0;
 		ASSERT(current->journal_info);
 	}
@@ -4281,7 +4281,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
 	      round_down(start, fs_info->sectorsize);
 	start = round_down(start, fs_info->sectorsize);
 
-	ret = btrfs_alloc_data_chunk_ondemand(inode, len);
+	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len);
 	if (ret < 0)
 		return ret;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 18e5146df864..073bc975bbb6 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2747,7 +2747,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 	 *
 	 * For qgroup space, it will be checked later.
 	 */
-	ret = btrfs_alloc_data_chunk_ondemand(inode, alloc_end - alloc_start);
+	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode),
+			alloc_end - alloc_start);
 	if (ret < 0)
 		return ret;
 
-- 
GitLab


From baa3ba39b91bdfa270b3f6db6fdc81a1a6b4ab34 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:37 +0200
Subject: [PATCH 277/898] btrfs: Make drop_outstanding_extent take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c17493ee2d9d..19c2a9b6b52b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5846,7 +5846,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
  * reserved extents that need to be freed.  This must be called with
  * BTRFS_I(inode)->lock held.
  */
-static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
+static unsigned drop_outstanding_extent(struct btrfs_inode *inode,
+		u64 num_bytes)
 {
 	unsigned drop_inode_space = 0;
 	unsigned dropped_extents = 0;
@@ -5854,25 +5855,23 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
 
 	num_extents = count_max_extents(num_bytes);
 	ASSERT(num_extents);
-	ASSERT(BTRFS_I(inode)->outstanding_extents >= num_extents);
-	BTRFS_I(inode)->outstanding_extents -= num_extents;
+	ASSERT(inode->outstanding_extents >= num_extents);
+	inode->outstanding_extents -= num_extents;
 
-	if (BTRFS_I(inode)->outstanding_extents == 0 &&
+	if (inode->outstanding_extents == 0 &&
 	    test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-			       &BTRFS_I(inode)->runtime_flags))
+			       &inode->runtime_flags))
 		drop_inode_space = 1;
 
 	/*
 	 * If we have more or the same amount of outstanding extents than we have
 	 * reserved then we need to leave the reserved extents count alone.
 	 */
-	if (BTRFS_I(inode)->outstanding_extents >=
-	    BTRFS_I(inode)->reserved_extents)
+	if (inode->outstanding_extents >= inode->reserved_extents)
 		return drop_inode_space;
 
-	dropped_extents = BTRFS_I(inode)->reserved_extents -
-		BTRFS_I(inode)->outstanding_extents;
-	BTRFS_I(inode)->reserved_extents -= dropped_extents;
+	dropped_extents = inode->reserved_extents - inode->outstanding_extents;
+	inode->reserved_extents -= dropped_extents;
 	return dropped_extents + drop_inode_space;
 }
 
@@ -6015,7 +6014,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
 out_fail:
 	spin_lock(&BTRFS_I(inode)->lock);
-	dropped = drop_outstanding_extent(inode, num_bytes);
+	dropped = drop_outstanding_extent(BTRFS_I(inode), num_bytes);
 	/*
 	 * If the inodes csum_bytes is the same as the original
 	 * csum_bytes then we know we haven't raced with any free()ers
@@ -6094,7 +6093,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&BTRFS_I(inode)->lock);
-	dropped = drop_outstanding_extent(inode, num_bytes);
+	dropped = drop_outstanding_extent(BTRFS_I(inode), num_bytes);
 
 	if (num_bytes)
 		to_free = calc_csum_metadata_size(inode, num_bytes, 0);
-- 
GitLab


From 0e6bf9b13caa41b34592369c47faab916233343b Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:38 +0200
Subject: [PATCH 278/898] btrfs: Make calc_csum_metadata_size take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 19c2a9b6b52b..1fe062685253 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5893,24 +5893,21 @@ static unsigned drop_outstanding_extent(struct btrfs_inode *inode,
  *
  * This must be called with BTRFS_I(inode)->lock held.
  */
-static u64 calc_csum_metadata_size(struct inode *inode, u64 num_bytes,
+static u64 calc_csum_metadata_size(struct btrfs_inode *inode, u64 num_bytes,
 				   int reserve)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 old_csums, num_csums;
 
-	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM &&
-	    BTRFS_I(inode)->csum_bytes == 0)
+	if (inode->flags & BTRFS_INODE_NODATASUM && inode->csum_bytes == 0)
 		return 0;
 
-	old_csums = btrfs_csum_bytes_to_leaves(fs_info,
-					       BTRFS_I(inode)->csum_bytes);
+	old_csums = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
 	if (reserve)
-		BTRFS_I(inode)->csum_bytes += num_bytes;
+		inode->csum_bytes += num_bytes;
 	else
-		BTRFS_I(inode)->csum_bytes -= num_bytes;
-	num_csums = btrfs_csum_bytes_to_leaves(fs_info,
-					       BTRFS_I(inode)->csum_bytes);
+		inode->csum_bytes -= num_bytes;
+	num_csums = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
 
 	/* No change, no need to reserve more */
 	if (old_csums == num_csums)
@@ -5974,7 +5971,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
 	/* We always want to reserve a slot for updating the inode. */
 	to_reserve = btrfs_calc_trans_metadata_size(fs_info, nr_extents + 1);
-	to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+	to_reserve += calc_csum_metadata_size(BTRFS_I(inode), num_bytes, 1);
 	csum_bytes = BTRFS_I(inode)->csum_bytes;
 	spin_unlock(&BTRFS_I(inode)->lock);
 
@@ -6021,7 +6018,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	 * so we can just reduce our inodes csum bytes and carry on.
 	 */
 	if (BTRFS_I(inode)->csum_bytes == csum_bytes) {
-		calc_csum_metadata_size(inode, num_bytes, 0);
+		calc_csum_metadata_size(BTRFS_I(inode), num_bytes, 0);
 	} else {
 		u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes;
 		u64 bytes;
@@ -6036,7 +6033,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		 */
 		bytes = csum_bytes - BTRFS_I(inode)->csum_bytes;
 		BTRFS_I(inode)->csum_bytes = csum_bytes;
-		to_free = calc_csum_metadata_size(inode, bytes, 0);
+		to_free = calc_csum_metadata_size(BTRFS_I(inode), bytes, 0);
 
 
 		/*
@@ -6046,7 +6043,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		 */
 		BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes;
 		bytes = csum_bytes - orig_csum_bytes;
-		bytes = calc_csum_metadata_size(inode, bytes, 0);
+		bytes = calc_csum_metadata_size(BTRFS_I(inode), bytes, 0);
 
 		/*
 		 * Now reset ->csum_bytes to what it should be.  If bytes is
@@ -6096,7 +6093,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 	dropped = drop_outstanding_extent(BTRFS_I(inode), num_bytes);
 
 	if (num_bytes)
-		to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+		to_free = calc_csum_metadata_size(BTRFS_I(inode), num_bytes, 0);
 	spin_unlock(&BTRFS_I(inode)->lock);
 	if (dropped > 0)
 		to_free += btrfs_calc_trans_metadata_size(fs_info, dropped);
-- 
GitLab


From 8ed7a2a0e0732b62d925041ff04a5e9621e0e58b Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:39 +0200
Subject: [PATCH 279/898] btrfs: Make btrfs_orphan_reserve_metadata take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  2 +-
 fs/btrfs/extent-tree.c | 10 +++++-----
 fs/btrfs/inode.c       |  2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 76e661d00822..52af63e1d9a0 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2695,7 +2695,7 @@ void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 				  struct btrfs_fs_info *fs_info);
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct inode *inode);
+				  struct btrfs_inode *inode);
 void btrfs_orphan_release_metadata(struct inode *inode);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1fe062685253..8156964abc10 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5742,10 +5742,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
 
 /* Can only return 0 or -ENOSPC */
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct inode *inode)
+				  struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	/*
 	 * We always use trans->block_rsv here as we will have reserved space
 	 * for our orphan when starting the transaction, using get_block_rsv()
@@ -5762,8 +5762,8 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 	 */
 	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	trace_btrfs_space_reservation(fs_info, "orphan",
-				      btrfs_ino(BTRFS_I(inode)), num_bytes, 1);
+	trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode), 
+			num_bytes, 1);
 	return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a465a927395e..12345d4f25a5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3215,7 +3215,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 
 	/* grab metadata reservation from transaction handle */
 	if (reserve) {
-		ret = btrfs_orphan_reserve_metadata(trans, inode);
+		ret = btrfs_orphan_reserve_metadata(trans, BTRFS_I(inode));
 		ASSERT(!ret);
 		if (ret) {
 			atomic_dec(&root->orphan_inodes);
-- 
GitLab


From 703b391a0362e0ee35260dd16d7d0c7a12fef0e6 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:40 +0200
Subject: [PATCH 280/898] btrfs: Make btrfs_orphan_release_metadata take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  2 +-
 fs/btrfs/extent-tree.c | 10 +++++-----
 fs/btrfs/inode.c       |  4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 52af63e1d9a0..8eb07a9dfa6a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2696,7 +2696,7 @@ void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 				  struct btrfs_inode *inode);
-void btrfs_orphan_release_metadata(struct inode *inode);
+void btrfs_orphan_release_metadata(struct btrfs_inode *inode);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
 				     int nitems,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 8156964abc10..2aa665674329 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5767,14 +5767,14 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 	return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 }
 
-void btrfs_orphan_release_metadata(struct inode *inode)
+void btrfs_orphan_release_metadata(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	trace_btrfs_space_reservation(fs_info, "orphan",
-				      btrfs_ino(BTRFS_I(inode)), num_bytes, 0);
+	trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode),
+			num_bytes, 0);
 	btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, num_bytes);
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 12345d4f25a5..8a14b47b4dc0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3237,7 +3237,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 			if (reserve) {
 				clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
 					  &BTRFS_I(inode)->runtime_flags);
-				btrfs_orphan_release_metadata(inode);
+				btrfs_orphan_release_metadata(BTRFS_I(inode));
 			}
 			if (ret != -EEXIST) {
 				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
@@ -3291,7 +3291,7 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
 	}
 
 	if (release_rsv)
-		btrfs_orphan_release_metadata(inode);
+		btrfs_orphan_release_metadata(BTRFS_I(inode));
 
 	return ret;
 }
-- 
GitLab


From 9f3db423f98c5c6c53b47f4bb2729901500bc330 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:41 +0200
Subject: [PATCH 281/898] btrfs: Make btrfs_delalloc_reserve_metadata take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  2 +-
 fs/btrfs/extent-tree.c | 69 +++++++++++++++++++++---------------------
 fs/btrfs/file.c        |  3 +-
 fs/btrfs/relocation.c  |  3 +-
 4 files changed, 39 insertions(+), 38 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8eb07a9dfa6a..23dcc42f479b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2703,7 +2703,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     u64 *qgroup_reserved, bool use_global_rsv);
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
-int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
 void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
 int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
 void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2aa665674329..4db3cf4675a1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5920,10 +5920,10 @@ static u64 calc_csum_metadata_size(struct btrfs_inode *inode, u64 num_bytes,
 	return btrfs_calc_trans_metadata_size(fs_info, old_csums - num_csums);
 }
 
-int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = &fs_info->delalloc_block_rsv;
 	u64 to_reserve = 0;
 	u64 csum_bytes;
@@ -5943,7 +5943,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	 * If we have a transaction open (can happen if we call truncate_block
 	 * from truncate), then we need FLUSH_LIMIT so we don't deadlock.
 	 */
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(inode)) {
 		flush = BTRFS_RESERVE_NO_FLUSH;
 		delalloc_lock = false;
 	} else if (current->journal_info) {
@@ -5955,25 +5955,24 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		schedule_timeout(1);
 
 	if (delalloc_lock)
-		mutex_lock(&BTRFS_I(inode)->delalloc_mutex);
+		mutex_lock(&inode->delalloc_mutex);
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
 	nr_extents = count_max_extents(num_bytes);
-	BTRFS_I(inode)->outstanding_extents += nr_extents;
+	inode->outstanding_extents += nr_extents;
 
 	nr_extents = 0;
-	if (BTRFS_I(inode)->outstanding_extents >
-	    BTRFS_I(inode)->reserved_extents)
-		nr_extents += BTRFS_I(inode)->outstanding_extents -
-			BTRFS_I(inode)->reserved_extents;
+	if (inode->outstanding_extents > inode->reserved_extents)
+		nr_extents += inode->outstanding_extents -
+			inode->reserved_extents;
 
 	/* We always want to reserve a slot for updating the inode. */
 	to_reserve = btrfs_calc_trans_metadata_size(fs_info, nr_extents + 1);
-	to_reserve += calc_csum_metadata_size(BTRFS_I(inode), num_bytes, 1);
-	csum_bytes = BTRFS_I(inode)->csum_bytes;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+	csum_bytes = inode->csum_bytes;
+	spin_unlock(&inode->lock);
 
 	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
 		ret = btrfs_qgroup_reserve_meta(root,
@@ -5989,38 +5988,38 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		goto out_fail;
 	}
 
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
 	if (test_and_set_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-			     &BTRFS_I(inode)->runtime_flags)) {
+			     &inode->runtime_flags)) {
 		to_reserve -= btrfs_calc_trans_metadata_size(fs_info, 1);
 		release_extra = true;
 	}
-	BTRFS_I(inode)->reserved_extents += nr_extents;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	inode->reserved_extents += nr_extents;
+	spin_unlock(&inode->lock);
 
 	if (delalloc_lock)
-		mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
+		mutex_unlock(&inode->delalloc_mutex);
 
 	if (to_reserve)
 		trace_btrfs_space_reservation(fs_info, "delalloc",
-				      btrfs_ino(BTRFS_I(inode)), to_reserve, 1);
+					      btrfs_ino(inode), to_reserve, 1);
 	if (release_extra)
 		btrfs_block_rsv_release(fs_info, block_rsv,
 				btrfs_calc_trans_metadata_size(fs_info, 1));
 	return 0;
 
 out_fail:
-	spin_lock(&BTRFS_I(inode)->lock);
-	dropped = drop_outstanding_extent(BTRFS_I(inode), num_bytes);
+	spin_lock(&inode->lock);
+	dropped = drop_outstanding_extent(inode, num_bytes);
 	/*
 	 * If the inodes csum_bytes is the same as the original
 	 * csum_bytes then we know we haven't raced with any free()ers
 	 * so we can just reduce our inodes csum bytes and carry on.
 	 */
-	if (BTRFS_I(inode)->csum_bytes == csum_bytes) {
-		calc_csum_metadata_size(BTRFS_I(inode), num_bytes, 0);
+	if (inode->csum_bytes == csum_bytes) {
+		calc_csum_metadata_size(inode, num_bytes, 0);
 	} else {
-		u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes;
+		u64 orig_csum_bytes = inode->csum_bytes;
 		u64 bytes;
 
 		/*
@@ -6031,9 +6030,9 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		 * number of bytes that were freed while we were trying our
 		 * reservation.
 		 */
-		bytes = csum_bytes - BTRFS_I(inode)->csum_bytes;
-		BTRFS_I(inode)->csum_bytes = csum_bytes;
-		to_free = calc_csum_metadata_size(BTRFS_I(inode), bytes, 0);
+		bytes = csum_bytes - inode->csum_bytes;
+		inode->csum_bytes = csum_bytes;
+		to_free = calc_csum_metadata_size(inode, bytes, 0);
 
 
 		/*
@@ -6041,9 +6040,9 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		 * been making this reservation and our ->csum_bytes were not
 		 * artificially inflated.
 		 */
-		BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes;
+		inode->csum_bytes = csum_bytes - num_bytes;
 		bytes = csum_bytes - orig_csum_bytes;
-		bytes = calc_csum_metadata_size(BTRFS_I(inode), bytes, 0);
+		bytes = calc_csum_metadata_size(inode, bytes, 0);
 
 		/*
 		 * Now reset ->csum_bytes to what it should be.  If bytes is
@@ -6053,23 +6052,23 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		 * need to do anything, the other free-ers did the correct
 		 * thing.
 		 */
-		BTRFS_I(inode)->csum_bytes = orig_csum_bytes - num_bytes;
+		inode->csum_bytes = orig_csum_bytes - num_bytes;
 		if (bytes > to_free)
 			to_free = bytes - to_free;
 		else
 			to_free = 0;
 	}
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_unlock(&inode->lock);
 	if (dropped)
 		to_free += btrfs_calc_trans_metadata_size(fs_info, dropped);
 
 	if (to_free) {
 		btrfs_block_rsv_release(fs_info, block_rsv, to_free);
 		trace_btrfs_space_reservation(fs_info, "delalloc",
-				      btrfs_ino(BTRFS_I(inode)), to_free, 0);
+					      btrfs_ino(inode), to_free, 0);
 	}
 	if (delalloc_lock)
-		mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
+		mutex_unlock(&inode->delalloc_mutex);
 	return ret;
 }
 
@@ -6137,7 +6136,7 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len)
 	ret = btrfs_check_data_free_space(inode, start, len);
 	if (ret < 0)
 		return ret;
-	ret = btrfs_delalloc_reserve_metadata(inode, len);
+	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);
 	if (ret < 0)
 		btrfs_free_reserved_data_space(inode, start, len);
 	return ret;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 073bc975bbb6..e32a92081547 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1599,7 +1599,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			}
 		}
 
-		ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
+		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
+				reserve_bytes);
 		if (ret) {
 			if (!only_release_metadata)
 				btrfs_free_reserved_data_space(inode, pos,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ddbde0f08365..4ee1490f086e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3203,7 +3203,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	index = (cluster->start - offset) >> PAGE_SHIFT;
 	last_index = (cluster->end - offset) >> PAGE_SHIFT;
 	while (index <= last_index) {
-		ret = btrfs_delalloc_reserve_metadata(inode, PAGE_SIZE);
+		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
+				PAGE_SIZE);
 		if (ret)
 			goto out;
 
-- 
GitLab


From 691fa059673b3b33c25d7925acb0a58e8204dbd6 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:42 +0200
Subject: [PATCH 282/898] btrfs: all btrfs_delalloc_release_metadata take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h            |  2 +-
 fs/btrfs/extent-tree.c      | 18 +++++++++---------
 fs/btrfs/file.c             |  5 +++--
 fs/btrfs/free-space-cache.c |  3 ++-
 fs/btrfs/inode-map.c        |  2 +-
 fs/btrfs/inode.c            |  7 ++++---
 fs/btrfs/relocation.c       |  4 ++--
 7 files changed, 22 insertions(+), 19 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 23dcc42f479b..7f7f3b60a73d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2704,7 +2704,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes);
 int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
 void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4db3cf4675a1..7b2313a4441e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6081,27 +6081,27 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
  * once we complete IO for a given set of bytes to release their metadata
  * reservations.
  */
-void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 to_free = 0;
 	unsigned dropped;
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
-	spin_lock(&BTRFS_I(inode)->lock);
-	dropped = drop_outstanding_extent(BTRFS_I(inode), num_bytes);
+	spin_lock(&inode->lock);
+	dropped = drop_outstanding_extent(inode, num_bytes);
 
 	if (num_bytes)
-		to_free = calc_csum_metadata_size(BTRFS_I(inode), num_bytes, 0);
-	spin_unlock(&BTRFS_I(inode)->lock);
+		to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+	spin_unlock(&inode->lock);
 	if (dropped > 0)
 		to_free += btrfs_calc_trans_metadata_size(fs_info, dropped);
 
 	if (btrfs_is_testing(fs_info))
 		return;
 
-	trace_btrfs_space_reservation(fs_info, "delalloc",
-				      btrfs_ino(BTRFS_I(inode)), to_free, 0);
+	trace_btrfs_space_reservation(fs_info, "delalloc", btrfs_ino(inode),
+				      to_free, 0);
 
 	btrfs_block_rsv_release(fs_info, &fs_info->delalloc_block_rsv, to_free);
 }
@@ -6159,7 +6159,7 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len)
  */
 void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len)
 {
-	btrfs_delalloc_release_metadata(inode, len);
+	btrfs_delalloc_release_metadata(BTRFS_I(inode), len);
 	btrfs_free_reserved_data_space(inode, start, len);
 }
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e32a92081547..0e30d14b4916 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1678,7 +1678,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 				spin_unlock(&BTRFS_I(inode)->lock);
 			}
 			if (only_release_metadata) {
-				btrfs_delalloc_release_metadata(inode,
+				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 								release_bytes);
 			} else {
 				u64 __pos;
@@ -1739,7 +1739,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	if (release_bytes) {
 		if (only_release_metadata) {
 			btrfs_end_write_no_snapshoting(root);
-			btrfs_delalloc_release_metadata(inode, release_bytes);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+					release_bytes);
 		} else {
 			btrfs_delalloc_release_space(inode,
 						round_down(pos, fs_info->sectorsize),
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index c0f313cbbbf2..7dcf0b100dcd 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -3545,7 +3545,8 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
 
 	if (ret) {
 		if (release_metadata)
-			btrfs_delalloc_release_metadata(inode, inode->i_size);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+					inode->i_size);
 #ifdef DEBUG
 		btrfs_err(fs_info,
 			  "failed to write free ino cache for root %llu",
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 3bbb8f095953..5c6c20ec64d8 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -499,7 +499,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
 					      prealloc, prealloc, &alloc_hint);
 	if (ret) {
-		btrfs_delalloc_release_metadata(inode, prealloc);
+		btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc);
 		goto out_put;
 	}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8a14b47b4dc0..dd0f1abdacd2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -316,7 +316,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
 	}
 
 	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
-	btrfs_delalloc_release_metadata(inode, end + 1 - start);
+	btrfs_delalloc_release_metadata(BTRFS_I(inode), end + 1 - start);
 	btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
 out:
 	/*
@@ -1737,7 +1737,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		 */
 		if (*bits & EXTENT_DO_ACCOUNTING &&
 		    root != fs_info->tree_root)
-			btrfs_delalloc_release_metadata(inode, len);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode), len);
 
 		/* For sanity tests. */
 		if (btrfs_is_testing(fs_info))
@@ -2914,7 +2914,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 			     ordered_extent->len - 1, &cached_state, GFP_NOFS);
 out:
 	if (root != fs_info->tree_root)
-		btrfs_delalloc_release_metadata(inode, ordered_extent->len);
+		btrfs_delalloc_release_metadata(BTRFS_I(inode),
+				ordered_extent->len);
 	if (trans)
 		btrfs_end_transaction(trans);
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 4ee1490f086e..e6470890ce26 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3216,7 +3216,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			page = find_or_create_page(inode->i_mapping, index,
 						   mask);
 			if (!page) {
-				btrfs_delalloc_release_metadata(inode,
+				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 							PAGE_SIZE);
 				ret = -ENOMEM;
 				goto out;
@@ -3235,7 +3235,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			if (!PageUptodate(page)) {
 				unlock_page(page);
 				put_page(page);
-				btrfs_delalloc_release_metadata(inode,
+				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 							PAGE_SIZE);
 				ret = -EIO;
 				goto out;
-- 
GitLab


From 6158e1ce1cc620df650ebdcfb3cc08a3d86f5a4c Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:43 +0200
Subject: [PATCH 283/898] btrfs: Make (__)btrfs_add_inode_defrag take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h |  2 +-
 fs/btrfs/file.c  | 22 +++++++++++-----------
 fs/btrfs/inode.c |  9 +++++----
 3 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7f7f3b60a73d..5246cbe4c17f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3215,7 +3215,7 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 int btrfs_auto_defrag_init(void);
 void btrfs_auto_defrag_exit(void);
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
-			   struct inode *inode);
+			   struct btrfs_inode *inode);
 int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
 void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0e30d14b4916..63645e86ad95 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -92,10 +92,10 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1,
  * If an existing record is found the defrag item you
  * pass in is freed
  */
-static int __btrfs_add_inode_defrag(struct inode *inode,
+static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
 				    struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct inode_defrag *entry;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -123,7 +123,7 @@ static int __btrfs_add_inode_defrag(struct inode *inode,
 			return -EEXIST;
 		}
 	}
-	set_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
+	set_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags);
 	rb_link_node(&defrag->rb_node, parent, p);
 	rb_insert_color(&defrag->rb_node, &fs_info->defrag_inodes);
 	return 0;
@@ -145,10 +145,10 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
  * enabled
  */
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
-			   struct inode *inode)
+			   struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct inode_defrag *defrag;
 	u64 transid;
 	int ret;
@@ -156,24 +156,24 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 	if (!__need_auto_defrag(fs_info))
 		return 0;
 
-	if (test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags))
+	if (test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags))
 		return 0;
 
 	if (trans)
 		transid = trans->transid;
 	else
-		transid = BTRFS_I(inode)->root->last_trans;
+		transid = inode->root->last_trans;
 
 	defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS);
 	if (!defrag)
 		return -ENOMEM;
 
-	defrag->ino = btrfs_ino(BTRFS_I(inode));
+	defrag->ino = btrfs_ino(inode);
 	defrag->transid = transid;
 	defrag->root = root->root_key.objectid;
 
 	spin_lock(&fs_info->defrag_inodes_lock);
-	if (!test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags)) {
+	if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) {
 		/*
 		 * If we set IN_DEFRAG flag and evict the inode from memory,
 		 * and then re-read this inode, this new inode doesn't have
@@ -208,7 +208,7 @@ static void btrfs_requeue_inode_defrag(struct inode *inode,
 	 * them together.
 	 */
 	spin_lock(&fs_info->defrag_inodes_lock);
-	ret = __btrfs_add_inode_defrag(inode, defrag);
+	ret = __btrfs_add_inode_defrag(BTRFS_I(inode), defrag);
 	spin_unlock(&fs_info->defrag_inodes_lock);
 	if (ret)
 		goto out;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index dd0f1abdacd2..c396533fd3e5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -389,12 +389,12 @@ static inline int inode_need_compress(struct inode *inode)
 	return 0;
 }
 
-static inline void inode_should_defrag(struct inode *inode,
+static inline void inode_should_defrag(struct btrfs_inode *inode,
 		u64 start, u64 end, u64 num_bytes, u64 small_write)
 {
 	/* If this is a small write inside eof, kick off a defrag */
 	if (num_bytes < small_write &&
-	    (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
+	    (start > 0 || end + 1 < inode->disk_i_size))
 		btrfs_add_inode_defrag(NULL, inode);
 }
 
@@ -440,7 +440,8 @@ static noinline void compress_file_range(struct inode *inode,
 	int compress_type = fs_info->compress_type;
 	int redirty = 0;
 
-	inode_should_defrag(inode, start, end, end - start + 1, SZ_16K);
+	inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
+			SZ_16K);
 
 	actual_end = min_t(u64, isize, end + 1);
 again:
@@ -943,7 +944,7 @@ static noinline int cow_file_range(struct inode *inode,
 	num_bytes = max(blocksize,  num_bytes);
 	disk_num_bytes = num_bytes;
 
-	inode_should_defrag(inode, start, end, num_bytes, SZ_64K);
+	inode_should_defrag(BTRFS_I(inode), start, end, num_bytes, SZ_64K);
 
 	if (start == 0) {
 		/* lets try to make an inline extent */
-- 
GitLab


From 46e59791836c75210bdf1f715592b49836fad848 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:44 +0200
Subject: [PATCH 284/898] btrfs: Make btrfs_requeue_inode_defrag take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 63645e86ad95..dd1b56504e10 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -194,10 +194,10 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
  * the same inode in the tree, we will merge them together (by
  * __btrfs_add_inode_defrag()) and free the one that we want to requeue.
  */
-static void btrfs_requeue_inode_defrag(struct inode *inode,
+static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode,
 				       struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret;
 
 	if (!__need_auto_defrag(fs_info))
@@ -208,7 +208,7 @@ static void btrfs_requeue_inode_defrag(struct inode *inode,
 	 * them together.
 	 */
 	spin_lock(&fs_info->defrag_inodes_lock);
-	ret = __btrfs_add_inode_defrag(BTRFS_I(inode), defrag);
+	ret = __btrfs_add_inode_defrag(inode, defrag);
 	spin_unlock(&fs_info->defrag_inodes_lock);
 	if (ret)
 		goto out;
@@ -334,7 +334,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	 */
 	if (num_defrag == BTRFS_DEFRAG_BATCH) {
 		defrag->last_offset = range.start;
-		btrfs_requeue_inode_defrag(inode, defrag);
+		btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag);
 	} else if (defrag->last_offset && !defrag->cycled) {
 		/*
 		 * we didn't fill our defrag batch, but
@@ -343,7 +343,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 		 */
 		defrag->last_offset = 0;
 		defrag->cycled = 1;
-		btrfs_requeue_inode_defrag(inode, defrag);
+		btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag);
 	} else {
 		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
 	}
-- 
GitLab


From dcdbc059f01e242f92e3239654a1a57d15b0da5a Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:45 +0200
Subject: [PATCH 285/898] btrfs: Make btrfs_drop_extent_cache take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h             |  2 +-
 fs/btrfs/file.c              | 11 ++++++-----
 fs/btrfs/inode.c             | 31 +++++++++++++++++--------------
 fs/btrfs/ioctl.c             |  2 +-
 fs/btrfs/relocation.c        |  8 ++++----
 fs/btrfs/tests/inode-tests.c |  2 +-
 6 files changed, 30 insertions(+), 26 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5246cbe4c17f..4db18e5dc8f9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3219,7 +3219,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
 void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
-void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
+void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			     int skip_pinned);
 extern const struct file_operations btrfs_file_operations;
 int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index dd1b56504e10..5df1de43aace 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -529,13 +529,13 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages,
  * this drops all the extents in the cache that intersect the range
  * [start, end].  Existing extents are split as required.
  */
-void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
+void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			     int skip_pinned)
 {
 	struct extent_map *em;
 	struct extent_map *split = NULL;
 	struct extent_map *split2 = NULL;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	u64 len = end - start + 1;
 	u64 gen;
 	int ret;
@@ -720,7 +720,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	int leafs_visited = 0;
 
 	if (drop_cache)
-		btrfs_drop_extent_cache(inode, start, end - 1, 0);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end - 1, 0);
 
 	if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
 		modify_tree = 0;
@@ -2297,7 +2297,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 
 	hole_em = alloc_extent_map();
 	if (!hole_em) {
-		btrfs_drop_extent_cache(inode, offset, end - 1, 0);
+		btrfs_drop_extent_cache(BTRFS_I(inode), offset, end - 1, 0);
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			&BTRFS_I(inode)->runtime_flags);
 	} else {
@@ -2314,7 +2314,8 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		hole_em->generation = trans->transid;
 
 		do {
-			btrfs_drop_extent_cache(inode, offset, end - 1, 0);
+			btrfs_drop_extent_cache(BTRFS_I(inode), offset,
+					end - 1, 0);
 			write_lock(&em_tree->lock);
 			ret = add_extent_mapping(em_tree, hole_em, 1);
 			write_unlock(&em_tree->lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c396533fd3e5..c2383a442ff8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -317,7 +317,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
 
 	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
 	btrfs_delalloc_release_metadata(BTRFS_I(inode), end + 1 - start);
-	btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), start, aligned_end - 1, 0);
 out:
 	/*
 	 * Don't forget to free the reserved space, as for inlined extent
@@ -807,7 +807,8 @@ static noinline void submit_compressed_extents(struct inode *inode,
 						BTRFS_ORDERED_COMPRESSED,
 						async_extent->compress_type);
 		if (ret) {
-			btrfs_drop_extent_cache(inode, async_extent->start,
+			btrfs_drop_extent_cache(BTRFS_I(inode),
+						async_extent->start,
 						async_extent->start +
 						async_extent->ram_size - 1, 0);
 			goto out_free_reserve;
@@ -972,7 +973,8 @@ static noinline int cow_file_range(struct inode *inode,
 	       btrfs_super_total_bytes(fs_info->super_copy));
 
 	alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
-	btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), start,
+			start + num_bytes - 1, 0);
 
 	while (disk_num_bytes > 0) {
 		unsigned long op;
@@ -1040,7 +1042,7 @@ static noinline int cow_file_range(struct inode *inode,
 	return ret;
 
 out_drop_extent_cache:
-	btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), start, start + ram_size - 1, 0);
 out_reserve:
 	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
@@ -2931,7 +2933,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		clear_extent_uptodate(io_tree, start, end, NULL, GFP_NOFS);
 
 		/* Drop the cache for the part of the extent we didn't write. */
-		btrfs_drop_extent_cache(inode, start, end, 0);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
 
 		/*
 		 * If the ordered extent had an IOERR or something else went
@@ -4337,7 +4339,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	 */
 	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
 	    root == fs_info->tree_root)
-		btrfs_drop_extent_cache(inode, ALIGN(new_size,
+		btrfs_drop_extent_cache(BTRFS_I(inode), ALIGN(new_size,
 					fs_info->sectorsize),
 					(u64)-1, 0);
 
@@ -4865,7 +4867,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 						hole_size);
 			if (err)
 				break;
-			btrfs_drop_extent_cache(inode, cur_offset,
+			btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
 						cur_offset + hole_size - 1, 0);
 			hole_em = alloc_extent_map();
 			if (!hole_em) {
@@ -4891,7 +4893,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 				write_unlock(&em_tree->lock);
 				if (err != -EEXIST)
 					break;
-				btrfs_drop_extent_cache(inode, cur_offset,
+				btrfs_drop_extent_cache(BTRFS_I(inode),
+							cur_offset,
 							cur_offset +
 							hole_size - 1, 0);
 			}
@@ -7164,7 +7167,7 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 	if (ret) {
 		if (em) {
 			free_extent_map(em);
-			btrfs_drop_extent_cache(inode, start,
+			btrfs_drop_extent_cache(BTRFS_I(inode), start,
 						start + len - 1, 0);
 		}
 		em = ERR_PTR(ret);
@@ -7531,7 +7534,7 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 	}
 
 	do {
-		btrfs_drop_extent_cache(inode, em->start,
+		btrfs_drop_extent_cache(BTRFS_I(inode), em->start,
 				em->start + em->len - 1, 0);
 		write_lock(&em_tree->lock);
 		ret = add_extent_mapping(em_tree, em, 1);
@@ -9280,7 +9283,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 void btrfs_test_destroy_inode(struct inode *inode)
 {
-	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
 #endif
@@ -9335,7 +9338,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	}
 	btrfs_qgroup_check_reserved_leak(inode);
 	inode_tree_del(inode);
-	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
 free:
 	call_rcu(&inode->i_rcu, btrfs_i_callback);
 }
@@ -10328,7 +10331,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 			break;
 		}
 
-		btrfs_drop_extent_cache(inode, cur_offset,
+		btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
 					cur_offset + ins.offset -1, 0);
 
 		em = alloc_extent_map();
@@ -10355,7 +10358,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 			write_unlock(&em_tree->lock);
 			if (ret != -EEXIST)
 				break;
-			btrfs_drop_extent_cache(inode, cur_offset,
+			btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
 						cur_offset + ins.offset - 1,
 						0);
 		}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 86f993c958ba..bc2e03a2569e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3359,7 +3359,7 @@ static void clone_update_extent_map(struct inode *inode,
 			free_extent_map(em);
 			break;
 		}
-		btrfs_drop_extent_cache(inode, em->start,
+		btrfs_drop_extent_cache(BTRFS_I(inode), em->start,
 					em->start + em->len - 1, 0);
 	}
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index e6470890ce26..e48625413fcb 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1714,8 +1714,8 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 				if (!ret)
 					continue;
 
-				btrfs_drop_extent_cache(inode, key.offset, end,
-							1);
+				btrfs_drop_extent_cache(BTRFS_I(inode),
+						key.offset,	end, 1);
 				unlock_extent(&BTRFS_I(inode)->io_tree,
 					      key.offset, end);
 			}
@@ -2130,7 +2130,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 
 		/* the lock_extent waits for readpage to complete */
 		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
-		btrfs_drop_extent_cache(inode, start, end, 1);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 1);
 		unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 	}
 	return 0;
@@ -3161,7 +3161,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 			free_extent_map(em);
 			break;
 		}
-		btrfs_drop_extent_cache(inode, start, end, 0);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
 	}
 	unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 	return ret;
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 4d0f038e14f1..924bcbf43275 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -293,7 +293,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	free_extent_map(em);
-	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
 
 	/*
 	 * All of the magic numbers are based on the mapping setup in
-- 
GitLab


From 35339c245b5939315e8763deb7f9b68fffe54912 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:46 +0200
Subject: [PATCH 286/898] btrfs: Make hole_mergeable take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 5df1de43aace..27dfdfb7ff19 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2195,7 +2195,7 @@ static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf,
+static int hole_mergeable(struct btrfs_inode *inode, struct extent_buffer *leaf,
 			  int slot, u64 start, u64 end)
 {
 	struct btrfs_file_extent_item *fi;
@@ -2205,7 +2205,7 @@ static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf,
 		return 0;
 
 	btrfs_item_key_to_cpu(leaf, &key, slot);
-	if (key.objectid != btrfs_ino(BTRFS_I(inode)) ||
+	if (key.objectid != btrfs_ino(inode) ||
 	    key.type != BTRFS_EXTENT_DATA_KEY)
 		return 0;
 
@@ -2255,7 +2255,8 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 	}
 
 	leaf = path->nodes[0];
-	if (hole_mergeable(inode, leaf, path->slots[0]-1, offset, end)) {
+	if (hole_mergeable(BTRFS_I(inode), leaf, path->slots[0] - 1,
+				offset, end)) {
 		u64 num_bytes;
 
 		path->slots[0]--;
@@ -2270,7 +2271,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		goto out;
 	}
 
-	if (hole_mergeable(inode, leaf, path->slots[0], offset, end)) {
+	if (hole_mergeable(BTRFS_I(inode), leaf, path->slots[0], offset, end)) {
 		u64 num_bytes;
 
 		key.offset = offset;
-- 
GitLab


From a012a74e78d99aa27f8487c050e9ac3183bc3785 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:47 +0200
Subject: [PATCH 287/898] btrfs: Make fill_holes take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 37 ++++++++++++++++++-------------------
 1 file changed, 18 insertions(+), 19 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 27dfdfb7ff19..ef4ecd003742 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2224,22 +2224,23 @@ static int hole_mergeable(struct btrfs_inode *inode, struct extent_buffer *leaf,
 	return 0;
 }
 
-static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
-		      struct btrfs_path *path, u64 offset, u64 end)
+static int fill_holes(struct btrfs_trans_handle *trans,
+		struct btrfs_inode *inode,
+		struct btrfs_path *path, u64 offset, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *fi;
 	struct extent_map *hole_em;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct btrfs_key key;
 	int ret;
 
 	if (btrfs_fs_incompat(fs_info, NO_HOLES))
 		goto out;
 
-	key.objectid = btrfs_ino(BTRFS_I(inode));
+	key.objectid = btrfs_ino(inode);
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = offset;
 
@@ -2255,8 +2256,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 	}
 
 	leaf = path->nodes[0];
-	if (hole_mergeable(BTRFS_I(inode), leaf, path->slots[0] - 1,
-				offset, end)) {
+	if (hole_mergeable(inode, leaf, path->slots[0] - 1, offset, end)) {
 		u64 num_bytes;
 
 		path->slots[0]--;
@@ -2271,7 +2271,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		goto out;
 	}
 
-	if (hole_mergeable(BTRFS_I(inode), leaf, path->slots[0], offset, end)) {
+	if (hole_mergeable(inode, leaf, path->slots[0], offset, end)) {
 		u64 num_bytes;
 
 		key.offset = offset;
@@ -2288,7 +2288,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(BTRFS_I(inode)),
+	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode),
 			offset, 0, 0, end - offset, 0, end - offset, 0, 0, 0);
 	if (ret)
 		return ret;
@@ -2298,9 +2298,8 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 
 	hole_em = alloc_extent_map();
 	if (!hole_em) {
-		btrfs_drop_extent_cache(BTRFS_I(inode), offset, end - 1, 0);
-		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			&BTRFS_I(inode)->runtime_flags);
+		btrfs_drop_extent_cache(inode, offset, end - 1, 0);
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
 	} else {
 		hole_em->start = offset;
 		hole_em->len = end - offset;
@@ -2315,8 +2314,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		hole_em->generation = trans->transid;
 
 		do {
-			btrfs_drop_extent_cache(BTRFS_I(inode), offset,
-					end - 1, 0);
+			btrfs_drop_extent_cache(inode, offset, end - 1, 0);
 			write_lock(&em_tree->lock);
 			ret = add_extent_mapping(em_tree, hole_em, 1);
 			write_unlock(&em_tree->lock);
@@ -2324,7 +2322,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		free_extent_map(hole_em);
 		if (ret)
 			set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-				&BTRFS_I(inode)->runtime_flags);
+					&inode->runtime_flags);
 	}
 
 	return 0;
@@ -2554,8 +2552,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		trans->block_rsv = &fs_info->trans_block_rsv;
 
 		if (cur_offset < drop_end && cur_offset < ino_size) {
-			ret = fill_holes(trans, inode, path, cur_offset,
-					 drop_end);
+			ret = fill_holes(trans, BTRFS_I(inode), path,
+					cur_offset, drop_end);
 			if (ret) {
 				/*
 				 * If we failed then we didn't insert our hole
@@ -2626,7 +2624,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	 * cur_offset == drop_end).
 	 */
 	if (cur_offset < ino_size && cur_offset < drop_end) {
-		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
+		ret = fill_holes(trans, BTRFS_I(inode), path,
+				cur_offset, drop_end);
 		if (ret) {
 			/* Same comment as above. */
 			btrfs_abort_transaction(trans, ret);
-- 
GitLab


From 7a6d7067958c32d1c76e0bfd1a0d46be06340b2e Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:48 +0200
Subject: [PATCH 288/898] btrfs: Make btrfs_mark_extent_written take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h | 2 +-
 fs/btrfs/file.c  | 8 ++++----
 fs/btrfs/inode.c | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4db18e5dc8f9..2bfc2e289f51 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3233,7 +3233,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root, struct inode *inode, u64 start,
 		       u64 end, int drop_cache);
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
-			      struct inode *inode, u64 start, u64 end);
+			      struct btrfs_inode *inode, u64 start, u64 end);
 int btrfs_release_file(struct inode *inode, struct file *file);
 int btrfs_dirty_pages(struct inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ef4ecd003742..e704b6ce2058 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1082,10 +1082,10 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
  * two or three.
  */
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
-			      struct inode *inode, u64 start, u64 end)
+			      struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
 	struct btrfs_file_extent_item *fi;
@@ -1102,7 +1102,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	int del_slot = 0;
 	int recow;
 	int ret;
-	u64 ino = btrfs_ino(BTRFS_I(inode));
+	u64 ino = btrfs_ino(inode);
 
 	path = btrfs_alloc_path();
 	if (!path)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c2383a442ff8..8114bbd359d4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2876,7 +2876,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		compress_type = ordered_extent->compress_type;
 	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
 		BUG_ON(compress_type);
-		ret = btrfs_mark_extent_written(trans, inode,
+		ret = btrfs_mark_extent_written(trans, BTRFS_I(inode),
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
 						logical_len);
-- 
GitLab


From a776c6fa1feba7a84519170ebdb7f4a4155b89d6 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:49 +0200
Subject: [PATCH 289/898] btrfs: Make btrfs_lookup_ordered_range take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c    |  4 ++--
 fs/btrfs/file.c         |  4 ++--
 fs/btrfs/inode.c        | 11 ++++++-----
 fs/btrfs/ordered-data.c |  9 ++++-----
 fs/btrfs/ordered-data.h |  7 ++++---
 fs/btrfs/scrub.c        |  2 +-
 6 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d15b5ddb6732..996306d322de 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3101,7 +3101,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 	inode = pages[0]->mapping->host;
 	while (1) {
 		lock_extent(tree, start, end);
-		ordered = btrfs_lookup_ordered_range(inode, start,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
 						     end - start + 1);
 		if (!ordered)
 			break;
@@ -3173,7 +3173,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 
 	while (1) {
 		lock_extent(tree, start, end);
-		ordered = btrfs_lookup_ordered_range(inode, start,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
 						PAGE_SIZE);
 		if (!ordered)
 			break;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e704b6ce2058..f3648e9bfa01 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1436,7 +1436,7 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 		struct btrfs_ordered_extent *ordered;
 		lock_extent_bits(&BTRFS_I(inode)->io_tree,
 				 start_pos, last_pos, cached_state);
-		ordered = btrfs_lookup_ordered_range(inode, start_pos,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start_pos,
 						     last_pos - start_pos + 1);
 		if (ordered &&
 		    ordered->file_offset + ordered->len > start_pos &&
@@ -1494,7 +1494,7 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
 
 	while (1) {
 		lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
-		ordered = btrfs_lookup_ordered_range(inode, lockstart,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart,
 						     lockend - lockstart + 1);
 		if (!ordered) {
 			break;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8114bbd359d4..723f69bd49f3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1966,7 +1966,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 	if (PagePrivate2(page))
 		goto out;
 
-	ordered = btrfs_lookup_ordered_range(inode, page_start,
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
 					PAGE_SIZE);
 	if (ordered) {
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
@@ -4838,7 +4838,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 
 		lock_extent_bits(io_tree, hole_start, block_end - 1,
 				 &cached_state);
-		ordered = btrfs_lookup_ordered_range(inode, hole_start,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), hole_start,
 						     block_end - hole_start);
 		if (!ordered)
 			break;
@@ -7428,7 +7428,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 		 * doing DIO to, so we need to make sure there's no ordered
 		 * extents in this range.
 		 */
-		ordered = btrfs_lookup_ordered_range(inode, lockstart,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart,
 						     lockend - lockstart + 1);
 
 		/*
@@ -8801,7 +8801,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 		lock_extent_bits(tree, page_start, page_end, &cached_state);
 again:
 	start = page_start;
-	ordered = btrfs_lookup_ordered_range(inode, start,
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
 					page_end - start + 1);
 	if (ordered) {
 		end = min(page_end, ordered->file_offset + ordered->len - 1);
@@ -8967,7 +8967,8 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * we can't set the delalloc bits if there are pending ordered
 	 * extents.  Drop our locks and wait for them to finish
 	 */
-	ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE);
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
+			PAGE_SIZE);
 	if (ordered) {
 		unlock_extent_cached(io_tree, page_start, page_end,
 				     &cached_state, GFP_NOFS);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index bc2aba810629..9a46878ba60f 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -879,15 +879,14 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
 /* Since the DIO code tries to lock a wide area we need to look for any ordered
  * extents that exist in the range, rather than just the start of the range.
  */
-struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
-							u64 file_offset,
-							u64 len)
+struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
+		struct btrfs_inode *inode, u64 file_offset, u64 len)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct rb_node *node;
 	struct btrfs_ordered_extent *entry = NULL;
 
-	tree = &BTRFS_I(inode)->ordered_tree;
+	tree = &inode->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	node = tree_search(tree, file_offset);
 	if (!node) {
@@ -923,7 +922,7 @@ bool btrfs_have_ordered_extents_in_range(struct inode *inode,
 {
 	struct btrfs_ordered_extent *oe;
 
-	oe = btrfs_lookup_ordered_range(inode, file_offset, len);
+	oe = btrfs_lookup_ordered_range(BTRFS_I(inode), file_offset, len);
 	if (oe) {
 		btrfs_put_ordered_extent(oe);
 		return true;
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index a8cb8efe6fae..195c93b67fe0 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -189,9 +189,10 @@ void btrfs_start_ordered_extent(struct inode *inode,
 int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
 struct btrfs_ordered_extent *
 btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset);
-struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
-							u64 file_offset,
-							u64 len);
+struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
+		struct btrfs_inode *inode,
+		u64 file_offset,
+		u64 len);
 bool btrfs_have_ordered_extents_in_range(struct inode *inode,
 					 u64 file_offset,
 					 u64 len);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index ff9a11c39f5e..82d873406aa3 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -4249,7 +4249,7 @@ static int check_extent_to_block(struct inode *inode, u64 start, u64 len,
 	io_tree = &BTRFS_I(inode)->io_tree;
 
 	lock_extent_bits(io_tree, lockstart, lockend, &cached_state);
-	ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart, len);
 	if (ordered) {
 		btrfs_put_ordered_extent(ordered);
 		ret = 1;
-- 
GitLab


From 85b7ab6705d9a2e6173361f5da7cbf8f9eb07864 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:50 +0200
Subject: [PATCH 290/898] btrfs: Make check_can_nocow take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f3648e9bfa01..1d09eccec477 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1474,11 +1474,11 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 	return ret;
 }
 
-static noinline int check_can_nocow(struct inode *inode, loff_t pos,
+static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 				    size_t *write_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct btrfs_ordered_extent *ordered;
 	u64 lockstart, lockend;
 	u64 num_bytes;
@@ -1493,19 +1493,20 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
 			   fs_info->sectorsize) - 1;
 
 	while (1) {
-		lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
-		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart,
+		lock_extent(&inode->io_tree, lockstart, lockend);
+		ordered = btrfs_lookup_ordered_range(inode, lockstart,
 						     lockend - lockstart + 1);
 		if (!ordered) {
 			break;
 		}
-		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
-		btrfs_start_ordered_extent(inode, ordered, 1);
+		unlock_extent(&inode->io_tree, lockstart, lockend);
+		btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1);
 		btrfs_put_ordered_extent(ordered);
 	}
 
 	num_bytes = lockend - lockstart + 1;
-	ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
+	ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes,
+			NULL, NULL, NULL);
 	if (ret <= 0) {
 		ret = 0;
 		btrfs_end_write_no_snapshoting(root);
@@ -1514,7 +1515,7 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
 				     num_bytes - pos + lockstart);
 	}
 
-	unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
+	unlock_extent(&inode->io_tree, lockstart, lockend);
 
 	return ret;
 }
@@ -1579,7 +1580,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		if (ret < 0) {
 			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 						      BTRFS_INODE_PREALLOC)) &&
-			    check_can_nocow(inode, pos, &write_bytes) > 0) {
+			    check_can_nocow(BTRFS_I(inode), pos,
+					&write_bytes) > 0) {
 				/*
 				 * For nodata cow case, no need to reserve
 				 * data space.
-- 
GitLab


From 2cff578cfceba883eef199c52674a301a8f91d19 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <n.borisov.lkml@gmail.com>
Date: Mon, 20 Feb 2017 13:50:51 +0200
Subject: [PATCH 291/898] btrfs: Make lock_and_cleanup_extent_if_need take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 1d09eccec477..dff7ec1770c1 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1415,13 +1415,13 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
  * the other < 0 number - Something wrong happens
  */
 static noinline int
-lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
+lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 				size_t num_pages, loff_t pos,
 				size_t write_bytes,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 start_pos;
 	u64 last_pos;
 	int i;
@@ -1432,30 +1432,30 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 		+ round_up(pos + write_bytes - start_pos,
 			   fs_info->sectorsize) - 1;
 
-	if (start_pos < inode->i_size) {
+	if (start_pos < inode->vfs_inode.i_size) {
 		struct btrfs_ordered_extent *ordered;
-		lock_extent_bits(&BTRFS_I(inode)->io_tree,
-				 start_pos, last_pos, cached_state);
-		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start_pos,
+		lock_extent_bits(&inode->io_tree, start_pos, last_pos,
+				cached_state);
+		ordered = btrfs_lookup_ordered_range(inode, start_pos,
 						     last_pos - start_pos + 1);
 		if (ordered &&
 		    ordered->file_offset + ordered->len > start_pos &&
 		    ordered->file_offset <= last_pos) {
-			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
-					     start_pos, last_pos,
-					     cached_state, GFP_NOFS);
+			unlock_extent_cached(&inode->io_tree, start_pos,
+					last_pos, cached_state, GFP_NOFS);
 			for (i = 0; i < num_pages; i++) {
 				unlock_page(pages[i]);
 				put_page(pages[i]);
 			}
-			btrfs_start_ordered_extent(inode, ordered, 1);
+			btrfs_start_ordered_extent(&inode->vfs_inode,
+					ordered, 1);
 			btrfs_put_ordered_extent(ordered);
 			return -EAGAIN;
 		}
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
 
-		clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos,
+		clear_extent_bit(&inode->io_tree, start_pos,
 				  last_pos, EXTENT_DIRTY | EXTENT_DELALLOC |
 				  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 				  0, 0, cached_state, GFP_NOFS);
@@ -1626,9 +1626,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		if (ret)
 			break;
 
-		ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
-						pos, write_bytes, &lockstart,
-						&lockend, &cached_state);
+		ret = lock_and_cleanup_extent_if_need(BTRFS_I(inode), pages,
+				num_pages, pos, write_bytes, &lockstart,
+				&lockend, &cached_state);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				goto again;
-- 
GitLab


From 4ac1f4acd7c60c95e3efa63d463418093aff9ce5 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:52 +0200
Subject: [PATCH 292/898] btrfs: make free_io_failure take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 14 +++++++-------
 fs/btrfs/extent_io.h |  4 +++-
 fs/btrfs/inode.c     |  6 +++---
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 996306d322de..0e73e48a9c4c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1959,11 +1959,11 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
 		SetPageUptodate(page);
 }
 
-int free_io_failure(struct inode *inode, struct io_failure_record *rec)
+int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec)
 {
 	int ret;
 	int err = 0;
-	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
+	struct extent_io_tree *failure_tree = &inode->io_failure_tree;
 
 	set_state_failrec(failure_tree, rec->start, NULL);
 	ret = clear_extent_bits(failure_tree, rec->start,
@@ -1972,7 +1972,7 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
 	if (ret)
 		err = ret;
 
-	ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start,
+	ret = clear_extent_bits(&inode->io_tree, rec->start,
 				rec->start + rec->len - 1,
 				EXTENT_DAMAGED);
 	if (ret && !err)
@@ -2140,7 +2140,7 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 	}
 
 out:
-	free_io_failure(inode, failrec);
+	free_io_failure(BTRFS_I(inode), failrec);
 
 	return 0;
 }
@@ -2393,7 +2393,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 
 	ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror);
 	if (!ret) {
-		free_io_failure(inode, failrec);
+		free_io_failure(BTRFS_I(inode), failrec);
 		return -EIO;
 	}
 
@@ -2406,7 +2406,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 				      (int)phy_offset, failed_bio->bi_end_io,
 				      NULL);
 	if (!bio) {
-		free_io_failure(inode, failrec);
+		free_io_failure(BTRFS_I(inode), failrec);
 		return -EIO;
 	}
 	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
@@ -2418,7 +2418,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror,
 					 failrec->bio_flags, 0);
 	if (ret) {
-		free_io_failure(inode, failrec);
+		free_io_failure(BTRFS_I(inode), failrec);
 		bio_put(bio);
 	}
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 270d03be290e..5b4132a9093a 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -480,6 +480,8 @@ struct io_failure_record {
 	int in_validation;
 };
 
+struct btrfs_inode;
+
 void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end);
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 				struct io_failure_record **failrec_ret);
@@ -489,7 +491,7 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 				    struct io_failure_record *failrec,
 				    struct page *page, int pg_offset, int icsum,
 				    bio_end_io_t *endio_func, void *data);
-int free_io_failure(struct inode *inode, struct io_failure_record *rec);
+int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 noinline u64 find_lock_delalloc_range(struct inode *inode,
 				      struct extent_io_tree *tree,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 723f69bd49f3..f1f9e201f9f3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7859,7 +7859,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	ret = btrfs_check_dio_repairable(inode, failed_bio, failrec,
 					 failed_mirror);
 	if (!ret) {
-		free_io_failure(inode, failrec);
+		free_io_failure(BTRFS_I(inode), failrec);
 		return -EIO;
 	}
 
@@ -7873,7 +7873,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
 				pgoff, isector, repair_endio, repair_arg);
 	if (!bio) {
-		free_io_failure(inode, failrec);
+		free_io_failure(BTRFS_I(inode), failrec);
 		return -EIO;
 	}
 	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
@@ -7884,7 +7884,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 
 	ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
 	if (ret) {
-		free_io_failure(inode, failrec);
+		free_io_failure(BTRFS_I(inode), failrec);
 		bio_put(bio);
 	}
 
-- 
GitLab


From 0970a22e58d4c49f2c3e84519613a9db8f00f579 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:53 +0200
Subject: [PATCH 293/898] btrfs: make btrfs_print_data_csum_error take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h | 8 ++++----
 fs/btrfs/compression.c | 5 +++--
 fs/btrfs/inode.c       | 2 +-
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 36eca5464e1b..c10d21b2f0df 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -324,21 +324,21 @@ static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
 		  &BTRFS_I(inode)->runtime_flags);
 }
 
-static inline void btrfs_print_data_csum_error(struct inode *inode,
+static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
 		u64 logical_start, u32 csum, u32 csum_expected, int mirror_num)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 
 	/* Output minus objectid, which is more meaningful */
 	if (root->objectid >= BTRFS_LAST_FREE_OBJECTID)
 		btrfs_warn_rl(root->fs_info,
 	"csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d",
-			root->objectid, btrfs_ino(BTRFS_I(inode)),
+			root->objectid, btrfs_ino(inode),
 			logical_start, csum, csum_expected, mirror_num);
 	else
 		btrfs_warn_rl(root->fs_info,
 	"csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d",
-			root->objectid, btrfs_ino(BTRFS_I(inode)),
+			root->objectid, btrfs_ino(inode),
 			logical_start, csum, csum_expected, mirror_num);
 }
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 903c32c9eb22..9ce85d5e5cae 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -124,8 +124,9 @@ static int check_compressed_csum(struct inode *inode,
 		kunmap_atomic(kaddr);
 
 		if (csum != *cb_sum) {
-			btrfs_print_data_csum_error(inode, disk_start, csum,
-						    *cb_sum, cb->mirror_num);
+			btrfs_print_data_csum_error(BTRFS_I(inode),
+					disk_start, csum,
+					*cb_sum, cb->mirror_num);
 			ret = -EIO;
 			goto fail;
 		}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f1f9e201f9f3..fc00117a0dd0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3032,7 +3032,7 @@ static int __readpage_endio_check(struct inode *inode,
 	kunmap_atomic(kaddr);
 	return 0;
 zeroit:
-	btrfs_print_data_csum_error(inode, start, csum, csum_expected,
+	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
 				    io_bio->mirror_num);
 	memset(kaddr + pgoff, 1, len);
 	flush_dcache_page(page);
-- 
GitLab


From f898ac6ae339782bc304b2b15c9e187e438da9f7 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:54 +0200
Subject: [PATCH 294/898] btrfs: make check_compressed_csum take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 9ce85d5e5cae..f32e86b61240 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -100,7 +100,7 @@ static struct bio *compressed_bio_alloc(struct block_device *bdev,
 	return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags);
 }
 
-static int check_compressed_csum(struct inode *inode,
+static int check_compressed_csum(struct btrfs_inode *inode,
 				 struct compressed_bio *cb,
 				 u64 disk_start)
 {
@@ -111,7 +111,7 @@ static int check_compressed_csum(struct inode *inode,
 	u32 csum;
 	u32 *cb_sum = &cb->sums;
 
-	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
+	if (inode->flags & BTRFS_INODE_NODATASUM)
 		return 0;
 
 	for (i = 0; i < cb->nr_pages; i++) {
@@ -124,8 +124,7 @@ static int check_compressed_csum(struct inode *inode,
 		kunmap_atomic(kaddr);
 
 		if (csum != *cb_sum) {
-			btrfs_print_data_csum_error(BTRFS_I(inode),
-					disk_start, csum,
+			btrfs_print_data_csum_error(inode, disk_start, csum,
 					*cb_sum, cb->mirror_num);
 			ret = -EIO;
 			goto fail;
@@ -166,7 +165,7 @@ static void end_compressed_bio_read(struct bio *bio)
 		goto out;
 
 	inode = cb->inode;
-	ret = check_compressed_csum(inode, cb,
+	ret = check_compressed_csum(BTRFS_I(inode), cb,
 				    (u64)bio->bi_iter.bi_sector << 9);
 	if (ret)
 		goto csum_failed;
-- 
GitLab


From 9d4f7f8ad69112137da0bbe4036b94739ae25f78 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:55 +0200
Subject: [PATCH 295/898] btrfs: make repair_io_failure take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 13 +++++++------
 fs/btrfs/extent_io.h |  8 ++++----
 fs/btrfs/scrub.c     |  2 +-
 3 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 0e73e48a9c4c..e99e8dad3cc7 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1992,10 +1992,11 @@ int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec)
  * currently, there can be no more than two copies of every data bit. thus,
  * exactly one rewrite is required.
  */
-int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
-		      struct page *page, unsigned int pg_offset, int mirror_num)
+int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length,
+		u64 logical, struct page *page,
+		unsigned int pg_offset, int mirror_num)
 {
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct bio *bio;
 	struct btrfs_device *dev;
 	u64 map_length = 0;
@@ -2054,7 +2055,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 
 	btrfs_info_rl_in_rcu(fs_info,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
-				  btrfs_ino(BTRFS_I(inode)), start,
+				  btrfs_ino(inode), start,
 				  rcu_str_deref(dev->name), sector);
 	btrfs_bio_counter_dec(fs_info);
 	bio_put(bio);
@@ -2074,7 +2075,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
-		ret = repair_io_failure(fs_info->btree_inode, start,
+		ret = repair_io_failure(BTRFS_I(fs_info->btree_inode), start,
 					PAGE_SIZE, start, p,
 					start - page_offset(p), mirror_num);
 		if (ret)
@@ -2133,7 +2134,7 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 		num_copies = btrfs_num_copies(fs_info, failrec->logical,
 					      failrec->len);
 		if (num_copies > 1)  {
-			repair_io_failure(inode, start, failrec->len,
+			repair_io_failure(BTRFS_I(inode), start, failrec->len,
 					  failrec->logical, page,
 					  pg_offset, failrec->failed_mirror);
 		}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 5b4132a9093a..039a6daa392b 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -451,10 +451,11 @@ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs);
 struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask);
 
 struct btrfs_fs_info;
+struct btrfs_inode;
 
-int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
-		      struct page *page, unsigned int pg_offset,
-		      int mirror_num);
+int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length,
+		u64 logical, struct page *page,
+		unsigned int pg_offset, int mirror_num);
 int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 		     unsigned int pg_offset);
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
@@ -480,7 +481,6 @@ struct io_failure_record {
 	int in_validation;
 };
 
-struct btrfs_inode;
 
 void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end);
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 82d873406aa3..bdf58b0eaef8 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -731,7 +731,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 			ret = -EIO;
 			goto out;
 		}
-		ret = repair_io_failure(inode, offset, PAGE_SIZE,
+		ret = repair_io_failure(BTRFS_I(inode), offset, PAGE_SIZE,
 					fixup->logical, page,
 					offset - page_offset(page),
 					fixup->mirror_num);
-- 
GitLab


From b30cb441fcf8786773dab590739ca4ebc2b4628b Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:56 +0200
Subject: [PATCH 296/898] btrfs: make clean_io_failure take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 21 +++++++++++----------
 fs/btrfs/extent_io.h |  4 ++--
 fs/btrfs/inode.c     |  4 ++--
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e99e8dad3cc7..b08fa96678ee 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2090,23 +2090,23 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
  * each time an IO finishes, we do a fast check in the IO failure tree
  * to see if we need to process or clean up an io_failure_record
  */
-int clean_io_failure(struct inode *inode, u64 start, struct page *page,
+int clean_io_failure(struct btrfs_inode *inode, u64 start, struct page *page,
 		     unsigned int pg_offset)
 {
 	u64 private;
 	struct io_failure_record *failrec;
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_state *state;
 	int num_copies;
 	int ret;
 
 	private = 0;
-	ret = count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
+	ret = count_range_bits(&inode->io_failure_tree, &private,
 				(u64)-1, 1, EXTENT_DIRTY, 0);
 	if (!ret)
 		return 0;
 
-	ret = get_state_failrec(&BTRFS_I(inode)->io_failure_tree, start,
+	ret = get_state_failrec(&inode->io_failure_tree, start,
 			&failrec);
 	if (ret)
 		return 0;
@@ -2123,25 +2123,25 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 	if (fs_info->sb->s_flags & MS_RDONLY)
 		goto out;
 
-	spin_lock(&BTRFS_I(inode)->io_tree.lock);
-	state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree,
+	spin_lock(&inode->io_tree.lock);
+	state = find_first_extent_bit_state(&inode->io_tree,
 					    failrec->start,
 					    EXTENT_LOCKED);
-	spin_unlock(&BTRFS_I(inode)->io_tree.lock);
+	spin_unlock(&inode->io_tree.lock);
 
 	if (state && state->start <= failrec->start &&
 	    state->end >= failrec->start + failrec->len - 1) {
 		num_copies = btrfs_num_copies(fs_info, failrec->logical,
 					      failrec->len);
 		if (num_copies > 1)  {
-			repair_io_failure(BTRFS_I(inode), start, failrec->len,
+			repair_io_failure(inode, start, failrec->len,
 					  failrec->logical, page,
 					  pg_offset, failrec->failed_mirror);
 		}
 	}
 
 out:
-	free_io_failure(BTRFS_I(inode), failrec);
+	free_io_failure(inode, failrec);
 
 	return 0;
 }
@@ -2577,7 +2577,8 @@ static void end_bio_extent_readpage(struct bio *bio)
 			if (ret)
 				uptodate = 0;
 			else
-				clean_io_failure(inode, start, page, 0);
+				clean_io_failure(BTRFS_I(inode), start,
+						page, 0);
 		}
 
 		if (likely(uptodate))
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 039a6daa392b..0f67222f4464 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -456,8 +456,8 @@ struct btrfs_inode;
 int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length,
 		u64 logical, struct page *page,
 		unsigned int pg_offset, int mirror_num);
-int clean_io_failure(struct inode *inode, u64 start, struct page *page,
-		     unsigned int pg_offset);
+int clean_io_failure(struct btrfs_inode *inode, u64 start,
+		struct page *page, unsigned int pg_offset);
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *eb, int mirror_num);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fc00117a0dd0..4498921bb608 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7914,7 +7914,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
 
 	done->uptodate = 1;
 	bio_for_each_segment_all(bvec, bio, i)
-		clean_io_failure(done->inode, done->start, bvec->bv_page, 0);
+	clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, 0);
 end:
 	complete(&done->done);
 	bio_put(bio);
@@ -8000,7 +8000,7 @@ static void btrfs_retry_endio(struct bio *bio)
 					bvec->bv_page, bvec->bv_offset,
 					done->start, bvec->bv_len);
 		if (!ret)
-			clean_io_failure(done->inode, done->start,
+			clean_io_failure(BTRFS_I(done->inode), done->start,
 					bvec->bv_page, bvec->bv_offset);
 		else
 			uptodate = 0;
-- 
GitLab


From 7ab7956ec3fc77667739d065748d96f87bff6c5d Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:57 +0200
Subject: [PATCH 297/898] btrfs: make btrfs_free_io_failure_record take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 4 ++--
 fs/btrfs/extent_io.h | 3 ++-
 fs/btrfs/inode.c     | 9 +++++----
 3 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index b08fa96678ee..ded750eb90c4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2152,9 +2152,9 @@ int clean_io_failure(struct btrfs_inode *inode, u64 start, struct page *page,
  * - under ordered extent
  * - the inode is freeing
  */
-void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
+	struct extent_io_tree *failure_tree = &inode->io_failure_tree;
 	struct io_failure_record *failrec;
 	struct extent_state *state, *next;
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0f67222f4464..345fc33f843d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -482,7 +482,8 @@ struct io_failure_record {
 };
 
 
-void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end);
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
+		u64 end);
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 				struct io_failure_record **failrec_ret);
 int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4498921bb608..4805489984eb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2803,9 +2803,10 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
-	btrfs_free_io_failure_record(inode, ordered_extent->file_offset,
-				     ordered_extent->file_offset +
-				     ordered_extent->len - 1);
+	btrfs_free_io_failure_record(BTRFS_I(inode),
+			ordered_extent->file_offset,
+			ordered_extent->file_offset +
+			ordered_extent->len - 1);
 
 	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
 		truncated = true;
@@ -5196,7 +5197,7 @@ void btrfs_evict_inode(struct inode *inode)
 	if (!special_file(inode->i_mode))
 		btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
-	btrfs_free_io_failure_record(inode, 0, (u64)-1);
+	btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);
 
 	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
 		BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-- 
GitLab


From 3d6ae7bb6a64b7dbc516863eeb99c3182d499aba Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:58 +0200
Subject: [PATCH 298/898] btrfs: make btrfs_orphan_del take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4805489984eb..ad93974f86a9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3271,20 +3271,20 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
  * item for this particular inode.
  */
 static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
-			    struct inode *inode)
+			    struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	int delete_item = 0;
 	int release_rsv = 0;
 	int ret = 0;
 
 	spin_lock(&root->orphan_lock);
 	if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-			       &BTRFS_I(inode)->runtime_flags))
+			       &inode->runtime_flags))
 		delete_item = 1;
 
 	if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-			       &BTRFS_I(inode)->runtime_flags))
+			       &inode->runtime_flags))
 		release_rsv = 1;
 	spin_unlock(&root->orphan_lock);
 
@@ -3292,11 +3292,11 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
 		atomic_dec(&root->orphan_inodes);
 		if (trans)
 			ret = btrfs_del_orphan_item(trans, root,
-						    btrfs_ino(BTRFS_I(inode)));
+						    btrfs_ino(inode));
 	}
 
 	if (release_rsv)
-		btrfs_orphan_release_metadata(BTRFS_I(inode));
+		btrfs_orphan_release_metadata(inode);
 
 	return ret;
 }
@@ -3467,7 +3467,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 
 			ret = btrfs_truncate(inode);
 			if (ret)
-				btrfs_orphan_del(NULL, inode);
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
 		} else {
 			nr_unlink++;
 		}
@@ -5012,7 +5012,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 			/* To get a stable disk_i_size */
 			err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
 			if (err) {
-				btrfs_orphan_del(NULL, inode);
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
 				return err;
 			}
 
@@ -5024,11 +5024,11 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 			 */
 			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans)) {
-				btrfs_orphan_del(NULL, inode);
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
 				return ret;
 			}
 			i_size_write(inode, BTRFS_I(inode)->disk_i_size);
-			err = btrfs_orphan_del(trans, inode);
+			err = btrfs_orphan_del(trans, BTRFS_I(inode));
 			if (err)
 				btrfs_abort_transaction(trans, err);
 			btrfs_end_transaction(trans);
@@ -5190,7 +5190,7 @@ void btrfs_evict_inode(struct inode *inode)
 		goto no_delete;
 
 	if (is_bad_inode(inode)) {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 		goto no_delete;
 	}
 	/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
@@ -5213,13 +5213,13 @@ void btrfs_evict_inode(struct inode *inode)
 
 	ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode));
 	if (ret) {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 		goto no_delete;
 	}
 
 	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
 	if (!rsv) {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 		goto no_delete;
 	}
 	rsv->size = min_size;
@@ -5261,14 +5261,14 @@ void btrfs_evict_inode(struct inode *inode)
 			btrfs_warn(fs_info,
 				   "Could not get space for a delete, will truncate on mount %d",
 				   ret);
-			btrfs_orphan_del(NULL, inode);
+			btrfs_orphan_del(NULL, BTRFS_I(inode));
 			btrfs_free_block_rsv(fs_info, rsv);
 			goto no_delete;
 		}
 
 		trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans)) {
-			btrfs_orphan_del(NULL, inode);
+			btrfs_orphan_del(NULL, BTRFS_I(inode));
 			btrfs_free_block_rsv(fs_info, rsv);
 			goto no_delete;
 		}
@@ -5294,7 +5294,7 @@ void btrfs_evict_inode(struct inode *inode)
 		if (ret) {
 			ret = btrfs_commit_transaction(trans);
 			if (ret) {
-				btrfs_orphan_del(NULL, inode);
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
 				btrfs_free_block_rsv(fs_info, rsv);
 				goto no_delete;
 			}
@@ -5323,9 +5323,9 @@ void btrfs_evict_inode(struct inode *inode)
 	 */
 	if (ret == 0) {
 		trans->block_rsv = root->orphan_block_rsv;
-		btrfs_orphan_del(trans, inode);
+		btrfs_orphan_del(trans, BTRFS_I(inode));
 	} else {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 	}
 
 	trans->block_rsv = &fs_info->trans_block_rsv;
@@ -6534,7 +6534,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 			 * If new hard link count is 1, it's a file created
 			 * with open(2) O_TMPFILE flag.
 			 */
-			err = btrfs_orphan_del(trans, inode);
+			err = btrfs_orphan_del(trans, BTRFS_I(inode));
 			if (err)
 				goto fail;
 		}
@@ -9167,7 +9167,7 @@ static int btrfs_truncate(struct inode *inode)
 
 	if (ret == 0 && inode->i_nlink > 0) {
 		trans->block_rsv = root->orphan_block_rsv;
-		ret = btrfs_orphan_del(trans, inode);
+		ret = btrfs_orphan_del(trans, BTRFS_I(inode));
 		if (ret)
 			err = ret;
 	}
-- 
GitLab


From 73f2e545b68f6af033fd2c083ca9dc3079e79083 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:50:59 +0200
Subject: [PATCH 299/898] btrfs: Make btrfs_orphan_add take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  3 ++-
 fs/btrfs/extent-tree.c |  2 +-
 fs/btrfs/inode.c       | 39 ++++++++++++++++++++-------------------
 fs/btrfs/relocation.c  |  2 +-
 4 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2bfc2e289f51..af68f8452f19 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3174,7 +3174,8 @@ int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct inode *inode);
 int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root, struct inode *inode);
-int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode);
+int btrfs_orphan_add(struct btrfs_trans_handle *trans,
+		struct btrfs_inode *inode);
 int btrfs_orphan_cleanup(struct btrfs_root *root);
 void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7b2313a4441e..3853fab2f49f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -10337,7 +10337,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	mutex_unlock(&trans->transaction->cache_write_mutex);
 
 	if (!IS_ERR(inode)) {
-		ret = btrfs_orphan_add(trans, inode);
+		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_add_delayed_iput(inode);
 			goto out;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ad93974f86a9..d5339b8d4663 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3172,10 +3172,11 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
  * NOTE: caller of this function should reserve 5 units of metadata for
  *	 this function.
  */
-int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
+int btrfs_orphan_add(struct btrfs_trans_handle *trans,
+		struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = NULL;
 	int reserve = 0;
 	int insert = 0;
@@ -3197,7 +3198,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	}
 
 	if (!test_and_set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-			      &BTRFS_I(inode)->runtime_flags)) {
+			      &inode->runtime_flags)) {
 #if 0
 		/*
 		 * For proper ENOSPC handling, we should do orphan
@@ -3214,39 +3215,38 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	}
 
 	if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-			      &BTRFS_I(inode)->runtime_flags))
+			      &inode->runtime_flags))
 		reserve = 1;
 	spin_unlock(&root->orphan_lock);
 
 	/* grab metadata reservation from transaction handle */
 	if (reserve) {
-		ret = btrfs_orphan_reserve_metadata(trans, BTRFS_I(inode));
+		ret = btrfs_orphan_reserve_metadata(trans, inode);
 		ASSERT(!ret);
 		if (ret) {
 			atomic_dec(&root->orphan_inodes);
 			clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-				  &BTRFS_I(inode)->runtime_flags);
+				  &inode->runtime_flags);
 			if (insert)
 				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-					  &BTRFS_I(inode)->runtime_flags);
+					  &inode->runtime_flags);
 			return ret;
 		}
 	}
 
 	/* insert an orphan item to track this unlinked/truncated file */
 	if (insert >= 1) {
-		ret = btrfs_insert_orphan_item(trans, root,
-				btrfs_ino(BTRFS_I(inode)));
+		ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
 		if (ret) {
 			atomic_dec(&root->orphan_inodes);
 			if (reserve) {
 				clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-					  &BTRFS_I(inode)->runtime_flags);
-				btrfs_orphan_release_metadata(BTRFS_I(inode));
+					  &inode->runtime_flags);
+				btrfs_orphan_release_metadata(inode);
 			}
 			if (ret != -EEXIST) {
 				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-					  &BTRFS_I(inode)->runtime_flags);
+					  &inode->runtime_flags);
 				btrfs_abort_transaction(trans, ret);
 				return ret;
 			}
@@ -3458,7 +3458,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 				ret = PTR_ERR(trans);
 				goto out;
 			}
-			ret = btrfs_orphan_add(trans, inode);
+			ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 			btrfs_end_transaction(trans);
 			if (ret) {
 				iput(inode);
@@ -4060,7 +4060,7 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
 		goto out;
 
 	if (inode->i_nlink == 0) {
-		ret = btrfs_orphan_add(trans, inode);
+		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret)
 			goto out;
 	}
@@ -4177,7 +4177,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		goto out;
 	}
 
-	err = btrfs_orphan_add(trans, inode);
+	err = btrfs_orphan_add(trans, BTRFS_I(inode));
 	if (err)
 		goto out;
 
@@ -4992,7 +4992,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		 * so we need to guarantee from this point on that everything
 		 * will be consistent.
 		 */
-		ret = btrfs_orphan_add(trans, inode);
+		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		btrfs_end_transaction(trans);
 		if (ret)
 			return ret;
@@ -9865,7 +9865,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 						 new_dentry->d_name.len);
 		}
 		if (!ret && new_inode->i_nlink == 0)
-			ret = btrfs_orphan_add(trans, d_inode(new_dentry));
+			ret = btrfs_orphan_add(trans,
+					BTRFS_I(d_inode(new_dentry)));
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			goto out_fail;
@@ -10482,7 +10483,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret)
 		goto out_inode;
-	ret = btrfs_orphan_add(trans, inode);
+	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 	if (ret)
 		goto out_inode;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index e48625413fcb..d60df51959f7 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4246,7 +4246,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	BUG_ON(IS_ERR(inode) || is_bad_inode(inode));
 	BTRFS_I(inode)->index_cnt = group->key.objectid;
 
-	err = btrfs_orphan_add(trans, inode);
+	err = btrfs_orphan_add(trans, BTRFS_I(inode));
 out:
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
-- 
GitLab


From aefa6115c04ee561302e133ab5916246cd3695f7 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:00 +0200
Subject: [PATCH 300/898] btrfs: Make check_parent_dirs_for_sync take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 071f64944711..399561b039c3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5045,14 +5045,14 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
  * a full commit is required.
  */
 static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
-					       struct inode *inode,
+					       struct btrfs_inode *inode,
 					       struct dentry *parent,
 					       struct super_block *sb,
 					       u64 last_committed)
 {
 	int ret = 0;
 	struct dentry *old_parent = NULL;
-	struct inode *orig_inode = inode;
+	struct btrfs_inode *orig_inode = inode;
 
 	/*
 	 * for regular files, if its inode is already on disk, we don't
@@ -5060,15 +5060,15 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 	 * we can use the last_unlink_trans field to record renames
 	 * and other fun in this file.
 	 */
-	if (S_ISREG(inode->i_mode) &&
-	    BTRFS_I(inode)->generation <= last_committed &&
-	    BTRFS_I(inode)->last_unlink_trans <= last_committed)
-			goto out;
+	if (S_ISREG(inode->vfs_inode.i_mode) &&
+	    inode->generation <= last_committed &&
+	    inode->last_unlink_trans <= last_committed)
+		goto out;
 
-	if (!S_ISDIR(inode->i_mode)) {
+	if (!S_ISDIR(inode->vfs_inode.i_mode)) {
 		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			goto out;
-		inode = d_inode(parent);
+		inode = BTRFS_I(d_inode(parent));
 	}
 
 	while (1) {
@@ -5079,10 +5079,10 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 		 * think this inode has already been logged.
 		 */
 		if (inode != orig_inode)
-			BTRFS_I(inode)->logged_trans = trans->transid;
+			inode->logged_trans = trans->transid;
 		smp_mb();
 
-		if (btrfs_must_commit_transaction(trans, BTRFS_I(inode))) {
+		if (btrfs_must_commit_transaction(trans, inode)) {
 			ret = 1;
 			break;
 		}
@@ -5091,8 +5091,8 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 			break;
 
 		if (IS_ROOT(parent)) {
-			inode = d_inode(parent);
-			if (btrfs_must_commit_transaction(trans, BTRFS_I(inode)))
+			inode = BTRFS_I(d_inode(parent));
+			if (btrfs_must_commit_transaction(trans, inode))
 				ret = 1;
 			break;
 		}
@@ -5100,7 +5100,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 		parent = dget_parent(parent);
 		dput(old_parent);
 		old_parent = parent;
-		inode = d_inode(parent);
+		inode = BTRFS_I(d_inode(parent));
 
 	}
 	dput(old_parent);
@@ -5429,7 +5429,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_no_trans;
 	}
 
-	ret = check_parent_dirs_for_sync(trans, inode, parent,
+	ret = check_parent_dirs_for_sync(trans, BTRFS_I(inode), parent,
 					 sb, last_committed);
 	if (ret)
 		goto end_no_trans;
-- 
GitLab


From 19df27a9e47085dcc81cbf9e7b464e7402511e18 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:01 +0200
Subject: [PATCH 301/898] btrfs: make btrfs_log_inode_parent take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 50 ++++++++++++++++++++++-----------------------
 1 file changed, 24 insertions(+), 26 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 399561b039c3..f8965b081212 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5390,7 +5390,8 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
  * the last committed transaction
  */
 static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
-			    	  struct btrfs_root *root, struct inode *inode,
+				  struct btrfs_root *root,
+				  struct btrfs_inode *inode,
 				  struct dentry *parent,
 				  const loff_t start,
 				  const loff_t end,
@@ -5404,9 +5405,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	int ret = 0;
 	u64 last_committed = fs_info->last_trans_committed;
 	bool log_dentries = false;
-	struct inode *orig_inode = inode;
+	struct btrfs_inode *orig_inode = inode;
 
-	sb = inode->i_sb;
+	sb = inode->vfs_inode.i_sb;
 
 	if (btrfs_test_opt(fs_info, NOTREELOG)) {
 		ret = 1;
@@ -5423,18 +5424,17 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_no_trans;
 	}
 
-	if (root != BTRFS_I(inode)->root ||
-	    btrfs_root_refs(&root->root_item) == 0) {
+	if (root != inode->root || btrfs_root_refs(&root->root_item) == 0) {
 		ret = 1;
 		goto end_no_trans;
 	}
 
-	ret = check_parent_dirs_for_sync(trans, BTRFS_I(inode), parent,
-					 sb, last_committed);
+	ret = check_parent_dirs_for_sync(trans, inode, parent, sb,
+			last_committed);
 	if (ret)
 		goto end_no_trans;
 
-	if (btrfs_inode_in_log(BTRFS_I(inode), trans->transid)) {
+	if (btrfs_inode_in_log(inode, trans->transid)) {
 		ret = BTRFS_NO_LOG_SYNC;
 		goto end_no_trans;
 	}
@@ -5443,8 +5443,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto end_no_trans;
 
-	ret = btrfs_log_inode(trans, root, BTRFS_I(inode), inode_only,
-			start, end, ctx);
+	ret = btrfs_log_inode(trans, root, inode, inode_only, start, end, ctx);
 	if (ret)
 		goto end_trans;
 
@@ -5454,14 +5453,14 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * we can use the last_unlink_trans field to record renames
 	 * and other fun in this file.
 	 */
-	if (S_ISREG(inode->i_mode) &&
-	    BTRFS_I(inode)->generation <= last_committed &&
-	    BTRFS_I(inode)->last_unlink_trans <= last_committed) {
+	if (S_ISREG(inode->vfs_inode.i_mode) &&
+	    inode->generation <= last_committed &&
+	    inode->last_unlink_trans <= last_committed) {
 		ret = 0;
 		goto end_trans;
 	}
 
-	if (S_ISDIR(inode->i_mode) && ctx && ctx->log_new_dentries)
+	if (S_ISDIR(inode->vfs_inode.i_mode) && ctx && ctx->log_new_dentries)
 		log_dentries = true;
 
 	/*
@@ -5505,8 +5504,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * but the file inode does not have a matching BTRFS_INODE_REF_KEY item
 	 * and has a link count of 2.
 	 */
-	if (BTRFS_I(inode)->last_unlink_trans > last_committed) {
-		ret = btrfs_log_all_parents(trans, BTRFS_I(orig_inode), ctx);
+	if (inode->last_unlink_trans > last_committed) {
+		ret = btrfs_log_all_parents(trans, orig_inode, ctx);
 		if (ret)
 			goto end_trans;
 	}
@@ -5515,14 +5514,13 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			break;
 
-		inode = d_inode(parent);
-		if (root != BTRFS_I(inode)->root)
+		inode = BTRFS_I(d_inode(parent));
+		if (root != inode->root)
 			break;
 
-		if (BTRFS_I(inode)->generation > last_committed) {
-			ret = btrfs_log_inode(trans, root, BTRFS_I(inode),
-					      LOG_INODE_EXISTS,
-					      0, LLONG_MAX, ctx);
+		if (inode->generation > last_committed) {
+			ret = btrfs_log_inode(trans, root, inode,
+					LOG_INODE_EXISTS, 0, LLONG_MAX, ctx);
 			if (ret)
 				goto end_trans;
 		}
@@ -5534,7 +5532,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		old_parent = parent;
 	}
 	if (log_dentries)
-		ret = log_new_dir_dentries(trans, root, BTRFS_I(orig_inode), ctx);
+		ret = log_new_dir_dentries(trans, root, orig_inode, ctx);
 	else
 		ret = 0;
 end_trans:
@@ -5566,8 +5564,8 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
 	struct dentry *parent = dget_parent(dentry);
 	int ret;
 
-	ret = btrfs_log_inode_parent(trans, root, d_inode(dentry), parent,
-				     start, end, 0, ctx);
+	ret = btrfs_log_inode_parent(trans, root, BTRFS_I(d_inode(dentry)),
+			parent, start, end, 0, ctx);
 	dput(parent);
 
 	return ret;
@@ -5829,7 +5827,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	    (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed))
 		return 0;
 
-	return btrfs_log_inode_parent(trans, root, &inode->vfs_inode, parent, 0,
+	return btrfs_log_inode_parent(trans, root, inode, parent, 0,
 				      LLONG_MAX, 1, NULL);
 }
 
-- 
GitLab


From 9cdc51241090a36d3b7b4ff374fb18b764b3b3a4 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:02 +0200
Subject: [PATCH 302/898] btrfs: Make btrfs_extent_item_to_extent_map take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h     |  2 +-
 fs/btrfs/file-item.c | 10 +++++-----
 fs/btrfs/inode.c     |  3 ++-
 fs/btrfs/ioctl.c     |  3 ++-
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index af68f8452f19..2e0845eafcbc 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3081,7 +3081,7 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 		       u64 file_start, int contig);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
-void btrfs_extent_item_to_extent_map(struct inode *inode,
+void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const struct btrfs_path *path,
 				     struct btrfs_file_extent_item *fi,
 				     const bool new_inline,
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a8a0dd217084..54ec6d6ef016 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -904,14 +904,14 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 	goto out;
 }
 
-void btrfs_extent_item_to_extent_map(struct inode *inode,
+void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const struct btrfs_path *path,
 				     struct btrfs_file_extent_item *fi,
 				     const bool new_inline,
 				     struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf = path->nodes[0];
 	const int slot = path->slots[0];
 	struct btrfs_key key;
@@ -976,8 +976,8 @@ void btrfs_extent_item_to_extent_map(struct inode *inode,
 		}
 	} else {
 		btrfs_err(fs_info,
-			  "unknown file extent item type %d, inode %llu, offset %llu, root %llu",
-			  type, btrfs_ino(BTRFS_I(inode)), extent_start,
+			  "unknown file extent item type %d, inode %llu, offset %llu, "
+			  "root %llu", type, btrfs_ino(inode), extent_start,
 			  root->root_key.objectid);
 	}
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d5339b8d4663..0b46542010fb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6862,7 +6862,8 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 		goto not_found_em;
 	}
 
-	btrfs_extent_item_to_extent_map(inode, path, item, new_inline, em);
+	btrfs_extent_item_to_extent_map(BTRFS_I(inode), path, item,
+			new_inline, em);
 
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bc2e03a2569e..bb4e6ec26b7f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3333,7 +3333,8 @@ static void clone_update_extent_map(struct inode *inode,
 
 		fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				    struct btrfs_file_extent_item);
-		btrfs_extent_item_to_extent_map(inode, path, fi, false, em);
+		btrfs_extent_item_to_extent_map(BTRFS_I(inode), path, fi,
+				false, em);
 		em->generation = -1;
 		if (btrfs_file_extent_type(path->nodes[0], fi) ==
 		    BTRFS_FILE_EXTENT_INLINE)
-- 
GitLab


From 6fc0ef687029760476e309aa85d437a47313eb08 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:03 +0200
Subject: [PATCH 303/898] btrfs: Make btrfs_clear_bit_hook take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c |  3 ++-
 fs/btrfs/extent_io.h |  6 ++++--
 fs/btrfs/inode.c     | 37 +++++++++++++++++++------------------
 3 files changed, 25 insertions(+), 21 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ded750eb90c4..d21082962565 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -428,7 +428,8 @@ static void clear_state_cb(struct extent_io_tree *tree,
 			   struct extent_state *state, unsigned *bits)
 {
 	if (tree->ops && tree->ops->clear_bit_hook)
-		tree->ops->clear_bit_hook(tree->mapping->host, state, bits);
+		tree->ops->clear_bit_hook(BTRFS_I(tree->mapping->host),
+				state, bits);
 }
 
 static void set_state_bits(struct extent_io_tree *tree,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 345fc33f843d..cd8b3dd6948d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -84,6 +84,7 @@ extern void le_bitmap_clear(u8 *map, unsigned int start, int len);
 
 struct extent_state;
 struct btrfs_root;
+struct btrfs_inode;
 struct btrfs_io_bio;
 struct io_failure_record;
 
@@ -107,8 +108,9 @@ struct extent_io_ops {
 				      struct extent_state *state, int uptodate);
 	void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
 			     unsigned *bits);
-	void (*clear_bit_hook)(struct inode *inode, struct extent_state *state,
-			       unsigned *bits);
+	void (*clear_bit_hook)(struct btrfs_inode *inode,
+			struct extent_state *state,
+			unsigned *bits);
 	void (*merge_extent_hook)(struct inode *inode,
 				  struct extent_state *new,
 				  struct extent_state *other);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0b46542010fb..0600d55bb173 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1703,18 +1703,18 @@ static void btrfs_set_bit_hook(struct inode *inode,
 /*
  * extent_io.c clear_bit_hook, see set_bit_hook for why
  */
-static void btrfs_clear_bit_hook(struct inode *inode,
+static void btrfs_clear_bit_hook(struct btrfs_inode *inode,
 				 struct extent_state *state,
 				 unsigned *bits)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 len = state->end + 1 - state->start;
 	u32 num_extents = count_max_extents(len);
 
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
 	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG))
-		BTRFS_I(inode)->defrag_bytes -= len;
-	spin_unlock(&BTRFS_I(inode)->lock);
+		inode->defrag_bytes -= len;
+	spin_unlock(&inode->lock);
 
 	/*
 	 * set_bit and clear bit hooks normally require _irqsave/restore
@@ -1722,15 +1722,15 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 	 * bit, which is only set or cleared with irqs on
 	 */
 	if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
-		struct btrfs_root *root = BTRFS_I(inode)->root;
-		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
+		struct btrfs_root *root = inode->root;
+		bool do_list = !btrfs_is_free_space_inode(inode);
 
 		if (*bits & EXTENT_FIRST_DELALLOC) {
 			*bits &= ~EXTENT_FIRST_DELALLOC;
 		} else if (!(*bits & EXTENT_DO_ACCOUNTING)) {
-			spin_lock(&BTRFS_I(inode)->lock);
-			BTRFS_I(inode)->outstanding_extents -= num_extents;
-			spin_unlock(&BTRFS_I(inode)->lock);
+			spin_lock(&inode->lock);
+			inode->outstanding_extents -= num_extents;
+			spin_unlock(&inode->lock);
 		}
 
 		/*
@@ -1740,7 +1740,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		 */
 		if (*bits & EXTENT_DO_ACCOUNTING &&
 		    root != fs_info->tree_root)
-			btrfs_delalloc_release_metadata(BTRFS_I(inode), len);
+			btrfs_delalloc_release_metadata(inode, len);
 
 		/* For sanity tests. */
 		if (btrfs_is_testing(fs_info))
@@ -1750,18 +1750,19 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		    && do_list && !(state->state & EXTENT_NORESERVE)
 		    && (*bits & (EXTENT_DO_ACCOUNTING |
 		    EXTENT_CLEAR_DATA_RESV)))
-			btrfs_free_reserved_data_space_noquota(inode,
+			btrfs_free_reserved_data_space_noquota(
+					&inode->vfs_inode,
 					state->start, len);
 
 		__percpu_counter_add(&fs_info->delalloc_bytes, -len,
 				     fs_info->delalloc_batch);
-		spin_lock(&BTRFS_I(inode)->lock);
-		BTRFS_I(inode)->delalloc_bytes -= len;
-		if (do_list && BTRFS_I(inode)->delalloc_bytes == 0 &&
+		spin_lock(&inode->lock);
+		inode->delalloc_bytes -= len;
+		if (do_list && inode->delalloc_bytes == 0 &&
 		    test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			     &BTRFS_I(inode)->runtime_flags))
-			btrfs_del_delalloc_inode(root, inode);
-		spin_unlock(&BTRFS_I(inode)->lock);
+				&inode->runtime_flags))
+			btrfs_del_delalloc_inode(root, &inode->vfs_inode);
+		spin_unlock(&inode->lock);
 	}
 }
 
-- 
GitLab


From a2f392e4015a45c896528d5fdfcec4bad3ddd121 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:04 +0200
Subject: [PATCH 304/898] btrfs: Make clone_update_extent_map take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bb4e6ec26b7f..12ae210f8719 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3311,20 +3311,19 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static void clone_update_extent_map(struct inode *inode,
+static void clone_update_extent_map(struct btrfs_inode *inode,
 				    const struct btrfs_trans_handle *trans,
 				    const struct btrfs_path *path,
 				    const u64 hole_offset,
 				    const u64 hole_len)
 {
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
 
 	em = alloc_extent_map();
 	if (!em) {
-		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			&BTRFS_I(inode)->runtime_flags);
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
 		return;
 	}
 
@@ -3333,13 +3332,12 @@ static void clone_update_extent_map(struct inode *inode,
 
 		fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				    struct btrfs_file_extent_item);
-		btrfs_extent_item_to_extent_map(BTRFS_I(inode), path, fi,
-				false, em);
+		btrfs_extent_item_to_extent_map(inode, path, fi, false, em);
 		em->generation = -1;
 		if (btrfs_file_extent_type(path->nodes[0], fi) ==
 		    BTRFS_FILE_EXTENT_INLINE)
 			set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-				&BTRFS_I(inode)->runtime_flags);
+					&inode->runtime_flags);
 	} else {
 		em->start = hole_offset;
 		em->len = hole_len;
@@ -3360,13 +3358,12 @@ static void clone_update_extent_map(struct inode *inode,
 			free_extent_map(em);
 			break;
 		}
-		btrfs_drop_extent_cache(BTRFS_I(inode), em->start,
+		btrfs_drop_extent_cache(inode, em->start,
 					em->start + em->len - 1, 0);
 	}
 
 	if (ret)
-		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			&BTRFS_I(inode)->runtime_flags);
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
 }
 
 /*
@@ -3792,11 +3789,12 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 
 			/* If we have an implicit hole (NO_HOLES feature). */
 			if (drop_start < new_key.offset)
-				clone_update_extent_map(inode, trans,
+				clone_update_extent_map(BTRFS_I(inode), trans,
 						NULL, drop_start,
 						new_key.offset - drop_start);
 
-			clone_update_extent_map(inode, trans, path, 0, 0);
+			clone_update_extent_map(BTRFS_I(inode), trans,
+					path, 0, 0);
 
 			btrfs_mark_buffer_dirty(leaf);
 			btrfs_release_path(path);
@@ -3846,8 +3844,9 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 			btrfs_end_transaction(trans);
 			goto out;
 		}
-		clone_update_extent_map(inode, trans, NULL, last_dest_end,
-					destoff + len - last_dest_end);
+		clone_update_extent_map(BTRFS_I(inode), trans, NULL,
+				last_dest_end,
+				destoff + len - last_dest_end);
 		ret = clone_finish_inode_update(trans, inode, destoff + len,
 						destoff, olen, no_time_update);
 	}
-- 
GitLab


From 1c8c9c5216295711c79d0e512dc8b3d5f1bfc35d Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:05 +0200
Subject: [PATCH 305/898] btrfs: Make check_extent_to_block take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/scrub.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index bdf58b0eaef8..b0251eb1239f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -4236,7 +4236,7 @@ static void copy_nocow_pages_worker(struct btrfs_work *work)
 	scrub_pending_trans_workers_dec(sctx);
 }
 
-static int check_extent_to_block(struct inode *inode, u64 start, u64 len,
+static int check_extent_to_block(struct btrfs_inode *inode, u64 start, u64 len,
 				 u64 logical)
 {
 	struct extent_state *cached_state = NULL;
@@ -4246,10 +4246,10 @@ static int check_extent_to_block(struct inode *inode, u64 start, u64 len,
 	u64 lockstart = start, lockend = start + len - 1;
 	int ret = 0;
 
-	io_tree = &BTRFS_I(inode)->io_tree;
+	io_tree = &inode->io_tree;
 
 	lock_extent_bits(io_tree, lockstart, lockend, &cached_state);
-	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart, len);
+	ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
 	if (ordered) {
 		btrfs_put_ordered_extent(ordered);
 		ret = 1;
@@ -4325,7 +4325,8 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
 	io_tree = &BTRFS_I(inode)->io_tree;
 	nocow_ctx_logical = nocow_ctx->logical;
 
-	ret = check_extent_to_block(inode, offset, len, nocow_ctx_logical);
+	ret = check_extent_to_block(BTRFS_I(inode), offset, len,
+			nocow_ctx_logical);
 	if (ret) {
 		ret = ret > 0 ? 0 : ret;
 		goto out;
@@ -4372,7 +4373,7 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
 			}
 		}
 
-		ret = check_extent_to_block(inode, offset, len,
+		ret = check_extent_to_block(BTRFS_I(inode), offset, len,
 					    nocow_ctx_logical);
 		if (ret) {
 			ret = ret > 0 ? 0 : ret;
-- 
GitLab


From fc4f21b1d8d023cf0a2b1b050ae18e15dbe7068e Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:06 +0200
Subject: [PATCH 306/898] btrfs: Make get_extent_t take btrfs_inode

In addition to changing the signature, this patch also switches
all the functions which are used as an argument to also take btrfs_inode.
Namely those are: btrfs_get_extent and btrfs_get_extent_filemap.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h             | 12 +++++-----
 fs/btrfs/disk-io.c           |  6 ++---
 fs/btrfs/extent_io.c         |  6 ++---
 fs/btrfs/extent_io.h         |  2 +-
 fs/btrfs/file.c              |  7 +++---
 fs/btrfs/inode.c             | 34 +++++++++++++++-------------
 fs/btrfs/ioctl.c             |  2 +-
 fs/btrfs/tests/inode-tests.c | 44 +++++++++++++++++++-----------------
 8 files changed, 59 insertions(+), 54 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2e0845eafcbc..809736ec549b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3100,9 +3100,9 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 						    int delay_iput);
 void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
 
-struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
-					   size_t pg_offset, u64 start, u64 len,
-					   int create);
+struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
+		struct page *page, size_t pg_offset, u64 start,
+		u64 len, int create);
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes);
@@ -3166,9 +3166,9 @@ void btrfs_destroy_cachep(void);
 long btrfs_ioctl_trans_end(struct file *file);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root, int *was_new);
-struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
-				    size_t pg_offset, u64 start, u64 end,
-				    int create);
+struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
+		struct page *page, size_t pg_offset,
+		u64 start, u64 end, int create);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      struct inode *inode);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2b06f557c176..a53ff3bff8eb 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -219,12 +219,12 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
  * extents on the btree inode are pretty simple, there's one extent
  * that covers the entire device
  */
-static struct extent_map *btree_get_extent(struct inode *inode,
+static struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d21082962565..c3abf846a449 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2860,7 +2860,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
 		*em_cached = NULL;
 	}
 
-	em = get_extent(inode, page, pg_offset, start, len, 0);
+	em = get_extent(BTRFS_I(inode), page, pg_offset, start, len, 0);
 	if (em_cached && !IS_ERR_OR_NULL(em)) {
 		BUG_ON(*em_cached);
 		atomic_inc(&em->refs);
@@ -3373,7 +3373,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 							 page_end, NULL, 1);
 			break;
 		}
-		em = epd->get_extent(inode, page, pg_offset, cur,
+		em = epd->get_extent(BTRFS_I(inode), page, pg_offset, cur,
 				     end - cur + 1, 1);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
@@ -4338,7 +4338,7 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 		if (len == 0)
 			break;
 		len = ALIGN(len, sectorsize);
-		em = get_extent(inode, NULL, 0, offset, len, 0);
+		em = get_extent(BTRFS_I(inode), NULL, 0, offset, len, 0);
 		if (IS_ERR_OR_NULL(em))
 			return em;
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index cd8b3dd6948d..c16260c6c14f 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -211,7 +211,7 @@ static inline int extent_compress_type(unsigned long bio_flags)
 
 struct extent_map_tree;
 
-typedef struct extent_map *(get_extent_t)(struct inode *inode,
+typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
 					  struct page *page,
 					  size_t pg_offset,
 					  u64 start, u64 len,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index dff7ec1770c1..48dfb8e4baf2 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2341,7 +2341,7 @@ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
 	struct extent_map *em;
 	int ret = 0;
 
-	em = btrfs_get_extent(inode, NULL, 0, *start, *len, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, *start, *len, 0);
 	if (IS_ERR_OR_NULL(em)) {
 		if (!em)
 			ret = -ENOMEM;
@@ -2833,7 +2833,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	/* First, check if we exceed the qgroup limit */
 	INIT_LIST_HEAD(&reserve_list);
 	while (1) {
-		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
 				      alloc_end - cur_offset, 0);
 		if (IS_ERR_OR_NULL(em)) {
 			if (!em)
@@ -2960,7 +2960,8 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 			 &cached_state);
 
 	while (start < inode->i_size) {
-		em = btrfs_get_extent_fiemap(inode, NULL, 0, start, len, 0);
+		em = btrfs_get_extent_fiemap(BTRFS_I(inode), NULL, 0,
+				start, len, 0);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			em = NULL;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0600d55bb173..7e12c727f791 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4852,7 +4852,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 
 	cur_offset = hole_start;
 	while (1) {
-		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
 				block_end - cur_offset, 0);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
@@ -6732,25 +6732,26 @@ static noinline int uncompress_inline(struct btrfs_path *path,
  * This also copies inline extents directly into the page.
  */
 
-struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
-				    size_t pg_offset, u64 start, u64 len,
-				    int create)
+struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
+		struct page *page,
+	    size_t pg_offset, u64 start, u64 len,
+		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret;
 	int err = 0;
 	u64 extent_start = 0;
 	u64 extent_end = 0;
-	u64 objectid = btrfs_ino(BTRFS_I(inode));
+	u64 objectid = btrfs_ino(inode);
 	u32 found_type;
 	struct btrfs_path *path = NULL;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	struct btrfs_file_extent_item *item;
 	struct extent_buffer *leaf;
 	struct btrfs_key found_key;
 	struct extent_map *em = NULL;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
+	struct extent_io_tree *io_tree = &inode->io_tree;
 	struct btrfs_trans_handle *trans = NULL;
 	const bool new_inline = !page || create;
 
@@ -6863,7 +6864,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 		goto not_found_em;
 	}
 
-	btrfs_extent_item_to_extent_map(BTRFS_I(inode), path, item,
+	btrfs_extent_item_to_extent_map(inode, path, item,
 			new_inline, em);
 
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
@@ -7000,7 +7001,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	write_unlock(&em_tree->lock);
 out:
 
-	trace_btrfs_get_extent(root, BTRFS_I(inode), em);
+	trace_btrfs_get_extent(root, inode, em);
 
 	btrfs_free_path(path);
 	if (trans) {
@@ -7016,9 +7017,10 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	return em;
 }
 
-struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
-					   size_t pg_offset, u64 start, u64 len,
-					   int create)
+struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
+		struct page *page,
+		size_t pg_offset, u64 start, u64 len,
+		int create)
 {
 	struct extent_map *em;
 	struct extent_map *hole_em = NULL;
@@ -7055,7 +7057,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 	em = NULL;
 
 	/* ok, we didn't find anything, lets look for delalloc */
-	found = count_range_bits(&BTRFS_I(inode)->io_tree, &range_start,
+	found = count_range_bits(&inode->io_tree, &range_start,
 				 end, len, EXTENT_DELALLOC, 1);
 	found_end = range_start + found;
 	if (found_end < range_start)
@@ -7625,7 +7627,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		goto err;
 	}
 
-	em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto unlock_err;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 12ae210f8719..45a708555f9b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1009,7 +1009,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
 
 		/* get the big lock and read metadata off disk */
 		lock_extent_bits(io_tree, start, end, &cached);
-		em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
 		unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS);
 
 		if (IS_ERR(em))
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 924bcbf43275..8c91d03cc82d 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -278,7 +278,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	/* First with no extents */
 	BTRFS_I(inode)->root = root;
-	em = btrfs_get_extent(inode, NULL, 0, 0, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, sectorsize, 0);
 	if (IS_ERR(em)) {
 		em = NULL;
 		test_msg("Got an error when we shouldn't have\n");
@@ -302,7 +302,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	 */
 	setup_file_extents(root, sectorsize);
 
-	em = btrfs_get_extent(inode, NULL, 0, 0, (u64)-1, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, (u64)-1, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -323,7 +323,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -350,7 +350,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -372,7 +372,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Regular extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -399,7 +399,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are split extents */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -428,7 +428,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -450,7 +450,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -484,7 +484,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -513,7 +513,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are a half written prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -543,7 +543,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -576,7 +576,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -611,7 +611,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Now for the compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -645,7 +645,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Split compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -680,7 +680,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -707,7 +707,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -742,7 +742,8 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* A hole between regular extents but no hole extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset + 6, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset + 6,
+			sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -769,7 +770,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096 * 1024, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, 4096 * 1024, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -802,7 +803,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -885,7 +886,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	insert_inode_item_key(root);
 	insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize,
 		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
-	em = btrfs_get_extent(inode, NULL, 0, 0, 2 * sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, 2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -907,7 +908,8 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	}
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, sectorsize, 2 * sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize,
+			2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
-- 
GitLab


From 9e3e97f45c1f4debe53f72ad309ec06890d3aac2 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:07 +0200
Subject: [PATCH 307/898] btrfs: Make btrfs_del_delalloc_inode take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7e12c727f791..1934db1af2fc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1632,15 +1632,15 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
 }
 
 static void btrfs_del_delalloc_inode(struct btrfs_root *root,
-				     struct inode *inode)
+				     struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 
 	spin_lock(&root->delalloc_lock);
-	if (!list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
-		list_del_init(&BTRFS_I(inode)->delalloc_inodes);
+	if (!list_empty(&inode->delalloc_inodes)) {
+		list_del_init(&inode->delalloc_inodes);
 		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			  &BTRFS_I(inode)->runtime_flags);
+			  &inode->runtime_flags);
 		root->nr_delalloc_inodes--;
 		if (!root->nr_delalloc_inodes) {
 			spin_lock(&fs_info->delalloc_root_lock);
@@ -1760,8 +1760,8 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode,
 		inode->delalloc_bytes -= len;
 		if (do_list && inode->delalloc_bytes == 0 &&
 		    test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-				&inode->runtime_flags))
-			btrfs_del_delalloc_inode(root, &inode->vfs_inode);
+					&inode->runtime_flags))
+			btrfs_del_delalloc_inode(root, inode);
 		spin_unlock(&inode->lock);
 	}
 }
-- 
GitLab


From db0a669fb002416faafe34481d6a6e21cdf0e926 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:08 +0200
Subject: [PATCH 308/898] btrfs: Make btrfs_add_link take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h    |  2 +-
 fs/btrfs/inode.c    | 39 ++++++++++++++++++++-------------------
 fs/btrfs/tree-log.c |  8 +++++---
 3 files changed, 26 insertions(+), 23 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 809736ec549b..f03c2f285eb1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3129,7 +3129,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_inode *dir, struct btrfs_inode *inode,
 		       const char *name, int name_len);
 int btrfs_add_link(struct btrfs_trans_handle *trans,
-		   struct inode *parent_inode, struct inode *inode,
+		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index);
 int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1934db1af2fc..91c6be6a72df 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6251,18 +6251,18 @@ static inline u8 btrfs_inode_type(struct inode *inode)
  * inode to the parent directory.
  */
 int btrfs_add_link(struct btrfs_trans_handle *trans,
-		   struct inode *parent_inode, struct inode *inode,
+		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret = 0;
 	struct btrfs_key key;
-	struct btrfs_root *root = BTRFS_I(parent_inode)->root;
-	u64 ino = btrfs_ino(BTRFS_I(inode));
-	u64 parent_ino = btrfs_ino(BTRFS_I(parent_inode));
+	struct btrfs_root *root = parent_inode->root;
+	u64 ino = btrfs_ino(inode);
+	u64 parent_ino = btrfs_ino(parent_inode);
 
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
-		memcpy(&key, &BTRFS_I(inode)->root->root_key, sizeof(key));
+		memcpy(&key, &inode->root->root_key, sizeof(key));
 	} else {
 		key.objectid = ino;
 		key.type = BTRFS_INODE_ITEM_KEY;
@@ -6283,8 +6283,8 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		return ret;
 
 	ret = btrfs_insert_dir_item(trans, root, name, name_len,
-				    BTRFS_I(parent_inode), &key,
-				    btrfs_inode_type(inode), index);
+				    parent_inode, &key,
+				    btrfs_inode_type(&inode->vfs_inode), index);
 	if (ret == -EEXIST || ret == -EOVERFLOW)
 		goto fail_dir_item;
 	else if (ret) {
@@ -6292,12 +6292,12 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size +
+	btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size +
 			   name_len * 2);
-	inode_inc_iversion(parent_inode);
-	parent_inode->i_mtime = parent_inode->i_ctime =
-		current_time(parent_inode);
-	ret = btrfs_update_inode(trans, root, parent_inode);
+	inode_inc_iversion(&parent_inode->vfs_inode);
+	parent_inode->vfs_inode.i_mtime = parent_inode->vfs_inode.i_ctime =
+		current_time(&parent_inode->vfs_inode);
+	ret = btrfs_update_inode(trans, root, &parent_inode->vfs_inode);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 	return ret;
@@ -6324,7 +6324,7 @@ static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
 			    struct inode *dir, struct dentry *dentry,
 			    struct inode *inode, int backref, u64 index)
 {
-	int err = btrfs_add_link(trans, dir, inode,
+	int err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 				 dentry->d_name.name, dentry->d_name.len,
 				 backref, index);
 	if (err > 0)
@@ -6601,8 +6601,9 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (err)
 		goto out_fail_inode;
 
-	err = btrfs_add_link(trans, dir, inode, dentry->d_name.name,
-			     dentry->d_name.len, 0, index);
+	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
+			dentry->d_name.name,
+			dentry->d_name.len, 0, index);
 	if (err)
 		goto out_fail_inode;
 
@@ -9592,7 +9593,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		goto out_fail;
 	}
 
-	ret = btrfs_add_link(trans, new_dir, old_inode,
+	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
 			     new_dentry->d_name.name,
 			     new_dentry->d_name.len, 0, old_idx);
 	if (ret) {
@@ -9600,7 +9601,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		goto out_fail;
 	}
 
-	ret = btrfs_add_link(trans, old_dir, new_inode,
+	ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode),
 			     old_dentry->d_name.name,
 			     old_dentry->d_name.len, 0, new_idx);
 	if (ret) {
@@ -9877,7 +9878,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
-	ret = btrfs_add_link(trans, new_dir, old_inode,
+	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
 			     new_dentry->d_name.name,
 			     new_dentry->d_name.len, 0, index);
 	if (ret) {
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f8965b081212..c9ada4b90004 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1322,8 +1322,9 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 			}
 
 			/* insert our name */
-			ret = btrfs_add_link(trans, dir, inode, name, namelen,
-					     0, ref_index);
+			ret = btrfs_add_link(trans, BTRFS_I(dir),
+					BTRFS_I(inode),
+					name, namelen, 0, ref_index);
 			if (ret)
 				goto out;
 
@@ -1641,7 +1642,8 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
 		return -EIO;
 	}
 
-	ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index);
+	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name,
+			name_len, 1, index);
 
 	/* FIXME, put inode into FIXUP list */
 
-- 
GitLab


From cef415af208984650de925e28d40aa4a6e8513f4 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:09 +0200
Subject: [PATCH 309/898] btrfs: Make btrfs_add_nondir take btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 91c6be6a72df..dafd3fdd6f2b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6321,10 +6321,10 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 }
 
 static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
-			    struct inode *dir, struct dentry *dentry,
-			    struct inode *inode, int backref, u64 index)
+			    struct btrfs_inode *dir, struct dentry *dentry,
+			    struct btrfs_inode *inode, int backref, u64 index)
 {
-	int err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
+	int err = btrfs_add_link(trans, dir, inode,
 				 dentry->d_name.name, dentry->d_name.len,
 				 backref, index);
 	if (err > 0)
@@ -6378,7 +6378,8 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (err)
 		goto out_unlock_inode;
 
-	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
+	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
+			0, index);
 	if (err) {
 		goto out_unlock_inode;
 	} else {
@@ -6455,7 +6456,8 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	if (err)
 		goto out_unlock_inode;
 
-	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
+	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
+			0, index);
 	if (err)
 		goto out_unlock_inode;
 
@@ -6521,7 +6523,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	ihold(inode);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
-	err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index);
+	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
+			1, index);
 
 	if (err) {
 		drop_inode = 1;
@@ -9703,8 +9706,8 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	ret = btrfs_add_nondir(trans, dir, dentry,
-				inode, 0, index);
+	ret = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
+				BTRFS_I(inode), 0, index);
 	if (ret)
 		goto out;
 
@@ -10253,7 +10256,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	 * elsewhere above.
 	 */
 	if (!err)
-		err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
+		err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
+				BTRFS_I(inode), 0, index);
 	if (err) {
 		drop_inode = 1;
 		goto out_unlock_inode;
-- 
GitLab


From abcefb1eeeff04734a59b4dd3724abbf0688252c Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:10 +0200
Subject: [PATCH 310/898] btrfs: make btrfs_inode_block_unlocked_dio take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h | 4 ++--
 fs/btrfs/inode.c       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index c10d21b2f0df..d84cf2b0c7b6 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -311,9 +311,9 @@ struct btrfs_dio_private {
  * to grab i_mutex. It is used to avoid the endless truncate due to
  * nonlocked dio read.
  */
-static inline void btrfs_inode_block_unlocked_dio(struct inode *inode)
+static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode)
 {
-	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags);
+	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
 	smp_mb();
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index dafd3fdd6f2b..59b93a2369aa 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5002,7 +5002,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		truncate_setsize(inode, newsize);
 
 		/* Disable nonlocked read DIO to avoid the end less truncate */
-		btrfs_inode_block_unlocked_dio(inode);
+		btrfs_inode_block_unlocked_dio(BTRFS_I(inode));
 		inode_dio_wait(inode);
 		btrfs_inode_resume_unlocked_dio(inode);
 
-- 
GitLab


From 0b581701d9771c55a908c612ca49850e6088fe08 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 20 Feb 2017 13:51:11 +0200
Subject: [PATCH 311/898] btrfs: make btrfs_inode_resume_unlocked_dio take
 btrfs_inode

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h | 5 ++---
 fs/btrfs/inode.c       | 2 +-
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index d84cf2b0c7b6..0c6baaba0651 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -317,11 +317,10 @@ static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode)
 	smp_mb();
 }
 
-static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
+static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode)
 {
 	smp_mb__before_atomic();
-	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
-		  &BTRFS_I(inode)->runtime_flags);
+	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
 }
 
 static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 59b93a2369aa..596e5cb4bfa2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5004,7 +5004,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		/* Disable nonlocked read DIO to avoid the end less truncate */
 		btrfs_inode_block_unlocked_dio(BTRFS_I(inode));
 		inode_dio_wait(inode);
-		btrfs_inode_resume_unlocked_dio(inode);
+		btrfs_inode_resume_unlocked_dio(BTRFS_I(inode));
 
 		ret = btrfs_truncate(inode);
 		if (ret && inode->i_nlink) {
-- 
GitLab


From 29e09229d9f26129a39462fae0ddabc4d9533989 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 17 Feb 2017 08:39:28 +0100
Subject: [PATCH 312/898] netfilter: use skb_to_full_sk in ip_route_me_harder

inet_sk(skb->sk) is illegal in case skb is attached to request socket.

Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener")
Reported by: Daniel J Blueman <daniel@quora.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Tested-by: Daniel J Blueman <daniel@quora.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index b3cc1335adbc..c0cc6aa8cfaa 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -23,7 +23,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
-	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
+	const struct sock *sk = skb_to_full_sk(skb);
+	__u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
 	struct net_device *dev = skb_dst(skb)->dev;
 	unsigned int hh_len;
 
@@ -40,7 +41,7 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	fl4.daddr = iph->daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_tos = RT_TOS(iph->tos);
-	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+	fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0;
 	if (!fl4.flowi4_oif)
 		fl4.flowi4_oif = l3mdev_master_ifindex(dev);
 	fl4.flowi4_mark = skb->mark;
@@ -61,7 +62,7 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t
 	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
 		struct dst_entry *dst = skb_dst(skb);
 		skb_dst_set(skb, NULL);
-		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
+		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), sk, 0);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 		skb_dst_set(skb, dst);
-- 
GitLab


From c3a49c8991212e1ef795c7a46881ac5cc7766993 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 28 Feb 2017 00:05:01 +0100
Subject: [PATCH 313/898] cpufreq: intel_pstate: Fix limits issue with
 operation mode switching

There is a problem with intel_pstate operation mode switching
introduced by commit fb1fe1041c04 (cpufreq: intel_pstate: Operation
mode control from sysfs), because the global sysfs limits are
preserved across operation modes while per-policy limits are
reinitialized from scratch on a mode switch and both sets of limits
may get out of sync this way.

Fix that by always reinitializing the global limits upon the
registration of the driver.

Fixes: fb1fe1041c04 (cpufreq: intel_pstate: Operation mode control from sysfs)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 drivers/cpufreq/intel_pstate.c | 65 ++++++++++++----------------------
 1 file changed, 22 insertions(+), 43 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index eb0f7fb71685..9ee13f195c37 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -364,37 +364,25 @@ static bool driver_registered __read_mostly;
 static bool acpi_ppc;
 #endif
 
-static struct perf_limits performance_limits = {
-	.no_turbo = 0,
-	.turbo_disabled = 0,
-	.max_perf_pct = 100,
-	.max_perf = int_ext_tofp(1),
-	.min_perf_pct = 100,
-	.min_perf = int_ext_tofp(1),
-	.max_policy_pct = 100,
-	.max_sysfs_pct = 100,
-	.min_policy_pct = 0,
-	.min_sysfs_pct = 0,
-};
+static struct perf_limits performance_limits;
+static struct perf_limits powersave_limits;
+static struct perf_limits *limits;
 
-static struct perf_limits powersave_limits = {
-	.no_turbo = 0,
-	.turbo_disabled = 0,
-	.max_perf_pct = 100,
-	.max_perf = int_ext_tofp(1),
-	.min_perf_pct = 0,
-	.min_perf = 0,
-	.max_policy_pct = 100,
-	.max_sysfs_pct = 100,
-	.min_policy_pct = 0,
-	.min_sysfs_pct = 0,
-};
+static void intel_pstate_init_limits(struct perf_limits *limits)
+{
+	memset(limits, 0, sizeof(*limits));
+	limits->max_perf_pct = 100;
+	limits->max_perf = int_ext_tofp(1);
+	limits->max_policy_pct = 100;
+	limits->max_sysfs_pct = 100;
+}
 
-#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
-static struct perf_limits *limits = &performance_limits;
-#else
-static struct perf_limits *limits = &powersave_limits;
-#endif
+static void intel_pstate_set_performance_limits(struct perf_limits *limits)
+{
+	intel_pstate_init_limits(limits);
+	limits->min_perf_pct = 100;
+	limits->min_perf = int_ext_tofp(1);
+}
 
 static DEFINE_MUTEX(intel_pstate_driver_lock);
 static DEFINE_MUTEX(intel_pstate_limits_lock);
@@ -2084,20 +2072,6 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu)
 	synchronize_sched();
 }
 
-static void intel_pstate_set_performance_limits(struct perf_limits *limits)
-{
-	limits->no_turbo = 0;
-	limits->turbo_disabled = 0;
-	limits->max_perf_pct = 100;
-	limits->max_perf = int_ext_tofp(1);
-	limits->min_perf_pct = 100;
-	limits->min_perf = int_ext_tofp(1);
-	limits->max_policy_pct = 100;
-	limits->max_sysfs_pct = 100;
-	limits->min_policy_pct = 0;
-	limits->min_sysfs_pct = 0;
-}
-
 static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
 					    struct perf_limits *limits)
 {
@@ -2466,6 +2440,11 @@ static int intel_pstate_register_driver(void)
 {
 	int ret;
 
+	intel_pstate_init_limits(&powersave_limits);
+	intel_pstate_set_performance_limits(&performance_limits);
+	limits = IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) ?
+			&performance_limits : &powersave_limits;
+
 	ret = cpufreq_register_driver(intel_pstate_driver);
 	if (ret) {
 		intel_pstate_driver_cleanup();
-- 
GitLab


From da353f6b30bc02da29b54f5f024039698fbd23f4 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 17:55:53 +0100
Subject: [PATCH 314/898] btrfs: constify device path passed to relevant
 helpers

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dev-replace.c |  5 +++--
 fs/btrfs/dev-replace.h |  5 +++--
 fs/btrfs/volumes.c     | 18 ++++++++++--------
 fs/btrfs/volumes.h     | 12 ++++++------
 4 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 5de280b9ad73..e653921f05d9 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -304,8 +304,9 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info)
 		dev_replace->cursor_left_last_write_of_item;
 }
 
-int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, char *tgtdev_name,
-				u64 srcdevid, char *srcdev_name, int read_src)
+int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
+		const char *tgtdev_name, u64 srcdevid, const char *srcdev_name,
+		int read_src)
 {
 	struct btrfs_root *root = fs_info->dev_root;
 	struct btrfs_trans_handle *trans;
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 54ea12bda15b..f94a76844ae7 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -27,8 +27,9 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info);
 int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info,
 			    struct btrfs_ioctl_dev_replace_args *args);
-int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, char *tgtdev_name,
-				u64 srcdevid, char *srcdev_name, int read_src);
+int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
+		const char *tgtdev_name, u64 srcdevid, const char *srcdev_name,
+		int read_src);
 void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			      struct btrfs_ioctl_dev_replace_args *args);
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1fac98728814..b443cc71830f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1725,7 +1725,7 @@ static int btrfs_add_device(struct btrfs_trans_handle *trans,
  * Function to update ctime/mtime for a given device path.
  * Mainly used for ctime/mtime based probe like libblkid.
  */
-static void update_dev_time(char *path_name)
+static void update_dev_time(const char *path_name)
 {
 	struct file *filp;
 
@@ -1851,7 +1851,8 @@ void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
 		fs_info->fs_devices->latest_bdev = next_device->bdev;
 }
 
-int btrfs_rm_device(struct btrfs_fs_info *fs_info, char *device_path, u64 devid)
+int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
+		u64 devid)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
@@ -2091,7 +2092,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 }
 
 static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info,
-				     char *device_path,
+				     const char *device_path,
 				     struct btrfs_device **device)
 {
 	int ret = 0;
@@ -2118,7 +2119,7 @@ static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
-					 char *device_path,
+					 const char *device_path,
 					 struct btrfs_device **device)
 {
 	*device = NULL;
@@ -2151,7 +2152,8 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
  * Lookup a device given by device id, or the path if the id is 0.
  */
 int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
-				 char *devpath, struct btrfs_device **device)
+				 const char *devpath,
+				 struct btrfs_device **device)
 {
 	int ret;
 
@@ -2307,7 +2309,7 @@ static int btrfs_finish_sprout(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path)
+int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path)
 {
 	struct btrfs_root *root = fs_info->dev_root;
 	struct request_queue *q;
@@ -2515,7 +2517,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path)
 }
 
 int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				  char *device_path,
+				  const char *device_path,
 				  struct btrfs_device *srcdev,
 				  struct btrfs_device **device_out)
 {
@@ -7102,7 +7104,7 @@ int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path)
+void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path)
 {
 	struct buffer_head *bh;
 	struct btrfs_super_block *disk_super;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 24ba6bc3ec34..59be81206dd7 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -422,16 +422,16 @@ void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step);
 void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
 		struct btrfs_device *device, struct btrfs_device *this_dev);
 int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
-					 char *device_path,
+					 const char *device_path,
 					 struct btrfs_device **device);
 int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
-					 char *devpath,
+					 const char *devpath,
 					 struct btrfs_device **device);
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
 					const u8 *uuid);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
-		    char *device_path, u64 devid);
+		    const char *device_path, u64 devid);
 void btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
@@ -439,9 +439,9 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
 				       u8 *uuid, u8 *fsid);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
-int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *path);
+int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
 int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				  char *device_path,
+				  const char *device_path,
 				  struct btrfs_device *srcdev,
 				  struct btrfs_device **device_out);
 int btrfs_balance(struct btrfs_balance_control *bctl,
@@ -474,7 +474,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *tgtdev);
 void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info,
 					      struct btrfs_device *tgtdev);
-void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path);
+void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path);
 int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
 			   u64 logical, u64 len, int mirror_num);
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
-- 
GitLab


From 9ed573674ae607bc616c804657bfaf5b6ea5889d Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 18:03:49 +0100
Subject: [PATCH 315/898] btrfs: constify input buffer of btrfs_csum_data

The function does not modify the input buffer, also update a typecast in
one caller.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 4 ++--
 fs/btrfs/disk-io.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a53ff3bff8eb..67d663ab658a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -265,7 +265,7 @@ static struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 	return em;
 }
 
-u32 btrfs_csum_data(char *data, u32 seed, size_t len)
+u32 btrfs_csum_data(const char *data, u32 seed, size_t len)
 {
 	return btrfs_crc32c(seed, data, len);
 }
@@ -3448,7 +3448,7 @@ static int write_dev_supers(struct btrfs_device *device,
 			btrfs_set_super_bytenr(sb, bytenr);
 
 			crc = ~(u32)0;
-			crc = btrfs_csum_data((char *)sb +
+			crc = btrfs_csum_data((const char *)sb +
 					      BTRFS_CSUM_SIZE, crc,
 					      BTRFS_SUPER_INFO_SIZE -
 					      BTRFS_CSUM_SIZE);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 0be2d4fe705b..2e0ec29bfd69 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -116,7 +116,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
 			  int atomic);
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
-u32 btrfs_csum_data(char *data, u32 seed, size_t len);
+u32 btrfs_csum_data(const char *data, u32 seed, size_t len);
 void btrfs_csum_final(u32 crc, u8 *result);
 int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 			enum btrfs_wq_endio_type metadata);
-- 
GitLab


From 14a3357b4097d94ac6401c597abc2d02965e0fdd Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 17:58:04 +0100
Subject: [PATCH 316/898] btrfs: constify buffers used by compression helpers

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 2 +-
 fs/btrfs/compression.h | 2 +-
 fs/btrfs/lzo.c         | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index f32e86b61240..d426e4a10b2b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1015,7 +1015,7 @@ void btrfs_exit_compress(void)
  *
  * total_out is the last byte of the buffer
  */
-int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio *bio)
 {
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 09879579fbc8..1c700bb20b52 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -32,7 +32,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 			 unsigned long max_out);
 int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 		     unsigned long start_byte, size_t srclen, size_t destlen);
-int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio *bio);
 
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 45d26980caf9..e074b85aa054 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -76,7 +76,7 @@ static inline void write_compress_length(char *buf, size_t len)
 	memcpy(buf, &dlen, LZO_LEN);
 }
 
-static inline size_t read_compress_length(char *buf)
+static inline size_t read_compress_length(const char *buf)
 {
 	__le32 dlen;
 
-- 
GitLab


From 52f75f4fe74ce86376d68b30c94d5fb11cb4019e Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 18:33:53 +0100
Subject: [PATCH 317/898] btrfs: constify name of subvolume in creation helpers

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 45a708555f9b..dabfc7ac48a6 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -434,7 +434,7 @@ int btrfs_is_empty_uuid(u8 *uuid)
 
 static noinline int create_subvol(struct inode *dir,
 				  struct dentry *dentry,
-				  char *name, int namelen,
+				  const char *name, int namelen,
 				  u64 *async_transid,
 				  struct btrfs_qgroup_inherit *inherit)
 {
@@ -832,7 +832,7 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
  * inside this filesystem so it's quite a bit simpler.
  */
 static noinline int btrfs_mksubvol(const struct path *parent,
-				   char *name, int namelen,
+				   const char *name, int namelen,
 				   struct btrfs_root *snap_src,
 				   u64 *async_transid, bool readonly,
 				   struct btrfs_qgroup_inherit *inherit)
@@ -1625,7 +1625,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 }
 
 static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
-				char *name, unsigned long fd, int subvol,
+				const char *name, unsigned long fd, int subvol,
 				u64 *transid, bool readonly,
 				struct btrfs_qgroup_inherit *inherit)
 {
-- 
GitLab


From 38c31464089f639630b7c28ce933a4d60e135a02 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 19:04:07 +0100
Subject: [PATCH 318/898] btrfs: merge length input and output parameter in
 compress_pages

The length parameter is basically duplicated for input and output in the
top level caller of the compress_pages chain. We can simply use one
variable for that and reduce stack consumption. The compression
implementation will sink the parameter to a local variable so everything
works as before.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 24 +++++++++++-------------
 fs/btrfs/compression.h |  5 ++---
 fs/btrfs/inode.c       |  2 +-
 fs/btrfs/lzo.c         |  4 ++--
 fs/btrfs/zlib.c        |  3 ++-
 5 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d426e4a10b2b..7e214fd254e4 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -911,27 +911,25 @@ static void free_workspaces(void)
 }
 
 /*
- * given an address space and start/len, compress the bytes.
+ * Given an address space and start and length, compress the bytes into @pages
+ * that are allocated on demand.
  *
- * pages are allocated to hold the compressed result and stored
- * in 'pages'
+ * @out_pages is used to return the number of pages allocated.  There
+ * may be pages allocated even if we return an error.
  *
- * out_pages is used to return the number of pages allocated.  There
- * may be pages allocated even if we return an error
- *
- * total_in is used to return the number of bytes actually read.  It
- * may be smaller then len if we had to exit early because we
+ * @total_in is used to return the number of bytes actually read.  It
+ * may be smaller than the input length if we had to exit early because we
  * ran out of room in the pages array or because we cross the
  * max_out threshold.
  *
- * total_out is used to return the total number of compressed bytes
+ * @total_out is an in/out parameter, must be set to the input length and will
+ * be also used to return the total number of compressed bytes
  *
- * max_out tells us the max number of bytes that we're allowed to
+ * @max_out tells us the max number of bytes that we're allowed to
  * stuff into pages
  */
 int btrfs_compress_pages(int type, struct address_space *mapping,
-			 u64 start, unsigned long len,
-			 struct page **pages,
+			 u64 start, struct page **pages,
 			 unsigned long nr_dest_pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
@@ -944,7 +942,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 	workspace = find_workspace(type);
 
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
-						      start, len, pages,
+						      start, pages,
 						      nr_dest_pages, out_pages,
 						      total_in, total_out,
 						      max_out);
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 1c700bb20b52..725d1e0bd25d 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -23,8 +23,7 @@ void btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
 int btrfs_compress_pages(int type, struct address_space *mapping,
-			 u64 start, unsigned long len,
-			 struct page **pages,
+			 u64 start, struct page **pages,
 			 unsigned long nr_dest_pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
@@ -59,7 +58,7 @@ struct btrfs_compress_op {
 
 	int (*compress_pages)(struct list_head *workspace,
 			      struct address_space *mapping,
-			      u64 start, unsigned long len,
+			      u64 start,
 			      struct page **pages,
 			      unsigned long nr_dest_pages,
 			      unsigned long *out_pages,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 596e5cb4bfa2..8b9eac33d431 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -517,7 +517,7 @@ static noinline void compress_file_range(struct inode *inode,
 		redirty = 1;
 		ret = btrfs_compress_pages(compress_type,
 					   inode->i_mapping, start,
-					   total_compressed, pages,
+					   pages,
 					   nr_pages, &nr_pages_ret,
 					   &total_in,
 					   &total_compressed,
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index e074b85aa054..489f78c4e5ec 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -86,7 +86,7 @@ static inline size_t read_compress_length(const char *buf)
 
 static int lzo_compress_pages(struct list_head *ws,
 			      struct address_space *mapping,
-			      u64 start, unsigned long len,
+			      u64 start,
 			      struct page **pages,
 			      unsigned long nr_dest_pages,
 			      unsigned long *out_pages,
@@ -102,7 +102,7 @@ static int lzo_compress_pages(struct list_head *ws,
 	struct page *in_page = NULL;
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
-
+	unsigned long len = *total_out;
 	size_t in_len;
 	size_t out_len;
 	char *buf;
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index da497f184ff4..42d76b7824c3 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -73,7 +73,7 @@ static struct list_head *zlib_alloc_workspace(void)
 
 static int zlib_compress_pages(struct list_head *ws,
 			       struct address_space *mapping,
-			       u64 start, unsigned long len,
+			       u64 start,
 			       struct page **pages,
 			       unsigned long nr_dest_pages,
 			       unsigned long *out_pages,
@@ -89,6 +89,7 @@ static int zlib_compress_pages(struct list_head *ws,
 	struct page *in_page = NULL;
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
+	unsigned long len = *total_out;
 
 	*out_pages = 0;
 	*total_out = 0;
-- 
GitLab


From 4d3a800ebb1299944408f3b40b5b6b996477fba2 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 19:04:07 +0100
Subject: [PATCH 319/898] btrfs: merge nr_pages input and output parameter in
 compress_pages

The parameter saying how many pages can be allocated at maximum can be
merged with the output page counter, to save some stack space.  The
compression implementation will sink the parameter to a local variable
so everything works as before.

The nr_pages variables can also be simply merged in compress_file_range
into one.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c |  7 +++----
 fs/btrfs/compression.h |  2 --
 fs/btrfs/inode.c       | 13 ++++++-------
 fs/btrfs/lzo.c         |  2 +-
 fs/btrfs/zlib.c        |  2 +-
 5 files changed, 11 insertions(+), 15 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 7e214fd254e4..11dcda57e15c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -914,8 +914,8 @@ static void free_workspaces(void)
  * Given an address space and start and length, compress the bytes into @pages
  * that are allocated on demand.
  *
- * @out_pages is used to return the number of pages allocated.  There
- * may be pages allocated even if we return an error.
+ * @out_pages is an in/out parameter, holds maximum number of pages to allocate
+ * and returns number of actually allocated pages
  *
  * @total_in is used to return the number of bytes actually read.  It
  * may be smaller than the input length if we had to exit early because we
@@ -930,7 +930,6 @@ static void free_workspaces(void)
  */
 int btrfs_compress_pages(int type, struct address_space *mapping,
 			 u64 start, struct page **pages,
-			 unsigned long nr_dest_pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
 			 unsigned long *total_out,
@@ -943,7 +942,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
 						      start, pages,
-						      nr_dest_pages, out_pages,
+						      out_pages,
 						      total_in, total_out,
 						      max_out);
 	free_workspace(type, workspace);
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 725d1e0bd25d..cfcec709c61b 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -24,7 +24,6 @@ void btrfs_exit_compress(void);
 
 int btrfs_compress_pages(int type, struct address_space *mapping,
 			 u64 start, struct page **pages,
-			 unsigned long nr_dest_pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
 			 unsigned long *total_out,
@@ -60,7 +59,6 @@ struct btrfs_compress_op {
 			      struct address_space *mapping,
 			      u64 start,
 			      struct page **pages,
-			      unsigned long nr_dest_pages,
 			      unsigned long *out_pages,
 			      unsigned long *total_in,
 			      unsigned long *total_out,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8b9eac33d431..83bbe1e31869 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -430,7 +430,6 @@ static noinline void compress_file_range(struct inode *inode,
 	int ret = 0;
 	struct page **pages = NULL;
 	unsigned long nr_pages;
-	unsigned long nr_pages_ret = 0;
 	unsigned long total_compressed = 0;
 	unsigned long total_in = 0;
 	unsigned long max_compressed = SZ_128K;
@@ -518,7 +517,7 @@ static noinline void compress_file_range(struct inode *inode,
 		ret = btrfs_compress_pages(compress_type,
 					   inode->i_mapping, start,
 					   pages,
-					   nr_pages, &nr_pages_ret,
+					   &nr_pages,
 					   &total_in,
 					   &total_compressed,
 					   max_compressed);
@@ -526,7 +525,7 @@ static noinline void compress_file_range(struct inode *inode,
 		if (!ret) {
 			unsigned long offset = total_compressed &
 				(PAGE_SIZE - 1);
-			struct page *page = pages[nr_pages_ret - 1];
+			struct page *page = pages[nr_pages - 1];
 			char *kaddr;
 
 			/* zero the tail end of the last page, we might be
@@ -607,7 +606,7 @@ static noinline void compress_file_range(struct inode *inode,
 			 * will submit them to the elevator.
 			 */
 			add_async_extent(async_cow, start, num_bytes,
-					total_compressed, pages, nr_pages_ret,
+					total_compressed, pages, nr_pages,
 					compress_type);
 
 			if (start + num_bytes < end) {
@@ -624,14 +623,14 @@ static noinline void compress_file_range(struct inode *inode,
 		 * the compression code ran but failed to make things smaller,
 		 * free any pages it allocated and our page pointer array
 		 */
-		for (i = 0; i < nr_pages_ret; i++) {
+		for (i = 0; i < nr_pages; i++) {
 			WARN_ON(pages[i]->mapping);
 			put_page(pages[i]);
 		}
 		kfree(pages);
 		pages = NULL;
 		total_compressed = 0;
-		nr_pages_ret = 0;
+		nr_pages = 0;
 
 		/* flag the file so we don't compress in the future */
 		if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) &&
@@ -660,7 +659,7 @@ static noinline void compress_file_range(struct inode *inode,
 	return;
 
 free_pages_out:
-	for (i = 0; i < nr_pages_ret; i++) {
+	for (i = 0; i < nr_pages; i++) {
 		WARN_ON(pages[i]->mapping);
 		put_page(pages[i]);
 	}
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 489f78c4e5ec..0baf978fbcaf 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -88,7 +88,6 @@ static int lzo_compress_pages(struct list_head *ws,
 			      struct address_space *mapping,
 			      u64 start,
 			      struct page **pages,
-			      unsigned long nr_dest_pages,
 			      unsigned long *out_pages,
 			      unsigned long *total_in,
 			      unsigned long *total_out,
@@ -103,6 +102,7 @@ static int lzo_compress_pages(struct list_head *ws,
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
 	unsigned long len = *total_out;
+	unsigned long nr_dest_pages = *out_pages;
 	size_t in_len;
 	size_t out_len;
 	char *buf;
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 42d76b7824c3..e7f2020f8ee7 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -75,7 +75,6 @@ static int zlib_compress_pages(struct list_head *ws,
 			       struct address_space *mapping,
 			       u64 start,
 			       struct page **pages,
-			       unsigned long nr_dest_pages,
 			       unsigned long *out_pages,
 			       unsigned long *total_in,
 			       unsigned long *total_out,
@@ -90,6 +89,7 @@ static int zlib_compress_pages(struct list_head *ws,
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
 	unsigned long len = *total_out;
+	unsigned long nr_dest_pages = *out_pages;
 
 	*out_pages = 0;
 	*total_out = 0;
-- 
GitLab


From ff7638665c9a82894cabd18d26a9f8957f280f55 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 19:30:39 +0100
Subject: [PATCH 320/898] btrfs: export compression buffer limits in a header

Move the buffer limit definitions out of compress_file_range.

Reviewed-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.h | 15 +++++++++++++++
 fs/btrfs/inode.c       | 10 ----------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index cfcec709c61b..619e64c27444 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -19,6 +19,21 @@
 #ifndef __BTRFS_COMPRESSION_
 #define __BTRFS_COMPRESSION_
 
+/*
+ * We want to make sure that amount of RAM required to uncompress an extent is
+ * reasonable, so we limit the total size in ram of a compressed extent to
+ * 128k.  This is a crucial number because it also controls how easily we can
+ * spread reads across cpus for decompression.
+ *
+ * We also want to make sure the amount of IO required to do a random read is
+ * reasonably small, so we limit the size of a compressed extent to 128k.
+ */
+
+/* Maximum length of compressed data stored on disk */
+#define BTRFS_MAX_COMPRESSED		(SZ_128K)
+/* Maximum size of data before compression */
+#define BTRFS_MAX_UNCOMPRESSED		(SZ_128K)
+
 void btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 83bbe1e31869..77fb24b94a9e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -471,16 +471,6 @@ static noinline void compress_file_range(struct inode *inode,
 	   (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
 		goto cleanup_and_bail_uncompressed;
 
-	/* we want to make sure that amount of ram required to uncompress
-	 * an extent is reasonable, so we limit the total size in ram
-	 * of a compressed extent to 128k.  This is a crucial number
-	 * because it also controls how easily we can spread reads across
-	 * cpus for decompression.
-	 *
-	 * We also want to make sure the amount of IO required to do
-	 * a random read is reasonably small, so we limit the size of
-	 * a compressed extent to 128k.
-	 */
 	total_compressed = min(total_compressed, max_uncompressed);
 	num_bytes = ALIGN(end - start + 1, blocksize);
 	num_bytes = max(blocksize,  num_bytes);
-- 
GitLab


From 069eac7850890acf0d3c21a6c8ca9f33ddb34a0d Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 19:36:54 +0100
Subject: [PATCH 321/898] btrfs: use predefined limits for calculating maximum
 number of pages for compression

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 77fb24b94a9e..11a4eeadf662 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -432,8 +432,6 @@ static noinline void compress_file_range(struct inode *inode,
 	unsigned long nr_pages;
 	unsigned long total_compressed = 0;
 	unsigned long total_in = 0;
-	unsigned long max_compressed = SZ_128K;
-	unsigned long max_uncompressed = SZ_128K;
 	int i;
 	int will_compress;
 	int compress_type = fs_info->compress_type;
@@ -446,7 +444,9 @@ static noinline void compress_file_range(struct inode *inode,
 again:
 	will_compress = 0;
 	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
-	nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_SIZE);
+	BUILD_BUG_ON((BTRFS_MAX_COMPRESSED % PAGE_SIZE) != 0);
+	nr_pages = min_t(unsigned long, nr_pages,
+			BTRFS_MAX_COMPRESSED / PAGE_SIZE);
 
 	/*
 	 * we don't want to send crud past the end of i_size through
@@ -471,7 +471,8 @@ static noinline void compress_file_range(struct inode *inode,
 	   (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
 		goto cleanup_and_bail_uncompressed;
 
-	total_compressed = min(total_compressed, max_uncompressed);
+	total_compressed = min_t(unsigned long, total_compressed,
+			BTRFS_MAX_UNCOMPRESSED);
 	num_bytes = ALIGN(end - start + 1, blocksize);
 	num_bytes = max(blocksize,  num_bytes);
 	total_in = 0;
@@ -510,7 +511,7 @@ static noinline void compress_file_range(struct inode *inode,
 					   &nr_pages,
 					   &total_in,
 					   &total_compressed,
-					   max_compressed);
+					   BTRFS_MAX_COMPRESSED);
 
 		if (!ret) {
 			unsigned long offset = total_compressed &
-- 
GitLab


From e5d74902362f1a06ea3674042d09f1af178c0a20 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 19:45:05 +0100
Subject: [PATCH 322/898] btrfs: derive maximum output size in the compression
 implementation

The value of max_out can be calculated from the parameters passed to the
compressors, which is number of pages and the page size, and we don't
have to needlessly pass it around.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 6 ++----
 fs/btrfs/compression.h | 6 ++----
 fs/btrfs/inode.c       | 3 +--
 fs/btrfs/lzo.c         | 4 ++--
 fs/btrfs/zlib.c        | 4 ++--
 5 files changed, 9 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 11dcda57e15c..c7721a6aa3bb 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -932,8 +932,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 			 u64 start, struct page **pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
-			 unsigned long *total_out,
-			 unsigned long max_out)
+			 unsigned long *total_out)
 {
 	struct list_head *workspace;
 	int ret;
@@ -943,8 +942,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
 						      start, pages,
 						      out_pages,
-						      total_in, total_out,
-						      max_out);
+						      total_in, total_out);
 	free_workspace(type, workspace);
 	return ret;
 }
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 619e64c27444..39ec43ab8df1 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -41,8 +41,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 			 u64 start, struct page **pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
-			 unsigned long *total_out,
-			 unsigned long max_out);
+			 unsigned long *total_out);
 int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 		     unsigned long start_byte, size_t srclen, size_t destlen);
 int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
@@ -76,8 +75,7 @@ struct btrfs_compress_op {
 			      struct page **pages,
 			      unsigned long *out_pages,
 			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out);
+			      unsigned long *total_out);
 
 	int (*decompress_bio)(struct list_head *workspace,
 				 struct page **pages_in,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 11a4eeadf662..0d932b9594de 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -510,8 +510,7 @@ static noinline void compress_file_range(struct inode *inode,
 					   pages,
 					   &nr_pages,
 					   &total_in,
-					   &total_compressed,
-					   BTRFS_MAX_COMPRESSED);
+					   &total_compressed);
 
 		if (!ret) {
 			unsigned long offset = total_compressed &
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 0baf978fbcaf..f48c8c14dc14 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -90,8 +90,7 @@ static int lzo_compress_pages(struct list_head *ws,
 			      struct page **pages,
 			      unsigned long *out_pages,
 			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out)
+			      unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
@@ -103,6 +102,7 @@ static int lzo_compress_pages(struct list_head *ws,
 	unsigned long bytes_left;
 	unsigned long len = *total_out;
 	unsigned long nr_dest_pages = *out_pages;
+	const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
 	size_t in_len;
 	size_t out_len;
 	char *buf;
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index e7f2020f8ee7..135b10823c6d 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -77,8 +77,7 @@ static int zlib_compress_pages(struct list_head *ws,
 			       struct page **pages,
 			       unsigned long *out_pages,
 			       unsigned long *total_in,
-			       unsigned long *total_out,
-			       unsigned long max_out)
+			       unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret;
@@ -90,6 +89,7 @@ static int zlib_compress_pages(struct list_head *ws,
 	unsigned long bytes_left;
 	unsigned long len = *total_out;
 	unsigned long nr_dest_pages = *out_pages;
+	const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
 
 	*out_pages = 0;
 	*total_out = 0;
-- 
GitLab


From 047e5e17c1e3551ef0fb34b629c66bec0591db0d Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 14 Feb 2017 17:33:27 +0100
Subject: [PATCH 323/898] btrfs: remove BUG_ON from __tree_mod_log_insert

All callers dereference the 'tm' parameter before it gets to this
function, the NULL check does not make much sense here.

Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 1192bc7d2ee7..2c3c943bfcdc 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -453,8 +453,6 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 	struct rb_node *parent = NULL;
 	struct tree_mod_elem *cur;
 
-	BUG_ON(!tm);
-
 	tm->seq = btrfs_inc_tree_mod_seq(fs_info);
 
 	tm_root = &fs_info->tree_mod_log;
-- 
GitLab


From fa2529923d3bc5f0b39ff7a7c52be74c4aea6f2a Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 15 Feb 2017 09:35:01 +0100
Subject: [PATCH 324/898] btrfs: handle allocation error in
 update_dev_stat_item

Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b443cc71830f..7c8c7bbee197 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6956,7 +6956,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
 	key.offset = device->devid;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 	ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
 	if (ret < 0) {
 		btrfs_warn_in_rcu(fs_info,
-- 
GitLab


From b9d04c607c21fafe0a346792d0d358e7ab9a768e Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 17 Feb 2017 19:42:43 +0100
Subject: [PATCH 325/898] btrfs: do proper error handling in
 btrfs_insert_xattr_item

The space check in btrfs_insert_xattr_item is duplicated in it's caller
(do_setxattr) so we won't hit the BUG_ON. Continuing without any check
could be disasterous so turn it to a proper error handling.

Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dir-item.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index b13d9536d4de..60a750678a82 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -80,7 +80,8 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	u32 data_size;
 
-	BUG_ON(name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info));
+	if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info))
+		return -ENOSPC;
 
 	key.objectid = objectid;
 	key.type = BTRFS_XATTR_ITEM_KEY;
-- 
GitLab


From c3988d630a4dfec5c09f2b6496734f320949ea9c Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 17 Feb 2017 15:18:32 +0100
Subject: [PATCH 326/898] btrfs: let writepage_end_io_hook return void

There's no error path in any of the instances, always return 0.

Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 9 +++------
 fs/btrfs/extent_io.h | 2 +-
 fs/btrfs/inode.c     | 6 ++----
 3 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c3abf846a449..94beb758e8aa 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2437,12 +2437,9 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
 
-	if (tree->ops && tree->ops->writepage_end_io_hook) {
-		ret = tree->ops->writepage_end_io_hook(page, start,
-					       end, NULL, uptodate);
-		if (ret)
-			uptodate = 0;
-	}
+	if (tree->ops && tree->ops->writepage_end_io_hook)
+		tree->ops->writepage_end_io_hook(page, start, end, NULL,
+				uptodate);
 
 	if (!uptodate) {
 		ClearPageUptodate(page);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index c16260c6c14f..78bb4d76127b 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -104,7 +104,7 @@ struct extent_io_ops {
 	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
 				    struct page *page, u64 start, u64 end,
 				    int mirror);
-	int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
+	void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
 				      struct extent_state *state, int uptodate);
 	void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
 			     unsigned *bits);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0d932b9594de..b904c74f31fd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2972,7 +2972,7 @@ static void finish_ordered_fn(struct btrfs_work *work)
 	btrfs_finish_ordered_io(ordered_extent);
 }
 
-static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
+static void btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 				struct extent_state *state, int uptodate)
 {
 	struct inode *inode = page->mapping->host;
@@ -2986,7 +2986,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	ClearPagePrivate2(page);
 	if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
 					    end - start + 1, uptodate))
-		return 0;
+		return;
 
 	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		wq = fs_info->endio_freespace_worker;
@@ -2999,8 +2999,6 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
 			NULL);
 	btrfs_queue_work(wq, &ordered_extent->work);
-
-	return 0;
 }
 
 static int __readpage_endio_check(struct inode *inode,
-- 
GitLab


From 4d53dddbec671bcb64a936a3d2b7bf1ce2252ed0 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 17 Feb 2017 15:27:44 +0100
Subject: [PATCH 327/898] btrfs: document existence of extent_io ops callbacks

Some of the callbacks defined in btree_extent_io_ops and
btrfs_extent_io_ops do always exist so we don't need to check the
existence before each call. This patch just reorders the definition and
documents which are mandatory/optional.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c   |  7 +++++--
 fs/btrfs/extent_io.h | 23 ++++++++++++++++-------
 fs/btrfs/inode.c     |  7 +++++--
 3 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 67d663ab658a..60d4f1b210d7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4653,9 +4653,12 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 }
 
 static const struct extent_io_ops btree_extent_io_ops = {
-	.readpage_end_io_hook = btree_readpage_end_io_hook,
-	.readpage_io_failed_hook = btree_io_failed_hook,
+	/* mandatory callbacks */
 	.submit_bio_hook = btree_submit_bio_hook,
+	.readpage_end_io_hook = btree_readpage_end_io_hook,
 	/* note we're sharing with inode.c for the merge bio hook */
 	.merge_bio_hook = btrfs_merge_bio_hook,
+
+	/* optional callbacks */
+	.readpage_io_failed_hook = btree_io_failed_hook,
 };
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 78bb4d76127b..1f8478dc9f8e 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -92,18 +92,27 @@ typedef	int (extent_submit_bio_hook_t)(struct inode *inode, struct bio *bio,
 				       int mirror_num, unsigned long bio_flags,
 				       u64 bio_offset);
 struct extent_io_ops {
-	int (*fill_delalloc)(struct inode *inode, struct page *locked_page,
-			     u64 start, u64 end, int *page_started,
-			     unsigned long *nr_written);
-	int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
+	/*
+	 * The following callbacks must be allways defined, the function
+	 * pointer will be called unconditionally.
+	 */
 	extent_submit_bio_hook_t *submit_bio_hook;
+	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
+				    struct page *page, u64 start, u64 end,
+				    int mirror);
 	int (*merge_bio_hook)(struct page *page, unsigned long offset,
 			      size_t size, struct bio *bio,
 			      unsigned long bio_flags);
+
+	/*
+	 * Optional hooks, called if the pointer is not NULL
+	 */
+	int (*fill_delalloc)(struct inode *inode, struct page *locked_page,
+			     u64 start, u64 end, int *page_started,
+			     unsigned long *nr_written);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
-	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
-				    struct page *page, u64 start, u64 end,
-				    int mirror);
+
+	int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
 	void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
 				      struct extent_state *state, int uptodate);
 	void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b904c74f31fd..3b327c8cfb16 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10547,10 +10547,13 @@ static const struct file_operations btrfs_dir_file_operations = {
 };
 
 static const struct extent_io_ops btrfs_extent_io_ops = {
-	.fill_delalloc = run_delalloc_range,
+	/* mandatory callbacks */
 	.submit_bio_hook = btrfs_submit_bio_hook,
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
+	.merge_bio_hook = btrfs_merge_bio_hook,
+
+	/* optional callbacks */
+	.fill_delalloc = run_delalloc_range,
 	.writepage_end_io_hook = btrfs_writepage_end_io_hook,
 	.writepage_start_hook = btrfs_writepage_start_hook,
 	.set_bit_hook = btrfs_set_bit_hook,
-- 
GitLab


From 20c9801d393d9f077c476f40440b481daaccb9d6 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 17 Feb 2017 15:59:35 +0100
Subject: [PATCH 328/898] btrfs: drop checks for mandatory extent_io_ops
 callbacks

We know that eadpage_end_io_hook, submit_bio_hook and merge_bio_hook are
always defined so we can drop the checks before we call them.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 94beb758e8aa..0786985a8cc5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2567,8 +2567,7 @@ static void end_bio_extent_readpage(struct bio *bio)
 		len = bvec->bv_len;
 
 		mirror = io_bio->mirror_num;
-		if (likely(uptodate && tree->ops &&
-			   tree->ops->readpage_end_io_hook)) {
+		if (likely(uptodate && tree->ops)) {
 			ret = tree->ops->readpage_end_io_hook(io_bio, offset,
 							      page, start, end,
 							      mirror);
@@ -2731,7 +2730,7 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 	bio->bi_private = NULL;
 	bio_get(bio);
 
-	if (tree->ops && tree->ops->submit_bio_hook)
+	if (tree->ops)
 		ret = tree->ops->submit_bio_hook(page->mapping->host, bio,
 					   mirror_num, bio_flags, start);
 	else
@@ -2746,7 +2745,7 @@ static int merge_bio(struct extent_io_tree *tree, struct page *page,
 		     unsigned long bio_flags)
 {
 	int ret = 0;
-	if (tree->ops && tree->ops->merge_bio_hook)
+	if (tree->ops)
 		ret = tree->ops->merge_bio_hook(page, offset, size, bio,
 						bio_flags);
 	return ret;
-- 
GitLab


From 20a7db8ab3f2057a518448b1728d504ffadef65e Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 17 Feb 2017 16:24:29 +0100
Subject: [PATCH 329/898] btrfs: add dummy callback for readpage_io_failed and
 drop checks

Make extent_io_ops::readpage_io_failed_hook callback mandatory and
define a dummy function for btrfs_extent_io_ops. As the failed IO
callback is not performance critical, the branch vs extra trade off does
not hurt.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c   | 2 +-
 fs/btrfs/extent_io.c | 2 +-
 fs/btrfs/extent_io.h | 2 +-
 fs/btrfs/inode.c     | 7 +++++++
 4 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 60d4f1b210d7..cad47ece2fdf 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4658,7 +4658,7 @@ static const struct extent_io_ops btree_extent_io_ops = {
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
 	/* note we're sharing with inode.c for the merge bio hook */
 	.merge_bio_hook = btrfs_merge_bio_hook,
+	.readpage_io_failed_hook = btree_io_failed_hook,
 
 	/* optional callbacks */
-	.readpage_io_failed_hook = btree_io_failed_hook,
 };
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 0786985a8cc5..28e81922a21c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2581,7 +2581,7 @@ static void end_bio_extent_readpage(struct bio *bio)
 		if (likely(uptodate))
 			goto readpage_ok;
 
-		if (tree->ops && tree->ops->readpage_io_failed_hook) {
+		if (tree->ops) {
 			ret = tree->ops->readpage_io_failed_hook(page, mirror);
 			if (!ret && !bio->bi_error)
 				uptodate = 1;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 1f8478dc9f8e..3e4fad4a909d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -103,6 +103,7 @@ struct extent_io_ops {
 	int (*merge_bio_hook)(struct page *page, unsigned long offset,
 			      size_t size, struct bio *bio,
 			      unsigned long bio_flags);
+	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
 
 	/*
 	 * Optional hooks, called if the pointer is not NULL
@@ -110,7 +111,6 @@ struct extent_io_ops {
 	int (*fill_delalloc)(struct inode *inode, struct page *locked_page,
 			     u64 start, u64 end, int *page_started,
 			     unsigned long *nr_written);
-	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
 
 	int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
 	void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3b327c8cfb16..ca1995cfd8e9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10509,6 +10509,12 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 }
 
+__attribute__((const))
+static int dummy_readpage_io_failed_hook(struct page *page, int failed_mirror)
+{
+	return 0;
+}
+
 static const struct inode_operations btrfs_dir_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.lookup		= btrfs_lookup,
@@ -10551,6 +10557,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
 	.merge_bio_hook = btrfs_merge_bio_hook,
+	.readpage_io_failed_hook = dummy_readpage_io_failed_hook,
 
 	/* optional callbacks */
 	.fill_delalloc = run_delalloc_range,
-- 
GitLab


From 2a7275a3d867b228216886aae35e1f64291180b1 Mon Sep 17 00:00:00 2001
From: Ley Foon Tan <ley.foon.tan@intel.com>
Date: Tue, 28 Feb 2017 18:37:16 +0800
Subject: [PATCH 330/898] PCI: altera: Fix TLP_CFG_DW0 for TLP write

eb5767122feb ("PCI: altera: Simplify TLB_CFG_DW0 usage") used
TLP_FMTTYPE_CFGRD* (instead of TLP_FMTTYPE_CFGWR*) for TLP writes, which
causes writing to configuration space to fail.  Fix it by using correct
FMTTYPE for write operation.

Fixes: eb5767122feb ("PCI: altera: Simplify TLB_CFG_DW0 usage")
Signed-off-by: Ley Foon Tan <ley.foon.tan@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: stable@vger.kernel.org	# v4.9+
---
 drivers/pci/host/pcie-altera.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/host/pcie-altera.c b/drivers/pci/host/pcie-altera.c
index 5043b5f00ed8..75ec5cea26f6 100644
--- a/drivers/pci/host/pcie-altera.c
+++ b/drivers/pci/host/pcie-altera.c
@@ -57,10 +57,14 @@
 #define TLP_WRITE_TAG			0x10
 #define RP_DEVFN			0
 #define TLP_REQ_ID(bus, devfn)		(((bus) << 8) | (devfn))
-#define TLP_CFG_DW0(pcie, bus)						\
+#define TLP_CFGRD_DW0(pcie, bus)					\
     ((((bus == pcie->root_bus_nr) ? TLP_FMTTYPE_CFGRD0			\
 				    : TLP_FMTTYPE_CFGRD1) << 24) |	\
      TLP_PAYLOAD_SIZE)
+#define TLP_CFGWR_DW0(pcie, bus)					\
+    ((((bus == pcie->root_bus_nr) ? TLP_FMTTYPE_CFGWR0			\
+				    : TLP_FMTTYPE_CFGWR1) << 24) |	\
+     TLP_PAYLOAD_SIZE)
 #define TLP_CFG_DW1(pcie, tag, be)	\
     (((TLP_REQ_ID(pcie->root_bus_nr,  RP_DEVFN)) << 16) | (tag << 8) | (be))
 #define TLP_CFG_DW2(bus, devfn, offset)	\
@@ -222,7 +226,7 @@ static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn,
 {
 	u32 headers[TLP_HDR_SIZE];
 
-	headers[0] = TLP_CFG_DW0(pcie, bus);
+	headers[0] = TLP_CFGRD_DW0(pcie, bus);
 	headers[1] = TLP_CFG_DW1(pcie, TLP_READ_TAG, byte_en);
 	headers[2] = TLP_CFG_DW2(bus, devfn, where);
 
@@ -237,7 +241,7 @@ static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn,
 	u32 headers[TLP_HDR_SIZE];
 	int ret;
 
-	headers[0] = TLP_CFG_DW0(pcie, bus);
+	headers[0] = TLP_CFGWR_DW0(pcie, bus);
 	headers[1] = TLP_CFG_DW1(pcie, TLP_WRITE_TAG, byte_en);
 	headers[2] = TLP_CFG_DW2(bus, devfn, where);
 
-- 
GitLab


From ad47047220777460c6d7dc8333808591f29e5c17 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Tue, 28 Feb 2017 11:55:16 -0500
Subject: [PATCH 331/898] dm raid: fix raid "check" regression due to improper
 cleanup in raid_message()

While cleaning up awkward branching in raid_message() a raid set "check"
regression was introduced because "check" needs both MD_RECOVERY_SYNC
and MD_RECOVERY_REQUESTED flags set.

Fix this regression by explicitly setting both flags for the "check"
case (like is also done for the "repair" case, but redundant set_bit()s
are perfectly fine because it adds clarity to what is needed in response
to both messages -- in addition this isn't fast path code).

Fixes: 105db59912 ("dm raid: cleanup awkward branching in raid_message() option processing")
Reported-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-raid.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5c9e95d66f3b..0460cf84fd0e 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3462,9 +3462,11 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv)
 	else if (!strcasecmp(argv[0], "recover"))
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	else {
-		if (!strcasecmp(argv[0], "check"))
+		if (!strcasecmp(argv[0], "check")) {
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-		else if (!strcasecmp(argv[0], "repair")) {
+			set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		} else if (!strcasecmp(argv[0], "repair")) {
 			set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		} else
-- 
GitLab


From d36a19541fe8f392778ac137d60f9be8dfdd8f9d Mon Sep 17 00:00:00 2001
From: Heinz Mauelshagen <heinzm@redhat.com>
Date: Tue, 28 Feb 2017 19:17:49 +0100
Subject: [PATCH 332/898] dm raid: fix data corruption on reshape request

The lvm2 sequence to manage dm-raid constructor flags that trigger a
rebuild or a reshape is defined as:

1) load table with flags (e.g. rebuild/delta_disks/data_offset)
2) clear out the flags in lvm2 metadata
3) store the lvm2 metadata, reload the table to reset the flags
   previously established during the initial load (1) -- in order to
   prevent repeatedly requesting a rebuild or a reshape on activation

Currently, loading an inactive table with rebuild/reshape flags
specified will cause dm-raid to rebuild/reshape on resume and thus start
updating the raid metadata (about the progress).  When the second table
reload, to reset the flags, occurs the constructor accesses the volatile
progress state kept in the raid superblocks.  Because the active mapping
is still processing the rebuild/reshape, that position will be stale by
the time the device is resumed.

In the reshape case, this causes data corruption by processing already
reshaped stripes again.  In the rebuild case, it does _not_ cause data
corruption but instead involves superfluous rebuilds.

Fix by keeping the raid set frozen during the first resume and then
allow the rebuild/reshape during the second resume.

Fixes: 9dbd1aa3a ("dm raid: add reshaping support to the target")
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 4.8+
---
 drivers/md/dm-raid.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 0460cf84fd0e..350527f60834 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3756,6 +3756,8 @@ static int raid_preresume(struct dm_target *ti)
 	return r;
 }
 
+#define RESUME_STAY_FROZEN_FLAGS (CTR_FLAG_DELTA_DISKS | CTR_FLAG_DATA_OFFSET)
+
 static void raid_resume(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
@@ -3773,7 +3775,15 @@ static void raid_resume(struct dm_target *ti)
 	mddev->ro = 0;
 	mddev->in_sync = 0;
 
-	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	/*
+	 * Keep the RAID set frozen if reshape/rebuild flags are set.
+	 * The RAID set is unfrozen once the next table load/resume,
+	 * which clears the reshape/rebuild flags, occurs.
+	 * This ensures that the constructor for the inactive table
+	 * retrieves an up-to-date reshape_position.
+	 */
+	if (!(rs->ctr_flags & RESUME_STAY_FROZEN_FLAGS))
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
 	if (mddev->suspended)
 		mddev_resume(mddev);
-- 
GitLab


From 2664f3c94abc7181171b7c05b2aaa76ea7d9d613 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Tue, 28 Feb 2017 15:31:44 -0500
Subject: [PATCH 333/898] dm raid: bump the target version

This version bump reflects that the reshape corruption fix (commit
92a39f6cc "dm raid: fix data corruption on reshape request") is
present.

Done as a separate fix because the above referenced commit is marked for
stable and target version bumps in a stable@ fix are a recipe for the
fix to never get backported to stable@ kernels (because of target
version number conflicts).

Also, move RESUME_STAY_FROZEN_FLAGS up with the reset the the _FLAGS
definitions now that we don't need to worry about stable@ conflicts as a
result of missing context.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-raid.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 350527f60834..f8564d63982f 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -101,6 +101,8 @@ struct raid_dev {
 #define CTR_FLAG_RAID10_USE_NEAR_SETS	(1 << __CTR_FLAG_RAID10_USE_NEAR_SETS)
 #define CTR_FLAG_JOURNAL_DEV		(1 << __CTR_FLAG_JOURNAL_DEV)
 
+#define RESUME_STAY_FROZEN_FLAGS (CTR_FLAG_DELTA_DISKS | CTR_FLAG_DATA_OFFSET)
+
 /*
  * Definitions of various constructor flags to
  * be used in checks of valid / invalid flags
@@ -3756,8 +3758,6 @@ static int raid_preresume(struct dm_target *ti)
 	return r;
 }
 
-#define RESUME_STAY_FROZEN_FLAGS (CTR_FLAG_DELTA_DISKS | CTR_FLAG_DATA_OFFSET)
-
 static void raid_resume(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
@@ -3791,7 +3791,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 10, 0},
+	.version = {1, 10, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
-- 
GitLab


From de09cdd09fa12c3f837902680c3011d96e811821 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 28 Feb 2017 16:32:44 -0500
Subject: [PATCH 334/898] intel_idle: stop exposing platform acronyms in sysfs

Cosmetic only -- no functional change in this patch.

sysfs before:

state4/desc:MWAIT 0x20
state4/name:C6-HSW

sysfs after:

state4/desc:MWAIT 0x20
state4/name:C6

We remove the platform acronyms from the end of the state name
(-HSW in this case) for three reasonse.

 1. more consistency with acpi_idle, which prints C1, C2, C3 etc.

 2. users know what platform they are on already
    an acronym for the processor code name here
    seems to cause more confusion than clarity.

 3. less clutter in "cpupower monitor" output,
    which truncates the names to 4 columns.

The precise definition of the state continues to be available in "desc".

Reported-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/idle/intel_idle.c | 172 +++++++++++++++++++-------------------
 1 file changed, 86 insertions(+), 86 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 7d8ea3d5fda6..e045a5caa5bb 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -125,7 +125,7 @@ static struct cpuidle_state *cpuidle_state_table;
  */
 static struct cpuidle_state nehalem_cstates[] = {
 	{
-		.name = "C1-NHM",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 3,
@@ -133,7 +133,7 @@ static struct cpuidle_state nehalem_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-NHM",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -141,7 +141,7 @@ static struct cpuidle_state nehalem_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-NHM",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 20,
@@ -149,7 +149,7 @@ static struct cpuidle_state nehalem_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-NHM",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 200,
@@ -162,7 +162,7 @@ static struct cpuidle_state nehalem_cstates[] = {
 
 static struct cpuidle_state snb_cstates[] = {
 	{
-		.name = "C1-SNB",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -170,7 +170,7 @@ static struct cpuidle_state snb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-SNB",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -178,7 +178,7 @@ static struct cpuidle_state snb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-SNB",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
@@ -186,7 +186,7 @@ static struct cpuidle_state snb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-SNB",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 104,
@@ -194,7 +194,7 @@ static struct cpuidle_state snb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7-SNB",
+		.name = "C7",
 		.desc = "MWAIT 0x30",
 		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 109,
@@ -207,7 +207,7 @@ static struct cpuidle_state snb_cstates[] = {
 
 static struct cpuidle_state byt_cstates[] = {
 	{
-		.name = "C1-BYT",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -215,7 +215,7 @@ static struct cpuidle_state byt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6N-BYT",
+		.name = "C6N",
 		.desc = "MWAIT 0x58",
 		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 300,
@@ -223,7 +223,7 @@ static struct cpuidle_state byt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6S-BYT",
+		.name = "C6S",
 		.desc = "MWAIT 0x52",
 		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 500,
@@ -231,7 +231,7 @@ static struct cpuidle_state byt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7-BYT",
+		.name = "C7",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 1200,
@@ -239,7 +239,7 @@ static struct cpuidle_state byt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7S-BYT",
+		.name = "C7S",
 		.desc = "MWAIT 0x64",
 		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 10000,
@@ -252,7 +252,7 @@ static struct cpuidle_state byt_cstates[] = {
 
 static struct cpuidle_state cht_cstates[] = {
 	{
-		.name = "C1-CHT",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -260,7 +260,7 @@ static struct cpuidle_state cht_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6N-CHT",
+		.name = "C6N",
 		.desc = "MWAIT 0x58",
 		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
@@ -268,7 +268,7 @@ static struct cpuidle_state cht_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6S-CHT",
+		.name = "C6S",
 		.desc = "MWAIT 0x52",
 		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 200,
@@ -276,7 +276,7 @@ static struct cpuidle_state cht_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7-CHT",
+		.name = "C7",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 1200,
@@ -284,7 +284,7 @@ static struct cpuidle_state cht_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7S-CHT",
+		.name = "C7S",
 		.desc = "MWAIT 0x64",
 		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 10000,
@@ -297,7 +297,7 @@ static struct cpuidle_state cht_cstates[] = {
 
 static struct cpuidle_state ivb_cstates[] = {
 	{
-		.name = "C1-IVB",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -305,7 +305,7 @@ static struct cpuidle_state ivb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-IVB",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -313,7 +313,7 @@ static struct cpuidle_state ivb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-IVB",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
@@ -321,7 +321,7 @@ static struct cpuidle_state ivb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-IVB",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
@@ -329,7 +329,7 @@ static struct cpuidle_state ivb_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7-IVB",
+		.name = "C7",
 		.desc = "MWAIT 0x30",
 		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 87,
@@ -342,7 +342,7 @@ static struct cpuidle_state ivb_cstates[] = {
 
 static struct cpuidle_state ivt_cstates[] = {
 	{
-		.name = "C1-IVT",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -350,7 +350,7 @@ static struct cpuidle_state ivt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-IVT",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -358,7 +358,7 @@ static struct cpuidle_state ivt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-IVT",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
@@ -366,7 +366,7 @@ static struct cpuidle_state ivt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-IVT",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 82,
@@ -379,7 +379,7 @@ static struct cpuidle_state ivt_cstates[] = {
 
 static struct cpuidle_state ivt_cstates_4s[] = {
 	{
-		.name = "C1-IVT-4S",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -387,7 +387,7 @@ static struct cpuidle_state ivt_cstates_4s[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-IVT-4S",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -395,7 +395,7 @@ static struct cpuidle_state ivt_cstates_4s[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-IVT-4S",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
@@ -403,7 +403,7 @@ static struct cpuidle_state ivt_cstates_4s[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-IVT-4S",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 84,
@@ -416,7 +416,7 @@ static struct cpuidle_state ivt_cstates_4s[] = {
 
 static struct cpuidle_state ivt_cstates_8s[] = {
 	{
-		.name = "C1-IVT-8S",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -424,7 +424,7 @@ static struct cpuidle_state ivt_cstates_8s[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-IVT-8S",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -432,7 +432,7 @@ static struct cpuidle_state ivt_cstates_8s[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-IVT-8S",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
@@ -440,7 +440,7 @@ static struct cpuidle_state ivt_cstates_8s[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-IVT-8S",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 88,
@@ -453,7 +453,7 @@ static struct cpuidle_state ivt_cstates_8s[] = {
 
 static struct cpuidle_state hsw_cstates[] = {
 	{
-		.name = "C1-HSW",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -461,7 +461,7 @@ static struct cpuidle_state hsw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-HSW",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -469,7 +469,7 @@ static struct cpuidle_state hsw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-HSW",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 33,
@@ -477,7 +477,7 @@ static struct cpuidle_state hsw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-HSW",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 133,
@@ -485,7 +485,7 @@ static struct cpuidle_state hsw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7s-HSW",
+		.name = "C7s",
 		.desc = "MWAIT 0x32",
 		.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 166,
@@ -493,7 +493,7 @@ static struct cpuidle_state hsw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C8-HSW",
+		.name = "C8",
 		.desc = "MWAIT 0x40",
 		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 300,
@@ -501,7 +501,7 @@ static struct cpuidle_state hsw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C9-HSW",
+		.name = "C9",
 		.desc = "MWAIT 0x50",
 		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 600,
@@ -509,7 +509,7 @@ static struct cpuidle_state hsw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C10-HSW",
+		.name = "C10",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 2600,
@@ -521,7 +521,7 @@ static struct cpuidle_state hsw_cstates[] = {
 };
 static struct cpuidle_state bdw_cstates[] = {
 	{
-		.name = "C1-BDW",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -529,7 +529,7 @@ static struct cpuidle_state bdw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-BDW",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -537,7 +537,7 @@ static struct cpuidle_state bdw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-BDW",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 40,
@@ -545,7 +545,7 @@ static struct cpuidle_state bdw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-BDW",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 133,
@@ -553,7 +553,7 @@ static struct cpuidle_state bdw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7s-BDW",
+		.name = "C7s",
 		.desc = "MWAIT 0x32",
 		.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 166,
@@ -561,7 +561,7 @@ static struct cpuidle_state bdw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C8-BDW",
+		.name = "C8",
 		.desc = "MWAIT 0x40",
 		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 300,
@@ -569,7 +569,7 @@ static struct cpuidle_state bdw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C9-BDW",
+		.name = "C9",
 		.desc = "MWAIT 0x50",
 		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 600,
@@ -577,7 +577,7 @@ static struct cpuidle_state bdw_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C10-BDW",
+		.name = "C10",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 2600,
@@ -590,7 +590,7 @@ static struct cpuidle_state bdw_cstates[] = {
 
 static struct cpuidle_state skl_cstates[] = {
 	{
-		.name = "C1-SKL",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -598,7 +598,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-SKL",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -606,7 +606,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C3-SKL",
+		.name = "C3",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 70,
@@ -614,7 +614,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-SKL",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 85,
@@ -622,7 +622,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7s-SKL",
+		.name = "C7s",
 		.desc = "MWAIT 0x33",
 		.flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 124,
@@ -630,7 +630,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C8-SKL",
+		.name = "C8",
 		.desc = "MWAIT 0x40",
 		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 200,
@@ -638,7 +638,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C9-SKL",
+		.name = "C9",
 		.desc = "MWAIT 0x50",
 		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 480,
@@ -646,7 +646,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C10-SKL",
+		.name = "C10",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 890,
@@ -659,7 +659,7 @@ static struct cpuidle_state skl_cstates[] = {
 
 static struct cpuidle_state skx_cstates[] = {
 	{
-		.name = "C1-SKX",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -667,7 +667,7 @@ static struct cpuidle_state skx_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-SKX",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -675,7 +675,7 @@ static struct cpuidle_state skx_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-SKX",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 133,
@@ -688,7 +688,7 @@ static struct cpuidle_state skx_cstates[] = {
 
 static struct cpuidle_state atom_cstates[] = {
 	{
-		.name = "C1E-ATM",
+		.name = "C1E",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 10,
@@ -696,7 +696,7 @@ static struct cpuidle_state atom_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C2-ATM",
+		.name = "C2",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10),
 		.exit_latency = 20,
@@ -704,7 +704,7 @@ static struct cpuidle_state atom_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C4-ATM",
+		.name = "C4",
 		.desc = "MWAIT 0x30",
 		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 100,
@@ -712,7 +712,7 @@ static struct cpuidle_state atom_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-ATM",
+		.name = "C6",
 		.desc = "MWAIT 0x52",
 		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 140,
@@ -724,7 +724,7 @@ static struct cpuidle_state atom_cstates[] = {
 };
 static struct cpuidle_state tangier_cstates[] = {
 	{
-		.name = "C1-TNG",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -732,7 +732,7 @@ static struct cpuidle_state tangier_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C4-TNG",
+		.name = "C4",
 		.desc = "MWAIT 0x30",
 		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 100,
@@ -740,7 +740,7 @@ static struct cpuidle_state tangier_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-TNG",
+		.name = "C6",
 		.desc = "MWAIT 0x52",
 		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 140,
@@ -748,7 +748,7 @@ static struct cpuidle_state tangier_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7-TNG",
+		.name = "C7",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 1200,
@@ -756,7 +756,7 @@ static struct cpuidle_state tangier_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C9-TNG",
+		.name = "C9",
 		.desc = "MWAIT 0x64",
 		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 10000,
@@ -768,7 +768,7 @@ static struct cpuidle_state tangier_cstates[] = {
 };
 static struct cpuidle_state avn_cstates[] = {
 	{
-		.name = "C1-AVN",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -776,7 +776,7 @@ static struct cpuidle_state avn_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-AVN",
+		.name = "C6",
 		.desc = "MWAIT 0x51",
 		.flags = MWAIT2flg(0x51) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 15,
@@ -788,7 +788,7 @@ static struct cpuidle_state avn_cstates[] = {
 };
 static struct cpuidle_state knl_cstates[] = {
 	{
-		.name = "C1-KNL",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
@@ -796,7 +796,7 @@ static struct cpuidle_state knl_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze },
 	{
-		.name = "C6-KNL",
+		.name = "C6",
 		.desc = "MWAIT 0x10",
 		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 120,
@@ -809,7 +809,7 @@ static struct cpuidle_state knl_cstates[] = {
 
 static struct cpuidle_state bxt_cstates[] = {
 	{
-		.name = "C1-BXT",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -817,7 +817,7 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-BXT",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -825,7 +825,7 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-BXT",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 133,
@@ -833,7 +833,7 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C7s-BXT",
+		.name = "C7s",
 		.desc = "MWAIT 0x31",
 		.flags = MWAIT2flg(0x31) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 155,
@@ -841,7 +841,7 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C8-BXT",
+		.name = "C8",
 		.desc = "MWAIT 0x40",
 		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 1000,
@@ -849,7 +849,7 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C9-BXT",
+		.name = "C9",
 		.desc = "MWAIT 0x50",
 		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 2000,
@@ -857,7 +857,7 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C10-BXT",
+		.name = "C10",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 10000,
@@ -870,7 +870,7 @@ static struct cpuidle_state bxt_cstates[] = {
 
 static struct cpuidle_state dnv_cstates[] = {
 	{
-		.name = "C1-DNV",
+		.name = "C1",
 		.desc = "MWAIT 0x00",
 		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
@@ -878,7 +878,7 @@ static struct cpuidle_state dnv_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C1E-DNV",
+		.name = "C1E",
 		.desc = "MWAIT 0x01",
 		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
@@ -886,7 +886,7 @@ static struct cpuidle_state dnv_cstates[] = {
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
-		.name = "C6-DNV",
+		.name = "C6",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 50,
-- 
GitLab


From 70cd4c10b290dd77fff6dc702a9a2c8c679df121 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@ozlabs.org>
Date: Mon, 27 Feb 2017 11:51:37 +1100
Subject: [PATCH 335/898] KVM: PPC: Book3S HV: Fix software walk of guest
 process page tables

This fixes some bugs in the code that walks the guest's page tables.
These bugs cause MMIO emulation to fail whenever the guest is in
virtial mode (MMU on), leading to the guest hanging if it tried to
access a virtio device.

The first bug was that when reading the guest's process table, we were
using the whole of arch->process_table, not just the field that contains
the process table base address.  The second bug was that the mask used
when reading the process table entry to get the radix tree base address,
RPDB_MASK, had the wrong value.

Fixes: 9e04ba69beec ("KVM: PPC: Book3S HV: Add basic infrastructure for radix guests")
Fixes: e99833448c5f ("powerpc/mm/radix: Add partition table format & callback")
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/include/asm/book3s/64/mmu.h | 3 ++-
 arch/powerpc/kvm/book3s_64_mmu_radix.c   | 5 +++--
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index d73e9dfa5237..440f3423e213 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -46,7 +46,7 @@ extern struct patb_entry *partition_tb;
 
 /* Bits in patb0 field */
 #define PATB_HR		(1UL << 63)
-#define RPDB_MASK	0x0ffffffffffff00fUL
+#define RPDB_MASK	0x0fffffffffffff00UL
 #define RPDB_SHIFT	(1UL << 8)
 #define RTS1_SHIFT	61		/* top 2 bits of radix tree size */
 #define RTS1_MASK	(3UL << RTS1_SHIFT)
@@ -57,6 +57,7 @@ extern struct patb_entry *partition_tb;
 /* Bits in patb1 field */
 #define PATB_GR		(1UL << 63)	/* guest uses radix; must match HR */
 #define PRTS_MASK	0x1f		/* process table size field */
+#define PRTB_MASK	0x0ffffffffffff000UL
 
 /*
  * Limit process table to PAGE_SIZE table. This
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 4344651f408c..f6b3e67c5762 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -32,6 +32,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u32 pid;
 	int ret, level, ps;
 	__be64 prte, rpte;
+	unsigned long ptbl;
 	unsigned long root, pte, index;
 	unsigned long rts, bits, offset;
 	unsigned long gpa;
@@ -53,8 +54,8 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		return -EINVAL;
 
 	/* Read partition table to find root of tree for effective PID */
-	ret = kvm_read_guest(kvm, kvm->arch.process_table + pid * 16,
-			     &prte, sizeof(prte));
+	ptbl = (kvm->arch.process_table & PRTB_MASK) + (pid * 16);
+	ret = kvm_read_guest(kvm, ptbl, &prte, sizeof(prte));
 	if (ret)
 		return ret;
 
-- 
GitLab


From 4e5acdc23a3dcbd6ad6dc93a9783dd9c838987c8 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@ozlabs.org>
Date: Tue, 28 Feb 2017 11:05:47 +1100
Subject: [PATCH 336/898] KVM: PPC: Book3S HV: Don't use ASDR for real-mode HPT
 faults on POWER9

In HPT mode on POWER9, the ASDR register is supposed to record
segment information for hypervisor page faults.  It turns out that
POWER9 DD1 does not record the page size information in the ASDR
for faults in guest real mode.  We have the necessary information
in memory already, so by moving the checks for real mode that already
existed, we can use the in-memory copy.  Since a load is likely to
be faster than reading an SPR, we do this unconditionally (not just
for POWER9 DD1).

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 47414a6fe2dd..7c6477d1840a 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1787,12 +1787,12 @@ kvmppc_hdsi:
 	/* HPTE not found fault or protection fault? */
 	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
 	beq	1f			/* if not, send it to the guest */
+	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
+	beq	3f
 BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
 	b	4f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
-	beq	3f
 	clrrdi	r0, r4, 28
 	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	li	r0, BOOK3S_INTERRUPT_DATA_SEGMENT
@@ -1879,12 +1879,12 @@ kvmppc_hisi:
 	bne	.Lradix_hisi		/* for radix, just save ASDR */
 	andis.	r0, r11, SRR1_ISI_NOPT@h
 	beq	1f
+	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
+	beq	3f
 BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
 	b	4f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
-	beq	3f
 	clrrdi	r0, r10, 28
 	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	li	r0, BOOK3S_INTERRUPT_INST_SEGMENT
-- 
GitLab


From 0aa5277c3a6dbe9d5991c490ef23fe900254d931 Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Tue, 28 Feb 2017 15:39:25 +0800
Subject: [PATCH 337/898] drm/i915/gvt: have more registers with F_CMD_ACCESS
 flags set

those registers are render registers, should have F_CMD_ACCESS flag set

v4:
rebase to lastest code base

v3:
per zhenyu's comments, move newly added registers to a separate patch

v2:
per Kevin's comments, move newly added registers to the tails of lists.

Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 223 +++++++++++++++-------------
 1 file changed, 123 insertions(+), 100 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 57b4d538f370..37956eee342c 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1523,6 +1523,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
 #define MMIO_GM(reg, d, r, w) \
 	MMIO_F(reg, 4, F_GMADR, 0xFFFFF000, 0, d, r, w)
 
+#define MMIO_GM_RDR(reg, d, r, w) \
+	MMIO_F(reg, 4, F_GMADR | F_CMD_ACCESS, 0xFFFFF000, 0, d, r, w)
+
 #define MMIO_RO(reg, d, f, rm, r, w) \
 	MMIO_F(reg, 4, F_RO | f, 0, rm, d, r, w)
 
@@ -1542,6 +1545,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
 #define MMIO_RING_GM(prefix, d, r, w) \
 	MMIO_RING_F(prefix, 4, F_GMADR, 0xFFFF0000, 0, d, r, w)
 
+#define MMIO_RING_GM_RDR(prefix, d, r, w) \
+	MMIO_RING_F(prefix, 4, F_GMADR | F_CMD_ACCESS, 0xFFFF0000, 0, d, r, w)
+
 #define MMIO_RING_RO(prefix, d, f, rm, r, w) \
 	MMIO_RING_F(prefix, 4, F_RO | f, 0, rm, d, r, w)
 
@@ -1550,45 +1556,48 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	int ret;
 
-	MMIO_RING_DFH(RING_IMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler);
+	MMIO_RING_DFH(RING_IMR, D_ALL, F_CMD_ACCESS, NULL,
+		intel_vgpu_reg_imr_handler);
 
 	MMIO_DFH(SDEIMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler);
 	MMIO_DFH(SDEIER, D_ALL, 0, NULL, intel_vgpu_reg_ier_handler);
 	MMIO_DFH(SDEIIR, D_ALL, 0, NULL, intel_vgpu_reg_iir_handler);
 	MMIO_D(SDEISR, D_ALL);
 
-	MMIO_RING_D(RING_HWSTAM, D_ALL);
+	MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_GM(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
-	MMIO_GM(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
-	MMIO_GM(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
-	MMIO_GM(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 
 #define RING_REG(base) (base + 0x28)
-	MMIO_RING_D(RING_REG, D_ALL);
+	MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x134)
-	MMIO_RING_D(RING_REG, D_ALL);
+	MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL);
 #undef RING_REG
 
-	MMIO_GM(0x2148, D_ALL, NULL, NULL);
-	MMIO_GM(CCID, D_ALL, NULL, NULL);
-	MMIO_GM(0x12198, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(0x2148, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(CCID, D_ALL, NULL, NULL);
+	MMIO_GM_RDR(0x12198, D_ALL, NULL, NULL);
 	MMIO_D(GEN7_CXT_SIZE, D_ALL);
 
-	MMIO_RING_D(RING_TAIL, D_ALL);
-	MMIO_RING_D(RING_HEAD, D_ALL);
-	MMIO_RING_D(RING_CTL, D_ALL);
-	MMIO_RING_D(RING_ACTHD, D_ALL);
-	MMIO_RING_GM(RING_START, D_ALL, NULL, NULL);
+	MMIO_RING_DFH(RING_TAIL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_HEAD, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_CTL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_GM_RDR(RING_START, D_ALL, NULL, NULL);
 
 	/* RING MODE */
 #define RING_REG(base) (base + 0x29c)
-	MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK, NULL, ring_mode_mmio_write);
+	MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL,
+		ring_mode_mmio_write);
 #undef RING_REG
 
-	MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 	MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
 			NULL, NULL);
 	MMIO_RING_DFH(RING_TIMESTAMP, D_ALL, F_CMD_ACCESS,
@@ -1596,28 +1605,30 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_RING_DFH(RING_TIMESTAMP_UDW, D_ALL, F_CMD_ACCESS,
 			ring_timestamp_mmio_read, NULL);
 
-	MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 	MMIO_DFH(CACHE_MODE_1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(CACHE_MODE_0, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(0x2124, D_ALL, F_MODE_MASK, NULL, NULL);
-
-	MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(0x2088, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(0x2470, D_ALL, F_MODE_MASK, NULL, NULL);
-	MMIO_D(GAM_ECOCHK, D_ALL);
-	MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(CACHE_MODE_0, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2124, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2088, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2470, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GAM_ECOCHK, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 	MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(0x9030, D_ALL);
-	MMIO_D(0x20a0, D_ALL);
-	MMIO_D(0x2420, D_ALL);
-	MMIO_D(0x2430, D_ALL);
-	MMIO_D(0x2434, D_ALL);
-	MMIO_D(0x2438, D_ALL);
-	MMIO_D(0x243c, D_ALL);
-	MMIO_DFH(0x7018, D_ALL, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(0x9030, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x20a0, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2420, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2430, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2434, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2438, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x243c, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x7018, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(GEN7_HALF_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
@@ -2148,8 +2159,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(FORCEWAKE_ACK, D_ALL);
 	MMIO_D(GEN6_GT_CORE_STATUS, D_ALL);
 	MMIO_D(GEN6_GT_THREAD_STATUS_REG, D_ALL);
-	MMIO_D(GTFIFODBG, D_ALL);
-	MMIO_D(GTFIFOCTL, D_ALL);
+	MMIO_DFH(GTFIFODBG, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GTFIFOCTL, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DH(FORCEWAKE_MT, D_PRE_SKL, NULL, mul_force_wake_write);
 	MMIO_DH(FORCEWAKE_ACK_HSW, D_HSW | D_BDW, NULL, NULL);
 	MMIO_D(ECOBUS, D_ALL);
@@ -2291,29 +2302,29 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(0x12178, D_ALL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x1217c, D_ALL, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_F(0x2290, 8, 0, 0, 0, D_HSW_PLUS, NULL, NULL);
-	MMIO_D(GEN7_OACONTROL, D_HSW);
+	MMIO_F(0x2290, 8, F_CMD_ACCESS, 0, 0, D_HSW_PLUS, NULL, NULL);
+	MMIO_DFH(GEN7_OACONTROL, D_HSW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(0x2b00, D_BDW_PLUS);
 	MMIO_D(0x2360, D_BDW_PLUS);
-	MMIO_F(0x5200, 32, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(0x5240, 32, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(0x5280, 16, 0, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(0x5200, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(0x5240, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(0x5280, 16, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
 
 	MMIO_DFH(0x1c17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0x1c178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(BCS_SWCTRL, D_ALL);
-
-	MMIO_F(HS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(DS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(IA_VERTICES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(IA_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(VS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(GS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(GS_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(CL_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(CL_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(PS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
-	MMIO_F(PS_DEPTH_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
+	MMIO_DFH(BCS_SWCTRL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_F(HS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(DS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(IA_VERTICES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(IA_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(VS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(GS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(GS_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(CL_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(CL_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(PS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+	MMIO_F(PS_DEPTH_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
 	MMIO_DH(0x4260, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
 	MMIO_DH(0x4264, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
 	MMIO_DH(0x4268, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
@@ -2329,7 +2340,7 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	int ret;
 
-	MMIO_DH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL,
+	MMIO_DFH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, NULL,
 			intel_vgpu_reg_imr_handler);
 
 	MMIO_DH(GEN8_GT_IMR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_imr_handler);
@@ -2394,24 +2405,31 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(GEN8_MASTER_IRQ, D_BDW_PLUS, NULL,
 		intel_vgpu_reg_master_irq_handler);
 
-	MMIO_D(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(0x1c134, D_BDW_PLUS);
-
-	MMIO_D(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(RING_HEAD(GEN8_BSD2_RING_BASE),  D_BDW_PLUS);
-	MMIO_GM(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
-	MMIO_D(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_D(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
-	MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK, NULL, ring_mode_mmio_write);
-	MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK,
-			NULL, NULL);
-	MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK,
-			NULL, NULL);
+	MMIO_DFH(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1c134, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_DFH(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(RING_HEAD(GEN8_BSD2_RING_BASE),  D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_GM_RDR(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
+	MMIO_DFH(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL,
+		ring_mode_mmio_write);
+	MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+		F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(RING_TIMESTAMP(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
 			ring_timestamp_mmio_read, NULL);
 
-	MMIO_RING_D(RING_ACTHD_UDW, D_BDW_PLUS);
+	MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 
 #define RING_REG(base) (base + 0xd0)
 	MMIO_RING_F(RING_REG, 4, F_RO, 0,
@@ -2428,13 +2446,16 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x234)
-	MMIO_RING_F(RING_REG, 8, F_RO, 0, ~0, D_BDW_PLUS, NULL, NULL);
-	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO, 0, ~0LL, D_BDW_PLUS, NULL, NULL);
+	MMIO_RING_F(RING_REG, 8, F_RO | F_CMD_ACCESS, 0, ~0, D_BDW_PLUS,
+		NULL, NULL);
+	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO | F_CMD_ACCESS, 0,
+		~0LL, D_BDW_PLUS, NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x244)
-	MMIO_RING_D(RING_REG, D_BDW_PLUS);
-	MMIO_D(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
+	MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+		NULL, NULL);
 #undef RING_REG
 
 #define RING_REG(base) (base + 0x370)
@@ -2468,8 +2489,8 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL);
 #undef RING_REG
 
-	MMIO_RING_GM(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL);
-	MMIO_GM(0x1c080, D_BDW_PLUS, NULL, NULL);
+	MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL);
+	MMIO_GM_RDR(RING_HWS_PGA(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
 
 	MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
@@ -2490,15 +2511,17 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(GEN8_EU_DISABLE2, D_BDW_PLUS);
 
 	MMIO_D(0xfdc, D_BDW_PLUS);
-	MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(GEN7_ROW_CHICKEN2, D_BDW_PLUS);
-	MMIO_D(GEN8_UCGCTL6, D_BDW_PLUS);
+	MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(GEN7_ROW_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
+	MMIO_DFH(GEN8_UCGCTL6, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_D(0xb1f0, D_BDW);
-	MMIO_D(0xb1c0, D_BDW);
+	MMIO_DFH(0xb1f0, D_BDW, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xb1c0, D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(GEN8_L3SQCREG4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(0xb100, D_BDW);
-	MMIO_D(0xb10c, D_BDW);
+	MMIO_DFH(0xb100, D_BDW, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xb10c, D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(0xb110, D_BDW);
 
 	MMIO_F(0x24d0, 48, F_CMD_ACCESS, 0, 0, D_BDW_PLUS,
@@ -2508,10 +2531,10 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x44484, D_BDW_PLUS);
 	MMIO_D(0x4448c, D_BDW_PLUS);
 
-	MMIO_D(0x83a4, D_BDW);
+	MMIO_DFH(0x83a4, D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(GEN8_L3_LRA_1_GPGPU, D_BDW_PLUS);
 
-	MMIO_D(0x8430, D_BDW);
+	MMIO_DFH(0x8430, D_BDW, F_CMD_ACCESS, NULL, NULL);
 
 	MMIO_D(0x110000, D_BDW_PLUS);
 
@@ -2523,9 +2546,9 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(0xe188, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(HALF_SLICE_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK, NULL, NULL);
+	MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_D(0x2248, D_BDW);
+	MMIO_DFH(0x2248, D_BDW, F_CMD_ACCESS, NULL, NULL);
 
 	return 0;
 }
@@ -2707,15 +2730,15 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_D(0xd08, D_SKL);
 	MMIO_D(0x20e0, D_SKL);
-	MMIO_D(0x20ec, D_SKL);
+	MMIO_DFH(0x20ec, D_SKL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
 	/* TRTT */
-	MMIO_D(0x4de0, D_SKL);
-	MMIO_D(0x4de4, D_SKL);
-	MMIO_D(0x4de8, D_SKL);
-	MMIO_D(0x4dec, D_SKL);
-	MMIO_D(0x4df0, D_SKL);
-	MMIO_DH(0x4df4, D_SKL, NULL, gen9_trtte_write);
+	MMIO_DFH(0x4de0, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4de4, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4de8, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4dec, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4df0, D_SKL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x4df4, D_SKL, F_CMD_ACCESS, NULL, gen9_trtte_write);
 	MMIO_DH(0x4dfc, D_SKL, NULL, gen9_trtt_chicken_write);
 
 	MMIO_D(0x45008, D_SKL);
@@ -2739,7 +2762,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(0x65f08, D_SKL);
 	MMIO_D(0x320f0, D_SKL);
 
-	MMIO_D(_REG_VCS2_EXCC, D_SKL);
+	MMIO_DFH(_REG_VCS2_EXCC, D_SKL, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(0x70034, D_SKL);
 	MMIO_D(0x71034, D_SKL);
 	MMIO_D(0x72034, D_SKL);
@@ -2752,7 +2775,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_PLANE_KEYMSK_1(PIPE_C), D_SKL);
 
 	MMIO_D(0x44500, D_SKL);
-	MMIO_D(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS);
+	MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
 	return 0;
 }
 
-- 
GitLab


From 9112caafdf01439a6e43f4d8c09ceed7dc613d4a Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Tue, 28 Feb 2017 15:40:10 +0800
Subject: [PATCH 338/898] drm/i915/gvt: add more registers into handlers list

those registers are render registers with F_CMD_ACCESS flag set

Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 37956eee342c..ef17c38e00c4 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2332,6 +2332,17 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(0x4270, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
 	MMIO_DFH(0x4094, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 
+	MMIO_DFH(ARB_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_GM_RDR(RING_BBADDR, D_ALL, NULL, NULL);
+	MMIO_DFH(0x2220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x12220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x22220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_SYNC_1, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_RING_DFH(RING_SYNC_0, D_ALL, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x22178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1a178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x1a17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0x2217c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	return 0;
 }
 
@@ -2550,6 +2561,15 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_DFH(0x2248, D_BDW, F_CMD_ACCESS, NULL, NULL);
 
+	MMIO_DFH(0xe220, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe230, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe240, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe260, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe270, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe280, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe2a0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe2b0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(0xe2c0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	return 0;
 }
 
@@ -2776,6 +2796,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_D(0x44500, D_SKL);
 	MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 	return 0;
 }
 
-- 
GitLab


From 1f58af304cce9e4a25b62b3619e69c586203c8ca Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Tue, 28 Feb 2017 15:41:03 +0800
Subject: [PATCH 339/898] drm/i915/gvt: fix an error for one register

register 0x20e0 should be mode register

v2: rebased to latest code base

Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index ef17c38e00c4..548aedfbd402 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2749,7 +2749,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_F(0xb020, 0x80, F_CMD_ACCESS, 0, 0, D_SKL, NULL, NULL);
 
 	MMIO_D(0xd08, D_SKL);
-	MMIO_D(0x20e0, D_SKL);
+	MMIO_DFH(0x20e0, D_SKL, F_MODE_MASK, NULL, NULL);
 	MMIO_DFH(0x20ec, D_SKL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
 
 	/* TRTT */
-- 
GitLab


From 858b0f571d30916bd69c45922045f24f26d6bfc9 Mon Sep 17 00:00:00 2001
From: Bing Niu <bing.niu@intel.com>
Date: Tue, 28 Feb 2017 11:39:48 -0500
Subject: [PATCH 340/898] drm/i915/gvt: set SFUSE_STRAP properly for vitual
 monitor detection

update the correct virtual montior connection status to vreg

v2: address yulei's comment on commit message

Signed-off-by: Bing Niu <bing.niu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/display.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 43e02e038375..5419ae6ec633 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -176,14 +176,20 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 		vgpu_vreg(vgpu, SDEISR) &= ~(SDE_PORTA_HOTPLUG_SPT |
 				SDE_PORTE_HOTPLUG_SPT);
 
-	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B))
+	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
 		vgpu_vreg(vgpu, SDEISR) |= SDE_PORTB_HOTPLUG_CPT;
+		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
+	}
 
-	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C))
+	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
 		vgpu_vreg(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT;
+		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIC_DETECTED;
+	}
 
-	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D))
+	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) {
 		vgpu_vreg(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT;
+		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED;
+	}
 
 	if (IS_SKYLAKE(dev_priv) &&
 			intel_vgpu_has_monitor_on_port(vgpu, PORT_E)) {
@@ -196,6 +202,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				GEN8_PORT_DP_A_HOTPLUG;
 		else
 			vgpu_vreg(vgpu, SDEISR) |= SDE_PORTA_HOTPLUG_SPT;
+
+		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_A)) |= DDI_INIT_DISPLAY_DETECTED;
 	}
 }
 
-- 
GitLab


From 40496c8ee73a5ca4fa581badf2247418980586b1 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Jan 2017 23:21:18 -0500
Subject: [PATCH 341/898] x86: msr-index.h: Define MSR_PKG_CST_CONFIG_CONTROL

define MSR_PKG_CST_CONFIG_CONTROL (0xE2),
which is the string used by Intel Documentation.

We use this MSR in intel_idle and turbostat by a previous name,
to be updated in the next patch.

Cc: x86@kernel.org
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/include/asm/msr-index.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 710273c617b8..975f23eefe14 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -47,6 +47,7 @@
 #define MSR_PLATFORM_INFO		0x000000ce
 
 #define MSR_NHM_SNB_PKG_CST_CFG_CTL	0x000000e2
+#define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)
 #define ATM_LNC_C6_AUTO_DEMOTE		(1UL << 25)
-- 
GitLab


From 6cfb2374f83bc70b8acb0ddb989988ba3f140b61 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Jan 2017 23:23:25 -0500
Subject: [PATCH 342/898] intel_idle: use new name for
 MSR_PKG_CST_CONFIG_CONTROL

previously known as  MSR_NHM_SNB_PKG_CST_CFG_CTL

Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/idle/intel_idle.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 7d8ea3d5fda6..930537da76d4 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -961,9 +961,9 @@ static void auto_demotion_disable(void)
 {
 	unsigned long long msr_bits;
 
-	rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
+	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits);
 	msr_bits &= ~(icpu->auto_demotion_disable_flags);
-	wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
+	wrmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits);
 }
 static void c1e_promotion_disable(void)
 {
@@ -1273,7 +1273,7 @@ static void sklh_idle_state_table_update(void)
 	if ((mwait_substates & (0xF << 28)) == 0)
 		return;
 
-	rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr);
+	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr);
 
 	/* PC10 is not enabled in PKG C-state limit */
 	if ((msr & 0xF) != 8)
-- 
GitLab


From 1df2e55abce64e2f3117fac3968a9ac382fbc9c3 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Jan 2017 23:24:57 -0500
Subject: [PATCH 343/898] tools/power turbostat: use new name for
 MSR_PKG_CST_CONFIG_CONTROL

Previously called MSR_NHM_SNB_PKG_CST_CFG_CTL

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index aedfaddbad30..d56f2b75dc58 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1761,12 +1761,12 @@ dump_nhm_cst_cfg(void)
 {
 	unsigned long long msr;
 
-	get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
 
 #define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
 
-	fprintf(outf, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr);
 
 	fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
 		(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
@@ -2383,7 +2383,7 @@ void check_permissions()
  * MSR_SMI_COUNT                   0x00000034
  *
  * MSR_PLATFORM_INFO               0x000000ce
- * MSR_NHM_SNB_PKG_CST_CFG_CTL     0x000000e2
+ * MSR_PKG_CST_CONFIG_CONTROL     0x000000e2
  *
  * MSR_MISC_PWR_MGMT               0x000001aa
  *
@@ -2393,7 +2393,7 @@ void check_permissions()
  * MSR_CORE_C6_RESIDENCY           0x000003fd
  *
  * Side effect:
- * sets global pkg_cstate_limit to decode MSR_NHM_SNB_PKG_CST_CFG_CTL
+ * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL
  */
 int probe_nhm_msrs(unsigned int family, unsigned int model)
 {
@@ -2462,7 +2462,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	default:
 		return 0;
 	}
-	get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
 	pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
 
 	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
-- 
GitLab


From 419c9e986ea453d07140bffb9708d730b6317e8e Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Jan 2017 23:26:22 -0500
Subject: [PATCH 344/898] x86: msr-index.h: Remove unused
 MSR_NHM_SNB_PKG_CST_CFG_CTL

The two users, intel_idle driver and turbostat utility
are using the new name, MSR_PKG_CST_CONFIG_CONTROL

Cc: x86@kernel.org
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/include/asm/msr-index.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 975f23eefe14..12ecc6c1e7f8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -46,7 +46,6 @@
 #define MSR_FSB_FREQ			0x000000cd
 #define MSR_PLATFORM_INFO		0x000000ce
 
-#define MSR_NHM_SNB_PKG_CST_CFG_CTL	0x000000e2
 #define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)
-- 
GitLab


From 0539ba118fe241b0d03202fda0cd19cb758b7fbd Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 10 Feb 2017 00:27:20 -0500
Subject: [PATCH 345/898] tools/power turbostat: Baytrail c-state support

The Baytrail SOC, with its Silvermont core, has some unique properties:

1. a hardware CC1 residency counter
2. a module-c6 residency counter
3. a package-c6 counter at traditional package-c7 counter address.

The SOC does not support c3, pc3, c7 or pc7 counters.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/include/asm/msr-index.h      |  2 ++
 tools/power/x86/turbostat/turbostat.c | 46 +++++++++++++++++++++------
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 12ecc6c1e7f8..079db99f6560 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -147,6 +147,7 @@
 /* C-state Residency Counters */
 #define MSR_PKG_C3_RESIDENCY		0x000003f8
 #define MSR_PKG_C6_RESIDENCY		0x000003f9
+#define MSR_ATOM_PKG_C6_RESIDENCY	0x000003fa
 #define MSR_PKG_C7_RESIDENCY		0x000003fa
 #define MSR_CORE_C3_RESIDENCY		0x000003fc
 #define MSR_CORE_C6_RESIDENCY		0x000003fd
@@ -203,6 +204,7 @@
 #define MSR_PKG_BOTH_CORE_GFXE_C0_RES	0x0000065B
 
 #define MSR_CORE_C1_RES			0x00000660
+#define MSR_MODULE_C6_RES_MS		0x00000664
 
 #define MSR_CC6_DEMOTION_POLICY_CONFIG	0x00000668
 #define MSR_MC6_DEMOTION_POLICY_CONFIG	0x00000669
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index d56f2b75dc58..19802be6dc02 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -167,6 +167,7 @@ struct core_data {
 	unsigned long long c3;
 	unsigned long long c6;
 	unsigned long long c7;
+	unsigned long long mc6_us;	/* duplicate as per-core for now, even though per module */
 	unsigned int core_temp_c;
 	unsigned int core_id;
 	unsigned long long counter[MAX_ADDED_COUNTERS];
@@ -375,6 +376,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "RAM_J" },
 	{ 0x0, "Core" },
 	{ 0x0, "CPU" },
+	{ 0x0, "Mod%c6" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -412,6 +414,7 @@ struct msr_counter bic[] = {
 #define	BIC_RAM_J	(1ULL << 31)
 #define	BIC_Core	(1ULL << 32)
 #define	BIC_CPU		(1ULL << 33)
+#define	BIC_Mod_c6	(1ULL << 34)
 
 unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
 unsigned long long bic_present;
@@ -504,6 +507,8 @@ void print_header(void)
 	if (DO_BIC(BIC_CPU_c7))
 		outp += sprintf(outp, "\tCPU%%c7");
 
+	if (DO_BIC(BIC_Mod_c6))
+		outp += sprintf(outp, "\tMod%%c6");
 
 	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "\tCoreTmp");
@@ -629,6 +634,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 			outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
 				i, mp->msr_num, c->counter[i]);
 		}
+		outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us);
 	}
 
 	if (p) {
@@ -774,6 +780,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_CPU_c7))
 		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
 
+	/* Mod%c6 */
+	if (DO_BIC(BIC_Mod_c6))
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->mc6_us / t->tsc);
+
 	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "\t%d", c->core_temp_c);
 
@@ -988,6 +998,7 @@ delta_core(struct core_data *new, struct core_data *old)
 	old->c6 = new->c6 - old->c6;
 	old->c7 = new->c7 - old->c7;
 	old->core_temp_c = new->core_temp_c;
+	old->mc6_us = new->mc6_us - old->mc6_us;
 
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1109,6 +1120,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	c->c3 = 0;
 	c->c6 = 0;
 	c->c7 = 0;
+	c->mc6_us = 0;
 	c->core_temp_c = 0;
 
 	p->pkg_wtd_core_c0 = 0;
@@ -1173,6 +1185,7 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	average.cores.c3 += c->c3;
 	average.cores.c6 += c->c6;
 	average.cores.c7 += c->c7;
+	average.cores.mc6_us += c->mc6_us;
 
 	average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
@@ -1246,6 +1259,7 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.cores.c3 /= topo.num_cores;
 	average.cores.c6 /= topo.num_cores;
 	average.cores.c7 /= topo.num_cores;
+	average.cores.mc6_us /= topo.num_cores;
 
 	if (do_skl_residency) {
 		average.packages.pkg_wtd_core_c0 /= topo.num_packages;
@@ -1376,8 +1390,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -5;
 		t->smi_count = msr & 0xFFFFFFFF;
 	}
-
-	if (use_c1_residency_msr) {
+	if (DO_BIC(BIC_CPU_c1) && use_c1_residency_msr) {
 		if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1))
 			return -6;
 	}
@@ -1409,6 +1422,10 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7))
 			return -8;
 
+	if (DO_BIC(BIC_Mod_c6))
+		if (get_msr(cpu, MSR_MODULE_C6_RES_MS, &c->mc6_us))
+			return -8;
+
 	if (DO_BIC(BIC_CoreTmp)) {
 		if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
 			return -9;
@@ -1437,9 +1454,16 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (do_pc3)
 		if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
 			return -9;
-	if (do_pc6)
-		if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6))
-			return -10;
+	if (do_pc6) {
+		if (do_slm_cstates) {
+			if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6))
+				return -10;
+		} else {
+			if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6))
+				return -10;
+		}
+	}
+
 	if (do_pc2)
 		if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2))
 			return -11;
@@ -1533,7 +1557,7 @@ char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2",
 int nhm_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int snb_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCL__8, PCL__9, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7};
 int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
@@ -3336,8 +3360,6 @@ int has_skl_msrs(unsigned int family, unsigned int model)
 	return 0;
 }
 
-
-
 int is_slm(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
@@ -3731,6 +3753,12 @@ void process_cpuid()
 	do_pc3 = (pkg_cstate_limit >= PCL__3);
 	do_pc6 = (pkg_cstate_limit >= PCL__6);
 	do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7);
+	if (has_slv_msrs(family, model)) {
+		do_pc2 = do_pc3 = do_pc7 = 0;
+		do_pc6 = 1;
+		BIC_PRESENT(BIC_Mod_c6);
+		use_c1_residency_msr = 1;
+	}
 	do_c8_c9_c10 = has_hsw_msrs(family, model);
 	do_irtl_hsw = has_hsw_msrs(family, model);
 	do_skl_residency = has_skl_msrs(family, model);
@@ -4112,7 +4140,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 4.17 1 Jan 2017"
+	fprintf(outf, "turbostat version 4.17 10 Jan 2017"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
-- 
GitLab


From 710f273ba96182fd93ee8540ae06583c7d889d7c Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Wed, 11 Jan 2017 22:12:25 -0500
Subject: [PATCH 346/898] tools/power turbostat: add precision to --debug
 frequency output

Add a digit of precision to the --debug output for frequency range.
This is useful when BCLK is not an integer.

old:
6 * 83 = 500 MHz max efficiency frequency
26 * 83 = 2166 MHz base frequency

new:
6 * 83.3 = 499.8 MHz max efficiency frequency
26 * 83.3 = 2165.8 MHz base frequency

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 42 +++++++++++++--------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 19802be6dc02..762b81497c3b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1581,11 +1581,11 @@ dump_nhm_platform_info(void)
 	fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 40) & 0xFF;
-	fprintf(outf, "%d * %.0f = %.0f MHz max efficiency frequency\n",
+	fprintf(outf, "%d * %.1f = %.1f MHz max efficiency frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
-	fprintf(outf, "%d * %.0f = %.0f MHz base frequency\n",
+	fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
@@ -1607,12 +1607,12 @@ dump_hsw_turbo_ratio_limits(void)
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 18 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 18 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 17 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 17 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1629,42 +1629,42 @@ dump_ivt_turbo_ratio_limits(void)
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 16 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 16 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 48) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 15 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 15 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 40) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 14 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 14 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 32) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 13 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 13 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 12 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 12 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 16) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 11 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 11 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 10 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 10 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 9 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 9 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1681,42 +1681,42 @@ dump_nhm_turbo_ratio_limits(void)
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 8 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 8 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 48) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 7 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 7 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 40) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 6 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 6 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 32) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 5 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 5 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 4 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 4 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 16) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 3 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 3 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 2 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 2 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 1 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1776,7 +1776,7 @@ dump_knl_turbo_ratio_limits(void)
 	for (i = buckets_no - 1; i >= 0; i--)
 		if (i > 0 ? ratio[i] != ratio[i - 1] : 1)
 			fprintf(outf,
-				"%d * %.0f = %.0f MHz max turbo %d active cores\n",
+				"%d * %.1f = %.1f MHz max turbo %d active cores\n",
 				ratio[i], bclk, ratio[i] * bclk, cores[i]);
 }
 
-- 
GitLab


From e651262477c6d8cba79dffc1a6039da43d9c96b0 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Wed, 11 Jan 2017 23:17:24 -0500
Subject: [PATCH 347/898] tools/power turbostat: further decode
 MSR_IA32_MISC_ENABLE

Decode MISC_ENABLE.NO_TURBO,
also use the #defines in msr-index.h for decoding this register

cpu0: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST MWAIT TURBO)

Although it is not architectural, decode also
MSR_IA32_MISC_ENABLE.prefetch-disable (bit-9).
documented to be present on: Core, P4, Intel-Xeon
reserved on: Atom, Silvermont, Nehalem, SNB, PHI ec.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 762b81497c3b..a1ec9d816dfa 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3509,11 +3509,13 @@ void decode_misc_enable_msr(void)
 	unsigned long long msr;
 
 	if (!get_msr(base_cpu, MSR_IA32_MISC_ENABLE, &msr))
-		fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%s %s %s)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%sTCC %sEIST %sMWAIT %sPREFETCH %sTURBO)\n",
 			base_cpu, msr,
-			msr & (1 << 3) ? "TCC" : "",
-			msr & (1 << 16) ? "EIST" : "",
-			msr & (1 << 18) ? "MONITOR" : "");
+			msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-",
+			msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-",
+			msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "",
+			msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "",
+			msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : "");
 }
 
 /*
-- 
GitLab


From 8a34fd0226eaae64d61ff9a113d276e28acb6b5c Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 12 Jan 2017 23:22:28 -0500
Subject: [PATCH 348/898] x86 msr-index.h: Define Atom specific core ratio MSR
 locations

These MSRs are currently used by the intel_pstate driver,
using a local definition.

Cc: x86@kernel.org
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/include/asm/msr-index.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 079db99f6560..83bc672c225c 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -209,6 +209,12 @@
 #define MSR_CC6_DEMOTION_POLICY_CONFIG	0x00000668
 #define MSR_MC6_DEMOTION_POLICY_CONFIG	0x00000669
 
+#define MSR_ATOM_CORE_RATIOS		0x0000066a
+#define MSR_ATOM_CORE_VIDS		0x0000066b
+#define MSR_ATOM_CORE_TURBO_RATIOS	0x0000066c
+#define MSR_ATOM_CORE_TURBO_VIDS	0x0000066d
+
+
 #define MSR_CORE_PERF_LIMIT_REASONS	0x00000690
 #define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
 #define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
-- 
GitLab


From 92134bdbc6272da6e98e9242cc6f1576cedc0735 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 25 Feb 2017 16:55:17 -0500
Subject: [PATCH 349/898] intel_pstate: use MSR_ATOM_RATIOS definitions from
 msr-index.h

Originally, these MSRs were locally defined in this driver.
Now the definitions are in msr-index.h -- use them.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 50bd6d987fc3..6e68b556305a 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -39,11 +39,6 @@
 
 #define INTEL_CPUFREQ_TRANSITION_LATENCY	20000
 
-#define ATOM_RATIOS		0x66a
-#define ATOM_VIDS		0x66b
-#define ATOM_TURBO_RATIOS	0x66c
-#define ATOM_TURBO_VIDS		0x66d
-
 #ifdef CONFIG_ACPI
 #include <acpi/processor.h>
 #include <acpi/cppc_acpi.h>
@@ -1258,7 +1253,7 @@ static int atom_get_min_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(ATOM_RATIOS, value);
+	rdmsrl(MSR_ATOM_CORE_RATIOS, value);
 	return (value >> 8) & 0x7F;
 }
 
@@ -1266,7 +1261,7 @@ static int atom_get_max_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(ATOM_RATIOS, value);
+	rdmsrl(MSR_ATOM_CORE_RATIOS, value);
 	return (value >> 16) & 0x7F;
 }
 
@@ -1274,7 +1269,7 @@ static int atom_get_turbo_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(ATOM_TURBO_RATIOS, value);
+	rdmsrl(MSR_ATOM_CORE_TURBO_RATIOS, value);
 	return value & 0x7F;
 }
 
@@ -1336,7 +1331,7 @@ static void atom_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
 
-	rdmsrl(ATOM_VIDS, value);
+	rdmsrl(MSR_ATOM_CORE_VIDS, value);
 	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
 	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
 	cpudata->vid.ratio = div_fp(
@@ -1344,7 +1339,7 @@ static void atom_get_vid(struct cpudata *cpudata)
 		int_tofp(cpudata->pstate.max_pstate -
 			cpudata->pstate.min_pstate));
 
-	rdmsrl(ATOM_TURBO_VIDS, value);
+	rdmsrl(MSR_ATOM_CORE_TURBO_VIDS, value);
 	cpudata->vid.turbo = value & 0x7f;
 }
 
-- 
GitLab


From 0f7887c49b0c454aef9936a6eadabe1c91b5af55 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 12 Jan 2017 23:49:18 -0500
Subject: [PATCH 350/898] tools/power turbostat: dump Atom P-states correctly

Turbostat dumps MSR_TURBO_RATIO_LIMIT on Core Architecture.
But Atom Architecture uses MSR_ATOM_CORE_RATIOS and
MSR_ATOM_CORE_TURBO_RATIOS.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 103 ++++++++++++++++++++------
 1 file changed, 82 insertions(+), 21 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index a1ec9d816dfa..da6ec640caf7 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1721,6 +1721,54 @@ dump_nhm_turbo_ratio_limits(void)
 	return;
 }
 
+static void
+dump_atom_turbo_ratio_limits(void)
+{
+	unsigned long long msr;
+	unsigned int ratio;
+
+	get_msr(base_cpu, MSR_ATOM_CORE_RATIOS, &msr);
+	fprintf(outf, "cpu%d: MSR_ATOM_CORE_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF);
+
+	ratio = (msr >> 0) & 0x3F;
+	if (ratio)
+		fprintf(outf, "%d * %.1f = %.1f MHz minimum operating frequency\n",
+			ratio, bclk, ratio * bclk);
+
+	ratio = (msr >> 8) & 0x3F;
+	if (ratio)
+		fprintf(outf, "%d * %.1f = %.1f MHz low frequency mode (LFM)\n",
+			ratio, bclk, ratio * bclk);
+
+	ratio = (msr >> 16) & 0x3F;
+	if (ratio)
+		fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n",
+			ratio, bclk, ratio * bclk);
+
+	get_msr(base_cpu, MSR_ATOM_CORE_TURBO_RATIOS, &msr);
+	fprintf(outf, "cpu%d: MSR_ATOM_CORE_TURBO_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF);
+
+	ratio = (msr >> 24) & 0x3F;
+	if (ratio)
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 4 active cores\n",
+			ratio, bclk, ratio * bclk);
+
+	ratio = (msr >> 16) & 0x3F;
+	if (ratio)
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 3 active cores\n",
+			ratio, bclk, ratio * bclk);
+
+	ratio = (msr >> 8) & 0x3F;
+	if (ratio)
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 2 active cores\n",
+			ratio, bclk, ratio * bclk);
+
+	ratio = (msr >> 0) & 0x3F;
+	if (ratio)
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 1 active core\n",
+			ratio, bclk, ratio * bclk);
+}
+
 static void
 dump_knl_turbo_ratio_limits(void)
 {
@@ -2496,8 +2544,32 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	has_base_hz = 1;
 	return 1;
 }
+/*
+ * SLV client has supporet for unique MSRs:
+ *
+ * MSR_CC6_DEMOTION_POLICY_CONFIG
+ * MSR_MC6_DEMOTION_POLICY_CONFIG
+ */
+
+int has_slv_msrs(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_MERRIFIELD:
+	case INTEL_FAM6_ATOM_MOOREFIELD:
+		return 1;
+	}
+	return 0;
+}
+
 int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
+	if (has_slv_msrs(family, model))
+		return 0;
+
 	switch (model) {
 	/* Nehalem compatible, but do not include turbo-ratio limit support */
 	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
@@ -2509,6 +2581,13 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 1;
 	}
 }
+int has_atom_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+	if (has_slv_msrs(family, model))
+		return 1;
+
+	return 0;
+}
 int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
@@ -2606,6 +2685,9 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
 	if (has_nhm_turbo_ratio_limit(family, model))
 		dump_nhm_turbo_ratio_limits();
 
+	if (has_atom_turbo_ratio_limit(family, model))
+		dump_atom_turbo_ratio_limits();
+
 	if (has_knl_turbo_ratio_limit(family, model))
 		dump_knl_turbo_ratio_limits();
 
@@ -3286,27 +3368,6 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	return 0;
 }
 
-/*
- * SLV client has supporet for unique MSRs:
- *
- * MSR_CC6_DEMOTION_POLICY_CONFIG
- * MSR_MC6_DEMOTION_POLICY_CONFIG
- */
-
-int has_slv_msrs(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_MERRIFIELD:
-	case INTEL_FAM6_ATOM_MOOREFIELD:
-		return 1;
-	}
-	return 0;
-}
-
 /*
  * HSW adds support for additional MSRs:
  *
-- 
GitLab


From b3a34e9382a4aacfa7c0b24f9548737bbb20338e Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 21 Jan 2017 00:50:08 -0500
Subject: [PATCH 351/898] tools/power turbostat: decode CPUID(6).TURBO

show the CPUID feature for turbo to clarify the case
when it may not be shown in MISC_ENABLE

CPUID(6): APERF, TURBO, DTS, PTM, No-HWP, No-HWPnotify, No-HWPwindow, No-HWPepp, No-HWPpkg, EPB
cpu4: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST MWAIT TURBO)

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index da6ec640caf7..1011b5f7f21f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3626,6 +3626,7 @@ void process_cpuid()
 {
 	unsigned int eax, ebx, ecx, edx, max_level, max_extended_level;
 	unsigned int fms, family, model, stepping;
+	unsigned int has_turbo;
 
 	eax = ebx = ecx = edx = 0;
 
@@ -3696,6 +3697,7 @@ void process_cpuid()
 	do_dts = eax & (1 << 0);
 	if (do_dts)
 		BIC_PRESENT(BIC_CoreTmp);
+	has_turbo = eax & (1 << 1);
 	do_ptm = eax & (1 << 6);
 	if (do_ptm)
 		BIC_PRESENT(BIC_PkgTmp);
@@ -3707,9 +3709,10 @@ void process_cpuid()
 	has_epb = ecx & (1 << 3);
 
 	if (debug)
-		fprintf(outf, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sHWP, "
+		fprintf(outf, "CPUID(6): %sAPERF, %sTURBO, %sDTS, %sPTM, %sHWP, "
 			"%sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n",
 			has_aperf ? "" : "No-",
+			has_turbo ? "" : "No-",
 			do_dts ? "" : "No-",
 			do_ptm ? "" : "No-",
 			has_hwp ? "" : "No-",
-- 
GitLab


From 98af74599ea0757098a5776ea29e581b661dcf6f Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 21 Jan 2017 01:15:09 -0500
Subject: [PATCH 352/898] x86 msr_index.h: Define MSR_MISC_FEATURE_CONTROL

This non-architectural MSR has disable bits
for various prefetchers on modern processors.

While these bits are generally touched only by the BIOS,
say, via BIOS SETUP, it is useful to dump them
when examining options that can alter performance.

Cc: x86@kernel.org
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/include/asm/msr-index.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 83bc672c225c..312fb7e14cdd 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -467,6 +467,7 @@
 
 #define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
 
+#define MSR_MISC_FEATURE_CONTROL	0x000001a4
 #define MSR_MISC_PWR_MGMT		0x000001aa
 
 #define MSR_IA32_ENERGY_PERF_BIAS	0x000001b0
-- 
GitLab


From 33148d671cc191fceaca5017e1bb060e9f30fbf7 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 21 Jan 2017 01:26:16 -0500
Subject: [PATCH 353/898] tools/power turbostat: decode
 MSR_MISC_FEATURE_CONTROL

useful for observing if the BIOS disabled prefetch
Not architectural, but docuemented as present on NHM, SNB
and is present on others.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 1011b5f7f21f..2f033f3d2a21 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -102,6 +102,7 @@ unsigned int has_hwp_notify;		/* IA32_HWP_INTERRUPT */
 unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
 unsigned int has_hwp_epp;		/* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
+unsigned int has_misc_feature_control;
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -2466,6 +2467,7 @@ void check_permissions()
  *
  * Side effect:
  * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL
+ * sets has_misc_feature_control
  */
 int probe_nhm_msrs(unsigned int family, unsigned int model)
 {
@@ -2496,6 +2498,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
 	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
 		pkg_cstate_limits = snb_pkg_cstate_limits;
+		has_misc_feature_control = 1;
 		break;
 	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
 	case INTEL_FAM6_HASWELL_X:	/* HSX */
@@ -2510,9 +2513,11 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		pkg_cstate_limits = hsw_pkg_cstate_limits;
+		has_misc_feature_control = 1;
 		break;
 	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 		pkg_cstate_limits = skx_pkg_cstate_limits;
+		has_misc_feature_control = 1;
 		break;
 	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
 		no_MSR_MISC_PWR_MGMT = 1;
@@ -3579,6 +3584,21 @@ void decode_misc_enable_msr(void)
 			msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : "");
 }
 
+void decode_misc_feature_control(void)
+{
+	unsigned long long msr;
+
+	if (!has_misc_feature_control)
+		return;
+
+	if (!get_msr(base_cpu, MSR_MISC_FEATURE_CONTROL, &msr))
+		fprintf(outf, "cpu%d: MSR_MISC_FEATURE_CONTROL: 0x%08llx (%sL2-Prefetch %sL2-Prefetch-pair %sL1-Prefetch %sL1-IP-Prefetch)\n",
+			base_cpu, msr,
+			msr & (0 << 0) ? "No-" : "",
+			msr & (1 << 0) ? "No-" : "",
+			msr & (2 << 0) ? "No-" : "",
+			msr & (3 << 0) ? "No-" : "");
+}
 /*
  * Decode MSR_MISC_PWR_MGMT
  *
@@ -3725,6 +3745,7 @@ void process_cpuid()
 	if (debug)
 		decode_misc_enable_msr();
 
+
 	if (max_level >= 0x7 && debug) {
 		int has_sgx;
 
@@ -3852,6 +3873,9 @@ void process_cpuid()
 	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
 		BIC_PRESENT(BIC_GFXMHz);
 
+	if (debug)
+		decode_misc_feature_control();
+
 	return;
 }
 
-- 
GitLab


From fee86541d28934da4eb235367f7e2137acb1b359 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 21 Jan 2017 01:59:12 -0500
Subject: [PATCH 354/898] tools/power turbostat: show all columns, independent
 of --debug

Some time ago, turbostat overflowed 80 columns.

So on the assumption that a "casual" user would always
want topology and frequency columns, we hid the rest
of the columns and the system configuration decoding
behind the --debug option.

Not everybody liked that change -- including me.
I use --debug 99% of the time...

Well, now we have "-o file" to put turbostat output into a file,
so unless you are watching real-time in a small window,
column count is less frequently a factor.

And more recently, we got the "--hide columnA,columnB" option
to specify columns to skip.

So now we "un-hide" the rest of the columns from behind --debug,
and show them all, by default.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 2f033f3d2a21..c50b452a404e 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -479,9 +479,6 @@ void print_header(void)
 	if (DO_BIC(BIC_TSC_MHz))
 		outp += sprintf(outp, "\tTSC_MHz");
 
-	if (!debug)
-		goto done;
-
 	if (DO_BIC(BIC_IRQ))
 		outp += sprintf(outp, "\tIRQ");
 	if (DO_BIC(BIC_SMI))
@@ -593,7 +590,6 @@ void print_header(void)
 		}
 	}
 
-done:
 	outp += sprintf(outp, "\n");
 }
 
@@ -741,9 +737,6 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_TSC_MHz))
 		outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
 
-	if (!debug)
-		goto done;
-
 	/* IRQ */
 	if (DO_BIC(BIC_IRQ))
 		outp += sprintf(outp, "\t%d", t->irq_count);
-- 
GitLab


From 96e4715857cf184536ef46e6ea92465f58a7b12d Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 21 Jan 2017 02:26:00 -0500
Subject: [PATCH 355/898] tools/power turbostat: print system config, unless
 --quiet

Some users want turbostat to tell them everything, by default.
Some users want turbostat to be quiet, by default.

I find that I'm in the 1st camp, and so I've never liked
needing to type the --debug parameter to decode the system
configuration.

So here we change the default and print the system configuration,
by default.  (The --debug option is now un-documented, though
it does still exist for debugging turbostat internals)

When you do not want to see the system configuration
header, use the new "--quiet" option.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.8 |   7 +-
 tools/power/x86/turbostat/turbostat.c | 105 +++++++++++++-------------
 2 files changed, 52 insertions(+), 60 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index e8fb1e02d121..a08de27713e0 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -53,8 +53,7 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--Dump\fP displays the raw counter values.
 .PP
-\fB--debug\fP displays additional system configuration information.  Invoking this parameter
-more than once may also enable internal turbostat debug information.
+\fB--quiet\fP Do not decode and print the system configuration header information.
 .PP
 \fB--interval seconds\fP overrides the default 5.0 second measurement interval.
 .PP
@@ -124,7 +123,6 @@ Or a command may be specified as in "FORK EXAMPLE" below.
 
 .fi
 .SH DEBUG EXAMPLE
-The "--debug" option prints additional system information before measurements:
 
 The first row of statistics is a summary for the entire system.
 For residency % columns, the summary is a weighted average.
@@ -188,9 +186,6 @@ should be sustainable on all CPUs indefinitely, given nominal power and cooling.
 The remaining rows show what maximum turbo frequency is possible
 depending on the number of idle cores.  Note that not all information is
 available on all processors.
-.PP
-The --debug option adds additional columns to the measurement ouput, including CPU idle power-state residency processor temperature sensor readinds.
-See the field definitions above.
 .SH FORK EXAMPLE
 If turbostat is invoked with a command, it will fork that command
 and output the statistics gathered after the command exits.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index c50b452a404e..6867557596af 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -49,6 +49,7 @@ FILE *outf;
 int *fd_percpu;
 struct timespec interval_ts = {5, 0};
 unsigned int debug;
+unsigned int quiet;
 unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int dump_only;
@@ -3114,7 +3115,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 	tdp = get_tdp(model);
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
-	if (debug)
+	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 
 	return;
@@ -3239,11 +3240,9 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
 		return -1;
 
-	if (debug) {
-		fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
-			"(%f Watts, %f Joules, %f sec.)\n", cpu, msr,
-			rapl_power_units, rapl_energy_units, rapl_time_units);
-	}
+	fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+		rapl_power_units, rapl_energy_units, rapl_time_units);
+
 	if (do_rapl & RAPL_PKG_POWER_INFO) {
 
 		if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr))
@@ -3264,7 +3263,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -9;
 
 		fprintf(outf, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n",
-			cpu, msr, (msr >> 63) & 1 ? "": "UN");
+			cpu, msr, (msr >> 63) & 1 ? "" : "UN");
 
 		print_power_limit_msr(cpu, msr, "PKG Limit #1");
 		fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
@@ -3290,40 +3289,34 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
 			return -9;
 		fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
-				cpu, msr, (msr >> 31) & 1 ? "": "UN");
+				cpu, msr, (msr >> 31) & 1 ? "" : "UN");
 
 		print_power_limit_msr(cpu, msr, "DRAM Limit");
 	}
 	if (do_rapl & RAPL_CORE_POLICY) {
-		if (debug) {
-			if (get_msr(cpu, MSR_PP0_POLICY, &msr))
-				return -7;
+		if (get_msr(cpu, MSR_PP0_POLICY, &msr))
+			return -7;
 
-			fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
-		}
+		fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
 	}
 	if (do_rapl & RAPL_CORES_POWER_LIMIT) {
-		if (debug) {
-			if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
-				return -9;
-			fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
-					cpu, msr, (msr >> 31) & 1 ? "": "UN");
-			print_power_limit_msr(cpu, msr, "Cores Limit");
-		}
+		if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
+			return -9;
+		fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
+				cpu, msr, (msr >> 31) & 1 ? "" : "UN");
+		print_power_limit_msr(cpu, msr, "Cores Limit");
 	}
 	if (do_rapl & RAPL_GFX) {
-		if (debug) {
-			if (get_msr(cpu, MSR_PP1_POLICY, &msr))
-				return -8;
+		if (get_msr(cpu, MSR_PP1_POLICY, &msr))
+			return -8;
 
-			fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
+		fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
 
-			if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr))
-				return -9;
-			fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
-					cpu, msr, (msr >> 31) & 1 ? "": "UN");
-			print_power_limit_msr(cpu, msr, "GFX Limit");
-		}
+		if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr))
+			return -9;
+		fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
+				cpu, msr, (msr >> 31) & 1 ? "" : "UN");
+		print_power_limit_msr(cpu, msr, "GFX Limit");
 	}
 	return 0;
 }
@@ -3469,7 +3462,7 @@ double slm_bclk(void)
 	}
 	freq = slm_freq_table[i];
 
-	if (debug)
+	if (!quiet)
 		fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
 
 	return freq;
@@ -3533,7 +3526,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 
 	target_c_local = (msr >> 16) & 0xFF;
 
-	if (debug)
+	if (!quiet)
 		fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
 			cpu, msr, target_c_local);
 
@@ -3648,7 +3641,7 @@ void process_cpuid()
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
 
-	if (debug)
+	if (!quiet)
 		fprintf(outf, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
@@ -3659,7 +3652,7 @@ void process_cpuid()
 	if (family == 6 || family == 0xf)
 		model += ((fms >> 16) & 0xf) << 4;
 
-	if (debug) {
+	if (!quiet) {
 		fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
 			max_level, family, model, stepping, family, model, stepping);
 		fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n",
@@ -3721,7 +3714,7 @@ void process_cpuid()
 	has_hwp_pkg = eax & (1 << 11);
 	has_epb = ecx & (1 << 3);
 
-	if (debug)
+	if (!quiet)
 		fprintf(outf, "CPUID(6): %sAPERF, %sTURBO, %sDTS, %sPTM, %sHWP, "
 			"%sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n",
 			has_aperf ? "" : "No-",
@@ -3735,11 +3728,11 @@ void process_cpuid()
 			has_hwp_pkg ? "" : "No-",
 			has_epb ? "" : "No-");
 
-	if (debug)
+	if (!quiet)
 		decode_misc_enable_msr();
 
 
-	if (max_level >= 0x7 && debug) {
+	if (max_level >= 0x7 && !quiet) {
 		int has_sgx;
 
 		ecx = 0;
@@ -3765,7 +3758,7 @@ void process_cpuid()
 
 		if (ebx_tsc != 0) {
 
-			if (debug && (ebx != 0))
+			if (!quiet && (ebx != 0))
 				fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
 					eax_crystal, ebx_tsc, crystal_hz);
 
@@ -3790,7 +3783,7 @@ void process_cpuid()
 
 			if (crystal_hz) {
 				tsc_hz =  (unsigned long long) crystal_hz * ebx_tsc / eax_crystal;
-				if (debug)
+				if (!quiet)
 					fprintf(outf, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n",
 						tsc_hz / 1000000, crystal_hz, ebx_tsc,  eax_crystal);
 			}
@@ -3805,7 +3798,7 @@ void process_cpuid()
 		base_mhz = max_mhz = bus_mhz = edx = 0;
 
 		__cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx);
-		if (debug)
+		if (!quiet)
 			fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n",
 				base_mhz, max_mhz, bus_mhz);
 	}
@@ -3845,16 +3838,16 @@ void process_cpuid()
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
 
-	if (debug)
+	if (!quiet)
 		decode_misc_pwr_mgmt_msr();
 
-	if (debug && has_slv_msrs(family, model))
+	if (!quiet && has_slv_msrs(family, model))
 		decode_c6_demotion_policy_msr();
 
 	rapl_probe(family, model);
 	perf_limit_reasons_probe(family, model);
 
-	if (debug)
+	if (!quiet)
 		dump_cstate_pstate_config_info(family, model);
 
 	if (has_skl_msrs(family, model))
@@ -3866,7 +3859,7 @@ void process_cpuid()
 	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
 		BIC_PRESENT(BIC_GFXMHz);
 
-	if (debug)
+	if (!quiet)
 		decode_misc_feature_control();
 
 	return;
@@ -3883,7 +3876,7 @@ void help()
 	"to print statistics, until interrupted.\n"
 	"--add		add a counter\n"
 	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
-	"--debug	run in \"debug\" mode\n"
+	"--quiet	skip decoding system configuration header\n"
 	"--interval sec	Override default 5-second measurement interval\n"
 	"--help		print this help message\n"
 	"--out file	create or truncate \"file\" for all output\n"
@@ -4136,24 +4129,24 @@ void turbostat_init()
 	process_cpuid();
 
 
-	if (debug)
+	if (!quiet)
 		for_all_cpus(print_hwp, ODD_COUNTERS);
 
-	if (debug)
+	if (!quiet)
 		for_all_cpus(print_epb, ODD_COUNTERS);
 
-	if (debug)
+	if (!quiet)
 		for_all_cpus(print_perf_limit, ODD_COUNTERS);
 
-	if (debug)
+	if (!quiet)
 		for_all_cpus(print_rapl, ODD_COUNTERS);
 
 	for_all_cpus(set_temperature_target, ODD_COUNTERS);
 
-	if (debug)
+	if (!quiet)
 		for_all_cpus(print_thermal, ODD_COUNTERS);
 
-	if (debug && do_irtl_snb)
+	if (!quiet && do_irtl_snb)
 		print_irtl();
 }
 
@@ -4429,7 +4422,7 @@ void cmdline(int argc, char **argv)
 	static struct option long_options[] = {
 		{"add",		required_argument,	0, 'a'},
 		{"Dump",	no_argument,		0, 'D'},
-		{"debug",	no_argument,		0, 'd'},
+		{"debug",	no_argument,		0, 'd'},	/* internal, not documented */
 		{"interval",	required_argument,	0, 'i'},
 		{"help",	no_argument,		0, 'h'},
 		{"hide",	required_argument,	0, 'H'},	// meh, -h taken by --help
@@ -4437,6 +4430,7 @@ void cmdline(int argc, char **argv)
 		{"out",		required_argument,	0, 'o'},
 		{"Package",	no_argument,		0, 'p'},
 		{"processor",	no_argument,		0, 'p'},
+		{"quiet",	no_argument,		0, 'q'},
 		{"show",	required_argument,	0, 's'},
 		{"Summary",	no_argument,		0, 'S'},
 		{"TCC",		required_argument,	0, 'T'},
@@ -4446,7 +4440,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpqST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -4491,6 +4485,9 @@ void cmdline(int argc, char **argv)
 		case 'p':
 			show_core_only++;
 			break;
+		case 'q':
+			quiet = 1;
+			break;
 		case 's':
 			parse_show_hide(optarg, SHOW_LIST);
 			break;
@@ -4514,7 +4511,7 @@ int main(int argc, char **argv)
 
 	cmdline(argc, argv);
 
-	if (debug)
+	if (!quiet)
 		print_version();
 
 	turbostat_init();
-- 
GitLab


From 008d396eb219ee5a1c98c9ef01c35752d35f0d6c Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 10 Feb 2017 00:29:51 -0500
Subject: [PATCH 356/898] tools/power turbostat: use tsc_tweak everwhere it is
 needed

The CPU ticks at a rate in the "bus clock" domain.
eg. 100 MHz * bus_ratio.

On newer processors, the TSC has been moved out of this BCLK
domain and into a separate crystal-clock domain.

While the TSC ticks "close to" the base frequency, those that look
closely at the numbers will notice small errors in calculations that
mix units of TSC clocks and bus clocks.

"tsc_tweak" was introduced to address the most visible
mixing -- the %Busy and the the Busy_MHz calculations.
(A simplification as since removed TSC from the BusyMHz calculation)

Here we apply the tsc_tweak to everyplace where BCLK
and TSC units are mixed.  The results is that
on a system which is 100% idle, the sum of the C-states
are now much more likely to be closer to 100%.

Reported-by: Travis Downs <travis.downs@gmail.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 48 ++++++++++++++-------------
 1 file changed, 25 insertions(+), 23 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 6867557596af..bbdf9ba9d41b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -680,7 +680,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 int format_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
-	double interval_float;
+	double interval_float, tsc;
 	char *fmt8;
 	int i;
 	struct msr_counter *mp;
@@ -695,6 +695,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
 
+	tsc = t->tsc * tsc_tweak;
+
 	/* topo columns, print blanks on 1st (average) line */
 	if (t == &average.threads) {
 		if (DO_BIC(BIC_Package))
@@ -725,14 +727,14 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			1.0 / units * t->aperf / interval_float);
 
 	if (DO_BIC(BIC_Busy))
-		outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
+		outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/tsc);
 
 	if (DO_BIC(BIC_Bzy_MHz)) {
 		if (has_base_hz)
 			outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf);
 		else
 			outp += sprintf(outp, "\t%.0f",
-				1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+				tsc / units * t->aperf / t->mperf / interval_float);
 	}
 
 	if (DO_BIC(BIC_TSC_MHz))
@@ -748,7 +750,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	/* C1 */
 	if (DO_BIC(BIC_CPU_c1))
-		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/tsc);
 
 	/* Added counters */
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
@@ -760,7 +762,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		} else if (mp->format == FORMAT_DELTA) {
 			outp += sprintf(outp, "\t%lld", t->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
-			outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/t->tsc);
+			outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/tsc);
 		}
 	}
 
@@ -769,15 +771,15 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		goto done;
 
 	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/tsc);
 	if (DO_BIC(BIC_CPU_c6))
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/tsc);
 	if (DO_BIC(BIC_CPU_c7))
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/tsc);
 
 	/* Mod%c6 */
 	if (DO_BIC(BIC_Mod_c6))
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->mc6_us / t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->mc6_us / tsc);
 
 	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "\t%d", c->core_temp_c);
@@ -791,7 +793,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		} else if (mp->format == FORMAT_DELTA) {
 			outp += sprintf(outp, "\t%lld", c->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
-			outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/t->tsc);
+			outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/tsc);
 		}
 	}
 
@@ -819,24 +821,24 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (do_skl_residency) {
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/t->tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/tsc);
 	}
 
 	if (do_pc2)
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/tsc);
 	if (do_pc3)
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/tsc);
 	if (do_pc6)
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/tsc);
 	if (do_pc7)
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/tsc);
 	if (do_c8_c9_c10) {
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/t->tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/t->tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/tsc);
 	}
 
 	/*
@@ -878,7 +880,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		} else if (mp->format == FORMAT_DELTA) {
 			outp += sprintf(outp, "\t%lld", p->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
-			outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/t->tsc);
+			outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/tsc);
 		}
 	}
 
@@ -1048,7 +1050,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 			old->c1 = 0;
 		else {
 			/* normal case, derive c1 */
-			old->c1 = old->tsc - old->mperf - core_delta->c3
+			old->c1 = (old->tsc * tsc_tweak) - old->mperf - core_delta->c3
 				- core_delta->c6 - core_delta->c7;
 		}
 	}
-- 
GitLab


From 0f47c08d8ccf8252a5c007502919bdc2126ffb1f Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 27 Jan 2017 00:50:45 -0500
Subject: [PATCH 357/898] tools/power turbostat: bug fixes to --add,
 --show/--hide features

Fix a bug with --add, where the title of the column
is un-initialized if not specified by the user.

The initial implementation of --show and --hide
neglected to handle the pc8/pc9/pc10 counters.

Fix a bug where "--show Core" only worked with --debug

Reported-by: Wendy Wang <wendy.wang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 138 ++++++++++++++------------
 1 file changed, 77 insertions(+), 61 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bbdf9ba9d41b..4b04ba86e44f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -55,11 +55,6 @@ unsigned int summary_only;
 unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
-unsigned int do_pc2;
-unsigned int do_pc3;
-unsigned int do_pc6;
-unsigned int do_pc7;
-unsigned int do_c8_c9_c10;
 unsigned int do_skl_residency;
 unsigned int do_slm_cstates;
 unsigned int use_c1_residency_msr;
@@ -365,6 +360,9 @@ struct msr_counter bic[] = {
 	{ 0x0, "Pkg%pc3" },
 	{ 0x0, "Pkg%pc6" },
 	{ 0x0, "Pkg%pc7" },
+	{ 0x0, "Pkg%pc8" },
+	{ 0x0, "Pkg%pc9" },
+	{ 0x0, "Pkg%pc10" },
 	{ 0x0, "PkgWatt" },
 	{ 0x0, "CorWatt" },
 	{ 0x0, "GFXWatt" },
@@ -403,26 +401,30 @@ struct msr_counter bic[] = {
 #define	BIC_Pkgpc3	(1ULL << 18)
 #define	BIC_Pkgpc6	(1ULL << 19)
 #define	BIC_Pkgpc7	(1ULL << 20)
-#define	BIC_PkgWatt	(1ULL << 21)
-#define	BIC_CorWatt	(1ULL << 22)
-#define	BIC_GFXWatt	(1ULL << 23)
-#define	BIC_PkgCnt	(1ULL << 24)
-#define	BIC_RAMWatt	(1ULL << 27)
-#define	BIC_PKG__	(1ULL << 28)
-#define	BIC_RAM__	(1ULL << 29)
-#define	BIC_Pkg_J	(1ULL << 30)
-#define	BIC_Cor_J	(1ULL << 31)
-#define	BIC_GFX_J	(1ULL << 30)
-#define	BIC_RAM_J	(1ULL << 31)
-#define	BIC_Core	(1ULL << 32)
-#define	BIC_CPU		(1ULL << 33)
-#define	BIC_Mod_c6	(1ULL << 34)
+#define	BIC_Pkgpc8	(1ULL << 21)
+#define	BIC_Pkgpc9	(1ULL << 22)
+#define	BIC_Pkgpc10	(1ULL << 23)
+#define	BIC_PkgWatt	(1ULL << 24)
+#define	BIC_CorWatt	(1ULL << 25)
+#define	BIC_GFXWatt	(1ULL << 26)
+#define	BIC_PkgCnt	(1ULL << 27)
+#define	BIC_RAMWatt	(1ULL << 28)
+#define	BIC_PKG__	(1ULL << 29)
+#define	BIC_RAM__	(1ULL << 30)
+#define	BIC_Pkg_J	(1ULL << 31)
+#define	BIC_Cor_J	(1ULL << 32)
+#define	BIC_GFX_J	(1ULL << 33)
+#define	BIC_RAM_J	(1ULL << 34)
+#define	BIC_Core	(1ULL << 35)
+#define	BIC_CPU		(1ULL << 36)
+#define	BIC_Mod_c6	(1ULL << 37)
 
 unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
 unsigned long long bic_present;
 
 #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
 #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
+#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
 
 /*
  * bic_lookup
@@ -539,19 +541,20 @@ void print_header(void)
 		outp += sprintf(outp, "\tCPUGFX%%");
 	}
 
-	if (do_pc2)
+	if (DO_BIC(BIC_Pkgpc2))
 		outp += sprintf(outp, "\tPkg%%pc2");
-	if (do_pc3)
+	if (DO_BIC(BIC_Pkgpc3))
 		outp += sprintf(outp, "\tPkg%%pc3");
-	if (do_pc6)
+	if (DO_BIC(BIC_Pkgpc6))
 		outp += sprintf(outp, "\tPkg%%pc6");
-	if (do_pc7)
+	if (DO_BIC(BIC_Pkgpc7))
 		outp += sprintf(outp, "\tPkg%%pc7");
-	if (do_c8_c9_c10) {
+	if (DO_BIC(BIC_Pkgpc8))
 		outp += sprintf(outp, "\tPkg%%pc8");
+	if (DO_BIC(BIC_Pkgpc9))
 		outp += sprintf(outp, "\tPkg%%pc9");
+	if (DO_BIC(BIC_Pkgpc10))
 		outp += sprintf(outp, "\tPk%%pc10");
-	}
 
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
@@ -644,11 +647,11 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "CPU + GFX: %016llX\n", p->pkg_both_core_gfxe_c0);
 
 		outp += sprintf(outp, "pc2: %016llX\n", p->pc2);
-		if (do_pc3)
+		if (DO_BIC(BIC_Pkgpc3))
 			outp += sprintf(outp, "pc3: %016llX\n", p->pc3);
-		if (do_pc6)
+		if (DO_BIC(BIC_Pkgpc6))
 			outp += sprintf(outp, "pc6: %016llX\n", p->pc6);
-		if (do_pc7)
+		if (DO_BIC(BIC_Pkgpc7))
 			outp += sprintf(outp, "pc7: %016llX\n", p->pc7);
 		outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
 		outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
@@ -827,19 +830,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/tsc);
 	}
 
-	if (do_pc2)
+	if (DO_BIC(BIC_Pkgpc2))
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/tsc);
-	if (do_pc3)
+	if (DO_BIC(BIC_Pkgpc3))
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/tsc);
-	if (do_pc6)
+	if (DO_BIC(BIC_Pkgpc6))
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/tsc);
-	if (do_pc7)
+	if (DO_BIC(BIC_Pkgpc7))
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/tsc);
-	if (do_c8_c9_c10) {
+	if (DO_BIC(BIC_Pkgpc8))
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/tsc);
+	if (DO_BIC(BIC_Pkgpc9))
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/tsc);
+	if (DO_BIC(BIC_Pkgpc10))
 		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/tsc);
-	}
 
 	/*
  	 * If measurement interval exceeds minimum RAPL Joule Counter range,
@@ -949,11 +953,11 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 		old->pkg_both_core_gfxe_c0 = new->pkg_both_core_gfxe_c0 - old->pkg_both_core_gfxe_c0;
 	}
 	old->pc2 = new->pc2 - old->pc2;
-	if (do_pc3)
+	if (DO_BIC(BIC_Pkgpc3))
 		old->pc3 = new->pc3 - old->pc3;
-	if (do_pc6)
+	if (DO_BIC(BIC_Pkgpc6))
 		old->pc6 = new->pc6 - old->pc6;
-	if (do_pc7)
+	if (DO_BIC(BIC_Pkgpc7))
 		old->pc7 = new->pc7 - old->pc7;
 	old->pc8 = new->pc8 - old->pc8;
 	old->pc9 = new->pc9 - old->pc9;
@@ -1126,11 +1130,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	p->pkg_both_core_gfxe_c0 = 0;
 
 	p->pc2 = 0;
-	if (do_pc3)
+	if (DO_BIC(BIC_Pkgpc3))
 		p->pc3 = 0;
-	if (do_pc6)
+	if (DO_BIC(BIC_Pkgpc6))
 		p->pc6 = 0;
-	if (do_pc7)
+	if (DO_BIC(BIC_Pkgpc7))
 		p->pc7 = 0;
 	p->pc8 = 0;
 	p->pc9 = 0;
@@ -1204,11 +1208,11 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	}
 
 	average.packages.pc2 += p->pc2;
-	if (do_pc3)
+	if (DO_BIC(BIC_Pkgpc3))
 		average.packages.pc3 += p->pc3;
-	if (do_pc6)
+	if (DO_BIC(BIC_Pkgpc6))
 		average.packages.pc6 += p->pc6;
-	if (do_pc7)
+	if (DO_BIC(BIC_Pkgpc7))
 		average.packages.pc7 += p->pc7;
 	average.packages.pc8 += p->pc8;
 	average.packages.pc9 += p->pc9;
@@ -1266,11 +1270,11 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	}
 
 	average.packages.pc2 /= topo.num_packages;
-	if (do_pc3)
+	if (DO_BIC(BIC_Pkgpc3))
 		average.packages.pc3 /= topo.num_packages;
-	if (do_pc6)
+	if (DO_BIC(BIC_Pkgpc6))
 		average.packages.pc6 /= topo.num_packages;
-	if (do_pc7)
+	if (DO_BIC(BIC_Pkgpc7))
 		average.packages.pc7 /= topo.num_packages;
 
 	average.packages.pc8 /= topo.num_packages;
@@ -1448,10 +1452,10 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_PKG_BOTH_CORE_GFXE_C0_RES, &p->pkg_both_core_gfxe_c0))
 			return -13;
 	}
-	if (do_pc3)
+	if (DO_BIC(BIC_Pkgpc3))
 		if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
 			return -9;
-	if (do_pc6) {
+	if (DO_BIC(BIC_Pkgpc6)) {
 		if (do_slm_cstates) {
 			if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6))
 				return -10;
@@ -1461,20 +1465,22 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		}
 	}
 
-	if (do_pc2)
+	if (DO_BIC(BIC_Pkgpc2))
 		if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2))
 			return -11;
-	if (do_pc7)
+	if (DO_BIC(BIC_Pkgpc7))
 		if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7))
 			return -12;
-	if (do_c8_c9_c10) {
+	if (DO_BIC(BIC_Pkgpc8))
 		if (get_msr(cpu, MSR_PKG_C8_RESIDENCY, &p->pc8))
 			return -13;
+	if (DO_BIC(BIC_Pkgpc9))
 		if (get_msr(cpu, MSR_PKG_C9_RESIDENCY, &p->pc9))
 			return -13;
+	if (DO_BIC(BIC_Pkgpc10))
 		if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10))
 			return -13;
-	}
+
 	if (do_rapl & RAPL_PKG) {
 		if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
 			return -13;
@@ -3824,17 +3830,27 @@ void process_cpuid()
 		BIC_PRESENT(BIC_CPU_c7);
 
 	do_irtl_snb = has_snb_msrs(family, model);
-	do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
-	do_pc3 = (pkg_cstate_limit >= PCL__3);
-	do_pc6 = (pkg_cstate_limit >= PCL__6);
-	do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7);
+	if (do_snb_cstates && (pkg_cstate_limit >= PCL__2))
+		BIC_PRESENT(BIC_Pkgpc2);
+	if (pkg_cstate_limit >= PCL__3)
+		BIC_PRESENT(BIC_Pkgpc3);
+	if (pkg_cstate_limit >= PCL__6)
+		BIC_PRESENT(BIC_Pkgpc6);
+	if (do_snb_cstates && (pkg_cstate_limit >= PCL__7))
+		BIC_PRESENT(BIC_Pkgpc7);
 	if (has_slv_msrs(family, model)) {
-		do_pc2 = do_pc3 = do_pc7 = 0;
-		do_pc6 = 1;
+		BIC_NOT_PRESENT(BIC_Pkgpc2);
+		BIC_NOT_PRESENT(BIC_Pkgpc3);
+		BIC_PRESENT(BIC_Pkgpc6);
+		BIC_NOT_PRESENT(BIC_Pkgpc7);
 		BIC_PRESENT(BIC_Mod_c6);
 		use_c1_residency_msr = 1;
 	}
-	do_c8_c9_c10 = has_hsw_msrs(family, model);
+	if (has_hsw_msrs(family, model)) {
+		BIC_PRESENT(BIC_Pkgpc8);
+		BIC_PRESENT(BIC_Pkgpc9);
+		BIC_PRESENT(BIC_Pkgpc10);
+	}
 	do_irtl_hsw = has_hsw_msrs(family, model);
 	do_skl_residency = has_skl_msrs(family, model);
 	do_slm_cstates = is_slm(family, model);
@@ -3981,7 +3997,7 @@ void topology_probe()
 	if (debug > 1)
 		fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
 			max_core_id, topo.num_cores_per_pkg);
-	if (debug && !summary_only && topo.num_cores_per_pkg > 1)
+	if (!summary_only && topo.num_cores_per_pkg > 1)
 		BIC_PRESENT(BIC_Core);
 
 	topo.num_packages = max_package_id + 1;
@@ -4282,7 +4298,7 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width,
 void parse_add_command(char *add_command)
 {
 	int msr_num = 0;
-	char name_buffer[NAME_BYTES];
+	char name_buffer[NAME_BYTES] = "";
 	int width = 64;
 	int fail = 0;
 	enum counter_scope scope = SCOPE_CPU;
-- 
GitLab


From 311f77708f362c1af0a999ba5ebbbc062fdc5601 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 16 Feb 2017 23:48:50 -0500
Subject: [PATCH 358/898] x86: intel-family.h: Add GEMINI_LAKE SOC

Cc: x86@kernel.org
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/include/asm/intel-family.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 8167fdb67ae8..9814db42b790 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -59,6 +59,7 @@
 #define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
 #define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Anniedale */
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C
+#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
 #define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
 
 /* Xeon Phi */
-- 
GitLab


From ac01ac1371d01beb02827f89fff9aac9d7941e91 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 27 Jan 2017 01:45:35 -0500
Subject: [PATCH 359/898] tools/power turbostat: initial Gemini Lake SOC
 support

Gemini Lake is similar to Apollo Lake (Broxton/Goldmont)

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 4b04ba86e44f..819d67fbb6ca 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2535,6 +2535,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		pkg_cstate_limits = phi_pkg_cstate_limits;
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
 	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 		pkg_cstate_limits = bxt_pkg_cstate_limits;
 		break;
@@ -3018,6 +3019,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 		}
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
 		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
 		if (rapl_joules)
 			BIC_PRESENT(BIC_Pkg_J);
@@ -3361,6 +3363,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
 	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 		return 1;
 	}
@@ -3392,6 +3395,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
 		return 1;
 	}
 	return 0;
@@ -3783,6 +3787,7 @@ void process_cpuid()
 					crystal_hz = 25000000;	/* 25.0 MHz */
 					break;
 				case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+				case INTEL_FAM6_ATOM_GEMINI_LAKE:
 					crystal_hz = 19200000;	/* 19.2 MHz */
 					break;
 				default:
-- 
GitLab


From 7170a374377d7c70d63a2d3eb38f8fe32e6ffadd Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 27 Jan 2017 02:13:27 -0500
Subject: [PATCH 360/898] tools/power turbostat: Denverton: use HW CC1 counter,
 skip C3, C7

The CC1 column in tubostat can be computed by subtracting
the core c-state residency countes from the total Cx residency.

CC1 = (Idle_time_as_measured by MPERF) - (all core C-states with
residency counters)

However, as the underlying counter reads are not atomic,
error can be noticed in this calculations, especially
when the numbers are small.

Denverton has a hardware CC1 residency counter
to improve the accuracy of the cc1 statistic -- use it.

At the same time, Denverton has no concept of CC3, PC3, CC7, PC7,
so skip collecting and printing those columns.

Finally, a note of clarification.
Turbostat prints the standard PC2 residency counter,
but on Denverton hardware, that actually means PC1E.
Turbostat prints the standard PC6 residency counter,
but on Denverton hardware, that actually means PC2.

At this point, we document that differnce in this commit message,
rather than adding a quirk to the software.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 819d67fbb6ca..1010135ee973 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2572,6 +2572,18 @@ int has_slv_msrs(unsigned int family, unsigned int model)
 	}
 	return 0;
 }
+int is_dnv(unsigned int family, unsigned int model)
+{
+
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_ATOM_DENVERTON:
+		return 1;
+	}
+	return 0;
+}
 
 int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
@@ -3851,6 +3863,14 @@ void process_cpuid()
 		BIC_PRESENT(BIC_Mod_c6);
 		use_c1_residency_msr = 1;
 	}
+	if (is_dnv(family, model)) {
+		BIC_PRESENT(BIC_CPU_c1);
+		BIC_NOT_PRESENT(BIC_CPU_c3);
+		BIC_NOT_PRESENT(BIC_Pkgpc3);
+		BIC_NOT_PRESENT(BIC_CPU_c7);
+		BIC_NOT_PRESENT(BIC_Pkgpc7);
+		use_c1_residency_msr = 1;
+	}
 	if (has_hsw_msrs(family, model)) {
 		BIC_PRESENT(BIC_Pkgpc8);
 		BIC_PRESENT(BIC_Pkgpc9);
-- 
GitLab


From 34c7619762f7b4ebbd5157b312e6022b725c031e Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 27 Jan 2017 02:36:41 -0500
Subject: [PATCH 361/898] tools/power turbostat: skip unused counters on SKX

Skip these four counters on SKX, as they are always zero:
cc3, pc3
cc7, pc7

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 1010135ee973..8c437115d41b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2584,6 +2584,18 @@ int is_dnv(unsigned int family, unsigned int model)
 	}
 	return 0;
 }
+int is_skx(unsigned int family, unsigned int model)
+{
+
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_SKYLAKE_X:
+		return 1;
+	}
+	return 0;
+}
 
 int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
@@ -3871,6 +3883,12 @@ void process_cpuid()
 		BIC_NOT_PRESENT(BIC_Pkgpc7);
 		use_c1_residency_msr = 1;
 	}
+	if (is_skx(family, model)) {
+		BIC_NOT_PRESENT(BIC_CPU_c3);
+		BIC_NOT_PRESENT(BIC_Pkgpc3);
+		BIC_NOT_PRESENT(BIC_CPU_c7);
+		BIC_NOT_PRESENT(BIC_Pkgpc7);
+	}
 	if (has_hsw_msrs(family, model)) {
 		BIC_PRESENT(BIC_Pkgpc8);
 		BIC_PRESENT(BIC_Pkgpc9);
-- 
GitLab


From 31e07522be566cd039ff7a770550076cc1707a0c Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 31 Jan 2017 23:07:49 -0500
Subject: [PATCH 362/898] tools/power turbostat: fix decoding for GLM, DNV, SKX
 turbo-ratio limits

Newer processors do not hard-code the the number of cpus in each bin
to {1, 2, 3, 4, 5, 6, 7, 8}  Rather, they can specify any number
of CPUS in each of the 8 bins:

eg.

...
37 * 100.0 = 3600.0 MHz max turbo 4 active cores
38 * 100.0 = 3700.0 MHz max turbo 3 active cores
39 * 100.0 = 3800.0 MHz max turbo 2 active cores
39 * 100.0 = 3900.0 MHz max turbo 1 active cores

could now look something like this:

...
37 * 100.0 = 3600.0 MHz max turbo 16 active cores
38 * 100.0 = 3700.0 MHz max turbo 8 active cores
39 * 100.0 = 3800.0 MHz max turbo 4 active cores
39 * 100.0 = 3900.0 MHz max turbo 2 active cores

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 90 ++++++++++++++++++++-------
 1 file changed, 67 insertions(+), 23 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 8c437115d41b..67a275882a8d 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1671,56 +1671,84 @@ dump_ivt_turbo_ratio_limits(void)
 			ratio, bclk, ratio * bclk);
 	return;
 }
+int has_turbo_ratio_group_limits(int family, int model)
+{
+
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_ATOM_DENVERTON:
+		return 1;
+	}
+	return 0;
+}
 
 static void
-dump_nhm_turbo_ratio_limits(void)
+dump_turbo_ratio_limits(int family, int model)
 {
-	unsigned long long msr;
-	unsigned int ratio;
+	unsigned long long msr, core_counts;
+	unsigned int ratio, group_size;
 
 	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
-
 	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr);
 
+	if (has_turbo_ratio_group_limits(family, model)) {
+		get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts);
+		fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, core_counts);
+	} else {
+		core_counts = 0x0807060504030201;
+	}
+
 	ratio = (msr >> 56) & 0xFF;
+	group_size = (core_counts >> 56) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 8 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 
 	ratio = (msr >> 48) & 0xFF;
+	group_size = (core_counts >> 48) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 7 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 
 	ratio = (msr >> 40) & 0xFF;
+	group_size = (core_counts >> 40) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 6 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 
 	ratio = (msr >> 32) & 0xFF;
+	group_size = (core_counts >> 32) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 5 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 
 	ratio = (msr >> 24) & 0xFF;
+	group_size = (core_counts >> 24) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 4 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 
 	ratio = (msr >> 16) & 0xFF;
+	group_size = (core_counts >> 16) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 3 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 
 	ratio = (msr >> 8) & 0xFF;
+	group_size = (core_counts >> 8) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 2 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 
 	ratio = (msr >> 0) & 0xFF;
+	group_size = (core_counts >> 0) & 0xFF;
 	if (ratio)
-		fprintf(outf, "%d * %.1f = %.1f MHz max turbo 1 active cores\n",
-			ratio, bclk, ratio * bclk);
+		fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n",
+			ratio, bclk, ratio * bclk, group_size);
 	return;
 }
 
@@ -2597,7 +2625,7 @@ int is_skx(unsigned int family, unsigned int model)
 	return 0;
 }
 
-int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
+int has_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
 	if (has_slv_msrs(family, model))
 		return 0;
@@ -2668,6 +2696,22 @@ int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 0;
 	}
 }
+int has_glm_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	if (family != 6)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_SKYLAKE_X:
+		return 1;
+	default:
+		return 0;
+	}
+}
 int has_config_tdp(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
@@ -2714,8 +2758,8 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
 	if (has_ivt_turbo_ratio_limit(family, model))
 		dump_ivt_turbo_ratio_limits();
 
-	if (has_nhm_turbo_ratio_limit(family, model))
-		dump_nhm_turbo_ratio_limits();
+	if (has_turbo_ratio_limit(family, model))
+		dump_turbo_ratio_limits(family, model);
 
 	if (has_atom_turbo_ratio_limit(family, model))
 		dump_atom_turbo_ratio_limits();
-- 
GitLab


From ade0ebacdf03591b3dab642e6e92da60c20ebdb3 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 10 Feb 2017 01:56:47 -0500
Subject: [PATCH 363/898] tools/power turbostat: skip unused counters on BDX

Skip these two counters on BDX, as they are always zero:
cc7, pc7

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 67a275882a8d..334c4c29d4b5 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2612,6 +2612,19 @@ int is_dnv(unsigned int family, unsigned int model)
 	}
 	return 0;
 }
+int is_bdx(unsigned int family, unsigned int model)
+{
+
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_BROADWELL_X:
+	case INTEL_FAM6_BROADWELL_XEON_D:
+		return 1;
+	}
+	return 0;
+}
 int is_skx(unsigned int family, unsigned int model)
 {
 
@@ -3933,6 +3946,10 @@ void process_cpuid()
 		BIC_NOT_PRESENT(BIC_CPU_c7);
 		BIC_NOT_PRESENT(BIC_Pkgpc7);
 	}
+	if (is_bdx(family, model)) {
+		BIC_NOT_PRESENT(BIC_CPU_c7);
+		BIC_NOT_PRESENT(BIC_Pkgpc7);
+	}
 	if (has_hsw_msrs(family, model)) {
 		BIC_PRESENT(BIC_Pkgpc8);
 		BIC_PRESENT(BIC_Pkgpc9);
-- 
GitLab


From 495c7654ccfb771d19ce1b9fbc7be21e45b14636 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Wed, 8 Feb 2017 02:41:51 -0500
Subject: [PATCH 364/898] tools/power turbostat: extend --add option to accept
 /sys path

Previously, the --add option could specify only an MSR.

Here is is extended so an arbitrary /sys attribute,
as specified by an absolute file path name.

sudo ./turbostat --add /sys/devices/system/cpu/cpu0/cpuidle/state5/usage

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 92 ++++++++++++++++++++-------
 1 file changed, 69 insertions(+), 23 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 334c4c29d4b5..841f837e317f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -138,6 +138,7 @@ unsigned int has_misc_feature_control;
  * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters
  */
 #define	NAME_BYTES 20
+#define PATH_BYTES 128
 
 int backwards_count;
 char *progname;
@@ -213,6 +214,7 @@ enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT};
 struct msr_counter {
 	unsigned int msr_num;
 	char name[NAME_BYTES];
+	char path[PATH_BYTES];
 	unsigned int width;
 	enum counter_type type;
 	enum counter_format format;
@@ -344,7 +346,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "Bzy_MHz" },
 	{ 0x0, "TSC_MHz" },
 	{ 0x0, "IRQ" },
-	{ 0x0, "SMI", 32, 0, FORMAT_DELTA, NULL},
+	{ 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL},
 	{ 0x0, "Busy%" },
 	{ 0x0, "CPU%c1" },
 	{ 0x0, "CPU%c3" },
@@ -1307,6 +1309,51 @@ static unsigned long long rdtsc(void)
 	return low | ((unsigned long long)high) << 32;
 }
 
+/*
+ * Open a file, and exit on failure
+ */
+FILE *fopen_or_die(const char *path, const char *mode)
+{
+	FILE *filep = fopen(path, mode);
+
+	if (!filep)
+		err(1, "%s: open failed", path);
+	return filep;
+}
+/*
+ * snapshot_sysfs_counter()
+ *
+ * return snapshot of given counter
+ */
+unsigned long long snapshot_sysfs_counter(char *path)
+{
+	FILE *fp;
+	int retval;
+	unsigned long long counter;
+
+	fp = fopen_or_die(path, "r");
+
+	retval = fscanf(fp, "%lld", &counter);
+	if (retval != 1)
+		err(1, "snapshot_sysfs_counter(%s)", path);
+
+	fclose(fp);
+
+	return counter;
+}
+
+int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
+{
+	if (mp->msr_num != 0) {
+		if (get_msr(cpu, mp->msr_num, counterp))
+			return -1;
+	} else {
+		*counterp = snapshot_sysfs_counter(mp->path);
+	}
+
+	return 0;
+}
+
 /*
  * get_counters(...)
  * migrate to cpu
@@ -1397,11 +1444,10 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	}
 
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
-		if (get_msr(cpu, mp->msr_num, &t->counter[i]))
+		if (get_mp(cpu, mp, &t->counter[i]))
 			return -10;
 	}
 
-
 	/* collect core counters only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
@@ -1434,7 +1480,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	}
 
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
-		if (get_msr(cpu, mp->msr_num, &c->counter[i]))
+		if (get_mp(cpu, mp, &c->counter[i]))
 			return -10;
 	}
 
@@ -1524,7 +1570,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		p->gfx_mhz = gfx_cur_mhz;
 
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
-		if (get_msr(cpu, mp->msr_num, &p->counter[i]))
+		if (get_mp(cpu, mp, &p->counter[i]))
 			return -10;
 	}
 
@@ -2013,16 +2059,6 @@ void free_all_buffers(void)
 	free(irqs_per_cpu);
 }
 
-/*
- * Open a file, and exit on failure
- */
-FILE *fopen_or_die(const char *path, const char *mode)
-{
-	FILE *filep = fopen(path, mode);
-	if (!filep)
-		err(1, "%s: open failed", path);
-	return filep;
-}
 
 /*
  * Parse a file containing a single int.
@@ -2581,7 +2617,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	return 1;
 }
 /*
- * SLV client has supporet for unique MSRs:
+ * SLV client has support for unique MSRs:
  *
  * MSR_CC6_DEMOTION_POLICY_CONFIG
  * MSR_MC6_DEMOTION_POLICY_CONFIG
@@ -4342,9 +4378,9 @@ void print_version() {
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
-int add_counter(unsigned int msr_num, char *name, unsigned int width,
-	enum counter_scope scope, enum counter_type type,
-	enum counter_format format)
+int add_counter(unsigned int msr_num, char *path, char *name,
+	unsigned int width, enum counter_scope scope,
+	enum counter_type type, enum counter_format format)
 {
 	struct msr_counter *msrp;
 
@@ -4356,6 +4392,8 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width,
 
 	msrp->msr_num = msr_num;
 	strncpy(msrp->name, name, NAME_BYTES);
+	if (path)
+		strncpy(msrp->path, path, PATH_BYTES);
 	msrp->width = width;
 	msrp->type = type;
 	msrp->format = format;
@@ -4402,6 +4440,7 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width,
 void parse_add_command(char *add_command)
 {
 	int msr_num = 0;
+	char *path = NULL;
 	char name_buffer[NAME_BYTES] = "";
 	int width = 64;
 	int fail = 0;
@@ -4417,6 +4456,11 @@ void parse_add_command(char *add_command)
 		if (sscanf(add_command, "msr%d", &msr_num) == 1)
 			goto next;
 
+		if (*add_command == '/') {
+			path = add_command;
+			goto next;
+		}
+
 		if (sscanf(add_command, "u%d", &width) == 1) {
 			if ((width == 32) || (width == 64))
 				goto next;
@@ -4466,12 +4510,14 @@ void parse_add_command(char *add_command)
 
 next:
 		add_command = strchr(add_command, ',');
-		if (add_command)
+		if (add_command) {
+			*add_command = '\0';
 			add_command++;
+		}
 
 	}
-	if (msr_num == 0) {
-		fprintf(stderr, "--add: (msrDDD | msr0xXXX) required\n");
+	if ((msr_num == 0) && (path == NULL)) {
+		fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter ) required\n");
 		fail++;
 	}
 
@@ -4495,7 +4541,7 @@ void parse_add_command(char *add_command)
 		}
 	}
 
-	if (add_counter(msr_num, name_buffer, width, scope, type, format))
+	if (add_counter(msr_num, path, name_buffer, width, scope, type, format))
 		fail++;
 
 	if (fail) {
-- 
GitLab


From 41618e63f2a869902f8534f0db337e85d6bd04c8 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 9 Feb 2017 18:25:22 -0500
Subject: [PATCH 365/898] tools/power turbostat: print sysfs C-state stats

When turbostat shows % of time in a CPU idle power state,
it has always been showing information from underlying
hardware residency counters.

While this reflects what the hardware is doing, and is thus
useful for understanding the hardware,
it doesn't directly tell us what Linux requested --
which is useful for tuning Linux itself.

Here we add columns to turbostat to show the
Linux cpuidle sub-system statistics:
/sys/devices/system/cpu/cpu*/cpuidle/state*/*

The first group of columns are the "usage", which is the
number of times software requested that C-state in the
measurement interval. eg C1 below.

The second group of columns are the "time", which is the percentage
of the measurement interval time that software has requested
the specified C-state. eg C1% below.

These software counters can be compared to the underlying
hardware residency counters (eg CPU%c1	CPU%c3	CPU%c6	CPU%c7)
to compare what sofware requested to what the hardware delivered.

These sysfs attributes are discovered when turbostat starts,
rather than being "built in".  So the --show and --hide
parameters do not know about these dynamic column names.
However "--show sysfs" and "--hide sysfs" act on the
entire group of columns:

turbostat --show sysfs
...
cpu4: POLL: CPUIDLE CORE POLL IDLE
cpu4: C1: MWAIT 0x00
cpu4: C1E: MWAIT 0x01
cpu4: C3: MWAIT 0x10
cpu4: C6: MWAIT 0x20
cpu4: C7s: MWAIT 0x32
...
C1 	C1E	C3 	C6 	C7s	C1% 	C1E%	C3%	C6% 	C7s%
3	6	5	1	188	0.00	0.02	0.00	0.00	99.93
0	6	5	0	58	0.00	0.16	0.02	0.00	99.70
0	0	0	0	9	0.00	0.00	0.00	0.00	99.96
0	0	0	1	24	0.00	0.00	0.00	0.02	99.93
0	0	0	0	9	0.00	0.00	0.00	0.00	99.97
0	0	0	0	32	0.00	0.00	0.00	0.00	99.96
0	0	0	0	7	0.00	0.00	0.00	0.00	99.98
2	0	0	0	36	0.00	0.00	0.00	0.00	99.97
1	0	0	0	13	0.00	0.00	0.00	0.00	99.98

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.8 |   4 +-
 tools/power/x86/turbostat/turbostat.c | 161 +++++++++++++++++++++++---
 2 files changed, 147 insertions(+), 18 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index a08de27713e0..e31b7213fd45 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -47,9 +47,9 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 		default: delta
 .fi
 .PP
-\fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.
+\fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
 .PP
-\fB--show column\fP show only the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.
+\fB--show column\fP show only the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
 .PP
 \fB--Dump\fP displays the raw counter values.
 .PP
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 841f837e317f..eb6cc8ccef06 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -208,7 +208,7 @@ struct pkg_data {
 #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
 
 enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
-enum counter_type {COUNTER_CYCLES, COUNTER_SECONDS};
+enum counter_type {COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC};
 enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT};
 
 struct msr_counter {
@@ -222,6 +222,7 @@ struct msr_counter {
 	unsigned int flags;
 #define	FLAGS_HIDE	(1 << 0)
 #define	FLAGS_SHOW	(1 << 1)
+#define	SYSFS_PERCPU	(1 << 1)
 };
 
 struct sys_counters {
@@ -379,6 +380,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "Core" },
 	{ 0x0, "CPU" },
 	{ 0x0, "Mod%c6" },
+	{ 0x0, "sysfs" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -420,9 +422,10 @@ struct msr_counter bic[] = {
 #define	BIC_Core	(1ULL << 35)
 #define	BIC_CPU		(1ULL << 36)
 #define	BIC_Mod_c6	(1ULL << 37)
+#define	BIC_sysfs	(1ULL << 38)
 
 unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
-unsigned long long bic_present;
+unsigned long long bic_present = BIC_sysfs;
 
 #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
 #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
@@ -489,9 +492,6 @@ void print_header(void)
 	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "\tSMI");
 
-	if (DO_BIC(BIC_CPU_c1))
-		outp += sprintf(outp, "\tCPU%%c1");
-
 	for (mp = sys.tp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
@@ -499,10 +499,12 @@ void print_header(void)
 			else
 				outp += sprintf(outp, "\t%10.10s", mp->name);
 		} else {
-			outp += sprintf(outp, "\t%-7.7s", mp->name);
+			outp += sprintf(outp, "\t%s", mp->name);
 		}
 	}
 
+	if (DO_BIC(BIC_CPU_c1))
+		outp += sprintf(outp, "\tCPU%%c1");
 	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
 		outp += sprintf(outp, "\tCPU%%c3");
 	if (DO_BIC(BIC_CPU_c6))
@@ -523,7 +525,7 @@ void print_header(void)
 			else
 				outp += sprintf(outp, "\t%10.10s", mp->name);
 		} else {
-			outp += sprintf(outp, "\t%-7.7s", mp->name);
+			outp += sprintf(outp, "\t%s", mp->name);
 		}
 	}
 
@@ -592,7 +594,7 @@ void print_header(void)
 			else
 				outp += sprintf(outp, "\t%10.10s", mp->name);
 		} else {
-			outp += sprintf(outp, "\t%-7.7s", mp->name);
+			outp += sprintf(outp, "\t%s", mp->name);
 		}
 	}
 
@@ -753,10 +755,6 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "\t%d", t->smi_count);
 
-	/* C1 */
-	if (DO_BIC(BIC_CPU_c1))
-		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/tsc);
-
 	/* Added counters */
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
@@ -767,10 +765,18 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		} else if (mp->format == FORMAT_DELTA) {
 			outp += sprintf(outp, "\t%lld", t->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
-			outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/tsc);
+			if (mp->type == COUNTER_USEC)
+				outp += sprintf(outp, "\t%.2f", t->counter[i]/interval_float/10000);
+			else
+				outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/tsc);
 		}
 	}
 
+	/* C1 */
+	if (DO_BIC(BIC_CPU_c1))
+		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/tsc);
+
+
 	/* print per-core data only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
@@ -1286,6 +1292,8 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
+		if (mp->flags & SYSFS_PERCPU && mp->type == COUNTER_ITEMS)
+			continue;
 		average.threads.counter[i] /= topo.num_cpus;
 	}
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
@@ -1348,7 +1356,16 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
 		if (get_msr(cpu, mp->msr_num, counterp))
 			return -1;
 	} else {
-		*counterp = snapshot_sysfs_counter(mp->path);
+		char path[128];
+
+		if (mp->flags & SYSFS_PERCPU) {
+			sprintf(path, "/sys/devices/system/cpu/cpu%d/%s",
+				 cpu, mp->path);
+
+			*counterp = snapshot_sysfs_counter(path);
+		} else {
+			*counterp = snapshot_sysfs_counter(mp->path);
+		}
 	}
 
 	return 0;
@@ -2822,6 +2839,48 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
 	dump_nhm_cst_cfg();
 }
 
+static void
+dump_sysfs_cstate_config(void)
+{
+	char path[64];
+	char name_buf[16];
+	char desc[64];
+	FILE *input;
+	int state;
+	char *sp;
+
+	if (!DO_BIC(BIC_sysfs))
+		return;
+
+	for (state = 0; state < 10; ++state) {
+
+		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
+			base_cpu, state);
+		input = fopen(path, "r");
+		if (input == NULL)
+			continue;
+		fgets(name_buf, sizeof(name_buf), input);
+
+		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
+		sp = strchr(name_buf, '-');
+		if (!sp)
+			sp = strchrnul(name_buf, '\n');
+		*sp = '\0';
+
+		fclose(input);
+
+		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
+			base_cpu, state);
+		input = fopen(path, "r");
+		if (input == NULL)
+			continue;
+		fgets(desc, sizeof(desc), input);
+
+		fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc);
+		fclose(input);
+	}
+}
+
 
 /*
  * print_epb()
@@ -4008,6 +4067,9 @@ void process_cpuid()
 	if (!quiet)
 		dump_cstate_pstate_config_info(family, model);
 
+	if (!quiet)
+		dump_sysfs_cstate_config();
+
 	if (has_skl_msrs(family, model))
 		calculate_tsc_tweak();
 
@@ -4380,7 +4442,7 @@ void print_version() {
 
 int add_counter(unsigned int msr_num, char *path, char *name,
 	unsigned int width, enum counter_scope scope,
-	enum counter_type type, enum counter_format format)
+	enum counter_type type, enum counter_format format, int flags)
 {
 	struct msr_counter *msrp;
 
@@ -4397,6 +4459,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 	msrp->width = width;
 	msrp->type = type;
 	msrp->format = format;
+	msrp->flags = flags;
 
 	switch (scope) {
 
@@ -4486,6 +4549,10 @@ void parse_add_command(char *add_command)
 			type = COUNTER_SECONDS;
 			goto next;
 		}
+		if (!strncmp(add_command, "usec", strlen("usec"))) {
+			type = COUNTER_USEC;
+			goto next;
+		}
 		if (!strncmp(add_command, "raw", strlen("raw"))) {
 			format = FORMAT_RAW;
 			goto next;
@@ -4541,7 +4608,7 @@ void parse_add_command(char *add_command)
 		}
 	}
 
-	if (add_counter(msr_num, path, name_buffer, width, scope, type, format))
+	if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0))
 		fail++;
 
 	if (fail) {
@@ -4549,6 +4616,65 @@ void parse_add_command(char *add_command)
 		exit(1);
 	}
 }
+
+void probe_sysfs(void)
+{
+	char path[64];
+	char name_buf[16];
+	FILE *input;
+	int state;
+	char *sp;
+
+	if (!DO_BIC(BIC_sysfs))
+		return;
+
+	for (state = 10; state > 0; --state) {
+
+		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
+			base_cpu, state);
+		input = fopen(path, "r");
+		if (input == NULL)
+			continue;
+		fgets(name_buf, sizeof(name_buf), input);
+
+		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
+		sp = strchr(name_buf, '-');
+		if (!sp)
+			sp = strchrnul(name_buf, '\n');
+		*sp = '%';
+		*(sp + 1) = '\0';
+
+		fclose(input);
+
+		sprintf(path, "cpuidle/state%d/time", state);
+
+		add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_USEC,
+				FORMAT_PERCENT, SYSFS_PERCPU);
+	}
+
+	for (state = 10; state > 0; --state) {
+
+		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
+			base_cpu, state);
+		input = fopen(path, "r");
+		if (input == NULL)
+			continue;
+		fgets(name_buf, sizeof(name_buf), input);
+		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
+		sp = strchr(name_buf, '-');
+		if (!sp)
+			sp = strchrnul(name_buf, '\n');
+		*sp = '\0';
+		fclose(input);
+
+		sprintf(path, "cpuidle/state%d/usage", state);
+
+		add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS,
+				FORMAT_DELTA, SYSFS_PERCPU);
+	}
+
+}
+
 /*
  * HIDE_LIST - hide this list of counters, show the rest [default]
  * SHOW_LIST - show this list of counters, hide the rest
@@ -4581,6 +4707,7 @@ void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
 	 *  multiple invocations simply clear more bits in enabled mask
 	 */
 	bic_enabled &= ~bic_lookup(optarg);
+
 }
 
 void cmdline(int argc, char **argv)
@@ -4682,6 +4809,8 @@ int main(int argc, char **argv)
 	if (!quiet)
 		print_version();
 
+	probe_sysfs();
+
 	turbostat_init();
 
 	/* dump counters and exit */
-- 
GitLab


From 1ef7d21afe2197013aefe0e93641aa2c5a9ac3db Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Fri, 10 Feb 2017 23:54:15 -0500
Subject: [PATCH 366/898] tools/power turbostat: add --cpu parameter

With the --cpu parameter, turbostat prints only lines
for the specified set of CPUs:

sudo ./turbostat --quiet --show Core,CPU --cpu 0,1,3..5,6-7
	Core	CPU
	-	-
	0	0
	0	4
	1	1
	1	5
	2	6
	3	3
	3	7

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.8 |  2 +
 tools/power/x86/turbostat/turbostat.c | 95 ++++++++++++++++++++++++++-
 2 files changed, 95 insertions(+), 2 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index e31b7213fd45..efe6a7147ff2 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -47,6 +47,8 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 		default: delta
 .fi
 .PP
+\fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  cpu-set is a comma delimited list of cpu ranges. cpu ranges can be individual cpu numbers or start and end numbers, separated by ".." or '-'.  eg. 1,2,8,14..17,21-44
+.PP
 \fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
 .PP
 \fB--show column\fP show only the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index eb6cc8ccef06..8c965bb2f461 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -143,8 +143,9 @@ unsigned int has_misc_feature_control;
 int backwards_count;
 char *progname;
 
-cpu_set_t *cpu_present_set, *cpu_affinity_set;
-size_t cpu_present_setsize, cpu_affinity_setsize;
+#define CPU_SUBSET_MAXCPUS	1024	/* need to use before probe... */
+cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset;
+size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
 #define MAX_ADDED_COUNTERS 16
 
 struct thread_data {
@@ -700,6 +701,11 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		return 0;
 
+	/*if not summary line and --cpu is used */
+	if ((t != &average.threads) &&
+		(cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset)))
+		return 0;
+
 	interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
 
 	tsc = t->tsc * tsc_tweak;
@@ -4096,6 +4102,7 @@ void help()
 	"to print statistics, until interrupted.\n"
 	"--add		add a counter\n"
 	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
+	"--cpu	cpu-set	limit output to summary plus cpu-set cpu-set\n"
 	"--quiet	skip decoding system configuration header\n"
 	"--interval sec	Override default 5-second measurement interval\n"
 	"--help		print this help message\n"
@@ -4158,6 +4165,15 @@ void topology_probe()
 	CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
 	for_all_proc_cpus(mark_cpu_present);
 
+	/*
+	 * Validate that all cpus in cpu_subset are also in cpu_present_set
+	 */
+	for (i = 0; i < CPU_SUBSET_MAXCPUS; ++i) {
+		if (CPU_ISSET_S(i, cpu_subset_size, cpu_subset))
+			if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set))
+				err(1, "cpu%d not present", i);
+	}
+
 	/*
 	 * Allocate and initialize cpu_affinity_set
 	 */
@@ -4675,6 +4691,77 @@ void probe_sysfs(void)
 
 }
 
+
+/*
+ * parse cpuset with following syntax
+ * 1,2,4..6,8-10 and set bits in cpu_subset
+ */
+void parse_cpu_command(char *optarg)
+{
+	unsigned int start, end;
+	char *next;
+
+	cpu_subset = CPU_ALLOC(CPU_SUBSET_MAXCPUS);
+	if (cpu_subset == NULL)
+		err(3, "CPU_ALLOC");
+	cpu_subset_size = CPU_ALLOC_SIZE(CPU_SUBSET_MAXCPUS);
+
+	CPU_ZERO_S(cpu_subset_size, cpu_subset);
+
+	next = optarg;
+
+	while (next && *next) {
+
+		if (*next == '-')	/* no negative cpu numbers */
+			goto error;
+
+		start = strtoul(next, &next, 10);
+
+		if (start >= CPU_SUBSET_MAXCPUS)
+			goto error;
+		CPU_SET_S(start, cpu_subset_size, cpu_subset);
+
+		if (*next == '\0')
+			break;
+
+		if (*next == ',') {
+			next += 1;
+			continue;
+		}
+
+		if (*next == '-') {
+			next += 1;	/* start range */
+		} else if (*next == '.') {
+			next += 1;
+			if (*next == '.')
+				next += 1;	/* start range */
+			else
+				goto error;
+		}
+
+		end = strtoul(next, &next, 10);
+		if (end <= start)
+			goto error;
+
+		while (++start <= end) {
+			if (start >= CPU_SUBSET_MAXCPUS)
+				goto error;
+			CPU_SET_S(start, cpu_subset_size, cpu_subset);
+		}
+
+		if (*next == ',')
+			next += 1;
+		else if (*next != '\0')
+			goto error;
+	}
+
+	return;
+
+error:
+	fprintf(stderr, "'--cpu %s' malformed\n", optarg);
+	exit(-1);
+}
+
 /*
  * HIDE_LIST - hide this list of counters, show the rest [default]
  * SHOW_LIST - show this list of counters, hide the rest
@@ -4716,6 +4803,7 @@ void cmdline(int argc, char **argv)
 	int option_index = 0;
 	static struct option long_options[] = {
 		{"add",		required_argument,	0, 'a'},
+		{"cpu",		required_argument,	0, 'c'},
 		{"Dump",	no_argument,		0, 'D'},
 		{"debug",	no_argument,		0, 'd'},	/* internal, not documented */
 		{"interval",	required_argument,	0, 'i'},
@@ -4741,6 +4829,9 @@ void cmdline(int argc, char **argv)
 		case 'a':
 			parse_add_command(optarg);
 			break;
+		case 'c':
+			parse_cpu_command(optarg);
+			break;
 		case 'D':
 			dump_only++;
 			break;
-- 
GitLab


From 218f0e8d5c388767be9c78fd2c5bc0a6f416d6d0 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 14 Feb 2017 22:07:52 -0500
Subject: [PATCH 367/898] tools/power turbostat: fix zero IRQ count shown in
 one-shot command mode

The IRQ column has been working for periodic mode,
but not in one-shot command mode, it shows only 0.

until now.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 8c965bb2f461..48b540a2fe81 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -619,9 +619,9 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c1: %016llX\n", t->c1);
 
 		if (DO_BIC(BIC_IRQ))
-			outp += sprintf(outp, "IRQ: %08X\n", t->irq_count);
+			outp += sprintf(outp, "IRQ: %d\n", t->irq_count);
 		if (DO_BIC(BIC_SMI))
-			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
+			outp += sprintf(outp, "SMI: %d\n", t->smi_count);
 
 		for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 			outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n",
@@ -2410,8 +2410,9 @@ int snapshot_gfx_mhz(void)
  */
 int snapshot_proc_sysfs_files(void)
 {
-	if (snapshot_proc_interrupts())
-		return 1;
+	if (DO_BIC(BIC_IRQ))
+		if (snapshot_proc_interrupts())
+			return 1;
 
 	if (DO_BIC(BIC_GFX_rc6))
 		snapshot_gfx_rc6_ms();
@@ -4391,6 +4392,7 @@ int fork_it(char **argv)
 	pid_t child_pid;
 	int status;
 
+	snapshot_proc_sysfs_files();
 	status = for_all_cpus(get_counters, EVEN_COUNTERS);
 	if (status)
 		exit(status);
@@ -4417,6 +4419,7 @@ int fork_it(char **argv)
 	 * n.b. fork_it() does not check for errors from for_all_cpus()
 	 * because re-starting is problematic when forking
 	 */
+	snapshot_proc_sysfs_files();
 	for_all_cpus(get_counters, ODD_COUNTERS);
 	gettimeofday(&tv_odd, (struct timezone *)NULL);
 	timersub(&tv_odd, &tv_even, &tv_delta);
@@ -4438,6 +4441,7 @@ int get_and_dump_counters(void)
 {
 	int status;
 
+	snapshot_proc_sysfs_files();
 	status = for_all_cpus(get_counters, ODD_COUNTERS);
 	if (status)
 		return status;
-- 
GitLab


From c8ade3616a1a5cf7767c0338d2b02007796f5d88 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Wed, 15 Feb 2017 17:15:11 -0500
Subject: [PATCH 368/898] tools/power turbostat: Add --list option to show
 available header names

It is handy to know the list of column header names,
so that they can be used with --add and --skip

The new --list option shows them:

sudo ./turbostat --list --hide sysfs
,Core,CPU,Avg_MHz,Busy%,Bzy_MHz,TSC_MHz,IRQ,SMI,CPU%c1,CPU%c3,CPU%c6,CPU%c7,CoreTmp,PkgTmp,GFX%rc6,GFXMHz,PkgWatt,CorWatt,GFXWatt

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 118 ++++++++++++++------------
 1 file changed, 66 insertions(+), 52 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 48b540a2fe81..7b02fbb65893 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -52,6 +52,7 @@ unsigned int debug;
 unsigned int quiet;
 unsigned int rapl_joules;
 unsigned int summary_only;
+unsigned int list_header_only;
 unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
@@ -469,133 +470,133 @@ unsigned long long bic_lookup(char *name_list)
 	return retval;
 }
 
-void print_header(void)
+void print_header(char *delim)
 {
 	struct msr_counter *mp;
 
 	if (DO_BIC(BIC_Package))
-		outp += sprintf(outp, "\tPackage");
+		outp += sprintf(outp, "%sPackage", delim);
 	if (DO_BIC(BIC_Core))
-		outp += sprintf(outp, "\tCore");
+		outp += sprintf(outp, "%sCore", delim);
 	if (DO_BIC(BIC_CPU))
-		outp += sprintf(outp, "\tCPU");
+		outp += sprintf(outp, "%sCPU", delim);
 	if (DO_BIC(BIC_Avg_MHz))
-		outp += sprintf(outp, "\tAvg_MHz");
+		outp += sprintf(outp, "%sAvg_MHz", delim);
 	if (DO_BIC(BIC_Busy))
-		outp += sprintf(outp, "\tBusy%%");
+		outp += sprintf(outp, "%sBusy%%", delim);
 	if (DO_BIC(BIC_Bzy_MHz))
-		outp += sprintf(outp, "\tBzy_MHz");
+		outp += sprintf(outp, "%sBzy_MHz", delim);
 	if (DO_BIC(BIC_TSC_MHz))
-		outp += sprintf(outp, "\tTSC_MHz");
+		outp += sprintf(outp, "%sTSC_MHz", delim);
 
 	if (DO_BIC(BIC_IRQ))
-		outp += sprintf(outp, "\tIRQ");
+		outp += sprintf(outp, "%sIRQ", delim);
 	if (DO_BIC(BIC_SMI))
-		outp += sprintf(outp, "\tSMI");
+		outp += sprintf(outp, "%sSMI", delim);
 
 	for (mp = sys.tp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
-				outp += sprintf(outp, "\t%18.18s", mp->name);
+				outp += sprintf(outp, "%s%18.18s", delim, mp->name);
 			else
-				outp += sprintf(outp, "\t%10.10s", mp->name);
+				outp += sprintf(outp, "%s%10.10s", delim, mp->name);
 		} else {
-			outp += sprintf(outp, "\t%s", mp->name);
+			outp += sprintf(outp, "%s%s", delim, mp->name);
 		}
 	}
 
 	if (DO_BIC(BIC_CPU_c1))
-		outp += sprintf(outp, "\tCPU%%c1");
+		outp += sprintf(outp, "%sCPU%%c1", delim);
 	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "\tCPU%%c3");
+		outp += sprintf(outp, "%sCPU%%c3", delim);
 	if (DO_BIC(BIC_CPU_c6))
-		outp += sprintf(outp, "\tCPU%%c6");
+		outp += sprintf(outp, "%sCPU%%c6", delim);
 	if (DO_BIC(BIC_CPU_c7))
-		outp += sprintf(outp, "\tCPU%%c7");
+		outp += sprintf(outp, "%sCPU%%c7", delim);
 
 	if (DO_BIC(BIC_Mod_c6))
-		outp += sprintf(outp, "\tMod%%c6");
+		outp += sprintf(outp, "%sMod%%c6", delim);
 
 	if (DO_BIC(BIC_CoreTmp))
-		outp += sprintf(outp, "\tCoreTmp");
+		outp += sprintf(outp, "%sCoreTmp", delim);
 
 	for (mp = sys.cp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
-				outp += sprintf(outp, "\t%18.18s", mp->name);
+				outp += sprintf(outp, "%s%18.18s", delim, mp->name);
 			else
-				outp += sprintf(outp, "\t%10.10s", mp->name);
+				outp += sprintf(outp, "%s%10.10s", delim, mp->name);
 		} else {
-			outp += sprintf(outp, "\t%s", mp->name);
+			outp += sprintf(outp, "%s%s", delim, mp->name);
 		}
 	}
 
 	if (DO_BIC(BIC_PkgTmp))
-		outp += sprintf(outp, "\tPkgTmp");
+		outp += sprintf(outp, "%sPkgTmp", delim);
 
 	if (DO_BIC(BIC_GFX_rc6))
-		outp += sprintf(outp, "\tGFX%%rc6");
+		outp += sprintf(outp, "%sGFX%%rc6", delim);
 
 	if (DO_BIC(BIC_GFXMHz))
-		outp += sprintf(outp, "\tGFXMHz");
+		outp += sprintf(outp, "%sGFXMHz", delim);
 
 	if (do_skl_residency) {
-		outp += sprintf(outp, "\tTotl%%C0");
-		outp += sprintf(outp, "\tAny%%C0");
-		outp += sprintf(outp, "\tGFX%%C0");
-		outp += sprintf(outp, "\tCPUGFX%%");
+		outp += sprintf(outp, "%sTotl%%C0", delim);
+		outp += sprintf(outp, "%sAny%%C0", delim);
+		outp += sprintf(outp, "%sGFX%%C0", delim);
+		outp += sprintf(outp, "%sCPUGFX%%", delim);
 	}
 
 	if (DO_BIC(BIC_Pkgpc2))
-		outp += sprintf(outp, "\tPkg%%pc2");
+		outp += sprintf(outp, "%sPkg%%pc2", delim);
 	if (DO_BIC(BIC_Pkgpc3))
-		outp += sprintf(outp, "\tPkg%%pc3");
+		outp += sprintf(outp, "%sPkg%%pc3", delim);
 	if (DO_BIC(BIC_Pkgpc6))
-		outp += sprintf(outp, "\tPkg%%pc6");
+		outp += sprintf(outp, "%sPkg%%pc6", delim);
 	if (DO_BIC(BIC_Pkgpc7))
-		outp += sprintf(outp, "\tPkg%%pc7");
+		outp += sprintf(outp, "%sPkg%%pc7", delim);
 	if (DO_BIC(BIC_Pkgpc8))
-		outp += sprintf(outp, "\tPkg%%pc8");
+		outp += sprintf(outp, "%sPkg%%pc8", delim);
 	if (DO_BIC(BIC_Pkgpc9))
-		outp += sprintf(outp, "\tPkg%%pc9");
+		outp += sprintf(outp, "%sPkg%%pc9", delim);
 	if (DO_BIC(BIC_Pkgpc10))
-		outp += sprintf(outp, "\tPk%%pc10");
+		outp += sprintf(outp, "%sPk%%pc10", delim);
 
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
-			outp += sprintf(outp, "\tPkgWatt");
+			outp += sprintf(outp, "%sPkgWatt", delim);
 		if (DO_BIC(BIC_CorWatt))
-			outp += sprintf(outp, "\tCorWatt");
+			outp += sprintf(outp, "%sCorWatt", delim);
 		if (DO_BIC(BIC_GFXWatt))
-			outp += sprintf(outp, "\tGFXWatt");
+			outp += sprintf(outp, "%sGFXWatt", delim);
 		if (DO_BIC(BIC_RAMWatt))
-			outp += sprintf(outp, "\tRAMWatt");
+			outp += sprintf(outp, "%sRAMWatt", delim);
 		if (DO_BIC(BIC_PKG__))
-			outp += sprintf(outp, "\tPKG_%%");
+			outp += sprintf(outp, "%sPKG_%%", delim);
 		if (DO_BIC(BIC_RAM__))
-			outp += sprintf(outp, "\tRAM_%%");
+			outp += sprintf(outp, "%sRAM_%%", delim);
 	} else if (do_rapl && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
-			outp += sprintf(outp, "\tPkg_J");
+			outp += sprintf(outp, "%sPkg_J", delim);
 		if (DO_BIC(BIC_Cor_J))
-			outp += sprintf(outp, "\tCor_J");
+			outp += sprintf(outp, "%sCor_J", delim);
 		if (DO_BIC(BIC_GFX_J))
-			outp += sprintf(outp, "\tGFX_J");
+			outp += sprintf(outp, "%sGFX_J", delim);
 		if (DO_BIC(BIC_RAM_J))
-			outp += sprintf(outp, "\tRAM_J");
+			outp += sprintf(outp, "%sRAM_J", delim);
 		if (DO_BIC(BIC_PKG__))
-			outp += sprintf(outp, "\tPKG_%%");
+			outp += sprintf(outp, "%sPKG_%%", delim);
 		if (DO_BIC(BIC_RAM__))
-			outp += sprintf(outp, "\tRAM_%%");
+			outp += sprintf(outp, "%sRAM_%%", delim);
 	}
 	for (mp = sys.pp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
-				outp += sprintf(outp, "\t%18.18s", mp->name);
+				outp += sprintf(outp, "%s%18.18s", delim, mp->name);
 			else
-				outp += sprintf(outp, "\t%10.10s", mp->name);
+				outp += sprintf(outp, "%s%10.10s", delim, mp->name);
 		} else {
-			outp += sprintf(outp, "\t%s", mp->name);
+			outp += sprintf(outp, "%s%s", delim, mp->name);
 		}
 	}
 
@@ -933,7 +934,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
 	static int printed;
 
 	if (!printed || !summary_only)
-		print_header();
+		print_header("\t");
 
 	if (topo.num_cpus > 1)
 		format_counters(&average.threads, &average.cores,
@@ -4107,6 +4108,7 @@ void help()
 	"--quiet	skip decoding system configuration header\n"
 	"--interval sec	Override default 5-second measurement interval\n"
 	"--help		print this help message\n"
+	"--list		list column headers only\n"
 	"--out file	create or truncate \"file\" for all output\n"
 	"--version	print version information\n"
 	"\n"
@@ -4814,6 +4816,7 @@ void cmdline(int argc, char **argv)
 		{"help",	no_argument,		0, 'h'},
 		{"hide",	required_argument,	0, 'H'},	// meh, -h taken by --help
 		{"Joules",	no_argument,		0, 'J'},
+		{"list",	no_argument,		0, 'l'},
 		{"out",		required_argument,	0, 'o'},
 		{"Package",	no_argument,		0, 'p'},
 		{"processor",	no_argument,		0, 'p'},
@@ -4866,6 +4869,10 @@ void cmdline(int argc, char **argv)
 		case 'J':
 			rapl_joules++;
 			break;
+		case 'l':
+			list_header_only++;
+			quiet++;
+			break;
 		case 'o':
 			outf = fopen_or_die(optarg, "w");
 			break;
@@ -4912,6 +4919,13 @@ int main(int argc, char **argv)
 	if (dump_only)
 		return get_and_dump_counters();
 
+	/* list header and exit */
+	if (list_header_only) {
+		print_header(",");
+		flush_output_stdout();
+		return 0;
+	}
+
 	/*
 	 * if any params left, it must be a command to fork
 	 */
-- 
GitLab


From 0de6c0df4ecc32ffaf064fea3a43846ba4474bd0 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Wed, 15 Feb 2017 21:45:40 -0500
Subject: [PATCH 369/898] tools/power turbostat: use wide columns to display
 large numbers

When a counter overlfows 7 columns, it shifts the remaining
columns to the right, so they no longer line up under
their column header.

Update turbostat to dectect when it is handling large
numbers, and switch to wider columns where, necessary.

Reported-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 68 ++++++++++++++++++++++-----
 1 file changed, 55 insertions(+), 13 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 7b02fbb65893..cafc6bba6539 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -50,6 +50,7 @@ int *fd_percpu;
 struct timespec interval_ts = {5, 0};
 unsigned int debug;
 unsigned int quiet;
+unsigned int sums_need_wide_columns;
 unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int list_header_only;
@@ -154,7 +155,7 @@ struct thread_data {
 	unsigned long long aperf;
 	unsigned long long mperf;
 	unsigned long long c1;
-	unsigned int irq_count;
+	unsigned long long  irq_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int flags;
@@ -489,8 +490,13 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_TSC_MHz))
 		outp += sprintf(outp, "%sTSC_MHz", delim);
 
-	if (DO_BIC(BIC_IRQ))
-		outp += sprintf(outp, "%sIRQ", delim);
+	if (DO_BIC(BIC_IRQ)) {
+		if (sums_need_wide_columns)
+			outp += sprintf(outp, "%s     IRQ", delim);
+		else
+			outp += sprintf(outp, "%sIRQ", delim);
+	}
+
 	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "%sSMI", delim);
 
@@ -501,7 +507,10 @@ void print_header(char *delim)
 			else
 				outp += sprintf(outp, "%s%10.10s", delim, mp->name);
 		} else {
-			outp += sprintf(outp, "%s%s", delim, mp->name);
+			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8s", delim, mp->name);
+			else
+				outp += sprintf(outp, "%s%s", delim, mp->name);
 		}
 	}
 
@@ -527,7 +536,10 @@ void print_header(char *delim)
 			else
 				outp += sprintf(outp, "%s%10.10s", delim, mp->name);
 		} else {
-			outp += sprintf(outp, "%s%s", delim, mp->name);
+			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8s", delim, mp->name);
+			else
+				outp += sprintf(outp, "%s%s", delim, mp->name);
 		}
 	}
 
@@ -596,7 +608,10 @@ void print_header(char *delim)
 			else
 				outp += sprintf(outp, "%s%10.10s", delim, mp->name);
 		} else {
-			outp += sprintf(outp, "%s%s", delim, mp->name);
+			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8s", delim, mp->name);
+			else
+				outp += sprintf(outp, "%s%s", delim, mp->name);
 		}
 	}
 
@@ -620,7 +635,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c1: %016llX\n", t->c1);
 
 		if (DO_BIC(BIC_IRQ))
-			outp += sprintf(outp, "IRQ: %d\n", t->irq_count);
+			outp += sprintf(outp, "IRQ: %lld\n", t->irq_count);
 		if (DO_BIC(BIC_SMI))
 			outp += sprintf(outp, "SMI: %d\n", t->smi_count);
 
@@ -755,8 +770,12 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
 
 	/* IRQ */
-	if (DO_BIC(BIC_IRQ))
-		outp += sprintf(outp, "\t%d", t->irq_count);
+	if (DO_BIC(BIC_IRQ)) {
+		if (sums_need_wide_columns)
+			outp += sprintf(outp, "\t%8lld", t->irq_count);
+		else
+			outp += sprintf(outp, "\t%lld", t->irq_count);
+	}
 
 	/* SMI */
 	if (DO_BIC(BIC_SMI))
@@ -770,7 +789,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "\t0x%016llx", t->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
-			outp += sprintf(outp, "\t%lld", t->counter[i]);
+			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "\t%8lld", t->counter[i]);
+			else
+				outp += sprintf(outp, "\t%lld", t->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
 			if (mp->type == COUNTER_USEC)
 				outp += sprintf(outp, "\t%.2f", t->counter[i]/interval_float/10000);
@@ -809,7 +831,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "\t0x%016llx", c->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
-			outp += sprintf(outp, "\t%lld", c->counter[i]);
+			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "\t%8lld", c->counter[i]);
+			else
+				outp += sprintf(outp, "\t%lld", c->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
 			outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/tsc);
 		}
@@ -897,7 +922,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "\t0x%016llx", p->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
-			outp += sprintf(outp, "\t%lld", p->counter[i]);
+			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "\t%8lld", p->counter[i]);
+			else
+				outp += sprintf(outp, "\t%lld", p->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
 			outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/tsc);
 		}
@@ -1272,6 +1300,9 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.threads.mperf /= topo.num_cpus;
 	average.threads.c1 /= topo.num_cpus;
 
+	if (average.threads.irq_count > 9999999)
+		sums_need_wide_columns = 1;
+
 	average.cores.c3 /= topo.num_cores;
 	average.cores.c6 /= topo.num_cores;
 	average.cores.c7 /= topo.num_cores;
@@ -1299,18 +1330,29 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
-		if (mp->flags & SYSFS_PERCPU && mp->type == COUNTER_ITEMS)
+		if (mp->type == COUNTER_ITEMS) {
+			if (average.threads.counter[i] > 9999999)
+				sums_need_wide_columns = 1;
 			continue;
+		}
 		average.threads.counter[i] /= topo.num_cpus;
 	}
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
+		if (mp->type == COUNTER_ITEMS) {
+			if (average.cores.counter[i] > 9999999)
+				sums_need_wide_columns = 1;
+		}
 		average.cores.counter[i] /= topo.num_cores;
 	}
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
+		if (mp->type == COUNTER_ITEMS) {
+			if (average.packages.counter[i] > 9999999)
+				sums_need_wide_columns = 1;
+		}
 		average.packages.counter[i] /= topo.num_packages;
 	}
 }
-- 
GitLab


From 6168c2e0fb5084d187aa8f3ec4093db5e161d4dc Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 16 Feb 2017 23:07:51 -0500
Subject: [PATCH 370/898] tools/power turbostat: update --list feature

Make it possible to take the entire un-edited output
from `turbostat --list` and feed it to "turbostat --show"
or "turbostat --hide".

To do this, the leading comma was removed
(no mater what columns are active)
and also they dynamic C-state "C1, C2, C3" etc are replaced
by the string "sysfs", which refers to them as a group.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 219 +++++++++++++-------------
 1 file changed, 113 insertions(+), 106 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index cafc6bba6539..851eaf06f358 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -474,33 +474,38 @@ unsigned long long bic_lookup(char *name_list)
 void print_header(char *delim)
 {
 	struct msr_counter *mp;
+	int printed = 0;
 
 	if (DO_BIC(BIC_Package))
-		outp += sprintf(outp, "%sPackage", delim);
+		outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Core))
-		outp += sprintf(outp, "%sCore", delim);
+		outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU))
-		outp += sprintf(outp, "%sCPU", delim);
+		outp += sprintf(outp, "%sCPU", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Avg_MHz))
-		outp += sprintf(outp, "%sAvg_MHz", delim);
+		outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Busy))
-		outp += sprintf(outp, "%sBusy%%", delim);
+		outp += sprintf(outp, "%sBusy%%", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Bzy_MHz))
-		outp += sprintf(outp, "%sBzy_MHz", delim);
+		outp += sprintf(outp, "%sBzy_MHz", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_TSC_MHz))
-		outp += sprintf(outp, "%sTSC_MHz", delim);
+		outp += sprintf(outp, "%sTSC_MHz", (printed++ ? delim : ""));
 
 	if (DO_BIC(BIC_IRQ)) {
 		if (sums_need_wide_columns)
-			outp += sprintf(outp, "%s     IRQ", delim);
+			outp += sprintf(outp, "%s     IRQ", (printed++ ? delim : ""));
 		else
-			outp += sprintf(outp, "%sIRQ", delim);
+			outp += sprintf(outp, "%sIRQ", (printed++ ? delim : ""));
 	}
 
 	if (DO_BIC(BIC_SMI))
-		outp += sprintf(outp, "%sSMI", delim);
+		outp += sprintf(outp, "%sSMI", (printed++ ? delim : ""));
 
 	for (mp = sys.tp; mp; mp = mp->next) {
+		if (*delim == ',') {
+			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), "sysfs");
+			break;
+		}
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
 				outp += sprintf(outp, "%s%18.18s", delim, mp->name);
@@ -515,19 +520,19 @@ void print_header(char *delim)
 	}
 
 	if (DO_BIC(BIC_CPU_c1))
-		outp += sprintf(outp, "%sCPU%%c1", delim);
+		outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "%sCPU%%c3", delim);
+		outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c6))
-		outp += sprintf(outp, "%sCPU%%c6", delim);
+		outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c7))
-		outp += sprintf(outp, "%sCPU%%c7", delim);
+		outp += sprintf(outp, "%sCPU%%c7", (printed++ ? delim : ""));
 
 	if (DO_BIC(BIC_Mod_c6))
-		outp += sprintf(outp, "%sMod%%c6", delim);
+		outp += sprintf(outp, "%sMod%%c6", (printed++ ? delim : ""));
 
 	if (DO_BIC(BIC_CoreTmp))
-		outp += sprintf(outp, "%sCoreTmp", delim);
+		outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
 
 	for (mp = sys.cp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
@@ -544,62 +549,62 @@ void print_header(char *delim)
 	}
 
 	if (DO_BIC(BIC_PkgTmp))
-		outp += sprintf(outp, "%sPkgTmp", delim);
+		outp += sprintf(outp, "%sPkgTmp", (printed++ ? delim : ""));
 
 	if (DO_BIC(BIC_GFX_rc6))
-		outp += sprintf(outp, "%sGFX%%rc6", delim);
+		outp += sprintf(outp, "%sGFX%%rc6", (printed++ ? delim : ""));
 
 	if (DO_BIC(BIC_GFXMHz))
-		outp += sprintf(outp, "%sGFXMHz", delim);
+		outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : ""));
 
 	if (do_skl_residency) {
-		outp += sprintf(outp, "%sTotl%%C0", delim);
-		outp += sprintf(outp, "%sAny%%C0", delim);
-		outp += sprintf(outp, "%sGFX%%C0", delim);
-		outp += sprintf(outp, "%sCPUGFX%%", delim);
+		outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
+		outp += sprintf(outp, "%sAny%%C0", (printed++ ? delim : ""));
+		outp += sprintf(outp, "%sGFX%%C0", (printed++ ? delim : ""));
+		outp += sprintf(outp, "%sCPUGFX%%", (printed++ ? delim : ""));
 	}
 
 	if (DO_BIC(BIC_Pkgpc2))
-		outp += sprintf(outp, "%sPkg%%pc2", delim);
+		outp += sprintf(outp, "%sPkg%%pc2", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc3))
-		outp += sprintf(outp, "%sPkg%%pc3", delim);
+		outp += sprintf(outp, "%sPkg%%pc3", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc6))
-		outp += sprintf(outp, "%sPkg%%pc6", delim);
+		outp += sprintf(outp, "%sPkg%%pc6", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc7))
-		outp += sprintf(outp, "%sPkg%%pc7", delim);
+		outp += sprintf(outp, "%sPkg%%pc7", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc8))
-		outp += sprintf(outp, "%sPkg%%pc8", delim);
+		outp += sprintf(outp, "%sPkg%%pc8", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc9))
-		outp += sprintf(outp, "%sPkg%%pc9", delim);
+		outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc10))
-		outp += sprintf(outp, "%sPk%%pc10", delim);
+		outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : ""));
 
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
-			outp += sprintf(outp, "%sPkgWatt", delim);
+			outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_CorWatt))
-			outp += sprintf(outp, "%sCorWatt", delim);
+			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFXWatt))
-			outp += sprintf(outp, "%sGFXWatt", delim);
+			outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_RAMWatt))
-			outp += sprintf(outp, "%sRAMWatt", delim);
+			outp += sprintf(outp, "%sRAMWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_PKG__))
-			outp += sprintf(outp, "%sPKG_%%", delim);
+			outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_RAM__))
-			outp += sprintf(outp, "%sRAM_%%", delim);
+			outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : ""));
 	} else if (do_rapl && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
-			outp += sprintf(outp, "%sPkg_J", delim);
+			outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Cor_J))
-			outp += sprintf(outp, "%sCor_J", delim);
+			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFX_J))
-			outp += sprintf(outp, "%sGFX_J", delim);
+			outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_RAM_J))
-			outp += sprintf(outp, "%sRAM_J", delim);
+			outp += sprintf(outp, "%sRAM_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_PKG__))
-			outp += sprintf(outp, "%sPKG_%%", delim);
+			outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_RAM__))
-			outp += sprintf(outp, "%sRAM_%%", delim);
+			outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : ""));
 	}
 	for (mp = sys.pp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
@@ -708,6 +713,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	char *fmt8;
 	int i;
 	struct msr_counter *mp;
+	char *delim = "\t";
+	int printed = 0;
 
 	 /* if showing only 1st thread in core and this isn't one, bail out */
 	if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
@@ -729,81 +736,81 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	/* topo columns, print blanks on 1st (average) line */
 	if (t == &average.threads) {
 		if (DO_BIC(BIC_Package))
-			outp += sprintf(outp, "\t-");
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Core))
-			outp += sprintf(outp, "\t-");
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_CPU))
-			outp += sprintf(outp, "\t-");
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 	} else {
 		if (DO_BIC(BIC_Package)) {
 			if (p)
-				outp += sprintf(outp, "\t%d", p->package_id);
+				outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->package_id);
 			else
-				outp += sprintf(outp, "\t-");
+				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		}
 		if (DO_BIC(BIC_Core)) {
 			if (c)
-				outp += sprintf(outp, "\t%d", c->core_id);
+				outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id);
 			else
-				outp += sprintf(outp, "\t-");
+				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		}
 		if (DO_BIC(BIC_CPU))
-			outp += sprintf(outp, "\t%d", t->cpu_id);
+			outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id);
 	}
 
 	if (DO_BIC(BIC_Avg_MHz))
-		outp += sprintf(outp, "\t%.0f",
+		outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""),
 			1.0 / units * t->aperf / interval_float);
 
 	if (DO_BIC(BIC_Busy))
-		outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->mperf/tsc);
 
 	if (DO_BIC(BIC_Bzy_MHz)) {
 		if (has_base_hz)
-			outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf);
+			outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), base_hz / units * t->aperf / t->mperf);
 		else
-			outp += sprintf(outp, "\t%.0f",
+			outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""),
 				tsc / units * t->aperf / t->mperf / interval_float);
 	}
 
 	if (DO_BIC(BIC_TSC_MHz))
-		outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
+		outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), 1.0 * t->tsc/units/interval_float);
 
 	/* IRQ */
 	if (DO_BIC(BIC_IRQ)) {
 		if (sums_need_wide_columns)
-			outp += sprintf(outp, "\t%8lld", t->irq_count);
+			outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->irq_count);
 		else
-			outp += sprintf(outp, "\t%lld", t->irq_count);
+			outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count);
 	}
 
 	/* SMI */
 	if (DO_BIC(BIC_SMI))
-		outp += sprintf(outp, "\t%d", t->smi_count);
+		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count);
 
 	/* Added counters */
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
-				outp += sprintf(outp, "\t0x%08lx", (unsigned long) t->counter[i]);
+				outp += sprintf(outp, "%s0x%08lx", (printed++ ? delim : ""), (unsigned long) t->counter[i]);
 			else
-				outp += sprintf(outp, "\t0x%016llx", t->counter[i]);
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
 			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
-				outp += sprintf(outp, "\t%8lld", t->counter[i]);
+				outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->counter[i]);
 			else
-				outp += sprintf(outp, "\t%lld", t->counter[i]);
+				outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
 			if (mp->type == COUNTER_USEC)
-				outp += sprintf(outp, "\t%.2f", t->counter[i]/interval_float/10000);
+				outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), t->counter[i]/interval_float/10000);
 			else
-				outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/tsc);
+				outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->counter[i]/tsc);
 		}
 	}
 
 	/* C1 */
 	if (DO_BIC(BIC_CPU_c1))
-		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1/tsc);
 
 
 	/* print per-core data only for 1st thread in core */
@@ -811,32 +818,32 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		goto done;
 
 	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
 	if (DO_BIC(BIC_CPU_c6))
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
 	if (DO_BIC(BIC_CPU_c7))
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c7/tsc);
 
 	/* Mod%c6 */
 	if (DO_BIC(BIC_Mod_c6))
-		outp += sprintf(outp, "\t%.2f", 100.0 * c->mc6_us / tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->mc6_us / tsc);
 
 	if (DO_BIC(BIC_CoreTmp))
-		outp += sprintf(outp, "\t%d", c->core_temp_c);
+		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_temp_c);
 
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
-				outp += sprintf(outp, "\t0x%08lx", (unsigned long) c->counter[i]);
+				outp += sprintf(outp, "%s0x%08lx", (printed++ ? delim : ""), (unsigned long) c->counter[i]);
 			else
-				outp += sprintf(outp, "\t0x%016llx", c->counter[i]);
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
 			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
-				outp += sprintf(outp, "\t%8lld", c->counter[i]);
+				outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), c->counter[i]);
 			else
-				outp += sprintf(outp, "\t%lld", c->counter[i]);
+				outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
-			outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/tsc);
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->counter[i]/tsc);
 		}
 	}
 
@@ -846,88 +853,88 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	/* PkgTmp */
 	if (DO_BIC(BIC_PkgTmp))
-		outp += sprintf(outp, "\t%d", p->pkg_temp_c);
+		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->pkg_temp_c);
 
 	/* GFXrc6 */
 	if (DO_BIC(BIC_GFX_rc6)) {
 		if (p->gfx_rc6_ms == -1) {	/* detect GFX counter reset */
-			outp += sprintf(outp, "\t**.**");
+			outp += sprintf(outp, "%s**.**", (printed++ ? delim : ""));
 		} else {
-			outp += sprintf(outp, "\t%.2f",
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
 				p->gfx_rc6_ms / 10.0 / interval_float);
 		}
 	}
 
 	/* GFXMHz */
 	if (DO_BIC(BIC_GFXMHz))
-		outp += sprintf(outp, "\t%d", p->gfx_mhz);
+		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz);
 
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (do_skl_residency) {
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/tsc);
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_core_c0/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_gfxe_c0/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_both_core_gfxe_c0/tsc);
 	}
 
 	if (DO_BIC(BIC_Pkgpc2))
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc2/tsc);
 	if (DO_BIC(BIC_Pkgpc3))
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc3/tsc);
 	if (DO_BIC(BIC_Pkgpc6))
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc6/tsc);
 	if (DO_BIC(BIC_Pkgpc7))
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc7/tsc);
 	if (DO_BIC(BIC_Pkgpc8))
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc8/tsc);
 	if (DO_BIC(BIC_Pkgpc9))
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc9/tsc);
 	if (DO_BIC(BIC_Pkgpc10))
-		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/tsc);
+		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc);
 
 	/*
  	 * If measurement interval exceeds minimum RAPL Joule Counter range,
  	 * indicate that results are suspect by printing "**" in fraction place.
  	 */
 	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "\t%.2f";
+		fmt8 = "%s%.2f";
 	else
 		fmt8 = "%6.0f**";
 
 	if (DO_BIC(BIC_PkgWatt))
-		outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_CorWatt))
-		outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_GFXWatt))
-		outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_RAMWatt))
-		outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units / interval_float);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float);
 	if (DO_BIC(BIC_Pkg_J))
-		outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
 	if (DO_BIC(BIC_Cor_J))
-		outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
 	if (DO_BIC(BIC_GFX_J))
-		outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
 	if (DO_BIC(BIC_RAM_J))
-		outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units);
 	if (DO_BIC(BIC_PKG__))
-		outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 	if (DO_BIC(BIC_RAM__))
-		outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
 
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
-				outp += sprintf(outp, "\t0x%08lx", (unsigned long) p->counter[i]);
+				outp += sprintf(outp, "%s0x%08lx", (printed++ ? delim : ""), (unsigned long) p->counter[i]);
 			else
-				outp += sprintf(outp, "\t0x%016llx", p->counter[i]);
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
 			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
-				outp += sprintf(outp, "\t%8lld", p->counter[i]);
+				outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), p->counter[i]);
 			else
-				outp += sprintf(outp, "\t%lld", p->counter[i]);
+				outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), p->counter[i]);
 		} else if (mp->format == FORMAT_PERCENT) {
-			outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/tsc);
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->counter[i]/tsc);
 		}
 	}
 
-- 
GitLab


From da67e2b9fd1d846a41978690da0a899d8e4378ec Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Wed, 15 Feb 2017 00:30:22 -0500
Subject: [PATCH 371/898] tools/power turbostat: turbostat.8 update

update examples to show recently updated features.
In particular
--add
--show
--hide
--cpu
--list

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.8 | 238 +++++++++++++++-----------
 1 file changed, 140 insertions(+), 98 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index efe6a7147ff2..b1b1ab80102c 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -16,9 +16,9 @@ idle power-state statistics, temperature and power on X86 processors.
 There are two ways to invoke turbostat.
 The first method is to supply a
 \fBcommand\fP, which is forked and statistics are printed
-upon its completion.
+in one-shot upon its completion.
 The second method is to omit the command,
-and turbostat displays statistics every 5 seconds.
+and turbostat displays statistics every 5 seconds interval.
 The 5-second interval can be changed using the --interval option.
 .PP
 Some information is not available on older processors.
@@ -28,9 +28,10 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--add attributes\fP add column with counter having specified 'attributes'.  The 'location' attribute is required, all others are optional.
 .nf
-	location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP}
+	location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP}
 		msrDDD is a decimal offset, eg. msr16
 		msr0xXXX is a hex offset, eg. msr0x10
+		/sys/path... is an absolute path to a sysfs attribute
 
 	scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP}
 		sample and print the counter for every cpu, core, or package.
@@ -45,6 +46,10 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 		'delta' shows the difference in values during the measurement interval.
 		'percent' shows the delta as a percentage of the cycles elapsed.
 		default: delta
+
+	name: "name_string"
+		Any string that does not match a key-word above is used
+		as the column header.
 .fi
 .PP
 \fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  cpu-set is a comma delimited list of cpu ranges. cpu ranges can be individual cpu numbers or start and end numbers, separated by ".." or '-'.  eg. 1,2,8,14..17,21-44
@@ -68,6 +73,8 @@ The file is truncated if it already exists, and it is created if it does not exi
 .PP
 \fB--Package\fP limits output to the system summary plus the 1st thread in each Package.
 .PP
+\fB--list\fP display column header names available for use by --show and --hide, then exit.
+.PP
 \fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package.  Ie. it skips hyper-threaded siblings.
 .PP
 \fB--Summary\fP limits output to a 1-line System Summary for each interval.
@@ -79,24 +86,25 @@ The file is truncated if it already exists, and it is created if it does not exi
 The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit,
 displays the statistics gathered since it was forked.
 .PP
-.SH DEFAULT FIELD DESCRIPTIONS
+.SH ROW DESCRIPTIONS
+The system configuration dump (if --quiet is not used) is followed by statistics.  The first row of the statistics labels the content of each column (below).  The second row of statistics is the system summary line.  The system summary line has a '-' in the columns for the Package, Core, and CPU.  The contents of the system summary line depends on the type of column.  Columns that count items (eg. IRQ) show the sum across all CPUs in the system.  Columns that show a percentage show the average across all CPUs in the system.  Columns that dump raw MSR values simply show 0 in the summary.  After the system summary row, each row describes a specific Package/Core/CPU.  Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system.
+.SH COLUMN DESCRIPTIONS
 .nf
+\fBCore\fP processor core number.  Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
 \fBCPU\fP Linux CPU (logical processor) number.  Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
-\fBAVG_MHz\fP number of cycles executed divided by time elapsed.
-\fBBusy%\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
-\fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
+\fBPackage\fP processor package number -- not present on systems with a single processor package.
+\fBAvg_MHz\fP number of cycles executed divided by time elapsed.  Note that this includes idle-time when 0 instructions are executed.
+\fBBusy%\fP percent of the measurement interval that the CPU executes instructions, aka. % of time in "C0" state.
+\fBBzy_MHz\fP average clock rate while the CPU was not idle (ie. in "c0" state).
 \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
-.fi
-.PP
-.SH DEBUG FIELD DESCRIPTIONS
-.nf
-\fBPackage\fP processor package number.
-\fBCore\fP processor core number.
-Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
-\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.
+\fBIRQ\fP The number of interrupts serviced by that CPU during the measurement interval.  The system total line is the sum of interrupts serviced across all CPUs.  turbostat parses /proc/interrupts to generate this summary.
+\fBSMI\fP The number of System Management Interrupts  serviced CPU during the measurement interval.  While this counter is actually per-CPU, SMI are triggered on all processors, so the number should be the same for all CPUs.
+\fBC1, C2, C3...\fP The number times Linux requested the C1, C2, C3 idle state during the measurement interval.  The system summary line shows the sum for all CPUs.  These are C-state names as exported in /sys/devices/system/cpu/cpu*/cpuidle/state*/name.  While their names are generic, their attributes are processor specific. They the system description section of output shows what MWAIT sub-states they are mapped to on each system.
+\fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3....  The system summary is the average of all CPUs in the system.  Note that these are software, reflecting what was requested.  The hardware counters reflect what was actually achieved.
+\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.  These numbers are from hardware residency counters.
 \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
 \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
-\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.
+\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.  These numbers are from hardware residency counters.
 \fBPkgWatt\fP Watts consumed by the whole package.
 \fBCorWatt\fP Watts consumed by the core part of the package.
 \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors.
@@ -104,50 +112,110 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
 \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
 \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
 .fi
+.SH TOO MUCH INFORMATION EXAMPLE
+By default, turbostat dumps all possible information -- a system configuration header, followed by columns for all counters.
+This is ideal for remote debugging, use the "--out" option to save everything to a text file, and get that file to the expert helping you debug.
 .PP
-.SH PERIODIC EXAMPLE
-Without any parameters, turbostat displays statistics ever 5 seconds.
-Periodic output goes to stdout, by default, unless --out is used to specify an output file.
-The 5-second interval can be changed with th "-i sec" option.
-Or a command may be specified as in "FORK EXAMPLE" below.
+When you are not interested in all that information, and there are several ways to see only what you want.  First the "--quiet" option will skip the configuration information, and turbostat will show only the counter columns.  Second, you can reduce the columns with the "--hide" and "--show" options.  If you use the "--show" option, then turbostat will show only the columns you list.  If you use the "--hide" option, turbostat will show all columns, except the ones you list.
+.PP
+To find out what columns are available for --show and --hide, the "--list" option is available.  Note, however, there is an exception.  The C-state columns collected from sysfs "C1,C2,C3,C1%,C2%,C3%" are not built-in counters, but are discovered after --show and --hide are processed.  You can use the special counter name "sysfs" to refer to all of them at the same time.
+.nf
+sudo ./turbostat --show sysfs --quiet sleep 10
+10.003837 sec
+	C1	C1E	C3	C6	C7s	C1%	C1E%	C3%	C6%	C7s%
+	4	21	2	2	459	0.14	0.82	0.00	0.00	98.93
+	1	17	2	2	130	0.00	0.02	0.00	0.00	99.80
+	0	0	0	0	31	0.00	0.00	0.00	0.00	99.95
+	2	1	0	0	52	1.14	6.49	0.00	0.00	92.21
+	1	2	0	0	52	0.00	0.08	0.00	0.00	99.86
+	0	0	0	0	71	0.00	0.00	0.00	0.00	99.89
+	0	0	0	0	25	0.00	0.00	0.00	0.00	99.96
+	0	0	0	0	74	0.00	0.00	0.00	0.00	99.94
+	0	1	0	0	24	0.00	0.00	0.00	0.00	99.84
+.fi
+.PP
+.SH ONE SHOT COMMAND EXAMPLE
+If turbostat is invoked with a command, it will fork that command
+and output the statistics gathered after the command exits.
+In this case, turbostat output goes to stderr, by default.
+Output can instead be saved to a file using the --out option.
+In this example, the "sleep 10" command is forked, and turbostat waits for it to complete before saving all statistics into "ts.out".  Note that "sleep 10" is not part of turbostat, but is simply an example of a command that turbostat can fork.  The "ts.out" file is what you want to edit in a very wide window, paste into a spreadsheet, or attach to a bugzilla entry.
+
 .nf
-[root@hsw]# ./turbostat
-     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
-       -     488   12.51    3898    3498
-       0       0    0.01    3885    3498
-       4    3897   99.99    3898    3498
-       1       0    0.00    3861    3498
-       5       0    0.00    3882    3498
-       2       1    0.02    3894    3498
-       6       2    0.06    3898    3498
-       3       0    0.00    3849    3498
-       7       0    0.00    3877    3498
+[root@hsw]# ./turbostat -o ts.out sleep 10
+[root@hsw]#
+.fi
 
+.SH PERIODIC INTERVAL EXAMPLE
+Without a command to fork, turbostat displays statistics ever 5 seconds.
+Periodic output goes to stdout, by default, unless --out is used to specify an output file.
+The 5-second interval can be changed with the "-i sec" option.
+.nf
+sudo ./turbostat --quiet --hide sysfs,IRQ,SMI,CoreTmp,PkgTmp,GFX%rc6,GFXMHz,PkgWatt,CorWatt,GFXWatt
+	Core	CPU	Avg_MHz	Busy%	Bzy_MHz	TSC_MHz	CPU%c1	CPU%c3	CPU%c6	CPU%c7
+	-	-	488	12.52	3900	3498	12.50	0.00	0.00	74.98
+	0	0	5	0.13	3900	3498	99.87	0.00	0.00	0.00
+	0	4	3897	99.99	3900	3498	0.01
+	1	1	0	0.00	3856	3498	0.01	0.00	0.00	99.98
+	1	5	0	0.00	3861	3498	0.01
+	2	2	1	0.02	3889	3498	0.03	0.00	0.00	99.95
+	2	6	0	0.00	3863	3498	0.05
+	3	3	0	0.01	3869	3498	0.02	0.00	0.00	99.97
+	3	7	0	0.00	3878	3498	0.03
+	Core	CPU	Avg_MHz	Busy%	Bzy_MHz	TSC_MHz	CPU%c1	CPU%c3	CPU%c6	CPU%c7
+	-	-	491	12.59	3900	3498	12.42	0.00	0.00	74.99
+	0	0	27	0.69	3900	3498	99.31	0.00	0.00	0.00
+	0	4	3898	99.99	3900	3498	0.01
+	1	1	0	0.00	3883	3498	0.01	0.00	0.00	99.99
+	1	5	0	0.00	3898	3498	0.01
+	2	2	0	0.01	3889	3498	0.02	0.00	0.00	99.98
+	2	6	0	0.00	3889	3498	0.02
+	3	3	0	0.00	3856	3498	0.01	0.00	0.00	99.99
+	3	7	0	0.00	3897	3498	0.01
 .fi
-.SH DEBUG EXAMPLE
+This example also shows the use of the --hide option to skip columns that are not wanted.
+Note that cpu4 in this example is 99.99% busy, while the other CPUs are all under 1% busy.
+Notice that cpu4's HT sibling is cpu0, which is under 1% busy, but can get into CPU%c1 only,
+because its cpu4's activity on shared hardware keeps it from entering a deeper C-state.
+
+.SH SYSTEM CONFIGURATION INFORMATION EXAMPLE
 
-The first row of statistics is a summary for the entire system.
-For residency % columns, the summary is a weighted average.
-For Temperature columns, the summary is the column maximum.
-For Watts columns, the summary is a system total.
-Subsequent rows show per-CPU statistics.
+By default, turbostat always dumps system configuration information
+before taking measurements.  In the example above, "--quiet" is used
+to suppress that output.  Here is an example of the configuration information:
 .nf
-turbostat version 4.1 10-Feb, 2015 - Len Brown <lenb@kernel.org>
+turbostat version 2017.02.15 - Len Brown <lenb@kernel.org>
 CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3c:3 (6:60:3)
-CPUID(6): APERF, DTS, PTM, EPB
+CPUID(1): SSE3 MONITOR - EIST TM2 TSC MSR ACPI-TM TM
+CPUID(6): APERF, TURBO, DTS, PTM, No-HWP, No-HWPnotify, No-HWPwindow, No-HWPepp, No-HWPpkg, EPB
+cpu4: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST No-MWAIT PREFETCH TURBO)
+CPUID(7): No-SGX
+cpu4: MSR_MISC_PWR_MGMT: 0x00400000 (ENable-EIST_Coordination DISable-EPB DISable-OOB)
 RAPL: 3121 sec. Joule Counter Range, at 84 Watts
-cpu0: MSR_NHM_PLATFORM_INFO: 0x80838f3012300
-8 * 100 = 800 MHz max efficiency
-35 * 100 = 3500 MHz TSC frequency
-cpu0: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled)
-cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0)
-cpu0: MSR_TURBO_RATIO_LIMIT: 0x25262727
-37 * 100 = 3700 MHz max turbo 4 active cores
-38 * 100 = 3800 MHz max turbo 3 active cores
-39 * 100 = 3900 MHz max turbo 2 active cores
-39 * 100 = 3900 MHz max turbo 1 active cores
+cpu4: MSR_PLATFORM_INFO: 0x80838f3012300
+8 * 100.0 = 800.0 MHz max efficiency frequency
+35 * 100.0 = 3500.0 MHz base frequency
+cpu4: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled)
+cpu4: MSR_TURBO_RATIO_LIMIT: 0x25262727
+37 * 100.0 = 3700.0 MHz max turbo 4 active cores
+38 * 100.0 = 3800.0 MHz max turbo 3 active cores
+39 * 100.0 = 3900.0 MHz max turbo 2 active cores
+39 * 100.0 = 3900.0 MHz max turbo 1 active cores
+cpu4: MSR_CONFIG_TDP_NOMINAL: 0x00000023 (base_ratio=35)
+cpu4: MSR_CONFIG_TDP_LEVEL_1: 0x00000000 ()
+cpu4: MSR_CONFIG_TDP_LEVEL_2: 0x00000000 ()
+cpu4: MSR_CONFIG_TDP_CONTROL: 0x80000000 ( lock=1)
+cpu4: MSR_TURBO_ACTIVATION_RATIO: 0x00000000 (MAX_NON_TURBO_RATIO=0 lock=0)
+cpu4: MSR_PKG_CST_CONFIG_CONTROL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0)
+cpu4: POLL: CPUIDLE CORE POLL IDLE
+cpu4: C1: MWAIT 0x00
+cpu4: C1E: MWAIT 0x01
+cpu4: C3: MWAIT 0x10
+cpu4: C6: MWAIT 0x20
+cpu4: C7s: MWAIT 0x32
+cpu4: MSR_MISC_FEATURE_CONTROL: 0x00000000 (L2-Prefetch L2-Prefetch-pair L1-Prefetch L1-IP-Prefetch)
 cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced)
-cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Auto-HWP, Amps, MultiCoreTurbo, Transitions, )
+cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Transitions, MultiCoreTurbo, Amps, Auto-HWP, )
 cpu0: MSR_GFX_PERF_LIMIT_REASONS, 0x00000000 (Active: ) (Logged: )
 cpu0: MSR_RING_PERF_LIMIT_REASONS, 0x0d000000 (Active: ) (Logged: Amps, PkgPwrL1, PkgPwrL2, )
 cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.)
@@ -162,23 +230,14 @@ cpu0: MSR_PP1_POLICY: 0
 cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
 cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00641400 (100 C)
-cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x88340800 (48 C)
-cpu0: MSR_IA32_THERM_STATUS: 0x88340000 (48 C +/- 1)
-cpu1: MSR_IA32_THERM_STATUS: 0x88440000 (32 C +/- 1)
-cpu2: MSR_IA32_THERM_STATUS: 0x88450000 (31 C +/- 1)
-cpu3: MSR_IA32_THERM_STATUS: 0x88490000 (27 C +/- 1)
-    Core     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp PkgWatt CorWatt GFXWatt
-       -       -     493   12.64    3898    3498       0   12.64    0.00    0.00   74.72      47      47   21.62   13.74    0.00
-       0       0       4    0.11    3894    3498       0   99.89    0.00    0.00    0.00      47      47   21.62   13.74    0.00
-       0       4    3897   99.98    3898    3498       0    0.02
-       1       1       7    0.17    3887    3498       0    0.04    0.00    0.00   99.79      32
-       1       5       0    0.00    3885    3498       0    0.21
-       2       2      29    0.76    3895    3498       0    0.10    0.01    0.01   99.13      32
-       2       6       2    0.06    3896    3498       0    0.80
-       3       3       1    0.02    3832    3498       0    0.03    0.00    0.00   99.95      28
-       3       7       0    0.00    3879    3498       0    0.04
-^C
-
+cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884c0800 (24 C)
+cpu0: MSR_IA32_THERM_STATUS: 0x884c0000 (24 C +/- 1)
+cpu1: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1)
+cpu2: MSR_IA32_THERM_STATUS: 0x884e0000 (22 C +/- 1)
+cpu3: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1)
+cpu4: MSR_PKGC3_IRTL: 0x00008842 (valid, 67584 ns)
+cpu4: MSR_PKGC6_IRTL: 0x00008873 (valid, 117760 ns)
+cpu4: MSR_PKGC7_IRTL: 0x00008891 (valid, 148480 ns)
 .fi
 The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency
 available at the minimum package voltage.  The \fBTSC frequency\fP is the base
@@ -188,39 +247,22 @@ should be sustainable on all CPUs indefinitely, given nominal power and cooling.
 The remaining rows show what maximum turbo frequency is possible
 depending on the number of idle cores.  Note that not all information is
 available on all processors.
-.SH FORK EXAMPLE
-If turbostat is invoked with a command, it will fork that command
-and output the statistics gathered after the command exits.
-In this case, turbostat output goes to stderr, by default.
-Output can instead be saved to a file using the --out option.
-eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds
-until ^C while the other CPUs are mostly idle:
-
+.SH ADD COUNTER EXAMPLE
+Here we limit turbostat to showing just the CPU number for cpu0 - cpu3.
+We add a counter showing the 32-bit raw value of MSR 0x199 (MSR_IA32_PERF_CTL),
+labeling it with the column header, "PRF_CTRL", and display it only once,
+afte the conclusion of a 0.1 second sleep.
 .nf
-root@hsw: turbostat cat /dev/zero > /dev/null
-^C
-     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
-       -     482   12.51    3854    3498
-       0       0    0.01    1960    3498
-       4       0    0.00    2128    3498
-       1       0    0.00    3003    3498
-       5    3854   99.98    3855    3498
-       2       0    0.01    3504    3498
-       6       3    0.08    3884    3498
-       3       0    0.00    2553    3498
-       7       0    0.00    2126    3498
-10.783983 sec
+sudo ./turbostat --quiet --cpu 0-3 --show CPU --add msr0x199,u32,raw,PRF_CTRL sleep .1
+0.101604 sec
+CPU	  PRF_CTRL
+-	0x00000000
+0	0x00000c00
+1	0x00000800
+2	0x00000a00
+3	0x00000800
 
 .fi
-Above the cycle soaker drives cpu5 up its 3.9 GHz turbo limit.
-The first row shows the average MHz and Busy% across all the processors in the system.
-
-Note that the Avg_MHz column reflects the total number of cycles executed
-divided by the measurement interval.  If the Busy% column is 100%,
-then the processor was running at that speed the entire interval.
-The Avg_MHz multiplied by the Busy% results in the Bzy_MHz --
-which is the average frequency while the processor was executing --
-not including any non-busy idle time.
 
 .SH NOTES
 
-- 
GitLab


From 4e4e1e7c6eaf387f8ec803f37f154fdd60e303c0 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 21 Feb 2017 22:33:42 -0500
Subject: [PATCH 372/898] tools/power turbostat: move --Package and --processor
 into the --cpu option

--Package is now "--cpu package",
which will display just the 1st CPU in each package

--processor is not "--cpu core"
which will display just the 1st CPU in each core

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.8 |  6 +-----
 tools/power/x86/turbostat/turbostat.c | 31 +++++++++++++++++----------
 2 files changed, 21 insertions(+), 16 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index b1b1ab80102c..5189d9d982fe 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -52,7 +52,7 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 		as the column header.
 .fi
 .PP
-\fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  cpu-set is a comma delimited list of cpu ranges. cpu ranges can be individual cpu numbers or start and end numbers, separated by ".." or '-'.  eg. 1,2,8,14..17,21-44
+\fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed.  Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed.  Otherwise, the system summary plus the specified set of CPUs are printed.  The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44
 .PP
 \fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
 .PP
@@ -71,12 +71,8 @@ The file is truncated if it already exists, and it is created if it does not exi
 .PP
 \fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts.
 .PP
-\fB--Package\fP limits output to the system summary plus the 1st thread in each Package.
-.PP
 \fB--list\fP display column header names available for use by --show and --hide, then exit.
 .PP
-\fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package.  Ie. it skips hyper-threaded siblings.
-.PP
 \fB--Summary\fP limits output to a 1-line System Summary for each interval.
 .PP
 \fB--TCC temperature\fP sets the Thermal Control Circuit temperature for systems which do not export that value.  This is used for making sense of the Digital Thermal Sensor outputs, as they return degrees Celsius below the TCC activation temperature.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 851eaf06f358..c005d9052679 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -4153,7 +4153,8 @@ void help()
 	"to print statistics, until interrupted.\n"
 	"--add		add a counter\n"
 	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
-	"--cpu	cpu-set	limit output to summary plus cpu-set cpu-set\n"
+	"--cpu	cpu-set	limit output to summary plus cpu-set:\n"
+	"		{core | package | j,k,l..m,n-p }\n"
 	"--quiet	skip decoding system configuration header\n"
 	"--interval sec	Override default 5-second measurement interval\n"
 	"--help		print this help message\n"
@@ -4756,6 +4757,21 @@ void parse_cpu_command(char *optarg)
 	unsigned int start, end;
 	char *next;
 
+	if (!strcmp(optarg, "core")) {
+		if (cpu_subset)
+			goto error;
+		show_core_only++;
+		return;
+	}
+	if (!strcmp(optarg, "package")) {
+		if (cpu_subset)
+			goto error;
+		show_pkg_only++;
+		return;
+	}
+	if (show_core_only || show_pkg_only)
+		goto error;
+
 	cpu_subset = CPU_ALLOC(CPU_SUBSET_MAXCPUS);
 	if (cpu_subset == NULL)
 		err(3, "CPU_ALLOC");
@@ -4813,7 +4829,8 @@ void parse_cpu_command(char *optarg)
 	return;
 
 error:
-	fprintf(stderr, "'--cpu %s' malformed\n", optarg);
+	fprintf(stderr, "\"--cpu %s\" malformed\n", optarg);
+	help();
 	exit(-1);
 }
 
@@ -4867,8 +4884,6 @@ void cmdline(int argc, char **argv)
 		{"Joules",	no_argument,		0, 'J'},
 		{"list",	no_argument,		0, 'l'},
 		{"out",		required_argument,	0, 'o'},
-		{"Package",	no_argument,		0, 'p'},
-		{"processor",	no_argument,		0, 'p'},
 		{"quiet",	no_argument,		0, 'q'},
 		{"show",	required_argument,	0, 's'},
 		{"Summary",	no_argument,		0, 'S'},
@@ -4879,7 +4894,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpqST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -4925,12 +4940,6 @@ void cmdline(int argc, char **argv)
 		case 'o':
 			outf = fopen_or_die(optarg, "w");
 			break;
-		case 'P':
-			show_pkg_only++;
-			break;
-		case 'p':
-			show_core_only++;
-			break;
 		case 'q':
 			quiet = 1;
 			break;
-- 
GitLab


From dd778a5e6bbd0f52f34c61ae9b42b725c5f22398 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 21 Feb 2017 23:21:13 -0500
Subject: [PATCH 373/898] tools/power turbostat: support "--hide C1" etc.

Originally, the only way to hide the sysfs C-state statistics columns
was with "--hide sysfs".  This was because we process "--hide" before
we probe for those columns.

hack --hide to remember deferred hide requests, and apply
them when sysfs is probed.

"--hide sysfs" is still available as short-hand to refer to
the entire group of counters.

The down-side of this change is that we no longer error check for
bogus --hide column names.  But the user will quickly figure that
out if a column they mean to hide is still there...

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.8 |   2 +-
 tools/power/x86/turbostat/turbostat.c | 115 ++++++++++++++++----------
 2 files changed, 73 insertions(+), 44 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 5189d9d982fe..fedca3285326 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -114,7 +114,7 @@ This is ideal for remote debugging, use the "--out" option to save everything to
 .PP
 When you are not interested in all that information, and there are several ways to see only what you want.  First the "--quiet" option will skip the configuration information, and turbostat will show only the counter columns.  Second, you can reduce the columns with the "--hide" and "--show" options.  If you use the "--show" option, then turbostat will show only the columns you list.  If you use the "--hide" option, turbostat will show all columns, except the ones you list.
 .PP
-To find out what columns are available for --show and --hide, the "--list" option is available.  Note, however, there is an exception.  The C-state columns collected from sysfs "C1,C2,C3,C1%,C2%,C3%" are not built-in counters, but are discovered after --show and --hide are processed.  You can use the special counter name "sysfs" to refer to all of them at the same time.
+To find out what columns are available for --show and --hide, the "--list" option is available.  For convenience, the special strings "sysfs" can be used to refer to all of the sysfs C-state counters at once:
 .nf
 sudo ./turbostat --show sysfs --quiet sleep 10
 10.003837 sec
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index c005d9052679..596259f48f50 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -434,12 +434,45 @@ unsigned long long bic_present = BIC_sysfs;
 #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
 #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
 
+#define MAX_DEFERRED 16
+char *deferred_skip_names[MAX_DEFERRED];
+int deferred_skip_index;
+
+/*
+ * HIDE_LIST - hide this list of counters, show the rest [default]
+ * SHOW_LIST - show this list of counters, hide the rest
+ */
+enum show_hide_mode { SHOW_LIST, HIDE_LIST } global_show_hide_mode = HIDE_LIST;
+
+void help(void)
+{
+	fprintf(outf,
+	"Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
+	"\n"
+	"Turbostat forks the specified COMMAND and prints statistics\n"
+	"when COMMAND completes.\n"
+	"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
+	"to print statistics, until interrupted.\n"
+	"--add		add a counter\n"
+	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
+	"--cpu	cpu-set	limit output to summary plus cpu-set:\n"
+	"		{core | package | j,k,l..m,n-p }\n"
+	"--quiet	skip decoding system configuration header\n"
+	"--interval sec	Override default 5-second measurement interval\n"
+	"--help		print this help message\n"
+	"--list		list column headers only\n"
+	"--out file	create or truncate \"file\" for all output\n"
+	"--version	print version information\n"
+	"\n"
+	"For more help, run \"man turbostat\"\n");
+}
+
 /*
  * bic_lookup
  * for all the strings in comma separate name_list,
  * set the approprate bit in return value.
  */
-unsigned long long bic_lookup(char *name_list)
+unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
 {
 	int i;
 	unsigned long long retval = 0;
@@ -459,8 +492,19 @@ unsigned long long bic_lookup(char *name_list)
 			}
 		}
 		if (i == MAX_BIC) {
-			fprintf(stderr, "Invalid counter name: %s\n", name_list);
-			exit(-1);
+			if (mode == SHOW_LIST) {
+				fprintf(stderr, "Invalid counter name: %s\n", name_list);
+				exit(-1);
+			}
+			deferred_skip_names[deferred_skip_index++] = name_list;
+			if (debug)
+				fprintf(stderr, "deferred \"%s\"\n", name_list);
+			if (deferred_skip_index >= MAX_DEFERRED) {
+				fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n",
+					MAX_DEFERRED, name_list);
+				help();
+				exit(1);
+			}
 		}
 
 		name_list = comma;
@@ -471,6 +515,7 @@ unsigned long long bic_lookup(char *name_list)
 	return retval;
 }
 
+
 void print_header(char *delim)
 {
 	struct msr_counter *mp;
@@ -502,20 +547,17 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sSMI", (printed++ ? delim : ""));
 
 	for (mp = sys.tp; mp; mp = mp->next) {
-		if (*delim == ',') {
-			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), "sysfs");
-			break;
-		}
+
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
-				outp += sprintf(outp, "%s%18.18s", delim, mp->name);
+				outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), mp->name);
 			else
-				outp += sprintf(outp, "%s%10.10s", delim, mp->name);
+				outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), mp->name);
 		} else {
 			if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns)
-				outp += sprintf(outp, "%s%8s", delim, mp->name);
+				outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), mp->name);
 			else
-				outp += sprintf(outp, "%s%s", delim, mp->name);
+				outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), mp->name);
 		}
 	}
 
@@ -4142,29 +4184,6 @@ void process_cpuid()
 	return;
 }
 
-void help()
-{
-	fprintf(outf,
-	"Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
-	"\n"
-	"Turbostat forks the specified COMMAND and prints statistics\n"
-	"when COMMAND completes.\n"
-	"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
-	"to print statistics, until interrupted.\n"
-	"--add		add a counter\n"
-	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
-	"--cpu	cpu-set	limit output to summary plus cpu-set:\n"
-	"		{core | package | j,k,l..m,n-p }\n"
-	"--quiet	skip decoding system configuration header\n"
-	"--interval sec	Override default 5-second measurement interval\n"
-	"--help		print this help message\n"
-	"--list		list column headers only\n"
-	"--out file	create or truncate \"file\" for all output\n"
-	"--version	print version information\n"
-	"\n"
-	"For more help, run \"man turbostat\"\n");
-}
-
 
 /*
  * in /dev/cpu/ return success for names that are numbers
@@ -4689,6 +4708,16 @@ void parse_add_command(char *add_command)
 	}
 }
 
+int is_deferred_skip(char *name)
+{
+	int i;
+
+	for (i = 0; i < deferred_skip_index; ++i)
+		if (!strcmp(name, deferred_skip_names[i]))
+			return 1;
+	return 0;
+}
+
 void probe_sysfs(void)
 {
 	char path[64];
@@ -4720,6 +4749,9 @@ void probe_sysfs(void)
 
 		sprintf(path, "cpuidle/state%d/time", state);
 
+		if (is_deferred_skip(name_buf))
+			continue;
+
 		add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_USEC,
 				FORMAT_PERCENT, SYSFS_PERCPU);
 	}
@@ -4741,6 +4773,9 @@ void probe_sysfs(void)
 
 		sprintf(path, "cpuidle/state%d/usage", state);
 
+		if (is_deferred_skip(name_buf))
+			continue;
+
 		add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS,
 				FORMAT_DELTA, SYSFS_PERCPU);
 	}
@@ -4834,12 +4869,6 @@ void parse_cpu_command(char *optarg)
 	exit(-1);
 }
 
-/*
- * HIDE_LIST - hide this list of counters, show the rest [default]
- * SHOW_LIST - show this list of counters, hide the rest
- */
-enum show_hide_mode { SHOW_LIST, HIDE_LIST } global_show_hide_mode = HIDE_LIST;
-
 int shown;
 /*
  * parse_show_hide() - process cmdline to set default counter action
@@ -4853,9 +4882,9 @@ void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
 	 */
 	if (new_mode == SHOW_LIST) {
 		if (shown == 0)
-			bic_enabled = bic_lookup(optarg);
+			bic_enabled = bic_lookup(optarg, new_mode);
 		else
-			bic_enabled |= bic_lookup(optarg);
+			bic_enabled |= bic_lookup(optarg, new_mode);
 		shown = 1;
 
 		return;
@@ -4865,7 +4894,7 @@ void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
 	 * --hide: do not show those specified
 	 *  multiple invocations simply clear more bits in enabled mask
 	 */
-	bic_enabled &= ~bic_lookup(optarg);
+	bic_enabled &= ~bic_lookup(optarg, new_mode);
 
 }
 
-- 
GitLab


From 7da6e3e2125d24040b3648ddc61edf70eb533849 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 21 Feb 2017 23:43:41 -0500
Subject: [PATCH 374/898] tools/power turbostat: show package number, even
 without --debug

On multi-package systems, the "Package" column was being displayed
only if --debug was used.  Show it always.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 596259f48f50..2c674ad5ab80 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -4294,7 +4294,7 @@ void topology_probe()
 	if (debug > 1)
 		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
 			max_package_id, topo.num_packages);
-	if (debug && !summary_only && topo.num_packages > 1)
+	if (!summary_only && topo.num_packages > 1)
 		BIC_PRESENT(BIC_Package);
 
 	topo.num_threads_per_core = max_siblings;
-- 
GitLab


From 7293fccdffdec0ab0c36c4e4cffacb3ff114928e Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Wed, 22 Feb 2017 00:11:12 -0500
Subject: [PATCH 375/898] tools/power turbostat: dump p-state software config

cpu1: cpufreq driver: acpi-cpufreq
cpu1: cpufreq governor: ondemand
cpufreq boost: 1

or

cpu0: cpufreq driver: intel_pstate
cpu0: cpufreq governor: powersave
cpufreq intel_pstate no_turbo: 0

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 50 +++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 2c674ad5ab80..7af5f42a9792 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2979,6 +2979,54 @@ dump_sysfs_cstate_config(void)
 		fclose(input);
 	}
 }
+static void
+dump_sysfs_pstate_config(void)
+{
+	char path[64];
+	char driver_buf[64];
+	char governor_buf[64];
+	FILE *input;
+	int turbo;
+
+	sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_driver",
+			base_cpu);
+	input = fopen(path, "r");
+	if (input == NULL) {
+		fprintf(stderr, "NSFOD %s\n", path);
+		return;
+	}
+	fgets(driver_buf, sizeof(driver_buf), input);
+	fclose(input);
+
+	sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor",
+			base_cpu);
+	input = fopen(path, "r");
+	if (input == NULL) {
+		fprintf(stderr, "NSFOD %s\n", path);
+		return;
+	}
+	fgets(governor_buf, sizeof(governor_buf), input);
+	fclose(input);
+
+	fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf);
+	fprintf(outf, "cpu%d: cpufreq governor: %s", base_cpu, governor_buf);
+
+	sprintf(path, "/sys/devices/system/cpu/cpufreq/boost");
+	input = fopen(path, "r");
+	if (input != NULL) {
+		fscanf(input, "%d", &turbo);
+		fprintf(outf, "cpufreq boost: %d\n", turbo);
+		fclose(input);
+	}
+
+	sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo");
+	input = fopen(path, "r");
+	if (input != NULL) {
+		fscanf(input, "%d", &turbo);
+		fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo);
+		fclose(input);
+	}
+}
 
 
 /*
@@ -4168,6 +4216,8 @@ void process_cpuid()
 
 	if (!quiet)
 		dump_sysfs_cstate_config();
+	if (!quiet)
+		dump_sysfs_pstate_config();
 
 	if (has_skl_msrs(family, model))
 		calculate_tsc_tweak();
-- 
GitLab


From 0815a3d09baf2cd330f75020bdaad0f1adac0ecb Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 23 Feb 2017 17:00:51 -0500
Subject: [PATCH 376/898] tools/power turbostat: show error on exec

When turbostat is run in one-shot command mode,
the parent takes the 'before' counter snapshot,
fork/exec/wait for the child to exit,
takes the 'after' counter snapshot,
and prints the results.

however, if the child fails to exec the command,
it immediately returns, without indicating that
anythign was wrong.

Add an error message showing that exec failed:

sudo turbostat sleeeep 4
...
turbostat: exec sleeeep: No such file or directory
...

Note that the parent will still print out the statistics,
because it can't tell the difference between the failed
exec and a command that is purposefully returning
the same status.  Unfortunately, this may obscure the
error message.  However, if the --out parameter is used,
the error message is evident on stderr.

Reported-by: Wendy Wang <wendy.wang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 7af5f42a9792..2d758abecd56 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -4525,6 +4525,7 @@ int fork_it(char **argv)
 	if (!child_pid) {
 		/* child */
 		execvp(argv[0], argv);
+		err(errno, "exec %s", argv[0]);
 	} else {
 
 		/* parent */
-- 
GitLab


From 5f3aea57773dc7f788e374994636ffc0234a355f Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Thu, 23 Feb 2017 18:10:27 -0500
Subject: [PATCH 377/898] tools/power turbostat: bugfix: --add u32 was printed
 as u64

When the "u32" keyword is used with --add, it means that
the output should be truncated to 32-bits.  This was not
happening and all 64-bits were printed.

Also, when no column name was used for an added MSR,
The default column name was in deximal, eg. MSR16.
Users report that they tend to use hex MSR numbers,
so print them in hex.  To always fit into the columns,
use the syntax M0x10.  Note that the user can always
supply any column header that they want.

eg --add msr0x10,MY_TSC

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 26 +++++++-------------------
 1 file changed, 7 insertions(+), 19 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 2d758abecd56..5216549957f4 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -834,7 +834,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
-				outp += sprintf(outp, "%s0x%08lx", (printed++ ? delim : ""), (unsigned long) t->counter[i]);
+				outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) t->counter[i]);
 			else
 				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
@@ -876,7 +876,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
-				outp += sprintf(outp, "%s0x%08lx", (printed++ ? delim : ""), (unsigned long) c->counter[i]);
+				outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) c->counter[i]);
 			else
 				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
@@ -967,7 +967,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 32)
-				outp += sprintf(outp, "%s0x%08lx", (printed++ ? delim : ""), (unsigned long) p->counter[i]);
+				outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) p->counter[i]);
 			else
 				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->counter[i]);
 		} else if (mp->format == FORMAT_DELTA) {
@@ -4732,22 +4732,10 @@ void parse_add_command(char *add_command)
 
 	/* generate default column header */
 	if (*name_buffer == '\0') {
-		if (format == FORMAT_RAW) {
-			if (width == 32)
-				sprintf(name_buffer, "msr%d", msr_num);
-			else
-				sprintf(name_buffer, "MSR%d", msr_num);
-		} else if (format == FORMAT_DELTA) {
-			if (width == 32)
-				sprintf(name_buffer, "cnt%d", msr_num);
-			else
-				sprintf(name_buffer, "CNT%d", msr_num);
-		} else if (format == FORMAT_PERCENT) {
-			if (width == 32)
-				sprintf(name_buffer, "msr%d%%", msr_num);
-			else
-				sprintf(name_buffer, "MSR%d%%", msr_num);
-		}
+		if (width == 32)
+			sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
+		else
+			sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
 	}
 
 	if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0))
-- 
GitLab


From e3942ed8c66bcff496abee5182422cd542962d9e Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 21 Jan 2017 02:33:23 -0500
Subject: [PATCH 378/898] tools/power turbostat: version 17.02.24

The turbostat before this last set of changes is obsolete.
This new version can do a lot more, but it also has
some different defaults, that might catch some off-guard.
So it seems a good time to give a new version number.

Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 5216549957f4..828dccd3f01e 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -4578,7 +4578,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 4.17 10 Jan 2017"
+	fprintf(outf, "turbostat version 17.02.24"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
-- 
GitLab


From b6b6fbc8310e1b12b05717da9df6953b138f812b Mon Sep 17 00:00:00 2001
From: Chuanxiao Dong <chuanxiao.dong@intel.com>
Date: Wed, 1 Mar 2017 14:34:52 +0800
Subject: [PATCH 379/898] drm/i915/gvt: use pfn_valid for better checking

Before get the page from pfn, use pfn_valid to check if pfn
is able to translate to page structure.

Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 182914c22ac5..241354890603 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -96,10 +96,10 @@ static int gvt_dma_map_iova(struct intel_vgpu *vgpu, kvm_pfn_t pfn,
 	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	dma_addr_t daddr;
 
-	page = pfn_to_page(pfn);
-	if (is_error_page(page))
+	if (unlikely(!pfn_valid(pfn)))
 		return -EFAULT;
 
+	page = pfn_to_page(pfn);
 	daddr = dma_map_page(dev, page, 0, PAGE_SIZE,
 			PCI_DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, daddr))
-- 
GitLab


From df06a2d57711a1472ced72207373eeb6422d4721 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 1 Mar 2017 00:03:37 -0800
Subject: [PATCH 380/898] tools/testing/nvdimm: make iset cookie predictable

For testing changes to the iset cookie algorithm we need a value that is
constant from run-to-run.

Stop including dynamic data in the emulated region_offset values. Also,
pick values that sort in a different order depending on whether the
comparison is a memcmp() of two 8-byte arrays or subtraction of two
64-bit values.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 45be8b55a663..798f17655433 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -887,7 +887,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->range_index = 0+1;
 	memdev->region_index = 4+1;
 	memdev->region_size = SPA0_SIZE/2;
-	memdev->region_offset = t->spa_set_dma[0];
+	memdev->region_offset = 1;
 	memdev->address = 0;
 	memdev->interleave_index = 0;
 	memdev->interleave_ways = 2;
@@ -902,7 +902,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->range_index = 0+1;
 	memdev->region_index = 5+1;
 	memdev->region_size = SPA0_SIZE/2;
-	memdev->region_offset = t->spa_set_dma[0] + SPA0_SIZE/2;
+	memdev->region_offset = (1 << 8);
 	memdev->address = 0;
 	memdev->interleave_index = 0;
 	memdev->interleave_ways = 2;
@@ -917,7 +917,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->range_index = 1+1;
 	memdev->region_index = 4+1;
 	memdev->region_size = SPA1_SIZE/4;
-	memdev->region_offset = t->spa_set_dma[1];
+	memdev->region_offset = (1 << 16);
 	memdev->address = SPA0_SIZE/2;
 	memdev->interleave_index = 0;
 	memdev->interleave_ways = 4;
@@ -932,7 +932,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->range_index = 1+1;
 	memdev->region_index = 5+1;
 	memdev->region_size = SPA1_SIZE/4;
-	memdev->region_offset = t->spa_set_dma[1] + SPA1_SIZE/4;
+	memdev->region_offset = (1 << 24);
 	memdev->address = SPA0_SIZE/2;
 	memdev->interleave_index = 0;
 	memdev->interleave_ways = 4;
@@ -947,7 +947,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->range_index = 1+1;
 	memdev->region_index = 6+1;
 	memdev->region_size = SPA1_SIZE/4;
-	memdev->region_offset = t->spa_set_dma[1] + 2*SPA1_SIZE/4;
+	memdev->region_offset = (1ULL << 32);
 	memdev->address = SPA0_SIZE/2;
 	memdev->interleave_index = 0;
 	memdev->interleave_ways = 4;
@@ -962,7 +962,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->range_index = 1+1;
 	memdev->region_index = 7+1;
 	memdev->region_size = SPA1_SIZE/4;
-	memdev->region_offset = t->spa_set_dma[1] + 3*SPA1_SIZE/4;
+	memdev->region_offset = (1ULL << 40);
 	memdev->address = SPA0_SIZE/2;
 	memdev->interleave_index = 0;
 	memdev->interleave_ways = 4;
@@ -1380,7 +1380,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		memdev->range_index = 11+1;
 		memdev->region_index = 9+1;
 		memdev->region_size = SPA0_SIZE;
-		memdev->region_offset = t->spa_set_dma[2];
+		memdev->region_offset = (1ULL << 48);
 		memdev->address = 0;
 		memdev->interleave_index = 0;
 		memdev->interleave_ways = 1;
-- 
GitLab


From 87bfbddd0935f7a3acf36b883707aee816d4bb49 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Noralf=20Tr=C3=B8nnes?= <noralf@tronnes.org>
Date: Sun, 26 Feb 2017 15:44:42 +0100
Subject: [PATCH 381/898] =?UTF-8?q?MAINTAINERS:=20Remove=20Noralf=20Tr?=
 =?UTF-8?q?=C3=B8nnes=20as=20fbtft=20maintainer?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Due to personal reasons I'm unable to continue as fbtft maintainer.

Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index ad4f2ce991ca..30ff892e1e2f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4979,7 +4979,6 @@ F:	lib/fault-inject.c
 
 FBTFT Framebuffer drivers
 M:	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
-M:	Noralf Trønnes <noralf@tronnes.org>
 S:	Maintained
 F:	drivers/staging/fbtft/
 
-- 
GitLab


From a45e47f4b342884dcf9e40a530033f64c379ffc7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 27 Feb 2017 21:42:16 +0100
Subject: [PATCH 382/898] staging: fsl-mc: fix warning in DT ranges parser

The fsl-mc-bus driver in staging contains a copy of the standard
'ranges' property parsing algorithm with a hack to treat a missing
property the same way as an empty one. This code produces false-positive
warnings for me in an allmodconfig build:

drivers/staging/fsl-mc/bus/fsl-mc-bus.c: In function 'fsl_mc_bus_probe':
drivers/staging/fsl-mc/bus/fsl-mc-bus.c:645:6: error: 'mc_size_cells' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/staging/fsl-mc/bus/fsl-mc-bus.c:682:8: error: 'mc_addr_cells' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/staging/fsl-mc/bus/fsl-mc-bus.c:644:6: note: 'mc_addr_cells' was declared here
drivers/staging/fsl-mc/bus/fsl-mc-bus.c:684:8: error: 'paddr_cells' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/staging/fsl-mc/bus/fsl-mc-bus.c:643:6: note: 'paddr_cells' was declared here

To avoid the warnings, I'm simplifying the argument handling to pass
the number of valid ranges in the property as the function return code
rather than passing it by reference. With this change, gcc can see that
we don't evaluate the cell numbers for an missing ranges property.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/fsl-mc/bus/fsl-mc-bus.c | 22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/staging/fsl-mc/bus/fsl-mc-bus.c b/drivers/staging/fsl-mc/bus/fsl-mc-bus.c
index 47acb0a29842..3be5f25ff113 100644
--- a/drivers/staging/fsl-mc/bus/fsl-mc-bus.c
+++ b/drivers/staging/fsl-mc/bus/fsl-mc-bus.c
@@ -588,8 +588,7 @@ static int parse_mc_ranges(struct device *dev,
 			   int *paddr_cells,
 			   int *mc_addr_cells,
 			   int *mc_size_cells,
-			   const __be32 **ranges_start,
-			   u8 *num_ranges)
+			   const __be32 **ranges_start)
 {
 	const __be32 *prop;
 	int range_tuple_cell_count;
@@ -602,8 +601,6 @@ static int parse_mc_ranges(struct device *dev,
 		dev_warn(dev,
 			 "missing or empty ranges property for device tree node '%s'\n",
 			 mc_node->name);
-
-		*num_ranges = 0;
 		return 0;
 	}
 
@@ -630,8 +627,7 @@ static int parse_mc_ranges(struct device *dev,
 		return -EINVAL;
 	}
 
-	*num_ranges = ranges_len / tuple_len;
-	return 0;
+	return ranges_len / tuple_len;
 }
 
 static int get_mc_addr_translation_ranges(struct device *dev,
@@ -639,7 +635,7 @@ static int get_mc_addr_translation_ranges(struct device *dev,
 						**ranges,
 					  u8 *num_ranges)
 {
-	int error;
+	int ret;
 	int paddr_cells;
 	int mc_addr_cells;
 	int mc_size_cells;
@@ -647,16 +643,16 @@ static int get_mc_addr_translation_ranges(struct device *dev,
 	const __be32 *ranges_start;
 	const __be32 *cell;
 
-	error = parse_mc_ranges(dev,
+	ret = parse_mc_ranges(dev,
 				&paddr_cells,
 				&mc_addr_cells,
 				&mc_size_cells,
-				&ranges_start,
-				num_ranges);
-	if (error < 0)
-		return error;
+				&ranges_start);
+	if (ret < 0)
+		return ret;
 
-	if (!(*num_ranges)) {
+	*num_ranges = ret;
+	if (!ret) {
 		/*
 		 * Missing or empty ranges property ("ranges;") for the
 		 * 'fsl,qoriq-mc' node. In this case, identity mapping
-- 
GitLab


From 9dcfe2c75b51f454f39c2de4756e841228865b47 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Mar 2017 09:25:55 +0100
Subject: [PATCH 383/898] locking/refcounts: Change WARN() to WARN_ONCE()

Linus noticed that the new refcount.h APIs used WARN(), which would turn
into a dmesg DoS if it triggers frequently on some buggy driver.

So make sure we only warn once. These warnings are never supposed to happen,
so it's typically not a problem to lose subsequent warnings.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Elena Reshetova <elena.reshetova@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/CA+55aFzbYUTZ=oqZ2YgDjY0C2_n6ODhTfqj6V+m5xWmDxsuB0w@mail.gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 lib/refcount.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/lib/refcount.c b/lib/refcount.c
index 1d33366189d1..aa09ad3c30b0 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -58,7 +58,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 		val = old;
 	}
 
-	WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
 
 	return true;
 }
@@ -66,7 +66,7 @@ EXPORT_SYMBOL_GPL(refcount_add_not_zero);
 
 void refcount_add(unsigned int i, refcount_t *r)
 {
-	WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_add);
 
@@ -97,7 +97,7 @@ bool refcount_inc_not_zero(refcount_t *r)
 		val = old;
 	}
 
-	WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
 
 	return true;
 }
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(refcount_inc_not_zero);
  */
 void refcount_inc(refcount_t *r)
 {
-	WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_inc);
 
@@ -125,7 +125,7 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 
 		new = val - i;
 		if (new > val) {
-			WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
 			return false;
 		}
 
@@ -164,7 +164,7 @@ EXPORT_SYMBOL_GPL(refcount_dec_and_test);
 
 void refcount_dec(refcount_t *r)
 {
-	WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_dec);
 
@@ -204,7 +204,7 @@ bool refcount_dec_not_one(refcount_t *r)
 
 		new = val - 1;
 		if (new > val) {
-			WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
 			return true;
 		}
 
-- 
GitLab


From 86ef58a4e35e8fa66afb5898cf6dec6a3bb29f67 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 28 Feb 2017 18:32:48 -0800
Subject: [PATCH 384/898] nfit, libnvdimm: fix interleave set cookie
 calculation

The interleave-set cookie is a sum that sanity checks the composition of
an interleave set has not changed from when the namespace was initially
created.  The checksum is calculated by sorting the DIMMs by their
location in the interleave-set. The comparison for the sort must be
64-bit wide, not byte-by-byte as performed by memcmp() in the broken
case.

Fix the implementation to accept correct cookie values in addition to
the Linux "memcmp" order cookies, but only allow correct cookies to be
generated going forward. It does mean that namespaces created by
third-party-tooling, or created by newer kernels with this fix, will not
validate on older kernels. However, there are a couple mitigating
conditions:

    1/ platforms with namespace-label capable NVDIMMs are not widely
       available.

    2/ interleave-sets with a single-dimm are by definition not affected
       (nothing to sort). This covers the QEMU-KVM NVDIMM emulation case.

The cookie stored in the namespace label will be fixed by any write the
namespace label, the most straightforward way to achieve this is to
write to the "alt_name" attribute of a namespace in sysfs.

Cc: <stable@vger.kernel.org>
Fixes: eaf961536e16 ("libnvdimm, nfit: add interleave-set state-tracking infrastructure")
Reported-by: Nicholas Moulin <nicholas.w.moulin@linux.intel.com>
Tested-by: Nicholas Moulin <nicholas.w.moulin@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit/core.c        | 16 +++++++++++++++-
 drivers/nvdimm/namespace_devs.c | 18 ++++++++++++++----
 drivers/nvdimm/nd.h             |  1 +
 drivers/nvdimm/region_devs.c    |  9 +++++++++
 include/linux/libnvdimm.h       |  2 ++
 5 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 7361d00818e2..662036bdc65e 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1603,7 +1603,7 @@ static size_t sizeof_nfit_set_info(int num_mappings)
 		+ num_mappings * sizeof(struct nfit_set_info_map);
 }
 
-static int cmp_map(const void *m0, const void *m1)
+static int cmp_map_compat(const void *m0, const void *m1)
 {
 	const struct nfit_set_info_map *map0 = m0;
 	const struct nfit_set_info_map *map1 = m1;
@@ -1612,6 +1612,14 @@ static int cmp_map(const void *m0, const void *m1)
 			sizeof(u64));
 }
 
+static int cmp_map(const void *m0, const void *m1)
+{
+	const struct nfit_set_info_map *map0 = m0;
+	const struct nfit_set_info_map *map1 = m1;
+
+	return map0->region_offset - map1->region_offset;
+}
+
 /* Retrieve the nth entry referencing this spa */
 static struct acpi_nfit_memory_map *memdev_from_spa(
 		struct acpi_nfit_desc *acpi_desc, u16 range_index, int n)
@@ -1667,6 +1675,12 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 	sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map),
 			cmp_map, NULL);
 	nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
+
+	/* support namespaces created with the wrong sort order */
+	sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map),
+			cmp_map_compat, NULL);
+	nd_set->altcookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
+
 	ndr_desc->nd_set = nd_set;
 	devm_kfree(dev, info);
 
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index ce3e8dfa10ad..1b481a5fb966 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1700,6 +1700,7 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id)
 struct device *create_namespace_pmem(struct nd_region *nd_region,
 		struct nd_namespace_label *nd_label)
 {
+	u64 altcookie = nd_region_interleave_set_altcookie(nd_region);
 	u64 cookie = nd_region_interleave_set_cookie(nd_region);
 	struct nd_label_ent *label_ent;
 	struct nd_namespace_pmem *nspm;
@@ -1718,7 +1719,11 @@ struct device *create_namespace_pmem(struct nd_region *nd_region,
 	if (__le64_to_cpu(nd_label->isetcookie) != cookie) {
 		dev_dbg(&nd_region->dev, "invalid cookie in label: %pUb\n",
 				nd_label->uuid);
-		return ERR_PTR(-EAGAIN);
+		if (__le64_to_cpu(nd_label->isetcookie) != altcookie)
+			return ERR_PTR(-EAGAIN);
+
+		dev_dbg(&nd_region->dev, "valid altcookie in label: %pUb\n",
+				nd_label->uuid);
 	}
 
 	nspm = kzalloc(sizeof(*nspm), GFP_KERNEL);
@@ -1733,9 +1738,14 @@ struct device *create_namespace_pmem(struct nd_region *nd_region,
 	res->name = dev_name(&nd_region->dev);
 	res->flags = IORESOURCE_MEM;
 
-	for (i = 0; i < nd_region->ndr_mappings; i++)
-		if (!has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i))
-			break;
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		if (has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i))
+			continue;
+		if (has_uuid_at_pos(nd_region, nd_label->uuid, altcookie, i))
+			continue;
+		break;
+	}
+
 	if (i < nd_region->ndr_mappings) {
 		struct nvdimm_drvdata *ndd = to_ndd(&nd_region->mapping[i]);
 
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 35dd75057e16..2a99c83aa19f 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -328,6 +328,7 @@ struct nd_region *to_nd_region(struct device *dev);
 int nd_region_to_nstype(struct nd_region *nd_region);
 int nd_region_register_namespaces(struct nd_region *nd_region, int *err);
 u64 nd_region_interleave_set_cookie(struct nd_region *nd_region);
+u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region);
 void nvdimm_bus_lock(struct device *dev);
 void nvdimm_bus_unlock(struct device *dev);
 bool is_nvdimm_bus_locked(struct device *dev);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 7cd705f3247c..b7cb5066d961 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -505,6 +505,15 @@ u64 nd_region_interleave_set_cookie(struct nd_region *nd_region)
 	return 0;
 }
 
+u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region)
+{
+	struct nd_interleave_set *nd_set = nd_region->nd_set;
+
+	if (nd_set)
+		return nd_set->altcookie;
+	return 0;
+}
+
 void nd_mapping_free_labels(struct nd_mapping *nd_mapping)
 {
 	struct nd_label_ent *label_ent, *e;
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 8458c5351e56..77e7af32543f 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -70,6 +70,8 @@ struct nd_cmd_desc {
 
 struct nd_interleave_set {
 	u64 cookie;
+	/* compatibility with initial buggy Linux implementation */
+	u64 altcookie;
 };
 
 struct nd_mapping_desc {
-- 
GitLab


From 75013fb16f8484898eaa8d0b08fed942d790f029 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 1 Mar 2017 01:23:24 +0900
Subject: [PATCH 385/898] kprobes/x86: Fix kernel panic when certain
 exception-handling addresses are probed

Fix to the exception table entry check by using probed address
instead of the address of copied instruction.

This bug may cause unexpected kernel panic if user probe an address
where an exception can happen which should be fixup by __ex_table
(e.g. copy_from_user.)

Unless user puts a kprobe on such address, this doesn't
cause any problem.

This bug has been introduced years ago, by commit:

  464846888d9a ("x86/kprobes: Fix a bug which can modify kernel code permanently").

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 464846888d9a ("x86/kprobes: Fix a bug which can modify kernel code permanently")
Link: http://lkml.kernel.org/r/148829899399.28855.12581062400757221722.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/kprobes/common.h | 2 +-
 arch/x86/kernel/kprobes/core.c   | 6 +++---
 arch/x86/kernel/kprobes/opt.c    | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f927ab..d688826e5736 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
 #endif
 
 /* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
 /* Recover instruction if given address is probed */
 extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
 					 unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 520b8dfe1640..88b3c942473d 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -166,12 +166,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
 
-	if (search_exception_tables((unsigned long)opcodes))
+	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
 
 retry:
@@ -416,7 +416,7 @@ static int arch_copy_kprobe(struct kprobe *p)
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	if (can_boost(p->ainsn.insn))
+	if (can_boost(p->ainsn.insn, p->addr))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3d1bee9d6a72..3e7c6e5a08ff 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
 
 	while (len < RELATIVEJUMP_SIZE) {
 		ret = __copy_instruction(dest + len, src + len);
-		if (!ret || !can_boost(dest + len))
+		if (!ret || !can_boost(dest + len, src + len))
 			return -EINVAL;
 		len += ret;
 	}
-- 
GitLab


From 10bce8410607a18eb3adf5d2739db8c8593e110d Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Mon, 27 Feb 2017 23:50:58 +0100
Subject: [PATCH 386/898] x86/kdebugfs: Move boot params hierarchy under
 (debugfs)/x86/

... since this is all x86-specific data and it makes sense to have it
under x86/ logically instead in the toplevel debugfs dir.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170227225058.27289-1-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/kdebugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index bdb83e431d89..38b64587b31b 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void)
 	struct dentry *dbp, *version, *data;
 	int error = -ENOMEM;
 
-	dbp = debugfs_create_dir("boot_params", NULL);
+	dbp = debugfs_create_dir("boot_params", arch_debugfs_dir);
 	if (!dbp)
 		return -ENOMEM;
 
-- 
GitLab


From e7c95effcd3a7a0c9535c809141ca499fede2c31 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 28 Feb 2017 07:05:59 +0100
Subject: [PATCH 387/898] s390/crypt: fix missing unlock in ctr_paes_crypt on
 error path

The ctr mode of protected key aes uses the ctrblk page if the
ctrblk_lock could be acquired. If the protected key has to be
reestablished and this operation fails the unlock for the
ctrblk_lock is missing. Add it.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/crypto/paes_s390.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index d69ea495c4d7..716b17238599 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -474,8 +474,11 @@ static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 			ret = blkcipher_walk_done(desc, walk, nbytes - n);
 		}
 		if (k < n) {
-			if (__ctr_paes_set_key(ctx) != 0)
+			if (__ctr_paes_set_key(ctx) != 0) {
+				if (locked)
+					spin_unlock(&ctrblk_lock);
 				return blkcipher_walk_done(desc, walk, -EIO);
+			}
 		}
 	}
 	if (locked)
-- 
GitLab


From d9fcf2a1cbd1ff65d0109b1b400938808007fcd5 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 28 Feb 2017 07:42:01 +0100
Subject: [PATCH 388/898] s390: fix in-kernel program checks

A program check inside the kernel takes a slightly different path in
entry.S compare to a normal user fault. A recent change moved the store
of the breaking event address into the path taken for in-kernel program
checks as well, but %r14 has not been setup to point to the correct
location. A wild store is the consequence.

Move the store of the breaking event address to the code path for
user space faults.

Fixes: 34525e1f7e8d ("s390: store breaking event address only for program checks")
Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/entry.S | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index dff2152350a7..6a7d737d514c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -490,7 +490,7 @@ ENTRY(pgm_check_handler)
 	jnz	.Lpgm_svcper		# -> single stepped svc
 1:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	j	3f
+	j	4f
 2:	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
 	lg	%r15,__LC_KERNEL_STACK
 	lgr	%r14,%r12
@@ -499,8 +499,8 @@ ENTRY(pgm_check_handler)
 	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
 	jz	3f
 	mvc	__THREAD_trap_tdb(256,%r14),0(%r13)
-3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
-	stg	%r10,__THREAD_last_break(%r14)
+3:	stg	%r10,__THREAD_last_break(%r14)
+4:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	stmg	%r8,%r9,__PT_PSW(%r11)
@@ -509,14 +509,14 @@ ENTRY(pgm_check_handler)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	stg	%r10,__PT_ARGS(%r11)
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
-	jz	4f
+	jz	5f
 	tmhh	%r8,0x0001		# kernel per event ?
 	jz	.Lpgm_kprobe
 	oi	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
 	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
 	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
-4:	REENABLE_IRQS
+5:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table
 	llgh	%r10,__PT_INT_CODE+2(%r11)
-- 
GitLab


From e69ca822ce0ed3ba006ce384d7d205c81d92373f Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 1 Mar 2017 09:16:03 +0100
Subject: [PATCH 389/898] s390/cputime: remove last traces of cputime_t

The cputime_t type is a thing of the past, replace the last occurences
of the type in the s390 code with a simple u64.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/cputime.h | 14 ++------------
 arch/s390/kernel/vtime.c        |  2 +-
 2 files changed, 3 insertions(+), 13 deletions(-)

diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index d1c407ddf703..e5672d6276a6 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -8,32 +8,22 @@
 #define _S390_CPUTIME_H
 
 #include <linux/types.h>
-#include <asm/div64.h>
 
 #define CPUTIME_PER_USEC 4096ULL
 #define CPUTIME_PER_SEC (CPUTIME_PER_USEC * USEC_PER_SEC)
 
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
 
-typedef unsigned long long __nocast cputime_t;
-typedef unsigned long long __nocast cputime64_t;
-
 #define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
 
-static inline unsigned long __div(unsigned long long n, unsigned long base)
-{
-	return n / base;
-}
-
 /*
  * Convert cputime to microseconds and back.
  */
-static inline unsigned int cputime_to_usecs(const cputime_t cputime)
+static inline u64 cputime_to_usecs(const u64 cputime)
 {
-	return (__force unsigned long long) cputime >> 12;
+	return cputime >> 12;
 }
 
-
 u64 arch_cpu_idle_time(int cpu);
 
 #define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 31bd96e81167..8f5f59a151b4 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -111,7 +111,7 @@ static inline u64 scale_vtime(u64 vtime)
 }
 
 static void account_system_index_scaled(struct task_struct *p,
-					cputime_t cputime, cputime_t scaled,
+					u64 cputime, u64 scaled,
 					enum cpu_usage_stat index)
 {
 	p->stimescaled += cputime_to_nsecs(scaled);
-- 
GitLab


From 3c915bdc1775acfa214195da1ffb39dabdd1a389 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 1 Mar 2017 09:18:34 +0100
Subject: [PATCH 390/898] s390/cputime: reset all accounting fields on fork

copy_thread has to reset all cputime related field in the task struct,
not only user_timer and system_timer.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/process.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 54281660582c..249deafaa6ee 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -121,7 +121,10 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp,
 	clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
 	/* Initialize per thread user and system timer values */
 	p->thread.user_timer = 0;
+	p->thread.guest_timer = 0;
 	p->thread.system_timer = 0;
+	p->thread.hardirq_timer = 0;
+	p->thread.softirq_timer = 0;
 
 	frame->sf.back_chain = 0;
 	/* new return point is ret_from_fork */
-- 
GitLab


From e53051e757d6cd66741955b93581e54415e48a70 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 1 Mar 2017 09:21:10 +0100
Subject: [PATCH 391/898] s390/cputime: provide archicture specific
 cputime_to_nsecs

The generic cputime_to_nsecs function first converts the cputime
to micro-seconds and then multiplies the result with 1000. This
looses some bits of accuracy, provide our own version of
cputime_to_nsecs that does not loose precision.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/cputime.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index e5672d6276a6..9072bf63a846 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -8,6 +8,7 @@
 #define _S390_CPUTIME_H
 
 #include <linux/types.h>
+#include <asm/timex.h>
 
 #define CPUTIME_PER_USEC 4096ULL
 #define CPUTIME_PER_SEC (CPUTIME_PER_USEC * USEC_PER_SEC)
@@ -17,13 +18,18 @@
 #define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
 
 /*
- * Convert cputime to microseconds and back.
+ * Convert cputime to microseconds.
  */
 static inline u64 cputime_to_usecs(const u64 cputime)
 {
 	return cputime >> 12;
 }
 
+/*
+ * Convert cputime to nanoseconds.
+ */
+#define cputime_to_nsecs(cputime) tod_to_ns(cputime)
+
 u64 arch_cpu_idle_time(int cpu);
 
 #define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
-- 
GitLab


From d03bd0454b101adb94d0b5a9cc11396182943cb4 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 1 Mar 2017 09:47:57 +0100
Subject: [PATCH 392/898] s390/timex: micro optimization for tod_to_ns

The conversion of a TOD value to nano-seconds currently uses a 32/32 bit
split with the calculation for "nsecs = (TOD * 125) >> 9". Using a
55/9 bit split saves an instruction.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/timex.h | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 354344dcc198..118535123f34 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -206,20 +206,16 @@ static inline unsigned long long get_tod_clock_monotonic(void)
  *    ns = (todval * 125) >> 9;
  *
  * In order to avoid an overflow with the multiplication we can rewrite this.
- * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits)
+ * With a split todval == 2^9 * th + tl (th upper 55 bits, tl lower 9 bits)
  * we end up with
  *
- *    ns = ((2^32 * th + tl) * 125 ) >> 9;
- * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9);
+ *    ns = ((2^9 * th + tl) * 125 ) >> 9;
+ * -> ns = (th * 125) + ((tl * 125) >> 9);
  *
  */
 static inline unsigned long long tod_to_ns(unsigned long long todval)
 {
-	unsigned long long ns;
-
-	ns = ((todval >> 32) << 23) * 125;
-	ns += ((todval & 0xffffffff) * 125) >> 9;
-	return ns;
+	return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
 }
 
 #endif
-- 
GitLab


From b28ace12661fbcfd90959c1e84ff5a85113a82a1 Mon Sep 17 00:00:00 2001
From: Franck Demathieu <fdemathieu@gmail.com>
Date: Thu, 23 Feb 2017 10:48:55 +0100
Subject: [PATCH 393/898] irqchip/crossbar: Fix incorrect type of local
 variables

The max and entry variables are unsigned according to the dt-bindings.
Fix following 3 sparse issues (-Wtypesign):

  drivers/irqchip/irq-crossbar.c:222:52: warning: incorrect type in argument 3 (different signedness)
  drivers/irqchip/irq-crossbar.c:222:52:    expected unsigned int [usertype] *out_value
  drivers/irqchip/irq-crossbar.c:222:52:    got int *<noident>

  drivers/irqchip/irq-crossbar.c:245:56: warning: incorrect type in argument 4 (different signedness)
  drivers/irqchip/irq-crossbar.c:245:56:    expected unsigned int [usertype] *out_value
  drivers/irqchip/irq-crossbar.c:245:56:    got int *<noident>

  drivers/irqchip/irq-crossbar.c:263:56: warning: incorrect type in argument 4 (different signedness)
  drivers/irqchip/irq-crossbar.c:263:56:    expected unsigned int [usertype] *out_value
  drivers/irqchip/irq-crossbar.c:263:56:    got int *<noident>

Signed-off-by: Franck Demathieu <fdemathieu@gmail.com>
Cc: marc.zyngier@arm.com
Cc: jason@lakedaemon.net
Link: http://lkml.kernel.org/r/20170223094855.6546-1-fdemathieu@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/irqchip/irq-crossbar.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 1eef56a89b1f..05bbf171df37 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -198,7 +198,8 @@ static const struct irq_domain_ops crossbar_domain_ops = {
 
 static int __init crossbar_of_init(struct device_node *node)
 {
-	int i, size, max = 0, reserved = 0, entry;
+	int i, size, reserved = 0;
+	u32 max = 0, entry;
 	const __be32 *irqsr;
 	int ret = -ENOMEM;
 
-- 
GitLab


From bb3f0a52630c84807fca9bdd76ac2f5dcec82689 Mon Sep 17 00:00:00 2001
From: Dou Liyang <douly.fnst@cn.fujitsu.com>
Date: Tue, 28 Feb 2017 13:50:52 +0800
Subject: [PATCH 394/898] x86/apic: Fix a warning message in logical CPU IDs
 allocation

The current warning message in allocate_logical_cpuid() is somewhat confusing:

  Only 1 processors supported.Processor 2/0x2 and the rest are ignored.

As it might imply that there's only one CPU in the system - while what we ran
into here is a kernel limitation.

Fix the warning message to clarify all that:

  APIC: NR_CPUS/possible_cpus limit of 2 reached. Processor 2/0x2 and the rest are ignored.

( Also update the error return from -1 to -EINVAL, which is the more
  canonical return value. )

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bp@alien8.de
Cc: nicstange@gmail.com
Cc: wanpeng.li@hotmail.com
Link: http://lkml.kernel.org/r/1488261052-25753-1-git-send-email-douly.fnst@cn.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/apic/apic.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4261b3282ad9..11088b86e5c7 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2062,10 +2062,10 @@ static int allocate_logical_cpuid(int apicid)
 
 	/* Allocate a new cpuid. */
 	if (nr_logical_cpuids >= nr_cpu_ids) {
-		WARN_ONCE(1, "Only %d processors supported."
+		WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. "
 			     "Processor %d/0x%x and the rest are ignored.\n",
-			     nr_cpu_ids - 1, nr_logical_cpuids, apicid);
-		return -1;
+			     nr_cpu_ids, nr_logical_cpuids, apicid);
+		return -EINVAL;
 	}
 
 	cpuid_to_apicid[nr_logical_cpuids] = apicid;
-- 
GitLab


From 11277aabcbbe13916151af897d29a5e9f71ca73f Mon Sep 17 00:00:00 2001
From: Dou Liyang <douly.fnst@cn.fujitsu.com>
Date: Thu, 23 Feb 2017 17:16:41 +0800
Subject: [PATCH 395/898] x86/apic: Simplify enable_IR_x2apic(), remove
 try_to_enable_IR()

The following commit:

  2e63ad4bd5dd ("x86/apic: Do not init irq remapping if ioapic is disabled")

... added a check for skipped IO-APIC setup to enable_IR_x2apic(), but this
check is also duplicated in try_to_enable_IR() - and it will never succeed in
calling irq_remapping_enable().

Remove the whole irq_remapping_enable() complication: if the IO-APIC is
disabled we cannot enable IRQ remapping.

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bp@alien8.de
Cc: nicstange@gmail.com
Cc: wanpeng.li@hotmail.com
Link: http://lkml.kernel.org/r/1487841401-1543-1-git-send-email-douly.fnst@cn.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/apic/apic.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 11088b86e5c7..aee7deddabd0 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1610,24 +1610,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { }
 static inline void __x2apic_enable(void) { }
 #endif /* !CONFIG_X86_X2APIC */
 
-static int __init try_to_enable_IR(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	if (!x2apic_enabled() && skip_ioapic_setup) {
-		pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
-		return -1;
-	}
-#endif
-	return irq_remapping_enable();
-}
-
 void __init enable_IR_x2apic(void)
 {
 	unsigned long flags;
 	int ret, ir_stat;
 
-	if (skip_ioapic_setup)
+	if (skip_ioapic_setup) {
+		pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
 		return;
+	}
 
 	ir_stat = irq_remapping_prepare();
 	if (ir_stat < 0 && !x2apic_supported())
@@ -1645,7 +1636,7 @@ void __init enable_IR_x2apic(void)
 
 	/* If irq_remapping_prepare() succeeded, try to enable it */
 	if (ir_stat >= 0)
-		ir_stat = try_to_enable_IR();
+		ir_stat = irq_remapping_enable();
 	/* ir_stat contains the remap mode or an error code */
 	try_to_enable_x2apic(ir_stat);
 
-- 
GitLab


From 2a4d0c627f5374f365a873dea4e10ae0bb437680 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dsafonov@virtuozzo.com>
Date: Mon, 13 Feb 2017 13:13:36 +0300
Subject: [PATCH 396/898] x86/selftests: Add clobbers for int80 on x86_64

Kernel erases R8..R11 registers prior returning to userspace
from int80:

  https://lkml.org/lkml/2009/10/1/164

GCC can reuse these registers and doesn't expect them to change
during syscall invocation. I met this kind of bug in CRIU once
GCC 6.1 and CLANG stored local variables in those registers
and the kernel zerofied them during syscall:

  https://github.com/xemul/criu/commit/990d33f1a1cdd17bca6c2eb059ab3be2564f7fa2

By that reason I suggest to add those registers to clobbers
in selftests.  Also, as noted by Andy - removed unneeded clobber
for flags in INT $0x80 inline asm.

Signed-off-by: Dmitry Safonov <dsafonov@virtuozzo.com>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: 0x7f454c46@gmail.com
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kselftest@vger.kernel.org
Link: http://lkml.kernel.org/r/20170213101336.20486-1-dsafonov@virtuozzo.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/testing/selftests/x86/fsgsbase.c           |  2 +-
 tools/testing/selftests/x86/ldt_gdt.c            | 16 +++++++++++-----
 tools/testing/selftests/x86/ptrace_syscall.c     |  3 ++-
 .../testing/selftests/x86/single_step_syscall.c  |  5 ++++-
 4 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 5b2b4b3c634c..b4967d875236 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -245,7 +245,7 @@ void do_unexpected_base(void)
 		long ret;
 		asm volatile ("int $0x80"
 			      : "=a" (ret) : "a" (243), "b" (low_desc)
-			      : "flags");
+			      : "r8", "r9", "r10", "r11");
 		memcpy(&desc, low_desc, sizeof(desc));
 		munmap(low_desc, sizeof(desc));
 
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 4af47079cf04..f6121612e769 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -45,6 +45,12 @@
 #define AR_DB			(1 << 22)
 #define AR_G			(1 << 23)
 
+#ifdef __x86_64__
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
+#else
+# define INT80_CLOBBERS
+#endif
+
 static int nerrs;
 
 /* Points to an array of 1024 ints, each holding its own index. */
@@ -588,7 +594,7 @@ static int invoke_set_thread_area(void)
 	asm volatile ("int $0x80"
 		      : "=a" (ret), "+m" (low_user_desc) :
 			"a" (243), "b" (low_user_desc)
-		      : "flags");
+		      : INT80_CLOBBERS);
 	return ret;
 }
 
@@ -657,7 +663,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 	if (sel != 0) {
 		result = "FAIL";
@@ -688,7 +694,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 	if (sel != 0) {
 		result = "FAIL";
@@ -721,7 +727,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
 	syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base);
@@ -774,7 +780,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
 	syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base);
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index b037ce9cf116..eaea92439708 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -58,7 +58,8 @@ static void do_full_int80(struct syscall_args32 *args)
 	asm volatile ("int $0x80"
 		      : "+a" (args->nr),
 			"+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2),
-			"+S" (args->arg3), "+D" (args->arg4), "+r" (bp));
+			"+S" (args->arg3), "+D" (args->arg4), "+r" (bp)
+			: : "r8", "r9", "r10", "r11");
 	args->arg5 = bp;
 #else
 	sys32_helper(args, int80_and_ret);
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 50c26358e8b7..a48da95c18fd 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -56,9 +56,11 @@ static volatile sig_atomic_t sig_traps;
 #ifdef __x86_64__
 # define REG_IP REG_RIP
 # define WIDTH "q"
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
 #else
 # define REG_IP REG_EIP
 # define WIDTH "l"
+# define INT80_CLOBBERS
 #endif
 
 static unsigned long get_eflags(void)
@@ -140,7 +142,8 @@ int main()
 
 	printf("[RUN]\tSet TF and check int80\n");
 	set_eflags(get_eflags() | X86_EFLAGS_TF);
-	asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid));
+	asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)
+			: INT80_CLOBBERS);
 	check_result();
 
 	/*
-- 
GitLab


From 6b0b7551428e4caae1e2c023a529465a9a9ae2d4 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Thu, 16 Feb 2017 17:00:50 +1100
Subject: [PATCH 397/898] perf/core: Rename CONFIG_[UK]PROBE_EVENT to
 CONFIG_[UK]PROBE_EVENTS

We have uses of CONFIG_UPROBE_EVENT and CONFIG_KPROBE_EVENT as
well as CONFIG_UPROBE_EVENTS and CONFIG_KPROBE_EVENTS.

Consistently use the plurals.

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: alexander.shishkin@linux.intel.com
Cc: davem@davemloft.net
Cc: sparclinux@vger.kernel.org
Link: http://lkml.kernel.org/r/20170216060050.20866-1-anton@ozlabs.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/trace/kprobetrace.txt         |  2 +-
 Documentation/trace/uprobetracer.txt        |  2 +-
 arch/powerpc/configs/85xx/kmp204x_defconfig |  2 +-
 arch/s390/configs/default_defconfig         |  2 +-
 arch/s390/configs/gcov_defconfig            |  2 +-
 arch/s390/configs/performance_defconfig     |  2 +-
 arch/s390/defconfig                         |  2 +-
 kernel/trace/Kconfig                        |  6 +++---
 kernel/trace/Makefile                       |  4 ++--
 kernel/trace/trace.c                        | 10 +++++-----
 kernel/trace/trace_probe.h                  |  4 ++--
 11 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index e4991fb1eedc..41ef9d8efe95 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -12,7 +12,7 @@ kprobes can probe (this means, all functions body except for __kprobes
 functions). Unlike the Tracepoint based event, this can be added and removed
 dynamically, on the fly.
 
-To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
index fa7b680ee8a0..bf526a7c5559 100644
--- a/Documentation/trace/uprobetracer.txt
+++ b/Documentation/trace/uprobetracer.txt
@@ -7,7 +7,7 @@
 Overview
 --------
 Uprobe based trace events are similar to kprobe based trace events.
-To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/arch/powerpc/configs/85xx/kmp204x_defconfig b/arch/powerpc/configs/85xx/kmp204x_defconfig
index aaaaa609cd24..34a4da23f000 100644
--- a/arch/powerpc/configs/85xx/kmp204x_defconfig
+++ b/arch/powerpc/configs/85xx/kmp204x_defconfig
@@ -210,7 +210,7 @@ CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_SCHEDSTATS=y
 CONFIG_RCU_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_CRYPTO_NULL=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD4=y
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 143b1e00b818..4b176fe83da4 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -609,7 +609,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index f05d2d6e1087..0de46cc397f6 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -560,7 +560,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 2358bf33c5ef..e167557b434c 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -558,7 +558,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 68bfd09f1b02..97189dbaf34b 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -179,7 +179,7 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_KPROBES_SANITY_TEST=y
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d5038005eb5d..d4a06e714645 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -429,7 +429,7 @@ config BLK_DEV_IO_TRACE
 
 	  If unsure, say N.
 
-config KPROBE_EVENT
+config KPROBE_EVENTS
 	depends on KPROBES
 	depends on HAVE_REGS_AND_STACK_ACCESS_API
 	bool "Enable kprobes-based dynamic events"
@@ -447,7 +447,7 @@ config KPROBE_EVENT
 	  This option is also required by perf-probe subcommand of perf tools.
 	  If you want to use perf tools, this option is strongly recommended.
 
-config UPROBE_EVENT
+config UPROBE_EVENTS
 	bool "Enable uprobes-based dynamic events"
 	depends on ARCH_SUPPORTS_UPROBES
 	depends on MMU
@@ -466,7 +466,7 @@ config UPROBE_EVENT
 
 config BPF_EVENTS
 	depends on BPF_SYSCALL
-	depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS
+	depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
 	bool
 	default y
 	help
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e57980845549..90f2701d92a7 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
-obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
@@ -66,7 +66,7 @@ ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
-obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 707445ceb7ef..f35109514a01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4341,22 +4341,22 @@ static const char readme_msg[] =
 	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
 	"\t  accepts: event-definitions (one definition per line)\n"
 	"\t   Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
 	"\t           -:[<group>/]<event>\n"
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"\t    place: <path>:<offset>\n"
 #endif
 	"\t     args: <name>=fetcharg[:type]\n"
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0c0ae54d44c6..903273c93e61 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype),			\
 #define FETCH_TYPE_STRING	0
 #define FETCH_TYPE_STRSIZE	1
 
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
@@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset)
 {
 	return NULL;
 }
-#endif /* CONFIG_KPROBE_EVENT */
+#endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {
 	struct fetch_param	fetch;
-- 
GitLab


From 1b17c6df852851b40c3c27c66b8fa2fd99cf25d8 Mon Sep 17 00:00:00 2001
From: Andrew Banman <abanman@hpe.com>
Date: Fri, 17 Feb 2017 11:07:49 -0600
Subject: [PATCH 398/898] x86/platform/uv/BAU: Fix HUB errors by remove initial
 write to sw-ack register

Writing to the software acknowledge clear register when there are no
pending messages causes a HUB error to assert. The original intent of this
write was to clear the pending bits before start of operation, but this is
an incorrect method and has been determined to be unnecessary.

Signed-off-by: Andrew Banman <abanman@hpe.com>
Acked-by: Mike Travis <mike.travis@hpe.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akpm@linux-foundation.org
Cc: rja@hpe.com
Cc: sivanich@hpe.com
Link: http://lkml.kernel.org/r/1487351269-181133-1-git-send-email-abanman@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/platform/uv/tlb_uv.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 766d4d3529a1..f25982cdff90 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1847,7 +1847,6 @@ static void pq_init(int node, int pnode)
 
 	ops.write_payload_first(pnode, first);
 	ops.write_payload_last(pnode, last);
-	ops.write_g_sw_ack(pnode, 0xffffUL);
 
 	/* in effect, all msg_type's are set to MSG_NOOP */
 	memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
-- 
GitLab


From 90b28ded88dda8bea82b4a86923e73ba0746d884 Mon Sep 17 00:00:00 2001
From: Matjaz Hegedic <matjaz.hegedic@gmail.com>
Date: Sun, 19 Feb 2017 19:32:48 +0100
Subject: [PATCH 399/898] x86/reboot/quirks: Add ASUS EeeBook X205TA reboot
 quirk

Without the parameter reboot=a, ASUS EeeBook X205TA will hang when it should reboot.

This adds the appropriate quirk, thus fixing the problem.

Signed-off-by: Matjaz Hegedic <matjaz.hegedic@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/reboot.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e244c19a2451..01c9cda3e1b7 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -223,6 +223,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
 		},
 	},
+	{	/* Handle problems with rebooting on ASUS EeeBook X205TA */
+		.callback = set_acpi_reboot,
+		.ident = "ASUS EeeBook X205TA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+		},
+	},
 
 	/* Certec */
 	{       /* Handle problems with rebooting on Certec BPC600 */
-- 
GitLab


From 73667e31a153a66da97feb1584726222504924f8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 14 Feb 2017 22:17:17 +0100
Subject: [PATCH 400/898] x86/hyperv: Hide unused label

This new 32-bit warning just showed up:

arch/x86/hyperv/hv_init.c: In function 'hyperv_init':
arch/x86/hyperv/hv_init.c:167:1: error: label 'register_msr_cs' defined but not used [-Werror=unused-label]

The easiest solution is to move the label up into the existing #ifdef that
has the goto.

Fixes: dee863b571b0 ("hv: export current Hyper-V clocksource")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: devel@linuxdriverproject.org
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Link: http://lkml.kernel.org/r/20170214211736.2641241-1-arnd@arndb.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/hyperv/hv_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index db64baf0e500..8bef70e7f3cc 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -158,13 +158,13 @@ void hyperv_init(void)
 		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 		return;
 	}
+register_msr_cs:
 #endif
 	/*
 	 * For 32 bit guests just use the MSR based mechanism for reading
 	 * the partition counter.
 	 */
 
-register_msr_cs:
 	hyperv_cs = &hyperv_cs_msr;
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
-- 
GitLab


From aa5ec3f715d576353c7d8f4f8085634bd845b73f Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Mon, 27 Feb 2017 21:29:22 +0900
Subject: [PATCH 401/898] x86/vmware: Remove duplicate inclusion of asm/timer.h

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Cc: akataria@vmware.com
Cc: virtualization@lists.linux-foundation.org
Link: http://lkml.kernel.org/r/20170227122922.26230-1-standby24x7@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/vmware.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 891f4dad7b2c..22403a28caf5 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -30,7 +30,6 @@
 #include <asm/hypervisor.h>
 #include <asm/timer.h>
 #include <asm/apic.h>
-#include <asm/timer.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)	"vmware: " fmt
-- 
GitLab


From e86a2d2d34e20289ae7d46692e16d43c3a785db9 Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Mon, 27 Feb 2017 22:07:03 +0900
Subject: [PATCH 402/898] x86/intel_rdt: Remove duplicate inclusion of
 linux/cpu.h

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Cc: fenghua.yu@intel.com
Link: http://lkml.kernel.org/r/20170227130703.26968-1-standby24x7@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 8af04afdfcb9..759577d9d166 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -27,7 +27,6 @@
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/cpu.h>
 #include <linux/task_work.h>
 
 #include <uapi/linux/magic.h>
-- 
GitLab


From 153654dbe595a68845ba14d5b0bfe299fa6a7e99 Mon Sep 17 00:00:00 2001
From: Rui Wang <rui.y.wang@intel.com>
Date: Tue, 28 Feb 2017 21:34:28 +0800
Subject: [PATCH 403/898] x86/PCI: Implement pcibios_release_device to release
 IRQ from IOAPIC

The revert of 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq()
and pcibios_free_irq()") causes a problem for IOAPIC hotplug. The
problem is that IRQs are allocated and freed in pci_enable_device()
and pci_disable_device(). But there are some drivers which don't call
pci_disable_device(), and they have good reasons not calling it, so
if they're using IOAPIC their IRQs won't have a chance to be released
from the IOAPIC. When this happens IOAPIC hot-removal fails with a
kernel stack dump and an error message like this:

  [149335.697989] pin16 on IOAPIC2 is still in use.

It turns out that we can fix it in a different way without moving IRQ
allocation into pcibios_alloc_irq(), thus avoiding the regression of
991de2e59090. We can keep the allocation and freeing of IRQs as is
within pci_enable_device()/pci_disable_device(), without breaking any
previous assumption of the rest of the system, keeping compatibility
with both the legacy and the modern drivers. We can accomplish this by
implementing the existing __weak hook of pcibios_release_device() thus
when a pci device is about to be deleted we get notified in the hook
and take the chance to release its IRQ, if any, from the IOAPIC.

Implement pcibios_release_device() for x86 to release any IRQ not released
by the driver.

Signed-off-by: Rui Wang <rui.y.wang@intel.com>
Cc: tony.luck@intel.com
Cc: linux-pci@vger.kernel.org
Cc: rjw@rjwysocki.net
Cc: linux-acpi@vger.kernel.org
Cc: fengguang.wu@intel.com
Cc: helgaas@kernel.org
Cc: kbuild-all@01.org
Cc: bhelgaas@google.com
Link: http://lkml.kernel.org/r/1488288869-31290-2-git-send-email-rui.y.wang@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/pci/common.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 0cb52ae0a8f0..190e718694b1 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -735,6 +735,15 @@ void pcibios_disable_device (struct pci_dev *dev)
 		pcibios_disable_irq(dev);
 }
 
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+void pcibios_release_device(struct pci_dev *dev)
+{
+	if (atomic_dec_return(&dev->enable_cnt) >= 0)
+		pcibios_disable_device(dev);
+
+}
+#endif
+
 int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
-- 
GitLab


From f2ae5da726172fcf82f7be801489dd585f6a38eb Mon Sep 17 00:00:00 2001
From: Rui Wang <rui.y.wang@intel.com>
Date: Tue, 28 Feb 2017 21:34:29 +0800
Subject: [PATCH 404/898] x86/ioapic: Split IOAPIC hot-removal into two steps

The hot removal of IOAPIC is handling PCI and ACPI removal in one go. That
only works when the PCI drivers released the interrupt resources, but
breaks when a IOAPIC interrupt is still associated to a PCI device.

The new pcibios_release_device() callback allows to solve that problem by
splitting the removal into two steps:

1) PCI removal:

   Release all PCI resources including eventually not yet released IOAPIC
   interrupts via the new pcibios_release_device() callback.

2) ACPI removal:

   After release of all PCI resources the ACPI resources can be released
   without issue.

[ tglx: Rewrote changelog ]

Signed-off-by: Rui Wang <rui.y.wang@intel.com>
Cc: tony.luck@intel.com
Cc: linux-pci@vger.kernel.org
Cc: rjw@rjwysocki.net
Cc: linux-acpi@vger.kernel.org
Cc: fengguang.wu@intel.com
Cc: helgaas@kernel.org
Cc: kbuild-all@01.org
Cc: bhelgaas@google.com
Link: http://lkml.kernel.org/r/1488288869-31290-3-git-send-email-rui.y.wang@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/acpi/internal.h |  2 ++
 drivers/acpi/ioapic.c   | 22 ++++++++++++++++------
 drivers/acpi/pci_root.c |  4 ++--
 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 219b90bc0922..f15900132912 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -41,8 +41,10 @@ void acpi_gpe_apply_masked_gpes(void);
 void acpi_container_init(void);
 void acpi_memory_hotplug_init(void);
 #ifdef	CONFIG_ACPI_HOTPLUG_IOAPIC
+void pci_ioapic_remove(struct acpi_pci_root *root);
 int acpi_ioapic_remove(struct acpi_pci_root *root);
 #else
+static inline void pci_ioapic_remove(struct acpi_pci_root *root) { return; }
 static inline int acpi_ioapic_remove(struct acpi_pci_root *root) { return 0; }
 #endif
 #ifdef CONFIG_ACPI_DOCK
diff --git a/drivers/acpi/ioapic.c b/drivers/acpi/ioapic.c
index 6d7ce6e12aaa..1120dfd625b8 100644
--- a/drivers/acpi/ioapic.c
+++ b/drivers/acpi/ioapic.c
@@ -206,24 +206,34 @@ int acpi_ioapic_add(acpi_handle root_handle)
 	return ACPI_SUCCESS(status) && ACPI_SUCCESS(retval) ? 0 : -ENODEV;
 }
 
-int acpi_ioapic_remove(struct acpi_pci_root *root)
+void pci_ioapic_remove(struct acpi_pci_root *root)
 {
-	int retval = 0;
 	struct acpi_pci_ioapic *ioapic, *tmp;
 
 	mutex_lock(&ioapic_list_lock);
 	list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
 		if (root->device->handle != ioapic->root_handle)
 			continue;
-
-		if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base))
-			retval = -EBUSY;
-
 		if (ioapic->pdev) {
 			pci_release_region(ioapic->pdev, 0);
 			pci_disable_device(ioapic->pdev);
 			pci_dev_put(ioapic->pdev);
 		}
+	}
+	mutex_unlock(&ioapic_list_lock);
+}
+
+int acpi_ioapic_remove(struct acpi_pci_root *root)
+{
+	int retval = 0;
+	struct acpi_pci_ioapic *ioapic, *tmp;
+
+	mutex_lock(&ioapic_list_lock);
+	list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
+		if (root->device->handle != ioapic->root_handle)
+			continue;
+		if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base))
+			retval = -EBUSY;
 		if (ioapic->res.flags && ioapic->res.parent)
 			release_resource(&ioapic->res);
 		list_del(&ioapic->list);
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index bf601d4df8cf..919be0aa2578 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -648,12 +648,12 @@ static void acpi_pci_root_remove(struct acpi_device *device)
 
 	pci_stop_root_bus(root->bus);
 
-	WARN_ON(acpi_ioapic_remove(root));
-
+	pci_ioapic_remove(root);
 	device_set_run_wake(root->bus->bridge, false);
 	pci_acpi_remove_bus_pm_notifier(device);
 
 	pci_remove_root_bus(root->bus);
+	WARN_ON(acpi_ioapic_remove(root));
 
 	dmar_device_remove(device->handle);
 
-- 
GitLab


From 58ab9a088ddac4efe823471275859d64f735577e Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 23 Feb 2017 14:26:03 -0800
Subject: [PATCH 405/898] x86/pkeys: Check against max pkey to avoid overflows

Kirill reported a warning from UBSAN about undefined behavior when using
protection keys.  He is running on hardware that actually has support for
it, which is not widely available.

The warning triggers because of very large shifts of integers when doing a
pkey_free() of a large, invalid value. This happens because we never check
that the pkey "fits" into the mm_pkey_allocation_map().

I do not believe there is any danger here of anything bad happening
other than some aliasing issues where somebody could do:

	pkey_free(35);

and the kernel would effectively execute:

	pkey_free(8);

While this might be confusing to an app that was doing something stupid, it
has to do something stupid and the effects are limited to the app shooting
itself in the foot.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: stable@vger.kernel.org
Cc: linux-kselftest@vger.kernel.org
Cc: shuah@kernel.org
Cc: kirill.shutemov@linux.intel.com
Link: http://lkml.kernel.org/r/20170223222603.A022ED65@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/pkeys.h | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 34684adb6899..b3b09b98896d 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -46,6 +46,15 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 static inline
 bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
 {
+	/*
+	 * "Allocated" pkeys are those that have been returned
+	 * from pkey_alloc().  pkey 0 is special, and never
+	 * returned from pkey_alloc().
+	 */
+	if (pkey <= 0)
+		return false;
+	if (pkey >= arch_max_pkey())
+		return false;
 	return mm_pkey_allocation_map(mm) & (1U << pkey);
 }
 
@@ -82,12 +91,6 @@ int mm_pkey_alloc(struct mm_struct *mm)
 static inline
 int mm_pkey_free(struct mm_struct *mm, int pkey)
 {
-	/*
-	 * pkey 0 is special, always allocated and can never
-	 * be freed.
-	 */
-	if (!pkey)
-		return -EINVAL;
 	if (!mm_pkey_is_allocated(mm, pkey))
 		return -EINVAL;
 
-- 
GitLab


From 940b2f2fd963c043418ce8af64605783b2b19140 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Sat, 18 Feb 2017 12:31:40 +0100
Subject: [PATCH 406/898] x86/events: Remove last remnants of old filenames

Update to the new file paths, remove them from introductory comments.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170218113140.8051-1-bp@alien8.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/events/amd/core.c                               | 2 +-
 arch/x86/events/intel/cstate.c                           | 2 +-
 arch/x86/events/intel/rapl.c                             | 2 +-
 arch/x86/events/intel/uncore.h                           | 6 +++---
 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index afb222b63cae..c84584bb9402 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -604,7 +604,7 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 			return &amd_f15_PMC20;
 		}
 	case AMD_EVENT_NB:
-		/* moved to perf_event_amd_uncore.c */
+		/* moved to uncore.c */
 		return &emptyconstraint;
 	default:
 		return &emptyconstraint;
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index aff4b5b69d40..238ae3248ba5 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -1,5 +1,5 @@
 /*
- * perf_event_intel_cstate.c: support cstate residency counters
+ * Support cstate residency counters
  *
  * Copyright (C) 2015, Intel Corp.
  * Author: Kan Liang (kan.liang@intel.com)
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 22054ca49026..9d05c7e67f60 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -1,5 +1,5 @@
 /*
- * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Support Intel RAPL energy consumption counters
  * Copyright (C) 2013 Google, Inc., Stephane Eranian
  *
  * Intel RAPL interface is specified in the IA-32 Manual Vol3b
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index ad986c1e29bc..df5989f27b1b 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -360,7 +360,7 @@ extern struct list_head pci2phy_map_head;
 extern struct pci_extra_dev *uncore_extra_pci_dev;
 extern struct event_constraint uncore_constraint_empty;
 
-/* perf_event_intel_uncore_snb.c */
+/* uncore_snb.c */
 int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
@@ -371,7 +371,7 @@ void nhm_uncore_cpu_init(void);
 void skl_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
 
-/* perf_event_intel_uncore_snbep.c */
+/* uncore_snbep.c */
 int snbep_uncore_pci_init(void);
 void snbep_uncore_cpu_init(void);
 int ivbep_uncore_pci_init(void);
@@ -385,5 +385,5 @@ void knl_uncore_cpu_init(void);
 int skx_uncore_pci_init(void);
 void skx_uncore_cpu_init(void);
 
-/* perf_event_intel_uncore_nhmex.c */
+/* uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 7913363bde5c..4f3c758d875d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -31,7 +31,7 @@
 #error Instruction buffer size too small
 #endif
 
-/* Based on branch_type() from perf_event_intel_lbr.c */
+/* Based on branch_type() from arch/x86/events/intel/lbr.c */
 static void intel_pt_insn_decoder(struct insn *insn,
 				  struct intel_pt_insn *intel_pt_insn)
 {
-- 
GitLab


From 72042a8c7b01048a36ece216aaf206b7d60ca661 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Mon, 20 Feb 2017 10:12:35 +1100
Subject: [PATCH 407/898] x86/purgatory: Make functions and variables static

Sparse emits several 'symbol not declared' warnings for various
functions and variables.

Add static keyword to functions and variables which have file scope
only.

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Link: http://lkml.kernel.org/r/1487545956-2547-2-git-send-email-me@tobin.cc
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/purgatory/purgatory.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 25e068ba3382..2a5f4373c797 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -18,11 +18,11 @@ struct sha_region {
 	unsigned long len;
 };
 
-unsigned long backup_dest = 0;
-unsigned long backup_src = 0;
-unsigned long backup_sz = 0;
+static unsigned long backup_dest;
+static unsigned long backup_src;
+static unsigned long backup_sz;
 
-u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
+static u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
 
 struct sha_region sha_regions[16] = {};
 
@@ -39,7 +39,7 @@ static int copy_backup_region(void)
 	return 0;
 }
 
-int verify_sha256_digest(void)
+static int verify_sha256_digest(void)
 {
 	struct sha_region *ptr, *end;
 	u8 digest[SHA256_DIGEST_SIZE];
-- 
GitLab


From e98fe5127b9cc8ab33d1094b81c19deb1f9082bf Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Mon, 20 Feb 2017 10:12:36 +1100
Subject: [PATCH 408/898] x86/purgatory: Fix sparse warning, symbol not
 declared

Sparse emits warning, 'symbol not declared' for a function that has
neither file scope nor a forward declaration. The functions only call
site is an ASM file.

Add a header file with the function declaration. Include the header file in
the C source file defining the function in order to fix the sparse
warning. Include the header file in ASM file containing the call site to
document the usage.

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Link: http://lkml.kernel.org/r/1487545956-2547-3-git-send-email-me@tobin.cc
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/purgatory/purgatory.c    | 1 +
 arch/x86/purgatory/purgatory.h    | 8 ++++++++
 arch/x86/purgatory/setup-x86_64.S | 1 +
 3 files changed, 10 insertions(+)
 create mode 100644 arch/x86/purgatory/purgatory.h

diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 2a5f4373c797..b6d5c8946e66 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -11,6 +11,7 @@
  */
 
 #include "sha256.h"
+#include "purgatory.h"
 #include "../boot/string.h"
 
 struct sha_region {
diff --git a/arch/x86/purgatory/purgatory.h b/arch/x86/purgatory/purgatory.h
new file mode 100644
index 000000000000..e2e365a6c192
--- /dev/null
+++ b/arch/x86/purgatory/purgatory.h
@@ -0,0 +1,8 @@
+#ifndef PURGATORY_H
+#define PURGATORY_H
+
+#ifndef __ASSEMBLY__
+extern void purgatory(void);
+#endif	/* __ASSEMBLY__ */
+
+#endif /* PURGATORY_H */
diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S
index fe3c91ba1bd0..f90e9dfa90bb 100644
--- a/arch/x86/purgatory/setup-x86_64.S
+++ b/arch/x86/purgatory/setup-x86_64.S
@@ -9,6 +9,7 @@
  * This source code is licensed under the GNU General Public License,
  * Version 2.  See the file COPYING for more details.
  */
+#include "purgatory.h"
 
 	.text
 	.globl purgatory_start
-- 
GitLab


From 8392f16d38bb5222c03073a3906b7fd272386faf Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Tue, 21 Feb 2017 19:36:39 +0100
Subject: [PATCH 409/898] x86/boot: Correct setup_header.start_sys name

It is called start_sys_seg elsewhere so rename it to that. It is an
obsolete field so we could just as well directly call it __u16 __pad...

No functional change.

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/20170221183639.16554-1-bp@alien8.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/uapi/asm/bootparam.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 5138dacf8bb8..07244ea16765 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -58,7 +58,7 @@ struct setup_header {
 	__u32	header;
 	__u16	version;
 	__u32	realmode_swtch;
-	__u16	start_sys;
+	__u16	start_sys_seg;
 	__u16	kernel_version;
 	__u8	type_of_loader;
 	__u8	loadflags;
-- 
GitLab


From 1fb1683cb343d80736625f3048de2107cf5bbf79 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Tue, 28 Feb 2017 14:36:56 +0000
Subject: [PATCH 410/898] crypto: arm/crc32 - fix build error with outdated
 binutils

Annotate a vmov instruction with an explicit element size of 32 bits.
This is inferred by recent toolchains, but apparently, older versions
need some help figuring this out.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/crc32-ce-core.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/crypto/crc32-ce-core.S b/arch/arm/crypto/crc32-ce-core.S
index e63d400dc5c1..5cbd4a6fedad 100644
--- a/arch/arm/crypto/crc32-ce-core.S
+++ b/arch/arm/crypto/crc32-ce-core.S
@@ -135,7 +135,7 @@ ENTRY(crc32c_pmull_le)
 	vld1.8		{q3-q4}, [BUF, :128]!
 	vmov.i8		qzr, #0
 	vmov.i8		qCONSTANT, #0
-	vmov		dCONSTANTl[0], CRC
+	vmov.32		dCONSTANTl[0], CRC
 	veor.8		d2, d2, dCONSTANTl
 	sub		LEN, LEN, #0x40
 	cmp		LEN, #0x40
-- 
GitLab


From efa7cebdbfde8506b54acd8947822394768cd476 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Tue, 28 Feb 2017 14:36:57 +0000
Subject: [PATCH 411/898] crypto: arm/crc32 - add build time test for CRC
 instruction support

The accelerated CRC32 module for ARM may use either the scalar CRC32
instructions, the NEON 64x64 to 128 bit polynomial multiplication
(vmull.p64) instruction, or both, depending on what the current CPU
supports.

However, this also requires support in binutils, and as it turns out,
versions of binutils exist that support the vmull.p64 instruction but
not the crc32 instructions.

So refactor the Makefile logic so that this module only gets built if
binutils has support for both.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/Makefile | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 1822c4697278..f2215fbeed13 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -15,7 +15,17 @@ ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-arm-ce.o
+crc-obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-arm-ce.o
+
+ifneq ($(crc-obj-y)$(crc-obj-m),)
+ifeq ($(call as-instr,.arch armv8-a\n.arch_extension crc,y,n),y)
+ce-obj-y += $(crc-obj-y)
+ce-obj-m += $(crc-obj-m)
+else
+$(warning These CRC Extensions modules need binutils 2.23 or higher)
+$(warning $(crc-obj-y) $(crc-obj-m))
+endif
+endif
 
 ifneq ($(ce-obj-y)$(ce-obj-m),)
 ifeq ($(call as-instr,.fpu crypto-neon-fp-armv8,y,n),y)
-- 
GitLab


From 1c68bb0f62bf8de8bb30123ea840d5168f25abea Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Tue, 28 Feb 2017 14:07:25 -0800
Subject: [PATCH 412/898] crypto: testmgr - Pad aes_ccm_enc_tv_template vector

Running with KASAN and crypto tests currently gives

 BUG: KASAN: global-out-of-bounds in __test_aead+0x9d9/0x2200 at addr ffffffff8212fca0
 Read of size 16 by task cryptomgr_test/1107
 Address belongs to variable 0xffffffff8212fca0
 CPU: 0 PID: 1107 Comm: cryptomgr_test Not tainted 4.10.0+ #45
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.1-1.fc24 04/01/2014
 Call Trace:
  dump_stack+0x63/0x8a
  kasan_report.part.1+0x4a7/0x4e0
  ? __test_aead+0x9d9/0x2200
  ? crypto_ccm_init_crypt+0x218/0x3c0 [ccm]
  kasan_report+0x20/0x30
  check_memory_region+0x13c/0x1a0
  memcpy+0x23/0x50
  __test_aead+0x9d9/0x2200
  ? kasan_unpoison_shadow+0x35/0x50
  ? alg_test_akcipher+0xf0/0xf0
  ? crypto_skcipher_init_tfm+0x2e3/0x310
  ? crypto_spawn_tfm2+0x37/0x60
  ? crypto_ccm_init_tfm+0xa9/0xd0 [ccm]
  ? crypto_aead_init_tfm+0x7b/0x90
  ? crypto_alloc_tfm+0xc4/0x190
  test_aead+0x28/0xc0
  alg_test_aead+0x54/0xd0
  alg_test+0x1eb/0x3d0
  ? alg_find_test+0x90/0x90
  ? __sched_text_start+0x8/0x8
  ? __wake_up_common+0x70/0xb0
  cryptomgr_test+0x4d/0x60
  kthread+0x173/0x1c0
  ? crypto_acomp_scomp_free_ctx+0x60/0x60
  ? kthread_create_on_node+0xa0/0xa0
  ret_from_fork+0x2c/0x40
 Memory state around the buggy address:
  ffffffff8212fb80: 00 00 00 00 01 fa fa fa fa fa fa fa 00 00 00 00
  ffffffff8212fc00: 00 01 fa fa fa fa fa fa 00 00 00 00 01 fa fa fa
 >ffffffff8212fc80: fa fa fa fa 00 05 fa fa fa fa fa fa 00 00 00 00
                                   ^
  ffffffff8212fd00: 01 fa fa fa fa fa fa fa 00 00 00 00 01 fa fa fa
  ffffffff8212fd80: fa fa fa fa 00 00 00 00 00 05 fa fa fa fa fa fa

This always happens on the same IV which is less than 16 bytes.

Per Ard,

"CCM IVs are 16 bytes, but due to the way they are constructed
internally, the final couple of bytes of input IV are dont-cares.

Apparently, we do read all 16 bytes, which triggers the KASAN errors."

Fix this by padding the IV with null bytes to be at least 16 bytes.

Cc: stable@vger.kernel.org
Fixes: 0bc5a6c5c79a ("crypto: testmgr - Disable rfc4309 test and convert
test vectors")
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/testmgr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index f85e51cf7dcc..663f034c89b9 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -22691,7 +22691,7 @@ static struct aead_testvec aes_ccm_enc_tv_template[] = {
 			  "\x09\x75\x9a\x9b\x3c\x9b\x27\x39",
 		.klen	= 32,
 		.iv	= "\x03\xf9\xd9\x4e\x63\xb5\x3d\x9d"
-			  "\x43\xf6\x1e\x50",
+			  "\x43\xf6\x1e\x50\0\0\0\0",
 		.assoc	= "\x57\xf5\x6b\x8b\x57\x5c\x3d\x3b"
 			  "\x13\x02\x01\x0c\x83\x4c\x96\x35"
 			  "\x8e\xd6\x39\xcf\x7d\x14\x9b\x94"
-- 
GitLab


From 25b68a8f0ab13a98de02650208ec927796659898 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <sds@tycho.nsa.gov>
Date: Fri, 17 Feb 2017 10:13:59 -0500
Subject: [PATCH 413/898] timerfd: Only check CAP_WAKE_ALARM when it is needed

timerfd_create() and do_timerfd_settime() evaluate capable(CAP_WAKE_ALARM)
unconditionally although CAP_WAKE_ALARM is only required for
CLOCK_REALTIME_ALARM and CLOCK_BOOTTIME_ALARM.

This can cause extraneous audit messages when using a LSM such as SELinux,
incorrectly causes PF_SUPERPRIV to be set even when no privilege was
exercised, and is inefficient.

Flip the order of the tests in both functions so that we only call
capable() if the capability is truly required for the operation.

Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Cc: linux-security-module@vger.kernel.org
Cc: selinux@tycho.nsa.gov
Link: http://lkml.kernel.org/r/1487344439-22293-1-git-send-email-sds@tycho.nsa.gov
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 fs/timerfd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/timerfd.c b/fs/timerfd.c
index 384fa759a563..c543cdb5f8ed 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -400,9 +400,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 	     clockid != CLOCK_BOOTTIME_ALARM))
 		return -EINVAL;
 
-	if (!capable(CAP_WAKE_ALARM) &&
-	    (clockid == CLOCK_REALTIME_ALARM ||
-	     clockid == CLOCK_BOOTTIME_ALARM))
+	if ((clockid == CLOCK_REALTIME_ALARM ||
+	     clockid == CLOCK_BOOTTIME_ALARM) &&
+	    !capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -449,7 +449,7 @@ static int do_timerfd_settime(int ufd, int flags,
 		return ret;
 	ctx = f.file->private_data;
 
-	if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) {
+	if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) {
 		fdput(f);
 		return -EPERM;
 	}
-- 
GitLab


From bba82fd75694832b59433bf4e9d7ede8de1dfd42 Mon Sep 17 00:00:00 2001
From: Robert O'Callahan <robert@ocallahan.org>
Date: Wed, 1 Feb 2017 17:06:11 +1300
Subject: [PATCH 414/898] KVM: x86: never specify a sample period for
 virtualized in_tx_cp counters
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pmc_reprogram_counter() always sets a sample period based on the value of
pmc->counter. However, hsw_hw_config() rejects sample periods less than
2^31 - 1. So for example, if a KVM guest does

    struct perf_event_attr attr;
    memset(&attr, 0, sizeof(attr));
    attr.type = PERF_TYPE_RAW;
    attr.size = sizeof(attr);
    attr.config = 0x2005101c4; // conditional branches retired IN_TXCP
    attr.sample_period = 0;
    int fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0);
    ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
    ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);

the guest kernel counts some conditional branch events, then updates the
virtual PMU register with a nonzero count. The host reaches
pmc_reprogram_counter() with nonzero pmc->counter, triggers EOPNOTSUPP
in hsw_hw_config(), prints "kvm_pmu: event creation failed" in
pmc_reprogram_counter(), and silently (from the guest's point of view) stops
counting events.

We fix event counting by forcing attr.sample_period to always be zero for
in_tx_cp counters. Sampling doesn't work, but it already didn't work and
can't be fixed without major changes to the approach in hsw_hw_config().

Signed-off-by: Robert O'Callahan <robert@ocallahan.org>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/pmu.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 06ce377dcbc9..026db42a86c3 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -113,12 +113,19 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.config = config,
 	};
 
+	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
+
 	if (in_tx)
 		attr.config |= HSW_IN_TX;
-	if (in_tx_cp)
+	if (in_tx_cp) {
+		/*
+		 * HSW_IN_TX_CHECKPOINTED is not supported with nonzero
+		 * period. Just clear the sample period so at least
+		 * allocating the counter doesn't fail.
+		 */
+		attr.sample_period = 0;
 		attr.config |= HSW_IN_TX_CHECKPOINTED;
-
-	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
+	}
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
 						 intr ? kvm_perf_overflow_intr :
-- 
GitLab


From d0e32fba85d5b7902db2715a9d5540fb0efdba83 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 Feb 2017 22:01:18 +0100
Subject: [PATCH 415/898] watchdog: wm831x watchdog really needs mfd

The wm831x watchdog driver can now be built without the wm831x mfd
driver, which results in a link error:

(.text+0x1a95c): undefined reference to `wm831x_set_bits'
(.text+0x1a95c): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `wm831x_set_bits'
(.text+0x1a968): undefined reference to `wm831x_reg_lock'
(.text+0x1a968): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `wm831x_reg_lock'
(.text+0x1a9dc): undefined reference to `wm831x_reg_unlock'
(.text+0x1a9dc): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `wm831x_reg_unlock'

This adds back the dependency that was removed. We can still build test
this driver on all architectures by enabling the MFD driver for it first.

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index c831b7967bf9..fda6f3d24780 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -176,7 +176,7 @@ config WDAT_WDT
 
 config WM831X_WATCHDOG
 	tristate "WM831x watchdog"
-	depends on MFD_WM831X || COMPILE_TEST
+	depends on MFD_WM831X
 	select WATCHDOG_CORE
 	help
 	  Support for the watchdog in the WM831x AudioPlus PMICs.  When
-- 
GitLab


From 0369fdf2e1169896529bd53c3b5fb15511768276 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 Feb 2017 22:01:19 +0100
Subject: [PATCH 416/898] watchdog: geode: restore hard CS5535_MFGPT dependency

Wtihout CONFIG_CS5535_MFGPT, the driver does not link right:

drivers/watchdog/built-in.o: In function `geodewdt_probe':
geodewdt.c:(.init.text+0xca3): undefined reference to `cs5535_mfgpt_alloc_timer'
geodewdt.c:(.init.text+0xcd4): undefined reference to `cs5535_mfgpt_write'
geodewdt.c:(.init.text+0xcef): undefined reference to `cs5535_mfgpt_toggle_event'

This adds back the dependency on this base driver.

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index fda6f3d24780..5b4bb1b6dd68 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -851,7 +851,7 @@ config SP5100_TCO
 
 config GEODE_WDT
 	tristate "AMD Geode CS5535/CS5536 Watchdog"
-	depends on CS5535_MFGPT || (X86 && COMPILE_TEST)
+	depends on CS5535_MFGPT
 	help
 	  This driver enables a watchdog capability built into the
 	  CS5535/CS5536 companion chips for the AMD Geode GX and LX
-- 
GitLab


From 6fb303a81a0b106e7f5522df929bbf4596780c48 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 Feb 2017 22:01:20 +0100
Subject: [PATCH 417/898] watchdog: menf21bmc: add I2C dependency

This driver fails to link when CONFIG_I2C is disabled or a loadable module while
the watchdog is built-in:

drivers/watchdog/built-in.o: In function `menf21bmc_wdt_shutdown':
menf21bmc_wdt.c:(.text+0x9b44): undefined reference to `i2c_smbus_write_word_data'
menf21bmc_wdt.c:(.text+0x9b44): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `i2c_smbus_write_word_data'

This adds a Kconfig dependency for it, to enforce a valid configuration.

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 5b4bb1b6dd68..4d2c336daa39 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -142,6 +142,7 @@ config GPIO_WATCHDOG_ARCH_INITCALL
 config MENF21BMC_WATCHDOG
 	tristate "MEN 14F021P00 BMC Watchdog"
 	depends on MFD_MENF21BMC || COMPILE_TEST
+	depends on I2C
 	select WATCHDOG_CORE
 	help
 	  Say Y here to include support for the MEN 14F021P00 BMC Watchdog.
-- 
GitLab


From 3eafee95643360d22c6725ea2188bd700c09c986 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 Feb 2017 22:01:21 +0100
Subject: [PATCH 418/898] watchdog: sp805: add back AMBA dependency

The driver fails to link if ARM_AMBA is disabled:

drivers/watchdog/sp805_wdt.o: In function `sp805_wdt_driver_init':
sp805_wdt.c:(.init.text+0x4): undefined reference to `amba_driver_register'

It seems that the COMPILE_TEST was added in the wrong place, as there
is no architecture dependency, but a bus dependency. This moves
the dependency accordingly.

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 4d2c336daa39..41a75b8ab213 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -218,7 +218,7 @@ config ZIIRAVE_WATCHDOG
 
 config ARM_SP805_WATCHDOG
 	tristate "ARM SP805 Watchdog"
-	depends on (ARM || ARM64) && (ARM_AMBA || COMPILE_TEST)
+	depends on (ARM || ARM64 || COMPILE_TEST) && ARM_AMBA
 	select WATCHDOG_CORE
 	help
 	  ARM Primecell SP805 Watchdog timer. This will reboot your system when
-- 
GitLab


From 2672b7e01abbe147a0a391216bc0dbd656608e0a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 Feb 2017 22:01:22 +0100
Subject: [PATCH 419/898] watchdog: bcm2835: add CONFIG_OF dependency

Without CONFIG_OF, the driver fails to link:

drivers/watchdog/built-in.o: In function `bcm2835_power_off':
bcm2835_wdt.c:(.text+0x1946): undefined reference to `of_find_device_by_node'

This adds a new dependency, to allow the COMPILE_TEST check to succeed.

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 41a75b8ab213..13390b00ec47 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1496,7 +1496,7 @@ config BCM63XX_WDT
 
 config BCM2835_WDT
 	tristate "Broadcom BCM2835 hardware watchdog"
-	depends on ARCH_BCM2835 || COMPILE_TEST
+	depends on ARCH_BCM2835 || (OF && COMPILE_TEST)
 	select WATCHDOG_CORE
 	help
 	  Watchdog driver for the built in watchdog hardware in Broadcom
-- 
GitLab


From ed4a9eca66720366d117d9b39f2335ca9b0a7aae Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 Feb 2017 22:01:23 +0100
Subject: [PATCH 420/898] watchdog: kempld: revert to full dependency

The kempld watchdog driver requires the respective MFD driver:

drivers/watchdog/built-in.o: In function `kempld_wdt_probe':
kempld_wdt.c:(.text+0x5c78): undefined reference to `kempld_get_mutex'
kempld_wdt.c:(.text+0x5c84): undefined reference to `kempld_read8'
kempld_wdt.c:(.text+0x5c8e): undefined reference to `kempld_release_mutex'
kempld_wdt.c:(.text+0x5d1c): undefined reference to `kempld_read8'
kempld_wdt.c:(.text+0x5d2c): undefined reference to `kempld_write8'

This adds the Kconfig dependency back.

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 13390b00ec47..47dbacf3bfb4 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1064,7 +1064,7 @@ config HP_WATCHDOG
 
 config KEMPLD_WDT
 	tristate "Kontron COM Watchdog Timer"
-	depends on MFD_KEMPLD || COMPILE_TEST
+	depends on MFD_KEMPLD
 	select WATCHDOG_CORE
 	help
 	  Support for the PLD watchdog on some Kontron ETX and COMexpress
-- 
GitLab


From 8d5755b3f77b57447ce5de253ef704ad028474d3 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@axis.com>
Date: Mon, 27 Feb 2017 13:49:09 +0100
Subject: [PATCH 421/898] watchdog: softdog: fire watchdog even if softirqs do
 not get to run

Checking for timer expiration is done from the softirq TIMER_SOFTIRQ.

Since commit 4cd13c21b207 ("softirq: Let ksoftirqd do its job"),
pending softirqs are no longer always handled immediately, instead,
if there are pending softirqs, and ksoftirqd is in state TASK_RUNNING,
the handling of the softirqs are deferred, and are instead supposed
to be handled by ksoftirqd, when ksoftirqd gets scheduled.

If a user space process with a real-time policy starts to misbehave
by never relinquishing the CPU while ksoftirqd is in state TASK_RUNNING,
what will happen is that all softirqs will get deferred, while ksoftirqd,
which is supposed to handle the deferred softirqs, will never get to run.

To make sure that the watchdog is able to fire even when we do not get
to run softirqs, replace the timers with hrtimers.

Signed-off-by: Niklas Cassel <niklas.cassel@axis.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/softdog.c | 44 +++++++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 17 deletions(-)

diff --git a/drivers/watchdog/softdog.c b/drivers/watchdog/softdog.c
index 7983029852ab..060740625485 100644
--- a/drivers/watchdog/softdog.c
+++ b/drivers/watchdog/softdog.c
@@ -21,13 +21,12 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/hrtimer.h>
 #include <linux/init.h>
-#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/reboot.h>
-#include <linux/timer.h>
 #include <linux/types.h>
 #include <linux/watchdog.h>
 
@@ -54,7 +53,10 @@ module_param(soft_panic, int, 0);
 MODULE_PARM_DESC(soft_panic,
 	"Softdog action, set to 1 to panic, 0 to reboot (default=0)");
 
-static void softdog_fire(unsigned long data)
+static struct hrtimer softdog_ticktock;
+static struct hrtimer softdog_preticktock;
+
+static enum hrtimer_restart softdog_fire(struct hrtimer *timer)
 {
 	module_put(THIS_MODULE);
 	if (soft_noboot) {
@@ -67,32 +69,33 @@ static void softdog_fire(unsigned long data)
 		emergency_restart();
 		pr_crit("Reboot didn't ?????\n");
 	}
-}
 
-static struct timer_list softdog_ticktock =
-		TIMER_INITIALIZER(softdog_fire, 0, 0);
+	return HRTIMER_NORESTART;
+}
 
 static struct watchdog_device softdog_dev;
 
-static void softdog_pretimeout(unsigned long data)
+static enum hrtimer_restart softdog_pretimeout(struct hrtimer *timer)
 {
 	watchdog_notify_pretimeout(&softdog_dev);
-}
 
-static struct timer_list softdog_preticktock =
-		TIMER_INITIALIZER(softdog_pretimeout, 0, 0);
+	return HRTIMER_NORESTART;
+}
 
 static int softdog_ping(struct watchdog_device *w)
 {
-	if (!mod_timer(&softdog_ticktock, jiffies + (w->timeout * HZ)))
+	if (!hrtimer_active(&softdog_ticktock))
 		__module_get(THIS_MODULE);
+	hrtimer_start(&softdog_ticktock, ktime_set(w->timeout, 0),
+		      HRTIMER_MODE_REL);
 
 	if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT)) {
 		if (w->pretimeout)
-			mod_timer(&softdog_preticktock, jiffies +
-				  (w->timeout - w->pretimeout) * HZ);
+			hrtimer_start(&softdog_preticktock,
+				      ktime_set(w->timeout - w->pretimeout, 0),
+				      HRTIMER_MODE_REL);
 		else
-			del_timer(&softdog_preticktock);
+			hrtimer_cancel(&softdog_preticktock);
 	}
 
 	return 0;
@@ -100,11 +103,11 @@ static int softdog_ping(struct watchdog_device *w)
 
 static int softdog_stop(struct watchdog_device *w)
 {
-	if (del_timer(&softdog_ticktock))
+	if (hrtimer_cancel(&softdog_ticktock))
 		module_put(THIS_MODULE);
 
 	if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT))
-		del_timer(&softdog_preticktock);
+		hrtimer_cancel(&softdog_preticktock);
 
 	return 0;
 }
@@ -136,8 +139,15 @@ static int __init softdog_init(void)
 	watchdog_set_nowayout(&softdog_dev, nowayout);
 	watchdog_stop_on_reboot(&softdog_dev);
 
-	if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT))
+	hrtimer_init(&softdog_ticktock, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	softdog_ticktock.function = softdog_fire;
+
+	if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT)) {
 		softdog_info.options |= WDIOF_PRETIMEOUT;
+		hrtimer_init(&softdog_preticktock, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_REL);
+		softdog_preticktock.function = softdog_pretimeout;
+	}
 
 	ret = watchdog_register_device(&softdog_dev);
 	if (ret)
-- 
GitLab


From 3736d4eb6af37492aeded7fec0072dedd959c842 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 1 Mar 2017 10:15:29 +0100
Subject: [PATCH 422/898] watchdog: kempld: fix gcc-4.3 build

gcc-4.3 can't decide whether the constant value in
kempld_prescaler[PRESCALER_21] is built-time constant or
not, and gets confused by the logic in do_div():

drivers/watchdog/kempld_wdt.o: In function `kempld_wdt_set_stage_timeout':
kempld_wdt.c:(.text.kempld_wdt_set_stage_timeout+0x130): undefined reference to `__aeabi_uldivmod'

This adds a call to ACCESS_ONCE() to force it to not consider
it to be constant, and leaves the more efficient normal case
in place for modern compilers, using an #ifdef to annotate
why we do this hack.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/kempld_wdt.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/watchdog/kempld_wdt.c b/drivers/watchdog/kempld_wdt.c
index 73c46b3a09ab..2f3b049ea301 100644
--- a/drivers/watchdog/kempld_wdt.c
+++ b/drivers/watchdog/kempld_wdt.c
@@ -140,12 +140,19 @@ static int kempld_wdt_set_stage_timeout(struct kempld_wdt_data *wdt_data,
 					unsigned int timeout)
 {
 	struct kempld_device_data *pld = wdt_data->pld;
-	u32 prescaler = kempld_prescaler[PRESCALER_21];
+	u32 prescaler;
 	u64 stage_timeout64;
 	u32 stage_timeout;
 	u32 remainder;
 	u8 stage_cfg;
 
+#if GCC_VERSION < 40400
+	/* work around a bug compiling do_div() */
+	prescaler = READ_ONCE(kempld_prescaler[PRESCALER_21]);
+#else
+	prescaler = kempld_prescaler[PRESCALER_21];
+#endif
+
 	if (!stage)
 		return -EINVAL;
 
-- 
GitLab


From 9297b652bd0a11e29251ffaac93369b8ad45932d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 1 Mar 2017 10:15:30 +0100
Subject: [PATCH 423/898] watchdog: db8500: add back prmcu dependency

When the db8500 watchdog is enabled without the PRCMU, we get a lot of
warnings about duplicate or missing helper functions:

In file included from drivers/watchdog/ux500_wdt.c:21:0:
include/linux/mfd/dbx500-prcmu.h:422:19: error: redefinition of 'prcmu_abb_read'
 static inline int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)

This restores the dependency as it was.

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 47dbacf3bfb4..a199e8536ce4 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -574,7 +574,7 @@ config IMX2_WDT
 
 config UX500_WATCHDOG
 	tristate "ST-Ericsson Ux500 watchdog"
-	depends on MFD_DB8500_PRCMU || (ARM && COMPILE_TEST)
+	depends on MFD_DB8500_PRCMU
 	select WATCHDOG_CORE
 	default y
 	help
-- 
GitLab


From 9ad82f117f057ed04643cc60ce16fbf59e1b167f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 1 Mar 2017 10:15:31 +0100
Subject: [PATCH 424/898] watchdog: retu: restore MFD dependency

The retu watchdog calls into the respective mfd driver, but fails to
link if that is diabled:

drivers/watchdog/built-in.o: In function `retu_wdt_set_timeout':
ziirave_wdt.c:(.text+0x8c88): undefined reference to `retu_write'
ziirave_wdt.c:(.text+0x8c88): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `retu_write'
drivers/watchdog/built-in.o: In function `retu_wdt_start':
ziirave_wdt.c:(.text+0x8cc8): undefined reference to `retu_write'
ziirave_wdt.c:(.text+0x8cc8): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `retu_write'

This restores the dependency as it was before

Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/watchdog/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index a199e8536ce4..52a70ee6014f 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -586,7 +586,7 @@ config UX500_WATCHDOG
 
 config RETU_WATCHDOG
 	tristate "Retu watchdog"
-	depends on MFD_RETU || COMPILE_TEST
+	depends on MFD_RETU
 	select WATCHDOG_CORE
 	help
 	  Retu watchdog driver for Nokia Internet Tablets (770, N800,
-- 
GitLab


From e3736c3eb3a6f7c0966923b629c9f92b558aa9c7 Mon Sep 17 00:00:00 2001
From: Elena Reshetova <elena.reshetova@intel.com>
Date: Mon, 20 Feb 2017 13:06:21 +0200
Subject: [PATCH 425/898] kvm: convert kvm.users_count from atomic_t to
 refcount_t
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.

Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David Windsor <dwindsor@gmail.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 include/linux/kvm_host.h | 3 ++-
 virt/kvm/kvm_main.c      | 8 ++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8d69d5150748..2c14ad9809da 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -26,6 +26,7 @@
 #include <linux/context_tracking.h>
 #include <linux/irqbypass.h>
 #include <linux/swait.h>
+#include <linux/refcount.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -401,7 +402,7 @@ struct kvm {
 #endif
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
-	atomic_t users_count;
+	refcount_t users_count;
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
 	spinlock_t ring_lock;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cc4d6e0dd2a2..c6b7aff634be 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -617,7 +617,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	mutex_init(&kvm->lock);
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
-	atomic_set(&kvm->users_count, 1);
+	refcount_set(&kvm->users_count, 1);
 	INIT_LIST_HEAD(&kvm->devices);
 
 	r = kvm_arch_init_vm(kvm, type);
@@ -747,13 +747,13 @@ static void kvm_destroy_vm(struct kvm *kvm)
 
 void kvm_get_kvm(struct kvm *kvm)
 {
-	atomic_inc(&kvm->users_count);
+	refcount_inc(&kvm->users_count);
 }
 EXPORT_SYMBOL_GPL(kvm_get_kvm);
 
 void kvm_put_kvm(struct kvm *kvm)
 {
-	if (atomic_dec_and_test(&kvm->users_count))
+	if (refcount_dec_and_test(&kvm->users_count))
 		kvm_destroy_vm(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_put_kvm);
@@ -3639,7 +3639,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
 	 * To avoid the race between open and the removal of the debugfs
 	 * directory we test against the users count.
 	 */
-	if (!atomic_add_unless(&stat_data->kvm->users_count, 1, 0))
+	if (!refcount_inc_not_zero(&stat_data->kvm->users_count))
 		return -ENOENT;
 
 	if (simple_attr_open(inode, file, get, set, fmt)) {
-- 
GitLab


From b7ceaec112aa35aa287325754d8c52b8304892cd Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Wed, 22 Feb 2017 07:36:16 -0800
Subject: [PATCH 426/898] x86/asm: Tidy up TSS limit code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In an earlier version of the patch ("x86/kvm/vmx: Defer TR reload
after VM exit") that introduced TSS limit validity tracking, I
confused which helper was which.  On reflection, the names I chose
sucked.  Rename the helpers to make it more obvious what's going on
and add some comments.

While I'm at it, clear __tss_limit_invalid when force-reloading as
well as when contitionally reloading, since any TR reload fixes the
limit.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/include/asm/desc.h | 18 +++++++++++-------
 arch/x86/kernel/ioport.c    |  8 +++++++-
 arch/x86/kernel/process.c   |  6 +++---
 3 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index cb8f9149f6c8..1548ca92ad3f 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -205,6 +205,8 @@ static inline void native_load_tr_desc(void)
 	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
 }
 
+DECLARE_PER_CPU(bool, __tss_limit_invalid);
+
 static inline void force_reload_TR(void)
 {
 	struct desc_struct *d = get_cpu_gdt_table(smp_processor_id());
@@ -220,18 +222,20 @@ static inline void force_reload_TR(void)
 	write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS);
 
 	load_TR_desc();
+	this_cpu_write(__tss_limit_invalid, false);
 }
 
-DECLARE_PER_CPU(bool, need_tr_refresh);
-
-static inline void refresh_TR(void)
+/*
+ * Call this if you need the TSS limit to be correct, which should be the case
+ * if and only if you have TIF_IO_BITMAP set or you're switching to a task
+ * with TIF_IO_BITMAP set.
+ */
+static inline void refresh_tss_limit(void)
 {
 	DEBUG_LOCKS_WARN_ON(preemptible());
 
-	if (unlikely(this_cpu_read(need_tr_refresh))) {
+	if (unlikely(this_cpu_read(__tss_limit_invalid)))
 		force_reload_TR();
-		this_cpu_write(need_tr_refresh, false);
-	}
 }
 
 /*
@@ -250,7 +254,7 @@ static inline void invalidate_tss_limit(void)
 	if (unlikely(test_thread_flag(TIF_IO_BITMAP)))
 		force_reload_TR();
 	else
-		this_cpu_write(need_tr_refresh, true);
+		this_cpu_write(__tss_limit_invalid, true);
 }
 
 static inline void native_load_gdt(const struct desc_ptr *dtr)
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index b01bc8517450..875d3d25dd6a 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -47,8 +47,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 		t->io_bitmap_ptr = bitmap;
 		set_thread_flag(TIF_IO_BITMAP);
 
+		/*
+		 * Now that we have an IO bitmap, we need our TSS limit to be
+		 * correct.  It's fine if we are preempted after doing this:
+		 * with TIF_IO_BITMAP set, context switches will keep our TSS
+		 * limit correct.
+		 */
 		preempt_disable();
-		refresh_TR();
+		refresh_tss_limit();
 		preempt_enable();
 	}
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7780efa635b9..0b302591b51f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -65,8 +65,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
-DEFINE_PER_CPU(bool, need_tr_refresh);
-EXPORT_PER_CPU_SYMBOL_GPL(need_tr_refresh);
+DEFINE_PER_CPU(bool, __tss_limit_invalid);
+EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
 
 /*
  * this gets called so that we can store lazy state into memory and copy the
@@ -218,7 +218,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 * Make sure that the TSS limit is correct for the CPU
 		 * to notice the IO bitmap.
 		 */
-		refresh_TR();
+		refresh_tss_limit();
 	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
 		/*
 		 * Clear any possible leftover bits:
-- 
GitLab


From 0eb1d0fa6a68324b51db4f7ae16d9b042c5b2de4 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Wed, 22 Feb 2017 07:36:17 -0800
Subject: [PATCH 427/898] selftests/x86: Add a basic selftest for ioperm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This doesn't fully exercise the interaction between KVM and ioperm(),
but it does test basic functionality.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 tools/testing/selftests/x86/Makefile |   2 +-
 tools/testing/selftests/x86/ioperm.c | 170 +++++++++++++++++++++++++++
 2 files changed, 171 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/x86/ioperm.c

diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 83d8b1c6cb0e..bed3e6086cb1 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -5,7 +5,7 @@ include ../lib.mk
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
-			check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test \
+			check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \
 			protection_keys test_vdso
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c
new file mode 100644
index 000000000000..b77313ba2ab1
--- /dev/null
+++ b/tools/testing/selftests/x86/ioperm.c
@@ -0,0 +1,170 @@
+/*
+ * ioperm.c - Test case for ioperm(2)
+ * Copyright (c) 2015 Andrew Lutomirski
+ */
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <signal.h>
+#include <setjmp.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdbool.h>
+#include <sched.h>
+#include <sys/io.h>
+
+static int nerrs = 0;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+
+}
+
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
+{
+	siglongjmp(jmpbuf, 1);
+}
+
+static bool try_outb(unsigned short port)
+{
+	sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
+	if (sigsetjmp(jmpbuf, 1) != 0) {
+		return false;
+	} else {
+		asm volatile ("outb %%al, %w[port]"
+			      : : [port] "Nd" (port), "a" (0));
+		return true;
+	}
+	clearhandler(SIGSEGV);
+}
+
+static void expect_ok(unsigned short port)
+{
+	if (!try_outb(port)) {
+		printf("[FAIL]\toutb to 0x%02hx failed\n", port);
+		exit(1);
+	}
+
+	printf("[OK]\toutb to 0x%02hx worked\n", port);
+}
+
+static void expect_gp(unsigned short port)
+{
+	if (try_outb(port)) {
+		printf("[FAIL]\toutb to 0x%02hx worked\n", port);
+		exit(1);
+	}
+
+	printf("[OK]\toutb to 0x%02hx failed\n", port);
+}
+
+int main(void)
+{
+	cpu_set_t cpuset;
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		err(1, "sched_setaffinity to CPU 0");
+
+	expect_gp(0x80);
+	expect_gp(0xed);
+
+	/*
+	 * Probe for ioperm support.  Note that clearing ioperm bits
+	 * works even as nonroot.
+	 */
+	printf("[RUN]\tenable 0x80\n");
+	if (ioperm(0x80, 1, 1) != 0) {
+		printf("[OK]\tioperm(0x80, 1, 1) failed (%d) -- try running as root\n",
+		       errno);
+		return 0;
+	}
+	expect_ok(0x80);
+	expect_gp(0xed);
+
+	printf("[RUN]\tdisable 0x80\n");
+	if (ioperm(0x80, 1, 0) != 0) {
+		printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+		return 1;
+	}
+	expect_gp(0x80);
+	expect_gp(0xed);
+
+	/* Make sure that fork() preserves ioperm. */
+	if (ioperm(0x80, 1, 1) != 0) {
+		printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+		return 1;
+	}
+
+	pid_t child = fork();
+	if (child == -1)
+		err(1, "fork");
+
+	if (child == 0) {
+		printf("[RUN]\tchild: check that we inherited permissions\n");
+		expect_ok(0x80);
+		expect_gp(0xed);
+		return 0;
+	} else {
+		int status;
+		if (waitpid(child, &status, 0) != child ||
+		    !WIFEXITED(status)) {
+			printf("[FAIL]\tChild died\n");
+			nerrs++;
+		} else if (WEXITSTATUS(status) != 0) {
+			printf("[FAIL]\tChild failed\n");
+			nerrs++;
+		} else {
+			printf("[OK]\tChild succeeded\n");
+		}
+	}
+
+	/* Test the capability checks. */
+
+	printf("\tDrop privileges\n");
+	if (setresuid(1, 1, 1) != 0) {
+		printf("[WARN]\tDropping privileges failed\n");
+		return 0;
+	}
+
+	printf("[RUN]\tdisable 0x80\n");
+	if (ioperm(0x80, 1, 0) != 0) {
+		printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+		return 1;
+	}
+	printf("[OK]\tit worked\n");
+
+	printf("[RUN]\tenable 0x80 again\n");
+	if (ioperm(0x80, 1, 1) == 0) {
+		printf("[FAIL]\tit succeeded but should have failed.\n");
+		return 1;
+	}
+	printf("[OK]\tit failed\n");
+	return 0;
+}
-- 
GitLab


From 0fce546f9f07b94ccc9de09cf48d35e18946d2fa Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Lefaure?= <jeremy.lefaure@lse.epita.fr>
Date: Sat, 25 Feb 2017 17:46:53 -0500
Subject: [PATCH 428/898] x86/kvm/vmx: remove unused variable in segment_base()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pointer 'struct desc_struct *d' is unused since commit 8c2e41f7ae12
("x86/kvm/vmx: Simplify segment_base()") so let's remove it.

Signed-off-by: Jérémy Lefaure <jeremy.lefaure@lse.epita.fr>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ef4ba71dbb66..764f1f897847 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2053,7 +2053,6 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 static unsigned long segment_base(u16 selector)
 {
 	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
-	struct desc_struct *d;
 	struct desc_struct *table;
 	unsigned long v;
 
-- 
GitLab


From acc9ab60132739e0c5ab40644444cd7b22d12886 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpeng.li@hotmail.com>
Date: Mon, 27 Feb 2017 04:24:39 -0800
Subject: [PATCH 429/898] KVM: nVMX: Fix pending events injection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

L2 fails to boot on a non-APICv box dues to 'commit 0ad3bed6c5ec
("kvm: nVMX: move nested events check to kvm_vcpu_running")'

KVM internal error. Suberror: 3
extra data[0]: 800000ef
extra data[1]: 1
RAX=0000000000000000 RBX=ffffffff81f36140 RCX=0000000000000000 RDX=0000000000000000
RSI=0000000000000000 RDI=0000000000000000 RBP=ffff88007c92fe90 RSP=ffff88007c92fe90
R8 =ffff88007fccdca0 R9 =0000000000000000 R10=00000000fffedb3d R11=0000000000000000
R12=0000000000000003 R13=0000000000000000 R14=0000000000000000 R15=ffff88007c92c000
RIP=ffffffff810645e6 RFL=00000246 [---Z-P-] CPL=0 II=0 A20=1 SMM=0 HLT=0
ES =0000 0000000000000000 ffffffff 00c00000
CS =0010 0000000000000000 ffffffff 00a09b00 DPL=0 CS64 [-RA]
SS =0000 0000000000000000 ffffffff 00c00000
DS =0000 0000000000000000 ffffffff 00c00000
FS =0000 0000000000000000 ffffffff 00c00000
GS =0000 ffff88007fcc0000 ffffffff 00c00000
LDT=0000 0000000000000000 ffffffff 00c00000
TR =0040 ffff88007fcd4200 00002087 00008b00 DPL=0 TSS64-busy
GDT=     ffff88007fcc9000 0000007f
IDT=     ffffffffff578000 00000fff
CR0=80050033 CR2=00000000ffffffff CR3=0000000001e0a000 CR4=003406e0
DR0=0000000000000000 DR1=0000000000000000 DR2=0000000000000000 DR3=0000000000000000
DR6=00000000fffe0ff0 DR7=0000000000000400
EFER=0000000000000d01

We should try to reinject previous events if any before trying to inject
new event if pending. If vmexit is triggered by L2 guest and L0 interested
in, we should reinject IDT-vectoring info to L2 through vmcs02 if any,
otherwise, we can consider new IRQs/NMIs which can be injected and call
nested events callback to switch from L2 to L1 if needed and inject the
proper vmexit events. However, 'commit 0ad3bed6c5ec ("kvm: nVMX: move
nested events check to kvm_vcpu_running")' results in the handle events
order reversely on non-APICv box. This patch fixes it by bailing out for
pending events and not consider new events in this scenario.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Fixes: 0ad3bed6c5ec ("kvm: nVMX: move nested events check to kvm_vcpu_running")
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 764f1f897847..283aa8601833 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10641,6 +10641,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (vcpu->arch.exception.pending ||
+		vcpu->arch.nmi_injected ||
+		vcpu->arch.interrupt.pending)
+		return -EBUSY;
+
 	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
 	    vmx->nested.preemption_timer_expired) {
 		if (vmx->nested.nested_run_pending)
@@ -10650,8 +10655,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 	}
 
 	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
-		if (vmx->nested.nested_run_pending ||
-		    vcpu->arch.interrupt.pending)
+		if (vmx->nested.nested_run_pending)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
-- 
GitLab


From 540b1c48c37ac0ad66212004db21e1ff7e2d78be Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 27 Feb 2017 15:43:06 +0000
Subject: [PATCH 430/898] rxrpc: Fix deadlock between call creation and
 sendmsg/recvmsg

All the routines by which rxrpc is accessed from the outside are serialised
by means of the socket lock (sendmsg, recvmsg, bind,
rxrpc_kernel_begin_call(), ...) and this presents a problem:

 (1) If a number of calls on the same socket are in the process of
     connection to the same peer, a maximum of four concurrent live calls
     are permitted before further calls need to wait for a slot.

 (2) If a call is waiting for a slot, it is deep inside sendmsg() or
     rxrpc_kernel_begin_call() and the entry function is holding the socket
     lock.

 (3) sendmsg() and recvmsg() or the in-kernel equivalents are prevented
     from servicing the other calls as they need to take the socket lock to
     do so.

 (4) The socket is stuck until a call is aborted and makes its slot
     available to the waiter.

Fix this by:

 (1) Provide each call with a mutex ('user_mutex') that arbitrates access
     by the users of rxrpc separately for each specific call.

 (2) Make rxrpc_sendmsg() and rxrpc_recvmsg() unlock the socket as soon as
     they've got a call and taken its mutex.

     Note that I'm returning EWOULDBLOCK from recvmsg() if MSG_DONTWAIT is
     set but someone else has the lock.  Should I instead only return
     EWOULDBLOCK if there's nothing currently to be done on a socket, and
     sleep in this particular instance because there is something to be
     done, but we appear to be blocked by the interrupt handler doing its
     ping?

 (3) Make rxrpc_new_client_call() unlock the socket after allocating a new
     call, locking its user mutex and adding it to the socket's call tree.
     The call is returned locked so that sendmsg() can add data to it
     immediately.

     From the moment the call is in the socket tree, it is subject to
     access by sendmsg() and recvmsg() - even if it isn't connected yet.

 (4) Lock new service calls in the UDP data_ready handler (in
     rxrpc_new_incoming_call()) because they may already be in the socket's
     tree and the data_ready handler makes them live immediately if a user
     ID has already been preassigned.

     Note that the new call is locked before any notifications are sent
     that it is live, so doing mutex_trylock() *ought* to always succeed.
     Userspace is prevented from doing sendmsg() on calls that are in a
     too-early state in rxrpc_do_sendmsg().

 (5) Make rxrpc_new_incoming_call() return the call with the user mutex
     held so that a ping can be scheduled immediately under it.

     Note that it might be worth moving the ping call into
     rxrpc_new_incoming_call() and then we can drop the mutex there.

 (6) Make rxrpc_accept_call() take the lock on the call it is accepting and
     release the socket after adding the call to the socket's tree.  This
     is slightly tricky as we've dequeued the call by that point and have
     to requeue it.

     Note that requeuing emits a trace event.

 (7) Make rxrpc_kernel_send_data() and rxrpc_kernel_recv_data() take the
     new mutex immediately and don't bother with the socket mutex at all.

This patch has the nice bonus that calls on the same socket are now to some
extent parallelisable.

Note that we might want to move rxrpc_service_prealloc() calls out from the
socket lock and give it its own lock, so that we don't hang progress in
other calls because we're waiting for the allocator.

We probably also want to avoid calling rxrpc_notify_socket() from within
the socket lock (rxrpc_accept_call()).

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Marc Dionne <marc.c.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/rxrpc.h |  2 ++
 net/rxrpc/af_rxrpc.c         | 12 ++++++--
 net/rxrpc/ar-internal.h      |  1 +
 net/rxrpc/call_accept.c      | 48 ++++++++++++++++++++++++++++++
 net/rxrpc/call_object.c      | 18 ++++++++++--
 net/rxrpc/input.c            |  1 +
 net/rxrpc/recvmsg.c          | 39 ++++++++++++++++++++----
 net/rxrpc/sendmsg.c          | 57 +++++++++++++++++++++++++++++-------
 8 files changed, 156 insertions(+), 22 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 593f586545eb..39123c06a566 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -119,6 +119,7 @@ enum rxrpc_recvmsg_trace {
 	rxrpc_recvmsg_full,
 	rxrpc_recvmsg_hole,
 	rxrpc_recvmsg_next,
+	rxrpc_recvmsg_requeue,
 	rxrpc_recvmsg_return,
 	rxrpc_recvmsg_terminal,
 	rxrpc_recvmsg_to_be_accepted,
@@ -277,6 +278,7 @@ enum rxrpc_congest_change {
 	EM(rxrpc_recvmsg_full,			"FULL") \
 	EM(rxrpc_recvmsg_hole,			"HOLE") \
 	EM(rxrpc_recvmsg_next,			"NEXT") \
+	EM(rxrpc_recvmsg_requeue,		"REQU") \
 	EM(rxrpc_recvmsg_return,		"RETN") \
 	EM(rxrpc_recvmsg_terminal,		"TERM") \
 	EM(rxrpc_recvmsg_to_be_accepted,	"TBAC") \
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 199b46e93e64..7fb59c3f1542 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -290,10 +290,11 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	cp.exclusive		= false;
 	cp.service_id		= srx->srx_service;
 	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp);
+	/* The socket has been unlocked. */
 	if (!IS_ERR(call))
 		call->notify_rx = notify_rx;
 
-	release_sock(&rx->sk);
+	mutex_unlock(&call->user_mutex);
 	_leave(" = %p", call);
 	return call;
 }
@@ -310,7 +311,10 @@ EXPORT_SYMBOL(rxrpc_kernel_begin_call);
 void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call)
 {
 	_enter("%d{%d}", call->debug_id, atomic_read(&call->usage));
+
+	mutex_lock(&call->user_mutex);
 	rxrpc_release_call(rxrpc_sk(sock->sk), call);
+	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put_kernel);
 }
 EXPORT_SYMBOL(rxrpc_kernel_end_call);
@@ -450,14 +454,16 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 	case RXRPC_SERVER_BOUND:
 	case RXRPC_SERVER_LISTENING:
 		ret = rxrpc_do_sendmsg(rx, m, len);
-		break;
+		/* The socket has been unlocked */
+		goto out;
 	default:
 		ret = -EINVAL;
-		break;
+		goto error_unlock;
 	}
 
 error_unlock:
 	release_sock(&rx->sk);
+out:
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 12be432be9b2..26a7b1db1361 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -467,6 +467,7 @@ struct rxrpc_call {
 	struct rxrpc_connection	*conn;		/* connection carrying call */
 	struct rxrpc_peer	*peer;		/* Peer record for remote address */
 	struct rxrpc_sock __rcu	*socket;	/* socket responsible */
+	struct mutex		user_mutex;	/* User access mutex */
 	ktime_t			ack_at;		/* When deferred ACK needs to happen */
 	ktime_t			resend_at;	/* When next resend needs to happen */
 	ktime_t			ping_at;	/* When next to send a ping */
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 7c4c64ab8da2..0ed181f53f32 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -323,6 +323,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
  *
  * If we want to report an error, we mark the skb with the packet type and
  * abort code and return NULL.
+ *
+ * The call is returned with the user access mutex held.
  */
 struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 					   struct rxrpc_connection *conn,
@@ -371,6 +373,18 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 	trace_rxrpc_receive(call, rxrpc_receive_incoming,
 			    sp->hdr.serial, sp->hdr.seq);
 
+	/* Lock the call to prevent rxrpc_kernel_send/recv_data() and
+	 * sendmsg()/recvmsg() inconveniently stealing the mutex once the
+	 * notification is generated.
+	 *
+	 * The BUG should never happen because the kernel should be well
+	 * behaved enough not to access the call before the first notification
+	 * event and userspace is prevented from doing so until the state is
+	 * appropriate.
+	 */
+	if (!mutex_trylock(&call->user_mutex))
+		BUG();
+
 	/* Make the call live. */
 	rxrpc_incoming_call(rx, call, skb);
 	conn = call->conn;
@@ -429,10 +443,12 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 /*
  * handle acceptance of a call by userspace
  * - assign the user call ID to the call at the front of the queue
+ * - called with the socket locked.
  */
 struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
 				     unsigned long user_call_ID,
 				     rxrpc_notify_rx_t notify_rx)
+	__releases(&rx->sk.sk_lock.slock)
 {
 	struct rxrpc_call *call;
 	struct rb_node *parent, **pp;
@@ -446,6 +462,7 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
 
 	if (list_empty(&rx->to_be_accepted)) {
 		write_unlock(&rx->call_lock);
+		release_sock(&rx->sk);
 		kleave(" = -ENODATA [empty]");
 		return ERR_PTR(-ENODATA);
 	}
@@ -470,10 +487,39 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
 	 */
 	call = list_entry(rx->to_be_accepted.next,
 			  struct rxrpc_call, accept_link);
+	write_unlock(&rx->call_lock);
+
+	/* We need to gain the mutex from the interrupt handler without
+	 * upsetting lockdep, so we have to release it there and take it here.
+	 * We are, however, still holding the socket lock, so other accepts
+	 * must wait for us and no one can add the user ID behind our backs.
+	 */
+	if (mutex_lock_interruptible(&call->user_mutex) < 0) {
+		release_sock(&rx->sk);
+		kleave(" = -ERESTARTSYS");
+		return ERR_PTR(-ERESTARTSYS);
+	}
+
+	write_lock(&rx->call_lock);
 	list_del_init(&call->accept_link);
 	sk_acceptq_removed(&rx->sk);
 	rxrpc_see_call(call);
 
+	/* Find the user ID insertion point. */
+	pp = &rx->calls.rb_node;
+	parent = NULL;
+	while (*pp) {
+		parent = *pp;
+		call = rb_entry(parent, struct rxrpc_call, sock_node);
+
+		if (user_call_ID < call->user_call_ID)
+			pp = &(*pp)->rb_left;
+		else if (user_call_ID > call->user_call_ID)
+			pp = &(*pp)->rb_right;
+		else
+			BUG();
+	}
+
 	write_lock_bh(&call->state_lock);
 	switch (call->state) {
 	case RXRPC_CALL_SERVER_ACCEPTING:
@@ -499,6 +545,7 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
 	write_unlock(&rx->call_lock);
 	rxrpc_notify_socket(call);
 	rxrpc_service_prealloc(rx, GFP_KERNEL);
+	release_sock(&rx->sk);
 	_leave(" = %p{%d}", call, call->debug_id);
 	return call;
 
@@ -515,6 +562,7 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
 	write_unlock(&rx->call_lock);
 out:
 	rxrpc_service_prealloc(rx, GFP_KERNEL);
+	release_sock(&rx->sk);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
 }
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8b94db3c9b2e..d79cd36987a9 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -115,6 +115,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
 	if (!call->rxtx_annotations)
 		goto nomem_2;
 
+	mutex_init(&call->user_mutex);
 	setup_timer(&call->timer, rxrpc_call_timer_expired,
 		    (unsigned long)call);
 	INIT_WORK(&call->processor, &rxrpc_process_call);
@@ -194,14 +195,16 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call)
 }
 
 /*
- * set up a call for the given data
- * - called in process context with IRQs enabled
+ * Set up a call for the given parameters.
+ * - Called with the socket lock held, which it must release.
+ * - If it returns a call, the call's lock will need releasing by the caller.
  */
 struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 					 struct rxrpc_conn_parameters *cp,
 					 struct sockaddr_rxrpc *srx,
 					 unsigned long user_call_ID,
 					 gfp_t gfp)
+	__releases(&rx->sk.sk_lock.slock)
 {
 	struct rxrpc_call *call, *xcall;
 	struct rb_node *parent, **pp;
@@ -212,6 +215,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 
 	call = rxrpc_alloc_client_call(srx, gfp);
 	if (IS_ERR(call)) {
+		release_sock(&rx->sk);
 		_leave(" = %ld", PTR_ERR(call));
 		return call;
 	}
@@ -219,6 +223,11 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage),
 			 here, (const void *)user_call_ID);
 
+	/* We need to protect a partially set up call against the user as we
+	 * will be acting outside the socket lock.
+	 */
+	mutex_lock(&call->user_mutex);
+
 	/* Publish the call, even though it is incompletely set up as yet */
 	write_lock(&rx->call_lock);
 
@@ -250,6 +259,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	list_add_tail(&call->link, &rxrpc_calls);
 	write_unlock(&rxrpc_call_lock);
 
+	/* From this point on, the call is protected by its own lock. */
+	release_sock(&rx->sk);
+
 	/* Set up or get a connection record and set the protocol parameters,
 	 * including channel number and call ID.
 	 */
@@ -279,6 +291,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	 */
 error_dup_user_ID:
 	write_unlock(&rx->call_lock);
+	release_sock(&rx->sk);
 	ret = -EEXIST;
 
 error:
@@ -287,6 +300,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
 			 here, ERR_PTR(ret));
 	rxrpc_release_call(rx, call);
+	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 78ec33477adf..9f4cfa25af7c 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1194,6 +1194,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
 			goto reject_packet;
 		}
 		rxrpc_send_ping(call, skb, skew);
+		mutex_unlock(&call->user_mutex);
 	}
 
 	rxrpc_input_call_packet(call, skb, skew);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index f3a688e10843..22447dbcc380 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -487,6 +487,20 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0);
 
+	/* We're going to drop the socket lock, so we need to lock the call
+	 * against interference by sendmsg.
+	 */
+	if (!mutex_trylock(&call->user_mutex)) {
+		ret = -EWOULDBLOCK;
+		if (flags & MSG_DONTWAIT)
+			goto error_requeue_call;
+		ret = -ERESTARTSYS;
+		if (mutex_lock_interruptible(&call->user_mutex) < 0)
+			goto error_requeue_call;
+	}
+
+	release_sock(&rx->sk);
+
 	if (test_bit(RXRPC_CALL_RELEASED, &call->flags))
 		BUG();
 
@@ -502,7 +516,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 				       &call->user_call_ID);
 		}
 		if (ret < 0)
-			goto error;
+			goto error_unlock_call;
 	}
 
 	if (msg->msg_name) {
@@ -533,12 +547,12 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	}
 
 	if (ret < 0)
-		goto error;
+		goto error_unlock_call;
 
 	if (call->state == RXRPC_CALL_COMPLETE) {
 		ret = rxrpc_recvmsg_term(call, msg);
 		if (ret < 0)
-			goto error;
+			goto error_unlock_call;
 		if (!(flags & MSG_PEEK))
 			rxrpc_release_call(rx, call);
 		msg->msg_flags |= MSG_EOR;
@@ -551,8 +565,21 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		msg->msg_flags &= ~MSG_MORE;
 	ret = copied;
 
-error:
+error_unlock_call:
+	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
+	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
+	return ret;
+
+error_requeue_call:
+	if (!(flags & MSG_PEEK)) {
+		write_lock_bh(&rx->recvmsg_lock);
+		list_add(&call->recvmsg_link, &rx->recvmsg_q);
+		write_unlock_bh(&rx->recvmsg_lock);
+		trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0);
+	} else {
+		rxrpc_put_call(call, rxrpc_call_put);
+	}
 error_no_call:
 	release_sock(&rx->sk);
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
@@ -609,7 +636,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 	iov.iov_len = size - *_offset;
 	iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset);
 
-	lock_sock(sock->sk);
+	mutex_lock(&call->user_mutex);
 
 	switch (call->state) {
 	case RXRPC_CALL_CLIENT_RECV_REPLY:
@@ -648,7 +675,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 read_phase_complete:
 	ret = 1;
 out:
-	release_sock(sock->sk);
+	mutex_unlock(&call->user_mutex);
 	_leave(" = %d [%zu,%d]", ret, *_offset, *_abort);
 	return ret;
 
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 0a6ef217aa8a..31c1538c1a8d 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -59,9 +59,12 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 		}
 
 		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
-		release_sock(&rx->sk);
+		mutex_unlock(&call->user_mutex);
 		*timeo = schedule_timeout(*timeo);
-		lock_sock(&rx->sk);
+		if (mutex_lock_interruptible(&call->user_mutex) < 0) {
+			ret = sock_intr_errno(*timeo);
+			break;
+		}
 	}
 
 	remove_wait_queue(&call->waitq, &myself);
@@ -171,7 +174,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
 /*
  * send data through a socket
  * - must be called in process context
- * - caller holds the socket locked
+ * - The caller holds the call user access mutex, but not the socket lock.
  */
 static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
@@ -437,10 +440,13 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg,
 
 /*
  * Create a new client call for sendmsg().
+ * - Called with the socket lock held, which it must release.
+ * - If it returns a call, the call's lock will need releasing by the caller.
  */
 static struct rxrpc_call *
 rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 				  unsigned long user_call_ID, bool exclusive)
+	__releases(&rx->sk.sk_lock.slock)
 {
 	struct rxrpc_conn_parameters cp;
 	struct rxrpc_call *call;
@@ -450,8 +456,10 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 
 	_enter("");
 
-	if (!msg->msg_name)
+	if (!msg->msg_name) {
+		release_sock(&rx->sk);
 		return ERR_PTR(-EDESTADDRREQ);
+	}
 
 	key = rx->key;
 	if (key && !rx->key->payload.data[0])
@@ -464,6 +472,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 	cp.exclusive		= rx->exclusive | exclusive;
 	cp.service_id		= srx->srx_service;
 	call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, GFP_KERNEL);
+	/* The socket is now unlocked */
 
 	_leave(" = %p\n", call);
 	return call;
@@ -475,6 +484,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
  * - the socket may be either a client socket or a server socket
  */
 int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
+	__releases(&rx->sk.sk_lock.slock)
 {
 	enum rxrpc_command cmd;
 	struct rxrpc_call *call;
@@ -488,12 +498,14 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code,
 				 &exclusive);
 	if (ret < 0)
-		return ret;
+		goto error_release_sock;
 
 	if (cmd == RXRPC_CMD_ACCEPT) {
+		ret = -EINVAL;
 		if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
-			return -EINVAL;
+			goto error_release_sock;
 		call = rxrpc_accept_call(rx, user_call_ID, NULL);
+		/* The socket is now unlocked. */
 		if (IS_ERR(call))
 			return PTR_ERR(call);
 		rxrpc_put_call(call, rxrpc_call_put);
@@ -502,12 +514,29 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 
 	call = rxrpc_find_call_by_user_ID(rx, user_call_ID);
 	if (!call) {
+		ret = -EBADSLT;
 		if (cmd != RXRPC_CMD_SEND_DATA)
-			return -EBADSLT;
+			goto error_release_sock;
+		ret = -EBUSY;
+		if (call->state == RXRPC_CALL_UNINITIALISED ||
+		    call->state == RXRPC_CALL_CLIENT_AWAIT_CONN ||
+		    call->state == RXRPC_CALL_SERVER_PREALLOC ||
+		    call->state == RXRPC_CALL_SERVER_SECURING ||
+		    call->state == RXRPC_CALL_SERVER_ACCEPTING)
+			goto error_release_sock;
 		call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID,
 							 exclusive);
+		/* The socket is now unlocked... */
 		if (IS_ERR(call))
 			return PTR_ERR(call);
+		/* ... and we have the call lock. */
+	} else {
+		ret = mutex_lock_interruptible(&call->user_mutex);
+		release_sock(&rx->sk);
+		if (ret < 0) {
+			ret = -ERESTARTSYS;
+			goto error_put;
+		}
 	}
 
 	_debug("CALL %d USR %lx ST %d on CONN %p",
@@ -535,9 +564,15 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		ret = rxrpc_send_data(rx, call, msg, len);
 	}
 
+	mutex_unlock(&call->user_mutex);
+error_put:
 	rxrpc_put_call(call, rxrpc_call_put);
 	_leave(" = %d", ret);
 	return ret;
+
+error_release_sock:
+	release_sock(&rx->sk);
+	return ret;
 }
 
 /**
@@ -562,7 +597,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 	ASSERTCMP(msg->msg_name, ==, NULL);
 	ASSERTCMP(msg->msg_control, ==, NULL);
 
-	lock_sock(sock->sk);
+	mutex_lock(&call->user_mutex);
 
 	_debug("CALL %d USR %lx ST %d on CONN %p",
 	       call->debug_id, call->user_call_ID, call->state, call->conn);
@@ -577,7 +612,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
 	}
 
-	release_sock(sock->sk);
+	mutex_unlock(&call->user_mutex);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -598,12 +633,12 @@ void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
 {
 	_enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
 
-	lock_sock(sock->sk);
+	mutex_lock(&call->user_mutex);
 
 	if (rxrpc_abort_call(why, call, 0, abort_code, error))
 		rxrpc_send_abort_packet(call);
 
-	release_sock(sock->sk);
+	mutex_unlock(&call->user_mutex);
 	_leave("");
 }
 
-- 
GitLab


From 5179b26694c92373275e4933f5d0ff32d585c675 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 28 Feb 2017 12:41:29 +0800
Subject: [PATCH 431/898] sctp: call rcu_read_lock before checking for
 duplicate transport nodes

Commit cd2b70875058 ("sctp: check duplicate node before inserting a
new transport") called rhltable_lookup() to check for the duplicate
transport node in transport rhashtable.

But rhltable_lookup() doesn't call rcu_read_lock inside, it could cause
a use-after-free issue if it tries to dereference the node that another
cpu has freed it. Note that sock lock can not avoid this as it is per
sock.

This patch is to fix it by calling rcu_read_lock before checking for
duplicate transport nodes.

Fixes: cd2b70875058 ("sctp: check duplicate node before inserting a new transport")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index fc458968fe4b..2a28ab20487f 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -884,14 +884,17 @@ int sctp_hash_transport(struct sctp_transport *t)
 	arg.paddr = &t->ipaddr;
 	arg.lport = htons(t->asoc->base.bind_addr.port);
 
+	rcu_read_lock();
 	list = rhltable_lookup(&sctp_transport_hashtable, &arg,
 			       sctp_hash_params);
 
 	rhl_for_each_entry_rcu(transport, tmp, list, node)
 		if (transport->asoc->ep == t->asoc->ep) {
+			rcu_read_unlock();
 			err = -EEXIST;
 			goto out;
 		}
+	rcu_read_unlock();
 
 	err = rhltable_insert_key(&sctp_transport_hashtable, &arg,
 				  &t->node, sctp_hash_params);
-- 
GitLab


From 4f7bfb3982e02aacc5fb6e1a121e5326c1778ac3 Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@oracle.com>
Date: Tue, 28 Feb 2017 01:45:40 -0500
Subject: [PATCH 432/898] rds: ib: add the static type to the variables

The variables rds_ib_mr_1m_pool_size and rds_ib_mr_8k_pool_size
are used only in the ib.c file. As such, the static type is
added to limit them in this file.

Cc: Joe Jin <joe.jin@oracle.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib.c    | 4 ++--
 net/rds/ib_mr.h | 2 --
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/rds/ib.c b/net/rds/ib.c
index 91fe46f1e4cc..0f557b243311 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -45,8 +45,8 @@
 #include "ib.h"
 #include "ib_mr.h"
 
-unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE;
-unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE;
+static unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE;
+static unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE;
 unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT;
 
 module_param(rds_ib_mr_1m_pool_size, int, 0444);
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 24c086db4511..5d6e98a79a5e 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -107,8 +107,6 @@ struct rds_ib_mr_pool {
 };
 
 extern struct workqueue_struct *rds_ib_mr_wq;
-extern unsigned int rds_ib_mr_1m_pool_size;
-extern unsigned int rds_ib_mr_8k_pool_size;
 extern bool prefer_frmr;
 
 struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_dev,
-- 
GitLab


From f7df4923fa986247e93ec2cdff5ca168fff14dcf Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 28 Feb 2017 08:55:40 +0100
Subject: [PATCH 433/898] mlxsw: spectrum_router: Avoid potential packets loss

When the structure of the LPM tree changes (f.e., due to the addition of
a new prefix), we unbind the old tree and then bind the new one. This
may result in temporary packet loss.

Instead, overwrite the old binding with the new one.

Fixes: 6b75c4807db3 ("mlxsw: spectrum_router: Add virtual router management")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 30 ++++++++++++-------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index d7ac22d7f940..bd8de6b9be71 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -441,30 +441,40 @@ static int
 mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
 {
-	struct mlxsw_sp_lpm_tree *lpm_tree;
+	struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
+	struct mlxsw_sp_lpm_tree *new_tree;
+	int err;
 
-	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage,
-				     &vr->lpm_tree->prefix_usage))
+	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage))
 		return 0;
 
-	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
+	new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
 					 vr->proto, false);
-	if (IS_ERR(lpm_tree)) {
+	if (IS_ERR(new_tree)) {
 		/* We failed to get a tree according to the required
 		 * prefix usage. However, the current tree might be still good
 		 * for us if our requirement is subset of the prefixes used
 		 * in the tree.
 		 */
 		if (mlxsw_sp_prefix_usage_subset(req_prefix_usage,
-						 &vr->lpm_tree->prefix_usage))
+						 &lpm_tree->prefix_usage))
 			return 0;
-		return PTR_ERR(lpm_tree);
+		return PTR_ERR(new_tree);
 	}
 
-	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
+	/* Prevent packet loss by overwriting existing binding */
+	vr->lpm_tree = new_tree;
+	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	if (err)
+		goto err_tree_bind;
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+
+	return 0;
+
+err_tree_bind:
 	vr->lpm_tree = lpm_tree;
-	return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
+	return err;
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
-- 
GitLab


From 0bf09c397e13b70ab6064eb2af69b8fa8e68a24e Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Tue, 28 Feb 2017 10:39:48 +0200
Subject: [PATCH 434/898] MAINTAINERS: Orphan usb/net/hso driver

The email address of Jan Dumon bounces, and there is not relevant information
in the linked website.

Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 846f97aa3508..5a00239fd7b3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6012,9 +6012,8 @@ F:	include/linux/hsi/
 F:	include/uapi/linux/hsi/
 
 HSO 3G MODEM DRIVER
-M:	Jan Dumon <j.dumon@option.com>
-W:	http://www.pharscape.org
-S:	Maintained
+L:	linux-usb@vger.kernel.org
+S:	Orphan
 F:	drivers/net/usb/hso.c
 
 HSR NETWORK PROTOCOL
-- 
GitLab


From 4f3de46f7a57a8ecc16c7ef69c6917b3731a7c5f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 28 Feb 2017 11:58:22 +0000
Subject: [PATCH 435/898] net: usb: asix_devices: fix missing return code check
 on call to asix_write_medium_mode

The call to asix_write_medium_mode is not updating the return code ret
and yet ret is being checked for an error. Fix this by assigning ret to
the return code from the call asix_write_medium_mode.

Detected by CoverityScan, CID#1357148 ("Logically Dead Code")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 6e98ede997d3..0dd510604118 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -346,7 +346,7 @@ static int ax88772_reset(struct usbnet *dev)
 	if (ret < 0)
 		goto out;
 
-	asix_write_medium_mode(dev, AX88772_MEDIUM_DEFAULT, 0);
+	ret = asix_write_medium_mode(dev, AX88772_MEDIUM_DEFAULT, 0);
 	if (ret < 0)
 		goto out;
 
-- 
GitLab


From b2d0fe35471d1a71471f99147ffb5986bd60e744 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 28 Feb 2017 15:02:15 +0300
Subject: [PATCH 436/898] net/mlx4: && vs & typo

Bitwise & was obviously intended here.

Fixes: 745d8ae4622c ("net/mlx4: Spoofcheck and zero MAC can't coexist")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mlx4/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index e965e5090d96..a858bcb6220b 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -109,7 +109,7 @@ static inline void mlx4_u64_to_mac(u8 *addr, u64 mac)
 	int i;
 
 	for (i = ETH_ALEN; i > 0; i--) {
-		addr[i - 1] = mac && 0xFF;
+		addr[i - 1] = mac & 0xFF;
 		mac >>= 8;
 	}
 }
-- 
GitLab


From 39e6c8208d7b6fb9d2047850fb3327db567b564b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 Feb 2017 10:34:50 -0800
Subject: [PATCH 437/898] net: solve a NAPI race

While playing with mlx4 hardware timestamping of RX packets, I found
that some packets were received by TCP stack with a ~200 ms delay...

Since the timestamp was provided by the NIC, and my probe was added
in tcp_v4_rcv() while in BH handler, I was confident it was not
a sender issue, or a drop in the network.

This would happen with a very low probability, but hurting RPC
workloads.

A NAPI driver normally arms the IRQ after the napi_complete_done(),
after NAPI_STATE_SCHED is cleared, so that the hard irq handler can grab
it.

Problem is that if another point in the stack grabs NAPI_STATE_SCHED bit
while IRQ are not disabled, we might have later an IRQ firing and
finding this bit set, right before napi_complete_done() clears it.

This can happen with busy polling users, or if gro_flush_timeout is
used. But some other uses of napi_schedule() in drivers can cause this
as well.

thread 1                                 thread 2 (could be on same cpu, or not)

// busy polling or napi_watchdog()
napi_schedule();
...
napi->poll()

device polling:
read 2 packets from ring buffer
                                          Additional 3rd packet is
available.
                                          device hard irq

                                          // does nothing because
NAPI_STATE_SCHED bit is owned by thread 1
                                          napi_schedule();

napi_complete_done(napi, 2);
rearm_irq();

Note that rearm_irq() will not force the device to send an additional
IRQ for the packet it already signaled (3rd packet in my example)

This patch adds a new NAPI_STATE_MISSED bit, that napi_schedule_prep()
can set if it could not grab NAPI_STATE_SCHED

Then napi_complete_done() properly reschedules the napi to make sure
we do not miss something.

Since we manipulate multiple bits at once, use cmpxchg() like in
sk_busy_loop() to provide proper transactions.

In v2, I changed napi_watchdog() to use a relaxed variant of
napi_schedule_prep() : No need to set NAPI_STATE_MISSED from this point.

In v3, I added more details in the changelog and clears
NAPI_STATE_MISSED in busy_poll_stop()

In v4, I added the ideas given by Alexander Duyck in v3 review

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 29 +++++----------
 net/core/dev.c            | 76 ++++++++++++++++++++++++++++++++++++---
 2 files changed, 81 insertions(+), 24 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f40f0ab3847a..97456b2539e4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -330,6 +330,7 @@ struct napi_struct {
 
 enum {
 	NAPI_STATE_SCHED,	/* Poll is scheduled */
+	NAPI_STATE_MISSED,	/* reschedule a napi */
 	NAPI_STATE_DISABLE,	/* Disable pending */
 	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
 	NAPI_STATE_HASHED,	/* In NAPI hash (busy polling possible) */
@@ -338,12 +339,13 @@ enum {
 };
 
 enum {
-	NAPIF_STATE_SCHED	 = (1UL << NAPI_STATE_SCHED),
-	NAPIF_STATE_DISABLE	 = (1UL << NAPI_STATE_DISABLE),
-	NAPIF_STATE_NPSVC	 = (1UL << NAPI_STATE_NPSVC),
-	NAPIF_STATE_HASHED	 = (1UL << NAPI_STATE_HASHED),
-	NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL),
-	NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_SCHED	 = BIT(NAPI_STATE_SCHED),
+	NAPIF_STATE_MISSED	 = BIT(NAPI_STATE_MISSED),
+	NAPIF_STATE_DISABLE	 = BIT(NAPI_STATE_DISABLE),
+	NAPIF_STATE_NPSVC	 = BIT(NAPI_STATE_NPSVC),
+	NAPIF_STATE_HASHED	 = BIT(NAPI_STATE_HASHED),
+	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
+	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
 };
 
 enum gro_result {
@@ -414,20 +416,7 @@ static inline bool napi_disable_pending(struct napi_struct *n)
 	return test_bit(NAPI_STATE_DISABLE, &n->state);
 }
 
-/**
- *	napi_schedule_prep - check if NAPI can be scheduled
- *	@n: NAPI context
- *
- * Test if NAPI routine is already running, and if not mark
- * it as running.  This is used as a condition variable to
- * insure only one NAPI poll instance runs.  We also make
- * sure there is no pending NAPI disable.
- */
-static inline bool napi_schedule_prep(struct napi_struct *n)
-{
-	return !napi_disable_pending(n) &&
-		!test_and_set_bit(NAPI_STATE_SCHED, &n->state);
-}
+bool napi_schedule_prep(struct napi_struct *n);
 
 /**
  *	napi_schedule - schedule NAPI poll
diff --git a/net/core/dev.c b/net/core/dev.c
index 304f2deae5f9..e63bf61b19be 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4883,6 +4883,39 @@ void __napi_schedule(struct napi_struct *n)
 }
 EXPORT_SYMBOL(__napi_schedule);
 
+/**
+ *	napi_schedule_prep - check if napi can be scheduled
+ *	@n: napi context
+ *
+ * Test if NAPI routine is already running, and if not mark
+ * it as running.  This is used as a condition variable
+ * insure only one NAPI poll instance runs.  We also make
+ * sure there is no pending NAPI disable.
+ */
+bool napi_schedule_prep(struct napi_struct *n)
+{
+	unsigned long val, new;
+
+	do {
+		val = READ_ONCE(n->state);
+		if (unlikely(val & NAPIF_STATE_DISABLE))
+			return false;
+		new = val | NAPIF_STATE_SCHED;
+
+		/* Sets STATE_MISSED bit if STATE_SCHED was already set
+		 * This was suggested by Alexander Duyck, as compiler
+		 * emits better code than :
+		 * if (val & NAPIF_STATE_SCHED)
+		 *     new |= NAPIF_STATE_MISSED;
+		 */
+		new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED *
+						   NAPIF_STATE_MISSED;
+	} while (cmpxchg(&n->state, val, new) != val);
+
+	return !(val & NAPIF_STATE_SCHED);
+}
+EXPORT_SYMBOL(napi_schedule_prep);
+
 /**
  * __napi_schedule_irqoff - schedule for receive
  * @n: entry to schedule
@@ -4897,7 +4930,7 @@ EXPORT_SYMBOL(__napi_schedule_irqoff);
 
 bool napi_complete_done(struct napi_struct *n, int work_done)
 {
-	unsigned long flags;
+	unsigned long flags, val, new;
 
 	/*
 	 * 1) Don't let napi dequeue from the cpu poll list
@@ -4927,7 +4960,27 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		list_del_init(&n->poll_list);
 		local_irq_restore(flags);
 	}
-	WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state));
+
+	do {
+		val = READ_ONCE(n->state);
+
+		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
+
+		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+
+		/* If STATE_MISSED was set, leave STATE_SCHED set,
+		 * because we will call napi->poll() one more time.
+		 * This C code was suggested by Alexander Duyck to help gcc.
+		 */
+		new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED *
+						    NAPIF_STATE_SCHED;
+	} while (cmpxchg(&n->state, val, new) != val);
+
+	if (unlikely(val & NAPIF_STATE_MISSED)) {
+		__napi_schedule(n);
+		return false;
+	}
+
 	return true;
 }
 EXPORT_SYMBOL(napi_complete_done);
@@ -4953,6 +5006,16 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 {
 	int rc;
 
+	/* Busy polling means there is a high chance device driver hard irq
+	 * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was
+	 * set in napi_schedule_prep().
+	 * Since we are about to call napi->poll() once more, we can safely
+	 * clear NAPI_STATE_MISSED.
+	 *
+	 * Note: x86 could use a single "lock and ..." instruction
+	 * to perform these two clear_bit()
+	 */
+	clear_bit(NAPI_STATE_MISSED, &napi->state);
 	clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
 
 	local_bh_disable();
@@ -5088,8 +5151,13 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	struct napi_struct *napi;
 
 	napi = container_of(timer, struct napi_struct, timer);
-	if (napi->gro_list)
-		napi_schedule_irqoff(napi);
+
+	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
+	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
+	 */
+	if (napi->gro_list && !napi_disable_pending(napi) &&
+	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+		__napi_schedule_irqoff(napi);
 
 	return HRTIMER_NORESTART;
 }
-- 
GitLab


From 56de859e9967c070464a9a9f4f18d73f9447298e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:36 -0800
Subject: [PATCH 438/898] vxlan: lock RCU on TX path

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: c6fcc4fc5f8b ("vxlan: avoid using stale vxlan socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b7911994112a..e375560cc74e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2105,6 +2105,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
 				     vxlan->cfg.port_max, true);
 
+	rcu_read_lock();
 	if (dst->sa.sa_family == AF_INET) {
 		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
 		struct rtable *rt;
@@ -2127,7 +2128,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 						    dst_port, vni, &rt->dst,
 						    rt->rt_flags);
 			if (err)
-				return;
+				goto out_unlock;
 		} else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
 			df = htons(IP_DF);
 		}
@@ -2166,7 +2167,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 						    dst_port, vni, ndst,
 						    rt6i_flags);
 			if (err)
-				return;
+				goto out_unlock;
 		}
 
 		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
@@ -2183,6 +2184,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				     label, src_port, dst_port, !udp_sum);
 #endif
 	}
+out_unlock:
+	rcu_read_unlock();
 	return;
 
 drop:
@@ -2191,6 +2194,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	return;
 
 tx_error:
+	rcu_read_unlock();
 	if (err == -ELOOP)
 		dev->stats.collisions++;
 	else if (err == -ENETUNREACH)
-- 
GitLab


From a717e3f740803cc88bd5c9a70c93504f6a368663 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:37 -0800
Subject: [PATCH 439/898] geneve: lock RCU on TX path

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: fceb9c3e3825 ("geneve: avoid using stale geneve socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 45301cb98bc1..7074b40ebd7f 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -881,12 +881,14 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 		info = &geneve->info;
 	}
 
+	rcu_read_lock();
 #if IS_ENABLED(CONFIG_IPV6)
 	if (info->mode & IP_TUNNEL_INFO_IPV6)
 		err = geneve6_xmit_skb(skb, dev, geneve, info);
 	else
 #endif
 		err = geneve_xmit_skb(skb, dev, geneve, info);
+	rcu_read_unlock();
 
 	if (likely(!err))
 		return NETDEV_TX_OK;
-- 
GitLab


From 8c171d6ca56c6891372a97af26b58b2cfad7fd9a Mon Sep 17 00:00:00 2001
From: Felix Jia <felix.jia@alliedtelesis.co.nz>
Date: Mon, 27 Feb 2017 12:41:23 +1300
Subject: [PATCH 440/898] net/ipv6: avoid possible dead locking on
 addr_gen_mode sysctl

The addr_gen_mode variable can be accessed by both sysctl and netlink.
Repleacd rtnl_lock() with rtnl_trylock() protect the sysctl operation to
avoid the possbile dead lock.`

Signed-off-by: Felix Jia <felix.jia@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3a2025f5bf2c..cfc485a8e1c0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5692,13 +5692,18 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
 	struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1;
 	struct net *net = (struct net *)ctl->extra2;
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
 
 	if (write) {
 		new_val = *((int *)ctl->data);
 
-		if (check_addr_gen_mode(new_val) < 0)
-			return -EINVAL;
+		if (check_addr_gen_mode(new_val) < 0) {
+			ret = -EINVAL;
+			goto out;
+		}
 
 		/* request for default */
 		if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) {
@@ -5707,20 +5712,23 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
 		/* request for individual net device */
 		} else {
 			if (!idev)
-				return ret;
+				goto out;
 
-			if (check_stable_privacy(idev, net, new_val) < 0)
-				return -EINVAL;
+			if (check_stable_privacy(idev, net, new_val) < 0) {
+				ret = -EINVAL;
+				goto out;
+			}
 
 			if (idev->cnf.addr_gen_mode != new_val) {
 				idev->cnf.addr_gen_mode = new_val;
-				rtnl_lock();
 				addrconf_dev_config(idev->dev);
-				rtnl_unlock();
 			}
 		}
 	}
 
+out:
+	rtnl_unlock();
+
 	return ret;
 }
 
-- 
GitLab


From 3b45a4106f146c336cbcaccb9d8d0fa0e5c3dc1d Mon Sep 17 00:00:00 2001
From: Liping Zhang <zlpnobody@gmail.com>
Date: Mon, 27 Feb 2017 20:59:39 +0800
Subject: [PATCH 441/898] net: route: add missing nla_policy entry for RTA_MARK
 attribute

This will add stricter validating for RTA_MARK attribute.

Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 1 +
 net/ipv6/route.c        | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b39a791f6756..42bfd08109dd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -622,6 +622,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_ENCAP_TYPE]	= { .type = NLA_U16 },
 	[RTA_ENCAP]		= { .type = NLA_NESTED },
 	[RTA_UID]		= { .type = NLA_U32 },
+	[RTA_MARK]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f54f4265b37f..d94f1dfa54c8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2891,6 +2891,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_ENCAP]		= { .type = NLA_NESTED },
 	[RTA_EXPIRES]		= { .type = NLA_U32 },
 	[RTA_UID]		= { .type = NLA_U32 },
+	[RTA_MARK]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
-- 
GitLab


From 4ab18701c66552944188dbcd0ce0012729baab84 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Tue, 3 Jan 2017 09:37:34 -0800
Subject: [PATCH 442/898] xtensa: move parse_tag_fdt out of #ifdef
 CONFIG_BLK_DEV_INITRD

FDT tag parsing is not related to whether BLK_DEV_INITRD is configured
or not, move it out of the corresponding #ifdef/#endif block.
This fixes passing external FDT to the kernel configured w/o
BLK_DEV_INITRD support.

Cc: stable@vger.kernel.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/kernel/setup.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 88a044af7504..23f2e034ba46 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -133,6 +133,8 @@ static int __init parse_tag_initrd(const bp_tag_t* tag)
 
 __tagtable(BP_TAG_INITRD, parse_tag_initrd);
 
+#endif /* CONFIG_BLK_DEV_INITRD */
+
 #ifdef CONFIG_OF
 
 static int __init parse_tag_fdt(const bp_tag_t *tag)
@@ -145,8 +147,6 @@ __tagtable(BP_TAG_FDT, parse_tag_fdt);
 
 #endif /* CONFIG_OF */
 
-#endif /* CONFIG_BLK_DEV_INITRD */
-
 static int __init parse_tag_cmdline(const bp_tag_t* tag)
 {
 	strlcpy(command_line, (char *)(tag->data), COMMAND_LINE_SIZE);
-- 
GitLab


From 9a736fcb096b43b68af8329eb12abc8256dceaba Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Sun, 25 Dec 2016 04:58:57 -0800
Subject: [PATCH 443/898] xtensa: clean up bootable image build targets

Currently xtensa uses 'zImage' as a synonym of 'all', but in fact xtensa
supports three targets: 'Image' (ELF image with reset vector), 'zImage'
(compressed redboot image) and 'uImage' (U-Boot image).
Provide separate 'Image', 'zImage' and 'uImage' make targets that only
build corresponding image type. Make 'all' build all images appropriate
for a platform.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/Makefile                   |  8 +++-----
 arch/xtensa/boot/Makefile              | 23 ++++++++++++++++-------
 arch/xtensa/boot/boot-elf/Makefile     |  2 +-
 arch/xtensa/boot/boot-redboot/Makefile |  2 +-
 arch/xtensa/boot/boot-uboot/Makefile   | 14 --------------
 5 files changed, 21 insertions(+), 28 deletions(-)
 delete mode 100644 arch/xtensa/boot/boot-uboot/Makefile

diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index e54189427b31..7ee02fe4a63d 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -93,11 +93,7 @@ endif
 
 boot		:= arch/xtensa/boot
 
-all: zImage
-
-bzImage : zImage
-
-zImage: vmlinux
+all Image zImage uImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
 %.dtb:
@@ -107,6 +103,8 @@ dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot)/dts
 
 define archhelp
+  @echo '* Image       - Kernel ELF image with reset vector'
   @echo '* zImage      - Compressed kernel image (arch/xtensa/boot/images/zImage.*)'
+  @echo '* uImage      - U-Boot wrapped image'
   @echo '  dtbs        - Build device tree blobs for enabled boards'
 endef
diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile
index ca20a892021b..53e4178711e6 100644
--- a/arch/xtensa/boot/Makefile
+++ b/arch/xtensa/boot/Makefile
@@ -21,14 +21,17 @@ subdir-y	:= lib
 
 # Subdirs for the boot loader(s)
 
-bootdir-$(CONFIG_XTENSA_PLATFORM_ISS)	 += boot-elf
-bootdir-$(CONFIG_XTENSA_PLATFORM_XT2000) += boot-redboot boot-elf boot-uboot
-bootdir-$(CONFIG_XTENSA_PLATFORM_XTFPGA) += boot-redboot boot-elf boot-uboot
+boot-$(CONFIG_XTENSA_PLATFORM_ISS)    += Image
+boot-$(CONFIG_XTENSA_PLATFORM_XT2000) += Image zImage uImage
+boot-$(CONFIG_XTENSA_PLATFORM_XTFPGA) += Image zImage uImage
 
-zImage Image: $(bootdir-y)
+all: $(boot-y)
+Image: boot-elf
+zImage: boot-redboot
+uImage: $(obj)/uImage
 
-$(bootdir-y): $(addprefix $(obj)/,$(subdir-y)) \
-	      $(addprefix $(obj)/,$(host-progs))
+boot-elf boot-redboot: $(addprefix $(obj)/,$(subdir-y)) \
+		       $(addprefix $(obj)/,$(host-progs))
 	$(Q)$(MAKE) $(build)=$(obj)/$@ $(MAKECMDGOALS)
 
 OBJCOPYFLAGS = --strip-all -R .comment -R .note.gnu.build-id -O binary
@@ -41,4 +44,10 @@ vmlinux.bin.gz: vmlinux.bin FORCE
 
 boot-elf: vmlinux.bin
 boot-redboot: vmlinux.bin.gz
-boot-uboot: vmlinux.bin.gz
+
+UIMAGE_LOADADDR = $(CONFIG_KERNEL_LOAD_ADDRESS)
+UIMAGE_COMPRESSION = gzip
+
+$(obj)/uImage: vmlinux.bin.gz FORCE
+	$(call if_changed,uimage)
+	$(Q)$(kecho) '  Kernel: $@ is ready'
diff --git a/arch/xtensa/boot/boot-elf/Makefile b/arch/xtensa/boot/boot-elf/Makefile
index 89db089f5a12..521471981356 100644
--- a/arch/xtensa/boot/boot-elf/Makefile
+++ b/arch/xtensa/boot/boot-elf/Makefile
@@ -31,4 +31,4 @@ $(obj)/../Image.elf: $(obj)/Image.o $(obj)/boot.lds
 		-o $@ $(obj)/Image.o
 	$(Q)$(kecho) '  Kernel: $@ is ready'
 
-zImage:	$(obj)/../Image.elf
+all Image: $(obj)/../Image.elf
diff --git a/arch/xtensa/boot/boot-redboot/Makefile b/arch/xtensa/boot/boot-redboot/Makefile
index 8be8b9436981..8632473ad319 100644
--- a/arch/xtensa/boot/boot-redboot/Makefile
+++ b/arch/xtensa/boot/boot-redboot/Makefile
@@ -32,4 +32,4 @@ $(obj)/../zImage.redboot: $(obj)/zImage.elf
 	$(Q)$(OBJCOPY) -S -O binary $< $@
 	$(Q)$(kecho) '  Kernel: $@ is ready'
 
-zImage: $(obj)/../zImage.redboot
+all zImage: $(obj)/../zImage.redboot
diff --git a/arch/xtensa/boot/boot-uboot/Makefile b/arch/xtensa/boot/boot-uboot/Makefile
deleted file mode 100644
index 0f4c417b4196..000000000000
--- a/arch/xtensa/boot/boot-uboot/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-
-UIMAGE_LOADADDR = $(CONFIG_KERNEL_LOAD_ADDRESS)
-UIMAGE_COMPRESSION = gzip
-
-$(obj)/../uImage: vmlinux.bin.gz FORCE
-	$(call if_changed,uimage)
-	$(Q)$(kecho) '  Kernel: $@ is ready'
-
-zImage: $(obj)/../uImage
-- 
GitLab


From b46dcfa378b0cdea1ee832802c9e36750e0fffa9 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Wed, 4 Jan 2017 10:40:49 -0800
Subject: [PATCH 444/898] xtensa: allow merging vectors into .text section

Currently code for exception/IRQ vectors is stored in kernel image as
initialization data and is copied to its working addresses during
startup. It doesn't always make sense. In many cases vectors location
can be automatically decided at kernel link time and code can be placed
right there. This is especially useful for XIP kernel.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/include/asm/vectors.h |  4 +++
 arch/xtensa/kernel/setup.c        |  3 +++
 arch/xtensa/kernel/vmlinux.lds.S  | 41 +++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+)

diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h
index 77d41cc7a688..65d3da9db19b 100644
--- a/arch/xtensa/include/asm/vectors.h
+++ b/arch/xtensa/include/asm/vectors.h
@@ -67,7 +67,11 @@ static inline unsigned long xtensa_get_kio_paddr(void)
 #endif /* CONFIG_MMU */
 
 #define RESET_VECTOR1_VADDR		(XCHAL_RESET_VECTOR1_VADDR)
+#ifdef CONFIG_VECTORS_OFFSET
 #define VECBASE_VADDR			(KERNELOFFSET - CONFIG_VECTORS_OFFSET)
+#else
+#define VECBASE_VADDR			_vecbase
+#endif
 
 #if defined(XCHAL_HAVE_VECBASE) && XCHAL_HAVE_VECBASE
 
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 23f2e034ba46..7fc7bb9f3b84 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -455,6 +455,7 @@ void __init setup_arch(char **cmdline_p)
 
 	mem_reserve(__pa(&_stext), __pa(&_end));
 
+#ifdef CONFIG_VECTORS_OFFSET
 	mem_reserve(__pa(&_WindowVectors_text_start),
 		    __pa(&_WindowVectors_text_end));
 
@@ -491,6 +492,8 @@ void __init setup_arch(char **cmdline_p)
 		    __pa(&_Level6InterruptVector_text_end));
 #endif
 
+#endif /* CONFIG_VECTORS_OFFSET */
+
 #ifdef CONFIG_SMP
 	mem_reserve(__pa(&_SecondaryResetVector_text_start),
 		    __pa(&_SecondaryResetVector_text_end));
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 31411fc82662..30d9fc21e076 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -59,6 +59,7 @@ jiffies = jiffies_64;
  * garbage.)
  */
 
+#ifdef CONFIG_VECTORS_OFFSET
 #define SECTION_VECTOR(sym, section, addr, max_prevsec_size, prevsec)       \
   section addr : AT((MIN(LOADADDR(prevsec) + max_prevsec_size,		    \
 		         LOADADDR(prevsec) + SIZEOF(prevsec)) + 3) & ~ 3)   \
@@ -68,6 +69,11 @@ jiffies = jiffies_64;
     *(section)								    \
     sym ## _end = ABSOLUTE(.);						    \
   }
+#else
+#define SECTION_VECTOR(section, addr)					    \
+  . = addr;								    \
+  *(section)
+#endif
 
 /*
  *  Mapping of input sections to output sections when linking.
@@ -85,6 +91,37 @@ SECTIONS
   {
     /* The HEAD_TEXT section must be the first section! */
     HEAD_TEXT
+
+#ifndef CONFIG_VECTORS_OFFSET
+  . = ALIGN(PAGE_SIZE);
+  _vecbase = .;
+
+  SECTION_VECTOR (.WindowVectors.text, WINDOW_VECTORS_VADDR)
+#if XCHAL_EXCM_LEVEL >= 2
+  SECTION_VECTOR (.Level2InterruptVector.text, INTLEVEL2_VECTOR_VADDR)
+#endif
+#if XCHAL_EXCM_LEVEL >= 3
+  SECTION_VECTOR (.Level3InterruptVector.text, INTLEVEL3_VECTOR_VADDR)
+#endif
+#if XCHAL_EXCM_LEVEL >= 4
+  SECTION_VECTOR (.Level4InterruptVector.text, INTLEVEL4_VECTOR_VADDR)
+#endif
+#if XCHAL_EXCM_LEVEL >= 5
+  SECTION_VECTOR (.Level5InterruptVector.text, INTLEVEL5_VECTOR_VADDR)
+#endif
+#if XCHAL_EXCM_LEVEL >= 6
+  SECTION_VECTOR (.Level6InterruptVector.text, INTLEVEL6_VECTOR_VADDR)
+#endif
+  SECTION_VECTOR (.DebugInterruptVector.literal, DEBUG_VECTOR_VADDR - 4)
+  SECTION_VECTOR (.DebugInterruptVector.text, DEBUG_VECTOR_VADDR)
+  SECTION_VECTOR (.KernelExceptionVector.literal, KERNEL_VECTOR_VADDR - 4)
+  SECTION_VECTOR (.KernelExceptionVector.text, KERNEL_VECTOR_VADDR)
+  SECTION_VECTOR (.UserExceptionVector.literal, USER_VECTOR_VADDR - 4)
+  SECTION_VECTOR (.UserExceptionVector.text, USER_VECTOR_VADDR)
+  SECTION_VECTOR (.DoubleExceptionVector.literal, DOUBLEEXC_VECTOR_VADDR - 48)
+  SECTION_VECTOR (.DoubleExceptionVector.text, DOUBLEEXC_VECTOR_VADDR)
+#endif
+
     TEXT_TEXT
     VMLINUX_SYMBOL(__sched_text_start) = .;
     *(.sched.literal .sched.text)
@@ -132,6 +169,7 @@ SECTIONS
     . = ALIGN(16);
     __boot_reloc_table_start = ABSOLUTE(.);
 
+#ifdef CONFIG_VECTORS_OFFSET
     RELOCATE_ENTRY(_WindowVectors_text,
 		   .WindowVectors.text);
 #if XCHAL_EXCM_LEVEL >= 2
@@ -164,6 +202,7 @@ SECTIONS
 		   .DoubleExceptionVector.text);
     RELOCATE_ENTRY(_DebugInterruptVector_text,
 		   .DebugInterruptVector.text);
+#endif
 #if defined(CONFIG_SMP)
     RELOCATE_ENTRY(_SecondaryResetVector_text,
 		   .SecondaryResetVector.text);
@@ -186,6 +225,7 @@ SECTIONS
   . = ALIGN(4);
   .dummy : { LONG(0) }
 
+#ifdef CONFIG_VECTORS_OFFSET
   /* The vectors are relocated to the real position at startup time */
 
   SECTION_VECTOR (_WindowVectors_text,
@@ -277,6 +317,7 @@ SECTIONS
 
   . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;
 
+#endif
 #if defined(CONFIG_SMP)
 
   SECTION_VECTOR (_SecondaryResetVector_text,
-- 
GitLab


From 28db0c7b1c7fbca3637994c1ce3c4ffe142e2755 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 1 Mar 2017 16:39:55 +0530
Subject: [PATCH 445/898] PM / OPP: Documentation: Fix opp-microvolt in
 examples

The triplet present in "opp-microvolt" property should be in the order
<target min max>, while all the examples have it in the order
<min target max>.

Fix it.

Luckily all of the users of "opp-microvolt" property have applied brain
instead of copying the examples from documentation and none of the
actual dts files have it wrong.

Reported-by: Rob Herring <robh@kernel.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/devicetree/bindings/opp/opp.txt | 44 +++++++++----------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt
index 9f5ca4457b5f..7951961ef356 100644
--- a/Documentation/devicetree/bindings/opp/opp.txt
+++ b/Documentation/devicetree/bindings/opp/opp.txt
@@ -188,14 +188,14 @@ Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
 
 		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = <970000 975000 985000>;
+			opp-microvolt = <975000 970000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp@1100000000 {
 			opp-hz = /bits/ 64 <1100000000>;
-			opp-microvolt = <980000 1000000 1010000>;
+			opp-microvolt = <1000000 980000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
@@ -267,14 +267,14 @@ independently.
 
 		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = <970000 975000 985000>;
+			opp-microvolt = <975000 970000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp@1100000000 {
 			opp-hz = /bits/ 64 <1100000000>;
-			opp-microvolt = <980000 1000000 1010000>;
+			opp-microvolt = <1000000 980000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
@@ -343,14 +343,14 @@ DVFS state together.
 
 		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = <970000 975000 985000>;
+			opp-microvolt = <975000 970000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp@1100000000 {
 			opp-hz = /bits/ 64 <1100000000>;
-			opp-microvolt = <980000 1000000 1010000>;
+			opp-microvolt = <1000000 980000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
@@ -369,7 +369,7 @@ DVFS state together.
 
 		opp@1300000000 {
 			opp-hz = /bits/ 64 <1300000000>;
-			opp-microvolt = <1045000 1050000 1055000>;
+			opp-microvolt = <1050000 1045000 1055000>;
 			opp-microamp = <95000>;
 			clock-latency-ns = <400000>;
 			opp-suspend;
@@ -382,7 +382,7 @@ DVFS state together.
 		};
 		opp@1500000000 {
 			opp-hz = /bits/ 64 <1500000000>;
-			opp-microvolt = <1010000 1100000 1110000>;
+			opp-microvolt = <1100000 1010000 1110000>;
 			opp-microamp = <95000>;
 			clock-latency-ns = <400000>;
 			turbo-mode;
@@ -424,9 +424,9 @@ Example 4: Handling multiple regulators
 
 		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
-					<960000 965000 975000>, /* Supply 1 */
-					<960000 965000 975000>; /* Supply 2 */
+			opp-microvolt = <975000 970000 985000>, /* Supply 0 */
+					<965000 960000 975000>, /* Supply 1 */
+					<965000 960000 975000>; /* Supply 2 */
 			opp-microamp =  <70000>,		/* Supply 0 */
 					<70000>,		/* Supply 1 */
 					<70000>;		/* Supply 2 */
@@ -437,9 +437,9 @@ Example 4: Handling multiple regulators
 
 		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
-					<960000 965000 975000>, /* Supply 1 */
-					<960000 965000 975000>; /* Supply 2 */
+			opp-microvolt = <975000 970000 985000>, /* Supply 0 */
+					<965000 960000 975000>, /* Supply 1 */
+					<965000 960000 975000>; /* Supply 2 */
 			opp-microamp =  <70000>,		/* Supply 0 */
 					<0>,			/* Supply 1 doesn't need this */
 					<70000>;		/* Supply 2 */
@@ -474,7 +474,7 @@ Example 5: opp-supported-hw
 			 */
 			opp-supported-hw = <0xF 0xFFFFFFFF 0xFFFFFFFF>
 			opp-hz = /bits/ 64 <600000000>;
-			opp-microvolt = <900000 915000 925000>;
+			opp-microvolt = <915000 900000 925000>;
 			...
 		};
 
@@ -487,7 +487,7 @@ Example 5: opp-supported-hw
 			 */
 			opp-supported-hw = <0x20 0xff0000ff 0x0000f4f0>
 			opp-hz = /bits/ 64 <800000000>;
-			opp-microvolt = <900000 915000 925000>;
+			opp-microvolt = <915000 900000 925000>;
 			...
 		};
 	};
@@ -512,18 +512,18 @@ Example 6: opp-microvolt-<name>, opp-microamp-<name>:
 
 		opp@1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt-slow = <900000 915000 925000>;
-			opp-microvolt-fast = <970000 975000 985000>;
+			opp-microvolt-slow = <915000 900000 925000>;
+			opp-microvolt-fast = <975000 970000 985000>;
 			opp-microamp-slow =  <70000>;
 			opp-microamp-fast =  <71000>;
 		};
 
 		opp@1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
-			opp-microvolt-slow = <900000 915000 925000>, /* Supply vcc0 */
-					      <910000 925000 935000>; /* Supply vcc1 */
-			opp-microvolt-fast = <970000 975000 985000>, /* Supply vcc0 */
-					     <960000 965000 975000>; /* Supply vcc1 */
+			opp-microvolt-slow = <915000 900000 925000>, /* Supply vcc0 */
+					      <925000 910000 935000>; /* Supply vcc1 */
+			opp-microvolt-fast = <975000 970000 985000>, /* Supply vcc0 */
+					     <965000 960000 975000>; /* Supply vcc1 */
 			opp-microamp =  <70000>; /* Will be used for both slow/fast */
 		};
 	};
-- 
GitLab


From 61cfac6f267dabcf2740a7ec8a0295833b28b5f5 Mon Sep 17 00:00:00 2001
From: Pavel Shilovsky <pshilov@microsoft.com>
Date: Tue, 28 Feb 2017 16:05:19 -0800
Subject: [PATCH 446/898] CIFS: Fix possible use after free in demultiplex
 thread

The recent changes that added SMB3 encryption support introduced
a possible use after free in the demultiplex thread. When we
process an encrypted packed we obtain a pointer to SMB session
but do not obtain a reference. This can possibly lead to a situation
when this session was freed before we copy a decryption key from
there. Fix this by obtaining a copy of the key rather than a pointer
to the session under a spinlock.

Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/smb2ops.c | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index a44b4dbe4aae..d2cdd9c19d17 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1609,6 +1609,26 @@ static void cifs_crypt_complete(struct crypto_async_request *req, int err)
 	complete(&res->completion);
 }
 
+static int
+smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
+{
+	struct cifs_ses *ses;
+	u8 *ses_enc_key;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+		if (ses->Suid != ses_id)
+			continue;
+		ses_enc_key = enc ? ses->smb3encryptionkey :
+							ses->smb3decryptionkey;
+		memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+		spin_unlock(&cifs_tcp_ses_lock);
+		return 0;
+	}
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	return 1;
+}
 /*
  * Encrypt or decrypt @rqst message. @rqst has the following format:
  * iov[0] - transform header (associate data),
@@ -1622,10 +1642,10 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 	struct smb2_transform_hdr *tr_hdr =
 			(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
 	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
-	struct cifs_ses *ses;
 	int rc = 0;
 	struct scatterlist *sg;
 	u8 sign[SMB2_SIGNATURE_SIZE] = {};
+	u8 key[SMB3_SIGN_KEY_SIZE];
 	struct aead_request *req;
 	char *iv;
 	unsigned int iv_len;
@@ -1635,9 +1655,10 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 
 	init_completion(&result.completion);
 
-	ses = smb2_find_smb_ses(server, tr_hdr->SessionId);
-	if (!ses) {
-		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
+	rc = smb2_get_enc_key(server, tr_hdr->SessionId, enc, key);
+	if (rc) {
+		cifs_dbg(VFS, "%s: Could not get %scryption key\n", __func__,
+			 enc ? "en" : "de");
 		return 0;
 	}
 
@@ -1649,8 +1670,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 
 	tfm = enc ? server->secmech.ccmaesencrypt :
 						server->secmech.ccmaesdecrypt;
-	rc = crypto_aead_setkey(tfm, enc ? ses->smb3encryptionkey :
-				ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
+	rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
 		return rc;
-- 
GitLab


From df2c43343b47a7138431f431118eb5819e205365 Mon Sep 17 00:00:00 2001
From: Yotam Gigi <yotamg@mellanox.com>
Date: Wed, 1 Mar 2017 16:50:45 +0200
Subject: [PATCH 447/898] bridge: Fix error path in nbp_vlan_init

Fix error path order in nbp_vlan_init, so if switchdev_port_attr_set
call failes, the vlan_hash wouldn't be destroyed before inited.

Fixes: efa5356b0d97 ("bridge: per vlan dst_metadata netlink support")
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 62e68c0dc687..b838213c408e 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -997,10 +997,10 @@ int nbp_vlan_init(struct net_bridge_port *p)
 	RCU_INIT_POINTER(p->vlgrp, NULL);
 	synchronize_rcu();
 	vlan_tunnel_deinit(vg);
-err_vlan_enabled:
 err_tunnel_init:
 	rhashtable_destroy(&vg->vlan_hash);
 err_rhtbl:
+err_vlan_enabled:
 	kfree(vg);
 
 	goto out;
-- 
GitLab


From eba38a968258b5ad9d70722ab8c584e1753f4b16 Mon Sep 17 00:00:00 2001
From: Gary Lin <glin@suse.com>
Date: Wed, 1 Mar 2017 16:25:51 +0800
Subject: [PATCH 448/898] bpf: update the comment about the length of analysis

Commit 07016151a446 ("bpf, verifier: further improve search
pruning") increased the limit of processed instructions from
32k to 64k, but the comment still mentioned the 32k limit.
This commit updates the comment to reflect the change.

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Gary Lin <glin@suse.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3fc6e39b223e..796b68d00119 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -33,7 +33,7 @@
  * - out of bounds or malformed jumps
  * The second pass is all possible path descent from the 1st insn.
  * Since it's analyzing all pathes through the program, the length of the
- * analysis is limited to 32k insn, which may be hit even if total number of
+ * analysis is limited to 64k insn, which may be hit even if total number of
  * insn is less then 4K, but there are too many branches that change stack/regs.
  * Number of 'branches to be analyzed' is limited to 1k
  *
-- 
GitLab


From 449809a66c1d0b1563dee84493e14bf3104d2d7e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 08:39:49 -0800
Subject: [PATCH 449/898] tcp/dccp: block BH for SYN processing

SYN processing really was meant to be handled from BH.

When I got rid of BH blocking while processing socket backlog
in commit 5413d1babe8f ("net: do not block BH while processing socket
backlog"), I forgot that a malicious user could transition to TCP_LISTEN
from a state that allowed (SYN) packets to be parked in the socket
backlog while socket is owned by the thread doing the listen() call.

Sure enough syzkaller found this and reported the bug ;)

=================================
[ INFO: inconsistent lock state ]
4.10.0+ #60 Not tainted
---------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
syz-executor0/5090 [HC0[0]:SC0[0]:HE1:SE1] takes:
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] spin_lock include/linux/spinlock.h:299 [inline]
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] inet_ehash_insert+0x240/0xad0
net/ipv4/inet_hashtables.c:407
{IN-SOFTIRQ-W} state was registered at:
  mark_irqflags kernel/locking/lockdep.c:2923 [inline]
  __lock_acquire+0xbcf/0x3270 kernel/locking/lockdep.c:3295
  lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
  __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
  _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
  spin_lock include/linux/spinlock.h:299 [inline]
  inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
  reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
  inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
  tcp_conn_request+0x25cc/0x3310 net/ipv4/tcp_input.c:6399
  tcp_v4_conn_request+0x157/0x220 net/ipv4/tcp_ipv4.c:1262
  tcp_rcv_state_process+0x802/0x4130 net/ipv4/tcp_input.c:5889
  tcp_v4_do_rcv+0x56b/0x940 net/ipv4/tcp_ipv4.c:1433
  tcp_v4_rcv+0x2e12/0x3210 net/ipv4/tcp_ipv4.c:1711
  ip_local_deliver_finish+0x4ce/0xc40 net/ipv4/ip_input.c:216
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_local_deliver+0x1ce/0x710 net/ipv4/ip_input.c:257
  dst_input include/net/dst.h:492 [inline]
  ip_rcv_finish+0xb1d/0x2110 net/ipv4/ip_input.c:396
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_rcv+0xd90/0x19c0 net/ipv4/ip_input.c:487
  __netif_receive_skb_core+0x1ad1/0x3400 net/core/dev.c:4179
  __netif_receive_skb+0x2a/0x170 net/core/dev.c:4217
  netif_receive_skb_internal+0x1d6/0x430 net/core/dev.c:4245
  napi_skb_finish net/core/dev.c:4602 [inline]
  napi_gro_receive+0x4e6/0x680 net/core/dev.c:4636
  e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4033 [inline]
  e1000_clean_rx_irq+0x5e0/0x1490
drivers/net/ethernet/intel/e1000/e1000_main.c:4489
  e1000_clean+0xb9a/0x2910 drivers/net/ethernet/intel/e1000/e1000_main.c:3834
  napi_poll net/core/dev.c:5171 [inline]
  net_rx_action+0xe70/0x1900 net/core/dev.c:5236
  __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
  invoke_softirq kernel/softirq.c:364 [inline]
  irq_exit+0x19e/0x1d0 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:658 [inline]
  do_IRQ+0x81/0x1a0 arch/x86/kernel/irq.c:250
  ret_from_intr+0x0/0x20
  native_safe_halt+0x6/0x10 arch/x86/include/asm/irqflags.h:53
  arch_safe_halt arch/x86/include/asm/paravirt.h:98 [inline]
  default_idle+0x8f/0x410 arch/x86/kernel/process.c:271
  arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:262
  default_idle_call+0x36/0x60 kernel/sched/idle.c:96
  cpuidle_idle_call kernel/sched/idle.c:154 [inline]
  do_idle+0x348/0x440 kernel/sched/idle.c:243
  cpu_startup_entry+0x18/0x20 kernel/sched/idle.c:345
  start_secondary+0x344/0x440 arch/x86/kernel/smpboot.c:272
  verify_cpu+0x0/0xfc
irq event stamp: 1741
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160
[inline]
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
_raw_spin_unlock_irqrestore+0xf7/0x1a0 kernel/locking/spinlock.c:191
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
_raw_spin_lock_irqsave+0xa2/0x110 kernel/locking/spinlock.c:159
softirqs last  enabled at (1738): [<ffffffff84d4deff>]
__do_softirq+0x7cf/0xb7d kernel/softirq.c:310
softirqs last disabled at (1571): [<ffffffff84d4b92c>]
do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&(&hashinfo->ehash_locks[i])->rlock);
  <Interrupt>
    lock(&(&hashinfo->ehash_locks[i])->rlock);

 *** DEADLOCK ***

1 lock held by syz-executor0/5090:
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>] lock_sock
include/net/sock.h:1460 [inline]
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>]
sock_setsockopt+0x233/0x1e40 net/core/sock.c:683

stack backtrace:
CPU: 1 PID: 5090 Comm: syz-executor0 Not tainted 4.10.0+ #60
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 print_usage_bug+0x3ef/0x450 kernel/locking/lockdep.c:2387
 valid_state kernel/locking/lockdep.c:2400 [inline]
 mark_lock_irq kernel/locking/lockdep.c:2602 [inline]
 mark_lock+0xf30/0x1410 kernel/locking/lockdep.c:3065
 mark_irqflags kernel/locking/lockdep.c:2941 [inline]
 __lock_acquire+0x6dc/0x3270 kernel/locking/lockdep.c:3295
 lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:299 [inline]
 inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
 inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
 dccp_v6_conn_request+0xada/0x11b0 net/dccp/ipv6.c:380
 dccp_rcv_state_process+0x51e/0x1660 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:896 [inline]
 __release_sock+0x127/0x3a0 net/core/sock.c:2052
 release_sock+0xa5/0x2b0 net/core/sock.c:2539
 sock_setsockopt+0x60f/0x1e40 net/core/sock.c:1016
 SYSC_setsockopt net/socket.c:1782 [inline]
 SyS_setsockopt+0x2fb/0x3a0 net/socket.c:1765
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007fe8b26c2b58 EFLAGS: 00000292 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 00000000004458b9
RDX: 000000000000001a RSI: 0000000000000001 RDI: 0000000000000006
RBP: 00000000006e2110 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000208c3000 R11: 0000000000000292 R12: 0000000000708000
R13: 0000000020000000 R14: 0000000000001000 R15: 0000000000000000

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/input.c     | 10 ++++++++--
 net/ipv4/tcp_input.c | 10 ++++++++--
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/net/dccp/input.c b/net/dccp/input.c
index 8fedc2d49770..4a05d7876850 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -577,6 +577,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
 	const int old_state = sk->sk_state;
+	bool acceptable;
 	int queued = 0;
 
 	/*
@@ -603,8 +604,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	 */
 	if (sk->sk_state == DCCP_LISTEN) {
 		if (dh->dccph_type == DCCP_PKT_REQUEST) {
-			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
-								    skb) < 0)
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
+			if (!acceptable)
 				return 1;
 			consume_skb(skb);
 			return 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2c0ff327b6df..39c393cc0fd3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5886,9 +5886,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (th->syn) {
 			if (th->fin)
 				goto discard;
-			if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
-				return 1;
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
 
+			if (!acceptable)
+				return 1;
 			consume_skb(skb);
 			return 0;
 		}
-- 
GitLab


From 0837e49ab3fa8d903a499984575d71efee8097ce Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 1 Mar 2017 15:11:23 +0000
Subject: [PATCH 450/898] KEYS: Differentiate uses of rcu_dereference_key() and
 user_key_payload()

rcu_dereference_key() and user_key_payload() are currently being used in
two different, incompatible ways:

 (1) As a wrapper to rcu_dereference() - when only the RCU read lock used
     to protect the key.

 (2) As a wrapper to rcu_dereference_protected() - when the key semaphor is
     used to protect the key and the may be being modified.

Fix this by splitting both of the key wrappers to produce:

 (1) RCU accessors for keys when caller has the key semaphore locked:

	dereference_key_locked()
	user_key_payload_locked()

 (2) RCU accessors for keys when caller holds the RCU read lock:

	dereference_key_rcu()
	user_key_payload_rcu()

This should fix following warning in the NFS idmapper

  ===============================
  [ INFO: suspicious RCU usage. ]
  4.10.0 #1 Tainted: G        W
  -------------------------------
  ./include/keys/user-type.h:53 suspicious rcu_dereference_protected() usage!
  other info that might help us debug this:
  rcu_scheduler_active = 2, debug_locks = 0
  1 lock held by mount.nfs/5987:
    #0:  (rcu_read_lock){......}, at: [<d000000002527abc>] nfs_idmap_get_key+0x15c/0x420 [nfsv4]
  stack backtrace:
  CPU: 1 PID: 5987 Comm: mount.nfs Tainted: G        W       4.10.0 #1
  Call Trace:
    dump_stack+0xe8/0x154 (unreliable)
    lockdep_rcu_suspicious+0x140/0x190
    nfs_idmap_get_key+0x380/0x420 [nfsv4]
    nfs_map_name_to_uid+0x2a0/0x3b0 [nfsv4]
    decode_getfattr_attrs+0xfac/0x16b0 [nfsv4]
    decode_getfattr_generic.constprop.106+0xbc/0x150 [nfsv4]
    nfs4_xdr_dec_lookup_root+0xac/0xb0 [nfsv4]
    rpcauth_unwrap_resp+0xe8/0x140 [sunrpc]
    call_decode+0x29c/0x910 [sunrpc]
    __rpc_execute+0x140/0x8f0 [sunrpc]
    rpc_run_task+0x170/0x200 [sunrpc]
    nfs4_call_sync_sequence+0x68/0xa0 [nfsv4]
    _nfs4_lookup_root.isra.44+0xd0/0xf0 [nfsv4]
    nfs4_lookup_root+0xe0/0x350 [nfsv4]
    nfs4_lookup_root_sec+0x70/0xa0 [nfsv4]
    nfs4_find_root_sec+0xc4/0x100 [nfsv4]
    nfs4_proc_get_rootfh+0x5c/0xf0 [nfsv4]
    nfs4_get_rootfh+0x6c/0x190 [nfsv4]
    nfs4_server_common_setup+0xc4/0x260 [nfsv4]
    nfs4_create_server+0x278/0x3c0 [nfsv4]
    nfs4_remote_mount+0x50/0xb0 [nfsv4]
    mount_fs+0x74/0x210
    vfs_kern_mount+0x78/0x220
    nfs_do_root_mount+0xb0/0x140 [nfsv4]
    nfs4_try_mount+0x60/0x100 [nfsv4]
    nfs_fs_mount+0x5ec/0xda0 [nfs]
    mount_fs+0x74/0x210
    vfs_kern_mount+0x78/0x220
    do_mount+0x254/0xf70
    SyS_mount+0x94/0x100
    system_call+0x38/0xe0

Reported-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
---
 Documentation/security/keys.txt          | 17 +++++++++++++++--
 drivers/md/dm-crypt.c                    |  2 +-
 fs/cifs/connect.c                        |  2 +-
 fs/crypto/keyinfo.c                      |  2 +-
 fs/ecryptfs/ecryptfs_kernel.h            |  2 +-
 fs/fscache/object-list.c                 |  2 +-
 fs/nfs/nfs4idmap.c                       |  2 +-
 include/keys/user-type.h                 |  9 +++++++--
 include/linux/key.h                      |  5 ++++-
 lib/digsig.c                             |  2 +-
 net/dns_resolver/dns_query.c             |  4 ++--
 security/keys/dh.c                       |  2 +-
 security/keys/encrypted-keys/encrypted.c |  4 ++--
 security/keys/trusted.c                  |  4 ++--
 security/keys/user_defined.c             |  6 +++---
 15 files changed, 43 insertions(+), 22 deletions(-)

diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 3849814bfe6d..0e03baf271bd 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -1151,8 +1151,21 @@ access the data:
      usage.  This is called key->payload.rcu_data0.  The following accessors
      wrap the RCU calls to this element:
 
-	rcu_assign_keypointer(struct key *key, void *data);
-	void *rcu_dereference_key(struct key *key);
+     (a) Set or change the first payload pointer:
+
+		rcu_assign_keypointer(struct key *key, void *data);
+
+     (b) Read the first payload pointer with the key semaphore held:
+
+		[const] void *dereference_key_locked([const] struct key *key);
+
+	 Note that the return value will inherit its constness from the key
+	 parameter.  Static analysis will give an error if it things the lock
+	 isn't held.
+
+     (c) Read the first payload pointer with the RCU read lock held:
+
+		const void *dereference_key_rcu(const struct key *key);
 
 
 ===================
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 1cb2ca9dfae3..389a3637ffcc 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1536,7 +1536,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	down_read(&key->sem);
 
-	ukp = user_key_payload(key);
+	ukp = user_key_payload_locked(key);
 	if (!ukp) {
 		up_read(&key->sem);
 		key_put(key);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 777ad9f4fc3c..8a3ecef30d3c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2455,7 +2455,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses)
 	}
 
 	down_read(&key->sem);
-	upayload = user_key_payload(key);
+	upayload = user_key_payload_locked(key);
 	if (IS_ERR_OR_NULL(upayload)) {
 		rc = upayload ? PTR_ERR(upayload) : -EINVAL;
 		goto out_key_put;
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 02eb6b9e4438..d5d896fa5a71 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -103,7 +103,7 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
 		goto out;
 	}
 	down_read(&keyring_key->sem);
-	ukp = user_key_payload(keyring_key);
+	ukp = user_key_payload_locked(keyring_key);
 	if (ukp->datalen != sizeof(struct fscrypt_key)) {
 		res = -EINVAL;
 		up_read(&keyring_key->sem);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 599a29237cfe..95c1c8d34539 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -117,7 +117,7 @@ ecryptfs_get_key_payload_data(struct key *key)
 
 	auth_tok = ecryptfs_get_encrypted_key_payload_data(key);
 	if (!auth_tok)
-		return (struct ecryptfs_auth_tok *)user_key_payload(key)->data;
+		return (struct ecryptfs_auth_tok *)user_key_payload_locked(key)->data;
 	else
 		return auth_tok;
 }
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index 5d5ddaa84b21..67f940892ef8 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -329,7 +329,7 @@ static void fscache_objlist_config(struct fscache_objlist_data *data)
 	config = 0;
 	rcu_read_lock();
 
-	confkey = user_key_payload(key);
+	confkey = user_key_payload_rcu(key);
 	buf = confkey->data;
 
 	for (len = confkey->datalen - 1; len >= 0; len--) {
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index c444285bb1b1..835c163f61af 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -316,7 +316,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
 	if (ret < 0)
 		goto out_up;
 
-	payload = user_key_payload(rkey);
+	payload = user_key_payload_rcu(rkey);
 	if (IS_ERR_OR_NULL(payload)) {
 		ret = PTR_ERR(payload);
 		goto out_up;
diff --git a/include/keys/user-type.h b/include/keys/user-type.h
index c56fef40f53e..e098cbe27db5 100644
--- a/include/keys/user-type.h
+++ b/include/keys/user-type.h
@@ -48,9 +48,14 @@ extern void user_describe(const struct key *user, struct seq_file *m);
 extern long user_read(const struct key *key,
 		      char __user *buffer, size_t buflen);
 
-static inline const struct user_key_payload *user_key_payload(const struct key *key)
+static inline const struct user_key_payload *user_key_payload_rcu(const struct key *key)
 {
-	return (struct user_key_payload *)rcu_dereference_key(key);
+	return (struct user_key_payload *)dereference_key_rcu(key);
+}
+
+static inline struct user_key_payload *user_key_payload_locked(const struct key *key)
+{
+	return (struct user_key_payload *)dereference_key_locked((struct key *)key);
 }
 
 #endif /* CONFIG_KEYS */
diff --git a/include/linux/key.h b/include/linux/key.h
index 722914798f37..e45212f2777e 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -354,7 +354,10 @@ static inline bool key_is_instantiated(const struct key *key)
 		!test_bit(KEY_FLAG_NEGATIVE, &key->flags);
 }
 
-#define rcu_dereference_key(KEY)					\
+#define dereference_key_rcu(KEY)					\
+	(rcu_dereference((KEY)->payload.rcu_data0))
+
+#define dereference_key_locked(KEY)					\
 	(rcu_dereference_protected((KEY)->payload.rcu_data0,		\
 				   rwsem_is_locked(&((struct key *)(KEY))->sem)))
 
diff --git a/lib/digsig.c b/lib/digsig.c
index 55b8b2f41a9e..03d7c63837ae 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -85,7 +85,7 @@ static int digsig_verify_rsa(struct key *key,
 	struct pubkey_hdr *pkh;
 
 	down_read(&key->sem);
-	ukp = user_key_payload(key);
+	ukp = user_key_payload_locked(key);
 
 	if (ukp->datalen < sizeof(*pkh))
 		goto err1;
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index ecc28cff08ab..d502c94b1a82 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -70,7 +70,7 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	      const char *options, char **_result, time64_t *_expiry)
 {
 	struct key *rkey;
-	const struct user_key_payload *upayload;
+	struct user_key_payload *upayload;
 	const struct cred *saved_cred;
 	size_t typelen, desclen;
 	char *desc, *cp;
@@ -141,7 +141,7 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	if (ret)
 		goto put;
 
-	upayload = user_key_payload(rkey);
+	upayload = user_key_payload_locked(rkey);
 	len = upayload->datalen;
 
 	ret = -ENOMEM;
diff --git a/security/keys/dh.c b/security/keys/dh.c
index 531ed2ec132f..893af4c45038 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -55,7 +55,7 @@ static ssize_t mpi_from_key(key_serial_t keyid, size_t maxlen, MPI *mpi)
 		if (status == 0) {
 			const struct user_key_payload *payload;
 
-			payload = user_key_payload(key);
+			payload = user_key_payload_locked(key);
 
 			if (maxlen == 0) {
 				*mpi = NULL;
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 4fb315cddf5b..0010955d7876 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -314,7 +314,7 @@ static struct key *request_user_key(const char *master_desc, const u8 **master_k
 		goto error;
 
 	down_read(&ukey->sem);
-	upayload = user_key_payload(ukey);
+	upayload = user_key_payload_locked(ukey);
 	*master_key = upayload->data;
 	*master_keylen = upayload->datalen;
 error:
@@ -926,7 +926,7 @@ static long encrypted_read(const struct key *key, char __user *buffer,
 	size_t asciiblob_len;
 	int ret;
 
-	epayload = rcu_dereference_key(key);
+	epayload = dereference_key_locked(key);
 
 	/* returns the hex encoded iv, encrypted-data, and hmac as ascii */
 	asciiblob_len = epayload->datablob_len + ivsize + 1
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 90d61751ff12..2ae31c5a87de 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1140,12 +1140,12 @@ static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
 static long trusted_read(const struct key *key, char __user *buffer,
 			 size_t buflen)
 {
-	struct trusted_key_payload *p;
+	const struct trusted_key_payload *p;
 	char *ascii_buf;
 	char *bufp;
 	int i;
 
-	p = rcu_dereference_key(key);
+	p = dereference_key_locked(key);
 	if (!p)
 		return -EINVAL;
 	if (!buffer || buflen <= 0)
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index e187c8909d9d..26605134f17a 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -107,7 +107,7 @@ int user_update(struct key *key, struct key_preparsed_payload *prep)
 	/* attach the new data, displacing the old */
 	key->expiry = prep->expiry;
 	if (!test_bit(KEY_FLAG_NEGATIVE, &key->flags))
-		zap = rcu_dereference_key(key);
+		zap = dereference_key_locked(key);
 	rcu_assign_keypointer(key, prep->payload.data[0]);
 	prep->payload.data[0] = NULL;
 
@@ -123,7 +123,7 @@ EXPORT_SYMBOL_GPL(user_update);
  */
 void user_revoke(struct key *key)
 {
-	struct user_key_payload *upayload = key->payload.data[0];
+	struct user_key_payload *upayload = user_key_payload_locked(key);
 
 	/* clear the quota */
 	key_payload_reserve(key, 0);
@@ -169,7 +169,7 @@ long user_read(const struct key *key, char __user *buffer, size_t buflen)
 	const struct user_key_payload *upayload;
 	long ret;
 
-	upayload = user_key_payload(key);
+	upayload = user_key_payload_locked(key);
 	ret = upayload->datalen;
 
 	/* we can return the data as is */
-- 
GitLab


From 2651225b5ebcdde60f684c4db8ec7e9e3800a74f Mon Sep 17 00:00:00 2001
From: Stephen Smalley <sds@tycho.nsa.gov>
Date: Tue, 28 Feb 2017 10:35:56 -0500
Subject: [PATCH 451/898] selinux: wrap cgroup seclabel support with its own
 policy capability

commit 1ea0ce40690dff38935538e8dab7b12683ded0d3 ("selinux: allow
changing labels for cgroupfs") broke the Android init program,
which looks up security contexts whenever creating directories
and attempts to assign them via setfscreatecon().
When creating subdirectories in cgroup mounts, this would previously
be ignored since cgroup did not support userspace setting of security
contexts.  However, after the commit, SELinux would attempt to honor
the requested context on cgroup directories and fail due to permission
denial.  Avoid breaking existing userspace/policy by wrapping this change
with a conditional on a new cgroup_seclabel policy capability.  This
preserves existing behavior until/unless a new policy explicitly enables
this capability.

Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
---
 security/selinux/hooks.c            | 7 ++++---
 security/selinux/include/security.h | 2 ++
 security/selinux/selinuxfs.c        | 3 ++-
 security/selinux/ss/services.c      | 4 ++++
 4 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 9a8f12f8d5b7..0a4b4b040e0a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -480,12 +480,13 @@ static int selinux_is_sblabel_mnt(struct super_block *sb)
 		sbsec->behavior == SECURITY_FS_USE_NATIVE ||
 		/* Special handling. Genfs but also in-core setxattr handler */
 		!strcmp(sb->s_type->name, "sysfs") ||
-		!strcmp(sb->s_type->name, "cgroup") ||
-		!strcmp(sb->s_type->name, "cgroup2") ||
 		!strcmp(sb->s_type->name, "pstore") ||
 		!strcmp(sb->s_type->name, "debugfs") ||
 		!strcmp(sb->s_type->name, "tracefs") ||
-		!strcmp(sb->s_type->name, "rootfs");
+		!strcmp(sb->s_type->name, "rootfs") ||
+		(selinux_policycap_cgroupseclabel &&
+		 (!strcmp(sb->s_type->name, "cgroup") ||
+		  !strcmp(sb->s_type->name, "cgroup2")));
 }
 
 static int sb_finish_set_opts(struct super_block *sb)
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index beaa14b8b6cf..f979c35e037e 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -71,6 +71,7 @@ enum {
 	POLICYDB_CAPABILITY_OPENPERM,
 	POLICYDB_CAPABILITY_EXTSOCKCLASS,
 	POLICYDB_CAPABILITY_ALWAYSNETWORK,
+	POLICYDB_CAPABILITY_CGROUPSECLABEL,
 	__POLICYDB_CAPABILITY_MAX
 };
 #define POLICYDB_CAPABILITY_MAX (__POLICYDB_CAPABILITY_MAX - 1)
@@ -79,6 +80,7 @@ extern int selinux_policycap_netpeer;
 extern int selinux_policycap_openperm;
 extern int selinux_policycap_extsockclass;
 extern int selinux_policycap_alwaysnetwork;
+extern int selinux_policycap_cgroupseclabel;
 
 /*
  * type_datum properties
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index c9e8a9898ce4..cb3fd98fb05a 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -46,7 +46,8 @@ static char *policycap_names[] = {
 	"network_peer_controls",
 	"open_perms",
 	"extended_socket_class",
-	"always_check_network"
+	"always_check_network",
+	"cgroup_seclabel"
 };
 
 unsigned int selinux_checkreqprot = CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE;
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index a70fcee9824b..b4aa491a0a23 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -74,6 +74,7 @@ int selinux_policycap_netpeer;
 int selinux_policycap_openperm;
 int selinux_policycap_extsockclass;
 int selinux_policycap_alwaysnetwork;
+int selinux_policycap_cgroupseclabel;
 
 static DEFINE_RWLOCK(policy_rwlock);
 
@@ -1993,6 +1994,9 @@ static void security_load_policycaps(void)
 					  POLICYDB_CAPABILITY_EXTSOCKCLASS);
 	selinux_policycap_alwaysnetwork = ebitmap_get_bit(&policydb.policycaps,
 						  POLICYDB_CAPABILITY_ALWAYSNETWORK);
+	selinux_policycap_cgroupseclabel =
+		ebitmap_get_bit(&policydb.policycaps,
+				POLICYDB_CAPABILITY_CGROUPSECLABEL);
 }
 
 static int security_preserve_bools(struct policydb *p);
-- 
GitLab


From f889491380582b4ba2981cf0b0d7d6a40fb30ab7 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 28 Feb 2017 17:56:02 +0800
Subject: [PATCH 452/898] vhost: introduce O(1) vq metadata cache

When device IOTLB is enabled, all address translations were stored in
interval tree. O(lgN) searching time could be slow for virtqueue
metadata (avail, used and descriptors) since they were accessed much
often than other addresses. So this patch introduces an O(1) array
which points to the interval tree nodes that store the translations of
vq metadata. Those array were update during vq IOTLB prefetching and
were reset during each invalidation and tlb update. Each time we want
to access vq metadata, this small array were queried before interval
tree. This would be sufficient for static mappings but not dynamic
mappings, we could do optimizations on top.

Test were done with l2fwd in guest (2M hugepage):

   noiommu  | before        | after
tx 1.32Mpps | 1.06Mpps(82%) | 1.30Mpps(98%)
rx 2.33Mpps | 1.46Mpps(63%) | 2.29Mpps(98%)

We can almost reach the same performance as noiommu mode.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 136 ++++++++++++++++++++++++++++++++++--------
 drivers/vhost/vhost.h |   8 +++
 2 files changed, 118 insertions(+), 26 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 1f7e4e4e6f8e..998bed505530 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -282,6 +282,22 @@ void vhost_poll_queue(struct vhost_poll *poll)
 }
 EXPORT_SYMBOL_GPL(vhost_poll_queue);
 
+static void __vhost_vq_meta_reset(struct vhost_virtqueue *vq)
+{
+	int j;
+
+	for (j = 0; j < VHOST_NUM_ADDRS; j++)
+		vq->meta_iotlb[j] = NULL;
+}
+
+static void vhost_vq_meta_reset(struct vhost_dev *d)
+{
+	int i;
+
+	for (i = 0; i < d->nvqs; ++i)
+		__vhost_vq_meta_reset(d->vqs[i]);
+}
+
 static void vhost_vq_reset(struct vhost_dev *dev,
 			   struct vhost_virtqueue *vq)
 {
@@ -312,6 +328,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->busyloop_timeout = 0;
 	vq->umem = NULL;
 	vq->iotlb = NULL;
+	__vhost_vq_meta_reset(vq);
 }
 
 static int vhost_worker(void *data)
@@ -691,6 +708,18 @@ static int vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem,
 	return 1;
 }
 
+static inline void __user *vhost_vq_meta_fetch(struct vhost_virtqueue *vq,
+					       u64 addr, unsigned int size,
+					       int type)
+{
+	const struct vhost_umem_node *node = vq->meta_iotlb[type];
+
+	if (!node)
+		return NULL;
+
+	return (void *)(uintptr_t)(node->userspace_addr + addr - node->start);
+}
+
 /* Can we switch to this memory table? */
 /* Caller should have device mutex but not vq mutex */
 static int memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem,
@@ -733,8 +762,14 @@ static int vhost_copy_to_user(struct vhost_virtqueue *vq, void __user *to,
 		 * could be access through iotlb. So -EAGAIN should
 		 * not happen in this case.
 		 */
-		/* TODO: more fast path */
 		struct iov_iter t;
+		void __user *uaddr = vhost_vq_meta_fetch(vq,
+				     (u64)(uintptr_t)to, size,
+				     VHOST_ADDR_DESC);
+
+		if (uaddr)
+			return __copy_to_user(uaddr, from, size);
+
 		ret = translate_desc(vq, (u64)(uintptr_t)to, size, vq->iotlb_iov,
 				     ARRAY_SIZE(vq->iotlb_iov),
 				     VHOST_ACCESS_WO);
@@ -762,8 +797,14 @@ static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to,
 		 * could be access through iotlb. So -EAGAIN should
 		 * not happen in this case.
 		 */
-		/* TODO: more fast path */
+		void __user *uaddr = vhost_vq_meta_fetch(vq,
+				     (u64)(uintptr_t)from, size,
+				     VHOST_ADDR_DESC);
 		struct iov_iter f;
+
+		if (uaddr)
+			return __copy_from_user(to, uaddr, size);
+
 		ret = translate_desc(vq, (u64)(uintptr_t)from, size, vq->iotlb_iov,
 				     ARRAY_SIZE(vq->iotlb_iov),
 				     VHOST_ACCESS_RO);
@@ -783,17 +824,12 @@ static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to,
 	return ret;
 }
 
-static void __user *__vhost_get_user(struct vhost_virtqueue *vq,
-				     void __user *addr, unsigned size)
+static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq,
+					  void __user *addr, unsigned int size,
+					  int type)
 {
 	int ret;
 
-	/* This function should be called after iotlb
-	 * prefetch, which means we're sure that vq
-	 * could be access through iotlb. So -EAGAIN should
-	 * not happen in this case.
-	 */
-	/* TODO: more fast path */
 	ret = translate_desc(vq, (u64)(uintptr_t)addr, size, vq->iotlb_iov,
 			     ARRAY_SIZE(vq->iotlb_iov),
 			     VHOST_ACCESS_RO);
@@ -814,14 +850,32 @@ static void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 	return vq->iotlb_iov[0].iov_base;
 }
 
-#define vhost_put_user(vq, x, ptr) \
+/* This function should be called after iotlb
+ * prefetch, which means we're sure that vq
+ * could be access through iotlb. So -EAGAIN should
+ * not happen in this case.
+ */
+static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
+					    void *addr, unsigned int size,
+					    int type)
+{
+	void __user *uaddr = vhost_vq_meta_fetch(vq,
+			     (u64)(uintptr_t)addr, size, type);
+	if (uaddr)
+		return uaddr;
+
+	return __vhost_get_user_slow(vq, addr, size, type);
+}
+
+#define vhost_put_user(vq, x, ptr)		\
 ({ \
 	int ret = -EFAULT; \
 	if (!vq->iotlb) { \
 		ret = __put_user(x, ptr); \
 	} else { \
 		__typeof__(ptr) to = \
-			(__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \
+			(__typeof__(ptr)) __vhost_get_user(vq, ptr,	\
+					  sizeof(*ptr), VHOST_ADDR_USED); \
 		if (to != NULL) \
 			ret = __put_user(x, to); \
 		else \
@@ -830,14 +884,16 @@ static void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 	ret; \
 })
 
-#define vhost_get_user(vq, x, ptr) \
+#define vhost_get_user(vq, x, ptr, type)		\
 ({ \
 	int ret; \
 	if (!vq->iotlb) { \
 		ret = __get_user(x, ptr); \
 	} else { \
 		__typeof__(ptr) from = \
-			(__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \
+			(__typeof__(ptr)) __vhost_get_user(vq, ptr, \
+							   sizeof(*ptr), \
+							   type); \
 		if (from != NULL) \
 			ret = __get_user(x, from); \
 		else \
@@ -846,6 +902,12 @@ static void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 	ret; \
 })
 
+#define vhost_get_avail(vq, x, ptr) \
+	vhost_get_user(vq, x, ptr, VHOST_ADDR_AVAIL)
+
+#define vhost_get_used(vq, x, ptr) \
+	vhost_get_user(vq, x, ptr, VHOST_ADDR_USED)
+
 static void vhost_dev_lock_vqs(struct vhost_dev *d)
 {
 	int i = 0;
@@ -951,6 +1013,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 			ret = -EFAULT;
 			break;
 		}
+		vhost_vq_meta_reset(dev);
 		if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size,
 					 msg->iova + msg->size - 1,
 					 msg->uaddr, msg->perm)) {
@@ -960,6 +1023,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 		vhost_iotlb_notify_vq(dev, msg);
 		break;
 	case VHOST_IOTLB_INVALIDATE:
+		vhost_vq_meta_reset(dev);
 		vhost_del_umem_range(dev->iotlb, msg->iova,
 				     msg->iova + msg->size - 1);
 		break;
@@ -1103,12 +1167,26 @@ static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
 			sizeof *used + num * sizeof *used->ring + s);
 }
 
+static void vhost_vq_meta_update(struct vhost_virtqueue *vq,
+				 const struct vhost_umem_node *node,
+				 int type)
+{
+	int access = (type == VHOST_ADDR_USED) ?
+		     VHOST_ACCESS_WO : VHOST_ACCESS_RO;
+
+	if (likely(node->perm & access))
+		vq->meta_iotlb[type] = node;
+}
+
 static int iotlb_access_ok(struct vhost_virtqueue *vq,
-			   int access, u64 addr, u64 len)
+			   int access, u64 addr, u64 len, int type)
 {
 	const struct vhost_umem_node *node;
 	struct vhost_umem *umem = vq->iotlb;
-	u64 s = 0, size;
+	u64 s = 0, size, orig_addr = addr;
+
+	if (vhost_vq_meta_fetch(vq, addr, len, type))
+		return true;
 
 	while (len > s) {
 		node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
@@ -1125,6 +1203,10 @@ static int iotlb_access_ok(struct vhost_virtqueue *vq,
 		}
 
 		size = node->size - addr + node->start;
+
+		if (orig_addr == addr && size >= len)
+			vhost_vq_meta_update(vq, node, type);
+
 		s += size;
 		addr += size;
 	}
@@ -1141,13 +1223,15 @@ int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
 		return 1;
 
 	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
-			       num * sizeof *vq->desc) &&
+			       num * sizeof(*vq->desc), VHOST_ADDR_DESC) &&
 	       iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
 			       sizeof *vq->avail +
-			       num * sizeof *vq->avail->ring + s) &&
+			       num * sizeof(*vq->avail->ring) + s,
+			       VHOST_ADDR_AVAIL) &&
 	       iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used,
 			       sizeof *vq->used +
-			       num * sizeof *vq->used->ring + s);
+			       num * sizeof(*vq->used->ring) + s,
+			       VHOST_ADDR_USED);
 }
 EXPORT_SYMBOL_GPL(vq_iotlb_prefetch);
 
@@ -1728,7 +1812,7 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq)
 		r = -EFAULT;
 		goto err;
 	}
-	r = vhost_get_user(vq, last_used_idx, &vq->used->idx);
+	r = vhost_get_used(vq, last_used_idx, &vq->used->idx);
 	if (r) {
 		vq_err(vq, "Can't access used idx at %p\n",
 		       &vq->used->idx);
@@ -1932,7 +2016,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 	last_avail_idx = vq->last_avail_idx;
 
 	if (vq->avail_idx == vq->last_avail_idx) {
-		if (unlikely(vhost_get_user(vq, avail_idx, &vq->avail->idx))) {
+		if (unlikely(vhost_get_avail(vq, avail_idx, &vq->avail->idx))) {
 			vq_err(vq, "Failed to access avail idx at %p\n",
 				&vq->avail->idx);
 			return -EFAULT;
@@ -1959,7 +2043,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 
 	/* Grab the next descriptor number they're advertising, and increment
 	 * the index we've seen. */
-	if (unlikely(vhost_get_user(vq, ring_head,
+	if (unlikely(vhost_get_avail(vq, ring_head,
 		     &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
 		vq_err(vq, "Failed to read head: idx %d address %p\n",
 		       last_avail_idx,
@@ -2175,7 +2259,7 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 		 * with the barrier that the Guest executes when enabling
 		 * interrupts. */
 		smp_mb();
-		if (vhost_get_user(vq, flags, &vq->avail->flags)) {
+		if (vhost_get_avail(vq, flags, &vq->avail->flags)) {
 			vq_err(vq, "Failed to get flags");
 			return true;
 		}
@@ -2202,7 +2286,7 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	 * interrupts. */
 	smp_mb();
 
-	if (vhost_get_user(vq, event, vhost_used_event(vq))) {
+	if (vhost_get_avail(vq, event, vhost_used_event(vq))) {
 		vq_err(vq, "Failed to get used event idx");
 		return true;
 	}
@@ -2246,7 +2330,7 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	__virtio16 avail_idx;
 	int r;
 
-	r = vhost_get_user(vq, avail_idx, &vq->avail->idx);
+	r = vhost_get_avail(vq, avail_idx, &vq->avail->idx);
 	if (r)
 		return false;
 
@@ -2281,7 +2365,7 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	/* They could have slipped one in as we were doing that: make
 	 * sure it's written, then check again. */
 	smp_mb();
-	r = vhost_get_user(vq, avail_idx, &vq->avail->idx);
+	r = vhost_get_avail(vq, avail_idx, &vq->avail->idx);
 	if (r) {
 		vq_err(vq, "Failed to check avail idx at %p: %d\n",
 		       &vq->avail->idx, r);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index a9cbbb148f46..f55671d53f28 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -76,6 +76,13 @@ struct vhost_umem {
 	int numem;
 };
 
+enum vhost_uaddr_type {
+	VHOST_ADDR_DESC = 0,
+	VHOST_ADDR_AVAIL = 1,
+	VHOST_ADDR_USED = 2,
+	VHOST_NUM_ADDRS = 3,
+};
+
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
 	struct vhost_dev *dev;
@@ -86,6 +93,7 @@ struct vhost_virtqueue {
 	struct vring_desc __user *desc;
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
+	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
 	struct file *kick;
 	struct file *call;
 	struct file *error;
-- 
GitLab


From c4baad50297d84bde1a7ad45e50c73adae4a2192 Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Wed, 1 Feb 2017 00:02:27 -0800
Subject: [PATCH 453/898] virtio-console: avoid DMA from stack

put_chars() stuffs the buffer it gets into an sg, but that buffer may be
on the stack. This breaks with CONFIG_VMAP_STACK=y (for me, it
manifested as printks getting turned into NUL bytes).

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/char/virtio_console.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 6266c0568e1d..e9b7e0b3cabe 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1136,6 +1136,8 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 {
 	struct port *port;
 	struct scatterlist sg[1];
+	void *data;
+	int ret;
 
 	if (unlikely(early_put_chars))
 		return early_put_chars(vtermno, buf, count);
@@ -1144,8 +1146,14 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 	if (!port)
 		return -EPIPE;
 
-	sg_init_one(sg, buf, count);
-	return __send_to_port(port, sg, 1, count, (void *)buf, false);
+	data = kmemdup(buf, count, GFP_ATOMIC);
+	if (!data)
+		return -ENOMEM;
+
+	sg_init_one(sg, data, count);
+	ret = __send_to_port(port, sg, 1, count, data, false);
+	kfree(data);
+	return ret;
 }
 
 /*
-- 
GitLab


From 4ecce920e13ace16a5ba45efe8909946c28fb2ad Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Mon, 13 Feb 2017 16:03:47 +0100
Subject: [PATCH 454/898] CIFS: move DFS response parsing out of SMB1 code

since the DFS payload is not tied to the SMB version we can:
* isolate the DFS payload in its own struct, and include that struct in
  packet structs
* move the function that parses the response to misc.c and make it work
  on the new DFS payload struct (add payload size and utf16 flag as a
  result).

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Acked-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/cifspdu.h   |  16 +++---
 fs/cifs/cifsproto.h |   5 ++
 fs/cifs/cifssmb.c   | 119 ++------------------------------------------
 fs/cifs/misc.c      | 105 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 125 insertions(+), 120 deletions(-)

diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index f5b87303ce46..1ce733f3582f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -2086,17 +2086,21 @@ typedef struct dfs_referral_level_3 { /* version 4 is same, + one flag bit */
 	__u8   ServiceSiteGuid[16];  /* MBZ, ignored */
 } __attribute__((packed)) REFERRAL3;
 
-typedef struct smb_com_transaction_get_dfs_refer_rsp {
-	struct smb_hdr hdr;	/* wct = 10 */
-	struct trans2_resp t2;
-	__u16 ByteCount;
-	__u8 Pad;
+struct get_dfs_referral_rsp {
 	__le16 PathConsumed;
 	__le16 NumberOfReferrals;
 	__le32 DFSFlags;
 	REFERRAL3 referrals[1];	/* array of level 3 dfs_referral structures */
 	/* followed by the strings pointed to by the referral structures */
-} __attribute__((packed)) TRANSACTION2_GET_DFS_REFER_RSP;
+} __packed;
+
+typedef struct smb_com_transaction_get_dfs_refer_rsp {
+	struct smb_hdr hdr;	/* wct = 10 */
+	struct trans2_resp t2;
+	__u16 ByteCount;
+	__u8 Pad;
+	struct get_dfs_referral_rsp dfs_data;
+} __packed TRANSACTION2_GET_DFS_REFER_RSP;
 
 /* DFS Flags */
 #define DFSREF_REFERRAL_SERVER  0x00000001 /* all targets are DFS roots */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 406d2c10ba78..c09783045288 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -284,6 +284,11 @@ extern int get_dfs_path(const unsigned int xid, struct cifs_ses *ses,
 			const struct nls_table *nls_codepage,
 			unsigned int *num_referrals,
 			struct dfs_info3_param **referrals, int remap);
+extern int parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size,
+			       unsigned int *num_of_nodes,
+			       struct dfs_info3_param **target_nodes,
+			       const struct nls_table *nls_codepage, int remap,
+			       const char *searchName, bool is_unicode);
 extern void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 				 struct cifs_sb_info *cifs_sb,
 				 struct smb_vol *vol);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index f5099fb8a22f..5005c7995b6a 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -4786,117 +4786,6 @@ CIFSGetSrvInodeNumber(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
-/* parses DFS refferal V3 structure
- * caller is responsible for freeing target_nodes
- * returns:
- * 	on success - 0
- *	on failure - errno
- */
-static int
-parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
-		unsigned int *num_of_nodes,
-		struct dfs_info3_param **target_nodes,
-		const struct nls_table *nls_codepage, int remap,
-		const char *searchName)
-{
-	int i, rc = 0;
-	char *data_end;
-	bool is_unicode;
-	struct dfs_referral_level_3 *ref;
-
-	if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
-		is_unicode = true;
-	else
-		is_unicode = false;
-	*num_of_nodes = le16_to_cpu(pSMBr->NumberOfReferrals);
-
-	if (*num_of_nodes < 1) {
-		cifs_dbg(VFS, "num_referrals: must be at least > 0, but we get num_referrals = %d\n",
-			 *num_of_nodes);
-		rc = -EINVAL;
-		goto parse_DFS_referrals_exit;
-	}
-
-	ref = (struct dfs_referral_level_3 *) &(pSMBr->referrals);
-	if (ref->VersionNumber != cpu_to_le16(3)) {
-		cifs_dbg(VFS, "Referrals of V%d version are not supported, should be V3\n",
-			 le16_to_cpu(ref->VersionNumber));
-		rc = -EINVAL;
-		goto parse_DFS_referrals_exit;
-	}
-
-	/* get the upper boundary of the resp buffer */
-	data_end = (char *)(&(pSMBr->PathConsumed)) +
-				le16_to_cpu(pSMBr->t2.DataCount);
-
-	cifs_dbg(FYI, "num_referrals: %d dfs flags: 0x%x ...\n",
-		 *num_of_nodes, le32_to_cpu(pSMBr->DFSFlags));
-
-	*target_nodes = kcalloc(*num_of_nodes, sizeof(struct dfs_info3_param),
-				GFP_KERNEL);
-	if (*target_nodes == NULL) {
-		rc = -ENOMEM;
-		goto parse_DFS_referrals_exit;
-	}
-
-	/* collect necessary data from referrals */
-	for (i = 0; i < *num_of_nodes; i++) {
-		char *temp;
-		int max_len;
-		struct dfs_info3_param *node = (*target_nodes)+i;
-
-		node->flags = le32_to_cpu(pSMBr->DFSFlags);
-		if (is_unicode) {
-			__le16 *tmp = kmalloc(strlen(searchName)*2 + 2,
-						GFP_KERNEL);
-			if (tmp == NULL) {
-				rc = -ENOMEM;
-				goto parse_DFS_referrals_exit;
-			}
-			cifsConvertToUTF16((__le16 *) tmp, searchName,
-					   PATH_MAX, nls_codepage, remap);
-			node->path_consumed = cifs_utf16_bytes(tmp,
-					le16_to_cpu(pSMBr->PathConsumed),
-					nls_codepage);
-			kfree(tmp);
-		} else
-			node->path_consumed = le16_to_cpu(pSMBr->PathConsumed);
-
-		node->server_type = le16_to_cpu(ref->ServerType);
-		node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags);
-
-		/* copy DfsPath */
-		temp = (char *)ref + le16_to_cpu(ref->DfsPathOffset);
-		max_len = data_end - temp;
-		node->path_name = cifs_strndup_from_utf16(temp, max_len,
-						is_unicode, nls_codepage);
-		if (!node->path_name) {
-			rc = -ENOMEM;
-			goto parse_DFS_referrals_exit;
-		}
-
-		/* copy link target UNC */
-		temp = (char *)ref + le16_to_cpu(ref->NetworkAddressOffset);
-		max_len = data_end - temp;
-		node->node_name = cifs_strndup_from_utf16(temp, max_len,
-						is_unicode, nls_codepage);
-		if (!node->node_name) {
-			rc = -ENOMEM;
-			goto parse_DFS_referrals_exit;
-		}
-
-		ref++;
-	}
-
-parse_DFS_referrals_exit:
-	if (rc) {
-		free_dfs_info_array(*target_nodes, *num_of_nodes);
-		*target_nodes = NULL;
-		*num_of_nodes = 0;
-	}
-	return rc;
-}
-
 int
 CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses,
 		const char *search_name, struct dfs_info3_param **target_nodes,
@@ -4993,9 +4882,11 @@ CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses,
 		 get_bcc(&pSMBr->hdr), le16_to_cpu(pSMBr->t2.DataOffset));
 
 	/* parse returned result into more usable form */
-	rc = parse_DFS_referrals(pSMBr, num_of_nodes,
-				 target_nodes, nls_codepage, remap,
-				 search_name);
+	rc = parse_dfs_referrals(&pSMBr->dfs_data,
+				 le16_to_cpu(pSMBr->t2.DataCount),
+				 num_of_nodes, target_nodes, nls_codepage,
+				 remap, search_name,
+				 pSMBr->hdr.Flags2 & SMBFLG2_UNICODE);
 
 GetDFSRefExit:
 	cifs_buf_release(pSMB);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index c6729156f9a0..d3fb11529ed9 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -640,3 +640,108 @@ cifs_add_pending_open(struct cifs_fid *fid, struct tcon_link *tlink,
 	cifs_add_pending_open_locked(fid, tlink, open);
 	spin_unlock(&tlink_tcon(open->tlink)->open_file_lock);
 }
+
+/* parses DFS refferal V3 structure
+ * caller is responsible for freeing target_nodes
+ * returns:
+ * - on success - 0
+ * - on failure - errno
+ */
+int
+parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size,
+		    unsigned int *num_of_nodes,
+		    struct dfs_info3_param **target_nodes,
+		    const struct nls_table *nls_codepage, int remap,
+		    const char *searchName, bool is_unicode)
+{
+	int i, rc = 0;
+	char *data_end;
+	struct dfs_referral_level_3 *ref;
+
+	*num_of_nodes = le16_to_cpu(rsp->NumberOfReferrals);
+
+	if (*num_of_nodes < 1) {
+		cifs_dbg(VFS, "num_referrals: must be at least > 0, but we get num_referrals = %d\n",
+			 *num_of_nodes);
+		rc = -EINVAL;
+		goto parse_DFS_referrals_exit;
+	}
+
+	ref = (struct dfs_referral_level_3 *) &(rsp->referrals);
+	if (ref->VersionNumber != cpu_to_le16(3)) {
+		cifs_dbg(VFS, "Referrals of V%d version are not supported, should be V3\n",
+			 le16_to_cpu(ref->VersionNumber));
+		rc = -EINVAL;
+		goto parse_DFS_referrals_exit;
+	}
+
+	/* get the upper boundary of the resp buffer */
+	data_end = (char *)rsp + rsp_size;
+
+	cifs_dbg(FYI, "num_referrals: %d dfs flags: 0x%x ...\n",
+		 *num_of_nodes, le32_to_cpu(rsp->DFSFlags));
+
+	*target_nodes = kcalloc(*num_of_nodes, sizeof(struct dfs_info3_param),
+				GFP_KERNEL);
+	if (*target_nodes == NULL) {
+		rc = -ENOMEM;
+		goto parse_DFS_referrals_exit;
+	}
+
+	/* collect necessary data from referrals */
+	for (i = 0; i < *num_of_nodes; i++) {
+		char *temp;
+		int max_len;
+		struct dfs_info3_param *node = (*target_nodes)+i;
+
+		node->flags = le32_to_cpu(rsp->DFSFlags);
+		if (is_unicode) {
+			__le16 *tmp = kmalloc(strlen(searchName)*2 + 2,
+						GFP_KERNEL);
+			if (tmp == NULL) {
+				rc = -ENOMEM;
+				goto parse_DFS_referrals_exit;
+			}
+			cifsConvertToUTF16((__le16 *) tmp, searchName,
+					   PATH_MAX, nls_codepage, remap);
+			node->path_consumed = cifs_utf16_bytes(tmp,
+					le16_to_cpu(rsp->PathConsumed),
+					nls_codepage);
+			kfree(tmp);
+		} else
+			node->path_consumed = le16_to_cpu(rsp->PathConsumed);
+
+		node->server_type = le16_to_cpu(ref->ServerType);
+		node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags);
+
+		/* copy DfsPath */
+		temp = (char *)ref + le16_to_cpu(ref->DfsPathOffset);
+		max_len = data_end - temp;
+		node->path_name = cifs_strndup_from_utf16(temp, max_len,
+						is_unicode, nls_codepage);
+		if (!node->path_name) {
+			rc = -ENOMEM;
+			goto parse_DFS_referrals_exit;
+		}
+
+		/* copy link target UNC */
+		temp = (char *)ref + le16_to_cpu(ref->NetworkAddressOffset);
+		max_len = data_end - temp;
+		node->node_name = cifs_strndup_from_utf16(temp, max_len,
+						is_unicode, nls_codepage);
+		if (!node->node_name) {
+			rc = -ENOMEM;
+			goto parse_DFS_referrals_exit;
+		}
+
+		ref++;
+	}
+
+parse_DFS_referrals_exit:
+	if (rc) {
+		free_dfs_info_array(*target_nodes, *num_of_nodes);
+		*target_nodes = NULL;
+		*num_of_nodes = 0;
+	}
+	return rc;
+}
-- 
GitLab


From 268a635d414df45a4a8da699d431da8f8ffcf014 Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Mon, 13 Feb 2017 16:14:17 +0100
Subject: [PATCH 455/898] CIFS: add build_path_from_dentry_optional_prefix()

this function does the same thing as add build_path_from_dentry() but
takes a boolean parameter to decide whether or not to prefix the path
with the tree name.

we cannot rely on tcon->Flags & SMB_SHARE_IS_IN_DFS for SMB2 as smb2
code never sets tcon->Flags but it sets tcon->share_flags and it seems
the SMB_SHARE_IS_IN_DFS has different semantics in SMB2: the prefix
shouldn't be added everytime it was in SMB1.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Acked-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/cifs_dfs_ref.c |  4 +++-
 fs/cifs/cifsproto.h    |  2 ++
 fs/cifs/dir.c          | 13 ++++++++++++-
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 9156be545b0f..6b61df117fd4 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -303,7 +303,9 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 	 * gives us the latter, so we must adjust the result.
 	 */
 	mnt = ERR_PTR(-ENOMEM);
-	full_path = build_path_from_dentry(mntpt);
+
+	/* always use tree name prefix */
+	full_path = build_path_from_dentry_optional_prefix(mntpt, true);
 	if (full_path == NULL)
 		goto cdda_exit;
 
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index c09783045288..9ee46c1c3ebd 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -61,6 +61,8 @@ extern void exit_cifs_idmap(void);
 extern int init_cifs_spnego(void);
 extern void exit_cifs_spnego(void);
 extern char *build_path_from_dentry(struct dentry *);
+extern char *build_path_from_dentry_optional_prefix(struct dentry *direntry,
+						    bool prefix);
 extern char *cifs_build_path_to_root(struct smb_vol *vol,
 				     struct cifs_sb_info *cifs_sb,
 				     struct cifs_tcon *tcon,
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 2c227a99f369..56366e984076 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -80,6 +80,17 @@ cifs_build_path_to_root(struct smb_vol *vol, struct cifs_sb_info *cifs_sb,
 /* Note: caller must free return buffer */
 char *
 build_path_from_dentry(struct dentry *direntry)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	bool prefix = tcon->Flags & SMB_SHARE_IS_IN_DFS;
+
+	return build_path_from_dentry_optional_prefix(direntry,
+						      prefix);
+}
+
+char *
+build_path_from_dentry_optional_prefix(struct dentry *direntry, bool prefix)
 {
 	struct dentry *temp;
 	int namelen;
@@ -92,7 +103,7 @@ build_path_from_dentry(struct dentry *direntry)
 	unsigned seq;
 
 	dirsep = CIFS_DIR_SEP(cifs_sb);
-	if (tcon->Flags & SMB_SHARE_IS_IN_DFS)
+	if (prefix)
 		dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1);
 	else
 		dfsplen = 0;
-- 
GitLab


From 51146625f34b348c15d55c378b5ae5c2fb963fc8 Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Tue, 28 Feb 2017 15:08:41 +0100
Subject: [PATCH 456/898] CIFS: add use_ipc flag to SMB2_ioctl()

when set, use the session IPC tree id instead of the tid in the provided
tcon.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/smb2file.c  |  3 ++-
 fs/cifs/smb2ops.c   | 23 ++++++++++++++++-------
 fs/cifs/smb2pdu.c   | 17 +++++++++++++++--
 fs/cifs/smb2proto.h |  3 ++-
 4 files changed, 35 insertions(+), 11 deletions(-)

diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index b2aff0c6f22c..b4b1f0305f29 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -73,7 +73,8 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 		nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */
 		nr_ioctl_req.Reserved = 0;
 		rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid,
-			fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true,
+			fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY,
+			true /* is_fsctl */, false /* use_ipc */,
 			(char *)&nr_ioctl_req, sizeof(nr_ioctl_req),
 			NULL, NULL /* no return info */);
 		if (rc == -EOPNOTSUPP) {
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index d2cdd9c19d17..eba00cd3bd16 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -282,6 +282,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
+			false /* use_ipc */,
 			NULL /* no data input */, 0 /* no data input */,
 			(char **)&out_buf, &ret_data_len);
 	if (rc != 0)
@@ -571,6 +572,7 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */,
+			false /* use_ipc */,
 			NULL, 0 /* no input */,
 			(char **)&res_key, &ret_data_len);
 
@@ -635,7 +637,8 @@ smb2_clone_range(const unsigned int xid,
 		/* Request server copy to target from src identified by key */
 		rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
-			true /* is_fsctl */, (char *)pcchunk,
+			true /* is_fsctl */, false /* use_ipc */,
+			(char *)pcchunk,
 			sizeof(struct copychunk_ioctl),	(char **)&retbuf,
 			&ret_data_len);
 		if (rc == 0) {
@@ -787,7 +790,8 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_SPARSE,
-			true /* is_fctl */, &setsparse, 1, NULL, NULL);
+			true /* is_fctl */, false /* use_ipc */,
+			&setsparse, 1, NULL, NULL);
 	if (rc) {
 		tcon->broken_sparse_sup = true;
 		cifs_dbg(FYI, "set sparse rc = %d\n", rc);
@@ -857,7 +861,8 @@ smb2_duplicate_extents(const unsigned int xid,
 	rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid,
 			FSCTL_DUPLICATE_EXTENTS_TO_FILE,
-			true /* is_fsctl */, (char *)&dup_ext_buf,
+			true /* is_fsctl */, false /* use_ipc */,
+			(char *)&dup_ext_buf,
 			sizeof(struct duplicate_extents_to_file),
 			NULL,
 			&ret_data_len);
@@ -891,7 +896,8 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 	return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
 			FSCTL_SET_INTEGRITY_INFORMATION,
-			true /* is_fsctl */, (char *)&integr_info,
+			true /* is_fsctl */, false /* use_ipc */,
+			(char *)&integr_info,
 			sizeof(struct fsctl_set_integrity_information_req),
 			NULL,
 			&ret_data_len);
@@ -910,7 +916,8 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
 			FSCTL_SRV_ENUMERATE_SNAPSHOTS,
-			true /* is_fsctl */, NULL, 0 /* no input data */,
+			true /* is_fsctl */, false /* use_ipc */,
+			NULL, 0 /* no input data */,
 			(char **)&retbuf,
 			&ret_data_len);
 	cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n",
@@ -1220,7 +1227,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
-			true /* is_fctl */, (char *)&fsctl_buf,
+			true /* is_fctl */, false /* use_ipc */,
+			(char *)&fsctl_buf,
 			sizeof(struct file_zero_data_information), NULL, NULL);
 	free_xid(xid);
 	return rc;
@@ -1254,7 +1262,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
-			true /* is_fctl */, (char *)&fsctl_buf,
+			true /* is_fctl */, false /* use_ipc */,
+			(char *)&fsctl_buf,
 			sizeof(struct file_zero_data_information), NULL, NULL);
 	free_xid(xid);
 	return rc;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index ad83b3db2840..8c4532dc749f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -620,6 +620,7 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
+		false /* use_ipc */,
 		(char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req),
 		(char **)&pneg_rsp, &rsplen);
 
@@ -1683,8 +1684,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
  */
 int
 SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
-	   u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data,
-	   u32 indatalen, char **out_data, u32 *plen /* returned data len */)
+	   u64 volatile_fid, u32 opcode, bool is_fsctl, bool use_ipc,
+	   char *in_data, u32 indatalen,
+	   char **out_data, u32 *plen /* returned data len */)
 {
 	struct smb2_ioctl_req *req;
 	struct smb2_ioctl_rsp *rsp;
@@ -1721,6 +1723,16 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (rc)
 		return rc;
 
+	if (use_ipc) {
+		if (ses->ipc_tid == 0) {
+			cifs_small_buf_release(req);
+			return -ENOTCONN;
+		}
+
+		cifs_dbg(FYI, "replacing tid 0x%x with IPC tid 0x%x\n",
+			 req->hdr.sync_hdr.TreeId, ses->ipc_tid);
+		req->hdr.sync_hdr.TreeId = ses->ipc_tid;
+	}
 	if (encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
@@ -1843,6 +1855,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SET_COMPRESSION, true /* is_fsctl */,
+			false /* use_ipc */,
 			(char *)&fsctl_input /* data input */,
 			2 /* in data len */, &ret_data /* out data */, NULL);
 
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 85fc7a789334..11d9f3013db8 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -121,7 +121,8 @@ extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms,
 		     struct smb2_err_rsp **err_buf);
 extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     u64 persistent_fid, u64 volatile_fid, u32 opcode,
-		     bool is_fsctl, char *in_data, u32 indatalen,
+		     bool is_fsctl, bool use_ipc,
+		     char *in_data, u32 indatalen,
 		     char **out_data, u32 *plen /* returned data len */);
 extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
-- 
GitLab


From 7f9f6d2ec51449a20bc35359c9e190bf861b57e1 Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Tue, 28 Feb 2017 15:26:30 +0100
Subject: [PATCH 457/898] CIFS: let ses->ipc_tid hold smb2 TreeIds

the TreeId field went from 2 bytes in CIFS to 4 bytes in SMB2+. this
commit updates the size of the ipc_tid field of a cifs_ses, which was
still using 2 bytes.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/cifsglob.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 1a90bb3e2986..af224cda8697 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -822,7 +822,7 @@ struct cifs_ses {
 	int ses_count;		/* reference counter */
 	enum statusEnum status;
 	unsigned overrideSecFlg;  /* if non-zero override global sec flags */
-	__u16 ipc_tid;		/* special tid for connection to IPC share */
+	__u32 ipc_tid;		/* special tid for connection to IPC share */
 	char *serverOS;		/* name of operating system underlying server */
 	char *serverNOS;	/* name of network operating system of server */
 	char *serverDomain;	/* security realm of server */
-- 
GitLab


From b9043cc5b99e9c93596a28647fd9f526f5bfa22c Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Mon, 13 Feb 2017 16:19:04 +0100
Subject: [PATCH 458/898] CIFS: set signing flag in SMB2+ TreeConnect if needed

cifs_enable_signing() already sets server->sign according to what the
server requires/offers and what mount options allows/forbids, so use
that.

this is required for IPC tcon that connects to signing-required servers.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Acked-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/smb2pdu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 8c4532dc749f..2fd93eeed15a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1168,8 +1168,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 
 		/* since no tcon, smb2_init can not do this, so do here */
 		req->hdr.sync_hdr.SessionId = ses->Suid;
-		/* if (ses->server->sec_mode & SECMODE_SIGN_REQUIRED)
-			req->hdr.Flags |= SMB2_FLAGS_SIGNED; */
+		if (ses->server->sign)
+			req->hdr.sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
 	} else if (encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-- 
GitLab


From 8953de2f02ad7b15e4964c82f9afd60f128e4e98 Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Wed, 1 Mar 2017 09:55:28 +0000
Subject: [PATCH 459/898] net: bridge: allow IPv6 when multicast flood is
 disabled

Even with multicast flooding turned off, IPv6 ND should still work so
that IPv6 connectivity is provided. Allow this by continuing to flood
multicast traffic originated by us.

Fixes: b6cb5ac8331b ("net: bridge: add per-port multicast flood flag")
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Mike Manning <mmanning@brocade.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 6bfac29318f2..902af6ba481c 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -186,8 +186,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		/* Do not flood unicast traffic to ports that turn it off */
 		if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD))
 			continue;
+		/* Do not flood if mc off, except for traffic we originate */
 		if (pkt_type == BR_PKT_MULTICAST &&
-		    !(p->flags & BR_MCAST_FLOOD))
+		    !(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
 			continue;
 
 		/* Do not flood to ports that enable proxy ARP */
-- 
GitLab


From 540e2894f7905538740aaf122bd8e0548e1c34a4 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 1 Mar 2017 12:57:20 +0100
Subject: [PATCH 460/898] net: don't call strlen() on the user buffer in
 packet_bind_spkt()

KMSAN (KernelMemorySanitizer, a new error detection tool) reports use of
uninitialized memory in packet_bind_spkt():
Acked-by: Eric Dumazet <edumazet@google.com>

==================================================================
BUG: KMSAN: use of unitialized memory
CPU: 0 PID: 1074 Comm: packet Not tainted 4.8.0-rc6+ #1891
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
 0000000000000000 ffff88006b6dfc08 ffffffff82559ae8 ffff88006b6dfb48
 ffffffff818a7c91 ffffffff85b9c870 0000000000000092 ffffffff85b9c550
 0000000000000000 0000000000000092 00000000ec400911 0000000000000002
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff82559ae8>] dump_stack+0x238/0x290 lib/dump_stack.c:51
 [<ffffffff818a6626>] kmsan_report+0x276/0x2e0 mm/kmsan/kmsan.c:1003
 [<ffffffff818a783b>] __msan_warning+0x5b/0xb0
mm/kmsan/kmsan_instr.c:424
 [<     inline     >] strlen lib/string.c:484
 [<ffffffff8259b58d>] strlcpy+0x9d/0x200 lib/string.c:144
 [<ffffffff84b2eca4>] packet_bind_spkt+0x144/0x230
net/packet/af_packet.c:3132
 [<ffffffff84242e4d>] SYSC_bind+0x40d/0x5f0 net/socket.c:1370
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
chained origin: 00000000eba00911
 [<ffffffff810bb787>] save_stack_trace+0x27/0x50
arch/x86/kernel/stacktrace.c:67
 [<     inline     >] kmsan_save_stack_with_flags mm/kmsan/kmsan.c:322
 [<     inline     >] kmsan_save_stack mm/kmsan/kmsan.c:334
 [<ffffffff818a59f8>] kmsan_internal_chain_origin+0x118/0x1e0
mm/kmsan/kmsan.c:527
 [<ffffffff818a7773>] __msan_set_alloca_origin4+0xc3/0x130
mm/kmsan/kmsan_instr.c:380
 [<ffffffff84242b69>] SYSC_bind+0x129/0x5f0 net/socket.c:1356
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
origin description: ----address@SYSC_bind (origin=00000000eb400911)
==================================================================
(the line numbers are relative to 4.8-rc6, but the bug persists
upstream)

, when I run the following program as root:

=====================================
 #include <string.h>
 #include <sys/socket.h>
 #include <netpacket/packet.h>
 #include <net/ethernet.h>

 int main() {
   struct sockaddr addr;
   memset(&addr, 0xff, sizeof(addr));
   addr.sa_family = AF_PACKET;
   int fd = socket(PF_PACKET, SOCK_PACKET, htons(ETH_P_ALL));
   bind(fd, &addr, sizeof(addr));
   return 0;
 }
=====================================

This happens because addr.sa_data copied from the userspace is not
zero-terminated, and copying it with strlcpy() in packet_bind_spkt()
results in calling strlen() on the kernel copy of that non-terminated
buffer.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2bd0d1949312..a0dbe7ca8f72 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3103,7 +3103,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 			    int addr_len)
 {
 	struct sock *sk = sock->sk;
-	char name[15];
+	char name[sizeof(uaddr->sa_data) + 1];
 
 	/*
 	 *	Check legality
@@ -3111,7 +3111,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 
 	if (addr_len != sizeof(struct sockaddr))
 		return -EINVAL;
-	strlcpy(name, uaddr->sa_data, sizeof(name));
+	/* uaddr->sa_data comes from the userspace, it's not guaranteed to be
+	 * zero-terminated.
+	 */
+	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
+	name[sizeof(uaddr->sa_data)] = 0;
 
 	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
-- 
GitLab


From 13baa00ad01bb3a9f893e3a08cbc2d072fc0c15d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:28:39 -0800
Subject: [PATCH 461/898] net: net_enable_timestamp() can be called from irq
 contexts

It is now very clear that silly TCP listeners might play with
enabling/disabling timestamping while new children are added
to their accept queue.

Meaning net_enable_timestamp() can be called from BH context
while current state of the static key is not enabled.

Lets play safe and allow all contexts.

The work queue is scheduled only under the problematic cases,
which are the static key enable/disable transition, to not slow down
critical paths.

This extends and improves what we did in commit 5fa8bbda38c6 ("net: use
a work queue to defer net_disable_timestamp() work")

Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 35 +++++++++++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index e63bf61b19be..8637b2b71f3d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1698,27 +1698,54 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
 static atomic_t netstamp_needed_deferred;
+static atomic_t netstamp_wanted;
 static void netstamp_clear(struct work_struct *work)
 {
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+	int wanted;
 
-	while (deferred--)
-		static_key_slow_dec(&netstamp_needed);
+	wanted = atomic_add_return(deferred, &netstamp_wanted);
+	if (wanted > 0)
+		static_key_enable(&netstamp_needed);
+	else
+		static_key_disable(&netstamp_needed);
 }
 static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
 
 void net_enable_timestamp(void)
 {
+#ifdef HAVE_JUMP_LABEL
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 0)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+			return;
+	}
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_inc(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	/* net_disable_timestamp() can be called from non process context */
-	atomic_inc(&netstamp_needed_deferred);
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 1)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+			return;
+	}
+	atomic_dec(&netstamp_needed_deferred);
 	schedule_work(&netstamp_work);
 #else
 	static_key_slow_dec(&netstamp_needed);
-- 
GitLab


From 48cac18ecf1de82f76259a54402c3adb7839ad01 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:45:06 -0800
Subject: [PATCH 462/898] ipv6: orphan skbs in reassembly unit

Andrey reported a use-after-free in IPv6 stack.

Issue here is that we free the socket while it still has skb
in TX path and in some queues.

It happens here because IPv6 reassembly unit messes skb->truesize,
breaking skb_set_owner_w() badly.

We fixed a similar issue for IPV4 in commit 8282f27449bf ("inet: frag:
Always orphan skbs inside ip_defrag()")
Acked-by: Joe Stringer <joe@ovn.org>

==================================================================
BUG: KASAN: use-after-free in sock_wfree+0x118/0x120
Read of size 8 at addr ffff880062da0060 by task a.out/4140

page:ffffea00018b6800 count:1 mapcount:0 mapping:          (null)
index:0x0 compound_mapcount: 0
flags: 0x100000000008100(slab|head)
raw: 0100000000008100 0000000000000000 0000000000000000 0000000180130013
raw: dead000000000100 dead000000000200 ffff88006741f140 0000000000000000
page dumped because: kasan: bad access detected

CPU: 0 PID: 4140 Comm: a.out Not tainted 4.10.0-rc3+ #59
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 describe_address mm/kasan/report.c:262
 kasan_report_error+0x121/0x560 mm/kasan/report.c:370
 kasan_report mm/kasan/report.c:392
 __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:413
 sock_flag ./arch/x86/include/asm/bitops.h:324
 sock_wfree+0x118/0x120 net/core/sock.c:1631
 skb_release_head_state+0xfc/0x250 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4e0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put ./include/net/inet_frag.h:133
 nf_ct_frag6_gather+0x1125/0x38b0 net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x21b/0x350 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn ./include/linux/netfilter.h:102
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook ./include/linux/netfilter.h:212
 __ip6_local_out+0x52c/0xaf0 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613
 rawv6_sendmsg+0x2cff/0x4130 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x620 net/socket.c:848
 new_sync_write fs/read_write.c:499
 __vfs_write+0x483/0x760 fs/read_write.c:512
 vfs_write+0x187/0x530 fs/read_write.c:560
 SYSC_write fs/read_write.c:607
 SyS_write+0xfb/0x230 fs/read_write.c:599
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203
RIP: 0033:0x7ff26e6f5b79
RSP: 002b:00007ff268e0ed98 EFLAGS: 00000206 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007ff268e0f9c0 RCX: 00007ff26e6f5b79
RDX: 0000000000000010 RSI: 0000000020f50fe1 RDI: 0000000000000003
RBP: 00007ff26ebc1220 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000
R13: 00007ff268e0f9c0 R14: 00007ff26efec040 R15: 0000000000000003

The buggy address belongs to the object at ffff880062da0000
 which belongs to the cache RAWv6 of size 1504
The buggy address ffff880062da0060 is located 96 bytes inside
 of 1504-byte region [ffff880062da0000, ffff880062da05e0)

Freed by task 4113:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1352
 slab_free_freelist_hook mm/slub.c:1374
 slab_free mm/slub.c:2951
 kmem_cache_free+0xb2/0x2c0 mm/slub.c:2973
 sk_prot_free net/core/sock.c:1377
 __sk_destruct+0x49c/0x6e0 net/core/sock.c:1452
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sk_free+0x23/0x30 net/core/sock.c:1479
 sock_put ./include/net/sock.h:1638
 sk_common_release+0x31e/0x4e0 net/core/sock.c:2782
 rawv6_close+0x54/0x80 net/ipv6/raw.c:1214
 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425
 inet6_release+0x50/0x70 net/ipv6/af_inet6.c:431
 sock_release+0x8d/0x1e0 net/socket.c:599
 sock_close+0x16/0x20 net/socket.c:1063
 __fput+0x332/0x7f0 fs/file_table.c:208
 ____fput+0x15/0x20 fs/file_table.c:244
 task_work_run+0x19b/0x270 kernel/task_work.c:116
 exit_task_work ./include/linux/task_work.h:21
 do_exit+0x186b/0x2800 kernel/exit.c:839
 do_group_exit+0x149/0x420 kernel/exit.c:943
 SYSC_exit_group kernel/exit.c:954
 SyS_exit_group+0x1d/0x20 kernel/exit.c:952
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Allocated by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544
 slab_post_alloc_hook mm/slab.h:432
 slab_alloc_node mm/slub.c:2708
 slab_alloc mm/slub.c:2716
 kmem_cache_alloc+0x1af/0x250 mm/slub.c:2721
 sk_prot_alloc+0x65/0x2a0 net/core/sock.c:1334
 sk_alloc+0x105/0x1010 net/core/sock.c:1396
 inet6_create+0x44d/0x1150 net/ipv6/af_inet6.c:183
 __sock_create+0x4f6/0x880 net/socket.c:1199
 sock_create net/socket.c:1239
 SYSC_socket net/socket.c:1269
 SyS_socket+0xf9/0x230 net/socket.c:1249
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Memory state around the buggy address:
 ffff880062d9ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff880062d9ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff880062da0000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880062da0080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880062da0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/netfilter/nf_conntrack_reasm.c | 1 +
 net/openvswitch/conntrack.c             | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 9948b5ce52da..986d4ca38832 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -589,6 +589,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
+	skb_orphan(skb);
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
 		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 85cd59526670..e0a87776a010 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -485,7 +485,6 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
 
-		skb_orphan(skb);
 		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
 		err = nf_ct_frag6_gather(net, skb, user);
 		if (err) {
-- 
GitLab


From 4ec3dd89052a437304e1451733c989b8cec681af Mon Sep 17 00:00:00 2001
From: Zhao Yan <yan.y.zhao@intel.com>
Date: Thu, 2 Mar 2017 15:12:47 +0800
Subject: [PATCH 463/898] drm/i915/gvt: fix an error for F_RO flag

the ro_mask is not stored into each mmio entry

Fixes: 12d14cc43b34 ("drm/i915/gvt: Introduce a framework for tracking HW registers.")
Signed-off-by: Zhao Yan <yan.y.zhao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 548aedfbd402..8e43395c748a 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -121,6 +121,7 @@ static int new_mmio_info(struct intel_gvt *gvt,
 		info->size = size;
 		info->length = (i + 4) < end ? 4 : (end - i);
 		info->addr_mask = addr_mask;
+		info->ro_mask = ro_mask;
 		info->device = device;
 		info->read = read ? read : intel_vgpu_default_mmio_read;
 		info->write = write ? write : intel_vgpu_default_mmio_write;
-- 
GitLab


From eb1e011a14748a1d9df9a7d7df9a5711721a1bdb Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 15 Feb 2017 09:49:26 +0100
Subject: [PATCH 464/898] average: change to declare precision, not factor

Declaring the factor is counter-intuitive, and people are prone
to using small(-ish) values even when that makes no sense.

Change the DECLARE_EWMA() macro to take the fractional precision,
in bits, rather than a factor, and update all users.

While at it, add some more documentation.

Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/virtio_net.c                    |  2 +-
 drivers/net/wireless/ath/ath5k/ath5k.h      |  2 +-
 drivers/net/wireless/ralink/rt2x00/rt2x00.h |  2 +-
 include/linux/average.h                     | 61 ++++++++++++++-------
 net/batman-adv/types.h                      |  2 +-
 net/mac80211/ieee80211_i.h                  |  2 +-
 net/mac80211/sta_info.h                     |  2 +-
 7 files changed, 47 insertions(+), 26 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index bf95016f442a..e9d7e2b70085 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -51,7 +51,7 @@ module_param(gso, bool, 0444);
  * at once, the weight is chosen so that the EWMA will be insensitive to short-
  * term, transient changes in packet size.
  */
-DECLARE_EWMA(pkt_len, 1, 64)
+DECLARE_EWMA(pkt_len, 0, 64)
 
 /* With mergeable buffers we align buffer address and use the low bits to
  * encode its true size. Buffer size is up to 1 page so we need to align to
diff --git a/drivers/net/wireless/ath/ath5k/ath5k.h b/drivers/net/wireless/ath/ath5k/ath5k.h
index 67fedb61fcc0..979800c6f57f 100644
--- a/drivers/net/wireless/ath/ath5k/ath5k.h
+++ b/drivers/net/wireless/ath/ath5k/ath5k.h
@@ -1252,7 +1252,7 @@ struct ath5k_statistics {
 #define ATH5K_TXQ_LEN_MAX	(ATH_TXBUF / 4)		/* bufs per queue */
 #define ATH5K_TXQ_LEN_LOW	(ATH5K_TXQ_LEN_MAX / 2)	/* low mark */
 
-DECLARE_EWMA(beacon_rssi, 1024, 8)
+DECLARE_EWMA(beacon_rssi, 10, 8)
 
 /* Driver state associated with an instance of a device */
 struct ath5k_hw {
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 26869b3bef45..340787894c69 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -257,7 +257,7 @@ struct link_qual {
 	int tx_failed;
 };
 
-DECLARE_EWMA(rssi, 1024, 8)
+DECLARE_EWMA(rssi, 10, 8)
 
 /*
  * Antenna settings about the currently active link.
diff --git a/include/linux/average.h b/include/linux/average.h
index d04aa58280de..7ddaf340d2ac 100644
--- a/include/linux/average.h
+++ b/include/linux/average.h
@@ -1,45 +1,66 @@
 #ifndef _LINUX_AVERAGE_H
 #define _LINUX_AVERAGE_H
 
-/* Exponentially weighted moving average (EWMA) */
+/*
+ * Exponentially weighted moving average (EWMA)
+ *
+ * This implements a fixed-precision EWMA algorithm, with both the
+ * precision and fall-off coefficient determined at compile-time
+ * and built into the generated helper funtions.
+ *
+ * The first argument to the macro is the name that will be used
+ * for the struct and helper functions.
+ *
+ * The second argument, the precision, expresses how many bits are
+ * used for the fractional part of the fixed-precision values.
+ *
+ * The third argument, the weight reciprocal, determines how the
+ * new values will be weighed vs. the old state, new values will
+ * get weight 1/weight_rcp and old values 1-1/weight_rcp. Note
+ * that this parameter must be a power of two for efficiency.
+ */
 
-#define DECLARE_EWMA(name, _factor, _weight)				\
+#define DECLARE_EWMA(name, _precision, _weight_rcp)			\
 	struct ewma_##name {						\
 		unsigned long internal;					\
 	};								\
 	static inline void ewma_##name##_init(struct ewma_##name *e)	\
 	{								\
-		BUILD_BUG_ON(!__builtin_constant_p(_factor));		\
-		BUILD_BUG_ON(!__builtin_constant_p(_weight));		\
-		BUILD_BUG_ON_NOT_POWER_OF_2(_factor);			\
-		BUILD_BUG_ON_NOT_POWER_OF_2(_weight);			\
+		BUILD_BUG_ON(!__builtin_constant_p(_precision));	\
+		BUILD_BUG_ON(!__builtin_constant_p(_weight_rcp));	\
+		/*							\
+		 * Even if you want to feed it just 0/1 you should have	\
+		 * some bits for the non-fractional part...		\
+		 */							\
+		BUILD_BUG_ON((_precision) > 30);			\
+		BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp);		\
 		e->internal = 0;					\
 	}								\
 	static inline unsigned long					\
 	ewma_##name##_read(struct ewma_##name *e)			\
 	{								\
-		BUILD_BUG_ON(!__builtin_constant_p(_factor));		\
-		BUILD_BUG_ON(!__builtin_constant_p(_weight));		\
-		BUILD_BUG_ON_NOT_POWER_OF_2(_factor);			\
-		BUILD_BUG_ON_NOT_POWER_OF_2(_weight);			\
-		return e->internal >> ilog2(_factor);			\
+		BUILD_BUG_ON(!__builtin_constant_p(_precision));	\
+		BUILD_BUG_ON(!__builtin_constant_p(_weight_rcp));	\
+		BUILD_BUG_ON((_precision) > 30);			\
+		BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp);		\
+		return e->internal >> (_precision);			\
 	}								\
 	static inline void ewma_##name##_add(struct ewma_##name *e,	\
 					     unsigned long val)		\
 	{								\
 		unsigned long internal = ACCESS_ONCE(e->internal);	\
-		unsigned long weight = ilog2(_weight);			\
-		unsigned long factor = ilog2(_factor);			\
+		unsigned long weight_rcp = ilog2(_weight_rcp);		\
+		unsigned long precision = _precision;			\
 									\
-		BUILD_BUG_ON(!__builtin_constant_p(_factor));		\
-		BUILD_BUG_ON(!__builtin_constant_p(_weight));		\
-		BUILD_BUG_ON_NOT_POWER_OF_2(_factor);			\
-		BUILD_BUG_ON_NOT_POWER_OF_2(_weight);			\
+		BUILD_BUG_ON(!__builtin_constant_p(_precision));	\
+		BUILD_BUG_ON(!__builtin_constant_p(_weight_rcp));	\
+		BUILD_BUG_ON((_precision) > 30);			\
+		BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp);		\
 									\
 		ACCESS_ONCE(e->internal) = internal ?			\
-			(((internal << weight) - internal) +		\
-				(val << factor)) >> weight :		\
-			(val << factor);				\
+			(((internal << weight_rcp) - internal) +	\
+				(val << precision)) >> weight_rcp :	\
+			(val << precision);				\
 	}
 
 #endif /* _LINUX_AVERAGE_H */
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 8f64a5c01345..66b25e410a41 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -402,7 +402,7 @@ struct batadv_gw_node {
 	struct rcu_head rcu;
 };
 
-DECLARE_EWMA(throughput, 1024, 8)
+DECLARE_EWMA(throughput, 10, 8)
 
 /**
  * struct batadv_hardif_neigh_node_bat_v - B.A.T.M.A.N. V private neighbor
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 159a1a733725..0e718437d080 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -428,7 +428,7 @@ struct ieee80211_sta_tx_tspec {
 	bool downgraded;
 };
 
-DECLARE_EWMA(beacon_signal, 16, 4)
+DECLARE_EWMA(beacon_signal, 4, 4)
 
 struct ieee80211_if_managed {
 	struct timer_list timer;
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 15599c70a38f..e65cda34d2bc 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -372,7 +372,7 @@ struct mesh_sta {
 	unsigned int fail_avg;
 };
 
-DECLARE_EWMA(signal, 1024, 8)
+DECLARE_EWMA(signal, 10, 8)
 
 struct ieee80211_sta_rx_stats {
 	unsigned long packets;
-- 
GitLab


From 9ccd27cc2e8bfbec502d7c64a353dc4489536b81 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 21:11:09 +0100
Subject: [PATCH 465/898] sched/headers: Make all include/linux/sched/*.h
 headers build standalone

Make each header self-sufficient, so that it can be built successfully
both in an allnoconfig and allyesconfig kernel.

Also standardize the naming of their header guards.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/deadline.h |  8 +++++---
 include/linux/sched/prio.h     |  6 +++---
 include/linux/sched/rt.h       | 10 ++++++----
 include/linux/sched/sysctl.h   | 10 +++++++---
 4 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 9089a2ae913d..975be862e083 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -1,5 +1,7 @@
-#ifndef _SCHED_DEADLINE_H
-#define _SCHED_DEADLINE_H
+#ifndef _LINUX_SCHED_DEADLINE_H
+#define _LINUX_SCHED_DEADLINE_H
+
+#include <linux/sched.h>
 
 /*
  * SCHED_DEADLINE tasks has negative priorities, reflecting
@@ -26,4 +28,4 @@ static inline bool dl_time_before(u64 a, u64 b)
 	return (s64)(a - b) < 0;
 }
 
-#endif /* _SCHED_DEADLINE_H */
+#endif /* _LINUX_SCHED_DEADLINE_H */
diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
index d9cf5a5762d9..2cc450f6ec54 100644
--- a/include/linux/sched/prio.h
+++ b/include/linux/sched/prio.h
@@ -1,5 +1,5 @@
-#ifndef _SCHED_PRIO_H
-#define _SCHED_PRIO_H
+#ifndef _LINUX_SCHED_PRIO_H
+#define _LINUX_SCHED_PRIO_H
 
 #define MAX_NICE	19
 #define MIN_NICE	-20
@@ -57,4 +57,4 @@ static inline long rlimit_to_nice(long prio)
 	return (MAX_NICE - prio + 1);
 }
 
-#endif /* _SCHED_PRIO_H */
+#endif /* _LINUX_SCHED_PRIO_H */
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index a30b172df6e1..3bd668414f61 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -1,7 +1,9 @@
-#ifndef _SCHED_RT_H
-#define _SCHED_RT_H
+#ifndef _LINUX_SCHED_RT_H
+#define _LINUX_SCHED_RT_H
 
-#include <linux/sched/prio.h>
+#include <linux/sched.h>
+
+struct task_struct;
 
 static inline int rt_prio(int prio)
 {
@@ -57,4 +59,4 @@ extern void normalize_rt_tasks(void);
  */
 #define RR_TIMESLICE		(100 * HZ / 1000)
 
-#endif /* _SCHED_RT_H */
+#endif /* _LINUX_SCHED_RT_H */
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 49308e142aae..0f5ecd4d298e 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -1,5 +1,9 @@
-#ifndef _SCHED_SYSCTL_H
-#define _SCHED_SYSCTL_H
+#ifndef _LINUX_SCHED_SYSCTL_H
+#define _LINUX_SCHED_SYSCTL_H
+
+#include <linux/types.h>
+
+struct ctl_table;
 
 #ifdef CONFIG_DETECT_HUNG_TASK
 extern int	     sysctl_hung_task_check_count;
@@ -78,4 +82,4 @@ extern int sysctl_schedstats(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos);
 
-#endif /* _SCHED_SYSCTL_H */
+#endif /* _LINUX_SCHED_SYSCTL_H */
-- 
GitLab


From c930b2c0de32f45ce8f67affe936ce7a05b07b00 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 12:22:54 +0100
Subject: [PATCH 466/898] sched/core: Convert ___assert_task_state() link time
 assert to BUILD_BUG_ON()

The length of TASK_STATE_TO_CHAR_STR was still checked using the old
link-time manual error method - convert it to BUILD_BUG_ON(). This
has a couple of advantages:

 - it's more obvious what's going on

 - it reduces the size and complexity of <linux/sched.h>

 - BUILD_BUG_ON() will fail during compilation, with a clearer
   error message than the link time assert.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 3 ---
 kernel/sched/core.c   | 3 +++
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4a28deb5f210..c204613396cd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -223,9 +223,6 @@ extern void proc_sched_set_task(struct task_struct *p);
 
 #define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn"
 
-extern char ___assert_task_state[1 - 2*!!(
-		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
-
 /* Convenience macros for the sake of set_current_state */
 #define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
 #define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bbfb917a9b49..7d76ccb79e91 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5233,6 +5233,9 @@ void sched_show_task(struct task_struct *p)
 	int ppid;
 	unsigned long state = p->state;
 
+	/* Make sure the string lines up properly with the number of task states: */
+	BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1);
+
 	if (!try_get_task_stack(p))
 		return;
 	if (state)
-- 
GitLab


From 59ddbcb2f45b958cf1f11f122b666cbcf50cd57b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 23:37:48 +0100
Subject: [PATCH 467/898] sched/core: Move the get_preempt_disable_ip() inline
 to sched/core.c

It's defined in <linux/sched.h>, but nothing outside the scheduler
uses it - so move it to the sched/core.c usage site.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 9 ---------
 kernel/sched/core.c   | 9 +++++++++
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c204613396cd..df42cac04243 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3419,15 +3419,6 @@ static inline void cond_resched_rcu(void)
 #endif
 }
 
-static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
-{
-#ifdef CONFIG_DEBUG_PREEMPT
-	return p->preempt_disable_ip;
-#else
-	return 0;
-#endif
-}
-
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPT,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7d76ccb79e91..2acdf19c5f7c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3211,6 +3211,15 @@ static inline void preempt_latency_start(int val) { }
 static inline void preempt_latency_stop(int val) { }
 #endif
 
+static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	return p->preempt_disable_ip;
+#else
+	return 0;
+#endif
+}
+
 /*
  * Print scheduling while atomic bug:
  */
-- 
GitLab


From 0c98d344fe5c27f6e4bce42ac503e9e9a51c7d1d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 15:38:10 +0100
Subject: [PATCH 468/898] sched/core: Remove the tsk_cpus_allowed() wrapper

So the original intention of tsk_cpus_allowed() was to 'future-proof'
the field - but it's pretty ineffectual at that, because half of
the code uses ->cpus_allowed directly ...

Also, the wrapper makes the code longer than the original expression!

So just get rid of it. This also shrinks <linux/sched.h> a bit.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/kernel/smp.c                  |  2 +-
 arch/powerpc/platforms/cell/spufs/sched.c  |  2 +-
 arch/sparc/kernel/sysfs.c                  |  2 +-
 drivers/cpufreq/sparc-us2e-cpufreq.c       |  4 ++--
 drivers/cpufreq/sparc-us3-cpufreq.c        |  4 ++--
 drivers/infiniband/hw/hfi1/affinity.c      |  2 +-
 drivers/infiniband/hw/hfi1/sdma.c          |  2 +-
 include/linux/sched.h                      |  3 ---
 kernel/sched/core.c                        | 20 ++++++++---------
 kernel/sched/cpudeadline.c                 |  4 ++--
 kernel/sched/cpupri.c                      |  4 ++--
 kernel/sched/deadline.c                    |  7 +++---
 kernel/sched/fair.c                        | 25 +++++++++++-----------
 kernel/sched/rt.c                          |  5 ++---
 lib/smp_processor_id.c                     |  2 +-
 samples/trace_events/trace-events-sample.c |  2 +-
 16 files changed, 42 insertions(+), 48 deletions(-)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 573fb3a461b5..21fdf02583fe 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -795,7 +795,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	 * se we pin us down to CPU 0 for a short while
 	 */
 	alloc_cpumask_var(&old_mask, GFP_NOWAIT);
-	cpumask_copy(old_mask, tsk_cpus_allowed(current));
+	cpumask_copy(old_mask, &current->cpus_allowed);
 	set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
 	
 	if (smp_ops && smp_ops->setup_cpu)
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 460f5f31d5cb..9b543df210fb 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -140,7 +140,7 @@ void __spu_update_sched_info(struct spu_context *ctx)
 	 * runqueue. The context will be rescheduled on the proper node
 	 * if it is timesliced or preempted.
 	 */
-	cpumask_copy(&ctx->cpus_allowed, tsk_cpus_allowed(current));
+	cpumask_copy(&ctx->cpus_allowed, &current->cpus_allowed);
 
 	/* Save the current cpu id for spu interrupt routing. */
 	ctx->last_ran = raw_smp_processor_id();
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index 4808b6d23455..d63fc613e7a9 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -106,7 +106,7 @@ static unsigned long run_on_cpu(unsigned long cpu,
 	cpumask_t old_affinity;
 	unsigned long ret;
 
-	cpumask_copy(&old_affinity, tsk_cpus_allowed(current));
+	cpumask_copy(&old_affinity, &current->cpus_allowed);
 	/* should return -EINVAL to userspace */
 	if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
 		return 0;
diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c
index b73feeb666f9..35ddb6da93aa 100644
--- a/drivers/cpufreq/sparc-us2e-cpufreq.c
+++ b/drivers/cpufreq/sparc-us2e-cpufreq.c
@@ -234,7 +234,7 @@ static unsigned int us2e_freq_get(unsigned int cpu)
 	cpumask_t cpus_allowed;
 	unsigned long clock_tick, estar;
 
-	cpumask_copy(&cpus_allowed, tsk_cpus_allowed(current));
+	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
 	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	clock_tick = sparc64_get_clock_tick(cpu) / 1000;
@@ -252,7 +252,7 @@ static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
 	unsigned long clock_tick, divisor, old_divisor, estar;
 	cpumask_t cpus_allowed;
 
-	cpumask_copy(&cpus_allowed, tsk_cpus_allowed(current));
+	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
 	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	new_freq = clock_tick = sparc64_get_clock_tick(cpu) / 1000;
diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c
index 9bb42ba50efa..a8d86a449ca1 100644
--- a/drivers/cpufreq/sparc-us3-cpufreq.c
+++ b/drivers/cpufreq/sparc-us3-cpufreq.c
@@ -82,7 +82,7 @@ static unsigned int us3_freq_get(unsigned int cpu)
 	unsigned long reg;
 	unsigned int ret;
 
-	cpumask_copy(&cpus_allowed, tsk_cpus_allowed(current));
+	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
 	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	reg = read_safari_cfg();
@@ -99,7 +99,7 @@ static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index)
 	unsigned long new_bits, new_freq, reg;
 	cpumask_t cpus_allowed;
 
-	cpumask_copy(&cpus_allowed, tsk_cpus_allowed(current));
+	cpumask_copy(&cpus_allowed, &current->cpus_allowed);
 	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
 	new_freq = sparc64_get_clock_tick(cpu) / 1000;
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 7a3d906b3671..e2cd2cd3b28a 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -576,7 +576,7 @@ int hfi1_get_proc_affinity(int node)
 	struct hfi1_affinity_node *entry;
 	cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask;
 	const struct cpumask *node_mask,
-		*proc_mask = tsk_cpus_allowed(current);
+		*proc_mask = &current->cpus_allowed;
 	struct hfi1_affinity_node_list *affinity = &node_affinity;
 	struct cpu_mask_set *set = &affinity->proc;
 
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 1d81cac1fa6c..5cde1ecda0fe 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -856,7 +856,7 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd,
 {
 	struct sdma_rht_node *rht_node;
 	struct sdma_engine *sde = NULL;
-	const struct cpumask *current_mask = tsk_cpus_allowed(current);
+	const struct cpumask *current_mask = &current->cpus_allowed;
 	unsigned long cpu_id;
 
 	/*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index df42cac04243..6d1cc20cc477 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1995,9 +1995,6 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
 }
 #endif
 
-/* Future-safe accessor for struct task_struct's cpus_allowed. */
-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
-
 static inline int tsk_nr_cpus_allowed(struct task_struct *p)
 {
 	return p->nr_cpus_allowed;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2acdf19c5f7c..ef5bbf760a08 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -981,7 +981,7 @@ static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_
 		return rq;
 
 	/* Affinity changed (again). */
-	if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
+	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
 		return rq;
 
 	rq = move_queued_task(rq, p, dest_cpu);
@@ -1259,10 +1259,10 @@ static int migrate_swap_stop(void *data)
 	if (task_cpu(arg->src_task) != arg->src_cpu)
 		goto unlock;
 
-	if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task)))
+	if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed))
 		goto unlock;
 
-	if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task)))
+	if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed))
 		goto unlock;
 
 	__migrate_swap_task(arg->src_task, arg->dst_cpu);
@@ -1303,10 +1303,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
 	if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
 		goto out;
 
-	if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task)))
+	if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed))
 		goto out;
 
-	if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
+	if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed))
 		goto out;
 
 	trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
@@ -1490,14 +1490,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		for_each_cpu(dest_cpu, nodemask) {
 			if (!cpu_active(dest_cpu))
 				continue;
-			if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
+			if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
 				return dest_cpu;
 		}
 	}
 
 	for (;;) {
 		/* Any allowed, online CPU? */
-		for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
+		for_each_cpu(dest_cpu, &p->cpus_allowed) {
 			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
 				continue;
 			if (!cpu_online(dest_cpu))
@@ -1552,7 +1552,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	if (tsk_nr_cpus_allowed(p) > 1)
 		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 	else
-		cpu = cpumask_any(tsk_cpus_allowed(p));
+		cpu = cpumask_any(&p->cpus_allowed);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -1564,7 +1564,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	 * [ this allows ->select_task() to simply return task_cpu(p) and
 	 *   not worry about this generic constraint ]
 	 */
-	if (unlikely(!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) ||
+	if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
 		     !cpu_online(cpu)))
 		cpu = select_fallback_rq(task_cpu(p), p);
 
@@ -5473,7 +5473,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (curr_cpu == target_cpu)
 		return 0;
 
-	if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p)))
+	if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed))
 		return -EINVAL;
 
 	/* TODO: This is not properly updating schedstats */
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index e73119013c53..fba235c7d026 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -128,10 +128,10 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	const struct sched_dl_entity *dl_se = &p->dl;
 
 	if (later_mask &&
-	    cpumask_and(later_mask, cp->free_cpus, tsk_cpus_allowed(p))) {
+	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
 		best_cpu = cpumask_any(later_mask);
 		goto out;
-	} else if (cpumask_test_cpu(cpudl_maximum(cp), tsk_cpus_allowed(p)) &&
+	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
 			dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
 		best_cpu = cpudl_maximum(cp);
 		if (later_mask)
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 11e9705bf937..981fcd7dc394 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -103,11 +103,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 		if (skip)
 			continue;
 
-		if (cpumask_any_and(tsk_cpus_allowed(p), vec->mask) >= nr_cpu_ids)
+		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
 			continue;
 
 		if (lowest_mask) {
-			cpumask_and(lowest_mask, tsk_cpus_allowed(p), vec->mask);
+			cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
 
 			/*
 			 * We have to ensure that we have at least one bit
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 27737f34757d..8e4d6e4e3ccc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -252,7 +252,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 		 * If we cannot preempt any rq, fall back to pick any
 		 * online cpu.
 		 */
-		cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p));
+		cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
 		if (cpu >= nr_cpu_ids) {
 			/*
 			 * Fail to find any suitable cpu.
@@ -1235,7 +1235,7 @@ static void set_curr_task_dl(struct rq *rq)
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
+	    cpumask_test_cpu(cpu, &p->cpus_allowed))
 		return 1;
 	return 0;
 }
@@ -1384,8 +1384,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 		/* Retry if something changed. */
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(later_rq->cpu,
-						       tsk_cpus_allowed(task)) ||
+				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) ||
 				     task_running(rq, task) ||
 				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 274c747a01ce..3b60d73ab290 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1551,7 +1551,7 @@ static void task_numa_compare(struct task_numa_env *env,
 	 */
 	if (cur) {
 		/* Skip this swap candidate if cannot move to the source cpu */
-		if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur)))
+		if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
 			goto unlock;
 
 		/*
@@ -1661,7 +1661,7 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 
 	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
 		/* Skip this CPU if the source task cannot migrate */
-		if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p)))
+		if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
 			continue;
 
 		env->dst_cpu = cpu;
@@ -5458,7 +5458,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 
 		/* Skip over this group if it has no CPUs allowed */
 		if (!cpumask_intersects(sched_group_cpus(group),
-					tsk_cpus_allowed(p)))
+					&p->cpus_allowed))
 			continue;
 
 		local_group = cpumask_test_cpu(this_cpu,
@@ -5578,7 +5578,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 		return cpumask_first(sched_group_cpus(group));
 
 	/* Traverse only the allowed CPUs */
-	for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
+	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
 		if (idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5717,7 +5717,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 	if (!test_idle_cores(target, false))
 		return -1;
 
-	cpumask_and(cpus, sched_domain_span(sd), tsk_cpus_allowed(p));
+	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
 
 	for_each_cpu_wrap(core, cpus, target, wrap) {
 		bool idle = true;
@@ -5751,7 +5751,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
 		return -1;
 
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
-		if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
+		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
 			return cpu;
@@ -5803,7 +5803,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	time = local_clock();
 
 	for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
-		if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
+		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
 			break;
@@ -5958,7 +5958,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	if (sd_flag & SD_BALANCE_WAKE) {
 		record_wakee(p);
 		want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
-			      && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
+			      && cpumask_test_cpu(cpu, &p->cpus_allowed);
 	}
 
 	rcu_read_lock();
@@ -6698,7 +6698,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
 		return 0;
 
-	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
+	if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) {
 		int cpu;
 
 		schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
@@ -6718,7 +6718,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 
 		/* Prevent to re-select dst_cpu via env's cpus */
 		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
-			if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
+			if (cpumask_test_cpu(cpu, &p->cpus_allowed)) {
 				env->flags |= LBF_DST_PINNED;
 				env->new_dst_cpu = cpu;
 				break;
@@ -7252,7 +7252,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 
 /*
  * Group imbalance indicates (and tries to solve) the problem where balancing
- * groups is inadequate due to tsk_cpus_allowed() constraints.
+ * groups is inadequate due to ->cpus_allowed constraints.
  *
  * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a
  * cpumask covering 1 cpu of the first group and 3 cpus of the second group.
@@ -8211,8 +8211,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			 * if the curr task on busiest cpu can't be
 			 * moved to this_cpu
 			 */
-			if (!cpumask_test_cpu(this_cpu,
-					tsk_cpus_allowed(busiest->curr))) {
+			if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
 				raw_spin_unlock_irqrestore(&busiest->lock,
 							    flags);
 				env.flags |= LBF_ALL_PINNED;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e8836cfc4cdb..cbd356f63883 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1591,7 +1591,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
+	    cpumask_test_cpu(cpu, &p->cpus_allowed))
 		return 1;
 	return 0;
 }
@@ -1726,8 +1726,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * Also make sure that it wasn't scheduled on its rq.
 			 */
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(lowest_rq->cpu,
-						       tsk_cpus_allowed(task)) ||
+				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) ||
 				     task_running(rq, task) ||
 				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 1afec32de6f2..690d75b132fa 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -22,7 +22,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1,
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	if (cpumask_equal(tsk_cpus_allowed(current), cpumask_of(this_cpu)))
+	if (cpumask_equal(&current->cpus_allowed, cpumask_of(this_cpu)))
 		goto out;
 
 	/*
diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c
index 30e282d33d4d..bc7fcf010a5b 100644
--- a/samples/trace_events/trace-events-sample.c
+++ b/samples/trace_events/trace-events-sample.c
@@ -33,7 +33,7 @@ static void simple_thread_func(int cnt)
 
 	/* Silly tracepoints */
 	trace_foo_bar("hello", cnt, array, random_strings[len],
-		      tsk_cpus_allowed(current));
+		      &current->cpus_allowed);
 
 	trace_foo_with_template_simple("HELLO", cnt);
 
-- 
GitLab


From 4b53a3412d6663214ce9c754eff9373a9cff9dee Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 15:41:03 +0100
Subject: [PATCH 469/898] sched/core: Remove the tsk_nr_cpus_allowed() wrapper

tsk_nr_cpus_allowed() too is a pretty pointless wrapper that
is not used consistently and which makes the code both harder
to read and longer as well.

So remove it - this also shrinks <linux/sched.h> a bit.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h   |  5 -----
 kernel/sched/core.c     |  2 +-
 kernel/sched/deadline.c | 28 ++++++++++++++--------------
 kernel/sched/rt.c       | 24 ++++++++++++------------
 4 files changed, 27 insertions(+), 32 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6d1cc20cc477..e732881517f2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1995,11 +1995,6 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
 }
 #endif
 
-static inline int tsk_nr_cpus_allowed(struct task_struct *p)
-{
-	return p->nr_cpus_allowed;
-}
-
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
 #define TNF_SHARED	0x04
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ef5bbf760a08..2d51ec65dc73 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1549,7 +1549,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 {
 	lockdep_assert_held(&p->pi_lock);
 
-	if (tsk_nr_cpus_allowed(p) > 1)
+	if (p->nr_cpus_allowed > 1)
 		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 	else
 		cpu = cpumask_any(&p->cpus_allowed);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8e4d6e4e3ccc..99b2c33a9fbc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -134,7 +134,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
 
-	if (tsk_nr_cpus_allowed(p) > 1)
+	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory++;
 
 	update_dl_migration(dl_rq);
@@ -144,7 +144,7 @@ static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
 
-	if (tsk_nr_cpus_allowed(p) > 1)
+	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory--;
 
 	update_dl_migration(dl_rq);
@@ -958,7 +958,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 	enqueue_dl_entity(&p->dl, pi_se, flags);
 
-	if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1)
+	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
 }
 
@@ -1032,9 +1032,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	 * try to make it stay here, it might be important.
 	 */
 	if (unlikely(dl_task(curr)) &&
-	    (tsk_nr_cpus_allowed(curr) < 2 ||
+	    (curr->nr_cpus_allowed < 2 ||
 	     !dl_entity_preempt(&p->dl, &curr->dl)) &&
-	    (tsk_nr_cpus_allowed(p) > 1)) {
+	    (p->nr_cpus_allowed > 1)) {
 		int target = find_later_rq(p);
 
 		if (target != -1 &&
@@ -1055,7 +1055,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	 * Current can't be migrated, useless to reschedule,
 	 * let's hope p can move out.
 	 */
-	if (tsk_nr_cpus_allowed(rq->curr) == 1 ||
+	if (rq->curr->nr_cpus_allowed == 1 ||
 	    cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
 		return;
 
@@ -1063,7 +1063,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	 * p is migratable, so let's not schedule it and
 	 * see if it is pushed or pulled somewhere else.
 	 */
-	if (tsk_nr_cpus_allowed(p) != 1 &&
+	if (p->nr_cpus_allowed != 1 &&
 	    cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
 		return;
 
@@ -1178,7 +1178,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
 	update_curr_dl(rq);
 
-	if (on_dl_rq(&p->dl) && tsk_nr_cpus_allowed(p) > 1)
+	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
 }
 
@@ -1279,7 +1279,7 @@ static int find_later_rq(struct task_struct *task)
 	if (unlikely(!later_mask))
 		return -1;
 
-	if (tsk_nr_cpus_allowed(task) == 1)
+	if (task->nr_cpus_allowed == 1)
 		return -1;
 
 	/*
@@ -1424,7 +1424,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
 
 	BUG_ON(rq->cpu != task_cpu(p));
 	BUG_ON(task_current(rq, p));
-	BUG_ON(tsk_nr_cpus_allowed(p) <= 1);
+	BUG_ON(p->nr_cpus_allowed <= 1);
 
 	BUG_ON(!task_on_rq_queued(p));
 	BUG_ON(!dl_task(p));
@@ -1463,7 +1463,7 @@ static int push_dl_task(struct rq *rq)
 	 */
 	if (dl_task(rq->curr) &&
 	    dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
-	    tsk_nr_cpus_allowed(rq->curr) > 1) {
+	    rq->curr->nr_cpus_allowed > 1) {
 		resched_curr(rq);
 		return 0;
 	}
@@ -1610,9 +1610,9 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 {
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
-	    tsk_nr_cpus_allowed(p) > 1 &&
+	    p->nr_cpus_allowed > 1 &&
 	    dl_task(rq->curr) &&
-	    (tsk_nr_cpus_allowed(rq->curr) < 2 ||
+	    (rq->curr->nr_cpus_allowed < 2 ||
 	     !dl_entity_preempt(&p->dl, &rq->curr->dl))) {
 		push_dl_tasks(rq);
 	}
@@ -1726,7 +1726,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 
 	if (rq->curr != p) {
 #ifdef CONFIG_SMP
-		if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded)
+		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
 			queue_push_tasks(rq);
 #endif
 		if (dl_task(rq->curr))
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index cbd356f63883..9f3e40226dec 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -335,7 +335,7 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
 
 	rt_rq->rt_nr_total++;
-	if (tsk_nr_cpus_allowed(p) > 1)
+	if (p->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory++;
 
 	update_rt_migration(rt_rq);
@@ -352,7 +352,7 @@ static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
 
 	rt_rq->rt_nr_total--;
-	if (tsk_nr_cpus_allowed(p) > 1)
+	if (p->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory--;
 
 	update_rt_migration(rt_rq);
@@ -1324,7 +1324,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 
 	enqueue_rt_entity(rt_se, flags);
 
-	if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1)
+	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 
@@ -1413,7 +1413,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 	 * will have to sort it out.
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
-	    (tsk_nr_cpus_allowed(curr) < 2 ||
+	    (curr->nr_cpus_allowed < 2 ||
 	     curr->prio <= p->prio)) {
 		int target = find_lowest_rq(p);
 
@@ -1437,7 +1437,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 * Current can't be migrated, useless to reschedule,
 	 * let's hope p can move out.
 	 */
-	if (tsk_nr_cpus_allowed(rq->curr) == 1 ||
+	if (rq->curr->nr_cpus_allowed == 1 ||
 	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
 		return;
 
@@ -1445,7 +1445,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 * p is migratable, so let's not schedule it and
 	 * see if it is pushed or pulled somewhere else.
 	 */
-	if (tsk_nr_cpus_allowed(p) != 1
+	if (p->nr_cpus_allowed != 1
 	    && cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
@@ -1579,7 +1579,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
 	 */
-	if (on_rt_rq(&p->rt) && tsk_nr_cpus_allowed(p) > 1)
+	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 
@@ -1629,7 +1629,7 @@ static int find_lowest_rq(struct task_struct *task)
 	if (unlikely(!lowest_mask))
 		return -1;
 
-	if (tsk_nr_cpus_allowed(task) == 1)
+	if (task->nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
 	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
@@ -1761,7 +1761,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
 
 	BUG_ON(rq->cpu != task_cpu(p));
 	BUG_ON(task_current(rq, p));
-	BUG_ON(tsk_nr_cpus_allowed(p) <= 1);
+	BUG_ON(p->nr_cpus_allowed <= 1);
 
 	BUG_ON(!task_on_rq_queued(p));
 	BUG_ON(!rt_task(p));
@@ -2121,9 +2121,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 {
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
-	    tsk_nr_cpus_allowed(p) > 1 &&
+	    p->nr_cpus_allowed > 1 &&
 	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
-	    (tsk_nr_cpus_allowed(rq->curr) < 2 ||
+	    (rq->curr->nr_cpus_allowed < 2 ||
 	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
 }
@@ -2196,7 +2196,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 */
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
-		if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded)
+		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
 			queue_push_tasks(rq);
 #endif /* CONFIG_SMP */
 		if (p->prio < rq->curr->prio)
-- 
GitLab


From f9411ebe3d85cbbea06298241e6053d031d281fc Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 09:50:49 +0100
Subject: [PATCH 470/898] rcu: Separate the RCU synchronization types and APIs
 into <linux/rcupdate_wait.h>

So rcupdate.h is a pretty complex header, in particular it includes
<linux/completion.h> which includes <linux/wait.h> - creating a
dependency that includes <linux/wait.h> in <linux/sched.h>,
which prevents the isolation of <linux/sched.h> from the derived
<linux/wait.h> header.

Solve part of the problem by decoupling rcupdate.h from completions:
this can be done by separating out the rcu_synchronize types and APIs,
and updating their usage sites.

Since this is a mostly RCU-internal types this will not just simplify
<linux/sched.h>'s dependencies, but will make all the hundreds of
.c files that include rcupdate.h but not completions or wait.h build
faster.

( For rcutiny this means that two dependent APIs have to be uninlined,
  but that shouldn't be much of a problem as they are rare variants. )

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/autofs4/autofs_i.h         |  1 +
 include/linux/dcache.h        |  1 +
 include/linux/rcupdate.h      | 40 ----------------------------
 include/linux/rcupdate_wait.h | 50 +++++++++++++++++++++++++++++++++++
 include/linux/rcutiny.h       | 11 ++------
 kernel/rcu/srcu.c             |  2 +-
 kernel/rcu/tiny.c             | 14 +++++++++-
 kernel/rcu/tree.c             |  2 +-
 kernel/rcu/update.c           |  1 +
 kernel/sched/core.c           |  1 +
 10 files changed, 71 insertions(+), 52 deletions(-)
 create mode 100644 include/linux/rcupdate_wait.h

diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c885daae68c8..beef981aa54f 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -14,6 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/completion.h>
 
 /* This is the range of ioctl() numbers we claim as ours */
 #define AUTOFS_IOC_FIRST     AUTOFS_IOC_READY
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 591b6c16f9c1..d2e38dc6172c 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -11,6 +11,7 @@
 #include <linux/rcupdate.h>
 #include <linux/lockref.h>
 #include <linux/stringhash.h>
+#include <linux/wait.h>
 
 struct path;
 struct vfsmount;
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6ade6a52d9d4..de88b33c0974 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,7 +40,6 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 #include <linux/lockdep.h>
-#include <linux/completion.h>
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
@@ -226,45 +225,6 @@ void call_rcu_sched(struct rcu_head *head,
 
 void synchronize_sched(void);
 
-/*
- * Structure allowing asynchronous waiting on RCU.
- */
-struct rcu_synchronize {
-	struct rcu_head head;
-	struct completion completion;
-};
-void wakeme_after_rcu(struct rcu_head *head);
-
-void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
-		   struct rcu_synchronize *rs_array);
-
-#define _wait_rcu_gp(checktiny, ...) \
-do {									\
-	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };		\
-	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];	\
-	__wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array),		\
-			__crcu_array, __rs_array);			\
-} while (0)
-
-#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
-
-/**
- * synchronize_rcu_mult - Wait concurrently for multiple grace periods
- * @...: List of call_rcu() functions for the flavors to wait on.
- *
- * This macro waits concurrently for multiple flavors of RCU grace periods.
- * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait
- * on concurrent RCU and RCU-bh grace periods.  Waiting on a give SRCU
- * domain requires you to write a wrapper function for that SRCU domain's
- * call_srcu() function, supplying the corresponding srcu_struct.
- *
- * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU
- * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called
- * is automatically a grace period.
- */
-#define synchronize_rcu_mult(...) \
-	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
-
 /**
  * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
  * @head: structure to be used for queueing the RCU updates.
diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h
new file mode 100644
index 000000000000..e774b4f5f220
--- /dev/null
+++ b/include/linux/rcupdate_wait.h
@@ -0,0 +1,50 @@
+#ifndef _LINUX_SCHED_RCUPDATE_WAIT_H
+#define _LINUX_SCHED_RCUPDATE_WAIT_H
+
+/*
+ * RCU synchronization types and methods:
+ */
+
+#include <linux/rcupdate.h>
+#include <linux/completion.h>
+
+/*
+ * Structure allowing asynchronous waiting on RCU.
+ */
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
+void wakeme_after_rcu(struct rcu_head *head);
+
+void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
+		   struct rcu_synchronize *rs_array);
+
+#define _wait_rcu_gp(checktiny, ...) \
+do {									\
+	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };		\
+	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];	\
+	__wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array),		\
+			__crcu_array, __rs_array);			\
+} while (0)
+
+#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
+
+/**
+ * synchronize_rcu_mult - Wait concurrently for multiple grace periods
+ * @...: List of call_rcu() functions for the flavors to wait on.
+ *
+ * This macro waits concurrently for multiple flavors of RCU grace periods.
+ * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait
+ * on concurrent RCU and RCU-bh grace periods.  Waiting on a give SRCU
+ * domain requires you to write a wrapper function for that SRCU domain's
+ * call_srcu() function, supplying the corresponding srcu_struct.
+ *
+ * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU
+ * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called
+ * is automatically a grace period.
+ */
+#define synchronize_rcu_mult(...) \
+	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
+
+#endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 4f9b2fa2173d..b452953e21c8 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -53,15 +53,8 @@ static inline void cond_synchronize_sched(unsigned long oldstate)
 	might_sleep();
 }
 
-static inline void rcu_barrier_bh(void)
-{
-	wait_rcu_gp(call_rcu_bh);
-}
-
-static inline void rcu_barrier_sched(void)
-{
-	wait_rcu_gp(call_rcu_sched);
-}
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
 
 static inline void synchronize_rcu_expedited(void)
 {
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index e773129c8b08..ef3bcfb15b39 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -30,7 +30,7 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/preempt.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/delay.h>
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index fa6a48d3917b..6ad330dbbae2 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -25,7 +25,7 @@
 #include <linux/completion.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
@@ -47,6 +47,18 @@ static void __call_rcu(struct rcu_head *head,
 
 #include "tiny_plugin.h"
 
+void rcu_barrier_bh(void)
+{
+	wait_rcu_gp(call_rcu_bh);
+}
+EXPORT_SYMBOL(rcu_barrier_bh);
+
+void rcu_barrier_sched(void)
+{
+	wait_rcu_gp(call_rcu_sched);
+}
+EXPORT_SYMBOL(rcu_barrier_sched);
+
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d80e0d2f68c6..cb62ce23ffc7 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -32,7 +32,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/nmi.h>
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 9e03db9ea9c0..a0e90e0afc75 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -49,6 +49,7 @@
 #include <linux/moduleparam.h>
 #include <linux/kthread.h>
 #include <linux/tick.h>
+#include <linux/rcupdate_wait.h>
 
 #define CREATE_TRACE_POINTS
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d51ec65dc73..1bd317db9810 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10,6 +10,7 @@
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
 #include <linux/context_tracking.h>
+#include <linux/rcupdate_wait.h>
 
 #include <linux/blkdev.h>
 #include <linux/kprobes.h>
-- 
GitLab


From 780de9dd2720debc14c501dab4dc80d1f75ad50e Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 11:50:56 +0100
Subject: [PATCH 471/898] sched/headers, cgroups: Remove the
 threadgroup_change_*() wrappery

threadgroup_change_begin()/end() is a pointless wrapper around
cgroup_threadgroup_change_begin()/end(), minus a might_sleep()
in the !CONFIG_CGROUPS=y case.

Remove the wrappery, move the might_sleep() (the down_read()
already has a might_sleep() check).

This debloats <linux/sched.h> a bit and simplifies this API.

Update all call sites.

No change in functionality.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/exec.c                   |  6 +++---
 include/linux/cgroup-defs.h | 13 ++++++++-----
 include/linux/sched.h       | 28 ----------------------------
 kernel/cgroup/pids.c        |  2 +-
 kernel/fork.c               |  6 +++---
 kernel/signal.c             |  6 +++---
 6 files changed, 18 insertions(+), 43 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 698a86094f76..e595e1529581 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1088,7 +1088,7 @@ static int de_thread(struct task_struct *tsk)
 		struct task_struct *leader = tsk->group_leader;
 
 		for (;;) {
-			threadgroup_change_begin(tsk);
+			cgroup_threadgroup_change_begin(tsk);
 			write_lock_irq(&tasklist_lock);
 			/*
 			 * Do this under tasklist_lock to ensure that
@@ -1099,7 +1099,7 @@ static int de_thread(struct task_struct *tsk)
 				break;
 			__set_current_state(TASK_KILLABLE);
 			write_unlock_irq(&tasklist_lock);
-			threadgroup_change_end(tsk);
+			cgroup_threadgroup_change_end(tsk);
 			schedule();
 			if (unlikely(__fatal_signal_pending(tsk)))
 				goto killed;
@@ -1157,7 +1157,7 @@ static int de_thread(struct task_struct *tsk)
 		if (unlikely(leader->ptrace))
 			__wake_up_parent(leader, leader->parent);
 		write_unlock_irq(&tasklist_lock);
-		threadgroup_change_end(tsk);
+		cgroup_threadgroup_change_end(tsk);
 
 		release_task(leader);
 	}
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 3c02404cfce9..6a3f850cabab 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -531,8 +531,8 @@ extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
  * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
  * @tsk: target task
  *
- * Called from threadgroup_change_begin() and allows cgroup operations to
- * synchronize against threadgroup changes using a percpu_rw_semaphore.
+ * Allows cgroup operations to synchronize against threadgroup changes
+ * using a percpu_rw_semaphore.
  */
 static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
 {
@@ -543,8 +543,7 @@ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
  * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups
  * @tsk: target task
  *
- * Called from threadgroup_change_end().  Counterpart of
- * cgroup_threadcgroup_change_begin().
+ * Counterpart of cgroup_threadcgroup_change_begin().
  */
 static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
 {
@@ -555,7 +554,11 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
 
 #define CGROUP_SUBSYS_COUNT 0
 
-static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {}
+static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
+{
+	might_sleep();
+}
+
 static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
 
 #endif	/* CONFIG_CGROUPS */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e732881517f2..3f61baac928b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3162,34 +3162,6 @@ static inline void unlock_task_sighand(struct task_struct *tsk,
 	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
 }
 
-/**
- * threadgroup_change_begin - mark the beginning of changes to a threadgroup
- * @tsk: task causing the changes
- *
- * All operations which modify a threadgroup - a new thread joining the
- * group, death of a member thread (the assertion of PF_EXITING) and
- * exec(2) dethreading the process and replacing the leader - are wrapped
- * by threadgroup_change_{begin|end}().  This is to provide a place which
- * subsystems needing threadgroup stability can hook into for
- * synchronization.
- */
-static inline void threadgroup_change_begin(struct task_struct *tsk)
-{
-	might_sleep();
-	cgroup_threadgroup_change_begin(tsk);
-}
-
-/**
- * threadgroup_change_end - mark the end of changes to a threadgroup
- * @tsk: task causing the changes
- *
- * See threadgroup_change_begin().
- */
-static inline void threadgroup_change_end(struct task_struct *tsk)
-{
-	cgroup_threadgroup_change_end(tsk);
-}
-
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 
 static inline struct thread_info *task_thread_info(struct task_struct *task)
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index 2bd673783f1a..e756dae49300 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -214,7 +214,7 @@ static void pids_cancel_attach(struct cgroup_taskset *tset)
 
 /*
  * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
- * on threadgroup_change_begin() held by the copy_process().
+ * on cgroup_threadgroup_change_begin() held by the copy_process().
  */
 static int pids_can_fork(struct task_struct *task)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 246bf9aaf9df..d043fedc03c8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1746,7 +1746,7 @@ static __latent_entropy struct task_struct *copy_process(
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-	threadgroup_change_begin(current);
+	cgroup_threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
@@ -1843,7 +1843,7 @@ static __latent_entropy struct task_struct *copy_process(
 
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
-	threadgroup_change_end(current);
+	cgroup_threadgroup_change_end(current);
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
@@ -1854,7 +1854,7 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p);
 bad_fork_free_pid:
-	threadgroup_change_end(current);
+	cgroup_threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_thread:
diff --git a/kernel/signal.c b/kernel/signal.c
index 214a8feeb771..bae358532d0a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2395,11 +2395,11 @@ void exit_signals(struct task_struct *tsk)
 	 * @tsk is about to have PF_EXITING set - lock out users which
 	 * expect stable threadgroup.
 	 */
-	threadgroup_change_begin(tsk);
+	cgroup_threadgroup_change_begin(tsk);
 
 	if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) {
 		tsk->flags |= PF_EXITING;
-		threadgroup_change_end(tsk);
+		cgroup_threadgroup_change_end(tsk);
 		return;
 	}
 
@@ -2410,7 +2410,7 @@ void exit_signals(struct task_struct *tsk)
 	 */
 	tsk->flags |= PF_EXITING;
 
-	threadgroup_change_end(tsk);
+	cgroup_threadgroup_change_end(tsk);
 
 	if (!signal_pending(tsk))
 		goto out;
-- 
GitLab


From 314ff7851fc8ea66cbf48eaa93d8ebfb5ca084a9 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 11:03:31 +0100
Subject: [PATCH 472/898] mm/vmacache, sched/headers: Introduce 'struct
 vmacache' and move it from <linux/sched.h> to <linux/mm_types>

The <linux/sched.h> header includes various vmacache related defines,
which are arguably misplaced.

Move them to mm_types.h and minimize the sched.h impact by putting
all task vmacache state into a new 'struct vmacache' structure.

No change in functionality.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm_types.h  | 12 ++++++++++++
 include/linux/sched.h     | 11 ++++-------
 include/linux/vmacache.h  |  2 +-
 kernel/debug/debug_core.c |  4 ++--
 mm/nommu.c                |  2 +-
 mm/vmacache.c             | 10 +++++-----
 6 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4f6d440ad785..137797cd7b50 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -360,6 +360,18 @@ struct vm_area_struct {
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 };
 
+/*
+ * The per task VMA cache array:
+ */
+#define VMACACHE_BITS 2
+#define VMACACHE_SIZE (1U << VMACACHE_BITS)
+#define VMACACHE_MASK (VMACACHE_SIZE - 1)
+
+struct vmacache {
+	u32 seqnum;
+	struct vm_area_struct *vmas[VMACACHE_SIZE];
+};
+
 struct core_thread {
 	struct task_struct *task;
 	struct core_thread *next;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3f61baac928b..e87c97e1a947 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -134,10 +134,6 @@ struct blk_plug;
 struct filename;
 struct nameidata;
 
-#define VMACACHE_BITS 2
-#define VMACACHE_SIZE (1U << VMACACHE_BITS)
-#define VMACACHE_MASK (VMACACHE_SIZE - 1)
-
 /*
  * These are the constant used to fake the fixed-point load-average
  * counting. Some notes:
@@ -1550,9 +1546,10 @@ struct task_struct {
 #endif
 
 	struct mm_struct *mm, *active_mm;
-	/* per-thread vma caching */
-	u32 vmacache_seqnum;
-	struct vm_area_struct *vmacache[VMACACHE_SIZE];
+
+	/* Per-thread vma caching: */
+	struct vmacache vmacache;
+
 #if defined(SPLIT_RSS_COUNTING)
 	struct task_rss_stat	rss_stat;
 #endif
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
index c3fa0fd43949..1081db987391 100644
--- a/include/linux/vmacache.h
+++ b/include/linux/vmacache.h
@@ -12,7 +12,7 @@
 
 static inline void vmacache_flush(struct task_struct *tsk)
 {
-	memset(tsk->vmacache, 0, sizeof(tsk->vmacache));
+	memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas));
 }
 
 extern void vmacache_flush_all(struct mm_struct *mm);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 79517e5549f1..a603ef28f70c 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -232,9 +232,9 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
 		int i;
 
 		for (i = 0; i < VMACACHE_SIZE; i++) {
-			if (!current->vmacache[i])
+			if (!current->vmacache.vmas[i])
 				continue;
-			flush_cache_range(current->vmacache[i],
+			flush_cache_range(current->vmacache.vmas[i],
 					  addr, addr + BREAK_INSTR_SIZE);
 		}
 	}
diff --git a/mm/nommu.c b/mm/nommu.c
index fe9f4fa4a7a7..aae06e854552 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -757,7 +757,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	mm->map_count--;
 	for (i = 0; i < VMACACHE_SIZE; i++) {
 		/* if the vma is cached, invalidate the entire cache */
-		if (curr->vmacache[i] == vma) {
+		if (curr->vmacache.vmas[i] == vma) {
 			vmacache_invalidate(mm);
 			break;
 		}
diff --git a/mm/vmacache.c b/mm/vmacache.c
index 035fdeb35b43..7c233f8e20ee 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -60,7 +60,7 @@ static inline bool vmacache_valid_mm(struct mm_struct *mm)
 void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
 {
 	if (vmacache_valid_mm(newvma->vm_mm))
-		current->vmacache[VMACACHE_HASH(addr)] = newvma;
+		current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma;
 }
 
 static bool vmacache_valid(struct mm_struct *mm)
@@ -71,12 +71,12 @@ static bool vmacache_valid(struct mm_struct *mm)
 		return false;
 
 	curr = current;
-	if (mm->vmacache_seqnum != curr->vmacache_seqnum) {
+	if (mm->vmacache_seqnum != curr->vmacache.seqnum) {
 		/*
 		 * First attempt will always be invalid, initialize
 		 * the new cache for this task here.
 		 */
-		curr->vmacache_seqnum = mm->vmacache_seqnum;
+		curr->vmacache.seqnum = mm->vmacache_seqnum;
 		vmacache_flush(curr);
 		return false;
 	}
@@ -93,7 +93,7 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
 		return NULL;
 
 	for (i = 0; i < VMACACHE_SIZE; i++) {
-		struct vm_area_struct *vma = current->vmacache[i];
+		struct vm_area_struct *vma = current->vmacache.vmas[i];
 
 		if (!vma)
 			continue;
@@ -121,7 +121,7 @@ struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
 		return NULL;
 
 	for (i = 0; i < VMACACHE_SIZE; i++) {
-		struct vm_area_struct *vma = current->vmacache[i];
+		struct vm_area_struct *vma = current->vmacache.vmas[i];
 
 		if (vma && vma->vm_start == start && vma->vm_end == end) {
 			count_vm_vmacache_event(VMACACHE_FIND_HITS);
-- 
GitLab


From af8601ad420f6afa6445c927ad9f36d9700d96d6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 09:57:00 +0100
Subject: [PATCH 473/898] kasan, sched/headers: Uninline
 kasan_enable/disable_current()

<linux/kasan.h> is a low level header that is included early
in affected kernel headers. But it includes <linux/sched.h>
which complicates the cleanup of sched.h dependencies.

But kasan.h has almost no need for sched.h: its only use of
scheduler functionality is in two inline functions which are
not used very frequently - so uninline kasan_enable_current()
and kasan_disable_current().

Also add a <linux/sched.h> dependency to a .c file that depended
on kasan.h including it.

This paves the way to remove the <linux/sched.h> include from kasan.h.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kasan.h | 10 ++--------
 lib/sbitmap.c         |  1 +
 mm/kasan/kasan.c      | 10 ++++++++++
 3 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index c908b25bf5a5..7793036eac80 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -30,16 +30,10 @@ static inline void *kasan_mem_to_shadow(const void *addr)
 }
 
 /* Enable reporting bugs after kasan_disable_current() */
-static inline void kasan_enable_current(void)
-{
-	current->kasan_depth++;
-}
+extern void kasan_enable_current(void);
 
 /* Disable reporting bugs for current task */
-static inline void kasan_disable_current(void)
-{
-	current->kasan_depth--;
-}
+extern void kasan_disable_current(void);
 
 void kasan_unpoison_shadow(const void *address, size_t size);
 
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 55e11c4b2f3b..60e800e0b5a0 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
+#include <linux/sched.h>
 #include <linux/random.h>
 #include <linux/sbitmap.h>
 #include <linux/seq_file.h>
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 25f0e6521f36..d99312ed7c22 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -39,6 +39,16 @@
 #include "kasan.h"
 #include "../slab.h"
 
+void kasan_enable_current(void)
+{
+	current->kasan_depth++;
+}
+
+void kasan_disable_current(void)
+{
+	current->kasan_depth--;
+}
+
 /*
  * Poisons the shadow memory for 'size' bytes starting from 'addr'.
  * Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE.
-- 
GitLab


From 105ab3d8ce7269887d24d224054677125e18037c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 474/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/topology.h>

We are going to split <linux/sched/topology.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/topology.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/kernel/topology.c     | 1 +
 arch/arm64/kernel/topology.c   | 1 +
 arch/powerpc/kernel/smp.c      | 1 +
 arch/s390/kernel/topology.c    | 1 +
 arch/x86/kernel/smpboot.c      | 1 +
 block/blk-mq.c                 | 1 +
 block/blk-softirq.c            | 1 +
 include/linux/cpuset.h         | 1 +
 include/linux/sched/topology.h | 6 ++++++
 kernel/sched/fair.c            | 2 ++
 kernel/sched/sched.h           | 1 +
 11 files changed, 17 insertions(+)
 create mode 100644 include/linux/sched/topology.h

diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index ebf47d91b804..f8a3ab82e77f 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -21,6 +21,7 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 565dd69888cc..08243533e5ee 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -20,6 +20,7 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/cpufreq.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 21fdf02583fe..fce17789c675 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 2cd5f4f1013c..17660e800e74 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/slab.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a0d38685f7df..fe7a66e6b5a0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -45,6 +45,7 @@
 #include <linux/smp.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/percpu.h>
 #include <linux/bootmem.h>
 #include <linux/err.h>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9e6b064e5339..746c14e0d157 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -20,6 +20,7 @@
 #include <linux/cpu.h>
 #include <linux/cache.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/topology.h>
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/prefetch.h>
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 06cf9807f49a..87b7df4851bf 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -9,6 +9,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 
 #include "blk.h"
 
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index bfc204e70338..c608c39cb161 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -9,6 +9,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/mm.h>
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
new file mode 100644
index 000000000000..4f1159f76f92
--- /dev/null
+++ b/include/linux/sched/topology.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_TOPOLOGY_H
+#define _LINUX_SCHED_TOPOLOGY_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_TOPOLOGY_H */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3b60d73ab290..11e0ab57748a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -21,6 +21,8 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/topology.h>
+
 #include <linux/latencytop.h>
 #include <linux/cpumask.h>
 #include <linux/cpuidle.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 71b10a9b73cf..9b9cb260d9cf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1,6 +1,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/topology.h>
 #include <linux/sched/rt.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
-- 
GitLab


From 4c822698cba8bdd93724117eded12bf34eb80252 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 475/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/idle.h>

We are going to split  <linux/sched/idle.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/idle.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/mwait.h   | 1 +
 arch/x86/kernel/process.c      | 1 +
 drivers/cpuidle/driver.c       | 1 +
 include/linux/sched/idle.h     | 6 ++++++
 include/linux/sched/topology.h | 2 ++
 kernel/sched/idle.c            | 1 +
 kernel/smp.c                   | 1 +
 7 files changed, 13 insertions(+)
 create mode 100644 include/linux/sched/idle.h

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index f37f2d8a2989..bda3c27f0da0 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_MWAIT_H
 
 #include <linux/sched.h>
+#include <linux/sched/idle.h>
 
 #include <asm/cpufeature.h>
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7780efa635b9..6395e0cd7dd6 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -7,6 +7,7 @@
 #include <linux/prctl.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/idle.h>
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/pm.h>
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index ab264d393233..e53fb861beb0 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -11,6 +11,7 @@
 #include <linux/mutex.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/idle.h>
 #include <linux/cpuidle.h>
 #include <linux/cpumask.h>
 #include <linux/tick.h>
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
new file mode 100644
index 000000000000..a3cf79b86986
--- /dev/null
+++ b/include/linux/sched/idle.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_IDLE_H
+#define _LINUX_SCHED_IDLE_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_IDLE_H */
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 4f1159f76f92..184b56b8aa64 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -3,4 +3,6 @@
 
 #include <linux/sched.h>
 
+#include <linux/sched/idle.h>
+
 #endif /* _LINUX_SCHED_TOPOLOGY_H */
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6a4bae0a649d..ac6d5176463d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -2,6 +2,7 @@
  * Generic entry point for the idle threads
  */
 #include <linux/sched.h>
+#include <linux/sched/idle.h>
 #include <linux/cpu.h>
 #include <linux/cpuidle.h>
 #include <linux/cpuhotplug.h>
diff --git a/kernel/smp.c b/kernel/smp.c
index 77fcdb9f2775..a817769b53c0 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -17,6 +17,7 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/sched/idle.h>
 #include <linux/hypervisor.h>
 
 #include "smpboot.h"
-- 
GitLab


From 84f001e15737f8214b0f5f0f7dfec0fb1027938f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 476/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/wake_q.h>

We are going to split <linux/sched/wake_q.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/wake_q.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/wake_q.h    | 6 ++++++
 ipc/mqueue.c                    | 1 +
 ipc/msg.c                       | 1 +
 ipc/sem.c                       | 1 +
 kernel/futex.c                  | 1 +
 kernel/locking/mutex.c          | 1 +
 kernel/locking/rtmutex.c        | 1 +
 kernel/locking/rtmutex_common.h | 1 +
 kernel/locking/rwsem-xadd.c     | 3 ++-
 kernel/sched/sched.h            | 1 +
 10 files changed, 16 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/wake_q.h

diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
new file mode 100644
index 000000000000..6383b35e4eba
--- /dev/null
+++ b/include/linux/sched/wake_q.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_WAKE_Q_H
+#define _LINUX_SCHED_WAKE_Q_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_WAKE_Q_H */
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 4fdd97031431..40e448de8a7e 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -35,6 +35,7 @@
 #include <linux/ipc_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/slab.h>
+#include <linux/sched/wake_q.h>
 
 #include <net/sock.h>
 #include "util.h"
diff --git a/ipc/msg.c b/ipc/msg.c
index e3e52ce01123..ecc387e573f6 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -31,6 +31,7 @@
 #include <linux/list.h>
 #include <linux/security.h>
 #include <linux/sched.h>
+#include <linux/sched/wake_q.h>
 #include <linux/syscalls.h>
 #include <linux/audit.h>
 #include <linux/seq_file.h>
diff --git a/ipc/sem.c b/ipc/sem.c
index e468cd1c12f0..947dc2348271 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -82,6 +82,7 @@
 #include <linux/rwsem.h>
 #include <linux/nsproxy.h>
 #include <linux/ipc_namespace.h>
+#include <linux/sched/wake_q.h>
 
 #include <linux/uaccess.h>
 #include "util.h"
diff --git a/kernel/futex.c b/kernel/futex.c
index b687cb22301c..8ddcf9ea953c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -61,6 +61,7 @@
 #include <linux/nsproxy.h>
 #include <linux/ptrace.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/wake_q.h>
 #include <linux/hugetlb.h>
 #include <linux/freezer.h>
 #include <linux/bootmem.h>
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index ad2d9e22697b..57f6311e2405 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -21,6 +21,7 @@
 #include <linux/ww_mutex.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/wake_q.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index d340be3a488f..d4f798491361 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
+#include <linux/sched/wake_q.h>
 #include <linux/timer.h>
 
 #include "rtmutex_common.h"
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 990134617b4c..856dfff5c33a 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -13,6 +13,7 @@
 #define __KERNEL_RTMUTEX_COMMON_H
 
 #include <linux/rtmutex.h>
+#include <linux/sched/wake_q.h>
 
 /*
  * This is the control structure for tasks blocked on a rt_mutex,
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 2ad8d8dc3bb1..4fe8d8ad4396 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -10,10 +10,11 @@
  * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
  */
 #include <linux/rwsem.h>
-#include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/export.h>
+#include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/wake_q.h>
 #include <linux/osq_lock.h>
 
 #include "rwsem.h"
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9b9cb260d9cf..683570739f46 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3,6 +3,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/wake_q.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
 #include <linux/kernel_stat.h>
-- 
GitLab


From e601757102cfd3eeae068f53b3bc1234f3a2b2e9 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 477/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/clock.h>

We are going to split <linux/sched/clock.h> out of <linux/sched.h>, which
will have to be picked up from other headers and .c files.

Create a trivial placeholder <linux/sched/clock.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/mach-bcm/platsmp.c             | 1 +
 arch/arm/mach-omap2/pm-debug.c          | 1 +
 arch/arm/probes/kprobes/test-core.c     | 1 +
 arch/cris/kernel/time.c                 | 2 +-
 arch/ia64/kernel/setup.c                | 1 +
 arch/microblaze/kernel/timer.c          | 1 +
 arch/mn10300/kernel/time.c              | 1 +
 arch/parisc/kernel/setup.c              | 1 +
 arch/parisc/kernel/time.c               | 1 +
 arch/powerpc/kernel/time.c              | 1 +
 arch/s390/kernel/time.c                 | 1 +
 arch/sparc/kernel/ds.c                  | 1 +
 arch/sparc/kernel/viohs.c               | 1 +
 arch/tile/kernel/time.c                 | 1 +
 arch/x86/events/amd/ibs.c               | 1 +
 arch/x86/events/core.c                  | 1 +
 arch/x86/kernel/cpu/amd.c               | 1 +
 arch/x86/kernel/cpu/centaur.c           | 1 +
 arch/x86/kernel/cpu/common.c            | 1 +
 arch/x86/kernel/cpu/cyrix.c             | 1 +
 arch/x86/kernel/cpu/intel.c             | 1 +
 arch/x86/kernel/cpu/transmeta.c         | 1 +
 arch/x86/kernel/kvmclock.c              | 1 +
 arch/x86/kernel/nmi.c                   | 1 +
 arch/x86/kernel/tsc.c                   | 1 +
 block/cfq-iosched.c                     | 1 +
 drivers/acpi/apei/ghes.c                | 1 +
 drivers/clocksource/arm_arch_timer.c    | 1 +
 drivers/clocksource/pxa_timer.c         | 1 +
 drivers/clocksource/timer-digicolor.c   | 1 +
 drivers/cpuidle/cpuidle.c               | 1 +
 drivers/firmware/tegra/bpmp.c           | 1 +
 drivers/gpu/drm/i915/i915_gem_request.c | 2 ++
 drivers/gpu/drm/i915/intel_drv.h        | 1 +
 drivers/md/bcache/bset.c                | 1 +
 drivers/md/bcache/btree.c               | 1 +
 drivers/md/bcache/sysfs.c               | 1 +
 drivers/md/bcache/util.c                | 1 +
 drivers/md/bcache/util.h                | 1 +
 drivers/md/bcache/writeback.c           | 1 +
 drivers/misc/cxl/native.c               | 1 +
 drivers/net/irda/pxaficp_ir.c           | 1 +
 drivers/perf/arm_pmu.c                  | 1 +
 drivers/vhost/net.c                     | 1 +
 include/linux/blkdev.h                  | 1 +
 include/linux/sched/clock.h             | 6 ++++++
 include/linux/skbuff.h                  | 1 +
 include/net/busy_poll.h                 | 1 +
 kernel/events/core.c                    | 1 +
 kernel/locking/lockdep.c                | 1 +
 kernel/locking/qspinlock_stat.h         | 1 +
 kernel/printk/printk.c                  | 1 +
 kernel/sched/clock.c                    | 1 +
 kernel/sched/core.c                     | 1 +
 kernel/sched/sched.h                    | 1 +
 kernel/time/sched_clock.c               | 1 +
 kernel/time/tick-sched.c                | 1 +
 kernel/torture.c                        | 1 +
 kernel/trace/ring_buffer.c              | 1 +
 kernel/trace/trace_clock.c              | 1 +
 kernel/trace/trace_hwlat.c              | 1 +
 kernel/trace/trace_output.c             | 1 +
 kernel/watchdog.c                       | 1 +
 lib/plist.c                             | 1 +
 net/ipv4/tcp_cdg.c                      | 2 ++
 65 files changed, 72 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/clock.h

diff --git a/arch/arm/mach-bcm/platsmp.c b/arch/arm/mach-bcm/platsmp.c
index 582886d0d02f..9e3f275934eb 100644
--- a/arch/arm/mach-bcm/platsmp.c
+++ b/arch/arm/mach-bcm/platsmp.c
@@ -21,6 +21,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c
index 003a6cb248be..5c46ea6756d7 100644
--- a/arch/arm/mach-omap2/pm-debug.c
+++ b/arch/arm/mach-omap2/pm-debug.c
@@ -21,6 +21,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index 9775de22e2ff..c893726aa52d 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -203,6 +203,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 #include <linux/kprobes.h>
 #include <linux/errno.h>
 #include <linux/stddef.h>
diff --git a/arch/cris/kernel/time.c b/arch/cris/kernel/time.c
index 2dda6da71521..bc562cf511a6 100644
--- a/arch/cris/kernel/time.c
+++ b/arch/cris/kernel/time.c
@@ -29,7 +29,7 @@
 #include <linux/timex.h>
 #include <linux/init.h>
 #include <linux/profile.h>
-#include <linux/sched.h>	/* just for sched_clock() - funny that */
+#include <linux/sched/clock.h>
 
 
 #define D(x)
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index d68322966f33..32a6cc36296f 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -32,6 +32,7 @@
 #include <linux/kernel.h>
 #include <linux/reboot.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/threads.h>
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index 1d6fad50fa76..999066192715 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -12,6 +12,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/sched_clock.h>
 #include <linux/clk.h>
 #include <linux/clockchips.h>
diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c
index 67c6416a58f8..06b83b17c5f1 100644
--- a/arch/mn10300/kernel/time.c
+++ b/arch/mn10300/kernel/time.c
@@ -10,6 +10,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 068ed3607bac..dee6f9d6a153 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -37,6 +37,7 @@
 #include <linux/proc_fs.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 
 #include <asm/processor.h>
 #include <asm/sections.h>
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 1e22f981cd81..89421df70160 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/rtc.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/sched_clock.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index bc84a8d47b9e..37833c5dc274 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -34,6 +34,7 @@
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index de66abb479c9..c31da46bc037 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index f87a55d77094..b542cc7c8d94 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -9,6 +9,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/kthread.h>
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index 526fcb5d8ce9..b30b30ab3ddd 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/slab.h>
 
 #include <asm/ldc.h>
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index c9357012b1c8..5bd4e88c7c60 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -20,6 +20,7 @@
 #include <linux/clockchips.h>
 #include <linux/hardirq.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/smp.h>
 #include <linux/delay.h>
 #include <linux/module.h>
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 496e60391fac..786fd875de92 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -12,6 +12,7 @@
 #include <linux/pci.h>
 #include <linux/ptrace.h>
 #include <linux/syscore_ops.h>
+#include <linux/sched/clock.h>
 
 #include <asm/apic.h>
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 1635c0c8df23..2ecc0e97772b 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/kdebug.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4e95b2e0d95f..35a5d5dca2fa 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -5,6 +5,7 @@
 
 #include <linux/io.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 2c234a6d94c4..adc0ebd8bed0 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,5 +1,6 @@
 
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 
 #include <asm/cpufeature.h>
 #include <asm/e820.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c64ca5929cb5..c7e2ca966386 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -8,6 +8,7 @@
 #include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/init.h>
 #include <linux/kprobes.h>
 #include <linux/kgdb.h>
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 47416f959a48..0a3bc19de017 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -10,6 +10,7 @@
 #include <asm/tsc.h>
 #include <asm/cpufeature.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 017ecd3bb553..fe0a615a051b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -4,6 +4,7 @@
 #include <linux/bitops.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/thread_info.h>
 #include <linux/init.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index c1ea5b999839..8457b4978668 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/mm.h>
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index bae6ea6cfb94..d88967659098 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -25,6 +25,7 @@
 #include <linux/hardirq.h>
 #include <linux/memblock.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index bfe4d6c96fbd..d17b1a940add 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -20,6 +20,7 @@
 #include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/sched/clock.h>
 
 #if defined(CONFIG_EDAC)
 #include <linux/edac.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2724dc82f992..46bcda4cb1c2 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -2,6 +2,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/timer.h>
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 137944777859..440b95ee593c 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -8,6 +8,7 @@
  */
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
 #include <linux/ktime.h>
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index e53bef6cf53c..b192b42a8351 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -44,6 +44,7 @@
 #include <linux/pci.h>
 #include <linux/aer.h>
 #include <linux/nmi.h>
+#include <linux/sched/clock.h>
 
 #include <acpi/ghes.h>
 #include <acpi/apei.h>
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 93aa1364376a..7a8a4117f123 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -24,6 +24,7 @@
 #include <linux/of_address.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 #include <linux/sched_clock.h>
 #include <linux/acpi.h>
 
diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c
index 9cae38eebec2..1c24de215c14 100644
--- a/drivers/clocksource/pxa_timer.c
+++ b/drivers/clocksource/pxa_timer.c
@@ -19,6 +19,7 @@
 #include <linux/clockchips.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched/clock.h>
 #include <linux/sched_clock.h>
 
 #include <clocksource/pxa.h>
diff --git a/drivers/clocksource/timer-digicolor.c b/drivers/clocksource/timer-digicolor.c
index 10318cc99c0e..e9f50d289362 100644
--- a/drivers/clocksource/timer-digicolor.c
+++ b/drivers/clocksource/timer-digicolor.c
@@ -31,6 +31,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqreturn.h>
+#include <linux/sched/clock.h>
 #include <linux/sched_clock.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 62810ff3b00f..548b90be7685 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/notifier.h>
 #include <linux/pm_qos.h>
 #include <linux/cpu.h>
diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c
index 4ff02d310868..84e4c9a58a0c 100644
--- a/drivers/firmware/tegra/bpmp.c
+++ b/drivers/firmware/tegra/bpmp.c
@@ -19,6 +19,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/semaphore.h>
+#include <linux/sched/clock.h>
 
 #include <soc/tegra/bpmp.h>
 #include <soc/tegra/bpmp-abi.h>
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index f31deeb72703..df3fef393dbe 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -24,6 +24,8 @@
 
 #include <linux/prefetch.h>
 #include <linux/dma-fence-array.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
 
 #include "i915_drv.h"
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b9cde116dab3..344f238b283f 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -28,6 +28,7 @@
 #include <linux/async.h>
 #include <linux/i2c.h>
 #include <linux/hdmi.h>
+#include <linux/sched/clock.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include <drm/drm_crtc.h>
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 646fe85261c1..18526d44688d 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -11,6 +11,7 @@
 #include "bset.h"
 
 #include <linux/console.h>
+#include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/prefetch.h>
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index a43eedd5804d..384559af310e 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -32,6 +32,7 @@
 #include <linux/prefetch.h>
 #include <linux/random.h>
 #include <linux/rcupdate.h>
+#include <linux/sched/clock.h>
 #include <trace/events/bcache.h>
 
 /*
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index b3ff57d61dde..f90f13616980 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -13,6 +13,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/sort.h>
+#include <linux/sched/clock.h>
 
 static const char * const cache_replacement_policies[] = {
 	"lru",
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index dde6172f3f10..8c3a938f4bf0 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/types.h>
+#include <linux/sched/clock.h>
 
 #include "util.h"
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index cf2cbc211d83..a126919ed102 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -6,6 +6,7 @@
 #include <linux/errno.h>
 #include <linux/blkdev.h>
 #include <linux/kernel.h>
+#include <linux/sched/clock.h>
 #include <linux/llist.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 69e1ae59cab8..6ac2e48b9235 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -13,6 +13,7 @@
 
 #include <linux/delay.h>
 #include <linux/kthread.h>
+#include <linux/sched/clock.h>
 #include <trace/events/bcache.h>
 
 /* Rate limiting */
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 09505f432eda..7ae710585267 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -9,6 +9,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/mm.h>
diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c
index 6e8f616be48e..1dba16bc7f8d 100644
--- a/drivers/net/irda/pxaficp_ir.c
+++ b/drivers/net/irda/pxaficp_ir.c
@@ -24,6 +24,7 @@
 #include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/irmod.h>
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 6d9335865880..9612b84bc3e0 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -20,6 +20,7 @@
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 #include <linux/spinlock.h>
 #include <linux/irq.h>
 #include <linux/irqdesc.h>
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 2fe35354f20e..5c98ad4d2f4c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -17,6 +17,7 @@
 #include <linux/workqueue.h>
 #include <linux/file.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 #include <linux/vmalloc.h>
 
 #include <linux/net.h>
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aecca0e7d9ca..796016e63c1d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -2,6 +2,7 @@
 #define _LINUX_BLKDEV_H
 
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 
 #ifdef CONFIG_BLOCK
 
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
new file mode 100644
index 000000000000..7cb7d79b2cf9
--- /dev/null
+++ b/include/linux/sched/clock.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_CLOCK_H
+#define _LINUX_SCHED_CLOCK_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_CLOCK_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 69ccd2636911..c776abd86937 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -34,6 +34,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/netdev_features.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <net/flow_dissector.h>
 #include <linux/splice.h>
 #include <linux/in6.h>
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index b8d637225a07..b96832df239e 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -25,6 +25,7 @@
 #define _LINUX_NET_BUSY_POLL_H
 
 #include <linux/netdevice.h>
+#include <linux/sched/clock.h>
 #include <net/ip.h>
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1031bdf9f012..42fe16a84f97 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -46,6 +46,7 @@
 #include <linux/filter.h>
 #include <linux/namei.h>
 #include <linux/parser.h>
+#include <linux/sched/clock.h>
 
 #include "internal.h"
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 9812e5dd409e..cdafaff926ca 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -28,6 +28,7 @@
 #define DISABLE_BRANCH_PROFILING
 #include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index e852be4851fc..4a30ef63c607 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -63,6 +63,7 @@ enum qlock_stats {
  */
 #include <linux/debugfs.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/fs.h>
 
 static const char * const qstat_names[qstat_num + 1] = {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 34da86e73d00..47050eedc206 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -45,6 +45,7 @@
 #include <linux/utsname.h>
 #include <linux/ctype.h>
 #include <linux/uio.h>
+#include <linux/sched/clock.h>
 
 #include <linux/uaccess.h>
 #include <asm/sections.h>
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index ad64efe41722..dd7817cdbf58 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -58,6 +58,7 @@
 #include <linux/percpu.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/static_key.h>
 #include <linux/workqueue.h>
 #include <linux/compiler.h>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1bd317db9810..1a7fd3d21e5a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,6 +6,7 @@
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/cpuset.h>
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 683570739f46..4d386461f13a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3,6 +3,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/clock.h>
 #include <linux/sched/wake_q.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index a26036d37a38..ea6b610c4c57 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/syscore_ops.h>
 #include <linux/hrtimer.h>
 #include <linux/sched_clock.h>
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2c115fdab397..4fee1c3abd0b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -19,6 +19,7 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/module.h>
 #include <linux/irq_work.h>
 #include <linux/posix-timers.h>
diff --git a/kernel/torture.c b/kernel/torture.c
index 01a99976f072..55de96529287 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -30,6 +30,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/completion.h>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a85739efcc30..96fc3c043ad6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -6,6 +6,7 @@
 #include <linux/trace_events.h>
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
+#include <linux/sched/clock.h>
 #include <linux/trace_seq.h>
 #include <linux/spinlock.h>
 #include <linux/irq_work.h>
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 0f06532a755b..5fdc779f411d 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/ktime.h>
 #include <linux/trace_clock.h>
 
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index edfacd954e1b..21ea6ae77d93 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -44,6 +44,7 @@
 #include <linux/uaccess.h>
 #include <linux/cpumask.h>
 #include <linux/delay.h>
+#include <linux/sched/clock.h>
 #include "trace.h"
 
 static struct trace_array	*hwlat_trace;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 070866c32eb9..107afca97649 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/ftrace.h>
+#include <linux/sched/clock.h>
 
 #include "trace_output.h"
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 63177be0159e..144d7b1b0364 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -21,6 +21,7 @@
 #include <linux/sched/rt.h>
 #include <linux/tick.h>
 #include <linux/workqueue.h>
+#include <linux/sched/clock.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
diff --git a/lib/plist.c b/lib/plist.c
index 3a30c53db061..199408f91057 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -175,6 +175,7 @@ void plist_requeue(struct plist_node *node, struct plist_head *head)
 
 #ifdef CONFIG_DEBUG_PI_LIST
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/module.h>
 #include <linux/init.h>
 
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 35b280361cb2..50a0f3e51d5b 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -27,6 +27,8 @@
 #include <linux/kernel.h>
 #include <linux/random.h>
 #include <linux/module.h>
+#include <linux/sched/clock.h>
+
 #include <net/tcp.h>
 
 #define HYSTART_ACK_TRAIN	1
-- 
GitLab


From ae7e81c077d60507dcec139e40a6d10cf932cf4b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 18:07:51 +0100
Subject: [PATCH 478/898] sched/headers: Prepare for new header dependencies
 before moving code to <uapi/linux/sched/types.h>

We are going to move scheduler ABI details to <uapi/linux/sched/types.h>,
which will be used from a number of .c files.

Create empty placeholder header that maps to <linux/types.h>.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/common/bL_switcher.c                 | 1 +
 crypto/crypto_engine.c                        | 1 +
 drivers/acpi/acpi_pad.c                       | 1 +
 drivers/block/drbd/drbd_receiver.c            | 1 +
 drivers/firmware/psci_checker.c               | 1 +
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 1 +
 drivers/gpu/drm/i915/intel_breadcrumbs.c      | 1 +
 drivers/media/pci/ivtv/ivtv-driver.c          | 1 +
 drivers/mmc/core/sdio_irq.c                   | 1 +
 drivers/spi/spi.c                             | 1 +
 drivers/staging/android/ion/ion_heap.c        | 1 +
 drivers/thermal/intel_powerclamp.c            | 1 +
 drivers/tty/serial/sc16is7xx.c                | 1 +
 include/uapi/linux/sched/types.h              | 6 ++++++
 kernel/irq/manage.c                           | 1 +
 kernel/kthread.c                              | 1 +
 kernel/locking/locktorture.c                  | 1 +
 kernel/rcu/rcuperf.c                          | 1 +
 kernel/rcu/rcutorture.c                       | 1 +
 kernel/rcu/tree.c                             | 1 +
 kernel/rcu/tree_plugin.h                      | 1 +
 kernel/sched/core.c                           | 1 +
 kernel/sched/cpufreq_schedutil.c              | 1 +
 kernel/trace/ring_buffer_benchmark.c          | 1 +
 kernel/trace/trace_selftest.c                 | 1 +
 kernel/watchdog.c                             | 1 +
 26 files changed, 31 insertions(+)
 create mode 100644 include/uapi/linux/sched/types.h

diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index 46730017b3c5..083c9e517d22 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/interrupt.h>
 #include <linux/cpu_pm.h>
 #include <linux/cpu.h>
diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
index f1bf3418d968..727bd5c3569e 100644
--- a/crypto/crypto_engine.c
+++ b/crypto/crypto_engine.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <crypto/engine.h>
 #include <crypto/internal/hash.h>
+#include <uapi/linux/sched/types.h>
 #include "internal.h"
 
 #define CRYPTO_ENGINE_MAX_QLEN 10
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index eb76a4c10dbf..754431031282 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/freezer.h>
 #include <linux/cpu.h>
 #include <linux/tick.h>
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c7728dd77230..8b40a5b2f8e6 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -36,6 +36,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mm_inline.h>
 #include <linux/slab.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/pkt_sched.h>
 #define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
diff --git a/drivers/firmware/psci_checker.c b/drivers/firmware/psci_checker.c
index 29d58feaf675..6523ce962865 100644
--- a/drivers/firmware/psci_checker.c
+++ b/drivers/firmware/psci_checker.c
@@ -20,6 +20,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/module.h>
 #include <linux/preempt.h>
 #include <linux/psci.h>
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 1bf83ed113b3..16f96563cd2b 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -24,6 +24,7 @@
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
 #include <drm/drmP.h>
 #include "gpu_scheduler.h"
 
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index fcfa423d08bd..7044e9a6abf7 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 
 #include "i915_drv.h"
 
diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c
index ab2ae53618e8..e73c153285f0 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.c
+++ b/drivers/media/pci/ivtv/ivtv-driver.c
@@ -59,6 +59,7 @@
 #include <media/tveeprom.h>
 #include <media/i2c/saa7115.h>
 #include "tuner-xc2028.h"
+#include <uapi/linux/sched/types.h>
 
 /* If you have already X v4l cards, then set this to X. This way
    the device numbers stay matched. Example: you have a WinTV card
diff --git a/drivers/mmc/core/sdio_irq.c b/drivers/mmc/core/sdio_irq.c
index d29faf2addfe..6d4b72080d51 100644
--- a/drivers/mmc/core/sdio_irq.c
+++ b/drivers/mmc/core/sdio_irq.c
@@ -15,6 +15,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/kthread.h>
 #include <linux/export.h>
 #include <linux/wait.h>
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 44222ef9471e..90b5b2efafbf 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -33,6 +33,7 @@
 #include <linux/pm_domain.h>
 #include <linux/export.h>
 #include <linux/sched/rt.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/ioport.h>
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index 4e5c0f17f579..c69d0bd53693 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/rtmutex.h>
 #include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
 #include "ion.h"
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index a47103a659fa..d718cd179ddb 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -50,6 +50,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/sched/rt.h>
+#include <uapi/linux/sched/types.h>
 
 #include <asm/nmi.h>
 #include <asm/msr.h>
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 793395451982..ca54ce074a5f 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -29,6 +29,7 @@
 #include <linux/tty_flip.h>
 #include <linux/spi/spi.h>
 #include <linux/uaccess.h>
+#include <uapi/linux/sched/types.h>
 
 #define SC16IS7XX_NAME			"sc16is7xx"
 #define SC16IS7XX_MAX_DEVS		8
diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h
new file mode 100644
index 000000000000..d162d315f4b5
--- /dev/null
+++ b/include/uapi/linux/sched/types.h
@@ -0,0 +1,6 @@
+#ifndef _UAPI_LINUX_SCHED_TYPES_H
+#define _UAPI_LINUX_SCHED_TYPES_H
+
+#include <linux/types.h>
+
+#endif /* _UAPI_LINUX_SCHED_TYPES_H */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 944d068b6c48..09740952e4de 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/task_work.h>
 
 #include "internals.h"
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 8461a4372e8a..ef9b9eb809c7 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -5,6 +5,7 @@
  * even if we're invoked from userspace (think modprobe, hotplug cpu,
  * etc.).
  */
+#include <uapi/linux/sched/types.h>
 #include <linux/sched.h>
 #include <linux/kthread.h>
 #include <linux/completion.h>
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 28350dc8ecbb..5ea0a8969ee2 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -32,6 +32,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/atomic.h>
 #include <linux/moduleparam.h>
 #include <linux/delay.h>
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 123ccbd22449..a4a86fb47e4a 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -30,6 +30,7 @@
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/completion.h>
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index d81345be730e..6a28b79710f0 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -33,6 +33,7 @@
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/completion.h>
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cb62ce23ffc7..e456327a63d6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -49,6 +49,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/wait.h>
 #include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/prefetch.h>
 #include <linux/delay.h>
 #include <linux/stop_machine.h>
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a240f3308be6..9dabb04003be 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -28,6 +28,7 @@
 #include <linux/gfp.h>
 #include <linux/oom.h>
 #include <linux/smpboot.h>
+#include <uapi/linux/sched/types.h>
 #include "../time/tick-internal.h"
 
 #ifdef CONFIG_RCU_BOOST
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1a7fd3d21e5a..ed39d1d0b64a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,6 +7,7 @@
  */
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/cpuset.h>
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index fd4659313640..8f8de3d4d6b7 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -13,6 +13,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/slab.h>
 #include <trace/events/power.h>
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 6df9a83e20d7..c190a4d5013c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -6,6 +6,7 @@
 #include <linux/ring_buffer.h>
 #include <linux/completion.h>
 #include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/module.h>
 #include <linux/ktime.h>
 #include <asm/local.h>
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index b0f86ea77881..cb917cebae29 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1,5 +1,6 @@
 /* Include in trace.c */
 
+#include <uapi/linux/sched/types.h>
 #include <linux/stringify.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 144d7b1b0364..52718f4512e9 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -19,6 +19,7 @@
 #include <linux/sysctl.h>
 #include <linux/smpboot.h>
 #include <linux/sched/rt.h>
+#include <uapi/linux/sched/types.h>
 #include <linux/tick.h>
 #include <linux/workqueue.h>
 #include <linux/sched/clock.h>
-- 
GitLab


From 4f17722c7256af8e17c2c4f29f170247264bdf48 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 08:45:17 +0100
Subject: [PATCH 479/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/loadavg.h>

We are going to split <linux/sched/loadavg.h> out of <linux/sched.h>, which
will have to be picked up from a couple of .c files.

Create a trivial placeholder <linux/sched/topology.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/m68k/kernel/time.c                         | 1 +
 arch/microblaze/kernel/heartbeat.c              | 1 +
 arch/powerpc/platforms/cell/cpufreq_spudemand.c | 1 +
 arch/powerpc/platforms/cell/spufs/sched.c       | 1 +
 arch/s390/appldata/appldata_os.c                | 1 +
 arch/sh/drivers/heartbeat.c                     | 1 +
 arch/sparc/kernel/led.c                         | 1 +
 drivers/cpuidle/governors/menu.c                | 1 +
 drivers/leds/trigger/ledtrig-heartbeat.c        | 1 +
 drivers/platform/x86/intel_ips.c                | 1 +
 fs/proc/loadavg.c                               | 1 +
 include/linux/sched/loadavg.h                   | 6 ++++++
 kernel/debug/kdb/kdb_main.c                     | 1 +
 kernel/sched/core.c                             | 1 +
 kernel/sched/loadavg.c                          | 1 +
 kernel/sys.c                                    | 1 +
 kernel/time/timekeeping.c                       | 1 +
 net/sched/em_meta.c                             | 1 +
 18 files changed, 23 insertions(+)
 create mode 100644 include/linux/sched/loadavg.h

diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 4e5aa2f4f522..87160b4415fb 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
diff --git a/arch/microblaze/kernel/heartbeat.c b/arch/microblaze/kernel/heartbeat.c
index 4643e3ab9414..2022130139d2 100644
--- a/arch/microblaze/kernel/heartbeat.c
+++ b/arch/microblaze/kernel/heartbeat.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/io.h>
 
 #include <asm/setup.h>
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
index 88301e53f085..882944c36ef5 100644
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -22,6 +22,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 9b543df210fb..d317c84dc794 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -24,6 +24,7 @@
 
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/sched/rt.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 08b9e942a262..079446619f89 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -17,6 +17,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/netdevice.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <asm/appldata.h>
 #include <asm/smp.h>
 
diff --git a/arch/sh/drivers/heartbeat.c b/arch/sh/drivers/heartbeat.c
index 49bace446a1a..c6d96049a0bb 100644
--- a/arch/sh/drivers/heartbeat.c
+++ b/arch/sh/drivers/heartbeat.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/timer.h>
 #include <linux/io.h>
 #include <linux/slab.h>
diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c
index 3ae36f36e758..44a3ed93c214 100644
--- a/arch/sparc/kernel/led.c
+++ b/arch/sparc/kernel/led.c
@@ -8,6 +8,7 @@
 #include <linux/jiffies.h>
 #include <linux/timer.h>
 #include <linux/uaccess.h>
+#include <linux/sched/loadavg.h>
 
 #include <asm/auxio.h>
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 8d6d25c38c02..fe86060e48f7 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -18,6 +18,7 @@
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/math64.h>
 #include <linux/cpu.h>
 
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index e6f2f8b9f09a..afa3b4099214 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/timer.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/leds.h>
 #include <linux/reboot.h>
 #include <linux/suspend.h>
diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c
index 55663b3d7282..58dcee562d64 100644
--- a/drivers/platform/x86/intel_ips.c
+++ b/drivers/platform/x86/intel_ips.c
@@ -68,6 +68,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/tick.h>
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index aec66e6c2060..add5255ce7e0 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -3,6 +3,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/proc_fs.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/seq_file.h>
 #include <linux/seqlock.h>
 #include <linux/time.h>
diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
new file mode 100644
index 000000000000..3ae74be327e8
--- /dev/null
+++ b/include/linux/sched/loadavg.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_LOADAVG_H
+#define _LINUX_SCHED_LOADAVG_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_LOADAVG_H */
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index ca183919d302..308937c7a687 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -18,6 +18,7 @@
 #include <linux/kmsg_dump.h>
 #include <linux/reboot.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/sysrq.h>
 #include <linux/smp.h>
 #include <linux/utsname.h>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ed39d1d0b64a..11a0684a29a7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <uapi/linux/sched/types.h>
+#include <linux/sched/loadavg.h>
 #include <linux/cpuset.h>
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index a2d6eb71f06b..7296b7308eca 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/sched/loadavg.h>
 
 #include "sched.h"
 
diff --git a/kernel/sys.c b/kernel/sys.c
index b07adca97ea3..28b8a4c1bc7e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -49,6 +49,7 @@
 #include <linux/binfmts.h>
 
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/rcupdate.h>
 #include <linux/uidgid.h>
 #include <linux/cred.h>
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 95b258dd75db..fb564acee0f3 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/syscore_ops.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 41c80b6c3906..ae7e4f5b348b 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -63,6 +63,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
 #include <linux/string.h>
 #include <linux/skbuff.h>
 #include <linux/random.h>
-- 
GitLab


From 4eb5aaa3af8a54e5e9bac90e2b42bbab1f1ee5a3 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:29 +0100
Subject: [PATCH 480/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/autogroup.h>

We are going to split <linux/sched/autogroup.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/autogroup.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/proc/base.c                  | 1 +
 include/linux/sched/autogroup.h | 6 ++++++
 kernel/exit.c                   | 1 +
 kernel/fork.c                   | 1 +
 kernel/sched/autogroup.h        | 1 +
 kernel/sys.c                    | 1 +
 6 files changed, 11 insertions(+)
 create mode 100644 include/linux/sched/autogroup.h

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1e1e182d571b..27af4ea315a3 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -85,6 +85,7 @@
 #include <linux/user_namespace.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
+#include <linux/sched/autogroup.h>
 #include <linux/flex_array.h>
 #include <linux/posix-timers.h>
 #ifdef CONFIG_HARDWALL
diff --git a/include/linux/sched/autogroup.h b/include/linux/sched/autogroup.h
new file mode 100644
index 000000000000..d745f22e57dc
--- /dev/null
+++ b/include/linux/sched/autogroup.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_AUTOGROUP_H
+#define _LINUX_SCHED_AUTOGROUP_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_AUTOGROUP_H */
diff --git a/kernel/exit.c b/kernel/exit.c
index 8a768a3672a5..9c0b92833fbb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -6,6 +6,7 @@
 
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/sched/autogroup.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/capability.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index d043fedc03c8..234f4bfb8efd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/sched/autogroup.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
 #include <linux/module.h>
diff --git a/kernel/sched/autogroup.h b/kernel/sched/autogroup.h
index 890c95f2587a..ce40c810cd5c 100644
--- a/kernel/sched/autogroup.h
+++ b/kernel/sched/autogroup.h
@@ -2,6 +2,7 @@
 
 #include <linux/kref.h>
 #include <linux/rwsem.h>
+#include <linux/sched/autogroup.h>
 
 struct autogroup {
 	/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 28b8a4c1bc7e..cfe82ae62423 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -49,6 +49,7 @@
 #include <linux/binfmts.h>
 
 #include <linux/sched.h>
+#include <linux/sched/autogroup.h>
 #include <linux/sched/loadavg.h>
 #include <linux/rcupdate.h>
 #include <linux/uidgid.h>
-- 
GitLab


From 6e84f31522f931027bf695752087ece278c10d3f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:29 +0100
Subject: [PATCH 481/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/mm.h>

We are going to split <linux/sched/mm.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/mm.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

The APIs that are going to be moved first are:

   mm_alloc()
   __mmdrop()
   mmdrop()
   mmdrop_async_fn()
   mmdrop_async()
   mmget_not_zero()
   mmput()
   mmput_async()
   get_task_mm()
   mm_access()
   mm_release()

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/include/asm/mmu_context.h          | 1 +
 arch/arc/kernel/troubleshoot.c              | 2 ++
 arch/arm/mach-rpc/ecard.c                   | 1 +
 arch/frv/mm/mmu-context.c                   | 1 +
 arch/m68k/sun3/mmu_emu.c                    | 1 +
 arch/powerpc/platforms/cell/spufs/context.c | 2 ++
 drivers/android/binder.c                    | 1 +
 drivers/gpu/drm/amd/amdkfd/kfd_process.c    | 1 +
 drivers/gpu/drm/etnaviv/etnaviv_gem.c       | 1 +
 drivers/gpu/drm/i915/i915_gem_userptr.c     | 1 +
 drivers/infiniband/core/umem.c              | 1 +
 drivers/infiniband/core/umem_odp.c          | 1 +
 drivers/infiniband/hw/hfi1/file_ops.c       | 1 +
 drivers/infiniband/hw/mlx4/main.c           | 2 ++
 drivers/infiniband/hw/mlx5/main.c           | 1 +
 drivers/infiniband/hw/usnic/usnic_uiom.c    | 1 +
 drivers/iommu/amd_iommu_v2.c                | 1 +
 drivers/iommu/intel-svm.c                   | 1 +
 drivers/lguest/lguest_user.c                | 1 +
 drivers/misc/cxl/fault.c                    | 1 +
 drivers/misc/mic/scif/scif_rma.c            | 2 ++
 drivers/oprofile/buffer_sync.c              | 1 +
 drivers/vfio/vfio_iommu_spapr_tce.c         | 2 ++
 drivers/vfio/vfio_iommu_type1.c             | 1 +
 drivers/vhost/vhost.c                       | 1 +
 drivers/xen/gntdev.c                        | 1 +
 fs/exec.c                                   | 1 +
 fs/proc/array.c                             | 1 +
 fs/proc/base.c                              | 1 +
 fs/proc/task_mmu.c                          | 1 +
 fs/proc/task_nommu.c                        | 2 ++
 fs/userfaultfd.c                            | 1 +
 include/linux/sched/mm.h                    | 6 ++++++
 kernel/cgroup/cpuset.c                      | 1 +
 kernel/events/core.c                        | 1 +
 kernel/events/uprobes.c                     | 1 +
 kernel/exit.c                               | 1 +
 kernel/fork.c                               | 1 +
 kernel/futex.c                              | 1 +
 kernel/ptrace.c                             | 1 +
 kernel/sched/sched.h                        | 1 +
 kernel/sys.c                                | 1 +
 kernel/trace/trace_output.c                 | 1 +
 kernel/tsacct.c                             | 1 +
 mm/khugepaged.c                             | 1 +
 mm/ksm.c                                    | 1 +
 mm/memcontrol.c                             | 1 +
 mm/memory.c                                 | 1 +
 mm/mempolicy.c                              | 1 +
 mm/migrate.c                                | 1 +
 mm/mmu_context.c                            | 1 +
 mm/mmu_notifier.c                           | 1 +
 mm/nommu.c                                  | 1 +
 mm/oom_kill.c                               | 1 +
 mm/process_vm_access.c                      | 1 +
 mm/rmap.c                                   | 1 +
 mm/swapfile.c                               | 1 +
 mm/util.c                                   | 1 +
 virt/kvm/async_pf.c                         | 1 +
 virt/kvm/kvm_main.c                         | 1 +
 60 files changed, 71 insertions(+)
 create mode 100644 include/linux/sched/mm.h

diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index b0b87f2447f5..64b5ebae1ae8 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -20,6 +20,7 @@
 
 #include <asm/arcregs.h>
 #include <asm/tlb.h>
+#include <linux/sched/mm.h>
 
 #include <asm-generic/mm_hooks.h>
 
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 82f9bc819f4a..0c48907f56a9 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -13,6 +13,8 @@
 #include <linux/fs_struct.h>
 #include <linux/proc_fs.h>
 #include <linux/file.h>
+#include <linux/sched/mm.h>
+
 #include <asm/arcregs.h>
 #include <asm/irqflags.h>
 
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index dc67a7fb3831..6b279d037774 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -31,6 +31,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/interrupt.h>
 #include <linux/completion.h>
 #include <linux/reboot.h>
diff --git a/arch/frv/mm/mmu-context.c b/arch/frv/mm/mmu-context.c
index 3473bde77f56..4031289bf2ec 100644
--- a/arch/frv/mm/mmu-context.c
+++ b/arch/frv/mm/mmu-context.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/mm.h>
 #include <asm/tlbflush.h>
 
diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c
index e9d7fbe4d5ae..7fdc61525e0b 100644
--- a/arch/m68k/sun3/mmu_emu.c
+++ b/arch/m68k/sun3/mmu_emu.c
@@ -15,6 +15,7 @@
 #include <linux/bootmem.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
+#include <linux/sched/mm.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 3b4152faeb1f..b500b17254a0 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -25,6 +25,8 @@
 #include <linux/slab.h>
 #include <linux/atomic.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
+
 #include <asm/spu.h>
 #include <asm/spu_csa.h>
 #include "spufs.h"
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 2bbcdc6fdfee..e33e7fbe870b 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -32,6 +32,7 @@
 #include <linux/debugfs.h>
 #include <linux/rbtree.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index ca5f2aa7232d..84d1ffd1eef9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -23,6 +23,7 @@
 #include <linux/mutex.h>
 #include <linux/log2.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/amd-iommu.h>
 #include <linux/notifier.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index e78f1406885d..ae2882b64b82 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -16,6 +16,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/shmem_fs.h>
+#include <linux/sched/mm.h>
 
 #include "etnaviv_drv.h"
 #include "etnaviv_gem.h"
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 0115989e324a..22b46398831e 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -31,6 +31,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/mempolicy.h>
 #include <linux/swap.h>
+#include <linux/sched/mm.h>
 
 struct i915_mm_struct {
 	struct mm_struct *mm;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 446b56a5260b..d525b1a2986a 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -35,6 +35,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/export.h>
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index f2fc0431512d..7279f259494f 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -32,6 +32,7 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/pid.h>
 #include <linux/slab.h>
 #include <linux/export.h>
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 3b19c16a9e45..f78c739b330a 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -48,6 +48,7 @@
 #include <linux/cdev.h>
 #include <linux/vmalloc.h>
 #include <linux/io.h>
+#include <linux/sched/mm.h>
 
 #include <rdma/ib.h>
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 88608906ce25..56da8f0d71bb 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -39,6 +39,8 @@
 #include <linux/inetdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
+#include <linux/sched/mm.h>
+
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 #include <net/devlink.h>
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 5b3355268725..4b1ec3ff152a 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -41,6 +41,7 @@
 #include <asm/pat.h>
 #endif
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/delay.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_addr.h>
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 1ccee6ea5bc3..ba868be5af2e 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -35,6 +35,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/iommu.h>
 #include <linux/workqueue.h>
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index f8ed8c95b685..063343909b0d 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -22,6 +22,7 @@
 #include <linux/profile.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/iommu.h>
 #include <linux/wait.h>
 #include <linux/pci.h>
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 51f2b228723f..23c427602c55 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -16,6 +16,7 @@
 #include <linux/intel-iommu.h>
 #include <linux/mmu_notifier.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/intel-svm.h>
 #include <linux/rculist.h>
diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c
index 30c60687d277..1a6787bc9386 100644
--- a/drivers/lguest/lguest_user.c
+++ b/drivers/lguest/lguest_user.c
@@ -8,6 +8,7 @@
 #include <linux/miscdevice.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/export.h>
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 377e650a2a1d..e33011e3e7e2 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -9,6 +9,7 @@
 
 #include <linux/workqueue.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/pid.h>
 #include <linux/mm.h>
 #include <linux/moduleparam.h>
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index f806a4471eb9..d0e9c60f944e 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -17,6 +17,8 @@
  */
 #include <linux/dma_remapping.h>
 #include <linux/pagemap.h>
+#include <linux/sched/mm.h>
+
 #include "scif_main.h"
 #include "scif_map.h"
 
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index 642478d35e99..eb0c35994b54 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -31,6 +31,7 @@
 #include <linux/fs.h>
 #include <linux/oprofile.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/gfp.h>
 
 #include "oprofile_stats.h"
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 59b3f62a2d64..185d50ee1b12 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -20,6 +20,8 @@
 #include <linux/err.h>
 #include <linux/vfio.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/mm.h>
+
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/mmu_context.h>
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index bd6f293c4ebd..7e94c7fc90ae 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -32,6 +32,7 @@
 #include <linux/mm.h>
 #include <linux/rbtree.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 4269e621e254..4a00140a7624 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -27,6 +27,7 @@
 #include <linux/cgroup.h>
 #include <linux/module.h>
 #include <linux/sort.h>
+#include <linux/sched/mm.h>
 #include <linux/interval_tree_generic.h>
 
 #include "vhost.h"
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 2ef2b61b69df..c77a0751a311 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -32,6 +32,7 @@
 #include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/highmem.h>
diff --git a/fs/exec.c b/fs/exec.c
index e595e1529581..8929da96cca1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -32,6 +32,7 @@
 #include <linux/swap.h>
 #include <linux/string.h>
 #include <linux/init.h>
+#include <linux/sched/mm.h>
 #include <linux/pagemap.h>
 #include <linux/perf_event.h>
 #include <linux/highmem.h>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index fe12b519d09b..61bea3a4ecc5 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -60,6 +60,7 @@
 #include <linux/tty.h>
 #include <linux/string.h>
 #include <linux/mman.h>
+#include <linux/sched/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/ioport.h>
 #include <linux/uaccess.h>
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 27af4ea315a3..9efe12376af1 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -86,6 +86,7 @@
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
+#include <linux/sched/mm.h>
 #include <linux/flex_array.h>
 #include <linux/posix-timers.h>
 #ifdef CONFIG_HARDWALL
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ee3efb229ef6..f08bd31c1081 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -11,6 +11,7 @@
 #include <linux/mempolicy.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
+#include <linux/sched/mm.h>
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 1ef97cfcf422..23266694db11 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -7,6 +7,8 @@
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
+#include <linux/sched/mm.h>
+
 #include "internal.h"
 
 /*
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 3c421d06a18e..18d12bfff770 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/hashtable.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/mm.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
new file mode 100644
index 000000000000..a7adba1cd0a9
--- /dev/null
+++ b/include/linux/sched/mm.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_MM_H
+#define _LINUX_SCHED_MM_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_MM_H */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index b3088886cd37..a5c46db2855c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -44,6 +44,7 @@
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/seq_file.h>
 #include <linux/security.h>
 #include <linux/slab.h>
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 42fe16a84f97..6f41548f2e32 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -47,6 +47,7 @@
 #include <linux/namei.h>
 #include <linux/parser.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/mm.h>
 
 #include "internal.h"
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index d630f8ac4d2f..62f2dbd13efc 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -27,6 +27,7 @@
 #include <linux/pagemap.h>	/* read_mapping_page */
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/export.h>
 #include <linux/rmap.h>		/* anon_vma_prepare */
 #include <linux/mmu_notifier.h>	/* set_pte_at_notify */
diff --git a/kernel/exit.c b/kernel/exit.c
index 9c0b92833fbb..48649ccbb649 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
+#include <linux/sched/mm.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/capability.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 234f4bfb8efd..1875468e2a81 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -13,6 +13,7 @@
 
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
+#include <linux/sched/mm.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
 #include <linux/module.h>
diff --git a/kernel/futex.c b/kernel/futex.c
index 8ddcf9ea953c..229a744b1781 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -62,6 +62,7 @@
 #include <linux/ptrace.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/freezer.h>
 #include <linux/bootmem.h>
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 49ba7c1ade9d..6fe5a2897912 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -10,6 +10,7 @@
 #include <linux/capability.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4d386461f13a..e2307a6c29f1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -5,6 +5,7 @@
 #include <linux/sched/rt.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/mm.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
 #include <linux/kernel_stat.h>
diff --git a/kernel/sys.c b/kernel/sys.c
index cfe82ae62423..dc71ec1e1967 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -51,6 +51,7 @@
 #include <linux/sched.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/mm.h>
 #include <linux/rcupdate.h>
 #include <linux/uidgid.h>
 #include <linux/cred.h>
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 107afca97649..02a4aeb22c47 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -9,6 +9,7 @@
 #include <linux/mutex.h>
 #include <linux/ftrace.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/mm.h>
 
 #include "trace_output.h"
 
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 5c21f0535056..571a2d3821d8 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -18,6 +18,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/tsacct_kern.h>
 #include <linux/acct.h>
 #include <linux/jiffies.h>
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 34bce5c308e3..212a2afe8830 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2,6 +2,7 @@
 
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/mmu_notifier.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
diff --git a/mm/ksm.c b/mm/ksm.c
index 520e4c37fec7..5632c9d02457 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -19,6 +19,7 @@
 #include <linux/fs.h>
 #include <linux/mman.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 45867e439d31..c52ec893e241 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -35,6 +35,7 @@
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/shmem_fs.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
diff --git a/mm/memory.c b/mm/memory.c
index 14fc0b40f0bb..b0495ec74d29 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -40,6 +40,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1e7873e40c9a..90892416ed75 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -73,6 +73,7 @@
 #include <linux/hugetlb.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/nodemask.h>
 #include <linux/cpuset.h>
 #include <linux/slab.h>
diff --git a/mm/migrate.c b/mm/migrate.c
index 2c63ac06791b..9a0897a14d37 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -40,6 +40,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
 #include <linux/page_owner.h>
+#include <linux/sched/mm.h>
 
 #include <asm/tlbflush.h>
 
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index daf67bb02b4a..8888b124a386 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -5,6 +5,7 @@
 
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/mmu_context.h>
 #include <linux/export.h>
 
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 32bc9f2ff7eb..a7652acd2ab9 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -17,6 +17,7 @@
 #include <linux/srcu.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 
 /* global SRCU for all MMs */
diff --git a/mm/nommu.c b/mm/nommu.c
index aae06e854552..79abed514a4b 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -17,6 +17,7 @@
 
 #include <linux/export.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/vmacache.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 51c091849dcb..d28936618698 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -22,6 +22,7 @@
 #include <linux/err.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/swap.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 84d0c7eada2b..8973cd231ece 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/uio.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/highmem.h>
 #include <linux/ptrace.h>
 #include <linux/slab.h>
diff --git a/mm/rmap.c b/mm/rmap.c
index 8774791e2809..0367a0506667 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -46,6 +46,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
diff --git a/mm/swapfile.c b/mm/swapfile.c
index fadc6a1c0da0..ff2bf3f61b14 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/slab.h>
diff --git a/mm/util.c b/mm/util.c
index b8f538863b5a..14f4e13323e2 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -5,6 +5,7 @@
 #include <linux/export.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/security.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 2366177172f6..bb298a200cd3 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/mmu_context.h>
+#include <linux/sched/mm.h>
 
 #include "async_pf.h"
 #include <trace/events/kvm.h>
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 35f71409d9ee..dd5de09bf362 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -33,6 +33,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 #include <linux/anon_inodes.h>
-- 
GitLab


From f7ccbae45c5e2c1077654b0e857e7efb1aa31c92 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:30 +0100
Subject: [PATCH 482/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/coredump.h>

We are going to split <linux/sched/coredump.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/coredump.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/binfmt_elf.c                | 1 +
 fs/binfmt_elf_fdpic.c          | 1 +
 fs/coredump.c                  | 1 +
 fs/exec.c                      | 1 +
 fs/proc/base.c                 | 1 +
 fs/proc/internal.h             | 1 +
 include/linux/khugepaged.h     | 3 ++-
 include/linux/ksm.h            | 1 +
 include/linux/sched/coredump.h | 6 ++++++
 kernel/cred.c                  | 1 +
 kernel/events/uprobes.c        | 1 +
 kernel/fork.c                  | 1 +
 kernel/ptrace.c                | 1 +
 kernel/sys.c                   | 1 +
 kernel/sysctl.c                | 1 +
 mm/huge_memory.c               | 1 +
 mm/khugepaged.c                | 1 +
 mm/ksm.c                       | 1 +
 mm/memory.c                    | 1 +
 mm/oom_kill.c                  | 1 +
 20 files changed, 26 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/coredump.h

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 443a6f537d56..fbbe52e1250e 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -35,6 +35,7 @@
 #include <linux/utsname.h>
 #include <linux/coredump.h>
 #include <linux/sched.h>
+#include <linux/sched/coredump.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
 #include <asm/param.h>
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index ffca4bbc3d63..222873bb689c 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -35,6 +35,7 @@
 #include <linux/elf-fdpic.h>
 #include <linux/elfcore.h>
 #include <linux/coredump.h>
+#include <linux/sched/coredump.h>
 #include <linux/dax.h>
 
 #include <linux/uaccess.h>
diff --git a/fs/coredump.c b/fs/coredump.c
index ae6b05629ca1..23a539b29225 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -16,6 +16,7 @@
 #include <linux/personality.h>
 #include <linux/binfmts.h>
 #include <linux/coredump.h>
+#include <linux/sched/coredump.h>
 #include <linux/utsname.h>
 #include <linux/pid_namespace.h>
 #include <linux/module.h>
diff --git a/fs/exec.c b/fs/exec.c
index 8929da96cca1..9c80d011594e 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -33,6 +33,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/pagemap.h>
 #include <linux/perf_event.h>
 #include <linux/highmem.h>
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9efe12376af1..4c5fa704e38c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -87,6 +87,7 @@
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/flex_array.h>
 #include <linux/posix-timers.h>
 #ifdef CONFIG_HARDWALL
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5d6960f5f1c0..550e8b183abe 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <linux/binfmts.h>
+#include <linux/sched/coredump.h>
 
 struct ctl_table_header;
 struct mempolicy;
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 1e032a1ddb3e..5d9a400af509 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -1,7 +1,8 @@
 #ifndef _LINUX_KHUGEPAGED_H
 #define _LINUX_KHUGEPAGED_H
 
-#include <linux/sched.h> /* MMF_VM_HUGEPAGE */
+#include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */
+
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern struct attribute_group khugepaged_attr_group;
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 481c8c4627ca..e1cfda4bee58 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -12,6 +12,7 @@
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/sched.h>
+#include <linux/sched/coredump.h>
 
 struct stable_node;
 struct mem_cgroup;
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
new file mode 100644
index 000000000000..ab81e564e076
--- /dev/null
+++ b/include/linux/sched/coredump.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_COREDUMP_H
+#define _LINUX_SCHED_COREDUMP_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/kernel/cred.c b/kernel/cred.c
index 5f264fb5737d..2bc66075740f 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -12,6 +12,7 @@
 #include <linux/cred.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/coredump.h>
 #include <linux/key.h>
 #include <linux/keyctl.h>
 #include <linux/init_task.h>
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 62f2dbd13efc..0e137f98a50c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/export.h>
 #include <linux/rmap.h>		/* anon_vma_prepare */
 #include <linux/mmu_notifier.h>	/* set_pte_at_notify */
diff --git a/kernel/fork.c b/kernel/fork.c
index 1875468e2a81..7332448b668a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
 #include <linux/module.h>
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 6fe5a2897912..bcdbdc19eb35 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
diff --git a/kernel/sys.c b/kernel/sys.c
index dc71ec1e1967..e2d743fb7f55 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -52,6 +52,7 @@
 #include <linux/sched/autogroup.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/rcupdate.h>
 #include <linux/uidgid.h>
 #include <linux/cred.h>
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index bb260ceb3718..acf0a5a06da7 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -63,6 +63,7 @@
 #include <linux/capability.h>
 #include <linux/binfmts.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/coredump.h>
 #include <linux/kexec.h>
 #include <linux/bpf.h>
 #include <linux/mount.h>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 71e3dede95b4..dee92fa26bbb 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -9,6 +9,7 @@
 
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/coredump.h>
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
 #include <linux/mmu_notifier.h>
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 212a2afe8830..ba40b7f673f4 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -3,6 +3,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/mmu_notifier.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
diff --git a/mm/ksm.c b/mm/ksm.c
index 5632c9d02457..19b4f2dea7a5 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -20,6 +20,7 @@
 #include <linux/mman.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
diff --git a/mm/memory.c b/mm/memory.c
index b0495ec74d29..6fc918b2c459 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -41,6 +41,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d28936618698..69f75b014607 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -23,6 +23,7 @@
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
 #include <linux/swap.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
-- 
GitLab


From 3f07c0144132e4f59d88055ac8ff3e691a5fa2b8 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:30 +0100
Subject: [PATCH 483/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/signal.h>

We are going to split <linux/sched/signal.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/signal.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/kernel/osf_sys.c                                 | 2 +-
 arch/alpha/kernel/signal.c                                  | 2 +-
 arch/alpha/kernel/traps.c                                   | 2 +-
 arch/alpha/mm/fault.c                                       | 2 +-
 arch/arc/kernel/traps.c                                     | 2 +-
 arch/arc/mm/fault.c                                         | 2 +-
 arch/arm/kernel/ptrace.c                                    | 2 +-
 arch/arm/kernel/traps.c                                     | 2 +-
 arch/arm/mm/alignment.c                                     | 2 +-
 arch/arm/mm/fault.c                                         | 2 +-
 arch/arm/mm/init.c                                          | 1 +
 arch/arm/mm/mmap.c                                          | 2 +-
 arch/arm/vfp/vfpmodule.c                                    | 2 +-
 arch/arm64/kernel/fpsimd.c                                  | 2 +-
 arch/arm64/kernel/ptrace.c                                  | 2 +-
 arch/arm64/kernel/traps.c                                   | 2 +-
 arch/arm64/mm/fault.c                                       | 2 +-
 arch/arm64/mm/mmap.c                                        | 2 +-
 arch/avr32/kernel/traps.c                                   | 2 +-
 arch/blackfin/kernel/trace.c                                | 2 +-
 arch/blackfin/kernel/traps.c                                | 1 +
 arch/cris/mm/fault.c                                        | 1 +
 arch/frv/kernel/traps.c                                     | 2 +-
 arch/h8300/kernel/ptrace_s.c                                | 2 +-
 arch/hexagon/kernel/traps.c                                 | 2 +-
 arch/hexagon/mm/vm_fault.c                                  | 1 +
 arch/ia64/kernel/asm-offsets.c                              | 2 +-
 arch/ia64/kernel/brl_emu.c                                  | 2 +-
 arch/ia64/kernel/mca.c                                      | 2 +-
 arch/ia64/kernel/traps.c                                    | 2 +-
 arch/ia64/kernel/unaligned.c                                | 2 +-
 arch/ia64/mm/fault.c                                        | 2 +-
 arch/ia64/mm/init.c                                         | 1 +
 arch/mips/kernel/branch.c                                   | 2 +-
 arch/mips/kernel/signal_o32.c                               | 1 +
 arch/mips/mm/mmap.c                                         | 2 +-
 arch/mips/sgi-ip22/ip22-berr.c                              | 2 +-
 arch/mips/sgi-ip22/ip22-reset.c                             | 2 +-
 arch/mn10300/kernel/fpu.c                                   | 2 ++
 arch/openrisc/mm/fault.c                                    | 2 +-
 arch/parisc/kernel/sys_parisc.c                             | 1 +
 arch/parisc/kernel/unaligned.c                              | 2 +-
 arch/parisc/math-emu/driver.c                               | 3 ++-
 arch/powerpc/kvm/book3s_64_vio.c                            | 1 +
 arch/powerpc/mm/mmap.c                                      | 2 +-
 arch/powerpc/mm/mmu_context_iommu.c                         | 2 +-
 arch/powerpc/platforms/cell/spufs/fault.c                   | 2 +-
 arch/powerpc/xmon/xmon.c                                    | 2 +-
 arch/s390/kernel/nmi.c                                      | 3 +++
 arch/s390/mm/mmap.c                                         | 1 +
 arch/score/kernel/traps.c                                   | 2 +-
 arch/sh/kernel/cpu/sh2a/fpu.c                               | 2 +-
 arch/sh/kernel/hw_breakpoint.c                              | 1 +
 arch/sh/kernel/traps.c                                      | 2 ++
 arch/sh/math-emu/math.c                                     | 2 +-
 arch/sh/mm/asids-debugfs.c                                  | 2 ++
 arch/sh/mm/fault.c                                          | 1 +
 arch/sparc/kernel/sys_sparc_32.c                            | 2 +-
 arch/sparc/kernel/sys_sparc_64.c                            | 2 +-
 arch/sparc/kernel/unaligned_32.c                            | 2 +-
 arch/tile/mm/mmap.c                                         | 2 +-
 arch/um/drivers/line.c                                      | 3 ++-
 arch/um/kernel/reboot.c                                     | 2 +-
 arch/um/kernel/skas/mmu.c                                   | 3 ++-
 arch/um/kernel/tlb.c                                        | 3 ++-
 arch/um/kernel/trap.c                                       | 2 +-
 arch/unicore32/kernel/fpu-ucf64.c                           | 2 +-
 arch/unicore32/kernel/traps.c                               | 1 +
 arch/unicore32/mm/fault.c                                   | 2 +-
 arch/x86/entry/vsyscall/vsyscall_64.c                       | 1 +
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c                    | 2 +-
 arch/x86/kvm/mmu.c                                          | 1 +
 arch/x86/mm/mmap.c                                          | 2 +-
 arch/xtensa/kernel/traps.c                                  | 2 +-
 drivers/android/binder.c                                    | 2 +-
 drivers/block/drbd/drbd_int.h                               | 2 +-
 drivers/char/snsc_event.c                                   | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_events.c                     | 2 +-
 drivers/gpu/drm/drm_lock.c                                  | 2 ++
 drivers/gpu/drm/ttm/ttm_lock.c                              | 2 +-
 drivers/infiniband/core/umem.c                              | 2 +-
 drivers/infiniband/hw/hfi1/user_pages.c                     | 2 +-
 drivers/infiniband/hw/qib/qib_user_pages.c                  | 1 +
 drivers/infiniband/hw/usnic/usnic_uiom.c                    | 2 +-
 drivers/isdn/i4l/isdn_tty.c                                 | 1 +
 drivers/isdn/mISDN/l1oip_core.c                             | 2 ++
 drivers/md/md.c                                             | 1 +
 drivers/md/raid1.c                                          | 3 +++
 drivers/md/raid5.c                                          | 2 ++
 drivers/misc/genwqe/card_dev.c                              | 2 +-
 drivers/misc/mic/cosm/cosm_scif_server.c                    | 2 ++
 drivers/misc/mic/cosm_client/cosm_scif_client.c             | 2 ++
 drivers/misc/mic/scif/scif_rma.c                            | 1 +
 drivers/net/slip/slip.c                                     | 2 +-
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c     | 2 +-
 drivers/parisc/power.c                                      | 2 +-
 drivers/ps3/ps3-sys-manager.c                               | 1 +
 drivers/s390/char/fs3270.c                                  | 1 +
 drivers/s390/char/keyboard.c                                | 2 +-
 drivers/scsi/bnx2fc/bnx2fc.h                                | 2 +-
 drivers/scsi/bnx2i/bnx2i.h                                  | 2 +-
 drivers/scsi/libiscsi.c                                     | 1 +
 drivers/staging/android/lowmemorykiller.c                   | 2 +-
 drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c       | 2 +-
 drivers/staging/rtl8188eu/include/osdep_service.h           | 2 +-
 drivers/staging/rtl8712/osdep_service.h                     | 2 +-
 drivers/staging/rtl8712/rtl8712_cmd.c                       | 1 +
 .../staging/vc04_services/interface/vchiq_arm/vchiq_arm.c   | 1 +
 .../staging/vc04_services/interface/vchiq_arm/vchiq_util.h  | 2 +-
 drivers/target/iscsi/iscsi_target.c                         | 1 +
 drivers/target/iscsi/iscsi_target_erl0.c                    | 2 ++
 drivers/target/iscsi/iscsi_target_login.c                   | 1 +
 drivers/target/iscsi/iscsi_target_nego.c                    | 1 +
 drivers/tty/pty.c                                           | 2 +-
 drivers/tty/sysrq.c                                         | 2 +-
 drivers/tty/tty_io.c                                        | 2 +-
 drivers/tty/vt/keyboard.c                                   | 2 +-
 drivers/tty/vt/vt.c                                         | 2 +-
 drivers/tty/vt/vt_ioctl.c                                   | 2 +-
 drivers/usb/atm/usbatm.c                                    | 2 +-
 drivers/usb/core/devio.c                                    | 1 +
 drivers/usb/gadget/function/f_mass_storage.c                | 1 +
 drivers/vfio/vfio_iommu_spapr_tce.c                         | 1 +
 drivers/vfio/vfio_iommu_type1.c                             | 2 +-
 drivers/w1/w1_family.c                                      | 2 +-
 drivers/w1/w1_int.c                                         | 1 +
 fs/attr.c                                                   | 1 +
 fs/autofs4/waitq.c                                          | 1 +
 fs/cifs/connect.c                                           | 1 +
 fs/coda/upcall.c                                            | 2 +-
 fs/coredump.c                                               | 2 +-
 fs/exec.c                                                   | 1 +
 fs/file.c                                                   | 2 +-
 fs/fs_struct.c                                              | 2 +-
 fs/jffs2/background.c                                       | 2 +-
 fs/lockd/svc.c                                              | 2 +-
 fs/ncpfs/inode.c                                            | 1 +
 fs/ncpfs/sock.c                                             | 1 +
 fs/nfs/callback.c                                           | 1 +
 fs/nfsd/nfssvc.c                                            | 2 +-
 fs/proc/fd.c                                                | 2 +-
 fs/select.c                                                 | 4 ++--
 include/linux/oom.h                                         | 2 +-
 include/linux/ptrace.h                                      | 1 +
 include/linux/sched/signal.h                                | 6 ++++++
 include/linux/signalfd.h                                    | 2 +-
 include/linux/taskstats_kern.h                              | 2 +-
 ipc/mqueue.c                                                | 1 +
 kernel/bpf/syscall.c                                        | 1 +
 kernel/cpu.c                                                | 2 +-
 kernel/debug/gdbstub.c                                      | 1 +
 kernel/debug/kdb/kdb_bt.c                                   | 2 +-
 kernel/hung_task.c                                          | 2 ++
 kernel/rcu/update.c                                         | 2 +-
 kernel/sched/sched.h                                        | 1 +
 kernel/time/itimer.c                                        | 1 +
 kernel/time/posix-cpu-timers.c                              | 2 +-
 kernel/time/tick-sched.c                                    | 2 +-
 kernel/tracepoint.c                                         | 2 +-
 kernel/tsacct.c                                             | 2 +-
 kernel/user_namespace.c                                     | 1 +
 lib/is_single_threaded.c                                    | 3 +--
 mm/filemap.c                                                | 1 +
 mm/kmemleak.c                                               | 2 +-
 mm/memory-failure.c                                         | 2 +-
 mm/vmacache.c                                               | 2 +-
 net/9p/client.c                                             | 2 +-
 net/atm/common.c                                            | 2 +-
 net/ax25/af_ax25.c                                          | 2 +-
 net/caif/caif_socket.c                                      | 2 +-
 net/core/stream.c                                           | 1 +
 net/decnet/af_decnet.c                                      | 2 +-
 net/irda/af_irda.c                                          | 1 +
 net/netrom/af_netrom.c                                      | 2 +-
 net/rose/af_rose.c                                          | 2 +-
 net/sctp/socket.c                                           | 1 +
 net/sunrpc/svc.c                                            | 2 +-
 net/unix/af_unix.c                                          | 2 +-
 net/x25/af_x25.c                                            | 2 +-
 security/selinux/hooks.c                                    | 2 +-
 180 files changed, 204 insertions(+), 121 deletions(-)
 create mode 100644 include/linux/sched/signal.h

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 9d27a7d333dc..568ca29f2ad9 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 17308f925306..b8221f112eee 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -6,7 +6,7 @@
  *  1997-11-02  Modified for POSIX.1b signals by Richard Henderson
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/errno.h>
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index af2994206b4b..6448ab00043d 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -10,7 +10,7 @@
 
 #include <linux/jiffies.h>
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/tty.h>
 #include <linux/delay.h>
 #include <linux/extable.h>
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 47948b4dd157..c25e8827e7cd 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -4,7 +4,7 @@
  *  Copyright (C) 1995  Linus Torvalds
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <asm/io.h>
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
index c927aa84e652..ff83e78d0cfb 100644
--- a/arch/arc/kernel/traps.c
+++ b/arch/arc/kernel/traps.c
@@ -13,7 +13,7 @@
  * Rahul Trivedi: Codito Technologies 2004
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kdebug.h>
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index e94e5aa33985..162c97528872 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -9,7 +9,7 @@
 
 #include <linux/signal.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ae738a6319f6..46f7bab81c40 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -10,7 +10,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/elf.h>
 #include <linux/smp.h>
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 9688ec0c6ef4..dc5f1a22b3c9 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -24,7 +24,7 @@
 #include <linux/bug.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/irq.h>
 
 #include <linux/atomic.h>
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 7d5f4c736a16..d7fe2de9cc9e 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -19,7 +19,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 
 #include <asm/cp15.h>
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c2b5b9892fd1..520c7778d330 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -16,7 +16,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/page-flags.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index bf4d3bc41a7a..2a9040dcf47e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/mman.h>
+#include <linux/sched/signal.h>
 #include <linux/export.h>
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 66353caa35b9..d448f9cd7715 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -5,7 +5,7 @@
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/shm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/io.h>
 #include <linux/personality.h>
 #include <linux/random.h>
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 569d5a650a4a..a71a48e71fff 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/notifier.h>
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/uaccess.h>
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index b883f1f75216..06da8ea16bbe 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -21,7 +21,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/hardirq.h>
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index a22161ccf447..64fc32ea3422 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -22,7 +22,7 @@
 #include <linux/audit.h>
 #include <linux/compat.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/ptrace.h>
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 7d47c2cdfd93..5b8779a849a2 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -29,7 +29,7 @@
 #include <linux/kexec.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/syscalls.h>
 
 #include <asm/atomic.h>
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 81283851c9af..30dd60ab8a65 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -26,7 +26,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/page-flags.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 #include <linux/preempt.h>
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 01c171723bb3..1e0a2650c88b 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -22,7 +22,7 @@
 #include <linux/mman.h>
 #include <linux/export.h>
 #include <linux/shm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/io.h>
 #include <linux/personality.h>
 #include <linux/random.h>
diff --git a/arch/avr32/kernel/traps.c b/arch/avr32/kernel/traps.c
index eb4a3fcfbaff..50b541325025 100644
--- a/arch/avr32/kernel/traps.c
+++ b/arch/avr32/kernel/traps.c
@@ -14,7 +14,7 @@
 #include <linux/extable.h>
 #include <linux/module.h>	/* print_modules */
 #include <linux/notifier.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 
 #include <asm/addrspace.h>
diff --git a/arch/blackfin/kernel/trace.c b/arch/blackfin/kernel/trace.c
index 719dd796c12c..01e546ad2f7a 100644
--- a/arch/blackfin/kernel/trace.c
+++ b/arch/blackfin/kernel/trace.c
@@ -11,7 +11,7 @@
 #include <linux/thread_info.h>
 #include <linux/mm.h>
 #include <linux/oom.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
diff --git a/arch/blackfin/kernel/traps.c b/arch/blackfin/kernel/traps.c
index 1ed85ddadc0d..32676d7721b1 100644
--- a/arch/blackfin/kernel/traps.c
+++ b/arch/blackfin/kernel/traps.c
@@ -9,6 +9,7 @@
 #include <linux/bug.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <asm/traps.h>
 #include <asm/cplb.h>
 #include <asm/blackfin.h>
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 94183d3639ef..1fca464f1b9e 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -8,6 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/extable.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <arch/system.h>
 
diff --git a/arch/frv/kernel/traps.c b/arch/frv/kernel/traps.c
index 31221fb4348e..43c134d6081c 100644
--- a/arch/frv/kernel/traps.c
+++ b/arch/frv/kernel/traps.c
@@ -9,7 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/h8300/kernel/ptrace_s.c b/arch/h8300/kernel/ptrace_s.c
index ef5a9c13e76d..c0af930052c0 100644
--- a/arch/h8300/kernel/ptrace_s.c
+++ b/arch/h8300/kernel/ptrace_s.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index 110dab152f82..4496bcf605ef 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -19,7 +19,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/kdebug.h>
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 489875fd2be4..3eec33c5cfd7 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -28,6 +28,7 @@
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/extable.h>
 #include <linux/hardirq.h>
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 60ef83e6db71..8786c8b4f187 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -6,7 +6,7 @@
 
 #define ASM_OFFSETS_C 1
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/pid.h>
 #include <linux/clocksource.h>
 #include <linux/kbuild.h>
diff --git a/arch/ia64/kernel/brl_emu.c b/arch/ia64/kernel/brl_emu.c
index 8682df6263d6..987b11be0021 100644
--- a/arch/ia64/kernel/brl_emu.c
+++ b/arch/ia64/kernel/brl_emu.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <asm/processor.h>
 
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 9509cc73b9c6..5ac51069e453 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -72,7 +72,7 @@
 #include <linux/jiffies.h>
 #include <linux/types.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/bootmem.h>
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index 8981ce98afb3..48ba46b025e1 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -9,7 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/tty.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/export.h>
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 99348d7f2255..a13680ca1e61 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -15,7 +15,7 @@
  */
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/tty.h>
 #include <linux/extable.h>
 #include <linux/ratelimit.h>
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 7f2feb21753c..15f09cfff335 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -4,7 +4,7 @@
  * Copyright (C) 1998-2002 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/extable.h>
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 06cdaef54b2e..8f3efa682ee8 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -12,6 +12,7 @@
 #include <linux/elf.h>
 #include <linux/memblock.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/mmzone.h>
 #include <linux/module.h>
 #include <linux/personality.h>
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index ae037a304ee4..b11facd11c9d 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -7,7 +7,7 @@
  * Copyright (C) 2001 MIPS Technologies, Inc.
  */
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/export.h>
 #include <asm/branch.h>
diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c
index 5e169fc5ca5c..2b3572fb5f1b 100644
--- a/arch/mips/kernel/signal_o32.c
+++ b/arch/mips/kernel/signal_o32.c
@@ -11,6 +11,7 @@
 #include <linux/compiler.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 
 #include <asm/abi.h>
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index d6d92c02308d..374d71e61ef6 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -13,7 +13,7 @@
 #include <linux/export.h>
 #include <linux/personality.h>
 #include <linux/random.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
 EXPORT_SYMBOL(shm_align_mask);
diff --git a/arch/mips/sgi-ip22/ip22-berr.c b/arch/mips/sgi-ip22/ip22-berr.c
index 3f6ccd53c15d..ff8e1935c873 100644
--- a/arch/mips/sgi-ip22/ip22-berr.c
+++ b/arch/mips/sgi-ip22/ip22-berr.c
@@ -6,7 +6,7 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 #include <asm/addrspace.h>
 #include <asm/traps.h>
diff --git a/arch/mips/sgi-ip22/ip22-reset.c b/arch/mips/sgi-ip22/ip22-reset.c
index a36f6b87548a..03a39ac5ead9 100644
--- a/arch/mips/sgi-ip22/ip22-reset.c
+++ b/arch/mips/sgi-ip22/ip22-reset.c
@@ -10,7 +10,7 @@
 #include <linux/rtc/ds1286.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/notifier.h>
 #include <linux/pm.h>
 #include <linux/timer.h>
diff --git a/arch/mn10300/kernel/fpu.c b/arch/mn10300/kernel/fpu.c
index 2578b7ae7dd5..50ce7b447fed 100644
--- a/arch/mn10300/kernel/fpu.c
+++ b/arch/mn10300/kernel/fpu.c
@@ -9,6 +9,8 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 #include <linux/uaccess.h>
+#include <linux/sched/signal.h>
+
 #include <asm/fpu.h>
 #include <asm/elf.h>
 #include <asm/exceptions.h>
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 53592a639744..e310ab499385 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -18,7 +18,7 @@
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/extable.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 #include <linux/uaccess.h>
 #include <asm/siginfo.h>
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index bf3294171230..ce07cd3f2507 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -30,6 +30,7 @@
 #include <linux/linkage.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/sched/signal.h>
 #include <linux/shm.h>
 #include <linux/syscalls.h>
 #include <linux/utsname.h>
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index 0a21067ac0a3..a08ab481e556 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -23,7 +23,7 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/ratelimit.h>
 #include <linux/uaccess.h>
diff --git a/arch/parisc/math-emu/driver.c b/arch/parisc/math-emu/driver.c
index 09ef4136c693..2fb59d2e2b29 100644
--- a/arch/parisc/math-emu/driver.c
+++ b/arch/parisc/math-emu/driver.c
@@ -27,7 +27,8 @@
  *  Copyright (C) 2001	      Hewlett-Packard <bame@debian.org>
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+
 #include "float.h"
 #include "math-emu.h"
 
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index ab9d14c0e460..3e26cd4979f9 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -24,6 +24,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/hugetlb.h>
 #include <linux/list.h>
 #include <linux/anon_inodes.h>
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 2f1e44362198..8013861aeaa7 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -25,7 +25,7 @@
 #include <linux/personality.h>
 #include <linux/mm.h>
 #include <linux/random.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/elf-randomize.h>
 #include <linux/security.h>
 #include <linux/mman.h>
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 7de7124ac91b..497130c5c742 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -10,7 +10,7 @@
  *
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/rculist.h>
 #include <linux/vmalloc.h>
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index e29e4d5afa2d..870c0a82d560 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -19,7 +19,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 
 #include <asm/spu.h>
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 26fa03fc9f3c..16321ad9e70c 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -13,7 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
 #include <linux/reboot.h>
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 80c093e0c6f1..9bf8327154ee 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -13,6 +13,9 @@
 #include <linux/errno.h>
 #include <linux/hardirq.h>
 #include <linux/time.h>
+#include <linux/module.h>
+#include <linux/sched/signal.h>
+
 #include <linux/export.h>
 #include <asm/lowcore.h>
 #include <asm/smp.h>
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 7ae1282d5be9..5ea09403bb87 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -26,6 +26,7 @@
 #include <linux/personality.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/sched/signal.h>
 #include <linux/random.h>
 #include <linux/compat.h>
 #include <linux/security.h>
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index 569ac02f68df..fa624f30f783 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -24,7 +24,7 @@
  */
 
 #include <linux/extable.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 #include <asm/cacheflush.h>
 #include <asm/irq.h>
diff --git a/arch/sh/kernel/cpu/sh2a/fpu.c b/arch/sh/kernel/cpu/sh2a/fpu.c
index 98bbaa447c93..352f894bece1 100644
--- a/arch/sh/kernel/cpu/sh2a/fpu.c
+++ b/arch/sh/kernel/cpu/sh2a/fpu.c
@@ -9,7 +9,7 @@
  *
  * FIXME! These routines can be optimized in big endian case.
  */
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <asm/processor.h>
 #include <asm/io.h>
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index 2197fc584186..afe965712a69 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -11,6 +11,7 @@
  */
 #include <linux/init.h>
 #include <linux/perf_event.h>
+#include <linux/sched/signal.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/percpu.h>
 #include <linux/kallsyms.h>
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index 9513fa7840aa..3036dee854d1 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -8,6 +8,8 @@
 #include <linux/hardirq.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <linux/sched/signal.h>
+
 #include <linux/extable.h>
 #include <linux/module.h>	/* print_modules */
 #include <asm/unwinder.h>
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index 5078cb809750..c86f4360c6ce 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -10,7 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 
diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c
index bf95fdaedd0c..110bd35165bf 100644
--- a/arch/sh/mm/asids-debugfs.c
+++ b/arch/sh/mm/asids-debugfs.c
@@ -20,6 +20,8 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
+#include <linux/sched/signal.h>
+
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
 
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 9bf876780cef..6fd1bf7481c7 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -13,6 +13,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/hardirq.h>
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index fb7b185ee941..ae49639a484e 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -7,7 +7,7 @@
 
 #include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 884c70331345..54d3999d8119 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -7,7 +7,7 @@
 
 #include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/mm.h>
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index d20d4e3fd129..8367dce5f41b 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -8,7 +8,7 @@
 
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c
index ef61c597898b..377e312dc27e 100644
--- a/arch/tile/mm/mmap.c
+++ b/arch/tile/mm/mmap.c
@@ -17,7 +17,7 @@
 #include <linux/mm.h>
 #include <linux/random.h>
 #include <linux/limits.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mman.h>
 #include <linux/compat.h>
 
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index 62087028a9ce..366e57f5e8d6 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -5,8 +5,9 @@
 
 #include <linux/irqreturn.h>
 #include <linux/kd.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
+
 #include "chan.h"
 #include <irq_kern.h>
 #include <irq_user.h>
diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c
index b60a9f8cda75..79218106a033 100644
--- a/arch/um/kernel/reboot.c
+++ b/arch/um/kernel/reboot.c
@@ -3,7 +3,7 @@
  * Licensed under the GPL
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/oom.h>
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 3943e9d7d13d..7a1f2a936fd1 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -5,8 +5,9 @@
  */
 
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
+
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/sections.h>
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index 3777b82759bd..37508b190106 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -5,7 +5,8 @@
 
 #include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <as-layout.h>
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index ad8f206ab5e8..9711ae4aaa6a 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -4,7 +4,7 @@
  */
 
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/hardirq.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
diff --git a/arch/unicore32/kernel/fpu-ucf64.c b/arch/unicore32/kernel/fpu-ucf64.c
index a53343a90ca2..12c8c9527b8e 100644
--- a/arch/unicore32/kernel/fpu-ucf64.c
+++ b/arch/unicore32/kernel/fpu-ucf64.c
@@ -13,7 +13,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/init.h>
 
 #include <asm/fpu-ucf64.h>
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index c54e32410ead..7f5e06f9a202 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -14,6 +14,7 @@
  */
 #include <linux/module.h>
 #include <linux/signal.h>
+#include <linux/sched/signal.h>
 #include <linux/spinlock.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index b656d216a8a8..bbefcc46a45e 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -17,7 +17,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/page-flags.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/io.h>
 
 #include <asm/pgtable.h>
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 636c4b341f36..df91fb393a01 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -27,6 +27,7 @@
 
 #include <linux/kernel.h>
 #include <linux/timer.h>
+#include <linux/sched/signal.h>
 #include <linux/syscalls.h>
 #include <linux/ratelimit.h>
 
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 8af04afdfcb9..d48af18e7baf 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -25,7 +25,7 @@
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/task_work.h>
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1cda35277278..ac7810513d0e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -36,6 +36,7 @@
 #include <linux/compiler.h>
 #include <linux/srcu.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/hash.h>
 #include <linux/kern_levels.h>
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index d2dc0438d654..5eabf34008f1 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -28,7 +28,7 @@
 #include <linux/mm.h>
 #include <linux/random.h>
 #include <linux/limits.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <asm/elf.h>
 
 struct va_alignment __read_mostly va_align = {
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 282bf721a4d6..84abd66e680d 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -24,7 +24,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/stringify.h>
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index e33e7fbe870b..aae4d8d4be36 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -31,7 +31,7 @@
 #include <linux/poll.h>
 #include <linux/debugfs.h>
 #include <linux/rbtree.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 4cb8f21ff4ef..724d1c50fc52 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -30,7 +30,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/list.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
diff --git a/drivers/char/snsc_event.c b/drivers/char/snsc_event.c
index 59bcefd6ec7c..e452673dff66 100644
--- a/drivers/char/snsc_event.c
+++ b/drivers/char/snsc_event.c
@@ -16,7 +16,7 @@
  */
 
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <asm/byteorder.h>
 #include <asm/sn/sn_sal.h>
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 6a3470f84998..d1ce83d73a87 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -23,7 +23,7 @@
 #include <linux/mm_types.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index 32d43f86a8f2..96bb6badb818 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -34,6 +34,8 @@
  */
 
 #include <linux/export.h>
+#include <linux/sched/signal.h>
+
 #include <drm/drmP.h>
 #include "drm_legacy.h"
 #include "drm_internal.h"
diff --git a/drivers/gpu/drm/ttm/ttm_lock.c b/drivers/gpu/drm/ttm/ttm_lock.c
index f154fb1929bd..913f4318cdc0 100644
--- a/drivers/gpu/drm/ttm/ttm_lock.c
+++ b/drivers/gpu/drm/ttm/ttm_lock.c
@@ -33,7 +33,7 @@
 #include <linux/atomic.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 
 #define TTM_WRITE_LOCK_PENDING    (1 << 0)
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index d525b1a2986a..27f155d2df8d 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -34,7 +34,7 @@
 
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/export.h>
 #include <linux/hugetlb.h>
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 20f4ddcac3b0..68295a12b771 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -46,7 +46,7 @@
  */
 
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/device.h>
 #include <linux/module.h>
 
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 75f08624ac05..ce83ba9a12ef 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/device.h>
 
 #include "qib.h"
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index ba868be5af2e..c49db7c33979 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -34,7 +34,7 @@
 
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/iommu.h>
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 63eaa0a9f8a1..1b169559a240 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
+#include <linux/sched/signal.h>
 #include "isdn_common.h"
 #include "isdn_tty.h"
 #ifdef CONFIG_ISDN_AUDIO
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 67c21876c35f..6ceca7db62ad 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -234,6 +234,8 @@
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include "core.h"
 #include "l1oip.h"
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 985374f20e2e..548d1b8014f8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -44,6 +44,7 @@
 
 */
 
+#include <linux/sched/signal.h>
 #include <linux/kthread.h>
 #include <linux/blkdev.h>
 #include <linux/badblocks.h>
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7453d94eeed7..fbc2d7851b49 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -37,7 +37,10 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/ratelimit.h>
+#include <linux/sched/signal.h>
+
 #include <trace/events/block.h>
+
 #include "md.h"
 #include "raid1.h"
 #include "bitmap.h"
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2ce23b01dbb2..4fb09b3fcb41 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -55,6 +55,8 @@
 #include <linux/ratelimit.h>
 #include <linux/nodemask.h>
 #include <linux/flex_array.h>
+#include <linux/sched/signal.h>
+
 #include <trace/events/block.h>
 
 #include "md.h"
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index cb290b8ca0c8..dd4617764f14 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -29,7 +29,7 @@
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/fs.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/wait.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
diff --git a/drivers/misc/mic/cosm/cosm_scif_server.c b/drivers/misc/mic/cosm/cosm_scif_server.c
index 5696df4326b5..85f7d09cc65f 100644
--- a/drivers/misc/mic/cosm/cosm_scif_server.c
+++ b/drivers/misc/mic/cosm/cosm_scif_server.c
@@ -19,6 +19,8 @@
  *
  */
 #include <linux/kthread.h>
+#include <linux/sched/signal.h>
+
 #include "cosm_main.h"
 
 /*
diff --git a/drivers/misc/mic/cosm_client/cosm_scif_client.c b/drivers/misc/mic/cosm_client/cosm_scif_client.c
index 03e98bf1ac15..aa530fcceaa9 100644
--- a/drivers/misc/mic/cosm_client/cosm_scif_client.c
+++ b/drivers/misc/mic/cosm_client/cosm_scif_client.c
@@ -22,6 +22,8 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/kthread.h>
+#include <linux/sched/signal.h>
+
 #include "../cosm/cosm_main.h"
 
 #define COSM_SCIF_MAX_RETRIES 10
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index d0e9c60f944e..329727e00e97 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -18,6 +18,7 @@
 #include <linux/dma_remapping.h>
 #include <linux/pagemap.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
 
 #include "scif_main.h"
 #include "scif_map.h"
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 08db4d687533..1da31dc47f86 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -66,7 +66,7 @@
 
 #include <linux/uaccess.h>
 #include <linux/bitops.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index c5744b45ec8f..65689469c5a1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -22,7 +22,7 @@
 #include <linux/pci_ids.h>
 #include <linux/netdevice.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mmc/sdio.h>
 #include <linux/mmc/sdio_ids.h>
 #include <linux/mmc/sdio_func.h>
diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index ef31b77404ef..e2a3112f1c98 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -39,7 +39,7 @@
 #include <linux/kernel.h>
 #include <linux/notifier.h>
 #include <linux/reboot.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kthread.h>
 #include <linux/pm.h>
 
diff --git a/drivers/ps3/ps3-sys-manager.c b/drivers/ps3/ps3-sys-manager.c
index f2ab435954f6..73e496a72113 100644
--- a/drivers/ps3/ps3-sys-manager.c
+++ b/drivers/ps3/ps3-sys-manager.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/workqueue.h>
 #include <linux/reboot.h>
+#include <linux/sched/signal.h>
 
 #include <asm/firmware.h>
 #include <asm/lv1call.h>
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index 85eca1cef063..c4518168fd02 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/slab.h>
diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c
index 82c913318b73..ba0e4f93503d 100644
--- a/drivers/s390/char/keyboard.c
+++ b/drivers/s390/char/keyboard.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/sysrq.h>
 
diff --git a/drivers/scsi/bnx2fc/bnx2fc.h b/drivers/scsi/bnx2fc/bnx2fc.h
index fdd4eb4e41b2..4fc8ed5fe067 100644
--- a/drivers/scsi/bnx2fc/bnx2fc.h
+++ b/drivers/scsi/bnx2fc/bnx2fc.h
@@ -39,7 +39,7 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/io.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/bnx2i/bnx2i.h b/drivers/scsi/bnx2i/bnx2i.h
index ed7f3228e234..89ef1a1678d1 100644
--- a/drivers/scsi/bnx2i/bnx2i.h
+++ b/drivers/scsi/bnx2i/bnx2i.h
@@ -25,7 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/in.h>
 #include <linux/kfifo.h>
 #include <linux/netdevice.h>
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 834d1212b6d5..07c08ce68d70 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <asm/unaligned.h>
 #include <net/tcp.h>
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index ec3b66561412..054660049395 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -37,7 +37,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/oom.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/swap.h>
 #include <linux/rcupdate.h>
 #include <linux/profile.h>
diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c
index cf902154f0aa..bcf9f3dd0310 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c
@@ -34,7 +34,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fs_struct.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 #include "../../../include/linux/libcfs/libcfs.h"
 
diff --git a/drivers/staging/rtl8188eu/include/osdep_service.h b/drivers/staging/rtl8188eu/include/osdep_service.h
index ee3f5ee06529..9e390648d93e 100644
--- a/drivers/staging/rtl8188eu/include/osdep_service.h
+++ b/drivers/staging/rtl8188eu/include/osdep_service.h
@@ -37,7 +37,7 @@
 #include <linux/io.h>
 #include <linux/mutex.h>
 #include <linux/sem.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/etherdevice.h>
 #include <linux/wireless.h>
 #include <net/iw_handler.h>
diff --git a/drivers/staging/rtl8712/osdep_service.h b/drivers/staging/rtl8712/osdep_service.h
index b8a170978434..5d33020554cd 100644
--- a/drivers/staging/rtl8712/osdep_service.h
+++ b/drivers/staging/rtl8712/osdep_service.h
@@ -33,7 +33,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/semaphore.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sem.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c
index f19b6b27aa71..5346c657485d 100644
--- a/drivers/staging/rtl8712/rtl8712_cmd.c
+++ b/drivers/staging/rtl8712/rtl8712_cmd.c
@@ -32,6 +32,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <linux/kref.h>
 #include <linux/netdevice.h>
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index cb0b7ca36b1e..8a0d214f6e9b 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -34,6 +34,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/cdev.h>
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_util.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_util.h
index 4055d4bf9f74..e63964f5a18a 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_util.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_util.h
@@ -47,7 +47,7 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/random.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/ctype.h>
 #include <linux/uaccess.h>
 #include <linux/time.h>  /* for time_t */
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index da2c73a255de..fa1d578d56bd 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -24,6 +24,7 @@
 #include <linux/vmalloc.h>
 #include <linux/idr.h>
 #include <linux/delay.h>
+#include <linux/sched/signal.h>
 #include <asm/unaligned.h>
 #include <net/ipv6.h>
 #include <scsi/scsi_proto.h>
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index b54e72c7ab0f..a4d5e6749932 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -17,6 +17,8 @@
  * GNU General Public License for more details.
  ******************************************************************************/
 
+#include <linux/sched/signal.h>
+
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index eab274d17b5c..b03cc03423c1 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/kthread.h>
+#include <linux/sched/signal.h>
 #include <linux/idr.h>
 #include <linux/tcp.h>        /* TCP_NODELAY */
 #include <net/ipv6.h>         /* ipv6_addr_v4mapped() */
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 46388c9e08da..29eb09e0cd15 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -19,6 +19,7 @@
 #include <linux/ctype.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <net/sock.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index a23fa5ed1d67..66b59a15780d 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -12,7 +12,7 @@
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/fcntl.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/string.h>
 #include <linux/major.h>
 #include <linux/mm.h>
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 71136742e606..65db0aeb3d80 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -14,7 +14,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
 #include <linux/interrupt.h>
 #include <linux/mm.h>
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index a1fd3f7d487a..985d33f0f315 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -69,7 +69,7 @@
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/fcntl.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/interrupt.h>
 #include <linux/tty.h>
 #include <linux/tty_driver.h>
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 397e1509fe51..6b3a2c00974d 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -26,7 +26,7 @@
 
 #include <linux/consolemap.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/mm.h>
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 9d3ce505e7ab..5c4933bb4b53 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -72,7 +72,7 @@
 
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/kernel.h>
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index a56edf2d58eb..0cbfe1ff6f6c 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -10,7 +10,7 @@
 
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/tty.h>
 #include <linux/timer.h>
 #include <linux/kernel.h>
diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c
index 5a59da0dc98a..3e80aa3b917a 100644
--- a/drivers/usb/atm/usbatm.c
+++ b/drivers/usb/atm/usbatm.c
@@ -74,7 +74,7 @@
 #include <linux/moduleparam.h>
 #include <linux/netdevice.h>
 #include <linux/proc_fs.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index ca425e8099ea..cfc3cff6e8d5 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -36,6 +36,7 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/signal.h>
 #include <linux/poll.h>
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 8f3659b65f53..4c8aacc232c0 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -207,6 +207,7 @@
 #include <linux/fs.h>
 #include <linux/kref.h>
 #include <linux/kthread.h>
+#include <linux/sched/signal.h>
 #include <linux/limits.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 185d50ee1b12..cf3de91fbfe7 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -21,6 +21,7 @@
 #include <linux/vfio.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
 
 #include <asm/iommu.h>
 #include <asm/tce.h>
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 7e94c7fc90ae..c26fa1f3ed86 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -31,7 +31,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/rbtree.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
diff --git a/drivers/w1/w1_family.c b/drivers/w1/w1_family.c
index df1c9bb90eb5..2096f460498f 100644
--- a/drivers/w1/w1_family.c
+++ b/drivers/w1/w1_family.c
@@ -14,7 +14,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/list.h>
-#include <linux/sched.h>	/* schedule_timeout() */
+#include <linux/sched/signal.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 
diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c
index 4ce1b66d5092..2cae7b29bb5f 100644
--- a/drivers/w1/w1_int.c
+++ b/drivers/w1/w1_int.c
@@ -17,6 +17,7 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/export.h>
 #include <linux/moduleparam.h>
 
diff --git a/fs/attr.c b/fs/attr.c
index c902b3d53508..135304146120 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -9,6 +9,7 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 #include <linux/capability.h>
 #include <linux/fsnotify.h>
 #include <linux/fcntl.h>
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 79fbd85db4ba..24a58bf9ca72 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/signal.h>
+#include <linux/sched/signal.h>
 #include <linux/file.h>
 #include "autofs_i.h"
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 777ad9f4fc3c..9bf25be05636 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/net.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 #include <linux/list.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index f6c6c8adbc01..e82357c89979 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/fs/coredump.c b/fs/coredump.c
index 23a539b29225..c74ab43b8383 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -17,6 +17,7 @@
 #include <linux/binfmts.h>
 #include <linux/coredump.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/signal.h>
 #include <linux/utsname.h>
 #include <linux/pid_namespace.h>
 #include <linux/module.h>
@@ -34,7 +35,6 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
-#include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/path.h>
 #include <linux/timekeeping.h>
diff --git a/fs/exec.c b/fs/exec.c
index 9c80d011594e..aa228b98ad5b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -34,6 +34,7 @@
 #include <linux/init.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/signal.h>
 #include <linux/pagemap.h>
 #include <linux/perf_event.h>
 #include <linux/highmem.h>
diff --git a/fs/file.c b/fs/file.c
index 69d6990e3021..ad6f094f2eff 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -12,7 +12,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/time.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/file.h>
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 7dca743b2ce1..543ed50f0387 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -1,5 +1,5 @@
 #include <linux/export.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/path.h>
 #include <linux/slab.h>
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index e5c1783ab64a..453a6a1fff34 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -16,7 +16,7 @@
 #include <linux/jffs2.h>
 #include <linux/mtd/mtd.h>
 #include <linux/completion.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include "nodelist.h"
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 7e4ea3b9f472..e7c8b9c76e48 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -17,7 +17,7 @@
 #include <linux/sysctl.h>
 #include <linux/moduleparam.h>
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/in.h>
 #include <linux/uio.h>
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 7eb89c23c847..d5606099712a 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -30,6 +30,7 @@
 #include <linux/vfs.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/sched/signal.h>
 #include <linux/namei.h>
 
 #include <net/sock.h>
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index 97b111d79489..bdea177aa405 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -16,6 +16,7 @@
 #include <linux/fcntl.h>
 #include <linux/stat.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/in.h>
 #include <linux/net.h>
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 484bebc20bca..bb79972dc638 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -9,6 +9,7 @@
 #include <linux/completion.h>
 #include <linux/ip.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index efd66da99201..786a4a2cb2d7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -6,7 +6,7 @@
  * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/freezer.h>
 #include <linux/module.h>
 #include <linux/fs_struct.h>
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 00ce1531b2f5..c330495c3115 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -1,4 +1,4 @@
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/dcache.h>
 #include <linux/path.h>
diff --git a/fs/select.c b/fs/select.c
index 305c0daf5d67..e2112270d75a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -15,7 +15,8 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/rt.h>
 #include <linux/syscalls.h>
 #include <linux/export.h>
 #include <linux/slab.h>
@@ -26,7 +27,6 @@
 #include <linux/fs.h>
 #include <linux/rcupdate.h>
 #include <linux/hrtimer.h>
-#include <linux/sched/rt.h>
 #include <linux/freezer.h>
 #include <net/busy_poll.h>
 #include <linux/vmalloc.h>
diff --git a/include/linux/oom.h b/include/linux/oom.h
index b4e36e92bc87..8a266e2be5a6 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -2,7 +2,7 @@
 #define __INCLUDE_LINUX_OOM_H
 
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/nodemask.h>
 #include <uapi/linux/oom.h>
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e0e539321ab9..422bc2e4cb6a 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -3,6 +3,7 @@
 
 #include <linux/compiler.h>		/* For unlikely.  */
 #include <linux/sched.h>		/* For struct task_struct.  */
+#include <linux/sched/signal.h>		/* For send_sig(), same_thread_group(), etc. */
 #include <linux/err.h>			/* for IS_ERR_VALUE */
 #include <linux/bug.h>			/* For BUG_ON.  */
 #include <linux/pid_namespace.h>	/* For task_active_pid_ns.  */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
new file mode 100644
index 000000000000..da69cd05cd68
--- /dev/null
+++ b/include/linux/sched/signal.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_SIGNAL_H
+#define _LINUX_SCHED_SIGNAL_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_SIGNAL_H */
diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h
index eadbe227c256..4985048640a7 100644
--- a/include/linux/signalfd.h
+++ b/include/linux/signalfd.h
@@ -8,7 +8,7 @@
 #define _LINUX_SIGNALFD_H
 
 #include <uapi/linux/signalfd.h>
-
+#include <linux/sched/signal.h>
 
 #ifdef CONFIG_SIGNALFD
 
diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h
index 58de6edf751f..e2a5daf8d14f 100644
--- a/include/linux/taskstats_kern.h
+++ b/include/linux/taskstats_kern.h
@@ -8,7 +8,7 @@
 #define _LINUX_TASKSTATS_KERN_H
 
 #include <linux/taskstats.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 
 #ifdef CONFIG_TASKSTATS
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 40e448de8a7e..4f7241fbeff3 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -36,6 +36,7 @@
 #include <linux/user_namespace.h>
 #include <linux/slab.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/signal.h>
 
 #include <net/sock.h>
 #include "util.h"
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 461eb1e66a0f..7af0dcc5d755 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -13,6 +13,7 @@
 #include <linux/bpf_trace.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/vmalloc.h>
 #include <linux/mmzone.h>
 #include <linux/anon_inodes.h>
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0a5f630f5c54..0aae3183b029 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -7,7 +7,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/notifier.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/unistd.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index 19d9a578c753..7510dc687c0d 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -29,6 +29,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/kgdb.h>
 #include <linux/kdb.h>
 #include <linux/serial_core.h>
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index fe15fff5df53..9b976a42376d 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -12,7 +12,7 @@
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kdb.h>
 #include <linux/nmi.h>
 #include "kdb_private.h"
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 40c07e4fa116..129247e56902 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -16,6 +16,8 @@
 #include <linux/export.h>
 #include <linux/sysctl.h>
 #include <linux/utsname.h>
+#include <linux/sched/signal.h>
+
 #include <trace/events/sched.h>
 
 /*
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index a0e90e0afc75..da128deb10ec 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -36,7 +36,7 @@
 #include <linux/spinlock.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/percpu.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e2307a6c29f1..641249471952 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -5,6 +5,7 @@
 #include <linux/sched/rt.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index a95f13c31464..f6b961c5e58c 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/syscalls.h>
 #include <linux/time.h>
+#include <linux/sched/signal.h>
 #include <linux/posix-timers.h>
 #include <linux/hrtimer.h>
 #include <trace/events/timer.h>
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index b4377a5e4269..a2475a9f57d8 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -2,7 +2,7 @@
  * Implement CPU time clocks for the POSIX clock interface.
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/posix-timers.h>
 #include <linux/errno.h>
 #include <linux/math64.h>
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 4fee1c3abd0b..0f411a4690a0 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -18,7 +18,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/percpu.h>
 #include <linux/profile.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/clock.h>
 #include <linux/module.h>
 #include <linux/irq_work.h>
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 1f9a31f934a4..9f6984d52fec 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -24,7 +24,7 @@
 #include <linux/tracepoint.h>
 #include <linux/err.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/static_key.h>
 
 extern struct tracepoint * const __start___tracepoints_ptrs[];
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 571a2d3821d8..d9a03b80b75d 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -17,7 +17,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/tsacct_kern.h>
 #include <linux/acct.h>
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 86b7854fec8e..2f735cbe05e8 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/user_namespace.h>
 #include <linux/proc_ns.h>
 #include <linux/highuid.h>
diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c
index 391fd23976a2..9745cfffcb69 100644
--- a/lib/is_single_threaded.c
+++ b/lib/is_single_threaded.c
@@ -9,8 +9,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the Licence, or (at your option) any later version.
  */
-
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 /*
  * Returns true if the task does not share ->mm with another thread/process.
diff --git a/mm/filemap.c b/mm/filemap.c
index 1944c631e3e6..1694623a6289 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -13,6 +13,7 @@
 #include <linux/compiler.h>
 #include <linux/dax.h>
 #include <linux/fs.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/capability.h>
 #include <linux/kernel_stat.h>
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index da3436953022..2df6d3687b2a 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -73,7 +73,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/jiffies.h>
 #include <linux/delay.h>
 #include <linux/export.h>
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 3d0f2fd4bf73..b74984db386e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -40,7 +40,7 @@
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/kernel-page-flags.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/ksm.h>
 #include <linux/rmap.h>
 #include <linux/export.h>
diff --git a/mm/vmacache.c b/mm/vmacache.c
index 7c233f8e20ee..4355d34c68a6 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -1,7 +1,7 @@
 /*
  * Copyright (C) 2014 Davidlohr Bueso.
  */
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/vmacache.h>
 
diff --git a/net/9p/client.c b/net/9p/client.c
index 3fc94a49ccd5..25cfd8a4bc36 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -32,7 +32,7 @@
 #include <linux/idr.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/uio.h>
 #include <net/9p/9p.h>
diff --git a/net/atm/common.c b/net/atm/common.c
index a3ca922d307b..9613381f5db0 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -13,7 +13,7 @@
 #include <linux/errno.h>	/* error codes */
 #include <linux/capability.h>
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/time.h>		/* struct timeval */
 #include <linux/skbuff.h>
 #include <linux/bitops.h>
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 90fcf5fc2e0a..a8e42cedf1db 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -20,7 +20,7 @@
 #include <linux/socket.h>
 #include <linux/in.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/timer.h>
 #include <linux/string.h>
 #include <linux/sockios.h>
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 92cbbd2afddb..adcad344c843 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -9,7 +9,7 @@
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
diff --git a/net/core/stream.c b/net/core/stream.c
index f575bcf64af2..20231dbb1da0 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/net.h>
 #include <linux/signal.h>
 #include <linux/tcp.h>
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index a90ed67027b0..e6e79eda9763 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -106,7 +106,7 @@ Version 0.0.6    2.1.110   07-aug-98   Eduardo Marcelo Serrat
 #include <linux/socket.h>
 #include <linux/in.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/timer.h>
 #include <linux/string.h>
 #include <linux/sockios.h>
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index ab254041dab7..81adc29a448d 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -46,6 +46,7 @@
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/init.h>
 #include <linux/net.h>
 #include <linux/irda.h>
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index ed212ffc1d9d..4bbf4526b885 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -17,7 +17,7 @@
 #include <linux/in.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/timer.h>
 #include <linux/string.h>
 #include <linux/sockios.h>
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 9ad301c46b88..b8a1df2c9785 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -20,7 +20,7 @@
 #include <linux/in.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/string.h>
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 465a9c8464f9..6f0a9be50f50 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -57,6 +57,7 @@
 #include <linux/kernel.h>
 #include <linux/wait.h>
 #include <linux/time.h>
+#include <linux/sched/signal.h>
 #include <linux/ip.h>
 #include <linux/capability.h>
 #include <linux/fcntl.h>
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index b94efd93d3e4..a08aeb56b8e4 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/net.h>
 #include <linux/in.h>
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e2d18b9f910f..ee37b390260a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -85,7 +85,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/stat.h>
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 079c883aa96e..fd28a49dbe8f 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -41,7 +41,7 @@
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/timer.h>
 #include <linux/string.h>
 #include <linux/net.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 9a8f12f8d5b7..b12f873f92ba 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -28,7 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/tracehook.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/lsm_hooks.h>
 #include <linux/xattr.h>
 #include <linux/capability.h>
-- 
GitLab


From 8703e8a465b1e9cadc3680b4b1248f5987e54518 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:30 +0100
Subject: [PATCH 484/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/user.h>

We are going to split <linux/sched/user.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/user.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 block/ioprio.c               | 1 +
 include/linux/cred.h         | 2 +-
 include/linux/sched/user.h   | 6 ++++++
 ipc/mqueue.c                 | 1 +
 kernel/fork.c                | 1 +
 kernel/signal.c              | 1 +
 kernel/user.c                | 1 +
 mm/mlock.c                   | 1 +
 net/core/scm.c               | 1 +
 security/keys/process_keys.c | 1 +
 10 files changed, 15 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/user.h

diff --git a/block/ioprio.c b/block/ioprio.c
index 3790669232ff..89c43e07787d 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -25,6 +25,7 @@
 #include <linux/ioprio.h>
 #include <linux/blkdev.h>
 #include <linux/capability.h>
+#include <linux/sched/user.h>
 #include <linux/syscalls.h>
 #include <linux/security.h>
 #include <linux/pid_namespace.h>
diff --git a/include/linux/cred.h b/include/linux/cred.h
index f0e70a1bb3ac..045d33e48069 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -18,8 +18,8 @@
 #include <linux/selinux.h>
 #include <linux/atomic.h>
 #include <linux/uidgid.h>
+#include <linux/sched/user.h>
 
-struct user_struct;
 struct cred;
 struct inode;
 
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
new file mode 100644
index 000000000000..83238e5ddadd
--- /dev/null
+++ b/include/linux/sched/user.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_USER_H
+#define _LINUX_SCHED_USER_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_USER_H */
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 4f7241fbeff3..e8d41ff57241 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -37,6 +37,7 @@
 #include <linux/slab.h>
 #include <linux/sched/wake_q.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/user.h>
 
 #include <net/sock.h>
 #include "util.h"
diff --git a/kernel/fork.c b/kernel/fork.c
index 7332448b668a..a5ad1e4ab604 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -15,6 +15,7 @@
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/user.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
 #include <linux/module.h>
diff --git a/kernel/signal.c b/kernel/signal.c
index bae358532d0a..762fcf64f0c3 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/user.h>
 #include <linux/fs.h>
 #include <linux/tty.h>
 #include <linux/binfmts.h>
diff --git a/kernel/user.c b/kernel/user.c
index b069ccbfb0b0..00281add65b2 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/bitops.h>
 #include <linux/key.h>
+#include <linux/sched/user.h>
 #include <linux/interrupt.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
diff --git a/mm/mlock.c b/mm/mlock.c
index cdbed8aaa426..1050511f8b2b 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -8,6 +8,7 @@
 #include <linux/capability.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/sched/user.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/pagemap.h>
diff --git a/net/core/scm.c b/net/core/scm.c
index b6d83686e149..b1ff8a441748 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -14,6 +14,7 @@
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/user.h>
 #include <linux/mm.h>
 #include <linux/kernel.h>
 #include <linux/stat.h>
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 918cddcd4516..b6fdd22205b1 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/user.h>
 #include <linux/keyctl.h>
 #include <linux/fs.h>
 #include <linux/err.h>
-- 
GitLab


From 38b8d208a4544c9a26b10baec89b8a21042e5305 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:31 +0100
Subject: [PATCH 485/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/nmi.h>

We are going to move softlockup APIs out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

<linux/nmi.h> already includes <linux/sched.h>.

Include the <linux/nmi.h> header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/ia64/kernel/time.c               | 1 +
 arch/ia64/kernel/uncached.c           | 1 +
 arch/powerpc/kernel/swsusp_64.c       | 1 +
 arch/x86/kernel/pvclock.c             | 2 ++
 arch/x86/xen/smp.c                    | 1 +
 drivers/ide/ide-taskfile.c            | 1 +
 drivers/mtd/nand/nand_base.c          | 1 +
 drivers/video/fbdev/nvidia/nv_accel.c | 2 ++
 init/main.c                           | 1 +
 kernel/debug/debug_core.c             | 1 +
 kernel/power/hibernate.c              | 1 +
 kernel/power/snapshot.c               | 1 +
 kernel/sched/clock.c                  | 1 +
 kernel/time/tick-sched.c              | 1 +
 kernel/time/timekeeping.c             | 1 +
 15 files changed, 17 insertions(+)

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index faa116822c4c..144f9db7a876 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -16,6 +16,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/time.h>
+#include <linux/nmi.h>
 #include <linux/interrupt.h>
 #include <linux/efi.h>
 #include <linux/timex.h>
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index f3976da36721..583f7ff6b589 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -19,6 +19,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/efi.h>
+#include <linux/nmi.h>
 #include <linux/genalloc.h>
 #include <linux/gfp.h>
 #include <asm/page.h>
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 0e899e47c325..51db012808f5 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -10,6 +10,7 @@
 #include <linux/irq.h>
 #include <linux/sched.h>
 #include <linux/interrupt.h>
+#include <linux/nmi.h>
 
 void do_after_copyback(void)
 {
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 9e93fe5803b4..5c3f6d6a5078 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -21,6 +21,8 @@
 #include <linux/sched.h>
 #include <linux/gfp.h>
 #include <linux/bootmem.h>
+#include <linux/nmi.h>
+
 #include <asm/fixmap.h>
 #include <asm/pvclock.h>
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 0dee6f59ea82..7ff2f1bfb7ec 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -18,6 +18,7 @@
 #include <linux/smp.h>
 #include <linux/irq_work.h>
 #include <linux/tick.h>
+#include <linux/nmi.h>
 
 #include <asm/paravirt.h>
 #include <asm/desc.h>
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index 247b9faccce1..4c0007cb74e3 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -19,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/hdreg.h>
 #include <linux/ide.h>
+#include <linux/nmi.h>
 #include <linux/scatterlist.h>
 #include <linux/uaccess.h>
 
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 1492c12906f6..b0524f8accb6 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -36,6 +36,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/nmi.h>
 #include <linux/types.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
diff --git a/drivers/video/fbdev/nvidia/nv_accel.c b/drivers/video/fbdev/nvidia/nv_accel.c
index ad6472a894ea..7341fed63e35 100644
--- a/drivers/video/fbdev/nvidia/nv_accel.c
+++ b/drivers/video/fbdev/nvidia/nv_accel.c
@@ -48,6 +48,8 @@
  */
 
 #include <linux/fb.h>
+#include <linux/nmi.h>
+
 #include "nv_type.h"
 #include "nv_proto.h"
 #include "nv_dma.h"
diff --git a/init/main.c b/init/main.c
index ae9f2008fb86..c891cfb8928f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -27,6 +27,7 @@
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
 #include <linux/tty.h>
+#include <linux/nmi.h>
 #include <linux/percpu.h>
 #include <linux/kmod.h>
 #include <linux/vmalloc.h>
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index a603ef28f70c..65c0f1363788 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -49,6 +49,7 @@
 #include <linux/init.h>
 #include <linux/kgdb.h>
 #include <linux/kdb.h>
+#include <linux/nmi.h>
 #include <linux/pid.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 86385af1080f..b8be5c803cdd 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/pm.h>
+#include <linux/nmi.h>
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 905d5bbd595f..d79a38de425a 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -22,6 +22,7 @@
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/nmi.h>
 #include <linux/syscalls.h>
 #include <linux/console.h>
 #include <linux/highmem.h>
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index dd7817cdbf58..a08795e21628 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -58,6 +58,7 @@
 #include <linux/percpu.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/nmi.h>
 #include <linux/sched/clock.h>
 #include <linux/static_key.h>
 #include <linux/workqueue.h>
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 0f411a4690a0..5e9e123b4321 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/percpu.h>
+#include <linux/nmi.h>
 #include <linux/profile.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/clock.h>
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fb564acee0f3..5b63a2102c29 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
 #include <linux/syscore_ops.h>
-- 
GitLab


From 55687da166bf51129ed6b110d7711f4c7560abe2 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:31 +0100
Subject: [PATCH 486/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/cpufreq.h>

We are going to split <linux/sched/cpufreq.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/cpufreq.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/cpufreq/cpufreq_governor.c | 1 -
 drivers/cpufreq/cpufreq_governor.h | 1 +
 drivers/cpufreq/cpufreq_ondemand.c | 1 +
 drivers/cpufreq/intel_pstate.c     | 2 +-
 include/linux/sched/cpufreq.h      | 6 ++++++
 kernel/sched/sched.h               | 1 +
 6 files changed, 10 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/sched/cpufreq.h

diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 631bd2c86c5e..47e24b5384b3 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -18,7 +18,6 @@
 
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 
 #include "cpufreq_governor.h"
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index f5717ca070cc..0236ec2cd654 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -20,6 +20,7 @@
 #include <linux/atomic.h>
 #include <linux/irq_work.h>
 #include <linux/cpufreq.h>
+#include <linux/sched/cpufreq.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 4a017e895296..3937acf7e026 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -16,6 +16,7 @@
 #include <linux/percpu-defs.h>
 #include <linux/slab.h>
 #include <linux/tick.h>
+#include <linux/sched/cpufreq.h>
 
 #include "cpufreq_ondemand.h"
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index eb0f7fb71685..8f6d29302aac 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -19,7 +19,7 @@
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/cpufreq.h>
 #include <linux/list.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
new file mode 100644
index 000000000000..07ed9664fa20
--- /dev/null
+++ b/include/linux/sched/cpufreq.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_CPUFREQ_H
+#define _LINUX_SCHED_CPUFREQ_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_CPUFREQ_H */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 641249471952..7dfeb14fa43c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -7,6 +7,7 @@
 #include <linux/sched/wake_q.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/cpufreq.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
 #include <linux/kernel_stat.h>
-- 
GitLab


From 010426079ec1228a7f980d2eef766a84c0f9241a Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:31 +0100
Subject: [PATCH 487/898] sched/headers: Prepare for new header dependencies
 before moving more code to <linux/sched/mm.h>

We are going to split more MM APIs out of <linux/sched.h>, which
will have to be picked up from a couple of .c files.

The APIs that we are going to move are:

  arch_pick_mmap_layout()
  arch_get_unmapped_area()
  arch_get_unmapped_area_topdown()
  mm_update_next_owner()

Include the header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/kernel/osf_sys.c      | 1 +
 arch/arc/mm/mmap.c               | 3 ++-
 arch/arm/mm/mmap.c               | 1 +
 arch/arm64/mm/mmap.c             | 1 +
 arch/frv/mm/elf-fdpic.c          | 1 +
 arch/ia64/kernel/sys_ia64.c      | 1 +
 arch/mips/mm/mmap.c              | 1 +
 arch/parisc/kernel/cache.c       | 1 +
 arch/parisc/kernel/sys_parisc.c  | 1 +
 arch/parisc/mm/hugetlbpage.c     | 1 +
 arch/powerpc/mm/mmap.c           | 1 +
 arch/s390/mm/mmap.c              | 1 +
 arch/sh/mm/mmap.c                | 1 +
 arch/sparc/kernel/sys_sparc_32.c | 1 +
 arch/sparc/kernel/sys_sparc_64.c | 1 +
 arch/sparc/mm/hugetlbpage.c      | 1 +
 arch/tile/mm/hugetlbpage.c       | 1 +
 arch/tile/mm/mmap.c              | 1 +
 arch/x86/kernel/sys_x86_64.c     | 1 +
 arch/x86/mm/hugetlbpage.c        | 1 +
 arch/x86/mm/mmap.c               | 1 +
 arch/xtensa/kernel/syscall.c     | 1 +
 22 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 568ca29f2ad9..3b9b2a382ba2 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -12,6 +12,7 @@
 
 #include <linux/errno.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
index 2e06d56e987b..3e25e8d6486b 100644
--- a/arch/arc/mm/mmap.c
+++ b/arch/arc/mm/mmap.c
@@ -13,7 +13,8 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
+
 #include <asm/cacheflush.h>
 
 #define COLOUR_ALIGN(addr, pgoff)			\
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index d448f9cd7715..2239fde10b80 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -6,6 +6,7 @@
 #include <linux/mman.h>
 #include <linux/shm.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/io.h>
 #include <linux/personality.h>
 #include <linux/random.h>
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 1e0a2650c88b..7b0d55756eb1 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -23,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/shm.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/io.h>
 #include <linux/personality.h>
 #include <linux/random.h>
diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c
index 836f14707a62..da82c25301e7 100644
--- a/arch/frv/mm/elf-fdpic.c
+++ b/arch/frv/mm/elf-fdpic.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/elf-fdpic.h>
diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c
index a09c12230bc5..ce4cc60d519b 100644
--- a/arch/ia64/kernel/sys_ia64.c
+++ b/arch/ia64/kernel/sys_ia64.c
@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/shm.h>
 #include <linux/file.h>		/* doh, must come after sched.h... */
 #include <linux/smp.h>
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 374d71e61ef6..64dd8bdd92c3 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -14,6 +14,7 @@
 #include <linux/personality.h>
 #include <linux/random.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 
 unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
 EXPORT_SYMBOL(shm_align_mask);
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 977f0a4f5ecf..7820b864de1a 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/pagemap.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <asm/pdc.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index ce07cd3f2507..e5288638a1d9 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -31,6 +31,7 @@
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/shm.h>
 #include <linux/syscalls.h>
 #include <linux/utsname.h>
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index 5d6eea925cf4..aa50ac090e9b 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -8,6 +8,7 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
 #include <linux/sysctl.h>
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 8013861aeaa7..a5d9ef59debe 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -26,6 +26,7 @@
 #include <linux/mm.h>
 #include <linux/random.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/elf-randomize.h>
 #include <linux/security.h>
 #include <linux/mman.h>
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 5ea09403bb87..50618614881f 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -27,6 +27,7 @@
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/random.h>
 #include <linux/compat.h>
 #include <linux/security.h>
diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c
index 6777177807c2..08e7af0be4a7 100644
--- a/arch/sh/mm/mmap.c
+++ b/arch/sh/mm/mmap.c
@@ -9,6 +9,7 @@
  */
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/mman.h>
 #include <linux/module.h>
 #include <asm/page.h>
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index ae49639a484e..ff3573059936 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -8,6 +8,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 54d3999d8119..c521ee277083 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -8,6 +8,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/mm.h>
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index e98a3f2e8f0f..323bc6b6e3ad 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -6,6 +6,7 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
 #include <linux/sysctl.h>
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 77ceaa343fce..cb10153b5c9f 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c
index 377e312dc27e..8ab28167c44b 100644
--- a/arch/tile/mm/mmap.c
+++ b/arch/tile/mm/mmap.c
@@ -18,6 +18,7 @@
 #include <linux/random.h>
 #include <linux/limits.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/mman.h>
 #include <linux/compat.h>
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index a55ed63b9f91..50215a4b9347 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -1,5 +1,6 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/syscalls.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 2ae8584b44c7..c5066a260803 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
 #include <linux/err.h>
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 5eabf34008f1..7940166c799b 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -29,6 +29,7 @@
 #include <linux/random.h>
 #include <linux/limits.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <asm/elf.h>
 
 struct va_alignment __read_mostly va_align = {
diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index d3fd100dffc9..06937928cb72 100644
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -25,6 +25,7 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/mman.h>
+#include <linux/sched/mm.h>
 #include <linux/shm.h>
 
 typedef void (*syscall_t)(void);
-- 
GitLab


From 6a3827d7509cbf96b7e961f8957c1f01d1bcf894 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:31 +0100
Subject: [PATCH 488/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/numa_balancing.h>

We are going to split <linux/sched/numa_balancing.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/numa_balancing.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/exec.c                            | 1 +
 fs/proc/array.c                      | 1 +
 include/linux/sched/numa_balancing.h | 6 ++++++
 include/trace/events/sched.h         | 2 +-
 kernel/fork.c                        | 1 +
 kernel/sched/sched.h                 | 1 +
 mm/huge_memory.c                     | 1 +
 mm/memory.c                          | 1 +
 mm/mempolicy.c                       | 1 +
 9 files changed, 14 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/numa_balancing.h

diff --git a/fs/exec.c b/fs/exec.c
index aa228b98ad5b..e857c7260b1f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -35,6 +35,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/pagemap.h>
 #include <linux/perf_event.h>
 #include <linux/highmem.h>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 61bea3a4ecc5..cfe7f934a300 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -61,6 +61,7 @@
 #include <linux/string.h>
 #include <linux/mman.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/proc_fs.h>
 #include <linux/ioport.h>
 #include <linux/uaccess.h>
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
new file mode 100644
index 000000000000..999182279f78
--- /dev/null
+++ b/include/linux/sched/numa_balancing.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_NUMA_BALANCING_H
+#define _LINUX_SCHED_NUMA_BALANCING_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_NUMA_BALANCING_H */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9b90c57517a9..9e3ef6c99e4b 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -4,7 +4,7 @@
 #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_SCHED_H
 
-#include <linux/sched.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/tracepoint.h>
 #include <linux/binfmts.h>
 
diff --git a/kernel/fork.c b/kernel/fork.c
index a5ad1e4ab604..08d6c091ac7c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -16,6 +16,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/user.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
 #include <linux/module.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7dfeb14fa43c..7e8ce0347fbf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -6,6 +6,7 @@
 #include <linux/sched/clock.h>
 #include <linux/sched/wake_q.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/cpufreq.h>
 #include <linux/u64_stats_sync.h>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index dee92fa26bbb..d36b2af4d1bf 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
 #include <linux/mmu_notifier.h>
diff --git a/mm/memory.c b/mm/memory.c
index 6fc918b2c459..d4994a28dc85 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -42,6 +42,7 @@
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 90892416ed75..18e0105810df 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -74,6 +74,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/numa_balancing.h>
 #include <linux/nodemask.h>
 #include <linux/cpuset.h>
 #include <linux/slab.h>
-- 
GitLab


From 1e4bae6468375f81a3d4bdf436deaa9ea294e12b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:32 +0100
Subject: [PATCH 489/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/jobctl.h>

We are going to split <linux/sched/jobctl.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/jobctl.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the file that is going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/jobctl.h | 4 ++++
 include/linux/sched/signal.h | 1 +
 2 files changed, 5 insertions(+)
 create mode 100644 include/linux/sched/jobctl.h

diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
new file mode 100644
index 000000000000..228e4644937b
--- /dev/null
+++ b/include/linux/sched/jobctl.h
@@ -0,0 +1,4 @@
+#ifndef _LINUX_SCHED_JOBCTL_H
+#define _LINUX_SCHED_JOBCTL_H
+
+#endif /* _LINUX_SCHED_JOBCTL_H */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index da69cd05cd68..ce93c4a02b79 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -2,5 +2,6 @@
 #define _LINUX_SCHED_SIGNAL_H
 
 #include <linux/sched.h>
+#include <linux/sched/jobctl.h>
 
 #endif /* _LINUX_SCHED_SIGNAL_H */
-- 
GitLab


From 7fce777cd4eacc0bdcb33017e5a4c495d28afed1 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 14:47:27 +0100
Subject: [PATCH 490/898] sched/headers: Prepare header dependency changes,
 move the <asm/paravirt.h> include to kernel/sched/sched.h

Recent header reorganizations unearthed this hidden dependency:

  kernel/sched/core.c:199:25: error: 'paravirt_steal_rq_enabled' undeclared (first use in this function)
  kernel/sched/core.c:200:11: error: implicit declaration of function 'paravirt_steal_clock' [-Werror=implicit-function-declaration]

So move the asm/paravirt.h include from kernel/sched/cpuclock.c to kernel/sched/sched.h.

( NOTE: We do this change before doing the changes that introduce the build failure,
        so the series remains fully bisectable. )

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cputime.c | 4 ----
 kernel/sched/sched.h   | 4 ++++
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2ecec3a4f1ee..54031fa681e2 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -6,10 +6,6 @@
 #include <linux/context_tracking.h>
 #include <linux/cputime.h>
 #include "sched.h"
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#endif
-
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7e8ce0347fbf..04f376cf7ba9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -20,6 +20,10 @@
 #include <linux/tick.h>
 #include <linux/slab.h>
 
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#endif
+
 #include "cpupri.h"
 #include "cpudeadline.h"
 #include "cpuacct.h"
-- 
GitLab


From 5b825c3af1d8a0af4deb4a5eb349d0d0050c62e5 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 17:54:15 +0100
Subject: [PATCH 491/898] sched/headers: Prepare to remove <linux/cred.h>
 inclusion from <linux/sched.h>

Add #include <linux/cred.h> dependencies to all .c files rely on sched.h
doing that for them.

Note that even if the count where we need to add extra headers seems high,
it's still a net win, because <linux/sched.h> is included in over
2,200 files ...

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/kernel/sys_oabi-compat.c                     | 1 +
 arch/mips/kernel/mips-mt-fpaff.c                      | 1 +
 arch/x86/include/asm/intel_rdt.h                      | 1 +
 arch/x86/kernel/cpu/intel_cacheinfo.c                 | 1 +
 block/ioprio.c                                        | 1 +
 drivers/misc/eeprom/eeprom.c                          | 1 +
 drivers/misc/lkdtm_heap.c                             | 1 +
 drivers/misc/vmw_vmci/vmci_context.c                  | 1 +
 drivers/misc/vmw_vmci/vmci_host.c                     | 1 +
 drivers/staging/lustre/lustre/include/lustre_compat.h | 1 +
 drivers/staging/lustre/lustre/ptlrpc/sec.c            | 1 +
 drivers/xen/balloon.c                                 | 1 +
 fs/9p/v9fs.c                                          | 1 +
 fs/affs/inode.c                                       | 1 +
 fs/affs/super.c                                       | 1 +
 fs/autofs4/dev-ioctl.c                                | 1 +
 fs/befs/linuxvfs.c                                    | 1 +
 fs/binfmt_elf.c                                       | 1 +
 fs/cachefiles/internal.h                              | 1 +
 fs/compat.c                                           | 1 +
 fs/exportfs/expfs.c                                   | 1 +
 fs/ext2/balloc.c                                      | 1 +
 fs/ext4/ialloc.c                                      | 2 ++
 fs/file_table.c                                       | 1 +
 fs/gfs2/inode.c                                       | 1 +
 fs/gfs2/sys.c                                         | 1 +
 fs/hfs/inode.c                                        | 1 +
 fs/hfsplus/inode.c                                    | 1 +
 fs/isofs/inode.c                                      | 1 +
 fs/jffs2/fs.c                                         | 1 +
 fs/libfs.c                                            | 1 +
 fs/namespace.c                                        | 1 +
 fs/ncpfs/ioctl.c                                      | 1 +
 fs/notify/fanotify/fanotify.c                         | 1 +
 fs/notify/inotify/inotify_fsnotify.c                  | 1 +
 fs/omfs/inode.c                                       | 1 +
 fs/overlayfs/copy_up.c                                | 1 +
 fs/overlayfs/inode.c                                  | 1 +
 fs/overlayfs/namei.c                                  | 1 +
 fs/overlayfs/super.c                                  | 1 +
 fs/overlayfs/util.c                                   | 1 +
 fs/posix_acl.c                                        | 1 +
 fs/proc/proc_sysctl.c                                 | 1 +
 fs/proc/root.c                                        | 1 +
 fs/quota/dquot.c                                      | 1 +
 fs/stat.c                                             | 1 +
 fs/xfs/xfs_ioctl.c                                    | 1 +
 include/linux/cred.h                                  | 1 +
 include/linux/sched/signal.h                          | 1 +
 include/linux/wait.h                                  | 1 +
 include/net/scm.h                                     | 1 +
 include/rdma/ib.h                                     | 1 +
 ipc/namespace.c                                       | 1 +
 kernel/pid_namespace.c                                | 1 +
 kernel/ucount.c                                       | 1 +
 kernel/uid16.c                                        | 1 +
 kernel/utsname.c                                      | 1 +
 mm/usercopy.c                                         | 1 +
 net/dns_resolver/dns_query.c                          | 2 ++
 net/netfilter/xt_owner.c                              | 2 ++
 net/sunrpc/auth.c                                     | 1 +
 security/apparmor/policy.c                            | 1 +
 security/keys/internal.h                              | 1 +
 security/keys/keyctl.c                                | 1 +
 security/keys/persistent.c                            | 2 ++
 65 files changed, 69 insertions(+)

diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 5f221acd21ae..b9786f491873 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -76,6 +76,7 @@
 #include <linux/syscalls.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/cred.h>
 #include <linux/fcntl.h>
 #include <linux/eventpoll.h>
 #include <linux/sem.h>
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 1a0a3b4ecc3e..ffc6bd3464d9 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/security.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 95ce5c85b009..0d64397cee58 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -3,6 +3,7 @@
 
 #ifdef CONFIG_INTEL_RDT_A
 
+#include <linux/sched.h>
 #include <linux/kernfs.h>
 #include <linux/jump_label.h>
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 0282b0df004a..c55fb2cb2acc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -11,6 +11,7 @@
 #include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/capability.h>
 #include <linux/sysfs.h>
 #include <linux/pci.h>
 
diff --git a/block/ioprio.c b/block/ioprio.c
index 89c43e07787d..4b9ab8367dda 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/ioprio.h>
+#include <linux/cred.h>
 #include <linux/blkdev.h>
 #include <linux/capability.h>
 #include <linux/sched/user.h>
diff --git a/drivers/misc/eeprom/eeprom.c b/drivers/misc/eeprom/eeprom.c
index 3d1d55157e5f..2fad790db3bf 100644
--- a/drivers/misc/eeprom/eeprom.c
+++ b/drivers/misc/eeprom/eeprom.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/capability.h>
 #include <linux/jiffies.h>
 #include <linux/i2c.h>
 #include <linux/mutex.h>
diff --git a/drivers/misc/lkdtm_heap.c b/drivers/misc/lkdtm_heap.c
index 0f1581664c1c..ffb6aeac07b3 100644
--- a/drivers/misc/lkdtm_heap.c
+++ b/drivers/misc/lkdtm_heap.c
@@ -4,6 +4,7 @@
  */
 #include "lkdtm.h"
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 /*
  * This tries to stay within the next largest power-of-2 kmalloc cache
diff --git a/drivers/misc/vmw_vmci/vmci_context.c b/drivers/misc/vmw_vmci/vmci_context.c
index f35f0c8606b9..21d0fa592145 100644
--- a/drivers/misc/vmw_vmci/vmci_context.c
+++ b/drivers/misc/vmw_vmci/vmci_context.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/slab.h>
 
 #include "vmci_queue_pair.h"
diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c
index ec090105eb4b..8a16a26e9658 100644
--- a/drivers/misc/vmw_vmci/vmci_host.c
+++ b/drivers/misc/vmw_vmci/vmci_host.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/init.h>
diff --git a/drivers/staging/lustre/lustre/include/lustre_compat.h b/drivers/staging/lustre/lustre/include/lustre_compat.h
index 300e96fb032a..da9ce195c52e 100644
--- a/drivers/staging/lustre/lustre/include/lustre_compat.h
+++ b/drivers/staging/lustre/lustre/include/lustre_compat.h
@@ -35,6 +35,7 @@
 
 #include <linux/fs_struct.h>
 #include <linux/namei.h>
+#include <linux/cred.h>
 
 #include "lustre_patchless_compat.h"
 
diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec.c b/drivers/staging/lustre/lustre/ptlrpc/sec.c
index e860df7c45a2..49f34fd655c3 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/sec.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/sec.c
@@ -38,6 +38,7 @@
 
 #include "../../include/linux/libcfs/libcfs.h"
 #include <linux/crypto.h>
+#include <linux/cred.h>
 #include <linux/key.h>
 
 #include "../include/obd.h"
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index db107fa50ca1..a6d4378eb8d9 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -41,6 +41,7 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
 #include <linux/bootmem.h>
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 072e7599583a..a89f3cfe3c7d 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -29,6 +29,7 @@
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/parser.h>
 #include <linux/idr.h>
 #include <linux/slab.h>
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index a5e6097eb5a9..abcc59899229 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -10,6 +10,7 @@
  *  (C) 1991  Linus Torvalds - minix filesystem
  */
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/gfp.h>
 #include "affs.h"
 
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 37532538e8ab..c2c27a8f128e 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -16,6 +16,7 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/slab.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 806df746f1a9..734cbf8d9676 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -17,6 +17,7 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/compat.h>
 #include <linux/syscalls.h>
 #include <linux/magic.h>
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 19407165f4aa..c500e954debb 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -18,6 +18,7 @@
 #include <linux/parser.h>
 #include <linux/namei.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/exportfs.h>
 
 #include "befs.h"
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index fbbe52e1250e..2c95257fa4da 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -36,6 +36,7 @@
 #include <linux/coredump.h>
 #include <linux/sched.h>
 #include <linux/sched/coredump.h>
+#include <linux/cred.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
 #include <asm/param.h>
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index cd1effee8a49..9bf90bcc56ac 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -19,6 +19,7 @@
 #include <linux/fscache-cache.h>
 #include <linux/timer.h>
 #include <linux/wait.h>
+#include <linux/cred.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
 
diff --git a/fs/compat.c b/fs/compat.c
index e50a2114f474..c61b506f5bc9 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -21,6 +21,7 @@
 #include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/time.h>
+#include <linux/cred.h>
 #include <linux/fs.h>
 #include <linux/fcntl.h>
 #include <linux/namei.h>
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index a4b531be9168..9ec1038f937e 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -15,6 +15,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 
 #define dprintk(fmt, args...) do{}while(0)
 
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 4c40c0786e16..d0bdb74f0e15 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -15,6 +15,7 @@
 #include <linux/quotaops.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/buffer_head.h>
 #include <linux/capability.h>
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index b14bae2598bc..17bc043308f3 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -21,6 +21,8 @@
 #include <linux/random.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
+#include <linux/cred.h>
+
 #include <asm/byteorder.h>
 
 #include "ext4.h"
diff --git a/fs/file_table.c b/fs/file_table.c
index 6d982b57de92..954d510b765a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/eventpoll.h>
 #include <linux/rcupdate.h>
 #include <linux/mount.h>
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index eb7724b8578a..9d28f55fbd1d 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -13,6 +13,7 @@
 #include <linux/buffer_head.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/cred.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/gfs2_ondisk.h>
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index f8d30e41d1d3..7a515345610c 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -10,6 +10,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index f776acf2378a..bfbba799430f 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/uio.h>
 #include <linux/xattr.h>
 
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 2e796f8302ff..e8638d528195 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/uio.h>
 
 #include "hfsplus_fs.h"
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 871c8b392099..020ba0936146 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/nls.h>
 #include <linux/ctype.h>
 #include <linux/statfs.h>
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 567653f7c0ce..76fa814df3d1 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -15,6 +15,7 @@
 #include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/fs.h>
 #include <linux/list.h>
 #include <linux/mtd/mtd.h>
diff --git a/fs/libfs.c b/fs/libfs.c
index 28d6f35feed6..217896ca4fae 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/mount.h>
 #include <linux/vfs.h>
 #include <linux/quotaops.h>
diff --git a/fs/namespace.c b/fs/namespace.c
index 8bfad42c1ccf..131cd7b94f47 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -15,6 +15,7 @@
 #include <linux/user_namespace.h>
 #include <linux/namei.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/idr.h>
 #include <linux/init.h>		/* init_rootfs */
 #include <linux/fs_struct.h>	/* get_fs_root et.al. */
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 4434e4977cf3..12550c2320cc 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -19,6 +19,7 @@
 #include <linux/highuid.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 
 #include <linux/uaccess.h>
 
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index a4c46221755e..e5f7e47de68e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h> /* UINT_MAX */
 #include <linux/mount.h>
 #include <linux/sched.h>
+#include <linux/sched/user.h>
 #include <linux/types.h>
 #include <linux/wait.h>
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index f36c29398de3..1aeb837ae414 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -30,6 +30,7 @@
 #include <linux/slab.h> /* kmem_* */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/user.h>
 
 #include "inotify.h"
 
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index df7ea8543a2e..8c9034ee7383 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/vfs.h>
+#include <linux/cred.h>
 #include <linux/parser.h>
 #include <linux/buffer_head.h>
 #include <linux/vmalloc.h>
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index f57043dace62..53d3f830358f 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -16,6 +16,7 @@
 #include <linux/security.h>
 #include <linux/uaccess.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/fdtable.h>
 #include <linux/ratelimit.h>
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 08643ac44a02..6639f487f835 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -9,6 +9,7 @@
 
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include "overlayfs.h"
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 023bb0b03352..b8b077821fb0 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/xattr.h>
 #include <linux/ratelimit.h>
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 20f48abbb82f..9aa37c2f7f7d 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -7,6 +7,7 @@
  * the Free Software Foundation.
  */
 
+#include <uapi/linux/magic.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/xattr.h>
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 952286f4826c..9dc1c0af586b 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -10,6 +10,7 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/xattr.h>
 #include "overlayfs.h"
 #include "ovl_entry.h"
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index c9d48dc78495..eebf5f6cf6d5 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -15,6 +15,7 @@
 #include <linux/atomic.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/xattr.h>
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 3e64c6502dc8..3d203b1f5a02 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -8,6 +8,7 @@
 #include <linux/printk.h>
 #include <linux/security.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
 #include <linux/module.h>
diff --git a/fs/proc/root.c b/fs/proc/root.c
index b90da888b81a..5d5fed20bfff 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -20,6 +20,7 @@
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
 #include <linux/parser.h>
+#include <linux/cred.h>
 
 #include "internal.h"
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 406fed92362a..74b489e3714d 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -72,6 +72,7 @@
 #include <linux/proc_fs.h>
 #include <linux/security.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/kmod.h>
 #include <linux/namei.h>
 #include <linux/capability.h>
diff --git a/fs/stat.c b/fs/stat.c
index 3f14d1ef0868..95bd41762770 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -12,6 +12,7 @@
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/syscalls.h>
 #include <linux/pagemap.h>
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index cf1363dbf32b..2fd7fdf5438f 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -43,6 +43,7 @@
 #include "xfs_acl.h"
 
 #include <linux/capability.h>
+#include <linux/cred.h>
 #include <linux/dcache.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 045d33e48069..b03e7d049a64 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -18,6 +18,7 @@
 #include <linux/selinux.h>
 #include <linux/atomic.h>
 #include <linux/uidgid.h>
+#include <linux/sched.h>
 #include <linux/sched/user.h>
 
 struct cred;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index ce93c4a02b79..0f4e9f4a43fd 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_SCHED_SIGNAL_H
 #define _LINUX_SCHED_SIGNAL_H
 
+#include <linux/cred.h>
 #include <linux/sched.h>
 #include <linux/sched/jobctl.h>
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 1421132e9086..aacb1282d19a 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -6,6 +6,7 @@
 #include <linux/list.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
+
 #include <asm/current.h>
 #include <uapi/linux/wait.h>
 
diff --git a/include/net/scm.h b/include/net/scm.h
index 59fa93c01d2a..142ea9e7a6d0 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -3,6 +3,7 @@
 
 #include <linux/limits.h>
 #include <linux/net.h>
+#include <linux/cred.h>
 #include <linux/security.h>
 #include <linux/pid.h>
 #include <linux/nsproxy.h>
diff --git a/include/rdma/ib.h b/include/rdma/ib.h
index a6b93706b0fc..9b4c22a36931 100644
--- a/include/rdma/ib.h
+++ b/include/rdma/ib.h
@@ -35,6 +35,7 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 
 struct ib_addr {
 	union {
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 0abdea496493..1f1d713ac19c 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -9,6 +9,7 @@
 #include <linux/rcupdate.h>
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/user_namespace.h>
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index eef2ce968636..25314c96fbe6 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -12,6 +12,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/syscalls.h>
+#include <linux/cred.h>
 #include <linux/err.h>
 #include <linux/acct.h>
 #include <linux/slab.h>
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 8a11fc0cb459..62630a40ab3a 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -8,6 +8,7 @@
 #include <linux/stat.h>
 #include <linux/sysctl.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/hash.h>
 #include <linux/user_namespace.h>
 
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 71645ae9303a..5c2dc5b2bf4f 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/highuid.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/syscalls.h>
 
 #include <linux/uaccess.h>
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 6976cd47dcf6..06585ad296ff 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -14,6 +14,7 @@
 #include <linux/utsname.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/user_namespace.h>
 #include <linux/proc_ns.h>
 
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 8345299e3e3b..7ccad05c0d5c 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -16,6 +16,7 @@
 
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 #include <asm/sections.h>
 
 enum {
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index ecc28cff08ab..ab9fec00a788 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -37,8 +37,10 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/dns_resolver.h>
 #include <linux/err.h>
+
 #include <keys/dns_resolver-type.h>
 #include <keys/user-type.h>
 
diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c
index 16477df45b3b..3d705c688a27 100644
--- a/net/netfilter/xt_owner.c
+++ b/net/netfilter/xt_owner.c
@@ -13,6 +13,8 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/file.h>
+#include <linux/cred.h>
+
 #include <net/sock.h>
 #include <net/inet_sock.h>
 #include <linux/netfilter/x_tables.h>
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index a1ee933e3029..d2623b9f23d6 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -8,6 +8,7 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index f44312a19522..462c5d36b871 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -76,6 +76,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/cred.h>
 #include <linux/user_namespace.h>
 
 #include "include/apparmor.h"
diff --git a/security/keys/internal.h b/security/keys/internal.h
index a705a7d92ad7..a2f4c0abb8d8 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -13,6 +13,7 @@
 #define _INTERNAL_H
 
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/key-type.h>
 #include <linux/task_work.h>
 #include <linux/keyctl.h>
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 04a764f71ec8..bcb0b597c391 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -18,6 +18,7 @@
 #include <linux/keyctl.h>
 #include <linux/fs.h>
 #include <linux/capability.h>
+#include <linux/cred.h>
 #include <linux/string.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
diff --git a/security/keys/persistent.c b/security/keys/persistent.c
index 1edc1f0a0ce2..d0cb5b32eff7 100644
--- a/security/keys/persistent.c
+++ b/security/keys/persistent.c
@@ -10,6 +10,8 @@
  */
 
 #include <linux/user_namespace.h>
+#include <linux/cred.h>
+
 #include "internal.h"
 
 unsigned persistent_keyring_expiry = 3 * 24 * 3600; /* Expire after 3 days of non-use */
-- 
GitLab


From 4cf421e55d69016989548e0fb8585e69f54bd283 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 10:03:42 +0100
Subject: [PATCH 492/898] sched/headers: Prepare for the removal of
 <asm/ptrace.h> from <linux/sched.h>

Fix up missing #includes in other places that rely on sched.h doing that for them.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/math-emu/math.c    | 1 +
 arch/sh/kernel/cpu/fpu.c      | 1 +
 arch/sh/kernel/process.c      | 1 +
 drivers/oprofile/cpu_buffer.c | 2 ++
 4 files changed, 5 insertions(+)

diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c
index fa5ae0ad8983..d17d705f6545 100644
--- a/arch/alpha/math-emu/math.c
+++ b/arch/alpha/math-emu/math.c
@@ -2,6 +2,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <asm/ptrace.h>
 
 #include <linux/uaccess.h>
 
diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c
index 4e332244ea75..4d4737d099c6 100644
--- a/arch/sh/kernel/cpu/fpu.c
+++ b/arch/sh/kernel/cpu/fpu.c
@@ -3,6 +3,7 @@
 #include <asm/processor.h>
 #include <asm/fpu.h>
 #include <asm/traps.h>
+#include <asm/ptrace.h>
 
 int init_fpu(struct task_struct *tsk)
 {
diff --git a/arch/sh/kernel/process.c b/arch/sh/kernel/process.c
index 53bc6c4c84ec..30bff33e810e 100644
--- a/arch/sh/kernel/process.c
+++ b/arch/sh/kernel/process.c
@@ -5,6 +5,7 @@
 #include <linux/export.h>
 #include <linux/stackprotector.h>
 #include <asm/fpu.h>
+#include <asm/ptrace.h>
 
 struct kmem_cache *task_xstate_cachep = NULL;
 unsigned int xstate_size;
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 0581461c3a67..eda2633a393d 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -23,6 +23,8 @@
 #include <linux/oprofile.h>
 #include <linux/errno.h>
 
+#include <asm/ptrace.h>
+
 #include "event_buffer.h"
 #include "cpu_buffer.h"
 #include "buffer_sync.h"
-- 
GitLab


From 037741a6d4ab2e4b0580dae97aca963d8a8dc68f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 10:08:30 +0100
Subject: [PATCH 493/898] sched/headers: Prepare for the removal of
 <linux/rtmutex.h> from <linux/sched.h>

Fix up missing #includes in other places that rely on sched.h doing that for them.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/i2c.h          | 1 +
 kernel/fork.c                | 1 +
 kernel/locking/locktorture.c | 1 +
 kernel/rcu/tree.h            | 1 +
 4 files changed, 4 insertions(+)

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index bed8fbb45f31..6b183521c616 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -30,6 +30,7 @@
 #include <linux/device.h>	/* for struct device */
 #include <linux/sched.h>	/* for completion */
 #include <linux/mutex.h>
+#include <linux/rtmutex.h>
 #include <linux/irqdomain.h>		/* for Host Notify IRQ */
 #include <linux/of.h>		/* for struct device_node */
 #include <linux/swab.h>		/* for swab16 */
diff --git a/kernel/fork.c b/kernel/fork.c
index 08d6c091ac7c..8fbe8bcd1e20 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -17,6 +17,7 @@
 #include <linux/sched/coredump.h>
 #include <linux/sched/user.h>
 #include <linux/sched/numa_balancing.h>
+#include <linux/rtmutex.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
 #include <linux/module.h>
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 5ea0a8969ee2..f24582d4dad3 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -33,6 +33,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <uapi/linux/sched/types.h>
+#include <linux/rtmutex.h>
 #include <linux/atomic.h>
 #include <linux/moduleparam.h>
 #include <linux/delay.h>
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index b60f2b6caa14..ec62a05bfdb3 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -24,6 +24,7 @@
 
 #include <linux/cache.h>
 #include <linux/spinlock.h>
+#include <linux/rtmutex.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
-- 
GitLab


From cc5efc2323a89dcf1a02c17b9b9f255c5a6e0492 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 10:06:45 +0100
Subject: [PATCH 494/898] sched/headers: Prepare for the removal of various
 unrelated headers from <linux/sched.h>

We are going to remove the following header inclusions from <linux/sched.h>:

	#include <asm/param.h>
	#include <linux/threads.h>
	#include <linux/kernel.h>
	#include <linux/types.h>
	#include <linux/timex.h>
	#include <linux/jiffies.h>
	#include <linux/rbtree.h>
	#include <linux/thread_info.h>
	#include <linux/cpumask.h>
	#include <linux/errno.h>
	#include <linux/nodemask.h>
	#include <linux/preempt.h>
	#include <asm/page.h>
	#include <linux/smp.h>
	#include <linux/compiler.h>
	#include <linux/completion.h>
	#include <linux/percpu.h>
	#include <linux/topology.h>
	#include <linux/rcupdate.h>
	#include <linux/time.h>
	#include <linux/timer.h>
	#include <linux/llist.h>
	#include <linux/uidgid.h>
	#include <asm/processor.h>

Fix up a single .h file that got hold of <linux/sysctl.h> via one of these headers.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/user_namespace.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 363e0e8082a9..08264641b502 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -5,6 +5,7 @@
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/sched.h>
+#include <linux/sysctl.h>
 #include <linux/err.h>
 
 #define UID_GID_MAP_MAX_EXTENTS 5
-- 
GitLab


From b12fb7f46af7d548503d75be59f493f958c6d1b3 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:33 +0100
Subject: [PATCH 495/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/xacct.h>

We are going to split <linux/sched/xacct.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/xacct.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the .c file that is going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/read_write.c             | 3 ++-
 include/linux/sched/xacct.h | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/xacct.h

diff --git a/fs/read_write.c b/fs/read_write.c
index 5816d4c4cab0..dc60075653a8 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -4,8 +4,9 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  */
 
-#include <linux/slab.h> 
+#include <linux/slab.h>
 #include <linux/stat.h>
+#include <linux/sched/xacct.h>
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/uio.h>
diff --git a/include/linux/sched/xacct.h b/include/linux/sched/xacct.h
new file mode 100644
index 000000000000..890f7ce5cd27
--- /dev/null
+++ b/include/linux/sched/xacct.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_XACCT_H
+#define _LINUX_SCHED_XACCT_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_XACCT_H */
-- 
GitLab


From 174cd4b1e5fbd0d74c68cf3a74f5bd4923485512 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 19:15:33 +0100
Subject: [PATCH 496/898] sched/headers: Prepare to move signal wakeup &
 sigpending methods from <linux/sched.h> into <linux/sched/signal.h>

Fix up affected files that include this signal functionality via sched.h.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/common/bL_switcher.c                 |  2 +-
 arch/cris/arch-v10/drivers/sync_serial.c      |  2 +-
 arch/cris/arch-v32/drivers/sync_serial.c      |  2 +-
 arch/mips/kernel/rtlx.c                       |  2 ++
 arch/mips/kvm/mips.c                          |  2 ++
 arch/powerpc/kvm/book3s_hv.c                  |  2 +-
 arch/powerpc/kvm/powerpc.c                    |  1 +
 arch/powerpc/platforms/83xx/suspend.c         |  1 +
 arch/powerpc/platforms/cell/spufs/sched.c     |  2 +-
 arch/powerpc/platforms/cell/spufs/spufs.h     |  1 +
 arch/s390/crypto/prng.c                       |  2 ++
 arch/s390/kvm/kvm-s390.c                      |  2 ++
 arch/s390/kvm/vsie.c                          |  2 ++
 arch/sh/kernel/cpu/fpu.c                      |  2 +-
 arch/sh/kernel/disassemble.c                  |  2 ++
 arch/sh/kernel/process.c                      |  2 +-
 arch/um/drivers/random.c                      |  2 +-
 arch/x86/kernel/apm_32.c                      |  2 +-
 block/blk-cgroup.c                            |  1 +
 block/blk-mq.c                                |  1 +
 crypto/algboss.c                              |  2 +-
 crypto/algif_aead.c                           |  1 +
 crypto/algif_skcipher.c                       |  1 +
 crypto/api.c                                  |  2 +-
 drivers/atm/horizon.c                         |  1 +
 drivers/base/core.c                           |  1 +
 drivers/base/power/wakeup.c                   |  2 +-
 drivers/block/drbd/drbd_main.c                |  1 +
 drivers/block/drbd/drbd_receiver.c            |  1 +
 drivers/block/drbd/drbd_worker.c              |  2 +-
 drivers/block/swim3.c                         |  2 +-
 drivers/char/applicom.c                       |  2 +-
 drivers/char/hpet.c                           |  1 +
 drivers/char/hw_random/core.c                 |  1 +
 drivers/char/ipmi/ipmi_watchdog.c             |  1 +
 drivers/char/lp.c                             |  2 +-
 drivers/char/ppdev.c                          |  2 +-
 drivers/char/rtc.c                            |  2 +-
 drivers/char/snsc.c                           |  2 +-
 drivers/dma-buf/dma-fence.c                   |  1 +
 .../gpu/drm/omapdrm/displays/panel-dsi-cm.c   |  2 +-
 drivers/gpu/drm/vc4/vc4_gem.c                 |  1 +
 drivers/gpu/vga/vgaarb.c                      |  2 +-
 drivers/hid/hid-debug.c                       |  2 +-
 drivers/hid/hid-roccat.c                      |  2 +-
 drivers/hid/hidraw.c                          |  2 +-
 drivers/hid/usbhid/hiddev.c                   |  1 +
 drivers/hsi/clients/cmt_speech.c              |  2 +-
 drivers/i2c/busses/i2c-ibm_iic.c              |  2 ++
 drivers/i2c/busses/i2c-mpc.c                  |  2 +-
 drivers/iio/industrialio-buffer.c             |  2 +-
 drivers/infiniband/ulp/ipoib/ipoib_cm.c       |  1 +
 drivers/infiniband/ulp/ipoib/ipoib_vlan.c     |  1 +
 drivers/isdn/capi/kcapi.c                     |  2 +-
 drivers/isdn/mISDN/timerdev.c                 |  2 ++
 drivers/lguest/core.c                         |  1 +
 drivers/macintosh/adb.c                       |  2 +-
 drivers/macintosh/smu.c                       |  1 +
 drivers/macintosh/via-pmu.c                   |  2 +-
 drivers/mailbox/mailbox-test.c                |  1 +
 drivers/md/dm.c                               |  1 +
 drivers/media/dvb-core/dvb_ca_en50221.c       |  2 +-
 drivers/media/dvb-core/dvb_demux.c            |  2 +-
 drivers/media/dvb-core/dvb_frontend.c         |  2 +-
 drivers/media/pci/cx18/cx18-driver.h          |  2 +-
 drivers/media/pci/ivtv/ivtv-driver.h          | 35 ++++++++++---------
 drivers/media/pci/pt1/pt1.c                   |  1 +
 drivers/media/pci/pt3/pt3.c                   |  1 +
 drivers/media/pci/solo6x10/solo6x10-i2c.c     |  1 +
 drivers/media/pci/zoran/zoran_device.c        |  1 +
 drivers/media/platform/vivid/vivid-radio-rx.c |  2 ++
 drivers/media/platform/vivid/vivid-radio-tx.c |  1 +
 drivers/media/rc/lirc_dev.c                   |  2 +-
 drivers/media/usb/cpia2/cpia2_core.c          |  1 +
 drivers/media/usb/gspca/cpia1.c               |  2 ++
 drivers/misc/cxl/fault.c                      |  2 +-
 drivers/misc/cxl/file.c                       |  2 +-
 drivers/misc/ibmasm/r_heartbeat.c             |  2 +-
 drivers/misc/lis3lv02d/lis3lv02d.c            |  1 +
 drivers/misc/mei/bus.c                        |  2 +-
 drivers/misc/mei/client.c                     |  2 +-
 drivers/misc/mei/main.c                       |  2 +-
 drivers/misc/mic/scif/scif_main.h             |  2 +-
 drivers/misc/vexpress-syscfg.c                |  2 +-
 drivers/mtd/tests/mtd_test.h                  |  2 +-
 drivers/net/bonding/bond_options.c            |  2 ++
 drivers/net/bonding/bond_sysfs.c              |  2 +-
 drivers/net/can/softing/softing_fw.c          |  2 +-
 drivers/net/ethernet/broadcom/tg3.c           |  1 +
 .../ethernet/cavium/liquidio/octeon_main.h    |  2 ++
 drivers/net/ethernet/sfc/falcon/falcon.c      |  2 ++
 drivers/net/irda/stir4200.c                   |  1 +
 drivers/net/macvtap.c                         |  2 +-
 drivers/net/ppp/ppp_generic.c                 |  1 +
 drivers/net/tun.c                             |  1 +
 drivers/net/usb/hso.c                         |  2 +-
 drivers/net/usb/qmi_wwan.c                    |  1 +
 drivers/net/wan/cosa.c                        |  2 +-
 drivers/net/wireless/ath/ath6kl/cfg80211.c    |  1 +
 .../net/wireless/broadcom/b43legacy/main.c    |  2 +-
 .../net/wireless/intersil/hostap/hostap_hw.c  |  2 +-
 .../wireless/intersil/hostap/hostap_ioctl.c   |  2 +-
 drivers/oprofile/event_buffer.c               |  2 +-
 drivers/parport/daisy.c                       |  2 +-
 drivers/parport/ieee1284.c                    |  2 +-
 drivers/parport/ieee1284_ops.c                |  2 +-
 drivers/parport/parport_ip32.c                |  2 +-
 drivers/parport/parport_pc.c                  |  2 +-
 drivers/parport/share.c                       |  2 +-
 drivers/pci/access.c                          |  2 +-
 drivers/pci/hotplug/cpci_hotplug_core.c       |  1 +
 drivers/pci/hotplug/cpqphp.h                  |  2 +-
 drivers/pci/hotplug/pciehp.h                  |  2 +-
 drivers/pci/hotplug/shpchp.h                  |  2 +-
 drivers/rtc/rtc-dev.c                         |  2 +-
 drivers/s390/cio/device.c                     |  1 +
 drivers/scsi/lpfc/lpfc_vport.c                |  1 +
 drivers/scsi/osst.c                           |  2 +-
 drivers/scsi/st.c                             |  2 +-
 drivers/soc/fsl/qbman/dpaa_sys.h              |  1 +
 drivers/staging/comedi/comedi_fops.c          |  2 +-
 drivers/staging/dgnc/dgnc_tty.c               |  2 +-
 drivers/staging/dgnc/dgnc_utils.c             |  2 +-
 drivers/staging/greybus/uart.c                |  2 +-
 .../lustre/include/lustre/lustre_user.h       |  1 +
 .../lustre/lustre/include/lustre_lib.h        |  2 +-
 .../lustre/lustre/include/obd_support.h       |  2 ++
 drivers/staging/media/lirc/lirc_sir.c         |  2 +-
 drivers/staging/media/lirc/lirc_zilog.c       |  2 +-
 drivers/staging/speakup/speakup_soft.c        |  2 +-
 drivers/target/iscsi/cxgbit/cxgbit_target.c   |  2 ++
 drivers/tty/n_gsm.c                           |  2 +-
 drivers/tty/serial/crisv10.c                  |  2 +-
 drivers/tty/serial/serial_core.c              |  1 +
 drivers/tty/tty_ioctl.c                       |  2 +-
 drivers/tty/tty_port.c                        |  2 +-
 drivers/uio/uio.c                             |  2 +-
 drivers/usb/class/cdc-acm.c                   |  1 +
 drivers/usb/class/usblp.c                     |  2 +-
 drivers/usb/gadget/function/f_fs.c            |  1 +
 drivers/usb/image/mdc800.c                    |  2 +-
 drivers/usb/misc/adutux.c                     |  1 +
 drivers/usb/misc/idmouse.c                    |  1 +
 drivers/usb/misc/rio500.c                     |  2 +-
 drivers/usb/misc/uss720.c                     |  1 +
 drivers/usb/mon/mon_bin.c                     |  1 +
 drivers/usb/mon/mon_text.c                    |  1 +
 drivers/usb/serial/digi_acceleport.c          |  1 +
 drivers/usb/serial/generic.c                  |  1 +
 drivers/vhost/net.c                           |  1 +
 drivers/vhost/vhost.c                         |  1 +
 drivers/video/fbdev/cobalt_lcdfb.c            |  1 +
 .../omap2/omapfb/displays/panel-dsi-cm.c      |  2 +-
 fs/afs/rxrpc.c                                |  2 ++
 fs/aio.c                                      |  2 +-
 fs/btrfs/ctree.h                              |  1 +
 fs/ceph/caps.c                                |  2 +-
 fs/cifs/inode.c                               |  2 ++
 fs/coda/psdev.c                               |  2 +-
 fs/dlm/user.c                                 |  1 +
 fs/ecryptfs/read_write.c                      |  2 ++
 fs/eventfd.c                                  |  2 +-
 fs/eventpoll.c                                |  2 +-
 fs/ext4/ext4.h                                |  1 +
 fs/f2fs/data.c                                |  1 +
 fs/fuse/dev.c                                 |  1 +
 fs/gfs2/lock_dlm.c                            |  1 +
 fs/gfs2/super.c                               |  2 +-
 fs/hpfs/hpfs_fn.h                             |  2 +-
 fs/hugetlbfs/inode.c                          |  2 +-
 fs/jffs2/nodemgmt.c                           |  2 +-
 fs/nfs/inode.c                                |  2 +-
 fs/nilfs2/segment.c                           |  2 ++
 fs/notify/fanotify/fanotify_user.c            |  1 +
 fs/notify/inotify/inotify_user.c              |  2 +-
 fs/ntfs/file.c                                |  2 +-
 fs/ocfs2/alloc.c                              |  1 +
 fs/ocfs2/dlm/dlmdomain.c                      |  1 +
 fs/ocfs2/dlmfs/userdlm.c                      |  1 +
 fs/ocfs2/dlmglue.c                            |  1 +
 fs/orangefs/orangefs-kernel.h                 |  2 +-
 fs/overlayfs/copy_up.c                        |  2 +-
 fs/splice.c                                   |  2 ++
 fs/userfaultfd.c                              |  2 +-
 fs/xfs/xfs_linux.h                            |  2 +-
 include/drm/drm_os_linux.h                    |  1 +
 include/linux/sunrpc/types.h                  |  1 +
 include/media/v4l2-ioctl.h                    |  1 +
 include/net/busy_poll.h                       |  1 +
 kernel/locking/mutex.c                        |  2 +-
 kernel/locking/rtmutex.c                      |  2 +-
 kernel/locking/rwsem-spinlock.c               |  2 +-
 kernel/locking/rwsem-xadd.c                   |  2 +-
 kernel/rcu/rcutorture.c                       |  2 +-
 kernel/sched/completion.c                     |  2 +-
 kernel/sched/swait.c                          |  2 +-
 kernel/sched/wait.c                           |  2 +-
 kernel/time/alarmtimer.c                      |  1 +
 kernel/time/hrtimer.c                         |  2 +-
 kernel/time/timer.c                           |  2 +-
 lib/percpu_ida.c                              |  2 +-
 mm/compaction.c                               |  1 +
 mm/gup.c                                      |  2 +-
 mm/hugetlb.c                                  |  1 +
 mm/memory_hotplug.c                           |  1 +
 mm/shmem.c                                    |  1 +
 mm/userfaultfd.c                              |  1 +
 net/atm/svc.c                                 |  2 +-
 net/bluetooth/af_bluetooth.c                  |  2 ++
 net/bluetooth/cmtp/capi.c                     |  2 +-
 net/bluetooth/hci_request.c                   |  2 ++
 net/bluetooth/l2cap_sock.c                    |  1 +
 net/bluetooth/rfcomm/sock.c                   |  1 +
 net/bluetooth/sco.c                           |  1 +
 net/bridge/br_sysfs_br.c                      |  1 +
 net/bridge/br_sysfs_if.c                      |  1 +
 net/core/ethtool.c                            |  2 +-
 net/core/net-sysfs.c                          |  1 +
 net/dccp/output.c                             |  1 +
 net/ipv4/devinet.c                            |  1 +
 net/ipv6/addrconf.c                           |  1 +
 net/irda/ircomm/ircomm_tty.c                  |  2 +-
 net/irda/irnet/irnet_ppp.c                    |  3 +-
 net/iucv/af_iucv.c                            |  2 +-
 net/kcm/kcmsock.c                             |  2 ++
 net/llc/af_llc.c                              |  2 ++
 net/nfc/llcp_sock.c                           |  1 +
 net/phonet/pep.c                              |  1 +
 net/phonet/socket.c                           |  2 ++
 net/rxrpc/conn_client.c                       |  2 ++
 net/rxrpc/recvmsg.c                           |  2 ++
 net/rxrpc/sendmsg.c                           |  2 ++
 net/tipc/socket.c                             |  2 ++
 net/vmw_vsock/af_vsock.c                      |  1 +
 net/vmw_vsock/virtio_transport_common.c       |  1 +
 sound/core/control.c                          |  1 +
 sound/core/hwdep.c                            |  1 +
 sound/core/oss/pcm_oss.c                      |  1 +
 sound/core/pcm_lib.c                          |  1 +
 sound/core/pcm_native.c                       |  1 +
 sound/core/rawmidi.c                          |  2 +-
 sound/core/seq/oss/seq_oss_device.h           |  2 +-
 sound/core/seq/oss/seq_oss_writeq.c           |  1 +
 sound/core/seq/seq_fifo.c                     |  2 ++
 sound/core/seq/seq_memory.c                   |  1 +
 sound/core/timer.c                            |  1 +
 sound/firewire/bebob/bebob.h                  |  1 +
 sound/firewire/dice/dice.h                    |  1 +
 sound/firewire/digi00x/digi00x.h              |  1 +
 sound/firewire/fireworks/fireworks.h          |  1 +
 sound/firewire/oxfw/oxfw.h                    |  1 +
 sound/firewire/tascam/tascam.h                |  1 +
 sound/isa/gus/gus_pcm.c                       |  2 ++
 sound/isa/msnd/msnd.c                         |  1 +
 sound/isa/sb/emu8000.c                        |  2 +-
 sound/isa/sb/emu8000_patch.c                  |  2 ++
 sound/isa/sb/emu8000_pcm.c                    |  2 ++
 sound/isa/wavefront/wavefront_synth.c         |  1 +
 sound/oss/dmabuf.c                            |  2 ++
 sound/oss/dmasound/dmasound_core.c            |  1 +
 sound/oss/midibuf.c                           |  2 ++
 sound/oss/msnd_pinnacle.c                     |  2 ++
 sound/oss/sound_config.h                      |  1 +
 sound/oss/swarm_cs4297a.c                     |  2 +-
 virt/kvm/kvm_main.c                           |  2 +-
 265 files changed, 319 insertions(+), 139 deletions(-)

diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index 083c9e517d22..57f3b7512636 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/interrupt.h>
 #include <linux/cpu_pm.h>
diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c
index 9ac75d68f184..cc62572c1b94 100644
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@@ -16,7 +16,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/major.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/interrupt.h>
 #include <linux/poll.h>
 #include <linux/init.h>
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index ef515af1a377..8efcc1a899a8 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/major.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mutex.h>
 #include <linux/interrupt.h>
 #include <linux/poll.h>
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index c5c4fd54d797..b80dd8b17a76 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -12,6 +12,8 @@
 #include <linux/syscalls.h>
 #include <linux/moduleloader.h>
 #include <linux/atomic.h>
+#include <linux/sched/signal.h>
+
 #include <asm/mipsmtregs.h>
 #include <asm/mips_mt.h>
 #include <asm/processor.h>
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index ed81e5ac1426..15a1b1716c2e 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -16,8 +16,10 @@
 #include <linux/module.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>
+
 #include <asm/fpu.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1e107ece4e37..fc56a9ce785d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -22,7 +22,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/preempt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/fs.h>
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 2b38d824e9e5..95c91a9de351 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -23,6 +23,7 @@
 #include <linux/kvm_host.h>
 #include <linux/vmalloc.h>
 #include <linux/hrtimer.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/file.h>
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 08f92f6ed228..978b85bb3233 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -15,6 +15,7 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/suspend.h>
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index d317c84dc794..1fbb5da17dd2 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -23,7 +23,7 @@
 #undef DEBUG
 
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/rt.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index aac733966092..5e59f80e95db 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -27,6 +27,7 @@
 #include <linux/spinlock.h>
 #include <linux/fs.h>
 #include <linux/cpumask.h>
+#include <linux/sched/signal.h>
 
 #include <asm/spu.h>
 #include <asm/spu_csa.h>
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 85b7f5efe06a..5a3ec04a7082 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -20,6 +20,8 @@
 #include <linux/cpufeature.h>
 #include <linux/random.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include <asm/debug.h>
 #include <linux/uaccess.h>
 #include <asm/timex.h>
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f5694838234d..fd6cd05bb6a7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -29,6 +29,8 @@
 #include <linux/timer.h>
 #include <linux/vmalloc.h>
 #include <linux/bitmap.h>
+#include <linux/sched/signal.h>
+
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
 #include <asm/stp.h>
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 38556e395915..5491be39776b 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -14,6 +14,8 @@
 #include <linux/bug.h>
 #include <linux/list.h>
 #include <linux/bitmap.h>
+#include <linux/sched/signal.h>
+
 #include <asm/gmap.h>
 #include <asm/mmu_context.h>
 #include <asm/sclp.h>
diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c
index 4d4737d099c6..37e35330aae6 100644
--- a/arch/sh/kernel/cpu/fpu.c
+++ b/arch/sh/kernel/cpu/fpu.c
@@ -1,4 +1,4 @@
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <asm/processor.h>
 #include <asm/fpu.h>
diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c
index 64d5d8dded7c..015fee58014b 100644
--- a/arch/sh/kernel/disassemble.c
+++ b/arch/sh/kernel/disassemble.c
@@ -12,6 +12,8 @@
 #include <linux/string.h>
 #include <linux/uaccess.h>
 
+#include <asm/ptrace.h>
+
 /*
  * Format of an instruction in memory.
  */
diff --git a/arch/sh/kernel/process.c b/arch/sh/kernel/process.c
index 30bff33e810e..80a61c5e3015 100644
--- a/arch/sh/kernel/process.c
+++ b/arch/sh/kernel/process.c
@@ -1,7 +1,7 @@
 #include <linux/mm.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/export.h>
 #include <linux/stackprotector.h>
 #include <asm/fpu.h>
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index 57f03050c850..37c51a6be690 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -6,7 +6,7 @@
  * This software may be used and distributed according to the terms
  * of the GNU General Public License, incorporated herein by reference.
  */
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/interrupt.h>
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 4a7080c84a5a..dc04b30cbd60 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -218,7 +218,7 @@
 #include <linux/apm_bios.h>
 #include <linux/init.h>
 #include <linux/time.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/pm.h>
 #include <linux/capability.h>
 #include <linux/device.h>
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 295e98c2c8cc..bbe7ee00bd3d 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -17,6 +17,7 @@
 #include <linux/ioprio.h>
 #include <linux/kdev_t.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/err.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 746c14e0d157..6f35b6fd4799 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -21,6 +21,7 @@
 #include <linux/cache.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
+#include <linux/sched/signal.h>
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/prefetch.h>
diff --git a/crypto/algboss.c b/crypto/algboss.c
index ccb85e1798f2..960d8548171b 100644
--- a/crypto/algboss.c
+++ b/crypto/algboss.c
@@ -19,7 +19,7 @@
 #include <linux/module.h>
 #include <linux/notifier.h>
 #include <linux/rtnetlink.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 533265f110e0..5a8053758657 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/net.h>
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index a9e79d8eff87..43839b00fe6c 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/net.h>
diff --git a/crypto/api.c b/crypto/api.c
index b16ce1653284..941cd4c6c7ec 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -21,7 +21,7 @@
 #include <linux/kmod.h>
 #include <linux/module.h>
 #include <linux/param.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include "internal.h"
diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c
index 2bf1ef1c3c78..0f18480b33b5 100644
--- a/drivers/atm/horizon.c
+++ b/drivers/atm/horizon.c
@@ -27,6 +27,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/pci.h>
 #include <linux/errno.h>
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 3050e6f99403..684bda4d14a1 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -26,6 +26,7 @@
 #include <linux/mutex.h>
 #include <linux/pm_runtime.h>
 #include <linux/netdevice.h>
+#include <linux/sched/signal.h>
 #include <linux/sysfs.h>
 
 #include "base.h"
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index f546f8f107b0..136854970489 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -8,7 +8,7 @@
 
 #include <linux/device.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/capability.h>
 #include <linux/export.h>
 #include <linux/suspend.h>
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 116509852a34..c7d530a95e53 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -52,6 +52,7 @@
 #define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/signal.h>
 
 #include <linux/drbd_limits.h>
 #include "drbd_int.h"
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 8b40a5b2f8e6..aa6bf9692eff 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -37,6 +37,7 @@
 #include <linux/mm_inline.h>
 #include <linux/slab.h>
 #include <uapi/linux/sched/types.h>
+#include <linux/sched/signal.h>
 #include <linux/pkt_sched.h>
 #define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index c6755c9a0aea..3bff33f21435 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -25,7 +25,7 @@
 
 #include <linux/module.h>
 #include <linux/drbd.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/wait.h>
 #include <linux/mm.h>
 #include <linux/memcontrol.h>
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index aabd8e9d3035..61b3ffa4f458 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -20,7 +20,7 @@
 
 #include <linux/stddef.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/timer.h>
 #include <linux/delay.h>
 #include <linux/fd.h>
diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c
index e5c62dcf2c11..e770ad977472 100644
--- a/drivers/char/applicom.c
+++ b/drivers/char/applicom.c
@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/mutex.h>
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 20b32bb8c2af..8bdc38d81adf 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/sysctl.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 #include <linux/bcd.h>
 #include <linux/seq_file.h>
 #include <linux/bitops.h>
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 5c654b5d4adf..503a41dfa193 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -17,6 +17,7 @@
 #include <linux/hw_random.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
+#include <linux/sched/signal.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/random.h>
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 30b9e83bf1bf..5ca24d9b101b 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -53,6 +53,7 @@
 #include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/sched/signal.h>
 
 #ifdef CONFIG_X86
 /*
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index 5b6742770656..565e4cf04a02 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -117,7 +117,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/major.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/fcntl.h>
 #include <linux/delay.h>
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index 87885d146dbb..2a558c706581 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -58,7 +58,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/device.h>
 #include <linux/ioctl.h>
 #include <linux/parport.h>
diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c
index 35259961cc38..974d48927b07 100644
--- a/drivers/char/rtc.c
+++ b/drivers/char/rtc.c
@@ -74,7 +74,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sysctl.h>
 #include <linux/wait.h>
 #include <linux/bcd.h>
diff --git a/drivers/char/snsc.c b/drivers/char/snsc.c
index ec07f0e99732..6aa32679fd58 100644
--- a/drivers/char/snsc.c
+++ b/drivers/char/snsc.c
@@ -16,7 +16,7 @@
  */
 
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/device.h>
 #include <linux/poll.h>
 #include <linux/init.h>
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index d1f1f456f5c4..d195d617076d 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -22,6 +22,7 @@
 #include <linux/export.h>
 #include <linux/atomic.h>
 #include <linux/dma-fence.h>
+#include <linux/sched/signal.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/dma_fence.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
index a2bb855a2851..ac5800c72cb4 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
@@ -18,7 +18,7 @@
 #include <linux/jiffies.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include <linux/of_device.h>
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index ab3016982466..1eef98c3331d 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -26,6 +26,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/device.h>
 #include <linux/io.h>
+#include <linux/sched/signal.h>
 
 #include "uapi/drm/vc4_drm.h"
 #include "vc4_drv.h"
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 0f5b2dd24507..92f1452dad57 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -41,7 +41,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/list.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/wait.h>
 #include <linux/spinlock.h>
 #include <linux/poll.h>
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index acfb522a432a..c6c9c51c806f 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -30,7 +30,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c
index 76d06cf87b2a..fb77dec720a4 100644
--- a/drivers/hid/hid-roccat.c
+++ b/drivers/hid/hid-roccat.c
@@ -25,7 +25,7 @@
 
 #include <linux/cdev.h>
 #include <linux/poll.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/hid-roccat.h>
 #include <linux/module.h>
 
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index f0e2757cb909..ec530454e6f6 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -33,7 +33,7 @@
 #include <linux/slab.h>
 #include <linux/hid.h>
 #include <linux/mutex.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/string.h>
 
 #include <linux/hidraw.h>
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 700145b15088..774bd701dae0 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -27,6 +27,7 @@
 
 #include <linux/poll.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/input.h>
diff --git a/drivers/hsi/clients/cmt_speech.c b/drivers/hsi/clients/cmt_speech.c
index 7175e6bedf21..727f968ac1cb 100644
--- a/drivers/hsi/clients/cmt_speech.c
+++ b/drivers/hsi/clients/cmt_speech.c
@@ -31,7 +31,7 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/poll.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/ioctl.h>
 #include <linux/uaccess.h>
 #include <linux/pm_qos.h>
diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c
index 412b91d255ad..961c5f42d956 100644
--- a/drivers/i2c/busses/i2c-ibm_iic.c
+++ b/drivers/i2c/busses/i2c-ibm_iic.c
@@ -37,6 +37,8 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
+#include <linux/sched/signal.h>
+
 #include <asm/irq.h>
 #include <linux/io.h>
 #include <linux/i2c.h>
diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c
index 565a49a0c564..96caf378b1dc 100644
--- a/drivers/i2c/busses/i2c-mpc.c
+++ b/drivers/i2c/busses/i2c-mpc.c
@@ -15,7 +15,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 4972986f6455..d2b465140a6b 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -20,7 +20,7 @@
 #include <linux/cdev.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 #include <linux/iio/iio.h>
 #include "iio_core.h"
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index a6d6c617b597..0cdf2b7f272f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/moduleparam.h>
+#include <linux/sched/signal.h>
 
 #include "ipoib.h"
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index deedb6fc1b05..3e10e3dac2e7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 
 #include <linux/init.h>
 #include <linux/seq_file.h>
diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 49d0f70c2bae..1dfd1085a04f 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -18,7 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/proc_fs.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/workqueue.h>
diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c
index 9438d7ec3308..b1e135fc1fb5 100644
--- a/drivers/isdn/mISDN/timerdev.c
+++ b/drivers/isdn/mISDN/timerdev.c
@@ -25,6 +25,8 @@
 #include <linux/module.h>
 #include <linux/mISDNif.h>
 #include <linux/mutex.h>
+#include <linux/sched/signal.h>
+
 #include "core.h"
 
 static DEFINE_MUTEX(mISDN_mutex);
diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index ac219045daf7..395ed1961dbf 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -8,6 +8,7 @@
 #include <linux/stddef.h>
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/vmalloc.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index 152414e6378a..fee939efc4fc 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -23,7 +23,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/adb.h>
 #include <linux/cuda.h>
 #include <linux/pmu.h>
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 227869159ac0..1ac66421877a 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -39,6 +39,7 @@
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <linux/memblock.h>
+#include <linux/sched/signal.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 43b8db2b5445..cce99f72e4ae 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -23,7 +23,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/miscdevice.h>
 #include <linux/blkdev.h>
 #include <linux/pci.h>
diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c
index 9c79f8019d2a..97fb956bb6e0 100644
--- a/drivers/mailbox/mailbox-test.c
+++ b/drivers/mailbox/mailbox-test.c
@@ -21,6 +21,7 @@
 #include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/sched/signal.h>
 
 #define MBOX_MAX_SIG_LEN	8
 #define MBOX_MAX_MSG_LEN	128
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9f37d7fc2786..f4ffd1eb8f44 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched/signal.h>
 #include <linux/blkpg.h>
 #include <linux/bio.h>
 #include <linux/mempool.h>
diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c
index 000d737ad827..8d65028c7a74 100644
--- a/drivers/media/dvb-core/dvb_ca_en50221.c
+++ b/drivers/media/dvb-core/dvb_ca_en50221.c
@@ -34,7 +34,7 @@
 #include <linux/vmalloc.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kthread.h>
 
 #include "dvb_ca_en50221.h"
diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c
index 4eac71e50c5f..6628f80d184f 100644
--- a/drivers/media/dvb-core/dvb_demux.c
+++ b/drivers/media/dvb-core/dvb_demux.c
@@ -19,7 +19,7 @@
 
 #define pr_fmt(fmt) "dvb_demux: " fmt
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index 85ae3669aa66..e3fff8f64d37 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -29,7 +29,7 @@
 
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
diff --git a/drivers/media/pci/cx18/cx18-driver.h b/drivers/media/pci/cx18/cx18-driver.h
index fef3c736fcba..7be2088c45fe 100644
--- a/drivers/media/pci/cx18/cx18-driver.h
+++ b/drivers/media/pci/cx18/cx18-driver.h
@@ -24,7 +24,7 @@
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/pci.h>
 #include <linux/interrupt.h>
diff --git a/drivers/media/pci/ivtv/ivtv-driver.h b/drivers/media/pci/ivtv/ivtv-driver.h
index cde452e30746..d27c5c2c07ea 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.h
+++ b/drivers/media/pci/ivtv/ivtv-driver.h
@@ -38,37 +38,38 @@
  *                using information provided by Jiun-Kuei Jung @ AVerMedia.
  */
 
-#include <asm/byteorder.h>
+#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/ivtv.h>
-#include <linux/kernel.h>
-#include <linux/kthread.h>
 #include <linux/list.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
+#include <linux/unistd.h>
 #include <linux/pagemap.h>
-#include <linux/pci.h>
 #include <linux/scatterlist.h>
-#include <linux/sched.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/uaccess.h>
-#include <linux/unistd.h>
+#include <asm/byteorder.h>
 
-#include <media/drv-intf/cx2341x.h>
-#include <media/i2c/ir-kbd-i2c.h>
-#include <media/tuner.h>
+#include <linux/dvb/video.h>
+#include <linux/dvb/audio.h>
 #include <media/v4l2-common.h>
+#include <media/v4l2-ioctl.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-fh.h>
-#include <media/v4l2-ioctl.h>
+#include <media/tuner.h>
+#include <media/drv-intf/cx2341x.h>
+#include <media/i2c/ir-kbd-i2c.h>
+
+#include <linux/ivtv.h>
 
 /* Memory layout */
 #define IVTV_ENCODER_OFFSET	0x00000000
diff --git a/drivers/media/pci/pt1/pt1.c b/drivers/media/pci/pt1/pt1.c
index da1eebd2016f..3219d2f3271e 100644
--- a/drivers/media/pci/pt1/pt1.c
+++ b/drivers/media/pci/pt1/pt1.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/media/pci/pt3/pt3.c b/drivers/media/pci/pt3/pt3.c
index 77f4d15f322b..e8b5d0992157 100644
--- a/drivers/media/pci/pt3/pt3.c
+++ b/drivers/media/pci/pt3/pt3.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 
 #include "dmxdev.h"
 #include "dvbdev.h"
diff --git a/drivers/media/pci/solo6x10/solo6x10-i2c.c b/drivers/media/pci/solo6x10/solo6x10-i2c.c
index c908672b2c40..e83bb79f9349 100644
--- a/drivers/media/pci/solo6x10/solo6x10-i2c.c
+++ b/drivers/media/pci/solo6x10/solo6x10-i2c.c
@@ -27,6 +27,7 @@
  * thread context, ACK the interrupt, and move on. -- BenC */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 
 #include "solo6x10.h"
 
diff --git a/drivers/media/pci/zoran/zoran_device.c b/drivers/media/pci/zoran/zoran_device.c
index 671907a6e6b6..40adceebca7e 100644
--- a/drivers/media/pci/zoran/zoran_device.c
+++ b/drivers/media/pci/zoran/zoran_device.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/ktime.h>
+#include <linux/sched/signal.h>
 
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
diff --git a/drivers/media/platform/vivid/vivid-radio-rx.c b/drivers/media/platform/vivid/vivid-radio-rx.c
index f99092ca8f5c..47c36c26096b 100644
--- a/drivers/media/platform/vivid/vivid-radio-rx.c
+++ b/drivers/media/platform/vivid/vivid-radio-rx.c
@@ -22,6 +22,8 @@
 #include <linux/delay.h>
 #include <linux/videodev2.h>
 #include <linux/v4l2-dv-timings.h>
+#include <linux/sched/signal.h>
+
 #include <media/v4l2-common.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-dv-timings.h>
diff --git a/drivers/media/platform/vivid/vivid-radio-tx.c b/drivers/media/platform/vivid/vivid-radio-tx.c
index 8c59d4f53200..0e8025b7b4dd 100644
--- a/drivers/media/platform/vivid/vivid-radio-tx.c
+++ b/drivers/media/platform/vivid/vivid-radio-tx.c
@@ -19,6 +19,7 @@
 
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/delay.h>
 #include <linux/videodev2.h>
 #include <linux/v4l2-dv-timings.h>
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index a54ca531d8ef..393dccaabdd0 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -19,7 +19,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/ioctl.h>
 #include <linux/fs.h>
diff --git a/drivers/media/usb/cpia2/cpia2_core.c b/drivers/media/usb/cpia2/cpia2_core.c
index 431dd0b4b332..b1d13444ff30 100644
--- a/drivers/media/usb/cpia2/cpia2_core.c
+++ b/drivers/media/usb/cpia2/cpia2_core.c
@@ -32,6 +32,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/firmware.h>
+#include <linux/sched/signal.h>
 
 #define FIRMWARE "cpia2/stv0672_vp4.bin"
 MODULE_FIRMWARE(FIRMWARE);
diff --git a/drivers/media/usb/gspca/cpia1.c b/drivers/media/usb/gspca/cpia1.c
index 23d3285f182a..e91d00762e94 100644
--- a/drivers/media/usb/gspca/cpia1.c
+++ b/drivers/media/usb/gspca/cpia1.c
@@ -27,6 +27,8 @@
 #define MODULE_NAME "cpia1"
 
 #include <linux/input.h>
+#include <linux/sched/signal.h>
+
 #include "gspca.h"
 
 MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index e33011e3e7e2..2fa015c05561 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/workqueue.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/pid.h>
 #include <linux/mm.h>
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 859959f19f10..e7139c76f961 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -12,7 +12,7 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/bitmap.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/poll.h>
 #include <linux/pid.h>
 #include <linux/fs.h>
diff --git a/drivers/misc/ibmasm/r_heartbeat.c b/drivers/misc/ibmasm/r_heartbeat.c
index 232034f5da48..5c7dd26db716 100644
--- a/drivers/misc/ibmasm/r_heartbeat.c
+++ b/drivers/misc/ibmasm/r_heartbeat.c
@@ -20,7 +20,7 @@
  *
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include "ibmasm.h"
 #include "dot_command.h"
 
diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c
index fb8705fc3aca..e389b0b5278d 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d.c
@@ -23,6 +23,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/dmi.h>
 #include <linux/module.h>
 #include <linux/types.h>
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index cb3e9e0ca049..df5f78ae3d25 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 68fe37b5bc52..d3e3372424d6 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -14,7 +14,7 @@
  *
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/wait.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 9d0b7050c79a..bf816449cd40 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -26,7 +26,7 @@
 #include <linux/init.h>
 #include <linux/ioctl.h>
 #include <linux/cdev.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uuid.h>
 #include <linux/compat.h>
 #include <linux/jiffies.h>
diff --git a/drivers/misc/mic/scif/scif_main.h b/drivers/misc/mic/scif/scif_main.h
index a08f0b600a9e..0e5eff9ad080 100644
--- a/drivers/misc/mic/scif/scif_main.h
+++ b/drivers/misc/mic/scif/scif_main.h
@@ -18,7 +18,7 @@
 #ifndef SCIF_MAIN_H
 #define SCIF_MAIN_H
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/pci.h>
 #include <linux/miscdevice.h>
 #include <linux/dmaengine.h>
diff --git a/drivers/misc/vexpress-syscfg.c b/drivers/misc/vexpress-syscfg.c
index c344483fa7d6..2cde80c7bb93 100644
--- a/drivers/misc/vexpress-syscfg.c
+++ b/drivers/misc/vexpress-syscfg.c
@@ -16,7 +16,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/syscore_ops.h>
 #include <linux/vexpress.h>
diff --git a/drivers/mtd/tests/mtd_test.h b/drivers/mtd/tests/mtd_test.h
index 4b7bee17c924..04afd0e7074f 100644
--- a/drivers/mtd/tests/mtd_test.h
+++ b/drivers/mtd/tests/mtd_test.h
@@ -1,5 +1,5 @@
 #include <linux/mtd/mtd.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 static inline int mtdtest_relax(void)
 {
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 577e57cad1dc..1bcbb8913e17 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -16,6 +16,8 @@
 #include <linux/rcupdate.h>
 #include <linux/ctype.h>
 #include <linux/inet.h>
+#include <linux/sched/signal.h>
+
 #include <net/bonding.h>
 
 static int bond_option_active_slave_set(struct bonding *bond,
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index e23c3ed737de..770623a0cc01 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -24,7 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/types.h>
 #include <linux/string.h>
diff --git a/drivers/net/can/softing/softing_fw.c b/drivers/net/can/softing/softing_fw.c
index 4063215c9b54..aac58ce6e371 100644
--- a/drivers/net/can/softing/softing_fw.c
+++ b/drivers/net/can/softing/softing_fw.c
@@ -17,7 +17,7 @@
  */
 
 #include <linux/firmware.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <asm/div64.h>
 #include <asm/io.h>
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index a448177990fe..30d1eb9ebec9 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -20,6 +20,7 @@
 #include <linux/moduleparam.h>
 #include <linux/stringify.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index 8cd389148166..aa36e9ae7676 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -23,6 +23,8 @@
 #ifndef _OCTEON_MAIN_H_
 #define  _OCTEON_MAIN_H_
 
+#include <linux/sched/signal.h>
+
 #if BITS_PER_LONG == 32
 #define CVM_CAST64(v) ((long long)(v))
 #elif BITS_PER_LONG == 64
diff --git a/drivers/net/ethernet/sfc/falcon/falcon.c b/drivers/net/ethernet/sfc/falcon/falcon.c
index c6ff0cc5ef18..93c713c1f627 100644
--- a/drivers/net/ethernet/sfc/falcon/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon/falcon.c
@@ -16,6 +16,8 @@
 #include <linux/i2c.h>
 #include <linux/mii.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include "net_driver.h"
 #include "bitfield.h"
 #include "efx.h"
diff --git a/drivers/net/irda/stir4200.c b/drivers/net/irda/stir4200.c
index 42da094b68dd..7ee514879531 100644
--- a/drivers/net/irda/stir4200.c
+++ b/drivers/net/irda/stir4200.c
@@ -40,6 +40,7 @@
 #include <linux/moduleparam.h>
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/ktime.h>
 #include <linux/types.h>
 #include <linux/time.h>
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index a4bfc10b61dd..da85057680d6 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -9,7 +9,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/cache.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index a411b43a69eb..f9c0e62716ea 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -24,6 +24,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/list.h>
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 30863e378925..dc1b1dd9157c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -44,6 +44,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/major.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index e7b516342678..4f2e8141dbe2 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -52,7 +52,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/delay.h>
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 24d5272cdce5..805674550683 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/netdevice.h>
 #include <linux/ethtool.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index 087eb266601f..4ca71bca39ac 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -78,7 +78,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
 #include <linux/fs.h>
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index b7fe0af4cb24..363b30a549c2 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -20,6 +20,7 @@
 #include <linux/moduleparam.h>
 #include <linux/inetdevice.h>
 #include <linux/export.h>
+#include <linux/sched/signal.h>
 
 #include "core.h"
 #include "cfg80211.h"
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index e97ab2b91663..cdafebb9c936 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -36,7 +36,7 @@
 #include <linux/etherdevice.h>
 #include <linux/firmware.h>
 #include <linux/workqueue.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/skbuff.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 544ef7adde7d..04dfd040a650 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -43,7 +43,7 @@
 #include <linux/delay.h>
 #include <linux/random.h>
 #include <linux/wait.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/rtnetlink.h>
 #include <linux/wireless.h>
 #include <net/iw_handler.h>
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c b/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
index a5656bc0e6aa..b2c6b065b542 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_ioctl.c
@@ -2,7 +2,7 @@
 
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/ethtool.h>
 #include <linux/if_arp.h>
 #include <linux/module.h>
diff --git a/drivers/oprofile/event_buffer.c b/drivers/oprofile/event_buffer.c
index 67935fbbbcab..32888f2bd1a9 100644
--- a/drivers/oprofile/event_buffer.c
+++ b/drivers/oprofile/event_buffer.c
@@ -14,7 +14,7 @@
 
 #include <linux/vmalloc.h>
 #include <linux/oprofile.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/capability.h>
 #include <linux/dcookies.h>
 #include <linux/fs.h>
diff --git a/drivers/parport/daisy.c b/drivers/parport/daisy.c
index d998d0ed2bec..46eb15fb57ff 100644
--- a/drivers/parport/daisy.c
+++ b/drivers/parport/daisy.c
@@ -23,7 +23,7 @@
 #include <linux/parport.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 #include <asm/current.h>
 #include <linux/uaccess.h>
diff --git a/drivers/parport/ieee1284.c b/drivers/parport/ieee1284.c
index f9fd4b33a546..74cc6dd982d2 100644
--- a/drivers/parport/ieee1284.c
+++ b/drivers/parport/ieee1284.c
@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/timer.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 
 #undef DEBUG /* undef me for production */
 
diff --git a/drivers/parport/ieee1284_ops.c b/drivers/parport/ieee1284_ops.c
index 75071605d22f..a959224d011b 100644
--- a/drivers/parport/ieee1284_ops.c
+++ b/drivers/parport/ieee1284_ops.c
@@ -17,7 +17,7 @@
 #include <linux/module.h>
 #include <linux/parport.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 
 #undef DEBUG /* undef me for production */
diff --git a/drivers/parport/parport_ip32.c b/drivers/parport/parport_ip32.c
index 30e981be14c2..dcbeeb220dda 100644
--- a/drivers/parport/parport_ip32.c
+++ b/drivers/parport/parport_ip32.c
@@ -102,7 +102,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/parport.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 3e56e7deab8e..9d42dfe65d44 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -44,7 +44,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index 3308427ed9f7..bc090daa850a 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -27,7 +27,7 @@
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kmod.h>
 #include <linux/device.h>
 
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index b9dd37c8c9ce..8b7382705bf2 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -1,7 +1,7 @@
 #include <linux/delay.h>
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/wait.h>
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index 7ec8a8f72c69..95f689f53920 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -27,6 +27,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
diff --git a/drivers/pci/hotplug/cpqphp.h b/drivers/pci/hotplug/cpqphp.h
index 9103a7b9f3b9..48c8a066a6b7 100644
--- a/drivers/pci/hotplug/cpqphp.h
+++ b/drivers/pci/hotplug/cpqphp.h
@@ -32,7 +32,7 @@
 #include <asm/io.h>		/* for read? and write? functions */
 #include <linux/delay.h>	/* for delays */
 #include <linux/mutex.h>
-#include <linux/sched.h>	/* for signal_pending() */
+#include <linux/sched/signal.h>	/* for signal_pending() */
 
 #define MY_NAME	"cpqphp"
 
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 37d70b5ad22f..06109d40c4ac 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -33,7 +33,7 @@
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
 #include <linux/delay.h>
-#include <linux/sched.h>		/* signal_pending() */
+#include <linux/sched/signal.h>		/* signal_pending() */
 #include <linux/pcieport_if.h>
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h
index 4da8fc601467..70c7ea6af034 100644
--- a/drivers/pci/hotplug/shpchp.h
+++ b/drivers/pci/hotplug/shpchp.h
@@ -33,7 +33,7 @@
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
 #include <linux/delay.h>
-#include <linux/sched.h>	/* signal_pending(), struct timer_list */
+#include <linux/sched/signal.h>	/* signal_pending(), struct timer_list */
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
 
diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c
index a6d9434addf6..6dc8f29697ab 100644
--- a/drivers/rtc/rtc-dev.c
+++ b/drivers/rtc/rtc-dev.c
@@ -15,7 +15,7 @@
 
 #include <linux/module.h>
 #include <linux/rtc.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include "rtc-core.h"
 
 static dev_t rtc_devt;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 79823ee9c100..b8006ea9099c 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -24,6 +24,7 @@
 #include <linux/delay.h>
 #include <linux/timer.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched/signal.h>
 
 #include <asm/ccwdev.h>
 #include <asm/cio.h>
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index e18bbc66e83b..4e36998a266c 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -28,6 +28,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/sched/signal.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 75ac662793a3..c47f4b349bac 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -35,7 +35,7 @@ static const char * osst_version = "0.99.4";
 
 #include <linux/fs.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/proc_fs.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 81212d4bd9bf..e5ef78a6848e 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -23,7 +23,7 @@ static const char *verstr = "20160209";
 
 #include <linux/fs.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/string.h>
diff --git a/drivers/soc/fsl/qbman/dpaa_sys.h b/drivers/soc/fsl/qbman/dpaa_sys.h
index 2eaf3184f61d..2ce394aa4c95 100644
--- a/drivers/soc/fsl/qbman/dpaa_sys.h
+++ b/drivers/soc/fsl/qbman/dpaa_sys.h
@@ -36,6 +36,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/kthread.h>
+#include <linux/sched/signal.h>
 #include <linux/vmalloc.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index 57e8599b54e6..8deac8d9225d 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -23,7 +23,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fcntl.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
diff --git a/drivers/staging/dgnc/dgnc_tty.c b/drivers/staging/dgnc/dgnc_tty.c
index c63e591631f6..c3b8fc54883d 100644
--- a/drivers/staging/dgnc/dgnc_tty.c
+++ b/drivers/staging/dgnc/dgnc_tty.c
@@ -19,7 +19,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sched.h>	/* For jiffies, task states */
+#include <linux/sched/signal.h>	/* For jiffies, task states, etc. */
 #include <linux/interrupt.h>	/* For tasklet and interrupt structs/defines */
 #include <linux/module.h>
 #include <linux/ctype.h>
diff --git a/drivers/staging/dgnc/dgnc_utils.c b/drivers/staging/dgnc/dgnc_utils.c
index 95272f4765fc..6f59240024d1 100644
--- a/drivers/staging/dgnc/dgnc_utils.c
+++ b/drivers/staging/dgnc/dgnc_utils.c
@@ -1,5 +1,5 @@
 #include <linux/tty.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include "dgnc_utils.h"
 
 /*
diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c
index ab0dbf5cab5a..43255e2e9276 100644
--- a/drivers/staging/greybus/uart.c
+++ b/drivers/staging/greybus/uart.c
@@ -14,7 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index 21aec0ca9ad3..7d8628ce0d3b 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -44,6 +44,7 @@
 
 #ifdef __KERNEL__
 # include <linux/quota.h>
+# include <linux/sched/signal.h>
 # include <linux/string.h> /* snprintf() */
 # include <linux/version.h>
 #else /* !__KERNEL__ */
diff --git a/drivers/staging/lustre/lustre/include/lustre_lib.h b/drivers/staging/lustre/lustre/include/lustre_lib.h
index 27f3148c4344..b04d613846ee 100644
--- a/drivers/staging/lustre/lustre/include/lustre_lib.h
+++ b/drivers/staging/lustre/lustre/include/lustre_lib.h
@@ -42,7 +42,7 @@
  * @{
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/types.h>
 #include "../../include/linux/libcfs/libcfs.h"
diff --git a/drivers/staging/lustre/lustre/include/obd_support.h b/drivers/staging/lustre/lustre/include/obd_support.h
index aaedec7d793c..dace6591a0a4 100644
--- a/drivers/staging/lustre/lustre/include/obd_support.h
+++ b/drivers/staging/lustre/lustre/include/obd_support.h
@@ -34,6 +34,8 @@
 #define _OBD_SUPPORT
 
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include "../../include/linux/libcfs/libcfs.h"
 #include "lustre_compat.h"
 #include "lprocfs_status.h"
diff --git a/drivers/staging/media/lirc/lirc_sir.c b/drivers/staging/media/lirc/lirc_sir.c
index c75ae43095ba..c6c3de94adaa 100644
--- a/drivers/staging/media/lirc/lirc_sir.c
+++ b/drivers/staging/media/lirc/lirc_sir.c
@@ -36,7 +36,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/fs.h>
diff --git a/drivers/staging/media/lirc/lirc_zilog.c b/drivers/staging/media/lirc/lirc_zilog.c
index 34aac3e2eb87..e4a533b6beb3 100644
--- a/drivers/staging/media/lirc/lirc_zilog.c
+++ b/drivers/staging/media/lirc/lirc_zilog.c
@@ -42,7 +42,7 @@
 #include <linux/module.h>
 #include <linux/kmod.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/poll.h>
 #include <linux/string.h>
diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c
index ff68a384f9c2..d2ff0afd685a 100644
--- a/drivers/staging/speakup/speakup_soft.c
+++ b/drivers/staging/speakup/speakup_soft.c
@@ -22,7 +22,7 @@
 #include <linux/unistd.h>
 #include <linux/miscdevice.h>	/* for misc_register, and SYNTH_MINOR */
 #include <linux/poll.h>		/* for poll_wait() */
-#include <linux/sched.h> /* schedule(), signal_pending(), TASK_INTERRUPTIBLE */
+#include <linux/sched/signal.h> /* schedule(), signal_pending(), TASK_INTERRUPTIBLE */
 
 #include "spk_priv.h"
 #include "speakup.h"
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
index 8bcb9b71f764..0c3e8fce3695 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_target.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -8,6 +8,8 @@
 
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
+#include <linux/sched/signal.h>
+
 #include <asm/unaligned.h>
 #include <net/tcp.h>
 #include <target/target_core_base.h>
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index f3932baed07d..55577cf9b6a4 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -39,7 +39,7 @@
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/fcntl.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/interrupt.h>
 #include <linux/tty.h>
 #include <linux/ctype.h>
diff --git a/drivers/tty/serial/crisv10.c b/drivers/tty/serial/crisv10.c
index e92c23470e51..59a2a7e18b5a 100644
--- a/drivers/tty/serial/crisv10.c
+++ b/drivers/tty/serial/crisv10.c
@@ -12,7 +12,7 @@ static char *serial_version = "$Revision: 1.25 $";
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/timer.h>
 #include <linux/interrupt.h>
 #include <linux/tty.h>
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 9939c3d9912b..3fe56894974a 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -24,6 +24,7 @@
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/of.h>
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index f27fc0f14c11..a9a978731c5b 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -9,7 +9,7 @@
 #include <linux/types.h>
 #include <linux/termios.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/major.h>
 #include <linux/tty.h>
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 5cd3cd932293..1d21a9c1d33e 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -11,7 +11,7 @@
 #include <linux/timer.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/wait.h>
 #include <linux/bitops.h>
 #include <linux/delay.h>
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 31d95dc9c202..60ce7fd54e89 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -20,7 +20,7 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/idr.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/string.h>
 #include <linux/kobject.h>
 #include <linux/cdev.h>
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 235e305f8473..d5388938bc7a 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -32,6 +32,7 @@
 #undef VERBOSE_DEBUG
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/slab.h>
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 071964c7847f..cc61055fb9be 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -49,7 +49,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 87fccf611b69..a5b7cd615698 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -23,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/hid.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/uio.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c
index 5cf2633cdb04..e92540a21b6b 100644
--- a/drivers/usb/image/mdc800.c
+++ b/drivers/usb/image/mdc800.c
@@ -85,7 +85,7 @@
  * (20/10/1999)
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/signal.h>
 #include <linux/spinlock.h>
 #include <linux/errno.h>
diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c
index c5fa584d8f0a..db9a9e6ff6be 100644
--- a/drivers/usb/misc/adutux.c
+++ b/drivers/usb/misc/adutux.c
@@ -21,6 +21,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/module.h>
diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c
index debc1fd74b0d..8b9fd7534f69 100644
--- a/drivers/usb/misc/idmouse.c
+++ b/drivers/usb/misc/idmouse.c
@@ -17,6 +17,7 @@
 */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
diff --git a/drivers/usb/misc/rio500.c b/drivers/usb/misc/rio500.c
index fc329c98a6e8..b106ce76997b 100644
--- a/drivers/usb/misc/rio500.c
+++ b/drivers/usb/misc/rio500.c
@@ -31,7 +31,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mutex.h>
 #include <linux/errno.h>
 #include <linux/random.h>
diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c
index 0a643fa74cab..e45a3a680db8 100644
--- a/drivers/usb/misc/uss720.c
+++ b/drivers/usb/misc/uss720.c
@@ -50,6 +50,7 @@
 #include <linux/completion.h>
 #include <linux/kref.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 /*
  * Version Information
diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c
index 9fb8b1e6ecc2..b6d8bf475c92 100644
--- a/drivers/usb/mon/mon_bin.c
+++ b/drivers/usb/mon/mon_bin.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/cdev.h>
diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c
index db1a4abf2806..19c416d69eb9 100644
--- a/drivers/usb/mon/mon_text.c
+++ b/drivers/usb/mon/mon_text.c
@@ -8,6 +8,7 @@
 #include <linux/list.h>
 #include <linux/usb.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
 #include <linux/export.h>
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index eb433922598c..ab78111e0968 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -27,6 +27,7 @@
 #include <linux/uaccess.h>
 #include <linux/usb.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 #include <linux/usb/serial.h>
 
 /* Defines */
diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index 944de657a07a..49ce2be90fa0 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/sysrq.h>
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 5c98ad4d2f4c..9b519897cc17 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -18,6 +18,7 @@
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/signal.h>
 #include <linux/vmalloc.h>
 
 #include <linux/net.h>
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 4a00140a7624..dcbe2e29bf17 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/sort.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/interval_tree_generic.h>
 
 #include "vhost.h"
diff --git a/drivers/video/fbdev/cobalt_lcdfb.c b/drivers/video/fbdev/cobalt_lcdfb.c
index 038ac6934fe9..9da90bd242f4 100644
--- a/drivers/video/fbdev/cobalt_lcdfb.c
+++ b/drivers/video/fbdev/cobalt_lcdfb.c
@@ -26,6 +26,7 @@
 #include <linux/uaccess.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 
 /*
  * Cursor position address
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
index 8b810696a42b..fd2b372d0264 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
@@ -19,7 +19,7 @@
 #include <linux/jiffies.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include <linux/of_device.h>
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 95f42872b787..4f6b00efc27c 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -10,6 +10,8 @@
  */
 
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <rxrpc/packet.h>
diff --git a/fs/aio.c b/fs/aio.c
index 7e2ab9c8e39c..0bb108476de2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -20,7 +20,7 @@
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/mm.h>
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 105d4d43993e..a8812d95359d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -20,6 +20,7 @@
 #define __BTRFS_CTREE__
 
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/highmem.h>
 #include <linux/fs.h>
 #include <linux/rwsem.h>
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index cd966f276a8d..68c78be19d5b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2,7 +2,7 @@
 
 #include <linux/fs.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7ab5be7944aa..1858fc20eb7d 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -23,6 +23,8 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/freezer.h>
+#include <linux/sched/signal.h>
+
 #include <asm/div64.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 822629126e89..f40e3953e7fe 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -22,7 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/major.h>
 #include <linux/time.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/fcntl.h>
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 1ce908c2232c..23488f559cf9 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -17,6 +17,7 @@
 #include <linux/dlm.h>
 #include <linux/dlm_device.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 #include "dlm_internal.h"
 #include "lockspace.h"
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 158a3a39f82d..039e627194a9 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -22,6 +22,8 @@
 
 #include <linux/fs.h>
 #include <linux/pagemap.h>
+#include <linux/sched/signal.h>
+
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 1231cd1999d8..68b9fffcb2c8 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -9,7 +9,7 @@
 #include <linux/poll.h>
 #include <linux/init.h>
 #include <linux/fs.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/list.h>
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 5ec16313da1a..341251421ced 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -13,7 +13,7 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/signal.h>
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2fd17e8e4984..77798a46b0c6 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -28,6 +28,7 @@
 #include <linux/timer.h>
 #include <linux/version.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 #include <linux/blockgroup_lock.h>
 #include <linux/percpu_counter.h>
 #include <linux/ratelimit.h>
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 1375fef11146..1602b4bccae6 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -22,6 +22,7 @@
 #include <linux/mm.h>
 #include <linux/memcontrol.h>
 #include <linux/cleancache.h>
+#include <linux/sched/signal.h>
 
 #include "f2fs.h"
 #include "node.h"
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index f11792672977..b681b43c766e 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/poll.h>
+#include <linux/sched/signal.h>
 #include <linux/uio.h>
 #include <linux/miscdevice.h>
 #include <linux/pagemap.h>
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 8b907c5cc913..0515f0a68637 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 #include <linux/delay.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/sched/signal.h>
 
 #include "incore.h"
 #include "glock.h"
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index e3ee387a6dfe..361796a84fce 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -10,7 +10,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bio.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index aebb78f9e47f..d352f3a6af7f 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -18,7 +18,7 @@
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/blkdev.h>
 #include <asm/unaligned.h>
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 54de77e78775..8f96461236f6 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -11,7 +11,7 @@
 
 #include <linux/thread_info.h>
 #include <asm/current.h>
-#include <linux/sched.h>		/* remove ASAP */
+#include <linux/sched/signal.h>		/* remove ASAP */
 #include <linux/falloc.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index cda0774c2c9c..a7bbe879cfc3 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -14,7 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/mtd/mtd.h>
 #include <linux/compiler.h>
-#include <linux/sched.h> /* For cond_resched() */
+#include <linux/sched/signal.h>
 #include "nodelist.h"
 #include "debug.h"
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5ca4d96b1942..685565b229c3 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -15,7 +15,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 7d18d62e8e07..febed1217b3f 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -30,6 +30,8 @@
 #include <linux/crc32.h>
 #include <linux/pagevec.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include "nilfs.h"
 #include "btnode.h"
 #include "page.h"
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 7ebfca6a1427..2b37f2785834 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
 
 #include <asm/ioctls.h>
 
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 1cf41c623be1..498d609b26c7 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -30,7 +30,7 @@
 #include <linux/inotify.h>
 #include <linux/kernel.h> /* roundup() */
 #include <linux/namei.h> /* LOOKUP_FOLLOW */
-#include <linux/sched.h> /* struct user */
+#include <linux/sched/signal.h>
 #include <linux/slab.h> /* struct kmem_cache */
 #include <linux/syscalls.h>
 #include <linux/types.h>
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 358ed7e1195a..c4f68c338735 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -24,7 +24,7 @@
 #include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/swap.h>
 #include <linux/uio.h>
 #include <linux/writeback.h>
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d4ec0d8961a6..fb15a96df0b6 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -30,6 +30,7 @@
 #include <linux/swap.h>
 #include <linux/quotaops.h>
 #include <linux/blkdev.h>
+#include <linux/sched/signal.h>
 
 #include <cluster/masklog.h>
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 32fd261ae13d..a2b19fbdcf46 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -33,6 +33,7 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/debugfs.h>
+#include <linux/sched/signal.h>
 
 #include "cluster/heartbeat.h"
 #include "cluster/nodemanager.h"
diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c
index f70cda2f090d..9cecf4857195 100644
--- a/fs/ocfs2/dlmfs/userdlm.c
+++ b/fs/ocfs2/dlmfs/userdlm.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/signal.h>
+#include <linux/sched/signal.h>
 
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8dce4099a6ca..3b7c937a36b5 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -33,6 +33,7 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 #include <linux/quotaops.h>
+#include <linux/sched/signal.h>
 
 #define MLOG_MASK_PREFIX ML_DLM_GLUE
 #include <cluster/masklog.h>
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 70355a9a2596..8948683b367f 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -41,7 +41,7 @@
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/uio.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/wait.h>
 #include <linux/dcache.h>
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 53d3f830358f..a34aa7aa2563 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -15,7 +15,7 @@
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include <linux/uaccess.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/fdtable.h>
diff --git a/fs/splice.c b/fs/splice.c
index 4ef78aa8ef61..e49336555739 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -33,6 +33,8 @@
 #include <linux/gfp.h>
 #include <linux/socket.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
+
 #include "internal.h"
 
 /*
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 18d12bfff770..973607df579d 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -14,7 +14,7 @@
 
 #include <linux/list.h>
 #include <linux/hashtable.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/mm.h>
 #include <linux/poll.h>
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 7a989de224f4..592fdf7111cb 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -55,7 +55,7 @@ typedef __u32			xfs_nlink_t;
 #include <linux/file.h>
 #include <linux/swap.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/bitops.h>
 #include <linux/major.h>
 #include <linux/pagemap.h>
diff --git a/include/drm/drm_os_linux.h b/include/drm/drm_os_linux.h
index 86ab99bc0ac5..35e1482ba8a1 100644
--- a/include/drm/drm_os_linux.h
+++ b/include/drm/drm_os_linux.h
@@ -4,6 +4,7 @@
  */
 
 #include <linux/interrupt.h>	/* For task queue support */
+#include <linux/sched/signal.h>
 #include <linux/delay.h>
 
 #ifndef readq
diff --git a/include/linux/sunrpc/types.h b/include/linux/sunrpc/types.h
index d222f47550af..11a7536c0fd2 100644
--- a/include/linux/sunrpc/types.h
+++ b/include/linux/sunrpc/types.h
@@ -10,6 +10,7 @@
 #define _LINUX_SUNRPC_TYPES_H_
 
 #include <linux/timer.h>
+#include <linux/sched/signal.h>
 #include <linux/workqueue.h>
 #include <linux/sunrpc/debug.h>
 #include <linux/list.h>
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index 574ff2ae94be..6cd94e5ee113 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -12,6 +12,7 @@
 #include <linux/poll.h>
 #include <linux/fs.h>
 #include <linux/mutex.h>
+#include <linux/sched/signal.h>
 #include <linux/compiler.h> /* need __user */
 #include <linux/videodev2.h>
 
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index b96832df239e..c0452de83086 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -26,6 +26,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/signal.h>
 #include <net/ip.h>
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 57f6311e2405..82ff5726bc1b 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -19,7 +19,7 @@
  */
 #include <linux/mutex.h>
 #include <linux/ww_mutex.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/wake_q.h>
 #include <linux/export.h>
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index d4f798491361..1c8c8707853a 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -12,7 +12,7 @@
  */
 #include <linux/spinlock.h>
 #include <linux/export.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
 #include <linux/sched/wake_q.h>
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 5eacab880f67..91e7bc8e9d5a 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -6,7 +6,7 @@
  * - Derived also from comments by Linus
  */
 #include <linux/rwsem.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/export.h>
 
 enum rwsem_waiter_type {
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 4fe8d8ad4396..9bd6e768164e 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -12,7 +12,7 @@
 #include <linux/rwsem.h>
 #include <linux/init.h>
 #include <linux/export.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/wake_q.h>
 #include <linux/osq_lock.h>
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 6a28b79710f0..cccc417a8135 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -32,7 +32,7 @@
 #include <linux/smp.h>
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index f063a25d4449..b294a8ee2842 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -11,7 +11,7 @@
  * Waiting for completion is a typically sync point, but not an exclusion point.
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/completion.h>
 
 /**
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 82f0dff90030..3d5610dcce11 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -1,4 +1,4 @@
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/swait.h>
 
 void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 9453efe9b25a..1fedfcf6fc9b 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -5,7 +5,7 @@
  */
 #include <linux/init.h>
 #include <linux/export.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/wait.h>
 #include <linux/hash.h>
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index e6dc9a538efa..04939053c823 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -19,6 +19,7 @@
 #include <linux/hrtimer.h>
 #include <linux/timerqueue.h>
 #include <linux/rtc.h>
+#include <linux/sched/signal.h>
 #include <linux/alarmtimer.h>
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 8e11d8d9f419..df512e8c04d4 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -43,7 +43,7 @@
 #include <linux/seq_file.h>
 #include <linux/err.h>
 #include <linux/debugobjects.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 82a6bfa0c307..f4465d2a25d1 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -38,7 +38,7 @@
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
 #include <linux/irq_work.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/sysctl.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 6d40944960de..010410990bc6 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -22,7 +22,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/percpu_ida.h>
diff --git a/mm/compaction.c b/mm/compaction.c
index 0fdfde016ee2..81e1eaa2a2cf 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -12,6 +12,7 @@
 #include <linux/migrate.h>
 #include <linux/compaction.h>
 #include <linux/mm_inline.h>
+#include <linux/sched/signal.h>
 #include <linux/backing-dev.h>
 #include <linux/sysctl.h>
 #include <linux/sysfs.h>
diff --git a/mm/gup.c b/mm/gup.c
index 94fab8fa432b..9c047e951aa3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -10,7 +10,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/rwsem.h>
 #include <linux/hugetlb.h>
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2e0e8159ce8e..a7aa811b7d14 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -18,6 +18,7 @@
 #include <linux/bootmem.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1d3ed58f92ab..295479b792ec 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -6,6 +6,7 @@
 
 #include <linux/stddef.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/swap.h>
 #include <linux/interrupt.h>
 #include <linux/pagemap.h>
diff --git a/mm/shmem.c b/mm/shmem.c
index a26649a6633f..de8cdef4ef9b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -29,6 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/file.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/export.h>
 #include <linux/swap.h>
 #include <linux/uio.h>
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 9f0ad2a4f102..479e631d43c2 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 878563a8354d..db9794ec61d8 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -10,7 +10,7 @@
 #include <linux/kernel.h>	/* printk */
 #include <linux/skbuff.h>
 #include <linux/wait.h>
-#include <linux/sched.h>	/* jiffies and HZ */
+#include <linux/sched/signal.h>
 #include <linux/fcntl.h>	/* O_NONBLOCK */
 #include <linux/init.h>
 #include <linux/atm.h>		/* ATM stuff */
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index cfb2faba46de..69e1f7d362a8 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -27,6 +27,8 @@
 #include <linux/module.h>
 #include <linux/debugfs.h>
 #include <linux/stringify.h>
+#include <linux/sched/signal.h>
+
 #include <asm/ioctls.h>
 
 #include <net/bluetooth/bluetooth.h>
diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c
index 46ac686c8911..bb308224099c 100644
--- a/net/bluetooth/cmtp/capi.c
+++ b/net/bluetooth/cmtp/capi.c
@@ -26,7 +26,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
 #include <linux/fcntl.h>
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 1015d9c8d97d..b5faff458d8b 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -21,6 +21,8 @@
    SOFTWARE IS DISCLAIMED.
 */
 
+#include <linux/sched/signal.h>
+
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index a8ba752732c9..f307b145ea54 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -29,6 +29,7 @@
 
 #include <linux/module.h>
 #include <linux/export.h>
+#include <linux/sched/signal.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 7511df72347f..aa1a814ceddc 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -27,6 +27,7 @@
 
 #include <linux/export.h>
 #include <linux/debugfs.h>
+#include <linux/sched/signal.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 3125ce670c2f..e4e9a2da1e7e 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/sched/signal.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 0f4034934d56..0b5dd607444c 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -19,6 +19,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/spinlock.h>
 #include <linux/times.h>
+#include <linux/sched/signal.h>
 
 #include "br_private.h"
 
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 05e8946ccc03..79aee759aba5 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -17,6 +17,7 @@
 #include <linux/if_bridge.h>
 #include <linux/rtnetlink.h>
 #include <linux/spinlock.h>
+#include <linux/sched/signal.h>
 
 #include "br_private.h"
 
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index be7bab1adcde..aecb2c7241b6 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -24,7 +24,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/net.h>
 
 /*
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index b0c04cf4851d..3945821e9c1f 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -15,6 +15,7 @@
 #include <net/switchdev.h>
 #include <linux/if_arp.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/nsproxy.h>
 #include <net/sock.h>
 #include <net/net_namespace.h>
diff --git a/net/dccp/output.c b/net/dccp/output.c
index b66c84db0766..91a15b3c4915 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 #include <net/inet_sock.h>
 #include <net/sock.h>
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5d367b7ff542..cebedd545e5e 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3a2025f5bf2c..77362b88a661 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -43,6 +43,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/net.h>
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 817b1b186aff..f6061c4bb0a8 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -32,7 +32,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/seq_file.h>
 #include <linux/termios.h>
 #include <linux/tty.h>
diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c
index 35dbf3dc3d28..7025dcb853d0 100644
--- a/net/irda/irnet/irnet_ppp.c
+++ b/net/irda/irnet/irnet_ppp.c
@@ -13,8 +13,9 @@
  *	2) as a control channel (write commands, read events)
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
+
 #include "irnet_ppp.h"		/* Private header */
 /* Please put other headers in irnet.h - Thanks */
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 13190b38f22e..89bbde1081ce 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -17,7 +17,7 @@
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/skbuff.h>
 #include <linux/init.h>
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index a646f3481240..309062f3debe 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -24,6 +24,8 @@
 #include <linux/uaccess.h>
 #include <linux/workqueue.h>
 #include <linux/syscalls.h>
+#include <linux/sched/signal.h>
+
 #include <net/kcm.h>
 #include <net/netns/generic.h>
 #include <net/sock.h>
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 5e9296382420..06186d608a27 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -26,6 +26,8 @@
 #include <linux/rtnetlink.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include <net/llc.h>
 #include <net/llc_sap.h>
 #include <net/llc_pdu.h>
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index b9edf5fae6ae..879885b31cce 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/nfc.h>
+#include <linux/sched/signal.h>
 
 #include "nfc.h"
 #include "llcp.h"
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 8bad5624a27a..222bedcd9575 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <net/sock.h>
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index ffd5f2297584..a6c8da3ee893 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -27,6 +27,8 @@
 #include <linux/kernel.h>
 #include <linux/net.h>
 #include <linux/poll.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include <net/tcp_states.h>
 
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 40a1ef2adeb4..c3be03e8d098 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -76,6 +76,8 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/timer.h>
+#include <linux/sched/signal.h>
+
 #include "ar-internal.h"
 
 __read_mostly unsigned int rxrpc_max_client_connections = 1000;
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index f3a688e10843..28274a3c9831 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -14,6 +14,8 @@
 #include <linux/net.h>
 #include <linux/skbuff.h>
 #include <linux/export.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 0a6ef217aa8a..19b36c60fb4c 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -15,6 +15,8 @@
 #include <linux/gfp.h>
 #include <linux/skbuff.h>
 #include <linux/export.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 6b09a778cc71..43e4045e72bc 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -35,6 +35,8 @@
  */
 
 #include <linux/rhashtable.h>
+#include <linux/sched/signal.h>
+
 #include "core.h"
 #include "name_table.h"
 #include "node.h"
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 8a398b3fb532..9192ead66751 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -90,6 +90,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/kmod.h>
 #include <linux/list.h>
 #include <linux/miscdevice.h>
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 849c4ad0411e..8d592a45b597 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -9,6 +9,7 @@
  */
 #include <linux/spinlock.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/virtio.h>
diff --git a/sound/core/control.c b/sound/core/control.c
index fb096cb20a80..c109b82eef4b 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/time.h>
+#include <linux/sched/signal.h>
 #include <sound/core.h>
 #include <sound/minors.h>
 #include <sound/info.h>
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index 36d2416f90d9..9602a7e38d8a 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -25,6 +25,7 @@
 #include <linux/time.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/minors.h>
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 698a01419515..36baf962f9b0 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -28,6 +28,7 @@
 
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index bb1261591a1f..5088d4b8db22 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/time.h>
 #include <linux/math64.h>
 #include <linux/export.h>
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index aec9c92250fd..13dec5ec93f2 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -23,6 +23,7 @@
 #include <linux/module.h>
 #include <linux/file.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/time.h>
 #include <linux/pm_qos.h>
 #include <linux/io.h>
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 8da9cb245d01..ab890336175f 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -22,7 +22,7 @@
 #include <sound/core.h>
 #include <linux/major.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/wait.h>
diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h
index d7b4d016b547..afa007c0cc2d 100644
--- a/sound/core/seq/oss/seq_oss_device.h
+++ b/sound/core/seq/oss/seq_oss_device.h
@@ -24,7 +24,7 @@
 #include <linux/time.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <sound/core.h>
 #include <sound/seq_oss.h>
 #include <sound/rawmidi.h>
diff --git a/sound/core/seq/oss/seq_oss_writeq.c b/sound/core/seq/oss/seq_oss_writeq.c
index 1f6788a18444..5e04f4df10e4 100644
--- a/sound/core/seq/oss/seq_oss_writeq.c
+++ b/sound/core/seq/oss/seq_oss_writeq.c
@@ -28,6 +28,7 @@
 #include "../seq_clientmgr.h"
 #include <linux/wait.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 
 /*
diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 86240d02b530..448efd4e980e 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -21,6 +21,8 @@
 
 #include <sound/core.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include "seq_fifo.h"
 #include "seq_lock.h"
 
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index dfa5156f3585..1a1acf3ddda4 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -23,6 +23,7 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 #include <linux/vmalloc.h>
 #include <sound/core.h>
 
diff --git a/sound/core/timer.c b/sound/core/timer.c
index ad153149b231..6d4fbc439246 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -27,6 +27,7 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 #include <sound/core.h>
 #include <sound/timer.h>
 #include <sound/control.h>
diff --git a/sound/firewire/bebob/bebob.h b/sound/firewire/bebob/bebob.h
index 175da875162d..17678d6ab5a2 100644
--- a/sound/firewire/bebob/bebob.h
+++ b/sound/firewire/bebob/bebob.h
@@ -17,6 +17,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 #include <sound/core.h>
 #include <sound/initval.h>
diff --git a/sound/firewire/dice/dice.h b/sound/firewire/dice/dice.h
index e6c07857f475..da00e75e09d4 100644
--- a/sound/firewire/dice/dice.h
+++ b/sound/firewire/dice/dice.h
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 
 #include <sound/control.h>
 #include <sound/core.h>
diff --git a/sound/firewire/digi00x/digi00x.h b/sound/firewire/digi00x/digi00x.h
index 2cd465c0caae..9dc761bdacca 100644
--- a/sound/firewire/digi00x/digi00x.h
+++ b/sound/firewire/digi00x/digi00x.h
@@ -16,6 +16,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 #include <sound/core.h>
 #include <sound/initval.h>
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h
index d73c12b8753d..9b19c7f05d57 100644
--- a/sound/firewire/fireworks/fireworks.h
+++ b/sound/firewire/fireworks/fireworks.h
@@ -17,6 +17,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 #include <sound/core.h>
 #include <sound/initval.h>
diff --git a/sound/firewire/oxfw/oxfw.h b/sound/firewire/oxfw/oxfw.h
index 2047dcb27625..d54d4a9ac4a1 100644
--- a/sound/firewire/oxfw/oxfw.h
+++ b/sound/firewire/oxfw/oxfw.h
@@ -13,6 +13,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
 
 #include <sound/control.h>
 #include <sound/core.h>
diff --git a/sound/firewire/tascam/tascam.h b/sound/firewire/tascam/tascam.h
index 1f61011579a7..d3cd4065722b 100644
--- a/sound/firewire/tascam/tascam.h
+++ b/sound/firewire/tascam/tascam.h
@@ -17,6 +17,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
 
 #include <sound/core.h>
 #include <sound/initval.h>
diff --git a/sound/isa/gus/gus_pcm.c b/sound/isa/gus/gus_pcm.c
index 25f6788ccef3..06505999155f 100644
--- a/sound/isa/gus/gus_pcm.c
+++ b/sound/isa/gus/gus_pcm.c
@@ -27,6 +27,8 @@
 
 #include <asm/dma.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/gus.h>
diff --git a/sound/isa/msnd/msnd.c b/sound/isa/msnd/msnd.c
index 835d4aa26761..8109ab3d29d1 100644
--- a/sound/isa/msnd/msnd.c
+++ b/sound/isa/msnd/msnd.c
@@ -36,6 +36,7 @@
  ********************************************************************/
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
diff --git a/sound/isa/sb/emu8000.c b/sound/isa/sb/emu8000.c
index 94c411299e5a..ec180708f160 100644
--- a/sound/isa/sb/emu8000.c
+++ b/sound/isa/sb/emu8000.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/wait.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/export.h>
diff --git a/sound/isa/sb/emu8000_patch.c b/sound/isa/sb/emu8000_patch.c
index 71d13c0bb746..c2e41d2762f7 100644
--- a/sound/isa/sb/emu8000_patch.c
+++ b/sound/isa/sb/emu8000_patch.c
@@ -20,6 +20,8 @@
  */
 
 #include "emu8000_local.h"
+
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/moduleparam.h>
 
diff --git a/sound/isa/sb/emu8000_pcm.c b/sound/isa/sb/emu8000_pcm.c
index 250fd0006b53..32f234f494e5 100644
--- a/sound/isa/sb/emu8000_pcm.c
+++ b/sound/isa/sb/emu8000_pcm.c
@@ -19,6 +19,8 @@
  */
 
 #include "emu8000_local.h"
+
+#include <linux/sched/signal.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <sound/initval.h>
diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c
index 718d5e3b7806..4dae9ff9ef5a 100644
--- a/sound/isa/wavefront/wavefront_synth.c
+++ b/sound/isa/wavefront/wavefront_synth.c
@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/time.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 #include <linux/firmware.h>
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
diff --git a/sound/oss/dmabuf.c b/sound/oss/dmabuf.c
index e3f29132d3ac..c5dd396c66a2 100644
--- a/sound/oss/dmabuf.c
+++ b/sound/oss/dmabuf.c
@@ -27,6 +27,8 @@
 
 #include <linux/mm.h>
 #include <linux/gfp.h>
+#include <linux/sched/signal.h>
+
 #include "sound_config.h"
 #include "sleep.h"
 
diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c
index 5f248fb41bea..fb3bbceb1fef 100644
--- a/sound/oss/dmasound/dmasound_core.c
+++ b/sound/oss/dmasound/dmasound_core.c
@@ -182,6 +182,7 @@
 #include <linux/soundcard.h>
 #include <linux/poll.h>
 #include <linux/mutex.h>
+#include <linux/sched/signal.h>
 
 #include <linux/uaccess.h>
 
diff --git a/sound/oss/midibuf.c b/sound/oss/midibuf.c
index 8f45cd999965..701c7625c971 100644
--- a/sound/oss/midibuf.c
+++ b/sound/oss/midibuf.c
@@ -16,6 +16,8 @@
 #include <linux/stddef.h>
 #include <linux/kmod.h>
 #include <linux/spinlock.h>
+#include <linux/sched/signal.h>
+
 #define MIDIBUF_C
 
 #include "sound_config.h"
diff --git a/sound/oss/msnd_pinnacle.c b/sound/oss/msnd_pinnacle.c
index a8bb4a06ba6f..f34ec01d2239 100644
--- a/sound/oss/msnd_pinnacle.c
+++ b/sound/oss/msnd_pinnacle.c
@@ -41,6 +41,8 @@
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/gfp.h>
+#include <linux/sched/signal.h>
+
 #include <asm/irq.h>
 #include <asm/io.h>
 #include "sound_config.h"
diff --git a/sound/oss/sound_config.h b/sound/oss/sound_config.h
index f2554ab78f5e..5253b0a70437 100644
--- a/sound/oss/sound_config.h
+++ b/sound/oss/sound_config.h
@@ -16,6 +16,7 @@
 
 #include <linux/fs.h>
 #include <linux/sound.h>
+#include <linux/sched/signal.h>
 
 #include "os.h"
 #include "soundvers.h"
diff --git a/sound/oss/swarm_cs4297a.c b/sound/oss/swarm_cs4297a.c
index f3af63e58b36..97899352b15f 100644
--- a/sound/oss/swarm_cs4297a.c
+++ b/sound/oss/swarm_cs4297a.c
@@ -64,7 +64,7 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/ioport.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/delay.h>
 #include <linux/sound.h>
 #include <linux/slab.h>
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dd5de09bf362..ae79f7679cc2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -32,7 +32,7 @@
 #include <linux/file.h>
 #include <linux/syscore_ops.h>
 #include <linux/cpu.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
-- 
GitLab


From 5b3cc15aff243cb518cbeed8b1a220cbfd023d9c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 20:43:54 +0100
Subject: [PATCH 497/898] sched/headers: Prepare to move the memalloc_noio_*()
 APIs to <linux/sched/mm.h>

Update the .c files that depend on these APIs.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/base/power/runtime.c | 2 +-
 drivers/md/dm-bufio.c        | 1 +
 drivers/md/dm-ioctl.c        | 1 +
 drivers/usb/core/hub.c       | 2 +-
 fs/ocfs2/cluster/tcp.c       | 1 +
 fs/xfs/kmem.c                | 1 +
 fs/xfs/xfs_buf.c             | 1 +
 mm/page_alloc.c              | 1 +
 mm/vmscan.c                  | 1 +
 net/ceph/crypto.c            | 1 +
 10 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index a14fac6a01d3..7bcf80fa9ada 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -7,7 +7,7 @@
  * This file is released under the GPLv2.
  */
 
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/export.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_wakeirq.h>
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index d36d427a9efb..df4859f6ac6a 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -11,6 +11,7 @@
 #include <linux/device-mapper.h>
 #include <linux/dm-io.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include <linux/jiffies.h>
 #include <linux/vmalloc.h>
 #include <linux/shrinker.h>
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index a5a9b17f0f7f..4da6fc6b1ffd 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/miscdevice.h>
+#include <linux/sched/mm.h>
 #include <linux/init.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index a56c75e09786..f0dd08198d74 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/completion.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index ec000575e863..4348027384f5 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -54,6 +54,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/mm.h>
 #include <linux/jiffies.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 339c696bbc01..2dfdc62f795e 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -16,6 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8c7d01b75922..b6208728ba39 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -33,6 +33,7 @@
 #include <linux/migrate.h>
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
+#include <linux/sched/mm.h>
 
 #include "xfs_format.h"
 #include "xfs_log_format.h"
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a7a6aac95a6d..eaa64d2ffdc5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -61,6 +61,7 @@
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/mm.h>
 #include <linux/page_owner.h>
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 70aa739c6b68..bc8031ef994d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/kernel_stat.h>
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 85747b7f91a9..46008d5ac504 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -8,6 +8,7 @@
 #include <crypto/aes.h>
 #include <crypto/skcipher.h>
 #include <linux/key-type.h>
+#include <linux/sched/mm.h>
 
 #include <keys/ceph-type.h>
 #include <keys/user-type.h>
-- 
GitLab


From fd7712337ff09a248df424c5843c149586a3f017 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 20:56:33 +0100
Subject: [PATCH 498/898] sched/headers: Prepare to remove the <linux/gfp.h>
 include from <linux/sched.h>

<linux/topology.h> is still needed - also update other headers
and .c files that depend on sched.h including gfp.h (and its
sub-headers) for them.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h    | 1 +
 include/linux/sched/mm.h | 1 +
 lib/percpu_ida.c         | 1 +
 3 files changed, 3 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e87c97e1a947..8ae7b3d85658 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -56,6 +56,7 @@ struct sched_param {
 #include <linux/llist.h>
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
+#include <linux/topology.h>
 #include <linux/magic.h>
 #include <linux/cgroup-defs.h>
 
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index a7adba1cd0a9..1cf7941bb946 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -2,5 +2,6 @@
 #define _LINUX_SCHED_MM_H
 
 #include <linux/sched.h>
+#include <linux/gfp.h>
 
 #endif /* _LINUX_SCHED_MM_H */
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 010410990bc6..6016f1deb1f5 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -14,6 +14,7 @@
  * General Public License for more details.
  */
 
+#include <linux/mm.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/bug.h>
-- 
GitLab


From 03441a3482a31462c93509939a388877e3cd9261 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:35 +0100
Subject: [PATCH 499/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/stat.h>

We are going to split <linux/sched/stat.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/stat.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c     | 1 +
 arch/s390/appldata/appldata_os.c | 1 +
 crypto/mcryptd.c                 | 1 +
 drivers/cpuidle/governors/menu.c | 1 +
 fs/proc/loadavg.c                | 1 +
 fs/proc/root.c                   | 1 +
 fs/proc/stat.c                   | 1 +
 include/linux/sched/stat.h       | 6 ++++++
 kernel/debug/kdb/kdb_main.c      | 1 +
 kernel/exit.c                    | 1 +
 kernel/fork.c                    | 1 +
 kernel/sched/sched.h             | 1 +
 kernel/sys.c                     | 1 +
 kernel/time/tick-sched.c         | 1 +
 virt/kvm/kvm_main.c              | 1 +
 15 files changed, 20 insertions(+)
 create mode 100644 include/linux/sched/stat.h

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index fc56a9ce785d..1ec86d9e2a82 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/preempt.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/stat.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/fs.h>
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 079446619f89..45b3178200ab 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -18,6 +18,7 @@
 #include <linux/netdevice.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/stat.h>
 #include <asm/appldata.h>
 #include <asm/smp.h>
 
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index c207458d6299..4e6472658852 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/scatterlist.h>
 #include <linux/sched.h>
+#include <linux/sched/stat.h>
 #include <linux/slab.h>
 #include <linux/hardirq.h>
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index fe86060e48f7..6d8a4026a903 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,6 +19,7 @@
 #include <linux/tick.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/stat.h>
 #include <linux/math64.h>
 #include <linux/cpu.h>
 
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index add5255ce7e0..983fce5c2418 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -4,6 +4,7 @@
 #include <linux/proc_fs.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/stat.h>
 #include <linux/seq_file.h>
 #include <linux/seqlock.h>
 #include <linux/time.h>
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 5d5fed20bfff..a50ba388255f 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -14,6 +14,7 @@
 #include <linux/stat.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/stat.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/user_namespace.h>
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index e47c3e8c4dfe..b95556e036bb 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -5,6 +5,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/proc_fs.h>
 #include <linux/sched.h>
+#include <linux/sched/stat.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/time.h>
diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
new file mode 100644
index 000000000000..30fe012aecb0
--- /dev/null
+++ b/include/linux/sched/stat.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_STAT_H
+#define _LINUX_SCHED_STAT_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_STAT_H */
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 308937c7a687..bf48a492b4be 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -19,6 +19,7 @@
 #include <linux/reboot.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/stat.h>
 #include <linux/sysrq.h>
 #include <linux/smp.h>
 #include <linux/utsname.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 48649ccbb649..5bad7dce1b7b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/stat.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/capability.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 8fbe8bcd1e20..8632905f64c5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -17,6 +17,7 @@
 #include <linux/sched/coredump.h>
 #include <linux/sched/user.h>
 #include <linux/sched/numa_balancing.h>
+#include <linux/sched/stat.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 04f376cf7ba9..6c8a1db44dde 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -9,6 +9,7 @@
 #include <linux/sched/numa_balancing.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/cpufreq.h>
+#include <linux/sched/stat.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
 #include <linux/kernel_stat.h>
diff --git a/kernel/sys.c b/kernel/sys.c
index e2d743fb7f55..8c0392c8be51 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -51,6 +51,7 @@
 #include <linux/sched.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/stat.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/rcupdate.h>
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 5e9e123b4321..29d79b175141 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -21,6 +21,7 @@
 #include <linux/profile.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/stat.h>
 #include <linux/module.h>
 #include <linux/irq_work.h>
 #include <linux/posix-timers.h>
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ae79f7679cc2..799499417f5b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -34,6 +34,7 @@
 #include <linux/cpu.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/stat.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 #include <linux/anon_inodes.h>
-- 
GitLab


From 370c91355c76cbcaad8ff79b4bb15a7f2ea59433 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:35 +0100
Subject: [PATCH 500/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/nohz.h>

We are going to split <linux/sched/nohz.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/nohz.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/nohz.h | 6 ++++++
 kernel/sched/sched.h       | 1 +
 kernel/time/hrtimer.c      | 1 +
 kernel/time/tick-sched.c   | 1 +
 kernel/time/timer.c        | 1 +
 5 files changed, 10 insertions(+)
 create mode 100644 include/linux/sched/nohz.h

diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
new file mode 100644
index 000000000000..fe6caf0dab10
--- /dev/null
+++ b/include/linux/sched/nohz.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_NOHZ_H
+#define _LINUX_SCHED_NOHZ_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_NOHZ_H */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6c8a1db44dde..5979f47c422c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -10,6 +10,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/cpufreq.h>
 #include <linux/sched/stat.h>
+#include <linux/sched/nohz.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
 #include <linux/kernel_stat.h>
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index df512e8c04d4..aed2207f5b2d 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -47,6 +47,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
+#include <linux/sched/nohz.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 29d79b175141..7fe53be86077 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -22,6 +22,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/stat.h>
+#include <linux/sched/nohz.h>
 #include <linux/module.h>
 #include <linux/irq_work.h>
 #include <linux/posix-timers.h>
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index f4465d2a25d1..d7999cb06229 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -40,6 +40,7 @@
 #include <linux/irq_work.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/sysctl.h>
+#include <linux/sched/nohz.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
 
-- 
GitLab


From b17b01533b719e9949e437abf66436a875739b40 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:35 +0100
Subject: [PATCH 501/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/debug.h>

We are going to split <linux/sched/debug.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/debug.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/kernel/process.c               | 1 +
 arch/alpha/kernel/traps.c                 | 1 +
 arch/arc/kernel/ctx_sw.c                  | 1 +
 arch/arc/kernel/stacktrace.c              | 2 ++
 arch/arc/kernel/troubleshoot.c            | 1 +
 arch/arm/kernel/process.c                 | 1 +
 arch/arm/kernel/stacktrace.c              | 1 +
 arch/arm/kernel/traps.c                   | 1 +
 arch/arm/mm/alignment.c                   | 1 +
 arch/arm/mm/fault.c                       | 1 +
 arch/arm/probes/kprobes/core.c            | 1 +
 arch/arm64/kernel/probes/kprobes.c        | 1 +
 arch/arm64/kernel/process.c               | 1 +
 arch/arm64/kernel/stacktrace.c            | 1 +
 arch/arm64/kernel/traps.c                 | 1 +
 arch/arm64/mm/fault.c                     | 1 +
 arch/avr32/kernel/nmi_debug.c             | 1 +
 arch/avr32/kernel/process.c               | 1 +
 arch/blackfin/kernel/dumpstack.c          | 2 ++
 arch/blackfin/kernel/early_printk.c       | 1 +
 arch/blackfin/kernel/nmi.c                | 1 +
 arch/blackfin/kernel/process.c            | 1 +
 arch/blackfin/kernel/trace.c              | 1 +
 arch/blackfin/kernel/traps.c              | 1 +
 arch/blackfin/mach-common/ints-priority.c | 1 +
 arch/blackfin/mm/isram-driver.c           | 1 +
 arch/c6x/kernel/traps.c                   | 1 +
 arch/cris/arch-v10/kernel/process.c       | 1 +
 arch/cris/arch-v10/kernel/traps.c         | 2 ++
 arch/cris/arch-v32/kernel/process.c       | 1 +
 arch/cris/arch-v32/kernel/traps.c         | 2 ++
 arch/cris/kernel/irq.c                    | 1 +
 arch/cris/kernel/stacktrace.c             | 2 +-
 arch/cris/kernel/traps.c                  | 1 +
 arch/frv/kernel/process.c                 | 1 +
 arch/frv/kernel/traps.c                   | 1 +
 arch/h8300/kernel/process.c               | 1 +
 arch/h8300/kernel/traps.c                 | 1 +
 arch/hexagon/kernel/process.c             | 1 +
 arch/hexagon/kernel/traps.c               | 1 +
 arch/hexagon/kernel/vm_events.c           | 1 +
 arch/ia64/hp/sim/simserial.c              | 1 +
 arch/ia64/kernel/mca.c                    | 1 +
 arch/ia64/kernel/process.c                | 1 +
 arch/ia64/kernel/traps.c                  | 1 +
 arch/m32r/kernel/process.c                | 1 +
 arch/m32r/kernel/traps.c                  | 1 +
 arch/m68k/kernel/process.c                | 1 +
 arch/m68k/kernel/traps.c                  | 1 +
 arch/m68k/mac/macints.c                   | 1 +
 arch/metag/kernel/process.c               | 1 +
 arch/metag/kernel/stacktrace.c            | 1 +
 arch/metag/kernel/traps.c                 | 1 +
 arch/metag/mm/fault.c                     | 1 +
 arch/microblaze/kernel/exceptions.c       | 1 +
 arch/microblaze/kernel/process.c          | 1 +
 arch/microblaze/kernel/traps.c            | 1 +
 arch/mips/kernel/process.c                | 1 +
 arch/mips/kernel/stacktrace.c             | 1 +
 arch/mips/kernel/traps.c                  | 1 +
 arch/mips/sgi-ip22/ip28-berr.c            | 1 +
 arch/mips/sgi-ip27/ip27-berr.c            | 1 +
 arch/mips/sgi-ip32/ip32-berr.c            | 1 +
 arch/mips/sgi-ip32/ip32-irq.c             | 1 +
 arch/mn10300/kernel/process.c             | 1 +
 arch/mn10300/kernel/traps.c               | 1 +
 arch/nios2/kernel/process.c               | 1 +
 arch/nios2/kernel/traps.c                 | 1 +
 arch/nios2/mm/fault.c                     | 1 +
 arch/openrisc/kernel/process.c            | 1 +
 arch/openrisc/kernel/traps.c              | 1 +
 arch/parisc/kernel/pa7300lc.c             | 1 +
 arch/parisc/kernel/process.c              | 1 +
 arch/parisc/kernel/signal.c               | 1 +
 arch/parisc/kernel/traps.c                | 1 +
 arch/parisc/kernel/unaligned.c            | 1 +
 arch/parisc/mm/fault.c                    | 1 +
 arch/powerpc/kernel/process.c             | 1 +
 arch/powerpc/kernel/stacktrace.c          | 1 +
 arch/powerpc/kernel/traps.c               | 1 +
 arch/s390/kernel/dumpstack.c              | 1 +
 arch/s390/kernel/process.c                | 1 +
 arch/s390/kernel/stacktrace.c             | 1 +
 arch/s390/kernel/traps.c                  | 1 +
 arch/s390/mm/fault.c                      | 1 +
 arch/score/kernel/traps.c                 | 1 +
 arch/sh/kernel/dumpstack.c                | 1 +
 arch/sh/kernel/nmi_debug.c                | 1 +
 arch/sh/kernel/process_32.c               | 1 +
 arch/sh/kernel/process_64.c               | 1 +
 arch/sh/kernel/stacktrace.c               | 1 +
 arch/sh/kernel/traps.c                    | 1 +
 arch/sh/kernel/traps_64.c                 | 1 +
 arch/sparc/kernel/process_32.c            | 1 +
 arch/sparc/kernel/process_64.c            | 1 +
 arch/sparc/kernel/stacktrace.c            | 1 +
 arch/sparc/kernel/sun4m_irq.c             | 1 +
 arch/sparc/kernel/sys_sparc_32.c          | 1 +
 arch/sparc/kernel/sys_sparc_64.c          | 1 +
 arch/sparc/kernel/traps_32.c              | 1 +
 arch/sparc/kernel/traps_64.c              | 1 +
 arch/sparc/mm/fault_64.c                  | 1 +
 arch/tile/include/asm/stack.h             | 2 ++
 arch/tile/kernel/process.c                | 1 +
 arch/tile/kernel/signal.c                 | 1 +
 arch/tile/kernel/stack.c                  | 1 +
 arch/tile/kernel/traps.c                  | 1 +
 arch/tile/kernel/unaligned.c              | 1 +
 arch/tile/mm/fault.c                      | 1 +
 arch/um/drivers/mconsole_kern.c           | 1 +
 arch/um/kernel/process.c                  | 1 +
 arch/um/kernel/sysrq.c                    | 2 ++
 arch/um/kernel/trap.c                     | 1 +
 arch/unicore32/kernel/process.c           | 1 +
 arch/unicore32/kernel/stacktrace.c        | 1 +
 arch/unicore32/kernel/traps.c             | 1 +
 arch/unicore32/mm/alignment.c             | 1 +
 arch/x86/kernel/amd_gart_64.c             | 1 +
 arch/x86/kernel/doublefault.c             | 1 +
 arch/x86/kernel/dumpstack.c               | 1 +
 arch/x86/kernel/dumpstack_32.c            | 1 +
 arch/x86/kernel/dumpstack_64.c            | 1 +
 arch/x86/kernel/kprobes/core.c            | 1 +
 arch/x86/kernel/nmi.c                     | 1 +
 arch/x86/kernel/process.c                 | 1 +
 arch/x86/kernel/stacktrace.c              | 1 +
 arch/x86/mm/extable.c                     | 2 ++
 arch/x86/platform/uv/uv_nmi.c             | 1 +
 arch/x86/um/sysrq_32.c                    | 1 +
 arch/x86/um/sysrq_64.c                    | 1 +
 arch/xtensa/kernel/process.c              | 1 +
 arch/xtensa/kernel/traps.c                | 1 +
 drivers/base/power/main.c                 | 1 +
 drivers/tty/sysrq.c                       | 2 ++
 drivers/tty/tty_ldsem.c                   | 1 +
 drivers/tty/vt/keyboard.c                 | 2 ++
 fs/proc/base.c                            | 1 +
 include/linux/sched/debug.h               | 6 ++++++
 kernel/debug/kdb/kdb_bt.c                 | 1 +
 kernel/debug/kdb/kdb_main.c               | 1 +
 kernel/hung_task.c                        | 1 +
 kernel/latencytop.c                       | 1 +
 kernel/locking/mutex.c                    | 1 +
 kernel/locking/rtmutex-debug.c            | 1 +
 kernel/locking/rtmutex.c                  | 1 +
 kernel/locking/rwsem-spinlock.c           | 1 +
 kernel/locking/rwsem-xadd.c               | 1 +
 kernel/locking/rwsem.c                    | 1 +
 kernel/locking/semaphore.c                | 1 +
 kernel/panic.c                            | 1 +
 kernel/power/process.c                    | 1 +
 kernel/printk/printk.c                    | 1 +
 kernel/rcu/tree.c                         | 1 +
 kernel/rcu/tree_plugin.h                  | 1 +
 kernel/rcu/update.c                       | 1 +
 kernel/sched/completion.c                 | 1 +
 kernel/sched/sched.h                      | 2 +-
 kernel/sched/wait.c                       | 1 +
 kernel/signal.c                           | 1 +
 kernel/time/alarmtimer.c                  | 1 +
 kernel/time/hrtimer.c                     | 1 +
 kernel/time/timer.c                       | 1 +
 kernel/watchdog.c                         | 1 +
 kernel/watchdog_hld.c                     | 2 ++
 lib/dump_stack.c                          | 1 +
 lib/nmi_backtrace.c                       | 1 +
 166 files changed, 181 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/sched/debug.h

diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index bca963a4aa48..88f7a974d311 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -11,6 +11,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 6448ab00043d..b137390e87e7 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -11,6 +11,7 @@
 #include <linux/jiffies.h>
 #include <linux/mm.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/tty.h>
 #include <linux/delay.h>
 #include <linux/extable.h>
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
index 6f4cb0dab1b9..9e1ae9d41925 100644
--- a/arch/arc/kernel/ctx_sw.c
+++ b/arch/arc/kernel/ctx_sw.c
@@ -16,6 +16,7 @@
 
 #include <asm/asm-offsets.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #ifdef CONFIG_ARC_PLAT_EZNPS
 #include <plat/ctop.h>
 #endif
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index b9192a653b7e..74315f302971 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -28,6 +28,8 @@
 #include <linux/export.h>
 #include <linux/stacktrace.h>
 #include <linux/kallsyms.h>
+#include <linux/sched/debug.h>
+
 #include <asm/arcregs.h>
 #include <asm/unwind.h>
 #include <asm/switch_to.h>
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 0c48907f56a9..f9caf79186d4 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -14,6 +14,7 @@
 #include <linux/proc_fs.h>
 #include <linux/file.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/debug.h>
 
 #include <asm/arcregs.h>
 #include <asm/irqflags.h>
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 91d2d5b01414..03d46395d1ff 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -12,6 +12,7 @@
 
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 92b72375c4c7..3a2fa203637a 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -1,5 +1,6 @@
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 
 #include <asm/stacktrace.h>
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index dc5f1a22b3c9..a9dad001b97d 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -25,6 +25,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/irq.h>
 
 #include <linux/atomic.h>
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index d7fe2de9cc9e..2c96190e018b 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -14,6 +14,7 @@
 #include <linux/moduleparam.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/sched/debug.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/proc_fs.h>
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 520c7778d330..ff8b0aa2dfde 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -17,6 +17,7 @@
 #include <linux/uaccess.h>
 #include <linux/page-flags.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index a4ec240ee7ba..b6dc9d838a9a 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/stop_machine.h>
+#include <linux/sched/debug.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
 #include <asm/opcodes.h>
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index f0593c92279b..2a07aae5b8a2 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -22,6 +22,7 @@
 #include <linux/extable.h>
 #include <linux/slab.h>
 #include <linux/stop_machine.h>
+#include <linux/sched/debug.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
 #include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1ad48f93abdd..40a16cdd9873 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -24,6 +24,7 @@
 #include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 8a552a33c6ef..7597e42feeea 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -19,6 +19,7 @@
 #include <linux/export.h>
 #include <linux/ftrace.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 
 #include <asm/irq.h>
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5b8779a849a2..5a5d83791837 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -30,6 +30,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/syscalls.h>
 
 #include <asm/atomic.h>
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 30dd60ab8a65..4bf899fb451b 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -27,6 +27,7 @@
 #include <linux/uaccess.h>
 #include <linux/page-flags.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 #include <linux/preempt.h>
diff --git a/arch/avr32/kernel/nmi_debug.c b/arch/avr32/kernel/nmi_debug.c
index 3414b8566c29..25823049bb99 100644
--- a/arch/avr32/kernel/nmi_debug.c
+++ b/arch/avr32/kernel/nmi_debug.c
@@ -9,6 +9,7 @@
 #include <linux/kdebug.h>
 #include <linux/notifier.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 
 #include <asm/irq.h>
 
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 68e5b9dac059..dac022d88d9d 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/fs.h>
diff --git a/arch/blackfin/kernel/dumpstack.c b/arch/blackfin/kernel/dumpstack.c
index 95ba6d9e9a3d..3c992c1f8ef2 100644
--- a/arch/blackfin/kernel/dumpstack.c
+++ b/arch/blackfin/kernel/dumpstack.c
@@ -10,6 +10,8 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
+#include <linux/sched/debug.h>
+
 #include <asm/trace.h>
 
 /*
diff --git a/arch/blackfin/kernel/early_printk.c b/arch/blackfin/kernel/early_printk.c
index 61fbd2de993d..4b89af9243d3 100644
--- a/arch/blackfin/kernel/early_printk.c
+++ b/arch/blackfin/kernel/early_printk.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/debug.h>
 #include <linux/init.h>
 #include <linux/serial_core.h>
 #include <linux/console.h>
diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c
index 9919d29287dc..633c37083e87 100644
--- a/arch/blackfin/kernel/nmi.c
+++ b/arch/blackfin/kernel/nmi.c
@@ -17,6 +17,7 @@
 #include <linux/nmi.h>
 #include <linux/smp.h>
 #include <linux/timer.h>
+#include <linux/sched/debug.h>
 #include <asm/blackfin.h>
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 4aa5545c4fde..e95d094c20a6 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -12,6 +12,7 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/tick.h>
 #include <linux/fs.h>
 #include <linux/err.h>
diff --git a/arch/blackfin/kernel/trace.c b/arch/blackfin/kernel/trace.c
index 01e546ad2f7a..23c05b8effb3 100644
--- a/arch/blackfin/kernel/trace.c
+++ b/arch/blackfin/kernel/trace.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/oom.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
diff --git a/arch/blackfin/kernel/traps.c b/arch/blackfin/kernel/traps.c
index 32676d7721b1..a323a40a46e9 100644
--- a/arch/blackfin/kernel/traps.c
+++ b/arch/blackfin/kernel/traps.c
@@ -10,6 +10,7 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <asm/traps.h>
 #include <asm/cplb.h>
 #include <asm/blackfin.h>
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 4986b4fbcee9..13e94bf9d8ba 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -16,6 +16,7 @@
 #include <linux/seq_file.h>
 #include <linux/irq.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/syscore_ops.h>
 #include <linux/gpio.h>
 #include <asm/delay.h>
diff --git a/arch/blackfin/mm/isram-driver.c b/arch/blackfin/mm/isram-driver.c
index 7e2e674ed444..aaa1e64b753b 100644
--- a/arch/blackfin/mm/isram-driver.c
+++ b/arch/blackfin/mm/isram-driver.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 
 #include <asm/blackfin.h>
 #include <asm/dma.h>
diff --git a/arch/c6x/kernel/traps.c b/arch/c6x/kernel/traps.c
index dcc2c2f6d67c..09b8a40d5680 100644
--- a/arch/c6x/kernel/traps.c
+++ b/arch/c6x/kernel/traps.c
@@ -10,6 +10,7 @@
  */
 #include <linux/module.h>
 #include <linux/ptrace.h>
+#include <linux/sched/debug.h>
 #include <linux/kallsyms.h>
 #include <linux/bug.h>
 
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index 96e5afef6b47..068a40374200 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/fs.h>
diff --git a/arch/cris/arch-v10/kernel/traps.c b/arch/cris/arch-v10/kernel/traps.c
index 96d004fe9740..c0a501f29bd8 100644
--- a/arch/cris/arch-v10/kernel/traps.c
+++ b/arch/cris/arch-v10/kernel/traps.c
@@ -10,6 +10,8 @@
 
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
+#include <linux/sched/debug.h>
+
 #include <arch/sv_addr_ag.h>
 #include <arch/system.h>
 
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index 4d1afa9f9fd3..613c2d71bf10 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/fs.h>
diff --git a/arch/cris/arch-v32/kernel/traps.c b/arch/cris/arch-v32/kernel/traps.c
index ad6174e217c9..a34256515036 100644
--- a/arch/cris/arch-v32/kernel/traps.c
+++ b/arch/cris/arch-v32/kernel/traps.c
@@ -5,6 +5,8 @@
 #include <linux/ptrace.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
+#include <linux/sched/debug.h>
+
 #include <hwregs/supp_reg.h>
 #include <hwregs/intr_vect_defs.h>
 #include <asm/irq.h>
diff --git a/arch/cris/kernel/irq.c b/arch/cris/kernel/irq.c
index 694850e8f077..09b864f46f8a 100644
--- a/arch/cris/kernel/irq.c
+++ b/arch/cris/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/irq.h>
+#include <linux/sched/debug.h>
 
 #include <linux/kernel_stat.h>
 #include <linux/signal.h>
diff --git a/arch/cris/kernel/stacktrace.c b/arch/cris/kernel/stacktrace.c
index 99838c74456d..f1cc3aaacd8d 100644
--- a/arch/cris/kernel/stacktrace.c
+++ b/arch/cris/kernel/stacktrace.c
@@ -1,5 +1,5 @@
 #include <linux/sched.h>
-#include <linux/stacktrace.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 #include <asm/stacktrace.h>
 
diff --git a/arch/cris/kernel/traps.c b/arch/cris/kernel/traps.c
index b2a312a7afc6..a01636a12a6e 100644
--- a/arch/cris/kernel/traps.c
+++ b/arch/cris/kernel/traps.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/utsname.h>
+#include <linux/sched/debug.h>
 #ifdef CONFIG_KALLSYMS
 #include <linux/kallsyms.h>
 #endif
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index b306241c4ef2..cf4c34c09ab3 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/frv/kernel/traps.c b/arch/frv/kernel/traps.c
index 43c134d6081c..ce29991e4219 100644
--- a/arch/frv/kernel/traps.c
+++ b/arch/frv/kernel/traps.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 891974a11704..d7cabf373fe3 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -25,6 +25,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c
index 044a36125846..ee7e3ce40d78 100644
--- a/arch/h8300/kernel/traps.c
+++ b/arch/h8300/kernel/traps.c
@@ -16,6 +16,7 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index d9edfd3fc52a..3bdd9592d025 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/tick.h>
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index 4496bcf605ef..b55f13c70b34 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -20,6 +20,7 @@
 
 #include <linux/init.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/kdebug.h>
diff --git a/arch/hexagon/kernel/vm_events.c b/arch/hexagon/kernel/vm_events.c
index 741aaa917cda..04f57ef22009 100644
--- a/arch/hexagon/kernel/vm_events.c
+++ b/arch/hexagon/kernel/vm_events.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/debug.h>
 #include <asm/registers.h>
 #include <linux/irq.h>
 #include <linux/hardirq.h>
diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index 21fd50def270..de8cba121013 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/major.h>
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 5ac51069e453..f9fe3ac64242 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -73,6 +73,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/bootmem.h>
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 52deab683ba1..804b251ee5d1 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -20,6 +20,7 @@
 #include <linux/notifier.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stddef.h>
 #include <linux/thread_info.h>
 #include <linux/unistd.h>
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index 48ba46b025e1..7b1fe9462158 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/tty.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/export.h>
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index e0568bee60c0..1a227c1fdb1a 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -22,6 +22,7 @@
 
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/sched/debug.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/unistd.h>
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index c3c5fdfae920..7c05bb393597 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -14,6 +14,7 @@
 #include <linux/kallsyms.h>
 #include <linux/stddef.h>
 #include <linux/ptrace.h>
+#include <linux/sched/debug.h>
 #include <linux/mm.h>
 #include <asm/page.h>
 #include <asm/processor.h>
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index f0a8e9b332cd..b4a4675f4119 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index 558f38402737..a926d2c88898 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c
index b5cd06df71fd..9637dee90dac 100644
--- a/arch/m68k/mac/macints.c
+++ b/arch/m68k/mac/macints.c
@@ -110,6 +110,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/delay.h>
diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c
index 35062796edf2..2e611bd37515 100644
--- a/arch/metag/kernel/process.c
+++ b/arch/metag/kernel/process.c
@@ -8,6 +8,7 @@
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/unistd.h>
diff --git a/arch/metag/kernel/stacktrace.c b/arch/metag/kernel/stacktrace.c
index 5510361d5bea..4f806d66a58c 100644
--- a/arch/metag/kernel/stacktrace.c
+++ b/arch/metag/kernel/stacktrace.c
@@ -1,5 +1,6 @@
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 
 #include <asm/stacktrace.h>
diff --git a/arch/metag/kernel/traps.c b/arch/metag/kernel/traps.c
index 17b2e2e38d5a..5ce67f9124aa 100644
--- a/arch/metag/kernel/traps.c
+++ b/arch/metag/kernel/traps.c
@@ -10,6 +10,7 @@
 
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index c765b3621b9b..5055477486b6 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
+#include <linux/sched/debug.h>
 #include <linux/interrupt.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c
index 42dd12a62ff5..e6f338d0496b 100644
--- a/arch/microblaze/kernel/exceptions.c
+++ b/arch/microblaze/kernel/exceptions.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kallsyms.h>
 
 #include <asm/exceptions.h>
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index b2dd37196b3b..8c5fdb2e2850 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -11,6 +11,7 @@
 #include <linux/cpu.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
 #include <linux/bitops.h>
diff --git a/arch/microblaze/kernel/traps.c b/arch/microblaze/kernel/traps.c
index cb619533a192..45bbba9d919f 100644
--- a/arch/microblaze/kernel/traps.c
+++ b/arch/microblaze/kernel/traps.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/kallsyms.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/debug_locks.h>
 
 #include <asm/exceptions.h>
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 803e255b6fc3..97574cdb532d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -11,6 +11,7 @@
  */
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/tick.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/mips/kernel/stacktrace.c b/arch/mips/kernel/stacktrace.c
index 506021f62549..986f910961d9 100644
--- a/arch/mips/kernel/stacktrace.c
+++ b/arch/mips/kernel/stacktrace.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2006 Atsushi Nemoto <anemo@mba.ocn.ne.jp>
  */
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 #include <linux/export.h>
 #include <asm/stacktrace.h>
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 49c6df20672a..1a9366a157cb 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -24,6 +24,7 @@
 #include <linux/extable.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/kallsyms.h>
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 9960a8302eac..1f2a5bc4779e 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/seq_file.h>
 
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index f8919b6a24c8..d12879eb2b1f 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/signal.h>	/* for SIGBUS */
 #include <linux/sched.h>	/* schow_regs(), force_sig() */
+#include <linux/sched/debug.h>
 
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index ba8f46d80ab8..57d8c7486fe6 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip32/ip32-irq.c b/arch/mips/sgi-ip32/ip32-irq.c
index 838d8589a1c0..a6a0ff7f5aed 100644
--- a/arch/mips/sgi-ip32/ip32-irq.c
+++ b/arch/mips/sgi-ip32/ip32-irq.c
@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/random.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index e5def2217f72..a1e2f8301d94 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c
index a7a987c7954f..800fd0801969 100644
--- a/arch/mn10300/kernel/traps.c
+++ b/arch/mn10300/kernel/traps.c
@@ -10,6 +10,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 2f8c74f93e70..3ad87a6b119b 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -14,6 +14,7 @@
 
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/tick.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c
index 72ed30a93c85..8184e7d6b385 100644
--- a/arch/nios2/kernel/traps.c
+++ b/arch/nios2/kernel/traps.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/export.h>
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index e7a14e1e0d6b..b804dd06ea1c 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -13,6 +13,7 @@
 
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 6e9d1cb519f2..899339dac938 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -22,6 +22,7 @@
 
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mm.h>
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 7e81ad258bca..2354ab88d948 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -22,6 +22,7 @@
 
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/extable.h>
 #include <linux/kmod.h>
diff --git a/arch/parisc/kernel/pa7300lc.c b/arch/parisc/kernel/pa7300lc.c
index 8a89780223aa..9b245fc67560 100644
--- a/arch/parisc/kernel/pa7300lc.c
+++ b/arch/parisc/kernel/pa7300lc.c
@@ -5,6 +5,7 @@
  *   Copyright (C) 2000 Philipp Rumpf */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
 #include <asm/io.h>
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index ea6603ee8d24..8c283caf2b4d 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -43,6 +43,7 @@
 #include <linux/personality.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index e58925ac64d1..9e03296641d7 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 378df9207406..991654c88eec 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index a08ab481e556..e36f7b75ab07 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/signal.h>
 #include <linux/ratelimit.h>
 #include <linux/uaccess.h>
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 1a0b4f63f0e9..c3cac4ddfe9c 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -13,6 +13,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/interrupt.h>
 #include <linux/extable.h>
 #include <linux/uaccess.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4379a079b3c2..76f58b87dcb2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -16,6 +16,7 @@
 
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 4f24606afc3f..66711958493c 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -12,6 +12,7 @@
 
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index e6cc56b61d01..ff365f9de27a 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -17,6 +17,7 @@
 
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 55d4fe174fd9..72c584d62f59 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <asm/processor.h>
 #include <asm/debug.h>
 #include <asm/dis.h>
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 54281660582c..ed99ff911b67 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -11,6 +11,7 @@
 #include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/elfcore.h>
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 0085b2d8ed7d..e66687dc6144 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 #include <linux/kallsyms.h>
 #include <linux/export.h>
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 283ad7840335..f787b9d8f54c 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -17,6 +17,7 @@
 #include <linux/extable.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index bb5560eb2435..5845d3028ffc 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -12,6 +12,7 @@
 #include <linux/perf_event.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index fa624f30f783..8a54d320fb41 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -25,6 +25,7 @@
 
 #include <linux/extable.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 
 #include <asm/cacheflush.h>
 #include <asm/irq.h>
diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c
index 8dfe645bcc4b..d00cab2f50f9 100644
--- a/arch/sh/kernel/dumpstack.c
+++ b/arch/sh/kernel/dumpstack.c
@@ -11,6 +11,7 @@
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
 #include <linux/debug_locks.h>
+#include <linux/sched/debug.h>
 #include <linux/kdebug.h>
 #include <linux/export.h>
 #include <linux/uaccess.h>
diff --git a/arch/sh/kernel/nmi_debug.c b/arch/sh/kernel/nmi_debug.c
index ff0abbd1e652..730d928f0d12 100644
--- a/arch/sh/kernel/nmi_debug.c
+++ b/arch/sh/kernel/nmi_debug.c
@@ -9,6 +9,7 @@
 #include <linux/kdebug.h>
 #include <linux/notifier.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/hardirq.h>
 
 enum nmi_action {
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 51741850a715..5098274e0f23 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -15,6 +15,7 @@
  */
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/elfcore.h>
 #include <linux/kallsyms.h>
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index e0b271bffd6a..ced21a417d9d 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/sched/debug.h>
 #include <asm/syscalls.h>
 #include <linux/uaccess.h>
 #include <asm/pgtable.h>
diff --git a/arch/sh/kernel/stacktrace.c b/arch/sh/kernel/stacktrace.c
index bf989e063a0c..7a73d2763e1b 100644
--- a/arch/sh/kernel/stacktrace.c
+++ b/arch/sh/kernel/stacktrace.c
@@ -10,6 +10,7 @@
  * for more details.
  */
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 #include <linux/thread_info.h>
 #include <linux/module.h>
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index 3036dee854d1..bc5c9f347b9e 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -4,6 +4,7 @@
 #include <linux/kdebug.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 #include <linux/kernel.h>
diff --git a/arch/sh/kernel/traps_64.c b/arch/sh/kernel/traps_64.c
index 00835edb6e20..014fb08cf133 100644
--- a/arch/sh/kernel/traps_64.c
+++ b/arch/sh/kernel/traps_64.c
@@ -10,6 +10,7 @@
  * for more details.
  */
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 48ffc3e7d1dd..237a471c8ed5 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d249ca10b203..98f6ff6eaa55 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
diff --git a/arch/sparc/kernel/stacktrace.c b/arch/sparc/kernel/stacktrace.c
index e78386a0029f..be4c14cccc05 100644
--- a/arch/sparc/kernel/stacktrace.c
+++ b/arch/sparc/kernel/stacktrace.c
@@ -1,4 +1,5 @@
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 #include <linux/thread_info.h>
 #include <linux/ftrace.h>
diff --git a/arch/sparc/kernel/sun4m_irq.c b/arch/sparc/kernel/sun4m_irq.c
index da737c712fa8..aa84da0b2d30 100644
--- a/arch/sparc/kernel/sun4m_irq.c
+++ b/arch/sparc/kernel/sun4m_irq.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/sched/debug.h>
 
 #include <asm/timer.h>
 #include <asm/traps.h>
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index ff3573059936..7aecb239626d 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/debug.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c521ee277083..ef4520efc813 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/debug.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/mm.h>
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index ecddac5a4c96..26740a2f285d 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/sched.h>  /* for jiffies */
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/smp.h>
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index e022d7b00390..4ff4c35f76b2 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -10,6 +10,7 @@
 
 #include <linux/extable.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/linkage.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 643c149a3151..b84c4dd14954 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -10,6 +10,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/ptrace.h>
 #include <linux/mman.h>
 #include <linux/signal.h>
diff --git a/arch/tile/include/asm/stack.h b/arch/tile/include/asm/stack.h
index c3cb42615a9f..3573325e340b 100644
--- a/arch/tile/include/asm/stack.h
+++ b/arch/tile/include/asm/stack.h
@@ -17,6 +17,8 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
+
 #include <asm/backtrace.h>
 #include <asm/page.h>
 #include <hv/hypervisor.h>
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index c84c54a1ac55..557b4c8435d0 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/preempt.h>
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 87299a6cfec8..8cc92ae6eb27 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index 22bbbd3ff4a3..a1c0787fe9d8 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 39f427bb0de2..54804866f238 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index f229e979584e..142acae78316 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -17,6 +17,7 @@
 #include <linux/smp.h>
 #include <linux/ptrace.h>
 #include <linux/slab.h>
+#include <linux/sched/debug.h>
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
 #include <linux/mman.h>
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 709f8e9ba3e9..005c91c2adca 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -16,6 +16,7 @@
 
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 8a4c72af3bc0..af326fb6510d 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/notifier.h>
 #include <linux/reboot.h>
+#include <linux/sched/debug.h>
 #include <linux/proc_fs.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 078630d6448c..c6c45ea4021f 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -17,6 +17,7 @@
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/seq_file.h>
 #include <linux/tick.h>
 #include <linux/threads.h>
diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c
index aa1b56f5ac68..34ae555c3e70 100644
--- a/arch/um/kernel/sysrq.c
+++ b/arch/um/kernel/sysrq.c
@@ -11,6 +11,8 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
+
 #include <asm/sysrq.h>
 #include <asm/stacktrace.h>
 #include <os.h>
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 9711ae4aaa6a..59158871b9fc 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -8,6 +8,7 @@
 #include <linux/hardirq.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/sched/debug.h>
 #include <asm/current.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index d7c6b676b3a5..c1a0eec88f1f 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -13,6 +13,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/unicore32/kernel/stacktrace.c b/arch/unicore32/kernel/stacktrace.c
index b34030bdabe3..9976e767d51c 100644
--- a/arch/unicore32/kernel/stacktrace.c
+++ b/arch/unicore32/kernel/stacktrace.c
@@ -11,6 +11,7 @@
  */
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 
 #include <asm/stacktrace.h>
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index 7f5e06f9a202..506e1a2127c6 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/signal.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/spinlock.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
index 24e836023e6c..3a7f6faa8794 100644
--- a/arch/unicore32/mm/alignment.c
+++ b/arch/unicore32/mm/alignment.c
@@ -15,6 +15,7 @@
  */
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/sched/debug.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/init.h>
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 82dfe32faaf4..df083efe6ee0 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
index b2f7207ba86c..f9c324e08d85 100644
--- a/arch/x86/kernel/doublefault.c
+++ b/arch/x86/kernel/doublefault.c
@@ -1,5 +1,6 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/init_task.h>
 #include <linux/fs.h>
 
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 0cfd01d2754c..7b9e7e68f316 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -10,6 +10,7 @@
 #include <linux/kdebug.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
+#include <linux/sched/debug.h>
 #include <linux/ftrace.h>
 #include <linux/kexec.h>
 #include <linux/bug.h>
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index bb3b5b9a6899..b0b3a3df7c20 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -2,6 +2,7 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
  */
+#include <linux/sched/debug.h>
 #include <linux/kallsyms.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index fac189efcc34..a8b117e93b46 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -2,6 +2,7 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
  */
+#include <linux/sched/debug.h>
 #include <linux/kallsyms.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 520b8dfe1640..6384eb754a58 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -45,6 +45,7 @@
 #include <linux/slab.h>
 #include <linux/hardirq.h>
 #include <linux/preempt.h>
+#include <linux/sched/debug.h>
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index d17b1a940add..f088ea4c66e7 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -13,6 +13,7 @@
 #include <linux/spinlock.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
+#include <linux/sched/debug.h>
 #include <linux/nmi.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6395e0cd7dd6..505be5589e52 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/idle.h>
+#include <linux/sched/debug.h>
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/pm.h>
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 0653788026e2..330cae0025d0 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2006-2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
 #include <linux/export.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 61a7e9ea9aa1..35ea061010a1 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,5 +1,7 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
+#include <linux/sched/debug.h>
+
 #include <asm/traps.h>
 #include <asm/kdebug.h>
 
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 9743d0ccfec6..c34bd8233f7c 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -27,6 +27,7 @@
 #include <linux/moduleparam.h>
 #include <linux/nmi.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/clocksource.h>
 
diff --git a/arch/x86/um/sysrq_32.c b/arch/x86/um/sysrq_32.c
index 16ee0e450e3e..f2383484840d 100644
--- a/arch/x86/um/sysrq_32.c
+++ b/arch/x86/um/sysrq_32.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kallsyms.h>
 #include <asm/ptrace.h>
 #include <asm/sysrq.h>
diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c
index 38b4e4abd0f8..903ad91b624f 100644
--- a/arch/x86/um/sysrq_64.c
+++ b/arch/x86/um/sysrq_64.c
@@ -7,6 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/utsname.h>
 #include <asm/current.h>
 #include <asm/ptrace.h>
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 826d25104846..afaa3588d869 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -17,6 +17,7 @@
 
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 84abd66e680d..d8bb2e62393e 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -25,6 +25,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/stringify.h>
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 249e0304597f..9faee1c893e5 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -27,6 +27,7 @@
 #include <linux/pm_wakeirq.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/async.h>
 #include <linux/suspend.h>
 #include <trace/events/power.h>
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 65db0aeb3d80..e5f0c7d0fe8d 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -16,6 +16,8 @@
 
 #include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/debug.h>
 #include <linux/interrupt.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index 9229de43e19d..4f6b1b10b537 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -32,6 +32,7 @@
 #include <linux/atomic.h>
 #include <linux/tty.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 6b3a2c00974d..c5f0fc906136 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -27,6 +27,8 @@
 #include <linux/consolemap.h>
 #include <linux/module.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/debug.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/mm.h>
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4c5fa704e38c..5914fed3712d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -88,6 +88,7 @@
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/debug.h>
 #include <linux/flex_array.h>
 #include <linux/posix-timers.h>
 #ifdef CONFIG_HARDWALL
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
new file mode 100644
index 000000000000..55bc0cd35fd5
--- /dev/null
+++ b/include/linux/sched/debug.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_DEBUG_H
+#define _LINUX_SCHED_DEBUG_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_DEBUG_H */
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 9b976a42376d..6ad4a9fcbd6f 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -13,6 +13,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/kdb.h>
 #include <linux/nmi.h>
 #include "kdb_private.h"
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index bf48a492b4be..c8146d53ca67 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -20,6 +20,7 @@
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/stat.h>
+#include <linux/sched/debug.h>
 #include <linux/sysrq.h>
 #include <linux/smp.h>
 #include <linux/utsname.h>
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 129247e56902..f0f8e2a8496f 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -17,6 +17,7 @@
 #include <linux/sysctl.h>
 #include <linux/utsname.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 
 #include <trace/events/sched.h>
 
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index b5c30d9f46c5..545839b838d6 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -55,6 +55,7 @@
 #include <linux/latencytop.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/list.h>
 #include <linux/stacktrace.h>
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 82ff5726bc1b..198527a62149 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -22,6 +22,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/debug.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 62b6cee8ea7f..97ee9df32e0f 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -18,6 +18,7 @@
  */
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/debug.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 1c8c8707853a..6edc32ecd9c5 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -16,6 +16,7 @@
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/debug.h>
 #include <linux/timer.h>
 
 #include "rtmutex_common.h"
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 91e7bc8e9d5a..7bc24d477805 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -7,6 +7,7 @@
  */
 #include <linux/rwsem.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/export.h>
 
 enum rwsem_waiter_type {
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 9bd6e768164e..34e727f18e49 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -15,6 +15,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/debug.h>
 #include <linux/osq_lock.h>
 
 #include "rwsem.h"
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 45ba475d4be3..90a74ccd85a4 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/export.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 9512e37637dc..561acdd39960 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -29,6 +29,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/semaphore.h>
 #include <linux/spinlock.h>
 #include <linux/ftrace.h>
diff --git a/kernel/panic.c b/kernel/panic.c
index 3ec16e603e88..a58932b41700 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -9,6 +9,7 @@
  * to indicate a major problem.
  */
 #include <linux/debug_locks.h>
+#include <linux/sched/debug.h>
 #include <linux/interrupt.h>
 #include <linux/kmsg_dump.h>
 #include <linux/kallsyms.h>
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 2fba066e125f..85e2915d8961 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -12,6 +12,7 @@
 #include <linux/oom.h>
 #include <linux/suspend.h>
 #include <linux/module.h>
+#include <linux/sched/debug.h>
 #include <linux/syscalls.h>
 #include <linux/freezer.h>
 #include <linux/delay.h>
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 47050eedc206..3caaaa04b92e 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -46,6 +46,7 @@
 #include <linux/ctype.h>
 #include <linux/uio.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/debug.h>
 
 #include <linux/uaccess.h>
 #include <asm/sections.h>
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e456327a63d6..50fee7689e71 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -35,6 +35,7 @@
 #include <linux/rcupdate_wait.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/nmi.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 9dabb04003be..0a62a8f1caac 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -27,6 +27,7 @@
 #include <linux/delay.h>
 #include <linux/gfp.h>
 #include <linux/oom.h>
+#include <linux/sched/debug.h>
 #include <linux/smpboot.h>
 #include <uapi/linux/sched/types.h>
 #include "../time/tick-internal.h"
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index da128deb10ec..55c8530316c7 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -37,6 +37,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/percpu.h>
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index b294a8ee2842..53f9558fa925 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/completion.h>
 
 /**
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5979f47c422c..e1e819f731b2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -11,6 +11,7 @@
 #include <linux/sched/cpufreq.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/nohz.h>
+#include <linux/sched/debug.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
 #include <linux/kernel_stat.h>
@@ -1830,7 +1831,6 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
 extern void
 print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
-
 #ifdef CONFIG_NUMA_BALANCING
 extern void
 show_numa_stats(struct task_struct *p, struct seq_file *m);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 1fedfcf6fc9b..4d2ea6f25568 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/mm.h>
 #include <linux/wait.h>
 #include <linux/hash.h>
diff --git a/kernel/signal.c b/kernel/signal.c
index 762fcf64f0c3..15092fd8c7b1 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/sched/user.h>
+#include <linux/sched/debug.h>
 #include <linux/fs.h>
 #include <linux/tty.h>
 #include <linux/binfmts.h>
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 04939053c823..ce3a31e8eb36 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -20,6 +20,7 @@
 #include <linux/timerqueue.h>
 #include <linux/rtc.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
 #include <linux/alarmtimer.h>
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index aed2207f5b2d..ec08f527d7ee 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -48,6 +48,7 @@
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
 #include <linux/sched/nohz.h>
+#include <linux/sched/debug.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index d7999cb06229..1dc0256bfb6e 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -41,6 +41,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/nohz.h>
+#include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 52718f4512e9..03e0b69bb5bf 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -23,6 +23,7 @@
 #include <linux/tick.h>
 #include <linux/workqueue.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/debug.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index b5de262a9eb9..54a427d1f344 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -13,6 +13,8 @@
 
 #include <linux/nmi.h>
 #include <linux/module.h>
+#include <linux/sched/debug.h>
+
 #include <asm/irq_regs.h>
 #include <linux/perf_event.h>
 
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index c30d07e99dba..625375e7f11f 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/smp.h>
 #include <linux/atomic.h>
 
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 5f7999eacad5..4e8a30d1c22f 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -17,6 +17,7 @@
 #include <linux/kprobes.h>
 #include <linux/nmi.h>
 #include <linux/cpu.h>
+#include <linux/sched/debug.h>
 
 #ifdef arch_trigger_cpumask_backtrace
 /* For reliability, we're prepared to waste bits here. */
-- 
GitLab


From ef8bd77f332bb0a4e467d7171bbfc6c57aa08a88 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:36 +0100
Subject: [PATCH 502/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/hotplug.h>

We are going to split <linux/sched/hotplug.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/hotplug.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/kernel/smp.c                        | 1 +
 arch/arm64/include/asm/mmu_context.h         | 1 +
 arch/arm64/kernel/smp.c                      | 1 +
 arch/ia64/kernel/process.c                   | 1 +
 arch/metag/kernel/smp.c                      | 1 +
 arch/mips/cavium-octeon/smp.c                | 1 +
 arch/mips/kernel/smp-bmips.c                 | 1 +
 arch/mips/kernel/smp-cps.c                   | 1 +
 arch/mips/loongson64/loongson-3/smp.c        | 1 +
 arch/powerpc/platforms/85xx/smp.c            | 1 +
 arch/powerpc/platforms/powermac/smp.c        | 1 +
 arch/powerpc/platforms/powernv/smp.c         | 1 +
 arch/powerpc/platforms/pseries/hotplug-cpu.c | 1 +
 arch/s390/kernel/smp.c                       | 1 +
 arch/sh/kernel/smp.c                         | 1 +
 arch/sparc/kernel/smp_64.c                   | 1 +
 arch/x86/kernel/smpboot.c                    | 1 +
 arch/xtensa/kernel/smp.c                     | 1 +
 include/linux/sched/hotplug.h                | 6 ++++++
 kernel/cpu.c                                 | 1 +
 kernel/sched/core.c                          | 1 +
 kernel/sched/sched.h                         | 4 +++-
 22 files changed, 29 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/hotplug.h

diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5a07c5a4b894..2083a5370308 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
 #include <linux/profile.h>
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 1ef40d82cfd3..3c9f7d18a7e6 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -25,6 +25,7 @@
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 827d52d78b67..f66e58523b96 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
 #include <linux/profile.h>
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 804b251ee5d1..2204ae450d65 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -21,6 +21,7 @@
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/hotplug.h>
 #include <linux/stddef.h>
 #include <linux/thread_info.h>
 #include <linux/unistd.h>
diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index c622293254e4..198eda75846b 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
 #include <linux/profile.h>
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 4355a4cf4d74..4b94b7fbafa3 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/init.h>
 #include <linux/export.h>
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 16e37a28f876..3daa2cae50b0 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -10,6 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index a2544c2394e4..1d3188c23bb8 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/irqchip/mips-gic.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/types.h>
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index cfcf240cedbe..66ede5b11355 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/smp.h>
 #include <linux/cpufreq.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index a83a6d26090d..078097a0b09d 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -12,6 +12,7 @@
 
 #include <linux/stddef.h>
 #include <linux/kernel.h>
+#include <linux/sched/hotplug.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index c9eb7d6540ea..746ca7321b03 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -23,6 +23,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index e39e6c428af1..8b67e1eefb5c 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index a1b63e00b2f7..7bc0e91f8715 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -24,6 +24,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/sched.h>	/* for idle_task_exit */
+#include <linux/sched/hotplug.h>
 #include <linux/cpu.h>
 #include <linux/of.h>
 #include <linux/slab.h>
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index d0a74d7ce433..b5766e03cdcb 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -31,6 +31,7 @@
 #include <linux/irqflags.h>
 #include <linux/cpu.h>
 #include <linux/slab.h>
+#include <linux/sched/hotplug.h>
 #include <linux/crash_dump.h>
 #include <linux/memblock.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index edc4769b047e..4abf119c129c 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -21,6 +21,7 @@
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/atomic.h>
 #include <linux/clockchips.h>
 #include <asm/processor.h>
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 8e3e13924594..15052d364e04 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -6,6 +6,7 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/hotplug.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/threads.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fe7a66e6b5a0..f3eb266d75ff 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -46,6 +46,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/topology.h>
+#include <linux/sched/hotplug.h>
 #include <linux/percpu.h>
 #include <linux/bootmem.h>
 #include <linux/err.h>
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index fcea72019df7..f2b3e1725349 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/sched/hotplug.h>
 #include <linux/reboot.h>
 #include <linux/seq_file.h>
 #include <linux/smp.h>
diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
new file mode 100644
index 000000000000..34670ed24894
--- /dev/null
+++ b/include/linux/sched/hotplug.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_HOTPLUG_H
+#define _LINUX_SCHED_HOTPLUG_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_HOTPLUG_H */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0aae3183b029..78c206579d01 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/notifier.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/hotplug.h>
 #include <linux/unistd.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 11a0684a29a7..956383844116 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9,6 +9,7 @@
 #include <linux/sched/clock.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/hotplug.h>
 #include <linux/cpuset.h>
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e1e819f731b2..0974eb2ef50d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3,6 +3,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/wake_q.h>
 #include <linux/sched/signal.h>
@@ -12,8 +13,9 @@
 #include <linux/sched/stat.h>
 #include <linux/sched/nohz.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/hotplug.h>
+
 #include <linux/u64_stats_sync.h>
-#include <linux/sched/deadline.h>
 #include <linux/kernel_stat.h>
 #include <linux/binfmts.h>
 #include <linux/mutex.h>
-- 
GitLab


From 299300258d1bc4e997b7db340a2e06636757fe2e Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:36 +0100
Subject: [PATCH 503/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/task.h>

We are going to split <linux/sched/task.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/task.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/kernel/process.c              | 1 +
 arch/arc/kernel/process.c                | 2 ++
 arch/arm/kernel/process.c                | 1 +
 arch/arm/mm/init.c                       | 1 +
 arch/arm64/kernel/process.c              | 1 +
 arch/avr32/kernel/process.c              | 1 +
 arch/blackfin/kernel/process.c           | 1 +
 arch/blackfin/kernel/trace.c             | 1 +
 arch/c6x/kernel/process.c                | 1 +
 arch/cris/arch-v10/kernel/process.c      | 1 +
 arch/cris/arch-v32/kernel/process.c      | 1 +
 arch/cris/kernel/process.c               | 1 +
 arch/frv/kernel/process.c                | 1 +
 arch/frv/mm/mmu-context.c                | 1 +
 arch/h8300/kernel/process.c              | 1 +
 arch/hexagon/kernel/process.c            | 1 +
 arch/ia64/kernel/mca.c                   | 1 +
 arch/ia64/kernel/perfmon.c               | 1 +
 arch/ia64/kernel/process.c               | 1 +
 arch/ia64/kernel/ptrace.c                | 1 +
 arch/m32r/kernel/process.c               | 1 +
 arch/m32r/kernel/smpboot.c               | 1 +
 arch/m68k/kernel/process.c               | 1 +
 arch/metag/kernel/process.c              | 1 +
 arch/metag/kernel/traps.c                | 1 +
 arch/microblaze/kernel/process.c         | 1 +
 arch/mips/kernel/mips-mt-fpaff.c         | 1 +
 arch/mips/kernel/process.c               | 1 +
 arch/mn10300/kernel/process.c            | 1 +
 arch/mn10300/kernel/smp.c                | 1 +
 arch/nios2/kernel/process.c              | 1 +
 arch/openrisc/kernel/process.c           | 1 +
 arch/parisc/kernel/process.c             | 1 +
 arch/powerpc/kernel/process.c            | 1 +
 arch/s390/kernel/process.c               | 1 +
 arch/s390/kernel/setup.c                 | 1 +
 arch/score/kernel/process.c              | 1 +
 arch/sh/kernel/cpu/fpu.c                 | 1 +
 arch/sh/kernel/process_32.c              | 1 +
 arch/sh/kernel/process_64.c              | 1 +
 arch/sh/mm/asids-debugfs.c               | 1 +
 arch/sparc/kernel/process_32.c           | 1 +
 arch/sparc/kernel/process_64.c           | 1 +
 arch/tile/kernel/process.c               | 1 +
 arch/tile/kernel/smpboot.c               | 1 +
 arch/tile/kernel/unaligned.c             | 1 +
 arch/tile/mm/fault.c                     | 2 ++
 arch/um/kernel/exec.c                    | 1 +
 arch/um/kernel/process.c                 | 1 +
 arch/um/kernel/reboot.c                  | 1 +
 arch/unicore32/kernel/process.c          | 1 +
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 1 +
 arch/x86/kernel/fpu/init.c               | 1 +
 arch/x86/kernel/process.c                | 1 +
 arch/x86/kernel/process_32.c             | 1 +
 arch/x86/kernel/process_64.c             | 1 +
 arch/x86/kernel/unwind_frame.c           | 1 +
 arch/xtensa/kernel/process.c             | 1 +
 drivers/misc/kgdbts.c                    | 2 ++
 drivers/tty/sysrq.c                      | 2 +-
 drivers/tty/tty_io.c                     | 1 +
 fs/exec.c                                | 1 +
 fs/fcntl.c                               | 1 +
 fs/fs_struct.c                           | 1 +
 fs/proc/array.c                          | 1 +
 fs/proc/kcore.c                          | 1 +
 include/linux/sched/task.h               | 6 ++++++
 init/main.c                              | 1 +
 kernel/cgroup/cgroup.c                   | 1 +
 kernel/cpu.c                             | 1 +
 kernel/exit.c                            | 1 +
 kernel/fork.c                            | 1 +
 kernel/kmod.c                            | 1 +
 kernel/kthread.c                         | 1 +
 kernel/locking/lockdep.c                 | 1 +
 kernel/pid.c                             | 1 +
 kernel/pid_namespace.c                   | 1 +
 kernel/power/process.c                   | 1 +
 kernel/ptrace.c                          | 1 +
 kernel/sched/sched.h                     | 1 +
 kernel/signal.c                          | 1 +
 kernel/smpboot.c                         | 1 +
 kernel/sys.c                             | 1 +
 kernel/trace/ftrace.c                    | 1 +
 kernel/tracepoint.c                      | 1 +
 lib/dma-debug.c                          | 1 +
 mm/kmemleak.c                            | 1 +
 mm/memory-failure.c                      | 1 +
 mm/memory.c                              | 1 +
 mm/oom_kill.c                            | 1 +
 mm/rmap.c                                | 1 +
 mm/swapfile.c                            | 1 +
 mm/usercopy.c                            | 2 ++
 security/keys/keyctl.c                   | 1 +
 security/selinux/hooks.c                 | 1 +
 95 files changed, 104 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/task.h

diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 88f7a974d311..713b4fac998e 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index a41a79a4f4fe..d618d26721ab 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -11,6 +11,8 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
+
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/unistd.h>
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 03d46395d1ff..d4c7c9a1afa9 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 2a9040dcf47e..1d8558ff9827 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -14,6 +14,7 @@
 #include <linux/bootmem.h>
 #include <linux/mman.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/export.h>
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 40a16cdd9873..f9b8e74ff8f2 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -25,6 +25,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index dac022d88d9d..75b944a5107c 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -7,6 +7,7 @@
  */
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/fs.h>
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index e95d094c20a6..1a1f444004b1 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/tick.h>
 #include <linux/fs.h>
 #include <linux/err.h>
diff --git a/arch/blackfin/kernel/trace.c b/arch/blackfin/kernel/trace.c
index 23c05b8effb3..151f22196ab6 100644
--- a/arch/blackfin/kernel/trace.c
+++ b/arch/blackfin/kernel/trace.c
@@ -13,6 +13,7 @@
 #include <linux/oom.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c
index 0ee7686a78f3..6b61779d426a 100644
--- a/arch/c6x/kernel/process.c
+++ b/arch/c6x/kernel/process.c
@@ -17,6 +17,7 @@
 #include <linux/mqueue.h>
 #include <linux/syscalls.h>
 #include <linux/reboot.h>
+#include <linux/sched/task.h>
 
 #include <asm/syscalls.h>
 
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index 068a40374200..808c2186b704 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/fs.h>
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index 613c2d71bf10..c852df262948 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -10,6 +10,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/fs.h>
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index 50a7dd451456..0bbd3a0c3d70 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -20,6 +20,7 @@
 #include <linux/spinlock.h>
 #include <linux/init_task.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/user.h>
 #include <linux/elfcore.h>
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index cf4c34c09ab3..c96dbd4b8626 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/frv/mm/mmu-context.c b/arch/frv/mm/mmu-context.c
index 4031289bf2ec..16946a58f64d 100644
--- a/arch/frv/mm/mmu-context.c
+++ b/arch/frv/mm/mmu-context.c
@@ -11,6 +11,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/mm.h>
 #include <asm/tlbflush.h>
 
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index d7cabf373fe3..54e4d6f01865 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index 3bdd9592d025..a2a822a875b6 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -20,6 +20,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/tick.h>
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index f9fe3ac64242..79c7c46d7dc1 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -74,6 +74,7 @@
 #include <linux/init.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/bootmem.h>
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 677a86826771..7e943d3c05ed 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 2204ae450d65..054facf22156 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task.h>
 #include <linux/stddef.h>
 #include <linux/thread_info.h>
 #include <linux/unistd.h>
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 0b1153e610ea..04fe1436e1cc 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -11,6 +11,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index 1a227c1fdb1a..2a450382934c 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -23,6 +23,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/unistd.h>
diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c
index f98d2f6519d6..a7d04684d2c7 100644
--- a/arch/m32r/kernel/smpboot.c
+++ b/arch/m32r/kernel/smpboot.c
@@ -45,6 +45,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/err.h>
 #include <linux/irq.h>
 #include <linux/bootmem.h>
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index b4a4675f4119..5d335d178706 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c
index 2e611bd37515..801e6f927e62 100644
--- a/arch/metag/kernel/process.c
+++ b/arch/metag/kernel/process.c
@@ -9,6 +9,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/unistd.h>
diff --git a/arch/metag/kernel/traps.c b/arch/metag/kernel/traps.c
index 5ce67f9124aa..23c5ac33a93f 100644
--- a/arch/metag/kernel/traps.c
+++ b/arch/metag/kernel/traps.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 8c5fdb2e2850..a642fe5ac5ff 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -12,6 +12,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
 #include <linux/bitops.h>
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index ffc6bd3464d9..8cab633e0e5a 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/cred.h>
 #include <linux/security.h>
 #include <linux/types.h>
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 97574cdb532d..8bfb833b3158 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/tick.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index a1e2f8301d94..8ca7a9de09a5 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index e65b5cc2fa67..d924f7a79708 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 3ad87a6b119b..5ee1ddf6a924 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/tick.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 899339dac938..0c5ad3bde0f5 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -23,6 +23,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mm.h>
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 8c283caf2b4d..e5f97239cc5e 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -44,6 +44,7 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 76f58b87dcb2..b99b12656f6f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index ed99ff911b67..250c41f05721 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -12,6 +12,7 @@
 #include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/elfcore.h>
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index e4d811f17971..3de07004c02e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
 #include <linux/mm.h>
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index aae9480706c2..32924159d8c9 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -28,6 +28,7 @@
 #include <linux/elfcore.h>
 #include <linux/pm.h>
 #include <linux/rcupdate.h>
+#include <linux/sched/task.h>
 
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c
index 37e35330aae6..b76370a47bf9 100644
--- a/arch/sh/kernel/cpu/fpu.c
+++ b/arch/sh/kernel/cpu/fpu.c
@@ -1,4 +1,5 @@
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <asm/processor.h>
 #include <asm/fpu.h>
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 5098274e0f23..493c3eb86aa5 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/elfcore.h>
 #include <linux/kallsyms.h>
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index ced21a417d9d..056607185158 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <asm/syscalls.h>
 #include <linux/uaccess.h>
 #include <asm/pgtable.h>
diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c
index 110bd35165bf..e5539e0f8e3b 100644
--- a/arch/sh/mm/asids-debugfs.c
+++ b/arch/sh/mm/asids-debugfs.c
@@ -21,6 +21,7 @@
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 237a471c8ed5..ed87c45a785b 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 98f6ff6eaa55..4c82a73af893 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -15,6 +15,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 557b4c8435d0..dbb4fa76d1dd 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -14,6 +14,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/preempt.h>
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index 53ce940a5016..f3fdd0c39b12 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/kernel_stat.h>
 #include <linux/bootmem.h>
 #include <linux/notifier.h>
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index 142acae78316..8149c38f67b6 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -18,6 +18,7 @@
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
 #include <linux/mman.h>
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 005c91c2adca..f58fa06a2214 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -17,6 +17,8 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 770ec07b6a6a..2df4e5d11939 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -8,6 +8,7 @@
 #include <linux/fs.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <asm/current.h>
 #include <asm/processor.h>
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index c6c45ea4021f..e76dc7c11251 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/seq_file.h>
 #include <linux/tick.h>
 #include <linux/threads.h>
diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c
index 79218106a033..0bc921cee0b1 100644
--- a/arch/um/kernel/reboot.c
+++ b/arch/um/kernel/reboot.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/oom.h>
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index c1a0eec88f1f..d58f1600b477 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index d48af18e7baf..0bbe0f3a039f 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -26,6 +26,7 @@
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/task_work.h>
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 19bdd1bf8160..c2f8dde3255c 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -7,6 +7,7 @@
 #include <asm/cmdline.h>
 
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/init.h>
 
 /*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 505be5589e52..441f00e7be8f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -9,6 +9,7 @@
 #include <linux/sched.h>
 #include <linux/sched/idle.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/pm.h>
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a0ac3e81518a..d79ffa47aab8 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -12,6 +12,7 @@
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a61e141b6891..124f5652ae3c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 23d15565d02a..7c0abdc9a732 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -1,4 +1,5 @@
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <asm/ptrace.h>
 #include <asm/bitops.h>
 #include <asm/stacktrace.h>
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index afaa3588d869..af33f9d4c624 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index 99635dd9dbac..fc7efedbc4be 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -103,6 +103,8 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
+#include <linux/sched/task.h>
+
 #include <asm/sections.h>
 
 #define v1printk(a...) do { \
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index e5f0c7d0fe8d..c6fc7141d7b2 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -17,7 +17,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/debug.h>
-#include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/interrupt.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 985d33f0f315..e6d1a6510886 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -70,6 +70,7 @@
 #include <linux/signal.h>
 #include <linux/fcntl.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/interrupt.h>
 #include <linux/tty.h>
 #include <linux/tty_driver.h>
diff --git a/fs/exec.c b/fs/exec.c
index e857c7260b1f..65145a3df065 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -36,6 +36,7 @@
 #include <linux/sched/coredump.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/numa_balancing.h>
+#include <linux/sched/task.h>
 #include <linux/pagemap.h>
 #include <linux/perf_event.h>
 #include <linux/highmem.h>
diff --git a/fs/fcntl.c b/fs/fcntl.c
index e1c54f20325c..be8fbe289087 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -7,6 +7,7 @@
 #include <linux/syscalls.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 543ed50f0387..be0250788b73 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -1,5 +1,6 @@
 #include <linux/export.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/path.h>
 #include <linux/slab.h>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cfe7f934a300..f3169b58af38 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -62,6 +62,7 @@
 #include <linux/mman.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/numa_balancing.h>
+#include <linux/sched/task.h>
 #include <linux/proc_fs.h>
 #include <linux/ioport.h>
 #include <linux/uaccess.h>
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index ea9f3d1ae830..4ee55274f155 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/ioport.h>
 #include <linux/memory.h>
+#include <linux/sched/task.h>
 #include <asm/sections.h>
 #include "internal.h"
 
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
new file mode 100644
index 000000000000..0023c91ff821
--- /dev/null
+++ b/include/linux/sched/task.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_TASK_H
+#define _LINUX_SCHED_TASK_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_TASK_H */
diff --git a/init/main.c b/init/main.c
index c891cfb8928f..47956b22add1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -76,6 +76,7 @@
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
 #include <linux/sched_clock.h>
+#include <linux/sched/task.h>
 #include <linux/context_tracking.h>
 #include <linux/random.h>
 #include <linux/list.h>
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index e8f87bf9840c..0125589c7428 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -41,6 +41,7 @@
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/percpu-rwsem.h>
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 78c206579d01..f7c063239fa5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -9,6 +9,7 @@
 #include <linux/notifier.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task.h>
 #include <linux/unistd.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 5bad7dce1b7b..e53408d156df 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -9,6 +9,7 @@
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/stat.h>
+#include <linux/sched/task.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/capability.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 8632905f64c5..0af64d5d8b73 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -18,6 +18,7 @@
 #include <linux/sched/user.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/sched/stat.h>
+#include <linux/sched/task.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 0c407f905ca4..ac5f5c2d098d 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -20,6 +20,7 @@
 */
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
 #include <linux/kmod.h>
diff --git a/kernel/kthread.c b/kernel/kthread.c
index ef9b9eb809c7..2f26adea0f84 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -7,6 +7,7 @@
  */
 #include <uapi/linux/sched/types.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/kthread.h>
 #include <linux/completion.h>
 #include <linux/err.h>
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index cdafaff926ca..12e38c213b70 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -29,6 +29,7 @@
 #include <linux/mutex.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/task.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
diff --git a/kernel/pid.c b/kernel/pid.c
index 0291804151b5..0143ac0ddceb 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -38,6 +38,7 @@
 #include <linux/syscalls.h>
 #include <linux/proc_ns.h>
 #include <linux/proc_fs.h>
+#include <linux/sched/task.h>
 
 #define pid_hashfn(nr, ns)	\
 	hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 25314c96fbe6..7c8367854dc4 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -19,6 +19,7 @@
 #include <linux/proc_ns.h>
 #include <linux/reboot.h>
 #include <linux/export.h>
+#include <linux/sched/task.h>
 
 struct pid_cache {
 	int nr_ids;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 85e2915d8961..c7209f060eeb 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -13,6 +13,7 @@
 #include <linux/suspend.h>
 #include <linux/module.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/syscalls.h>
 #include <linux/freezer.h>
 #include <linux/delay.h>
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index bcdbdc19eb35..0af928712174 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/task.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0974eb2ef50d..6b7155ae5c33 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -14,6 +14,7 @@
 #include <linux/sched/nohz.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task.h>
 
 #include <linux/u64_stats_sync.h>
 #include <linux/kernel_stat.h>
diff --git a/kernel/signal.c b/kernel/signal.c
index 15092fd8c7b1..25d099fd80f7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/sched/user.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/tty.h>
 #include <linux/binfmts.h>
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 4a5c6e73ecd4..1d71c051a951 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -9,6 +9,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/export.h>
 #include <linux/percpu.h>
 #include <linux/kthread.h>
diff --git a/kernel/sys.c b/kernel/sys.c
index 8c0392c8be51..7f1ecd2e41c1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -54,6 +54,7 @@
 #include <linux/sched/stat.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/task.h>
 #include <linux/rcupdate.h>
 #include <linux/uidgid.h>
 #include <linux/cred.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0c0609326391..0d1597c9ee30 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -15,6 +15,7 @@
 
 #include <linux/stop_machine.h>
 #include <linux/clocksource.h>
+#include <linux/sched/task.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
 #include <linux/suspend.h>
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 9f6984d52fec..685c50ae6300 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/static_key.h>
 
 extern struct tracepoint * const __start___tracepoints_ptrs[];
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 60c57ec936db..942adf13418d 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -19,6 +19,7 @@
 
 #include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
+#include <linux/sched/task.h>
 #include <linux/stacktrace.h>
 #include <linux/dma-debug.h>
 #include <linux/spinlock.h>
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 2df6d3687b2a..a3970573359e 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -74,6 +74,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/jiffies.h>
 #include <linux/delay.h>
 #include <linux/export.h>
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b74984db386e..27f7210e7fab 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -41,6 +41,7 @@
 #include <linux/page-flags.h>
 #include <linux/kernel-page-flags.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/ksm.h>
 #include <linux/rmap.h>
 #include <linux/export.h>
diff --git a/mm/memory.c b/mm/memory.c
index d4994a28dc85..a97a4cec2e1f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -43,6 +43,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/numa_balancing.h>
+#include <linux/sched/task.h>
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 69f75b014607..d083714a2bb9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -24,6 +24,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/task.h>
 #include <linux/swap.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
diff --git a/mm/rmap.c b/mm/rmap.c
index 0367a0506667..2da487d6cea8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -47,6 +47,7 @@
 
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
diff --git a/mm/swapfile.c b/mm/swapfile.c
index ff2bf3f61b14..521ef9b6064f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -7,6 +7,7 @@
 
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/slab.h>
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 7ccad05c0d5c..d155e12563b1 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -17,6 +17,8 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <asm/sections.h>
 
 enum {
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index bcb0b597c391..52c34532c785 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 #include <linux/key.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b12f873f92ba..57ff53696144 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -29,6 +29,7 @@
 #include <linux/tracehook.h>
 #include <linux/errno.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/lsm_hooks.h>
 #include <linux/xattr.h>
 #include <linux/capability.h>
-- 
GitLab


From 68db0cf10678630d286f4bbbbdfa102951a35faa Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:37 +0100
Subject: [PATCH 504/898] sched/headers: Prepare for new header dependencies
 before moving code to <linux/sched/task_stack.h>

We are going to split <linux/sched/task_stack.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.

Create a trivial placeholder <linux/sched/task_stack.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.

Include the new header in the files that are going to need it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/kernel/osf_sys.c            | 1 +
 arch/alpha/kernel/process.c            | 1 +
 arch/alpha/kernel/ptrace.c             | 1 +
 arch/alpha/kernel/signal.c             | 1 +
 arch/arc/kernel/kgdb.c                 | 1 +
 arch/arc/kernel/process.c              | 1 +
 arch/arc/kernel/ptrace.c               | 1 +
 arch/arc/kernel/signal.c               | 2 ++
 arch/arm/kernel/perf_regs.c            | 1 +
 arch/arm/kernel/process.c              | 1 +
 arch/arm/kernel/ptrace.c               | 1 +
 arch/arm/kernel/smp.c                  | 1 +
 arch/arm/kernel/traps.c                | 1 +
 arch/arm64/include/asm/compat.h        | 1 +
 arch/arm64/kernel/debug-monitors.c     | 1 +
 arch/arm64/kernel/kgdb.c               | 2 ++
 arch/arm64/kernel/perf_regs.c          | 1 +
 arch/arm64/kernel/process.c            | 1 +
 arch/arm64/kernel/ptrace.c             | 1 +
 arch/arm64/kernel/smp.c                | 1 +
 arch/arm64/kernel/stacktrace.c         | 1 +
 arch/arm64/kernel/traps.c              | 1 +
 arch/avr32/kernel/process.c            | 1 +
 arch/avr32/kernel/ptrace.c             | 1 +
 arch/avr32/kernel/stacktrace.c         | 1 +
 arch/blackfin/kernel/process.c         | 1 +
 arch/blackfin/kernel/ptrace.c          | 1 +
 arch/blackfin/kernel/signal.c          | 1 +
 arch/blackfin/kernel/stacktrace.c      | 1 +
 arch/blackfin/mach-common/smp.c        | 1 +
 arch/c6x/kernel/process.c              | 1 +
 arch/c6x/kernel/ptrace.c               | 1 +
 arch/cris/arch-v10/kernel/process.c    | 1 +
 arch/cris/arch-v10/kernel/ptrace.c     | 1 +
 arch/cris/arch-v10/kernel/signal.c     | 1 +
 arch/cris/arch-v32/kernel/process.c    | 1 +
 arch/cris/arch-v32/kernel/ptrace.c     | 1 +
 arch/cris/arch-v32/kernel/signal.c     | 1 +
 arch/frv/kernel/process.c              | 1 +
 arch/h8300/kernel/process.c            | 1 +
 arch/h8300/kernel/signal.c             | 1 +
 arch/hexagon/kernel/kgdb.c             | 1 +
 arch/hexagon/kernel/process.c          | 1 +
 arch/hexagon/kernel/ptrace.c           | 1 +
 arch/hexagon/kernel/signal.c           | 2 ++
 arch/hexagon/kernel/stacktrace.c       | 1 +
 arch/hexagon/kernel/traps.c            | 1 +
 arch/ia64/kernel/perfmon.c             | 1 +
 arch/ia64/kernel/process.c             | 1 +
 arch/ia64/kernel/ptrace.c              | 1 +
 arch/ia64/kernel/setup.c               | 1 +
 arch/ia64/kernel/sys_ia64.c            | 1 +
 arch/m32r/kernel/process.c             | 1 +
 arch/m32r/kernel/ptrace.c              | 1 +
 arch/m68k/kernel/process.c             | 1 +
 arch/m68k/kernel/ptrace.c              | 1 +
 arch/metag/kernel/process.c            | 1 +
 arch/metag/kernel/ptrace.c             | 2 ++
 arch/metag/kernel/signal.c             | 1 +
 arch/metag/kernel/smp.c                | 1 +
 arch/metag/kernel/traps.c              | 1 +
 arch/microblaze/kernel/process.c       | 1 +
 arch/microblaze/kernel/ptrace.c        | 1 +
 arch/microblaze/kernel/unwind.c        | 1 +
 arch/mips/include/asm/fpu.h            | 1 +
 arch/mips/kernel/crash.c               | 1 +
 arch/mips/kernel/perf_event.c          | 1 +
 arch/mips/kernel/process.c             | 1 +
 arch/mips/kernel/ptrace.c              | 1 +
 arch/mips/kernel/ptrace32.c            | 1 +
 arch/mips/kernel/stacktrace.c          | 1 +
 arch/mips/kernel/syscall.c             | 1 +
 arch/mips/loongson64/loongson-3/smp.c  | 1 +
 arch/mips/paravirt/paravirt-smp.c      | 1 +
 arch/mips/sibyte/bcm1480/smp.c         | 1 +
 arch/mn10300/kernel/process.c          | 1 +
 arch/mn10300/kernel/ptrace.c           | 1 +
 arch/nios2/kernel/process.c            | 1 +
 arch/nios2/kernel/ptrace.c             | 1 +
 arch/openrisc/kernel/process.c         | 1 +
 arch/openrisc/kernel/ptrace.c          | 1 +
 arch/parisc/kernel/process.c           | 1 +
 arch/powerpc/kernel/process.c          | 1 +
 arch/powerpc/mm/fault.c                | 1 +
 arch/powerpc/perf/perf_regs.c          | 1 +
 arch/s390/include/asm/compat.h         | 1 +
 arch/s390/include/asm/kprobes.h        | 1 +
 arch/s390/kernel/compat_signal.c       | 1 +
 arch/s390/kernel/dumpstack.c           | 1 +
 arch/s390/kernel/process.c             | 1 +
 arch/s390/kernel/ptrace.c              | 1 +
 arch/s390/kernel/runtime_instr.c       | 2 ++
 arch/s390/kernel/signal.c              | 1 +
 arch/s390/kernel/smp.c                 | 1 +
 arch/s390/kernel/uprobes.c             | 2 ++
 arch/score/kernel/process.c            | 1 +
 arch/score/kernel/ptrace.c             | 1 +
 arch/sh/kernel/cpu/fpu.c               | 1 +
 arch/sh/kernel/dumpstack.c             | 1 +
 arch/sh/kernel/kgdb.c                  | 2 ++
 arch/sh/kernel/process.c               | 1 +
 arch/sh/kernel/process_32.c            | 1 +
 arch/sh/kernel/process_64.c            | 1 +
 arch/sh/kernel/ptrace_32.c             | 1 +
 arch/sh/kernel/ptrace_64.c             | 1 +
 arch/sh/kernel/signal_32.c             | 1 +
 arch/sh/kernel/sys_sh32.c              | 1 +
 arch/sh/kernel/traps.c                 | 1 +
 arch/sh/kernel/traps_32.c              | 2 ++
 arch/sparc/kernel/process_32.c         | 1 +
 arch/sparc/kernel/process_64.c         | 1 +
 arch/sparc/kernel/ptrace_64.c          | 1 +
 arch/tile/kernel/compat_signal.c       | 1 +
 arch/tile/kernel/kgdb.c                | 2 ++
 arch/tile/kernel/process.c             | 1 +
 arch/tile/kernel/ptrace.c              | 2 ++
 arch/tile/kernel/signal.c              | 1 +
 arch/tile/kernel/stack.c               | 1 +
 arch/um/kernel/exec.c                  | 1 +
 arch/um/kernel/process.c               | 1 +
 arch/um/kernel/skas/process.c          | 1 +
 arch/unicore32/kernel/process.c        | 1 +
 arch/unicore32/kernel/ptrace.c         | 1 +
 arch/unicore32/kernel/traps.c          | 1 +
 arch/x86/entry/common.c                | 1 +
 arch/x86/entry/vdso/vma.c              | 1 +
 arch/x86/ia32/ia32_aout.c              | 1 +
 arch/x86/ia32/ia32_signal.c            | 1 +
 arch/x86/kernel/dumpstack.c            | 1 +
 arch/x86/kernel/fpu/regset.c           | 1 +
 arch/x86/kernel/ioport.c               | 1 +
 arch/x86/kernel/irq_64.c               | 1 +
 arch/x86/kernel/perf_regs.c            | 1 +
 arch/x86/kernel/process.c              | 1 +
 arch/x86/kernel/process_32.c           | 1 +
 arch/x86/kernel/process_64.c           | 1 +
 arch/x86/kernel/ptrace.c               | 1 +
 arch/x86/kernel/signal.c               | 1 +
 arch/x86/kernel/smpboot.c              | 1 +
 arch/x86/kernel/stacktrace.c           | 1 +
 arch/x86/kernel/step.c                 | 1 +
 arch/x86/kernel/traps.c                | 1 +
 arch/x86/kernel/unwind_frame.c         | 1 +
 arch/x86/kernel/vm86_32.c              | 1 +
 arch/x86/mm/fault.c                    | 1 +
 arch/xtensa/kernel/process.c           | 1 +
 arch/xtensa/kernel/ptrace.c            | 1 +
 arch/xtensa/kernel/signal.c            | 1 +
 arch/xtensa/kernel/smp.c               | 1 +
 block/blk-map.c                        | 1 +
 drivers/hv/vmbus_drv.c                 | 2 ++
 drivers/ide/ide-cd.c                   | 1 +
 drivers/md/bcache/closure.h            | 1 +
 drivers/misc/lkdtm_usercopy.c          | 1 +
 drivers/mtd/nand/gpmi-nand/gpmi-nand.c | 1 +
 fs/binfmt_aout.c                       | 1 +
 fs/binfmt_elf.c                        | 1 +
 fs/binfmt_elf_fdpic.c                  | 3 ++-
 fs/binfmt_flat.c                       | 1 +
 fs/coredump.c                          | 1 +
 include/linux/elfcore.h                | 2 ++
 include/linux/perf_regs.h              | 2 ++
 include/linux/sched/task_stack.h       | 6 ++++++
 init/main.c                            | 1 +
 kernel/events/callchain.c              | 2 ++
 kernel/exit.c                          | 1 +
 kernel/fork.c                          | 1 +
 kernel/printk/printk.c                 | 1 +
 kernel/sched/sched.h                   | 1 +
 kernel/seccomp.c                       | 1 +
 kernel/signal.c                        | 1 +
 kernel/trace/trace_stack.c             | 1 +
 lib/debugobjects.c                     | 1 +
 lib/dma-debug.c                        | 1 +
 lib/syscall.c                          | 1 +
 mm/kasan/kasan.c                       | 1 +
 mm/kmemleak.c                          | 1 +
 mm/util.c                              | 1 +
 178 files changed, 198 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/sched/task_stack.h

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 3b9b2a382ba2..73446baa632e 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 713b4fac998e..0b9635040721 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c
index bc4d2cdcf21d..285a82d491ef 100644
--- a/arch/alpha/kernel/ptrace.c
+++ b/arch/alpha/kernel/ptrace.c
@@ -6,6 +6,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index b8221f112eee..8129dd92cadc 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/errno.h>
diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c
index ecf6a7869375..9a3c34af2ae8 100644
--- a/arch/arc/kernel/kgdb.c
+++ b/arch/arc/kernel/kgdb.c
@@ -10,6 +10,7 @@
 
 #include <linux/kgdb.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <asm/disasm.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index d618d26721ab..2a018de6d6cd 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 
 #include <linux/mm.h>
 #include <linux/fs.h>
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index 4442204fe238..31150060d38b 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -8,6 +8,7 @@
 
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
+#include <linux/sched/task_stack.h>
 #include <linux/regset.h>
 #include <linux/unistd.h>
 #include <linux/elf.h>
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index d347bbc086fe..48685445002e 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -53,6 +53,8 @@
 #include <linux/uaccess.h>
 #include <linux/syscalls.h>
 #include <linux/tracehook.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/ucontext.h>
 
 struct rt_sigframe {
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 592dda3f21ff..c366b83bf955 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -3,6 +3,7 @@
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
 #include <linux/bug.h>
+#include <linux/sched/task_stack.h>
 #include <asm/perf_regs.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d4c7c9a1afa9..939e8b58c59d 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 46f7bab81c40..58e3771e4c5b 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -11,6 +11,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/elf.h>
 #include <linux/smp.h>
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 2083a5370308..b724cff7ad60 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -13,6 +13,7 @@
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
 #include <linux/profile.h>
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index a9dad001b97d..948c648fea00 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -26,6 +26,7 @@
 #include <linux/init.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/irq.h>
 
 #include <linux/atomic.h>
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index eb8432bb82b8..e39d487bf724 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -23,6 +23,7 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 2bd426448fc1..32913567da08 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -26,6 +26,7 @@
 #include <linux/kprobes.h>
 #include <linux/stat.h>
 #include <linux/uaccess.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cpufeature.h>
 #include <asm/cputype.h>
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index d217c9e95b06..2122cd187f19 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -24,6 +24,8 @@
 #include <linux/kdebug.h>
 #include <linux/kgdb.h>
 #include <linux/kprobes.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/debug-monitors.h>
 #include <asm/insn.h>
 #include <asm/traps.h>
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 3f62b35fb6f1..bd1b74c2436f 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
 #include <linux/bug.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/compat.h>
 #include <asm/perf_regs.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f9b8e74ff8f2..043d373b8369 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 64fc32ea3422..c142459a88f3 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -23,6 +23,7 @@
 #include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/ptrace.h>
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index f66e58523b96..83c0a839a6ad 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -23,6 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
 #include <linux/profile.h>
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 7597e42feeea..feac80c22f61 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -20,6 +20,7 @@
 #include <linux/ftrace.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 
 #include <asm/irq.h>
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5a5d83791837..bdbd0c3febf4 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -31,6 +31,7 @@
 #include <linux/init.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/syscalls.h>
 
 #include <asm/atomic.h>
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 75b944a5107c..ad0dfccedb79 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/fs.h>
diff --git a/arch/avr32/kernel/ptrace.c b/arch/avr32/kernel/ptrace.c
index a89b893279bb..41a14e96a1db 100644
--- a/arch/avr32/kernel/ptrace.c
+++ b/arch/avr32/kernel/ptrace.c
@@ -8,6 +8,7 @@
 #undef DEBUG
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
diff --git a/arch/avr32/kernel/stacktrace.c b/arch/avr32/kernel/stacktrace.c
index c09f0d8dd679..f8cc995cf0e0 100644
--- a/arch/avr32/kernel/stacktrace.c
+++ b/arch/avr32/kernel/stacktrace.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/thread_info.h>
 #include <linux/module.h>
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 1a1f444004b1..b691ef875a40 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/tick.h>
 #include <linux/fs.h>
 #include <linux/err.h>
diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c
index 360d99645163..a6827095b99a 100644
--- a/arch/blackfin/kernel/ptrace.c
+++ b/arch/blackfin/kernel/ptrace.c
@@ -7,6 +7,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/elf.h>
diff --git a/arch/blackfin/kernel/signal.c b/arch/blackfin/kernel/signal.c
index ea570db598e5..5f5172779204 100644
--- a/arch/blackfin/kernel/signal.c
+++ b/arch/blackfin/kernel/signal.c
@@ -12,6 +12,7 @@
 #include <linux/binfmts.h>
 #include <linux/uaccess.h>
 #include <linux/tracehook.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
diff --git a/arch/blackfin/kernel/stacktrace.c b/arch/blackfin/kernel/stacktrace.c
index 30301e1eace5..17198f3650b6 100644
--- a/arch/blackfin/kernel/stacktrace.c
+++ b/arch/blackfin/kernel/stacktrace.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/thread_info.h>
 #include <linux/module.h>
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index a2e6db2ce811..3ac98252d299 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
 #include <linux/clockchips.h>
diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c
index 6b61779d426a..c4ecb24c2d5c 100644
--- a/arch/c6x/kernel/process.c
+++ b/arch/c6x/kernel/process.c
@@ -18,6 +18,7 @@
 #include <linux/syscalls.h>
 #include <linux/reboot.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/syscalls.h>
 
diff --git a/arch/c6x/kernel/ptrace.c b/arch/c6x/kernel/ptrace.c
index 3c494e84444d..a27e1f02ce18 100644
--- a/arch/c6x/kernel/ptrace.c
+++ b/arch/c6x/kernel/ptrace.c
@@ -14,6 +14,7 @@
 #include <linux/tracehook.h>
 #include <linux/regset.h>
 #include <linux/elf.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cacheflush.h>
 
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index 808c2186b704..e299d30105b5 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/fs.h>
diff --git a/arch/cris/arch-v10/kernel/ptrace.c b/arch/cris/arch-v10/kernel/ptrace.c
index eca94c7d56e7..c2f2b9b83cc4 100644
--- a/arch/cris/arch-v10/kernel/ptrace.c
+++ b/arch/cris/arch-v10/kernel/ptrace.c
@@ -4,6 +4,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/cris/arch-v10/kernel/signal.c b/arch/cris/arch-v10/kernel/signal.c
index db30c98e4926..bab4a8dd6bfd 100644
--- a/arch/cris/arch-v10/kernel/signal.c
+++ b/arch/cris/arch-v10/kernel/signal.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index c852df262948..c530a8fa87ce 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/fs.h>
diff --git a/arch/cris/arch-v32/kernel/ptrace.c b/arch/cris/arch-v32/kernel/ptrace.c
index c366bc05466a..0461e95bbb62 100644
--- a/arch/cris/arch-v32/kernel/ptrace.c
+++ b/arch/cris/arch-v32/kernel/ptrace.c
@@ -4,6 +4,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/cris/arch-v32/kernel/signal.c b/arch/cris/arch-v32/kernel/signal.c
index 816bf2ca93ef..ea2e8e1398e8 100644
--- a/arch/cris/arch-v32/kernel/signal.c
+++ b/arch/cris/arch-v32/kernel/signal.c
@@ -3,6 +3,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index c96dbd4b8626..5a4c92abc99e 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 54e4d6f01865..0f5db5bb561b 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -27,6 +27,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index d784f7117f9a..1e8070d08770 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -25,6 +25,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
diff --git a/arch/hexagon/kernel/kgdb.c b/arch/hexagon/kernel/kgdb.c
index 62dece3ad827..16c24b22d0b2 100644
--- a/arch/hexagon/kernel/kgdb.c
+++ b/arch/hexagon/kernel/kgdb.c
@@ -20,6 +20,7 @@
 
 #include <linux/irq.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kdebug.h>
 #include <linux/kgdb.h>
 
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index a2a822a875b6..de715bab7956 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/tick.h>
diff --git a/arch/hexagon/kernel/ptrace.c b/arch/hexagon/kernel/ptrace.c
index 390a9ad14ca1..ecd75e2e8eb3 100644
--- a/arch/hexagon/kernel/ptrace.c
+++ b/arch/hexagon/kernel/ptrace.c
@@ -22,6 +22,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c
index c6b22b9945a7..78aa7304a5c9 100644
--- a/arch/hexagon/kernel/signal.c
+++ b/arch/hexagon/kernel/signal.c
@@ -21,6 +21,8 @@
 #include <linux/linkage.h>
 #include <linux/syscalls.h>
 #include <linux/tracehook.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/registers.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
diff --git a/arch/hexagon/kernel/stacktrace.c b/arch/hexagon/kernel/stacktrace.c
index f94918b449a8..41866a06adf7 100644
--- a/arch/hexagon/kernel/stacktrace.c
+++ b/arch/hexagon/kernel/stacktrace.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/thread_info.h>
 #include <linux/module.h>
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index b55f13c70b34..2942a9204a9a 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/kdebug.h>
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 7e943d3c05ed..09f86ebfcc7b 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 054facf22156..d344d0d691aa 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -23,6 +23,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stddef.h>
 #include <linux/thread_info.h>
 #include <linux/unistd.h>
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 04fe1436e1cc..3f8293378a83 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 32a6cc36296f..b2b4f5216180 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -33,6 +33,7 @@
 #include <linux/reboot.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/task_stack.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/threads.h>
diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c
index ce4cc60d519b..5ce927c854a6 100644
--- a/arch/ia64/kernel/sys_ia64.c
+++ b/arch/ia64/kernel/sys_ia64.c
@@ -11,6 +11,7 @@
 #include <linux/mman.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
 #include <linux/shm.h>
 #include <linux/file.h>		/* doh, must come after sched.h... */
 #include <linux/smp.h>
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index 2a450382934c..d8ffcfec599c 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/unistd.h>
diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c
index a68acb9fa515..2d887400e30e 100644
--- a/arch/m32r/kernel/ptrace.c
+++ b/arch/m32r/kernel/ptrace.c
@@ -16,6 +16,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/smp.h>
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 5d335d178706..e475c945c8b2 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c
index 9cd86d7343a6..748c63bd0081 100644
--- a/arch/m68k/kernel/ptrace.c
+++ b/arch/m68k/kernel/ptrace.c
@@ -12,6 +12,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c
index 801e6f927e62..c4606ce743d2 100644
--- a/arch/metag/kernel/process.c
+++ b/arch/metag/kernel/process.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/unistd.h>
diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c
index 7563628822bd..5fd16ee5280c 100644
--- a/arch/metag/kernel/ptrace.c
+++ b/arch/metag/kernel/ptrace.c
@@ -15,6 +15,8 @@
 #include <linux/tracehook.h>
 #include <linux/elf.h>
 #include <linux/uaccess.h>
+#include <linux/sched/task_stack.h>
+
 #include <trace/syscall.h>
 
 #define CREATE_TRACE_POINTS
diff --git a/arch/metag/kernel/signal.c b/arch/metag/kernel/signal.c
index ce49d429c74a..338925d808e6 100644
--- a/arch/metag/kernel/signal.c
+++ b/arch/metag/kernel/signal.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index 198eda75846b..cab2aa64ca82 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
 #include <linux/profile.h>
diff --git a/arch/metag/kernel/traps.c b/arch/metag/kernel/traps.c
index 23c5ac33a93f..444851e510d5 100644
--- a/arch/metag/kernel/traps.c
+++ b/arch/metag/kernel/traps.c
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/signal.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index a642fe5ac5ff..e92a817e645f 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
 #include <linux/bitops.h>
diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c
index 8cfa98cadf3d..badd286882ae 100644
--- a/arch/microblaze/kernel/ptrace.c
+++ b/arch/microblaze/kernel/ptrace.c
@@ -27,6 +27,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/elf.h>
diff --git a/arch/microblaze/kernel/unwind.c b/arch/microblaze/kernel/unwind.c
index 61c04eed14d5..34c270cb11fc 100644
--- a/arch/microblaze/kernel/unwind.c
+++ b/arch/microblaze/kernel/unwind.c
@@ -17,6 +17,7 @@
 #include <linux/kallsyms.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/types.h>
 #include <linux/errno.h>
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index f06f97bd62df..321752bcbab6 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -11,6 +11,7 @@
 #define _ASM_FPU_H
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/thread_info.h>
 #include <linux/bitops.h>
 
diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c
index 5a71518be0f1..ca25cd393b1c 100644
--- a/arch/mips/kernel/crash.c
+++ b/arch/mips/kernel/crash.c
@@ -8,6 +8,7 @@
 #include <linux/irq.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 /* This keeps a track of which one is crashing cpu. */
 static int crashing_cpu = -1;
diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index d64056e0bb56..f298eb2ff6c2 100644
--- a/arch/mips/kernel/perf_event.c
+++ b/arch/mips/kernel/perf_event.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/perf_event.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/stacktrace.h>
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 8bfb833b3158..fb6b6b650719 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/tick.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index fdef26382c37..339601267265 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -19,6 +19,7 @@
 #include <linux/elf.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 4f0998525626..40e212d6b26b 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -18,6 +18,7 @@
 #include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
diff --git a/arch/mips/kernel/stacktrace.c b/arch/mips/kernel/stacktrace.c
index 986f910961d9..7c7c902249f2 100644
--- a/arch/mips/kernel/stacktrace.c
+++ b/arch/mips/kernel/stacktrace.c
@@ -5,6 +5,7 @@
  */
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/export.h>
 #include <asm/stacktrace.h>
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index c86ddbaa4598..f1d17ece4181 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -26,6 +26,7 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include <linux/elf.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/asm.h>
 #include <asm/branch.h>
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 66ede5b11355..64659fc73940 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -18,6 +18,7 @@
 #include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 #include <linux/cpufreq.h>
 #include <asm/processor.h>
diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c
index f8d3e081b2eb..72eb1a56c645 100644
--- a/arch/mips/paravirt/paravirt-smp.c
+++ b/arch/mips/paravirt/paravirt-smp.c
@@ -10,6 +10,7 @@
 #include <linux/cpumask.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/mipsregs.h>
 #include <asm/setup.h>
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index 4c71aea25663..d0e94ffcc1b8 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -21,6 +21,7 @@
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 8ca7a9de09a5..c9fa42619c6a 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/mn10300/kernel/ptrace.c b/arch/mn10300/kernel/ptrace.c
index 976020f469c1..8009876a7ac4 100644
--- a/arch/mn10300/kernel/ptrace.c
+++ b/arch/mn10300/kernel/ptrace.c
@@ -11,6 +11,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 5ee1ddf6a924..869a4d59de32 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/tick.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/nios2/kernel/ptrace.c b/arch/nios2/kernel/ptrace.c
index 681dda92eff1..de97bcb7dd44 100644
--- a/arch/nios2/kernel/ptrace.c
+++ b/arch/nios2/kernel/ptrace.c
@@ -14,6 +14,7 @@
 #include <linux/ptrace.h>
 #include <linux/regset.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/tracehook.h>
 #include <linux/uaccess.h>
 #include <linux/user.h>
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 0c5ad3bde0f5..828a29110459 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -24,6 +24,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mm.h>
diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c
index 228288887d74..eb97a8e7c8aa 100644
--- a/arch/openrisc/kernel/ptrace.c
+++ b/arch/openrisc/kernel/ptrace.c
@@ -18,6 +18,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/string.h>
 
 #include <linux/mm.h>
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index e5f97239cc5e..06f7ca7fe70b 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -45,6 +45,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b99b12656f6f..d645da302bf2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -18,6 +18,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8dc758658972..51def8a515be 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -17,6 +17,7 @@
 
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index d24a8a3668fa..cbd82fde5770 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/perf_event.h>
 #include <linux/bug.h>
 #include <linux/stddef.h>
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 352f7bdaf11f..0ddd37e6c29d 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -5,6 +5,7 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/thread_info.h>
 
 #define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p(typeof(0?(t)0:0ULL), u64))
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 84c0f9086483..1293c4066cfc 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -35,6 +35,7 @@
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
+#include <linux/sched/task_stack.h>
 
 #define __ARCH_WANT_KPROBES_INSN_SLOT
 
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 362350cc485c..c620049c61f2 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -10,6 +10,7 @@
 
 #include <linux/compat.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 72c584d62f59..829e1c53005c 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <asm/processor.h>
 #include <asm/debug.h>
 #include <asm/dis.h>
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 250c41f05721..20cd339e11ae 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/elfcore.h>
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 12020b55887b..c14df0a1ec3c 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index fffa0e5462af..429d3a782f1c 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -11,6 +11,8 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/runtime_instr.h>
 #include <asm/cpu_mf.h>
 #include <asm/irq.h>
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 62a4c263e887..289dd50f9744 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index b5766e03cdcb..47a973b5b4f1 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -32,6 +32,7 @@
 #include <linux/cpu.h>
 #include <linux/slab.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/crash_dump.h>
 #include <linux/memblock.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index 66956c09d5bf..314e0ee3016a 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -9,6 +9,8 @@
 #include <linux/uprobes.h>
 #include <linux/compat.h>
 #include <linux/kdebug.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/switch_to.h>
 #include <asm/facility.h>
 #include <asm/kprobes.h>
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index 32924159d8c9..eb64d7a677cb 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
diff --git a/arch/score/kernel/ptrace.c b/arch/score/kernel/ptrace.c
index 8b75e54816c1..d8455e60bce0 100644
--- a/arch/score/kernel/ptrace.c
+++ b/arch/score/kernel/ptrace.c
@@ -28,6 +28,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
+#include <linux/sched/task_stack.h>
 
 #include <linux/uaccess.h>
 
diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c
index b76370a47bf9..547c73478459 100644
--- a/arch/sh/kernel/cpu/fpu.c
+++ b/arch/sh/kernel/cpu/fpu.c
@@ -1,5 +1,6 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <asm/processor.h>
 #include <asm/fpu.h>
diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c
index d00cab2f50f9..b564b1eae4ae 100644
--- a/arch/sh/kernel/dumpstack.c
+++ b/arch/sh/kernel/dumpstack.c
@@ -12,6 +12,7 @@
 #include <linux/ftrace.h>
 #include <linux/debug_locks.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kdebug.h>
 #include <linux/export.h>
 #include <linux/uaccess.h>
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index adad46e41a1d..4f04c6638a4d 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -14,6 +14,8 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 
diff --git a/arch/sh/kernel/process.c b/arch/sh/kernel/process.c
index 80a61c5e3015..f8a695a223dd 100644
--- a/arch/sh/kernel/process.c
+++ b/arch/sh/kernel/process.c
@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/export.h>
 #include <linux/stackprotector.h>
 #include <asm/fpu.h>
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 493c3eb86aa5..2c7bdf8cb934 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -17,6 +17,7 @@
 #include <linux/mm.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <linux/elfcore.h>
 #include <linux/kallsyms.h>
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index 056607185158..ee2abe96f9f3 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -27,6 +27,7 @@
 #include <linux/io.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <asm/syscalls.h>
 #include <linux/uaccess.h>
 #include <asm/pgtable.h>
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 1aabfd356b35..5fc3ff606210 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -12,6 +12,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/sh/kernel/ptrace_64.c b/arch/sh/kernel/ptrace_64.c
index c49d0d05a215..1e0656d9e7af 100644
--- a/arch/sh/kernel/ptrace_64.c
+++ b/arch/sh/kernel/ptrace_64.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/rwsem.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/bitops.h>
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 5128d3001ee5..08bce11badc6 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -9,6 +9,7 @@
  *
  */
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c
index d5287d76809c..a2e1231a90a3 100644
--- a/arch/sh/kernel/sys_sh32.c
+++ b/arch/sh/kernel/sys_sh32.c
@@ -1,5 +1,6 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/sem.h>
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index bc5c9f347b9e..b32d1c3a4655 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -5,6 +5,7 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 #include <linux/kernel.h>
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index ff639342a8be..57cff00cad17 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -25,6 +25,8 @@
 #include <linux/sysfs.h>
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/alignment.h>
 #include <asm/fpu.h>
 #include <asm/kprobes.h>
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index ed87c45a785b..b6dac8e980f0 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 4c82a73af893..1badc493e62e 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 901063c1cf7e..df9e731a76f5 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -12,6 +12,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/export.h>
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index c667e104a0c2..0e863f1ee08c 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/tile/kernel/kgdb.c b/arch/tile/kernel/kgdb.c
index 9247d6b562f4..d4eb5fb2df9d 100644
--- a/arch/tile/kernel/kgdb.c
+++ b/arch/tile/kernel/kgdb.c
@@ -19,6 +19,8 @@
 #include <linux/kdebug.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/cacheflush.h>
 
 static tile_bundle_bits singlestep_insn = TILEGX_BPT_BUNDLE | DIE_SSTEPBP;
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index dbb4fa76d1dd..f0a0e18e4dfb 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/preempt.h>
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index e279572824b1..e1a078e6828e 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -23,6 +23,8 @@
 #include <linux/elf.h>
 #include <linux/tracehook.h>
 #include <linux/context_tracking.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/traps.h>
 #include <arch/chip.h>
 
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 8cc92ae6eb27..f2bf557bb005 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -15,6 +15,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index a1c0787fe9d8..94ecbc6676e5 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -14,6 +14,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 2df4e5d11939..31968677a0d0 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -9,6 +9,7 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <asm/current.h>
 #include <asm/processor.h>
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index e76dc7c11251..a9bd61820042 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/seq_file.h>
 #include <linux/tick.h>
 #include <linux/threads.h>
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index 527fa5881915..ddecf326dab2 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -5,6 +5,7 @@
 
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <as-layout.h>
 #include <kern.h>
 #include <os.h>
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index d58f1600b477..d22c1dc7e39e 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
diff --git a/arch/unicore32/kernel/ptrace.c b/arch/unicore32/kernel/ptrace.c
index 9f07c08da050..a102c2b4f358 100644
--- a/arch/unicore32/kernel/ptrace.c
+++ b/arch/unicore32/kernel/ptrace.c
@@ -15,6 +15,7 @@
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/uaccess.h>
+#include <linux/sched/task_stack.h>
 
 /*
  * this routine will get a word off of the processes privileged stack.
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index 506e1a2127c6..5f25b39f04d4 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -16,6 +16,7 @@
 #include <linux/signal.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/spinlock.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index b83c61cfd154..370c42c7f046 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 572cee3fccff..226ca70dc6bd 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/random.h>
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 7c0a711989d2..8d0879f1d42c 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -26,6 +26,7 @@
 #include <linux/init.h>
 #include <linux/jiffies.h>
 #include <linux/perf_event.h>
+#include <linux/sched/task_stack.h>
 
 #include <linux/uaccess.h>
 #include <asm/pgalloc.h>
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 95c0b4ae09b0..724153797209 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 7b9e7e68f316..09d4ac0d2661 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/ftrace.h>
 #include <linux/kexec.h>
 #include <linux/bug.h>
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index c114b132d121..b188b16841e3 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -5,6 +5,7 @@
 #include <asm/fpu/signal.h>
 #include <asm/fpu/regset.h>
 #include <asm/fpu/xstate.h>
+#include <linux/sched/task_stack.h>
 
 /*
  * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index b01bc8517450..ca49bab3e467 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/capability.h>
 #include <linux/errno.h>
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 6b0678a541e2..3be74fbdeff2 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -15,6 +15,7 @@
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
 #include <linux/smp.h>
+#include <linux/sched/task_stack.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index da8cb987b973..587d887f7f17 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -1,6 +1,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/perf_event.h>
 #include <linux/bug.h>
 #include <linux/stddef.h>
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 441f00e7be8f..56b059486c3b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -10,6 +10,7 @@
 #include <linux/sched/idle.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/pm.h>
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index d79ffa47aab8..4c818f8bc135 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 124f5652ae3c..d6b784a5520d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 9cc7d5a330ef..2364b23ea3e5 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -6,6 +6,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 763af1d0de64..396c042e9d0e 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -10,6 +10,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f3eb266d75ff..bd1f1ad35284 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -47,6 +47,7 @@
 #include <linux/sched.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/percpu.h>
 #include <linux/bootmem.h>
 #include <linux/err.h>
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 330cae0025d0..8e2b79b88e51 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -5,6 +5,7 @@
  */
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/export.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index a23ce84a3f6c..f07f83b3611b 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -2,6 +2,7 @@
  * x86 single-step support code, common to 32-bit and 64-bit.
  */
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1dc86ee60a03..948443e115c1 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -29,6 +29,7 @@
 #include <linux/errno.h>
 #include <linux/kexec.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/bug.h>
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 7c0abdc9a732..478d15dbaee4 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -1,5 +1,6 @@
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <asm/ptrace.h>
 #include <asm/bitops.h>
 #include <asm/stacktrace.h>
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 0442d98367ae..23ee89ce59a9 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -35,6 +35,7 @@
 #include <linux/interrupt.h>
 #include <linux/syscalls.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/string.h>
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e3254ca0eec4..428e31763cb9 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
  */
 #include <linux/sched.h>		/* test_thread_flag(), ...	*/
+#include <linux/sched/task_stack.h>	/* task_stack_*(), ...		*/
 #include <linux/kdebug.h>		/* oops_begin/end, ...		*/
 #include <linux/extable.h>		/* search_exception_tables	*/
 #include <linux/bootmem.h>		/* max_low_pfn			*/
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index af33f9d4c624..58f96d1230d4 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index 32519b71d914..e0f583fed06a 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -20,6 +20,7 @@
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/security.h>
 #include <linux/signal.h>
 #include <linux/smp.h>
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index c41294745731..70a131945443 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -20,6 +20,7 @@
 #include <linux/ptrace.h>
 #include <linux/personality.h>
 #include <linux/tracehook.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/ucontext.h>
 #include <linux/uaccess.h>
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index f2b3e1725349..fd894eaa63f3 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -22,6 +22,7 @@
 #include <linux/kdebug.h>
 #include <linux/module.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/reboot.h>
 #include <linux/seq_file.h>
 #include <linux/smp.h>
diff --git a/block/blk-map.c b/block/blk-map.c
index 2f18c2a0be1b..3b5cb863318f 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -2,6 +2,7 @@
  * Functions related to mapping data to requests
  */
 #include <linux/kernel.h>
+#include <linux/sched/task_stack.h>
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index f7f6b9144b07..da6b59ba5940 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -34,6 +34,8 @@
 #include <linux/kernel_stat.h>
 #include <linux/clockchips.h>
 #include <linux/cpu.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/hyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index aef00511ca86..74f1b7dc03f7 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/sched/task_stack.h>
 #include <linux/delay.h>
 #include <linux/timer.h>
 #include <linux/seq_file.h>
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 9b2fe2d3e3a9..1ec84ca81146 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -3,6 +3,7 @@
 
 #include <linux/llist.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/workqueue.h>
 
 /*
diff --git a/drivers/misc/lkdtm_usercopy.c b/drivers/misc/lkdtm_usercopy.c
index 1dd611423d8b..df6ac985fbb5 100644
--- a/drivers/misc/lkdtm_usercopy.c
+++ b/drivers/misc/lkdtm_usercopy.c
@@ -5,6 +5,7 @@
 #include "lkdtm.h"
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mman.h>
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index 6c062b8251d2..d52139635b67 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -20,6 +20,7 @@
  */
 #include <linux/clk.h>
 #include <linux/slab.h>
+#include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mtd/partitions.h>
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 2a59139f520b..9be82c4e14a4 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/coredump.h>
 #include <linux/slab.h>
+#include <linux/sched/task_stack.h>
 
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 2c95257fa4da..92c00a13b28b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -36,6 +36,7 @@
 #include <linux/coredump.h>
 #include <linux/sched.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/task_stack.h>
 #include <linux/cred.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 222873bb689c..6103a8149ccd 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -15,6 +15,8 @@
 #include <linux/fs.h>
 #include <linux/stat.h>
 #include <linux/sched.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/errno.h>
@@ -35,7 +37,6 @@
 #include <linux/elf-fdpic.h>
 #include <linux/elfcore.h>
 #include <linux/coredump.h>
-#include <linux/sched/coredump.h>
 #include <linux/dax.h>
 
 #include <linux/uaccess.h>
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 9b2917a30294..2edcefc0a294 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -19,6 +19,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/errno.h>
diff --git a/fs/coredump.c b/fs/coredump.c
index c74ab43b8383..592683711c64 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -18,6 +18,7 @@
 #include <linux/coredump.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/utsname.h>
 #include <linux/pid_namespace.h>
 #include <linux/module.h>
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 698d51a0eea3..c8240a12c42d 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -3,6 +3,8 @@
 
 #include <linux/user.h>
 #include <linux/bug.h>
+#include <linux/sched/task_stack.h>
+
 #include <asm/elf.h>
 #include <uapi/linux/elfcore.h>
 
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index a5f98d53d732..9b7dd59fe28d 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_PERF_REGS_H
 #define _LINUX_PERF_REGS_H
 
+#include <linux/sched/task_stack.h>
+
 struct perf_regs {
 	__u64		abi;
 	struct pt_regs	*regs;
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
new file mode 100644
index 000000000000..933cd49824c2
--- /dev/null
+++ b/include/linux/sched/task_stack.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_TASK_STACK_H
+#define _LINUX_SCHED_TASK_STACK_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_TASK_STACK_H */
diff --git a/init/main.c b/init/main.c
index 47956b22add1..c2d337a136d1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -77,6 +77,7 @@
 #include <linux/elevator.h>
 #include <linux/sched_clock.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/context_tracking.h>
 #include <linux/random.h>
 #include <linux/list.h>
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index e9fdb5203de5..c04917cad1bf 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -11,6 +11,8 @@
 
 #include <linux/perf_event.h>
 #include <linux/slab.h>
+#include <linux/sched/task_stack.h>
+
 #include "internal.h"
 
 struct callchain_cpus_entries {
diff --git a/kernel/exit.c b/kernel/exit.c
index e53408d156df..771c33fc9952 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -10,6 +10,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/capability.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 0af64d5d8b73..c87b6f03c710 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -19,6 +19,7 @@
 #include <linux/sched/numa_balancing.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 3caaaa04b92e..2984fb0f0257 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -47,6 +47,7 @@
 #include <linux/uio.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 
 #include <linux/uaccess.h>
 #include <asm/sections.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6b7155ae5c33..4e2fec3f12a0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -15,6 +15,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 
 #include <linux/u64_stats_sync.h>
 #include <linux/kernel_stat.h>
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e15185c28de5..65f61077ad50 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -18,6 +18,7 @@
 #include <linux/compat.h>
 #include <linux/coredump.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/seccomp.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
diff --git a/kernel/signal.c b/kernel/signal.c
index 25d099fd80f7..e6d470a5f75a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -17,6 +17,7 @@
 #include <linux/sched/user.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/fs.h>
 #include <linux/tty.h>
 #include <linux/binfmts.h>
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2a1abbaca10e..1d68b5b7ad41 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -2,6 +2,7 @@
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
  *
  */
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 8c28cbd7e104..17afb0430161 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -13,6 +13,7 @@
 #include <linux/debugobjects.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 942adf13418d..b157b46cc9a6 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -17,6 +17,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
+#include <linux/sched/task_stack.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
 #include <linux/sched/task.h>
diff --git a/lib/syscall.c b/lib/syscall.c
index 63239e097b13..17d5ff5fa6a3 100644
--- a/lib/syscall.c
+++ b/lib/syscall.c
@@ -1,5 +1,6 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/export.h>
 #include <asm/syscall.h>
 
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index d99312ed7c22..98b27195e38b 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/printk.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/slab.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index a3970573359e..26c874e90b12 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -75,6 +75,7 @@
 #include <linux/list.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
 #include <linux/jiffies.h>
 #include <linux/delay.h>
 #include <linux/export.h>
diff --git a/mm/util.c b/mm/util.c
index 14f4e13323e2..656dc5e37a87 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -6,6 +6,7 @@
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
 #include <linux/security.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
-- 
GitLab


From dfc3401a33086a3fd465468e171ea0e82430569b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 23:15:21 +0100
Subject: [PATCH 505/898] sched/headers: Prepare to move the 'root_task_group'
 declaration to <linux/sched/autogroup.h>

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/init_task.h | 1 +
 kernel/sched/sched.h      | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 3a85d61f7614..452c9799318c 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -12,6 +12,7 @@
 #include <linux/securebits.h>
 #include <linux/seqlock.h>
 #include <linux/rbtree.h>
+#include <linux/sched/autogroup.h>
 #include <net/net_namespace.h>
 #include <linux/sched/rt.h>
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4e2fec3f12a0..b1f1c8443837 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1,5 +1,6 @@
 
 #include <linux/sched.h>
+#include <linux/sched/autogroup.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/rt.h>
-- 
GitLab


From e6d930b4e0115eb0732eec0efb11c3b09a8000fc Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 23:43:50 +0100
Subject: [PATCH 506/898] signals: Prepare to split out <linux/signal_types.h>
 from <linux/signal.h>

Introduce dummy header and add dependencies to places that will depend on it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/include/asm/abi.h  | 2 ++
 include/linux/signal.h       | 3 +--
 include/linux/signal_types.h | 7 +++++++
 3 files changed, 10 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/signal_types.h

diff --git a/arch/mips/include/asm/abi.h b/arch/mips/include/asm/abi.h
index 940760844e2f..dba7f4b6bebf 100644
--- a/arch/mips/include/asm/abi.h
+++ b/arch/mips/include/asm/abi.h
@@ -9,6 +9,8 @@
 #ifndef _ASM_ABI_H
 #define _ASM_ABI_H
 
+#include <linux/signal_types.h>
+
 #include <asm/signal.h>
 #include <asm/siginfo.h>
 #include <asm/vdso.h>
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 5308304993be..d1c2b05a7a55 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -1,9 +1,8 @@
 #ifndef _LINUX_SIGNAL_H
 #define _LINUX_SIGNAL_H
 
-#include <linux/list.h>
 #include <linux/bug.h>
-#include <uapi/linux/signal.h>
+#include <linux/signal_types.h>
 
 struct task_struct;
 
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
new file mode 100644
index 000000000000..28799c88f490
--- /dev/null
+++ b/include/linux/signal_types.h
@@ -0,0 +1,7 @@
+#ifndef _LINUX_SIGNAL_TYPES_H
+#define _LINUX_SIGNAL_TYPES_H
+
+#include <linux/list.h>
+#include <uapi/linux/signal.h>
+
+#endif /* _LINUX_SIGNAL_TYPES_H */
-- 
GitLab


From f361bf4a66c9bfabace46f6ff5d97005c9b524fe Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 23:47:37 +0100
Subject: [PATCH 507/898] sched/headers: Prepare for the reduction of
 <linux/sched.h>'s signal API dependency

Instead of including the full <linux/signal.h>, we are going to include the
types-only <linux/signal_types.h> header in <linux/sched.h>, to further
decouple the scheduler header from the signal headers.

This means that various files which relied on the full <linux/signal.h> need
to be updated to gain an explicit dependency on it.

Update the code that relies on sched.h's inclusion of the <linux/signal.h> header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/kernel/sys_compat.c          | 1 +
 drivers/gpu/drm/i915/i915_gem_request.c | 1 +
 drivers/isdn/mISDN/stack.c              | 2 ++
 fs/btrfs/extent-tree.c                  | 1 +
 fs/btrfs/free-space-cache.c             | 1 +
 fs/buffer.c                             | 1 +
 fs/ceph/addr.c                          | 1 +
 fs/dax.c                                | 1 +
 fs/ioctl.c                              | 2 ++
 fs/iomap.c                              | 2 ++
 fs/ocfs2/super.c                        | 1 +
 include/linux/sched.h                   | 1 +
 include/linux/sched/signal.h            | 1 +
 kernel/pid_namespace.c                  | 1 +
 mm/page-writeback.c                     | 1 +
 15 files changed, 18 insertions(+)

diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index abaf582fc7a8..8b8bbd3eaa52 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -21,6 +21,7 @@
 #include <linux/compat.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index df3fef393dbe..e7c3c0318ff6 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -26,6 +26,7 @@
 #include <linux/dma-fence-array.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/signal.h>
 
 #include "i915_drv.h"
 
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index b324474c0c12..696f22fd5ab4 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -19,6 +19,8 @@
 #include <linux/mISDNif.h>
 #include <linux/kthread.h>
 #include <linux/sched.h>
+#include <linux/signal.h>
+
 #include "core.h"
 
 static u_int	*debug;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c35b96633554..dad395b0b9fc 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 1a131f7d6c1b..493a654b6012 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -18,6 +18,7 @@
 
 #include <linux/pagemap.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/math64.h>
 #include <linux/ratelimit.h>
diff --git a/fs/buffer.c b/fs/buffer.c
index 28484b3ebc98..9196f2a270da 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/syscalls.h>
 #include <linux/fs.h>
 #include <linux/iomap.h>
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f297a9e18642..1a3e1b40799a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/pagevec.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/signal.h>
 
 #include "super.h"
 #include "mds_client.h"
diff --git a/fs/dax.c b/fs/dax.c
index 7436c98b92c8..de622d4282a6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -27,6 +27,7 @@
 #include <linux/pagevec.h>
 #include <linux/pmem.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uio.h>
 #include <linux/vmstat.h>
 #include <linux/pfn_t.h>
diff --git a/fs/ioctl.c b/fs/ioctl.c
index cb9b02940805..569db68d02b3 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -15,6 +15,8 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/falloc.h>
+#include <linux/sched/signal.h>
+
 #include "internal.h"
 
 #include <asm/ioctls.h>
diff --git a/fs/iomap.c b/fs/iomap.c
index 0f85f2410605..3ca1a8e44135 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -26,6 +26,8 @@
 #include <linux/buffer_head.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/dax.h>
+#include <linux/sched/signal.h>
+
 #include "internal.h"
 
 /*
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a24e42f95341..ca1646fbcaef 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -42,6 +42,7 @@
 #include <linux/seq_file.h>
 #include <linux/quotaops.h>
 #include <linux/cleancache.h>
+#include <linux/signal.h>
 
 #define CREATE_TRACE_POINTS
 #include "ocfs2_trace.h"
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8ae7b3d85658..ea05116bc3c2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -36,6 +36,7 @@ struct sched_param {
 #include <linux/signal.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
+#include <linux/signal_types.h>
 #include <linux/pid.h>
 #include <linux/percpu.h>
 #include <linux/topology.h>
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 0f4e9f4a43fd..7e10a7824523 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_SCHED_SIGNAL_H
 #define _LINUX_SCHED_SIGNAL_H
 
+#include <linux/signal.h>
 #include <linux/cred.h>
 #include <linux/sched.h>
 #include <linux/sched/jobctl.h>
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 7c8367854dc4..de461aa0bf9a 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -20,6 +20,7 @@
 #include <linux/reboot.h>
 #include <linux/export.h>
 #include <linux/sched/task.h>
+#include <linux/sched/signal.h>
 
 struct pid_cache {
 	int nr_ids;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 26a60818a8fc..d8ac2a7fb9e7 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,6 +36,7 @@
 #include <linux/pagevec.h>
 #include <linux/timer.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/signal.h>
 #include <linux/mm_inline.h>
 #include <trace/events/writeback.h>
 
-- 
GitLab


From 2e58f173ab89b29a1373088b8727133dbf7322b0 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 00:12:19 +0100
Subject: [PATCH 508/898] mm/headers, sched/headers: Prepare to split
 <linux/mm_types_task.h> out of <linux/mm_types.h>

We are going to separate all the MM types that are embedded directly in 'struct task_struct'
into the new <linux/mm_types_task.h> header.

Create a new <linux/mm_types_task.h> that only contains some includes from mm_types.h itself.

This should be trivially correct and easy to bisect to.

(This patch does not materially move the types yet.)

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm_types.h      |  6 +++---
 include/linux/mm_types_task.h | 10 ++++++++++
 2 files changed, 13 insertions(+), 3 deletions(-)
 create mode 100644 include/linux/mm_types_task.h

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 137797cd7b50..6daaf0a51968 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1,9 +1,9 @@
 #ifndef _LINUX_MM_TYPES_H
 #define _LINUX_MM_TYPES_H
 
+#include <linux/mm_types_task.h>
+
 #include <linux/auxvec.h>
-#include <linux/types.h>
-#include <linux/threads.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/rbtree.h>
@@ -13,7 +13,7 @@
 #include <linux/uprobes.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
-#include <asm/page.h>
+
 #include <asm/mmu.h>
 
 #ifndef AT_VECTOR_SIZE_ARCH
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
new file mode 100644
index 000000000000..2419d302f03c
--- /dev/null
+++ b/include/linux/mm_types_task.h
@@ -0,0 +1,10 @@
+#ifndef _LINUX_MM_TYPES_TASK_H
+#define _LINUX_MM_TYPES_TASK_H
+
+#include <linux/types.h>
+#include <linux/threads.h>
+#include <linux/atomic.h>
+
+#include <asm/page.h>
+
+#endif /* _LINUX_MM_TYPES_TASK_H */
-- 
GitLab


From 589ee62844e042b0b7d19ef57fb4cff77f3ca294 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 00:16:44 +0100
Subject: [PATCH 509/898] sched/headers: Prepare to remove the
 <linux/mm_types.h> dependency from <linux/sched.h>

Update code that relied on sched.h including various MM types for them.

This will allow us to remove the <linux/mm_types.h> include from <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/a.out-core.h              | 1 +
 arch/alpha/include/asm/mmu_context.h             | 2 ++
 arch/arc/mm/tlb.c                                | 2 ++
 arch/arm/include/asm/mmu_context.h               | 2 ++
 arch/arm/include/asm/tlbflush.h                  | 7 ++++---
 arch/arm/kernel/suspend.c                        | 1 +
 arch/arm/kernel/swp_emulate.c                    | 1 +
 arch/arm/mm/idmap.c                              | 1 +
 arch/arm64/include/asm/mmu_context.h             | 1 +
 arch/arm64/kernel/traps.c                        | 1 +
 arch/avr32/include/asm/mmu_context.h             | 2 ++
 arch/blackfin/include/asm/mmu_context.h          | 2 ++
 arch/blackfin/kernel/flat.c                      | 1 +
 arch/blackfin/kernel/process.c                   | 1 +
 arch/blackfin/mm/sram-alloc.c                    | 2 ++
 arch/cris/arch-v10/mm/tlb.c                      | 2 ++
 arch/cris/arch-v32/mm/tlb.c                      | 1 +
 arch/cris/include/asm/pgtable.h                  | 2 +-
 arch/cris/mm/tlb.c                               | 2 ++
 arch/h8300/kernel/traps.c                        | 1 +
 arch/hexagon/include/asm/mmu_context.h           | 2 ++
 arch/hexagon/kernel/smp.c                        | 1 +
 arch/ia64/include/asm/mmu_context.h              | 1 +
 arch/ia64/include/asm/pgtable.h                  | 2 +-
 arch/ia64/sn/kernel/sn2/sn2_smp.c                | 1 +
 arch/m32r/include/asm/mmu_context.h              | 2 ++
 arch/m68k/include/asm/a.out-core.h               | 1 +
 arch/m68k/include/asm/mmu_context.h              | 1 +
 arch/metag/include/asm/mmu_context.h             | 1 +
 arch/microblaze/include/asm/mmu_context_mm.h     | 2 ++
 arch/microblaze/mm/pgtable.c                     | 1 +
 arch/mips/include/asm/elf.h                      | 2 ++
 arch/mips/include/asm/mmu_context.h              | 2 ++
 arch/mips/kernel/smp.c                           | 2 +-
 arch/mips/math-emu/dsemul.c                      | 1 +
 arch/mips/mm/ioremap.c                           | 1 +
 arch/mn10300/include/asm/mmu_context.h           | 2 ++
 arch/mn10300/kernel/smp.c                        | 2 +-
 arch/mn10300/mm/tlb-smp.c                        | 2 +-
 arch/nios2/include/asm/mmu_context.h             | 2 ++
 arch/nios2/kernel/process.c                      | 1 +
 arch/powerpc/kernel/io-workarounds.c             | 2 +-
 arch/powerpc/kvm/e500_mmu_host.c                 | 2 +-
 arch/powerpc/lib/feature-fixups.c                | 1 +
 arch/powerpc/mm/hash_utils_64.c                  | 2 +-
 arch/powerpc/mm/pgtable-book3s64.c               | 2 ++
 arch/powerpc/mm/pgtable-hash64.c                 | 2 ++
 arch/powerpc/mm/pgtable-radix.c                  | 2 +-
 arch/powerpc/mm/slb.c                            | 2 ++
 arch/s390/include/asm/elf.h                      | 2 +-
 arch/s390/include/asm/mmu_context.h              | 1 +
 arch/s390/kernel/processor.c                     | 1 +
 arch/s390/kvm/gaccess.c                          | 2 ++
 arch/s390/kvm/priv.c                             | 2 ++
 arch/score/include/asm/mmu_context.h             | 2 ++
 arch/score/kernel/traps.c                        | 1 +
 arch/sh/include/asm/mmu_context.h                | 2 ++
 arch/sparc/include/asm/mmu_context_64.h          | 2 ++
 arch/sparc/include/asm/pgtable_64.h              | 3 +++
 arch/sparc/kernel/asm-offsets.c                  | 1 +
 arch/sparc/kernel/traps_32.c                     | 1 +
 arch/sparc/mm/tsb.c                              | 2 ++
 arch/tile/include/asm/mmu_context.h              | 2 ++
 arch/um/include/asm/mmu_context.h                | 2 ++
 arch/um/kernel/exec.c                            | 2 +-
 arch/um/kernel/reboot.c                          | 1 +
 arch/um/kernel/skas/process.c                    | 3 ++-
 arch/x86/entry/vsyscall/vsyscall_64.c            | 1 +
 arch/x86/events/core.c                           | 2 +-
 arch/x86/include/asm/a.out-core.h                | 2 ++
 arch/x86/include/asm/mpx.h                       | 2 ++
 arch/x86/mm/mpx.c                                | 1 +
 arch/x86/um/syscalls_64.c                        | 1 +
 arch/x86/xen/mmu.c                               | 2 +-
 arch/xtensa/include/asm/mmu_context.h            | 1 +
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c | 2 ++
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c  | 2 ++
 drivers/infiniband/hw/cxgb3/iwch_provider.c      | 2 +-
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h           | 2 +-
 drivers/media/v4l2-core/videobuf-dma-sg.c        | 2 +-
 fs/binfmt_misc.c                                 | 2 +-
 fs/kernfs/file.c                                 | 2 +-
 include/drm/drm_mm.h                             | 1 +
 include/linux/init_task.h                        | 1 +
 include/linux/sched/mm.h                         | 1 +
 kernel/sched/debug.c                             | 2 +-
 kernel/sched/fair.c                              | 2 +-
 kernel/signal.c                                  | 2 +-
 lib/is_single_threaded.c                         | 1 +
 89 files changed, 125 insertions(+), 25 deletions(-)

diff --git a/arch/alpha/include/asm/a.out-core.h b/arch/alpha/include/asm/a.out-core.h
index 9e33e92e524c..1610d078b064 100644
--- a/arch/alpha/include/asm/a.out-core.h
+++ b/arch/alpha/include/asm/a.out-core.h
@@ -15,6 +15,7 @@
 #ifdef __KERNEL__
 
 #include <linux/user.h>
+#include <linux/mm_types.h>
 
 /*
  * Fill in the user structure for an ECOFF core dump.
diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h
index 4c51c05333c6..384bd47b5187 100644
--- a/arch/alpha/include/asm/mmu_context.h
+++ b/arch/alpha/include/asm/mmu_context.h
@@ -7,6 +7,8 @@
  * Copyright (C) 1996, Linus Torvalds
  */
 
+#include <linux/mm_types.h>
+
 #include <asm/machvec.h>
 #include <asm/compiler.h>
 #include <asm-generic/mm_hooks.h>
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index bdb295e09160..d0126fdfe2d8 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -53,6 +53,8 @@
 
 #include <linux/module.h>
 #include <linux/bug.h>
+#include <linux/mm_types.h>
+
 #include <asm/arcregs.h>
 #include <asm/setup.h>
 #include <asm/mmu_context.h>
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 3cc14dd8587c..7f303295ef19 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -15,7 +15,9 @@
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 #include <linux/preempt.h>
+
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index def9e570199f..1897b5196fb5 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -10,6 +10,10 @@
 #ifndef _ASMARM_TLBFLUSH_H
 #define _ASMARM_TLBFLUSH_H
 
+#ifndef __ASSEMBLY__
+# include <linux/mm_types.h>
+#endif
+
 #ifdef CONFIG_MMU
 
 #include <asm/glue.h>
@@ -644,9 +648,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 #elif defined(CONFIG_SMP)	/* !CONFIG_MMU */
 
 #ifndef __ASSEMBLY__
-
-#include <linux/mm_types.h>
-
 static inline void local_flush_tlb_all(void)									{ }
 static inline void local_flush_tlb_mm(struct mm_struct *mm)							{ }
 static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)			{ }
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index 9a2f882a0a2d..ef794c799cb6 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -1,5 +1,6 @@
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
 
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 853221f81104..3bda08bee674 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -23,6 +23,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/syscalls.h>
 #include <linux/perf_event.h>
 
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index c1a48f88764e..3e511bec69b8 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -1,6 +1,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
 
 #include <asm/cputype.h>
 #include <asm/idmap.h>
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 3c9f7d18a7e6..3257895a9b5e 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -26,6 +26,7 @@
 #include <linux/compiler.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/mm_types.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index bdbd0c3febf4..e52be6aa44ee 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -33,6 +33,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/syscalls.h>
+#include <linux/mm_types.h>
 
 #include <asm/atomic.h>
 #include <asm/bug.h>
diff --git a/arch/avr32/include/asm/mmu_context.h b/arch/avr32/include/asm/mmu_context.h
index 27ff23407100..cd87abba8db7 100644
--- a/arch/avr32/include/asm/mmu_context.h
+++ b/arch/avr32/include/asm/mmu_context.h
@@ -12,6 +12,8 @@
 #ifndef __ASM_AVR32_MMU_CONTEXT_H
 #define __ASM_AVR32_MMU_CONTEXT_H
 
+#include <linux/mm_types.h>
+
 #include <asm/tlbflush.h>
 #include <asm/sysreg.h>
 #include <asm-generic/mm_hooks.h>
diff --git a/arch/blackfin/include/asm/mmu_context.h b/arch/blackfin/include/asm/mmu_context.h
index 15b16d3e8de8..0ce6de873b27 100644
--- a/arch/blackfin/include/asm/mmu_context.h
+++ b/arch/blackfin/include/asm/mmu_context.h
@@ -9,6 +9,8 @@
 
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
+
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
diff --git a/arch/blackfin/kernel/flat.c b/arch/blackfin/kernel/flat.c
index a88daddbf074..b5b658449616 100644
--- a/arch/blackfin/kernel/flat.c
+++ b/arch/blackfin/kernel/flat.c
@@ -6,6 +6,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 #include <linux/flat.h>
 
 #define FLAT_BFIN_RELOC_TYPE_16_BIT 0
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index b691ef875a40..89d5162d4ca6 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -15,6 +15,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/mm_types.h>
 #include <linux/tick.h>
 #include <linux/fs.h>
 #include <linux/err.h>
diff --git a/arch/blackfin/mm/sram-alloc.c b/arch/blackfin/mm/sram-alloc.c
index 1f3b3ef3e103..d2a96c2c02a3 100644
--- a/arch/blackfin/mm/sram-alloc.c
+++ b/arch/blackfin/mm/sram-alloc.c
@@ -19,6 +19,8 @@
 #include <linux/spinlock.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
+
 #include <asm/blackfin.h>
 #include <asm/mem_map.h>
 #include "blackfin_sram.h"
diff --git a/arch/cris/arch-v10/mm/tlb.c b/arch/cris/arch-v10/mm/tlb.c
index 21d78c599bab..3225d38bdaea 100644
--- a/arch/cris/arch-v10/mm/tlb.c
+++ b/arch/cris/arch-v10/mm/tlb.c
@@ -10,6 +10,8 @@
  *
  */
 
+#include <linux/mm_types.h>
+
 #include <asm/tlb.h>
 #include <asm/mmu_context.h>
 #include <arch/svinto.h>
diff --git a/arch/cris/arch-v32/mm/tlb.c b/arch/cris/arch-v32/mm/tlb.c
index c030d020660a..bc3de5b5e27c 100644
--- a/arch/cris/arch-v32/mm/tlb.c
+++ b/arch/cris/arch-v32/mm/tlb.c
@@ -6,6 +6,7 @@
  * Authors:   Bjorn Wesen <bjornw@axis.com>
  *            Tobias Anderberg <tobiasa@axis.com>, CRISv32 port.
  */
+#include <linux/mm_types.h>
 
 #include <asm/tlb.h>
 #include <asm/mmu_context.h>
diff --git a/arch/cris/include/asm/pgtable.h b/arch/cris/include/asm/pgtable.h
index ceefc314d64d..2a3210ba4c72 100644
--- a/arch/cris/include/asm/pgtable.h
+++ b/arch/cris/include/asm/pgtable.h
@@ -9,7 +9,7 @@
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <asm/mmu.h>
 #endif
 #include <arch/pgtable.h>
diff --git a/arch/cris/mm/tlb.c b/arch/cris/mm/tlb.c
index b7f8de576777..8413741cfa0f 100644
--- a/arch/cris/mm/tlb.c
+++ b/arch/cris/mm/tlb.c
@@ -9,6 +9,8 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/mm_types.h>
+
 #include <asm/tlb.h>
 
 #define D(x)
diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c
index ee7e3ce40d78..e47a9e0dc278 100644
--- a/arch/h8300/kernel/traps.c
+++ b/arch/h8300/kernel/traps.c
@@ -17,6 +17,7 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/mm_types.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
diff --git a/arch/hexagon/include/asm/mmu_context.h b/arch/hexagon/include/asm/mmu_context.h
index d423d2e73c30..d8a071afdd1d 100644
--- a/arch/hexagon/include/asm/mmu_context.h
+++ b/arch/hexagon/include/asm/mmu_context.h
@@ -21,6 +21,8 @@
 #ifndef _ASM_MMU_CONTEXT_H
 #define _ASM_MMU_CONTEXT_H
 
+#include <linux/mm_types.h>
+
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index c02a6455839e..1f63e91a353b 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -29,6 +29,7 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/cpu.h>
+#include <linux/mm_types.h>
 
 #include <asm/time.h>    /*  timer_interrupt  */
 #include <asm/hexagon_vm.h>
diff --git a/arch/ia64/include/asm/mmu_context.h b/arch/ia64/include/asm/mmu_context.h
index 7f2a456603cb..9b99368633b5 100644
--- a/arch/ia64/include/asm/mmu_context.h
+++ b/arch/ia64/include/asm/mmu_context.h
@@ -26,6 +26,7 @@
 #include <linux/compiler.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 #include <linux/spinlock.h>
 
 #include <asm/processor.h>
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 9f3ed9ee8f13..384794e665fc 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -147,7 +147,7 @@
 
 # ifndef __ASSEMBLY__
 
-#include <linux/sched.h>	/* for mm_struct */
+#include <linux/sched/mm.h>	/* for mm_struct */
 #include <linux/bitops.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index c98dc965fe82..b73b0ebf8214 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -13,6 +13,7 @@
 #include <linux/spinlock.h>
 #include <linux/threads.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
diff --git a/arch/m32r/include/asm/mmu_context.h b/arch/m32r/include/asm/mmu_context.h
index 9fc78fc44445..1230b7050d8e 100644
--- a/arch/m32r/include/asm/mmu_context.h
+++ b/arch/m32r/include/asm/mmu_context.h
@@ -12,6 +12,8 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/atomic.h>
+#include <linux/mm_types.h>
+
 #include <asm/pgalloc.h>
 #include <asm/mmu.h>
 #include <asm/tlbflush.h>
diff --git a/arch/m68k/include/asm/a.out-core.h b/arch/m68k/include/asm/a.out-core.h
index f6bfc1d63ff6..ae91ea6bb303 100644
--- a/arch/m68k/include/asm/a.out-core.h
+++ b/arch/m68k/include/asm/a.out-core.h
@@ -16,6 +16,7 @@
 
 #include <linux/user.h>
 #include <linux/elfcore.h>
+#include <linux/mm_types.h>
 
 /*
  * fill in the user structure for an a.out core dump
diff --git a/arch/m68k/include/asm/mmu_context.h b/arch/m68k/include/asm/mmu_context.h
index dc3be991d634..4a6ae6dffa34 100644
--- a/arch/m68k/include/asm/mmu_context.h
+++ b/arch/m68k/include/asm/mmu_context.h
@@ -2,6 +2,7 @@
 #define __M68K_MMU_CONTEXT_H
 
 #include <asm-generic/mm_hooks.h>
+#include <linux/mm_types.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/arch/metag/include/asm/mmu_context.h b/arch/metag/include/asm/mmu_context.h
index ae2a71b5e0be..2e0312748197 100644
--- a/arch/metag/include/asm/mmu_context.h
+++ b/arch/metag/include/asm/mmu_context.h
@@ -9,6 +9,7 @@
 #include <asm/cacheflush.h>
 
 #include <linux/io.h>
+#include <linux/mm_types.h>
 
 static inline void enter_lazy_tlb(struct mm_struct *mm,
 				  struct task_struct *tsk)
diff --git a/arch/microblaze/include/asm/mmu_context_mm.h b/arch/microblaze/include/asm/mmu_context_mm.h
index d68647746448..99472d2ca340 100644
--- a/arch/microblaze/include/asm/mmu_context_mm.h
+++ b/arch/microblaze/include/asm/mmu_context_mm.h
@@ -12,6 +12,8 @@
 #define _ASM_MICROBLAZE_MMU_CONTEXT_H
 
 #include <linux/atomic.h>
+#include <linux/mm_types.h>
+
 #include <asm/bitops.h>
 #include <asm/mmu.h>
 #include <asm-generic/mm_hooks.h>
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index cc732fe357ad..4c0599239915 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -31,6 +31,7 @@
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 #include <linux/init.h>
+#include <linux/mm_types.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index 7a6c466e5f2a..0eb1a75be105 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -10,6 +10,8 @@
 
 #include <linux/auxvec.h>
 #include <linux/fs.h>
+#include <linux/mm_types.h>
+
 #include <uapi/linux/elf.h>
 
 #include <asm/current.h>
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 2abf94f72c0a..da2004cef2d5 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -13,8 +13,10 @@
 
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 #include <linux/smp.h>
 #include <linux/slab.h>
+
 #include <asm/cacheflush.h>
 #include <asm/dsemul.h>
 #include <asm/hazards.h>
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 8c60a296294c..6e71130549ea 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -28,7 +28,7 @@
 #include <linux/export.h>
 #include <linux/time.h>
 #include <linux/timex.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/cpumask.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index c4469ff4a996..6664908514b3 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -1,5 +1,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
 
 #include <asm/branch.h>
 #include <asm/cacheflush.h>
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index 1f189627440f..1986e09fb457 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/mm_types.h>
 #include <asm/cacheflush.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>
diff --git a/arch/mn10300/include/asm/mmu_context.h b/arch/mn10300/include/asm/mmu_context.h
index 75dbe696f830..d2034f5e6eda 100644
--- a/arch/mn10300/include/asm/mmu_context.h
+++ b/arch/mn10300/include/asm/mmu_context.h
@@ -23,6 +23,8 @@
 #define _ASM_MMU_CONTEXT_H
 
 #include <linux/atomic.h>
+#include <linux/mm_types.h>
+
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm-generic/mm_hooks.h>
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index d924f7a79708..35d2c3fe6f76 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -21,7 +21,7 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/task.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
diff --git a/arch/mn10300/mm/tlb-smp.c b/arch/mn10300/mm/tlb-smp.c
index 9a39ea9031d4..085f2bb691ac 100644
--- a/arch/mn10300/mm/tlb-smp.c
+++ b/arch/mn10300/mm/tlb-smp.c
@@ -20,7 +20,7 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <asm/tlbflush.h>
diff --git a/arch/nios2/include/asm/mmu_context.h b/arch/nios2/include/asm/mmu_context.h
index 294b4b1f81d4..78ab3dacf579 100644
--- a/arch/nios2/include/asm/mmu_context.h
+++ b/arch/nios2/include/asm/mmu_context.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_NIOS2_MMU_CONTEXT_H
 #define _ASM_NIOS2_MMU_CONTEXT_H
 
+#include <linux/mm_types.h>
+
 #include <asm-generic/mm_hooks.h>
 
 extern void mmu_context_init(void);
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 869a4d59de32..509e7855e8dc 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -17,6 +17,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/mm_types.h>
 #include <linux/tick.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index 5f8613ceb97f..a582e0d42525 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -12,7 +12,7 @@
 #undef DEBUG
 
 #include <linux/kernel.h>
-#include <linux/sched.h>	/* for init_mm */
+#include <linux/sched/mm.h>	/* for init_mm */
 
 #include <asm/io.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index b0333cc737dd..0fda4230f6c0 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -25,7 +25,7 @@
 #include <linux/highmem.h>
 #include <linux/log2.h>
 #include <linux/uaccess.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/rwsem.h>
 #include <linux/vmalloc.h>
 #include <linux/hugetlb.h>
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 043415f0bdb1..f3917705c686 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/init.h>
+#include <linux/sched/mm.h>
 #include <asm/cputable.h>
 #include <asm/code-patching.h>
 #include <asm/page.h>
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 12d679df50bd..c554768b1fa2 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -23,7 +23,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
 #include <linux/sysctl.h>
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index b798ff674fab..5fcb3dd74c13 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -8,6 +8,8 @@
  */
 
 #include <linux/sched.h>
+#include <linux/mm_types.h>
+
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
index c23e286a6b8f..8b85a14b08ea 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -10,6 +10,8 @@
  */
 
 #include <linux/sched.h>
+#include <linux/mm_types.h>
+
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index feeda90cd06d..2a590a98e652 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -8,7 +8,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 48fc28bab544..5e01b2ece1d0 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -22,6 +22,8 @@
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
 #include <linux/compiler.h>
+#include <linux/mm_types.h>
+
 #include <asm/udbg.h>
 #include <asm/code-patching.h>
 
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 83aaefed2a7b..1d48880b3cc1 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -132,7 +132,7 @@ typedef s390_fp_regs compat_elf_fpregset_t;
 typedef s390_compat_regs compat_elf_gregset_t;
 
 #include <linux/compat.h>
-#include <linux/sched.h>	/* for task_struct */
+#include <linux/sched/mm.h>	/* for task_struct */
 #include <asm/mmu_context.h>
 
 #include <asm/vdso.h>
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 9b828c073176..6e31d87fb669 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -9,6 +9,7 @@
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
+#include <linux/mm_types.h>
 #include <asm/tlbflush.h>
 #include <asm/ctl_reg.h>
 
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index bc2b60dcb178..bf7854523831 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/seq_file.h>
+#include <linux/mm_types.h>
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <asm/diag.h>
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 4492c9363178..d55c829a5944 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -6,7 +6,9 @@
  */
 
 #include <linux/vmalloc.h>
+#include <linux/mm_types.h>
 #include <linux/err.h>
+
 #include <asm/pgtable.h>
 #include <asm/gmap.h>
 #include "kvm-s390.h"
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index fb4b494cde9b..64b6a309f2c4 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -15,6 +15,8 @@
 #include <linux/gfp.h>
 #include <linux/errno.h>
 #include <linux/compat.h>
+#include <linux/mm_types.h>
+
 #include <asm/asm-offsets.h>
 #include <asm/facility.h>
 #include <asm/current.h>
diff --git a/arch/score/include/asm/mmu_context.h b/arch/score/include/asm/mmu_context.h
index 2644577c96e8..073f95d350de 100644
--- a/arch/score/include/asm/mmu_context.h
+++ b/arch/score/include/asm/mmu_context.h
@@ -3,7 +3,9 @@
 
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 #include <linux/slab.h>
+
 #include <asm-generic/mm_hooks.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index 8a54d320fb41..fe68de6c746c 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -26,6 +26,7 @@
 #include <linux/extable.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/mm_types.h>
 
 #include <asm/cacheflush.h>
 #include <asm/irq.h>
diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h
index 35ffdd081d26..eb6ac3c10c44 100644
--- a/arch/sh/include/asm/mmu_context.h
+++ b/arch/sh/include/asm/mmu_context.h
@@ -11,6 +11,8 @@
 #include <cpu/mmu_context.h>
 #include <asm/tlbflush.h>
 #include <linux/uaccess.h>
+#include <linux/mm_types.h>
+
 #include <asm/io.h>
 #include <asm-generic/mm_hooks.h>
 
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index d0317993e947..22fede6eba11 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -6,6 +6,8 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/spinlock.h>
+#include <linux/mm_types.h>
+
 #include <asm/spitfire.h>
 #include <asm-generic/mm_hooks.h>
 
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 7932a4a37817..56e49c8f770d 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -878,6 +878,9 @@ static inline unsigned long pud_pfn(pud_t pud)
 #define pte_offset_map			pte_index
 #define pte_unmap(pte)			do { } while (0)
 
+/* We cannot include <linux/mm_types.h> at this point yet: */
+extern struct mm_struct init_mm;
+
 /* Actual page table PTE updates.  */
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm,
diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c
index f76389a32342..3f09e1c83f58 100644
--- a/arch/sparc/kernel/asm-offsets.c
+++ b/arch/sparc/kernel/asm-offsets.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 // #include <linux/mm.h>
 #include <linux/kbuild.h>
 
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 26740a2f285d..2de72a49308a 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -11,6 +11,7 @@
 
 #include <linux/sched.h>  /* for jiffies */
 #include <linux/sched/debug.h>
+#include <linux/mm_types.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/smp.h>
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 23479c3d39f0..0a04811f06b7 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -6,6 +6,8 @@
 #include <linux/kernel.h>
 #include <linux/preempt.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
+
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
diff --git a/arch/tile/include/asm/mmu_context.h b/arch/tile/include/asm/mmu_context.h
index f67753db1f78..45a4b4c424cf 100644
--- a/arch/tile/include/asm/mmu_context.h
+++ b/arch/tile/include/asm/mmu_context.h
@@ -16,6 +16,8 @@
 #define _ASM_TILE_MMU_CONTEXT_H
 
 #include <linux/smp.h>
+#include <linux/mm_types.h>
+
 #include <asm/setup.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 1a60e1328e2f..94ac2739918c 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -7,6 +7,8 @@
 #define __UM_MMU_CONTEXT_H
 
 #include <linux/sched.h>
+#include <linux/mm_types.h>
+
 #include <asm/mmu.h>
 
 extern void uml_setup_stubs(struct mm_struct *mm);
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 31968677a0d0..a43d42bf0a86 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -7,7 +7,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/ptrace.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/slab.h>
diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c
index 0bc921cee0b1..71f3e9217cf2 100644
--- a/arch/um/kernel/reboot.c
+++ b/arch/um/kernel/reboot.c
@@ -5,6 +5,7 @@
 
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
+#include <linux/sched/mm.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/oom.h>
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index ddecf326dab2..3a952a4f7965 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -4,8 +4,9 @@
  */
 
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/task_stack.h>
+
 #include <as-layout.h>
 #include <kern.h>
 #include <os.h>
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index df91fb393a01..ce1d7534fa53 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -28,6 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/timer.h>
 #include <linux/sched/signal.h>
+#include <linux/mm_types.h>
 #include <linux/syscalls.h>
 #include <linux/ratelimit.h>
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 2ecc0e97772b..349d4d17aa7f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -20,7 +20,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/kdebug.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/clock.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
index 7a15588e45d4..7d3ece8bfb61 100644
--- a/arch/x86/include/asm/a.out-core.h
+++ b/arch/x86/include/asm/a.out-core.h
@@ -17,6 +17,8 @@
 
 #include <linux/user.h>
 #include <linux/elfcore.h>
+#include <linux/mm_types.h>
+
 #include <asm/debugreg.h>
 
 /*
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index 0b416d4cf73b..a0d662be4c5b 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -2,6 +2,8 @@
 #define _ASM_X86_MPX_H
 
 #include <linux/types.h>
+#include <linux/mm_types.h>
+
 #include <asm/ptrace.h>
 #include <asm/insn.h>
 
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index c98079684bdb..5126dfd52b18 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -7,6 +7,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
 #include <linux/syscalls.h>
 #include <linux/sched/sysctl.h>
 
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index e6552275320b..10d907098c26 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/uaccess.h>
 #include <asm/prctl.h> /* XXX This should get the constants from libc */
 #include <os.h>
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f6740b5b1738..37cb5aad71de 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -38,7 +38,7 @@
  *
  * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
  */
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/highmem.h>
 #include <linux/debugfs.h>
 #include <linux/bug.h>
diff --git a/arch/xtensa/include/asm/mmu_context.h b/arch/xtensa/include/asm/mmu_context.h
index 04c8ebdc4517..f7e186dfc4e4 100644
--- a/arch/xtensa/include/asm/mmu_context.h
+++ b/arch/xtensa/include/asm/mmu_context.h
@@ -17,6 +17,7 @@
 
 #include <linux/stringify.h>
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 
 #include <asm/vectors.h>
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index d83de985e88c..6acc4313363e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -23,6 +23,8 @@
 
 #include <linux/printk.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
+
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 #include "cik_regs.h"
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index fa32c32fa1c2..a9b9882a9a77 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -23,6 +23,8 @@
 
 #include <linux/printk.h>
 #include <linux/slab.h>
+#include <linux/mm_types.h>
+
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 #include "vi_structs.h"
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 318ec5267bdf..86ecd3ea6a4b 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -37,7 +37,7 @@
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/list.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/spinlock.h>
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index d19662f635b1..5846c47c8d55 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -37,7 +37,7 @@
 #include <linux/idr.h>
 #include <linux/completion.h>
 #include <linux/netdevice.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/inet.h>
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 36bd904946bd..0b5c43f7e020 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -21,7 +21,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 9b4688ab1d8e..bee1a36bc2ec 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -12,7 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/magic.h>
 #include <linux/binfmts.h>
 #include <linux/slab.h>
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 35043a8c4529..8e4dc7ab584c 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -13,7 +13,7 @@
 #include <linux/slab.h>
 #include <linux/poll.h>
 #include <linux/pagemap.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/fsnotify.h>
 
 #include "kernfs-internal.h"
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index d81b0ba9921f..2ef16bf25826 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -40,6 +40,7 @@
 #include <linux/bug.h>
 #include <linux/rbtree.h>
 #include <linux/kernel.h>
+#include <linux/mm_types.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #ifdef CONFIG_DRM_DEBUG_MM
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 452c9799318c..f6841c19c913 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -15,6 +15,7 @@
 #include <linux/sched/autogroup.h>
 #include <net/net_namespace.h>
 #include <linux/sched/rt.h>
+#include <linux/mm_types.h>
 
 #include <asm/thread_info.h>
 
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 1cf7941bb946..d32e3932b2e3 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -2,6 +2,7 @@
 #define _LINUX_SCHED_MM_H
 
 #include <linux/sched.h>
+#include <linux/mm_types.h>
 #include <linux/gfp.h>
 
 #endif /* _LINUX_SCHED_MM_H */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 109adc0e9cb9..e865d8bfb881 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/proc_fs.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 11e0ab57748a..3e88b35ac157 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -20,7 +20,7 @@
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  */
 
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/topology.h>
 
 #include <linux/latencytop.h>
diff --git a/kernel/signal.c b/kernel/signal.c
index e6d470a5f75a..2008aa999976 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -13,7 +13,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/user.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c
index 9745cfffcb69..8d4678edcc0e 100644
--- a/lib/is_single_threaded.c
+++ b/lib/is_single_threaded.c
@@ -10,6 +10,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 
 /*
  * Returns true if the task does not share ->mm with another thread/process.
-- 
GitLab


From 9164bb4a18dfa592cd0aca455ea57abf89ca4526 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 01:20:53 +0100
Subject: [PATCH 510/898] sched/headers: Prepare to move 'init_task' and
 'init_thread_union' from <linux/sched.h> to <linux/sched/task.h>

Update all usage sites first.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/kernel/setup.c     | 1 +
 arch/arm64/mm/kasan_init.c    | 1 +
 arch/frv/mm/init.c            | 1 +
 arch/metag/mm/init.c          | 1 +
 arch/nios2/kernel/setup.c     | 1 +
 arch/powerpc/kernel/paca.c    | 1 +
 arch/um/kernel/skas/process.c | 1 +
 arch/um/kernel/um_arch.c      | 2 ++
 arch/x86/kernel/cpu/common.c  | 1 +
 arch/x86/mm/kasan_init_64.c   | 1 +
 fs/namespace.c                | 2 ++
 include/linux/sched/signal.h  | 1 +
 init/init_task.c              | 1 +
 kernel/delayacct.c            | 1 +
 lib/is_single_threaded.c      | 1 +
 mm/vmacache.c                 | 1 +
 16 files changed, 18 insertions(+)

diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 952e2c0dabd5..42274bda0ccb 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -42,6 +42,7 @@
 #include <linux/of_fdt.h>
 #include <linux/efi.h>
 #include <linux/psci.h>
+#include <linux/sched/task.h>
 #include <linux/mm.h>
 
 #include <asm/acpi.h>
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 201d918e7575..55d1e9205543 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) "kasan: " fmt
 #include <linux/kasan.h>
 #include <linux/kernel.h>
+#include <linux/sched/task.h>
 #include <linux/memblock.h>
 #include <linux/start_kernel.h>
 #include <linux/mm.h>
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index 88a159743528..328f0a292316 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -18,6 +18,7 @@
 
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/pagemap.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index c0ec116b3993..188d4d9fbed4 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -12,6 +12,7 @@
 #include <linux/percpu.h>
 #include <linux/memblock.h>
 #include <linux/initrd.h>
+#include <linux/sched/task.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c
index a3fa80d1aacc..6e57ffa5db27 100644
--- a/arch/nios2/kernel/setup.c
+++ b/arch/nios2/kernel/setup.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/console.h>
 #include <linux/bootmem.h>
 #include <linux/initrd.h>
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index fa20060ff7a5..dfc479df9634 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -10,6 +10,7 @@
 #include <linux/smp.h>
 #include <linux/export.h>
 #include <linux/memblock.h>
+#include <linux/sched/task.h>
 
 #include <asm/lppaca.h>
 #include <asm/paca.h>
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index 3a952a4f7965..d4dbf08722d6 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/task.h>
 
 #include <as-layout.h>
 #include <kern.h>
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index e8175a8aa22c..4b85acd4020c 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -11,7 +11,9 @@
 #include <linux/string.h>
 #include <linux/utsname.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/kmsg_dump.h>
+
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c7e2ca966386..f2fd8fefc589 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -9,6 +9,7 @@
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/task.h>
 #include <linux/init.h>
 #include <linux/kprobes.h>
 #include <linux/kgdb.h>
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 0493c17b8a51..8d63d7a104c3 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -4,6 +4,7 @@
 #include <linux/kdebug.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/vmalloc.h>
 
 #include <asm/tlbflush.h>
diff --git a/fs/namespace.c b/fs/namespace.c
index 131cd7b94f47..cc1375eff88c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -25,6 +25,8 @@
 #include <linux/magic.h>
 #include <linux/bootmem.h>
 #include <linux/task_work.h>
+#include <linux/sched/task.h>
+
 #include "pnode.h"
 #include "internal.h"
 
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 7e10a7824523..320eca0446cd 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -5,5 +5,6 @@
 #include <linux/cred.h>
 #include <linux/sched.h>
 #include <linux/sched/jobctl.h>
+#include <linux/sched/task.h>
 
 #endif /* _LINUX_SCHED_SIGNAL_H */
diff --git a/init/init_task.c b/init/init_task.c
index 53d4ce942a88..66787e30a419 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -4,6 +4,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/task.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 660549656991..c94135fc2698 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/taskstats.h>
 #include <linux/time.h>
diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c
index 8d4678edcc0e..9c7d89df40ed 100644
--- a/lib/is_single_threaded.c
+++ b/lib/is_single_threaded.c
@@ -10,6 +10,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/sched/mm.h>
 
 /*
diff --git a/mm/vmacache.c b/mm/vmacache.c
index 4355d34c68a6..7ffa0ee341b5 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -2,6 +2,7 @@
  * Copyright (C) 2014 Davidlohr Bueso.
  */
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/mm.h>
 #include <linux/vmacache.h>
 
-- 
GitLab


From b2d091031075ac9a1598e3cc3a29c28f02e64c0d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 01:27:20 +0100
Subject: [PATCH 511/898] sched/headers: Prepare to use <linux/rcuupdate.h>
 instead of <linux/rculist.h> in <linux/sched.h>

We don't actually need the full rculist.h header in sched.h anymore,
we will be able to include the smaller rcupdate.h header instead.

But first update code that relied on the implicit header inclusion.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/kvm/book3s_mmu_hpte.c  | 1 +
 arch/x86/kvm/irq_comm.c             | 2 ++
 arch/x86/kvm/page_track.c           | 2 ++
 drivers/md/bcache/btree.c           | 2 ++
 drivers/misc/vmw_vmci/vmci_event.c  | 1 +
 drivers/nvme/target/admin-cmd.c     | 2 ++
 drivers/nvme/target/core.c          | 2 ++
 drivers/s390/cio/qdio_thinint.c     | 2 ++
 drivers/scsi/libfc/fc_disc.c        | 2 ++
 drivers/scsi/libfc/fc_rport.c       | 2 ++
 include/linux/dmar.h                | 2 +-
 include/linux/pid.h                 | 2 +-
 include/linux/rhashtable.h          | 2 +-
 include/linux/sched/signal.h        | 1 +
 include/net/bluetooth/hci_core.h    | 2 ++
 kernel/trace/trace_events_hist.c    | 1 +
 kernel/trace/trace_events_trigger.c | 1 +
 kernel/trace/trace_kprobe.c         | 1 +
 kernel/trace/trace_uprobe.c         | 1 +
 lib/bug.c                           | 1 +
 lib/rhashtable.c                    | 1 +
 net/mac80211/mesh_plink.c           | 2 ++
 net/mac802154/llsec.c               | 2 ++
 security/apparmor/policy.c          | 1 +
 security/tomoyo/domain.c            | 2 ++
 security/tomoyo/group.c             | 2 ++
 security/tomoyo/util.c              | 2 ++
 27 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 5a1ab1250a05..905a934c1ef4 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -21,6 +21,7 @@
 #include <linux/kvm_host.h>
 #include <linux/hash.h>
 #include <linux/slab.h>
+#include <linux/rculist.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index b96d3893f121..6825cd36d13b 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -23,6 +23,8 @@
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/rculist.h>
+
 #include <trace/events/kvm.h>
 
 #include <asm/msidef.h>
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 4a1c13eaa518..37942e419c32 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -14,6 +14,8 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/rculist.h>
+
 #include <asm/kvm_host.h>
 #include <asm/kvm_page_track.h>
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 384559af310e..450d0e848ae4 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -33,6 +33,8 @@
 #include <linux/random.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
+#include <linux/rculist.h>
+
 #include <trace/events/bcache.h>
 
 /*
diff --git a/drivers/misc/vmw_vmci/vmci_event.c b/drivers/misc/vmw_vmci/vmci_event.c
index 8449516d6ac6..84258a48029d 100644
--- a/drivers/misc/vmw_vmci/vmci_event.c
+++ b/drivers/misc/vmw_vmci/vmci_event.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/rculist.h>
 
 #include "vmci_driver.h"
 #include "vmci_event.h"
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 94e524fea568..a7bcff45f437 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -13,6 +13,8 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/module.h>
+#include <linux/rculist.h>
+
 #include <generated/utsrelease.h>
 #include <asm/unaligned.h>
 #include "nvmet.h"
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 5267ce20c12d..11b0a0a5f661 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -14,6 +14,8 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/rculist.h>
+
 #include "nvmet.h"
 
 static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 8ad98a902a91..c61164f4528e 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -8,6 +8,8 @@
 #include <linux/slab.h>
 #include <linux/kernel_stat.h>
 #include <linux/atomic.h>
+#include <linux/rculist.h>
+
 #include <asm/debug.h>
 #include <asm/qdio.h>
 #include <asm/airq.h>
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 6103231104da..fd501f8dbb11 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -36,6 +36,8 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/export.h>
+#include <linux/rculist.h>
+
 #include <asm/unaligned.h>
 
 #include <scsi/fc/fc_gs.h>
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index c991f3b822f8..b44c3136eb51 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -65,6 +65,8 @@
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/export.h>
+#include <linux/rculist.h>
+
 #include <asm/unaligned.h>
 
 #include <scsi/libfc.h>
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index e9bc9292bd3a..e8ffba1052d3 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -26,7 +26,7 @@
 #include <linux/msi.h>
 #include <linux/irqreturn.h>
 #include <linux/rwsem.h>
-#include <linux/rcupdate.h>
+#include <linux/rculist.h>
 
 struct acpi_dmar_header;
 
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 298ead5512e5..4d179316e431 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_PID_H
 #define _LINUX_PID_H
 
-#include <linux/rcupdate.h>
+#include <linux/rculist.h>
 
 enum pid_type
 {
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index f2e12a845910..092292b6675e 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -25,7 +25,7 @@
 #include <linux/list_nulls.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
-#include <linux/rcupdate.h>
+#include <linux/rculist.h>
 
 /*
  * The end of the chain is marked with a special nulls marks which has
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 320eca0446cd..c6958a53fef3 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_SCHED_SIGNAL_H
 #define _LINUX_SCHED_SIGNAL_H
 
+#include <linux/rculist.h>
 #include <linux/signal.h>
 #include <linux/cred.h>
 #include <linux/sched.h>
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 90708f68cc02..95ccc1eef558 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -26,6 +26,8 @@
 #define __HCI_CORE_H
 
 #include <linux/leds.h>
+#include <linux/rculist.h>
+
 #include <net/bluetooth/hci.h>
 #include <net/bluetooth/hci_sock.h>
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index f3a960ed75a1..1c21d0e2a145 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/stacktrace.h>
+#include <linux/rculist.h>
 
 #include "tracing_map.h"
 #include "trace.h"
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 6721a1e89f39..f2ac9d44f6c4 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -22,6 +22,7 @@
 #include <linux/ctype.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/rculist.h>
 
 #include "trace.h"
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index eadd96ef772f..5f688cc724f0 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -20,6 +20,7 @@
 
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/rculist.h>
 
 #include "trace_probe.h"
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index f4379e772171..a7581fec9681 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -24,6 +24,7 @@
 #include <linux/uprobes.h>
 #include <linux/namei.h>
 #include <linux/string.h>
+#include <linux/rculist.h>
 
 #include "trace_probe.h"
 
diff --git a/lib/bug.c b/lib/bug.c
index bc3656e944d2..06edbbef0623 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -45,6 +45,7 @@
 #include <linux/kernel.h>
 #include <linux/bug.h>
 #include <linux/sched.h>
+#include <linux/rculist.h>
 
 extern const struct bug_entry __start___bug_table[], __stop___bug_table[];
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index c5b9b9351cec..f8635fd57442 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/log2.h>
 #include <linux/sched.h>
+#include <linux/rculist.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index fcba70e57073..953d71e784a9 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -9,6 +9,8 @@
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/random.h>
+#include <linux/rculist.h>
+
 #include "ieee80211_i.h"
 #include "rate.h"
 #include "mesh.h"
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index 6a3e1c2181d3..1e1c9b20bab7 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -18,6 +18,8 @@
 #include <linux/bug.h>
 #include <linux/completion.h>
 #include <linux/ieee802154.h>
+#include <linux/rculist.h>
+
 #include <crypto/aead.h>
 #include <crypto/skcipher.h>
 
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 462c5d36b871..def1fbd6bdfd 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -77,6 +77,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/cred.h>
+#include <linux/rculist.h>
 #include <linux/user_namespace.h>
 
 #include "include/apparmor.h"
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index 838ffa78cfda..00d223e9fb37 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -5,8 +5,10 @@
  */
 
 #include "common.h"
+
 #include <linux/binfmts.h>
 #include <linux/slab.h>
+#include <linux/rculist.h>
 
 /* Variables definitions.*/
 
diff --git a/security/tomoyo/group.c b/security/tomoyo/group.c
index 50092534ec54..944ad77d8fba 100644
--- a/security/tomoyo/group.c
+++ b/security/tomoyo/group.c
@@ -5,6 +5,8 @@
  */
 
 #include <linux/slab.h>
+#include <linux/rculist.h>
+
 #include "common.h"
 
 /**
diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c
index 5fe3679137ae..848317fea704 100644
--- a/security/tomoyo/util.c
+++ b/security/tomoyo/util.c
@@ -5,6 +5,8 @@
  */
 
 #include <linux/slab.h>
+#include <linux/rculist.h>
+
 #include "common.h"
 
 /* Lock for protecting policy. */
-- 
GitLab


From f719ff9bcee2a422647790f12d53d3755f47c727 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 10:57:33 +0100
Subject: [PATCH 512/898] sched/headers: Prepare to move the
 task_lock()/unlock() APIs to <linux/sched/task.h>

But first update the code that uses these facilities with the
new header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/math-emu/dsemul.c                | 1 +
 block/blk-ioc.c                            | 1 +
 block/ioprio.c                             | 1 +
 drivers/staging/android/ion/ion.c          | 1 +
 drivers/staging/lustre/lustre/ptlrpc/sec.c | 1 +
 fs/proc/internal.h                         | 1 +
 fs/proc/proc_net.c                         | 1 +
 fs/proc_namespace.c                        | 2 ++
 include/linux/cpuset.h                     | 1 +
 ipc/namespace.c                            | 1 +
 kernel/cgroup/cpuset.c                     | 1 +
 kernel/sched/debug.c                       | 1 +
 kernel/utsname.c                           | 1 +
 mm/mempolicy.c                             | 1 +
 mm/mmu_context.c                           | 1 +
 net/core/net_namespace.c                   | 2 ++
 net/core/netclassid_cgroup.c               | 2 ++
 net/core/netprio_cgroup.c                  | 2 ++
 18 files changed, 22 insertions(+)

diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 6664908514b3..b6bfd3625369 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -1,6 +1,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/mm_types.h>
+#include <linux/sched/task.h>
 
 #include <asm/branch.h>
 #include <asm/cacheflush.h>
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index b12f9c87b4c3..6bfa39675337 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -7,6 +7,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
+#include <linux/sched/task.h>
 
 #include "blk.h"
 
diff --git a/block/ioprio.c b/block/ioprio.c
index 4b9ab8367dda..0c47a00f92a8 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -27,6 +27,7 @@
 #include <linux/blkdev.h>
 #include <linux/capability.h>
 #include <linux/sched/user.h>
+#include <linux/sched/task.h>
 #include <linux/syscalls.h>
 #include <linux/security.h>
 #include <linux/pid_namespace.h>
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 2c3ffbcbd621..f45115fce4eb 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -36,6 +36,7 @@
 #include <linux/debugfs.h>
 #include <linux/dma-buf.h>
 #include <linux/idr.h>
+#include <linux/sched/task.h>
 
 #include "ion.h"
 #include "ion_priv.h"
diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec.c b/drivers/staging/lustre/lustre/ptlrpc/sec.c
index 49f34fd655c3..366f2ce20f5e 100644
--- a/drivers/staging/lustre/lustre/ptlrpc/sec.c
+++ b/drivers/staging/lustre/lustre/ptlrpc/sec.c
@@ -40,6 +40,7 @@
 #include <linux/crypto.h>
 #include <linux/cred.h>
 #include <linux/key.h>
+#include <linux/sched/task.h>
 
 #include "../include/obd.h"
 #include "../include/obd_class.h"
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 550e8b183abe..26a6daf02185 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -15,6 +15,7 @@
 #include <linux/atomic.h>
 #include <linux/binfmts.h>
 #include <linux/sched/coredump.h>
+#include <linux/sched/task.h>
 
 struct ctl_table_header;
 struct mempolicy;
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index ffd72a6c6e04..5cbc65d7a1e1 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/mount.h>
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 3f1190d18991..b5713fefb4c1 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -10,6 +10,8 @@
 #include <linux/nsproxy.h>
 #include <linux/security.h>
 #include <linux/fs_struct.h>
+#include <linux/sched/task.h>
+
 #include "proc/internal.h" /* only for get_proc_task() in ->open() */
 
 #include "pnode.h"
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index c608c39cb161..611fce58d670 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -10,6 +10,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/topology.h>
+#include <linux/sched/task.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/mm.h>
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 1f1d713ac19c..b4d80f9f7246 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -14,6 +14,7 @@
 #include <linux/mount.h>
 #include <linux/user_namespace.h>
 #include <linux/proc_ns.h>
+#include <linux/sched/task.h>
 
 #include "util.h"
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index a5c46db2855c..0f41292be0fb 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -45,6 +45,7 @@
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/seq_file.h>
 #include <linux/security.h>
 #include <linux/slab.h>
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e865d8bfb881..38f019324f1a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -12,6 +12,7 @@
 
 #include <linux/proc_fs.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 06585ad296ff..913fe4336d2b 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -17,6 +17,7 @@
 #include <linux/cred.h>
 #include <linux/user_namespace.h>
 #include <linux/proc_ns.h>
+#include <linux/sched/task.h>
 
 static struct ucounts *inc_uts_namespaces(struct user_namespace *ns)
 {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 18e0105810df..75b2745bac41 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -75,6 +75,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/numa_balancing.h>
+#include <linux/sched/task.h>
 #include <linux/nodemask.h>
 #include <linux/cpuset.h>
 #include <linux/slab.h>
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index 8888b124a386..3e612ae748e9 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -6,6 +6,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/mmu_context.h>
 #include <linux/export.h>
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 3c4bbec39713..652468ff65b7 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -16,6 +16,8 @@
 #include <linux/export.h>
 #include <linux/user_namespace.h>
 #include <linux/net_namespace.h>
+#include <linux/sched/task.h>
+
 #include <net/sock.h>
 #include <net/netlink.h>
 #include <net/net_namespace.h>
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 11fce17274f6..6ae56037bb13 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -12,6 +12,8 @@
 #include <linux/slab.h>
 #include <linux/cgroup.h>
 #include <linux/fdtable.h>
+#include <linux/sched/task.h>
+
 #include <net/cls_cgroup.h>
 #include <net/sock.h>
 
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 756637dc7a57..0f9275ee5595 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -20,6 +20,8 @@
 #include <linux/cgroup.h>
 #include <linux/rcupdate.h>
 #include <linux/atomic.h>
+#include <linux/sched/task.h>
+
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
 #include <net/sock.h>
-- 
GitLab


From 32ef5517c298042ed58408545f475df43afe1f24 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 11:48:36 +0100
Subject: [PATCH 513/898] sched/headers: Prepare to move cputime functionality
 from <linux/sched.h> into <linux/sched/cputime.h>

Introduce a trivial, mostly empty <linux/sched/cputime.h> header
to prepare for the moving of cputime functionality out of sched.h.

Update all code that relies on these facilities.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/kernel/osf_sys.c    | 1 +
 arch/ia64/kernel/time.c        | 2 +-
 arch/powerpc/kernel/time.c     | 2 +-
 arch/s390/kernel/idle.c        | 2 +-
 arch/s390/kernel/vtime.c       | 2 +-
 arch/x86/kernel/apm_32.c       | 1 +
 arch/x86/kvm/hyperv.c          | 2 ++
 drivers/isdn/mISDN/stack.c     | 1 +
 drivers/s390/cio/cio.c         | 2 +-
 fs/binfmt_elf.c                | 1 +
 fs/binfmt_elf_fdpic.c          | 1 +
 fs/proc/array.c                | 1 +
 fs/proc/stat.c                 | 2 +-
 include/linux/sched/cputime.h  | 7 +++++++
 kernel/acct.c                  | 2 ++
 kernel/delayacct.c             | 1 +
 kernel/exit.c                  | 1 +
 kernel/fork.c                  | 1 +
 kernel/sched/cputime.c         | 2 +-
 kernel/sched/sched.h           | 1 +
 kernel/signal.c                | 1 +
 kernel/sys.c                   | 1 +
 kernel/time/itimer.c           | 1 +
 kernel/time/posix-cpu-timers.c | 1 +
 kernel/tsacct.c                | 1 +
 25 files changed, 33 insertions(+), 7 deletions(-)
 create mode 100644 include/linux/sched/cputime.h

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 73446baa632e..0b961093ca5c 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -14,6 +14,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 144f9db7a876..aa7be020a904 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -22,7 +22,7 @@
 #include <linux/timex.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/platform_device.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 
 #include <asm/machvec.h>
 #include <asm/delay.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 37833c5dc274..07b90725855e 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -58,7 +58,7 @@
 #include <linux/clk-provider.h>
 #include <linux/suspend.h>
 #include <linux/rtc.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 #include <asm/trace.h>
 
 #include <asm/io.h>
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index fb07a70820af..9340b2a07935 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -12,7 +12,7 @@
 #include <linux/notifier.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include "entry.h"
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 31bd96e81167..c14fc9029912 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -6,7 +6,7 @@
  */
 
 #include <linux/kernel_stat.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/timex.h>
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index dc04b30cbd60..5a414545e8a3 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -219,6 +219,7 @@
 #include <linux/init.h>
 #include <linux/time.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/cputime.h>
 #include <linux/pm.h>
 #include <linux/capability.h>
 #include <linux/device.h>
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index f701d4430727..ebae57ac5902 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -28,6 +28,8 @@
 
 #include <linux/kvm_host.h>
 #include <linux/highmem.h>
+#include <linux/sched/cputime.h>
+
 #include <asm/apicdef.h>
 #include <trace/events/kvm.h>
 
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 696f22fd5ab4..8b7faea2ddf8 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -19,6 +19,7 @@
 #include <linux/mISDNif.h>
 #include <linux/kthread.h>
 #include <linux/sched.h>
+#include <linux/sched/cputime.h>
 #include <linux/signal.h>
 
 #include "core.h"
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index de6fccc13124..1b350665c823 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -29,7 +29,7 @@
 #include <asm/chpid.h>
 #include <asm/airq.h>
 #include <asm/isc.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 #include <asm/fcx.h>
 #include <asm/nmi.h>
 #include <asm/crw.h>
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 92c00a13b28b..5075fd5c62c8 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -37,6 +37,7 @@
 #include <linux/sched.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 #include <linux/cred.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 6103a8149ccd..cf93a4fad012 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/errno.h>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index f3169b58af38..88c355574aa0 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -63,6 +63,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/sched/task.h>
+#include <linux/sched/cputime.h>
 #include <linux/proc_fs.h>
 #include <linux/ioport.h>
 #include <linux/uaccess.h>
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index b95556e036bb..bd4e55f4aa20 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/irqnr.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 #include <linux/tick.h>
 
 #ifndef arch_irq_stat_cpu
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
new file mode 100644
index 000000000000..6ed4fe43de28
--- /dev/null
+++ b/include/linux/sched/cputime.h
@@ -0,0 +1,7 @@
+#ifndef _LINUX_SCHED_CPUTIME_H
+#define _LINUX_SCHED_CPUTIME_H
+
+#include <linux/sched/signal.h>
+#include <linux/cputime.h>
+
+#endif /* _LINUX_SCHED_CPUTIME_H */
diff --git a/kernel/acct.c b/kernel/acct.c
index ca9cb55b5855..5b1284370367 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -56,6 +56,8 @@
 #include <linux/syscalls.h>
 #include <linux/mount.h>
 #include <linux/uaccess.h>
+#include <linux/sched/cputime.h>
+
 #include <asm/div64.h>
 #include <linux/blkdev.h> /* sector_div */
 #include <linux/pid_namespace.h>
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index c94135fc2698..4a1c33416b6a 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -15,6 +15,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/cputime.h>
 #include <linux/slab.h>
 #include <linux/taskstats.h>
 #include <linux/time.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 771c33fc9952..e126ebf2400c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -11,6 +11,7 @@
 #include <linux/sched/stat.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/capability.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index c87b6f03c710..916e78004b8f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -20,6 +20,7 @@
 #include <linux/sched/stat.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
 #include <linux/unistd.h>
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 54031fa681e2..f3778e2b46c8 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -4,7 +4,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/static_key.h>
 #include <linux/context_tracking.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 #include "sched.h"
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b1f1c8443837..76e3af3f39f4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -17,6 +17,7 @@
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 
 #include <linux/u64_stats_sync.h>
 #include <linux/kernel_stat.h>
diff --git a/kernel/signal.c b/kernel/signal.c
index 2008aa999976..7e59ebc2c25e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -18,6 +18,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 #include <linux/fs.h>
 #include <linux/tty.h>
 #include <linux/binfmts.h>
diff --git a/kernel/sys.c b/kernel/sys.c
index 7f1ecd2e41c1..7ff6d1b10cec 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -55,6 +55,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/task.h>
+#include <linux/sched/cputime.h>
 #include <linux/rcupdate.h>
 #include <linux/uidgid.h>
 #include <linux/cred.h>
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index f6b961c5e58c..087d6a1279b8 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -11,6 +11,7 @@
 #include <linux/syscalls.h>
 #include <linux/time.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/cputime.h>
 #include <linux/posix-timers.h>
 #include <linux/hrtimer.h>
 #include <trace/events/timer.h>
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index a2475a9f57d8..4513ad16a253 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -3,6 +3,7 @@
  */
 
 #include <linux/sched/signal.h>
+#include <linux/sched/cputime.h>
 #include <linux/posix-timers.h>
 #include <linux/errno.h>
 #include <linux/math64.h>
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index d9a03b80b75d..370724b45391 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/cputime.h>
 #include <linux/tsacct_kern.h>
 #include <linux/acct.h>
 #include <linux/jiffies.h>
-- 
GitLab


From 3905f9ad455e0fd2ddb557566c5561b4a3027c07 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 12:07:04 +0100
Subject: [PATCH 514/898] sched/headers: Prepare to move sched_info_on() and
 force_schedstat_enabled() from <linux/sched.h> to <linux/sched/stat.h>

But first update usage sites with the new header dependency.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kvm/cpuid.c | 2 ++
 arch/x86/kvm/x86.c   | 2 ++
 fs/proc/base.c       | 1 +
 kernel/latencytop.c  | 1 +
 kernel/profile.c     | 2 ++
 5 files changed, 8 insertions(+)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 1d155cc56629..efde6cc50875 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,6 +16,8 @@
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <linux/sched/stat.h>
+
 #include <asm/processor.h>
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b2a4b11274b0..1faf620a6fdc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -54,6 +54,8 @@
 #include <linux/pvclock_gtod.h>
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
+#include <linux/sched/stat.h>
+
 #include <trace/events/kvm.h>
 
 #include <asm/debugreg.h>
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5914fed3712d..2dae60075f6e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -89,6 +89,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/stat.h>
 #include <linux/flex_array.h>
 #include <linux/posix-timers.h>
 #ifdef CONFIG_HARDWALL
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 545839b838d6..96b4179cee6a 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -56,6 +56,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/stat.h>
 #include <linux/list.h>
 #include <linux/stacktrace.h>
 
diff --git a/kernel/profile.c b/kernel/profile.c
index f67ce0aa6bc4..9aa2a4445b0d 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -25,6 +25,8 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/stat.h>
+
 #include <asm/sections.h>
 #include <asm/irq_regs.h>
 #include <asm/ptrace.h>
-- 
GitLab


From 5c2c5c5514393e31859439ef83a34051d7c68332 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:24:31 +0100
Subject: [PATCH 515/898] sched/headers, vfs/execve: Prepare to move the
 do_execve*() prototypes from <linux/sched.h> to <linux/binfmts.h>

But first update the usage sites with the new header dependency.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 init/main.c   | 1 +
 kernel/kmod.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/init/main.c b/init/main.c
index c2d337a136d1..ca9f53fb4125 100644
--- a/init/main.c
+++ b/init/main.c
@@ -15,6 +15,7 @@
 #include <linux/extable.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
+#include <linux/binfmts.h>
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
 #include <linux/stackprotector.h>
diff --git a/kernel/kmod.c b/kernel/kmod.c
index ac5f5c2d098d..563f97e2be36 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/binfmts.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
 #include <linux/kmod.h>
-- 
GitLab


From 3f8c24529b42fc5044c2a44bdb8ba69aec2bee37 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:31:22 +0100
Subject: [PATCH 516/898] sched/headers: Prepare to move kstack_end() from
 <linux/sched.h> to <linux/sched/task_stack.h>

But first update the usage sites with the new header dependency.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/m32r/kernel/traps.c       | 2 ++
 arch/metag/kernel/stacktrace.c | 1 +
 arch/openrisc/kernel/traps.c   | 1 +
 arch/um/kernel/sysrq.c         | 1 +
 arch/xtensa/kernel/traps.c     | 1 +
 mm/slab.c                      | 1 +
 6 files changed, 7 insertions(+)

diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index 7c05bb393597..832bb2bb29bd 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -15,7 +15,9 @@
 #include <linux/stddef.h>
 #include <linux/ptrace.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
+
 #include <asm/page.h>
 #include <asm/processor.h>
 
diff --git a/arch/metag/kernel/stacktrace.c b/arch/metag/kernel/stacktrace.c
index 4f806d66a58c..91ffc4b75c33 100644
--- a/arch/metag/kernel/stacktrace.c
+++ b/arch/metag/kernel/stacktrace.c
@@ -1,6 +1,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 
 #include <asm/stacktrace.h>
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 2354ab88d948..803e9e756f77 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -23,6 +23,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/extable.h>
 #include <linux/kmod.h>
diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c
index 34ae555c3e70..a76295f7ede9 100644
--- a/arch/um/kernel/sysrq.c
+++ b/arch/um/kernel/sysrq.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/sysrq.h>
 #include <asm/stacktrace.h>
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index d8bb2e62393e..c82c43bff296 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/stringify.h>
diff --git a/mm/slab.c b/mm/slab.c
index bd63450a9b16..807d86c76908 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -116,6 +116,7 @@
 #include	<linux/kmemcheck.h>
 #include	<linux/memory.h>
 #include	<linux/prefetch.h>
+#include	<linux/sched/task_stack.h>
 
 #include	<net/sock.h>
 
-- 
GitLab


From 61855b6b03df9b6a15bd265c2c3ae7b5e23da312 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:35:41 +0100
Subject: [PATCH 517/898] sched/headers: Prepare to move exit_files() and
 exit_itimers() from <linux/sched.h> to <linux/sched/task.h>

But first update the usage site.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/time/posix-timers.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1e6623d76750..50a6a47020de 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/mutex.h>
+#include <linux/sched/task.h>
 
 #include <linux/uaccess.h>
 #include <linux/list.h>
-- 
GitLab


From 1777e4635507265ba53d8dc4cd248e7d7c306fa0 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:47:12 +0100
Subject: [PATCH 518/898] sched/headers: Prepare to move _init() prototypes
 from <linux/sched.h> to <linux/sched/init.h>

But first introduce a trivial header and update usage sites.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/ia64/kernel/setup.c   | 1 +
 arch/m32r/kernel/traps.c   | 1 +
 arch/s390/kernel/setup.c   | 1 +
 include/linux/cpu.h        | 2 ++
 include/linux/sched/init.h | 6 ++++++
 init/main.c                | 1 +
 kernel/sched/sched.h       | 1 +
 7 files changed, 13 insertions(+)
 create mode 100644 include/linux/sched/init.h

diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index b2b4f5216180..63bef6fc0f3e 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -29,6 +29,7 @@
 #include <linux/bootmem.h>
 #include <linux/console.h>
 #include <linux/delay.h>
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/reboot.h>
 #include <linux/sched.h>
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index 832bb2bb29bd..647dd94a0c39 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -17,6 +17,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/mm.h>
+#include <linux/cpu.h>
 
 #include <asm/page.h>
 #include <asm/processor.h>
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 3de07004c02e..911dc0b49be0 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -19,6 +19,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
 #include <linux/mm.h>
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 21f9c74496e7..f92081234afd 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -30,6 +30,8 @@ struct cpu {
 
 extern void boot_cpu_init(void);
 extern void boot_cpu_state_init(void);
+extern void cpu_init(void);
+extern void trap_init(void);
 
 extern int register_cpu(struct cpu *cpu, int num);
 extern struct device *get_cpu_device(unsigned cpu);
diff --git a/include/linux/sched/init.h b/include/linux/sched/init.h
new file mode 100644
index 000000000000..15e46313e55e
--- /dev/null
+++ b/include/linux/sched/init.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SCHED_INIT_H
+#define _LINUX_SCHED_INIT_H
+
+#include <linux/sched.h>
+
+#endif /* _LINUX_SCHED_INIT_H */
diff --git a/init/main.c b/init/main.c
index ca9f53fb4125..eae2f15657c6 100644
--- a/init/main.c
+++ b/init/main.c
@@ -63,6 +63,7 @@
 #include <linux/device.h>
 #include <linux/kthread.h>
 #include <linux/sched.h>
+#include <linux/sched/init.h>
 #include <linux/signal.h>
 #include <linux/idr.h>
 #include <linux/kgdb.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 76e3af3f39f4..5cbf92214ad8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -18,6 +18,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/init.h>
 
 #include <linux/u64_stats_sync.h>
 #include <linux/kernel_stat.h>
-- 
GitLab


From 0881e7bd341e2158b314596bcf2059e88e68f04e Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 15:30:50 +0100
Subject: [PATCH 519/898] sched/headers: Prepare to move the
 get_task_struct()/put_task_struct() and related APIs from <linux/sched.h> to
 <linux/sched/task.h>

But first update usage sites with the new header dependency.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/dma/dmatest.c                         | 1 +
 drivers/gpu/drm/etnaviv/etnaviv_gem.c         | 1 +
 drivers/infiniband/core/umem_odp.c            | 1 +
 drivers/infiniband/hw/mlx4/main.c             | 1 +
 drivers/infiniband/hw/mlx5/main.c             | 1 +
 drivers/md/persistent-data/dm-block-manager.c | 1 +
 drivers/misc/cxl/main.c                       | 2 ++
 drivers/net/xen-netback/interface.c           | 1 +
 drivers/oprofile/buffer_sync.c                | 1 +
 drivers/tty/tty_ldsem.c                       | 1 +
 drivers/usb/usbip/usbip_common.h              | 1 +
 kernel/irq/manage.c                           | 1 +
 12 files changed, 13 insertions(+)

diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index c9297605058c..54d581d407aa 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -16,6 +16,7 @@
 #include <linux/freezer.h>
 #include <linux/init.h>
 #include <linux/kthread.h>
+#include <linux/sched/task.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/random.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index ae2882b64b82..fd56f92f3469 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -17,6 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/shmem_fs.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 
 #include "etnaviv_drv.h"
 #include "etnaviv_gem.h"
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 7279f259494f..cb2742b548bb 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -33,6 +33,7 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/pid.h>
 #include <linux/slab.h>
 #include <linux/export.h>
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 56da8f0d71bb..fba94df28cf1 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -40,6 +40,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 
 #include <net/ipv6.h>
 #include <net/addrconf.h>
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 4b1ec3ff152a..4dc0a8785fe0 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -42,6 +42,7 @@
 #endif
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/delay.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_addr.h>
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 0863905dee02..8589e0a14068 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -13,6 +13,7 @@
 #include <linux/rwsem.h>
 #include <linux/device-mapper.h>
 #include <linux/stacktrace.h>
+#include <linux/sched/task.h>
 
 #define DM_MSG_PREFIX "block manager"
 
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index cc1706a92ace..b0b6ed31918e 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -19,6 +19,8 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/pci.h>
+#include <linux/sched/task.h>
+
 #include <asm/cputable.h>
 #include <misc/cxl-base.h>
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index a2d326760a72..829b26cd4549 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -31,6 +31,7 @@
 #include "common.h"
 
 #include <linux/kthread.h>
+#include <linux/sched/task.h>
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index eb0c35994b54..ac27f3d3fbb4 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -32,6 +32,7 @@
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/gfp.h>
 
 #include "oprofile_stats.h"
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index 4f6b1b10b537..52b7baef4f7a 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -33,6 +33,7 @@
 #include <linux/tty.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task.h>
 
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index 9f490375ac92..f8573a52e41a 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -31,6 +31,7 @@
 #include <linux/types.h>
 #include <linux/usb.h>
 #include <linux/wait.h>
+#include <linux/sched/task.h>
 #include <uapi/linux/usbip.h>
 
 #define USBIP_VERSION "1.0.0"
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 09740952e4de..a4afe5cc5af1 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/task.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/task_work.h>
 
-- 
GitLab


From 50d34394cee68dd12c5e01fff073d1167700bfce Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 16:03:58 +0100
Subject: [PATCH 520/898] sched/headers: Prepare to remove the <linux/magic.h>
 include from <linux/sched/task_stack.h>

Update files that depend on the magic.h inclusion.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/dax/dax.c                 | 1 +
 drivers/virtio/virtio_balloon.c   | 1 +
 include/linux/sched/task_stack.h  | 1 +
 mm/zsmalloc.c                     | 1 +
 security/integrity/evm/evm_main.c | 2 ++
 5 files changed, 6 insertions(+)

diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index b75c77254fdb..8d9829ff2a78 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -13,6 +13,7 @@
 #include <linux/pagemap.h>
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/magic.h>
 #include <linux/mount.h>
 #include <linux/pfn_t.h>
 #include <linux/hash.h>
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 9d2738e9217f..a610061fabf6 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -31,6 +31,7 @@
 #include <linux/wait.h>
 #include <linux/mm.h>
 #include <linux/mount.h>
+#include <linux/magic.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 933cd49824c2..d2d578e85f7d 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -2,5 +2,6 @@
 #define _LINUX_SCHED_TASK_STACK_H
 
 #include <linux/sched.h>
+#include <linux/magic.h>
 
 #endif /* _LINUX_SCHED_TASK_STACK_H */
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b7b1fb6c8c21..b7ee9c34dbd6 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/magic.h>
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/highmem.h>
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index e2ed498c0f5f..063d38aef64e 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -22,6 +22,8 @@
 #include <linux/xattr.h>
 #include <linux/integrity.h>
 #include <linux/evm.h>
+#include <linux/magic.h>
+
 #include <crypto/hash.h>
 #include <crypto/algapi.h>
 #include "evm.h"
-- 
GitLab


From b69339ba109549beeaf45c45c52ac7025bfcd954 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 16:15:03 +0100
Subject: [PATCH 521/898] sched/headers: Prepare to remove spurious
 <linux/sched.h> inclusion dependencies

In the following patches we are going to remove various headers
from sched.h and other headers that sched.h includes.

To make those patches build cleanly prepare the scene by adding
dependencies to various files that learned to rely on those
to-be-removed dependencies.

These changes all make sense standalone: they add a header for
a data type that a particular .c or .h file is using.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/misc/vmw_vmci/vmci_resource.c | 1 +
 include/linux/sched.h                 | 1 +
 include/sound/control.h               | 1 +
 include/target/target_core_base.h     | 1 +
 4 files changed, 4 insertions(+)

diff --git a/drivers/misc/vmw_vmci/vmci_resource.c b/drivers/misc/vmw_vmci/vmci_resource.c
index 9a53a30de445..1ab6e8737a5f 100644
--- a/drivers/misc/vmw_vmci/vmci_resource.c
+++ b/drivers/misc/vmw_vmci/vmci_resource.c
@@ -17,6 +17,7 @@
 #include <linux/hash.h>
 #include <linux/types.h>
 #include <linux/rculist.h>
+#include <linux/completion.h>
 
 #include "vmci_resource.h"
 #include "vmci_driver.h"
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ea05116bc3c2..b5c6d602dfe9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -18,6 +18,7 @@ struct sched_param {
 #include <linux/types.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
+#include <linux/mutex.h>
 #include <linux/plist.h>
 #include <linux/rbtree.h>
 #include <linux/thread_info.h>
diff --git a/include/sound/control.h b/include/sound/control.h
index 21d047f229a1..bd7246de58e7 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -22,6 +22,7 @@
  *
  */
 
+#include <linux/wait.h>
 #include <sound/asound.h>
 
 #define snd_kcontrol_chip(kcontrol) ((kcontrol)->private_data)
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 878560e60c75..8be9ba73383d 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -5,6 +5,7 @@
 #include <linux/dma-direction.h> /* enum dma_data_direction */
 #include <linux/percpu_ida.h>    /* struct percpu_ida */
 #include <linux/semaphore.h>     /* struct semaphore */
+#include <linux/completion.h>
 
 #define TARGET_CORE_VERSION		"v5.0"
 
-- 
GitLab


From a60b9eda67beac2318fa159545ba7d022f780736 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 522/898] sched/headers: Move scheduler topology interfaces to
 <linux/sched/topology.h>

The vast majority of sched.h users does not require the topology types and
interfaces, so split them out into <linux/sched/topology.h>.

This reduces the size of linux/sched.h by ~6%.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h          | 212 --------------------------------
 include/linux/sched/topology.h | 213 +++++++++++++++++++++++++++++++++
 2 files changed, 213 insertions(+), 212 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b5c6d602dfe9..55480782ce7f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -960,12 +960,6 @@ enum cpu_idle_type {
 # define SCHED_FIXEDPOINT_SHIFT	10
 # define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)
 
-/*
- * Increase resolution of cpu_capacity calculations
- */
-#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
-#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
-
 /*
  * Wake-queues are lists of tasks with a pending wakeup, whose
  * callers have already marked the task as woken internally,
@@ -1016,214 +1010,8 @@ extern void wake_q_add(struct wake_q_head *head,
 		       struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
 
-/*
- * sched-domains (multiprocessor balancing) declarations:
- */
-#ifdef CONFIG_SMP
-#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
-#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
-#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
-#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
-#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY	0x0040  /* Groups have different max cpu capacities */
-#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu capacity */
-#define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
-#define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
-#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
-#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
-#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
-#define SD_NUMA			0x4000	/* cross-node balancing */
-
-#ifdef CONFIG_SCHED_SMT
-static inline int cpu_smt_flags(void)
-{
-	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
-}
-#endif
-
-#ifdef CONFIG_SCHED_MC
-static inline int cpu_core_flags(void)
-{
-	return SD_SHARE_PKG_RESOURCES;
-}
-#endif
-
-#ifdef CONFIG_NUMA
-static inline int cpu_numa_flags(void)
-{
-	return SD_NUMA;
-}
-#endif
-
-extern int arch_asym_cpu_priority(int cpu);
-
-struct sched_domain_attr {
-	int relax_domain_level;
-};
-
-#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
-	.relax_domain_level = -1,			\
-}
-
-extern int sched_domain_level_max;
-
-struct sched_group;
-
-struct sched_domain_shared {
-	atomic_t	ref;
-	atomic_t	nr_busy_cpus;
-	int		has_idle_cores;
-};
-
-struct sched_domain {
-	/* These fields must be setup */
-	struct sched_domain *parent;	/* top domain must be null terminated */
-	struct sched_domain *child;	/* bottom domain must be null terminated */
-	struct sched_group *groups;	/* the balancing groups of the domain */
-	unsigned long min_interval;	/* Minimum balance interval ms */
-	unsigned long max_interval;	/* Maximum balance interval ms */
-	unsigned int busy_factor;	/* less balancing by factor if busy */
-	unsigned int imbalance_pct;	/* No balance until over watermark */
-	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
-	unsigned int busy_idx;
-	unsigned int idle_idx;
-	unsigned int newidle_idx;
-	unsigned int wake_idx;
-	unsigned int forkexec_idx;
-	unsigned int smt_gain;
-
-	int nohz_idle;			/* NOHZ IDLE status */
-	int flags;			/* See SD_* */
-	int level;
-
-	/* Runtime fields. */
-	unsigned long last_balance;	/* init to jiffies. units in jiffies */
-	unsigned int balance_interval;	/* initialise to 1. units in ms. */
-	unsigned int nr_balance_failed; /* initialise to 0 */
-
-	/* idle_balance() stats */
-	u64 max_newidle_lb_cost;
-	unsigned long next_decay_max_lb_cost;
-
-	u64 avg_scan_cost;		/* select_idle_sibling */
-
-#ifdef CONFIG_SCHEDSTATS
-	/* load_balance() stats */
-	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
-
-	/* Active load balancing */
-	unsigned int alb_count;
-	unsigned int alb_failed;
-	unsigned int alb_pushed;
-
-	/* SD_BALANCE_EXEC stats */
-	unsigned int sbe_count;
-	unsigned int sbe_balanced;
-	unsigned int sbe_pushed;
-
-	/* SD_BALANCE_FORK stats */
-	unsigned int sbf_count;
-	unsigned int sbf_balanced;
-	unsigned int sbf_pushed;
-
-	/* try_to_wake_up() stats */
-	unsigned int ttwu_wake_remote;
-	unsigned int ttwu_move_affine;
-	unsigned int ttwu_move_balance;
-#endif
-#ifdef CONFIG_SCHED_DEBUG
-	char *name;
-#endif
-	union {
-		void *private;		/* used during construction */
-		struct rcu_head rcu;	/* used during destruction */
-	};
-	struct sched_domain_shared *shared;
-
-	unsigned int span_weight;
-	/*
-	 * Span of all CPUs in this domain.
-	 *
-	 * NOTE: this field is variable length. (Allocated dynamically
-	 * by attaching extra space to the end of the structure,
-	 * depending on how many CPUs the kernel has booted up with)
-	 */
-	unsigned long span[0];
-};
-
-static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
-{
-	return to_cpumask(sd->span);
-}
-
-extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-				    struct sched_domain_attr *dattr_new);
-
-/* Allocate an array of sched domains, for partition_sched_domains(). */
-cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
-void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
-
-bool cpus_share_cache(int this_cpu, int that_cpu);
-
-typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
-typedef int (*sched_domain_flags_f)(void);
-
-#define SDTL_OVERLAP	0x01
-
-struct sd_data {
-	struct sched_domain **__percpu sd;
-	struct sched_domain_shared **__percpu sds;
-	struct sched_group **__percpu sg;
-	struct sched_group_capacity **__percpu sgc;
-};
-
-struct sched_domain_topology_level {
-	sched_domain_mask_f mask;
-	sched_domain_flags_f sd_flags;
-	int		    flags;
-	int		    numa_level;
-	struct sd_data      data;
-#ifdef CONFIG_SCHED_DEBUG
-	char                *name;
-#endif
-};
-
-extern void set_sched_topology(struct sched_domain_topology_level *tl);
 extern void wake_up_if_idle(int cpu);
 
-#ifdef CONFIG_SCHED_DEBUG
-# define SD_INIT_NAME(type)		.name = #type
-#else
-# define SD_INIT_NAME(type)
-#endif
-
-#else /* CONFIG_SMP */
-
-struct sched_domain_attr;
-
-static inline void
-partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-			struct sched_domain_attr *dattr_new)
-{
-}
-
-static inline bool cpus_share_cache(int this_cpu, int that_cpu)
-{
-	return true;
-}
-
-#endif	/* !CONFIG_SMP */
-
-
 struct io_context;			/* See blkdev.h */
 
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 184b56b8aa64..b3550b36e65d 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -5,4 +5,217 @@
 
 #include <linux/sched/idle.h>
 
+/*
+ * sched-domains (multiprocessor balancing) declarations:
+ */
+#ifdef CONFIG_SMP
+
+#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
+#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
+#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
+#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
+#define SD_ASYM_CPUCAPACITY	0x0040  /* Groups have different max cpu capacities */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu capacity */
+#define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
+#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
+#define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
+#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
+#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
+#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
+#define SD_NUMA			0x4000	/* cross-node balancing */
+
+/*
+ * Increase resolution of cpu_capacity calculations
+ */
+#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
+#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
+
+#ifdef CONFIG_SCHED_SMT
+static inline int cpu_smt_flags(void)
+{
+	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+static inline int cpu_core_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_NUMA
+static inline int cpu_numa_flags(void)
+{
+	return SD_NUMA;
+}
+#endif
+
+extern int arch_asym_cpu_priority(int cpu);
+
+struct sched_domain_attr {
+	int relax_domain_level;
+};
+
+#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
+	.relax_domain_level = -1,			\
+}
+
+extern int sched_domain_level_max;
+
+struct sched_group;
+
+struct sched_domain_shared {
+	atomic_t	ref;
+	atomic_t	nr_busy_cpus;
+	int		has_idle_cores;
+};
+
+struct sched_domain {
+	/* These fields must be setup */
+	struct sched_domain *parent;	/* top domain must be null terminated */
+	struct sched_domain *child;	/* bottom domain must be null terminated */
+	struct sched_group *groups;	/* the balancing groups of the domain */
+	unsigned long min_interval;	/* Minimum balance interval ms */
+	unsigned long max_interval;	/* Maximum balance interval ms */
+	unsigned int busy_factor;	/* less balancing by factor if busy */
+	unsigned int imbalance_pct;	/* No balance until over watermark */
+	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
+	unsigned int busy_idx;
+	unsigned int idle_idx;
+	unsigned int newidle_idx;
+	unsigned int wake_idx;
+	unsigned int forkexec_idx;
+	unsigned int smt_gain;
+
+	int nohz_idle;			/* NOHZ IDLE status */
+	int flags;			/* See SD_* */
+	int level;
+
+	/* Runtime fields. */
+	unsigned long last_balance;	/* init to jiffies. units in jiffies */
+	unsigned int balance_interval;	/* initialise to 1. units in ms. */
+	unsigned int nr_balance_failed; /* initialise to 0 */
+
+	/* idle_balance() stats */
+	u64 max_newidle_lb_cost;
+	unsigned long next_decay_max_lb_cost;
+
+	u64 avg_scan_cost;		/* select_idle_sibling */
+
+#ifdef CONFIG_SCHEDSTATS
+	/* load_balance() stats */
+	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
+
+	/* Active load balancing */
+	unsigned int alb_count;
+	unsigned int alb_failed;
+	unsigned int alb_pushed;
+
+	/* SD_BALANCE_EXEC stats */
+	unsigned int sbe_count;
+	unsigned int sbe_balanced;
+	unsigned int sbe_pushed;
+
+	/* SD_BALANCE_FORK stats */
+	unsigned int sbf_count;
+	unsigned int sbf_balanced;
+	unsigned int sbf_pushed;
+
+	/* try_to_wake_up() stats */
+	unsigned int ttwu_wake_remote;
+	unsigned int ttwu_move_affine;
+	unsigned int ttwu_move_balance;
+#endif
+#ifdef CONFIG_SCHED_DEBUG
+	char *name;
+#endif
+	union {
+		void *private;		/* used during construction */
+		struct rcu_head rcu;	/* used during destruction */
+	};
+	struct sched_domain_shared *shared;
+
+	unsigned int span_weight;
+	/*
+	 * Span of all CPUs in this domain.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 */
+	unsigned long span[0];
+};
+
+static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
+{
+	return to_cpumask(sd->span);
+}
+
+extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+				    struct sched_domain_attr *dattr_new);
+
+/* Allocate an array of sched domains, for partition_sched_domains(). */
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
+
+bool cpus_share_cache(int this_cpu, int that_cpu);
+
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
+typedef int (*sched_domain_flags_f)(void);
+
+#define SDTL_OVERLAP	0x01
+
+struct sd_data {
+	struct sched_domain **__percpu sd;
+	struct sched_domain_shared **__percpu sds;
+	struct sched_group **__percpu sg;
+	struct sched_group_capacity **__percpu sgc;
+};
+
+struct sched_domain_topology_level {
+	sched_domain_mask_f mask;
+	sched_domain_flags_f sd_flags;
+	int		    flags;
+	int		    numa_level;
+	struct sd_data      data;
+#ifdef CONFIG_SCHED_DEBUG
+	char                *name;
+#endif
+};
+
+extern void set_sched_topology(struct sched_domain_topology_level *tl);
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(type)		.name = #type
+#else
+# define SD_INIT_NAME(type)
+#endif
+
+#else /* CONFIG_SMP */
+
+struct sched_domain_attr;
+
+static inline void
+partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+			struct sched_domain_attr *dattr_new)
+{
+}
+
+static inline bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
+#endif	/* !CONFIG_SMP */
+
 #endif /* _LINUX_SCHED_TOPOLOGY_H */
-- 
GitLab


From b768917d2c08edc4b5616c86a569e524d190434b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:51:00 +0100
Subject: [PATCH 523/898] sched/headers: Move the 'cpu_idle_type' enum from
 <linux/sched.h> to <linux/sched/idle.h>

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 7 -------
 include/linux/sched/idle.h | 7 +++++++
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 55480782ce7f..8a8252e9e0c7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -943,13 +943,6 @@ static inline int sched_info_on(void)
 void force_schedstat_enabled(void);
 #endif
 
-enum cpu_idle_type {
-	CPU_IDLE,
-	CPU_NOT_IDLE,
-	CPU_NEWLY_IDLE,
-	CPU_MAX_IDLE_TYPES
-};
-
 /*
  * Integer metrics need fixed point arithmetic, e.g., sched/fair
  * has a few: load, load_avg, util_avg, freq, and capacity.
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index a3cf79b86986..6aabc9968cba 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -3,4 +3,11 @@
 
 #include <linux/sched.h>
 
+enum cpu_idle_type {
+	CPU_IDLE,
+	CPU_NOT_IDLE,
+	CPU_NEWLY_IDLE,
+	CPU_MAX_IDLE_TYPES
+};
+
 #endif /* _LINUX_SCHED_IDLE_H */
-- 
GitLab


From 4437722b0486c36dc90a1adf584fca4cea6cf1de Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:58:52 +0100
Subject: [PATCH 524/898] sched/headers: Move the wake_up_if_idle() prototype
 to <linux/sched/idle.h>

No need to clutter <linux/sched.h> with this rarely used prototype.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 2 --
 include/linux/sched/idle.h | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8a8252e9e0c7..c30705c3e553 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1003,8 +1003,6 @@ extern void wake_q_add(struct wake_q_head *head,
 		       struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
 
-extern void wake_up_if_idle(int cpu);
-
 struct io_context;			/* See blkdev.h */
 
 
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index 6aabc9968cba..72b6b6ab6354 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -10,4 +10,6 @@ enum cpu_idle_type {
 	CPU_MAX_IDLE_TYPES
 };
 
+extern void wake_up_if_idle(int cpu);
+
 #endif /* _LINUX_SCHED_IDLE_H */
-- 
GitLab


From 5dbe91de599423d243738a205367506444ebb4a4 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 18:47:28 +0100
Subject: [PATCH 525/898] sched/headers: Move idle polling methods to
 <linux/sched/idle.h>

Further reduce the size of <linux/sched.h> by moving these APIs:

	tsk_is_polling()
	__current_set_polling()
	current_set_polling_and_test()
	__current_clr_polling()
	current_clr_polling_and_test()
	current_clr_polling()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 76 --------------------------------------
 include/linux/sched/idle.h | 76 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+), 76 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c30705c3e553..4f512e337584 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3176,82 +3176,6 @@ static inline int spin_needbreak(spinlock_t *lock)
 #endif
 }
 
-/*
- * Idle thread specific functions to determine the need_resched
- * polling state.
- */
-#ifdef TIF_POLLING_NRFLAG
-static inline int tsk_is_polling(struct task_struct *p)
-{
-	return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
-}
-
-static inline void __current_set_polling(void)
-{
-	set_thread_flag(TIF_POLLING_NRFLAG);
-}
-
-static inline bool __must_check current_set_polling_and_test(void)
-{
-	__current_set_polling();
-
-	/*
-	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_curr()
-	 */
-	smp_mb__after_atomic();
-
-	return unlikely(tif_need_resched());
-}
-
-static inline void __current_clr_polling(void)
-{
-	clear_thread_flag(TIF_POLLING_NRFLAG);
-}
-
-static inline bool __must_check current_clr_polling_and_test(void)
-{
-	__current_clr_polling();
-
-	/*
-	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_curr()
-	 */
-	smp_mb__after_atomic();
-
-	return unlikely(tif_need_resched());
-}
-
-#else
-static inline int tsk_is_polling(struct task_struct *p) { return 0; }
-static inline void __current_set_polling(void) { }
-static inline void __current_clr_polling(void) { }
-
-static inline bool __must_check current_set_polling_and_test(void)
-{
-	return unlikely(tif_need_resched());
-}
-static inline bool __must_check current_clr_polling_and_test(void)
-{
-	return unlikely(tif_need_resched());
-}
-#endif
-
-static inline void current_clr_polling(void)
-{
-	__current_clr_polling();
-
-	/*
-	 * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
-	 * Once the bit is cleared, we'll get IPIs with every new
-	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
-	 * fold.
-	 */
-	smp_mb(); /* paired with resched_curr() */
-
-	preempt_fold_need_resched();
-}
-
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index 72b6b6ab6354..66ee32f87f0b 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -12,4 +12,80 @@ enum cpu_idle_type {
 
 extern void wake_up_if_idle(int cpu);
 
+/*
+ * Idle thread specific functions to determine the need_resched
+ * polling state.
+ */
+#ifdef TIF_POLLING_NRFLAG
+static inline int tsk_is_polling(struct task_struct *p)
+{
+	return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
+}
+
+static inline void __current_set_polling(void)
+{
+	set_thread_flag(TIF_POLLING_NRFLAG);
+}
+
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	__current_set_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_curr()
+	 */
+	smp_mb__after_atomic();
+
+	return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
+{
+	clear_thread_flag(TIF_POLLING_NRFLAG);
+}
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_curr()
+	 */
+	smp_mb__after_atomic();
+
+	return unlikely(tif_need_resched());
+}
+
+#else
+static inline int tsk_is_polling(struct task_struct *p) { return 0; }
+static inline void __current_set_polling(void) { }
+static inline void __current_clr_polling(void) { }
+
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
+#endif
+
+static inline void current_clr_polling(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
+	 * Once the bit is cleared, we'll get IPIs with every new
+	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
+	 * fold.
+	 */
+	smp_mb(); /* paired with resched_curr() */
+
+	preempt_fold_need_resched();
+}
+
 #endif /* _LINUX_SCHED_IDLE_H */
-- 
GitLab


From eb61baf69871b9836783a81bc451189edb0d9de2 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 17:09:06 +0100
Subject: [PATCH 526/898] sched/headers: Move the wake-queue types and
 interfaces from sched.h into <linux/sched/wake_q.h>

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h        | 54 +++---------------------------------
 include/linux/sched/wake_q.h | 47 +++++++++++++++++++++++++++++++
 ipc/msg.c                    |  1 -
 3 files changed, 51 insertions(+), 51 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f512e337584..5cda7cf09505 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -953,56 +953,6 @@ void force_schedstat_enabled(void);
 # define SCHED_FIXEDPOINT_SHIFT	10
 # define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)
 
-/*
- * Wake-queues are lists of tasks with a pending wakeup, whose
- * callers have already marked the task as woken internally,
- * and can thus carry on. A common use case is being able to
- * do the wakeups once the corresponding user lock as been
- * released.
- *
- * We hold reference to each task in the list across the wakeup,
- * thus guaranteeing that the memory is still valid by the time
- * the actual wakeups are performed in wake_up_q().
- *
- * One per task suffices, because there's never a need for a task to be
- * in two wake queues simultaneously; it is forbidden to abandon a task
- * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
- * already in a wake queue, the wakeup will happen soon and the second
- * waker can just skip it.
- *
- * The DEFINE_WAKE_Q macro declares and initializes the list head.
- * wake_up_q() does NOT reinitialize the list; it's expected to be
- * called near the end of a function. Otherwise, the list can be
- * re-initialized for later re-use by wake_q_init().
- *
- * Note that this can cause spurious wakeups. schedule() callers
- * must ensure the call is done inside a loop, confirming that the
- * wakeup condition has in fact occurred.
- */
-struct wake_q_node {
-	struct wake_q_node *next;
-};
-
-struct wake_q_head {
-	struct wake_q_node *first;
-	struct wake_q_node **lastp;
-};
-
-#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
-
-#define DEFINE_WAKE_Q(name)				\
-	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
-
-static inline void wake_q_init(struct wake_q_head *head)
-{
-	head->first = WAKE_Q_TAIL;
-	head->lastp = &head->first;
-}
-
-extern void wake_q_add(struct wake_q_head *head,
-		       struct task_struct *task);
-extern void wake_up_q(struct wake_q_head *head);
-
 struct io_context;			/* See blkdev.h */
 
 
@@ -1234,6 +1184,10 @@ enum perf_event_task_context {
 	perf_nr_task_contexts,
 };
 
+struct wake_q_node {
+	struct wake_q_node *next;
+};
+
 /* Track pages that require TLB flushes */
 struct tlbflush_unmap_batch {
 	/*
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 6383b35e4eba..d03d8a9047dc 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -1,6 +1,53 @@
 #ifndef _LINUX_SCHED_WAKE_Q_H
 #define _LINUX_SCHED_WAKE_Q_H
 
+/*
+ * Wake-queues are lists of tasks with a pending wakeup, whose
+ * callers have already marked the task as woken internally,
+ * and can thus carry on. A common use case is being able to
+ * do the wakeups once the corresponding user lock as been
+ * released.
+ *
+ * We hold reference to each task in the list across the wakeup,
+ * thus guaranteeing that the memory is still valid by the time
+ * the actual wakeups are performed in wake_up_q().
+ *
+ * One per task suffices, because there's never a need for a task to be
+ * in two wake queues simultaneously; it is forbidden to abandon a task
+ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
+ * already in a wake queue, the wakeup will happen soon and the second
+ * waker can just skip it.
+ *
+ * The DEFINE_WAKE_Q macro declares and initializes the list head.
+ * wake_up_q() does NOT reinitialize the list; it's expected to be
+ * called near the end of a function. Otherwise, the list can be
+ * re-initialized for later re-use by wake_q_init().
+ *
+ * Note that this can cause spurious wakeups. schedule() callers
+ * must ensure the call is done inside a loop, confirming that the
+ * wakeup condition has in fact occurred.
+ */
+
 #include <linux/sched.h>
 
+struct wake_q_head {
+	struct wake_q_node *first;
+	struct wake_q_node **lastp;
+};
+
+#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
+
+#define DEFINE_WAKE_Q(name)				\
+	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+
+static inline void wake_q_init(struct wake_q_head *head)
+{
+	head->first = WAKE_Q_TAIL;
+	head->lastp = &head->first;
+}
+
+extern void wake_q_add(struct wake_q_head *head,
+		       struct task_struct *task);
+extern void wake_up_q(struct wake_q_head *head);
+
 #endif /* _LINUX_SCHED_WAKE_Q_H */
diff --git a/ipc/msg.c b/ipc/msg.c
index ecc387e573f6..104926dc72be 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -30,7 +30,6 @@
 #include <linux/proc_fs.h>
 #include <linux/list.h>
 #include <linux/security.h>
-#include <linux/sched.h>
 #include <linux/sched/wake_q.h>
 #include <linux/syscalls.h>
 #include <linux/audit.h>
-- 
GitLab


From 5689810360c2e88ce1619e8bcfa859852f9a1d1a Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Tue, 7 Feb 2017 12:07:18 +0100
Subject: [PATCH 527/898] sched/headers: Move scheduler clock interfaces to
 <linux/sched/clock.h>

Move the sched_clock interfaces into a separate header file, to reduce
the size of sched.h.

Include <linux/sched/clock.h> in all files that made use of one of the
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h       | 100 ------------------------------------
 include/linux/sched/clock.h |  98 +++++++++++++++++++++++++++++++++++
 2 files changed, 98 insertions(+), 100 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5cda7cf09505..b42d2f9d673a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2190,103 +2190,6 @@ static inline void calc_load_exit_idle(void) { }
 #define cpu_relax_yield() cpu_relax()
 #endif
 
-/*
- * Do not use outside of architecture code which knows its limitations.
- *
- * sched_clock() has no promise of monotonicity or bounded drift between
- * CPUs, use (which you should not) requires disabling IRQs.
- *
- * Please use one of the three interfaces below.
- */
-extern unsigned long long notrace sched_clock(void);
-/*
- * See the comment in kernel/sched/clock.c
- */
-extern u64 running_clock(void);
-extern u64 sched_clock_cpu(int cpu);
-
-
-extern void sched_clock_init(void);
-
-#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline void sched_clock_init_late(void)
-{
-}
-
-static inline void sched_clock_tick(void)
-{
-}
-
-static inline void clear_sched_clock_stable(void)
-{
-}
-
-static inline void sched_clock_idle_sleep_event(void)
-{
-}
-
-static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
-{
-}
-
-static inline u64 cpu_clock(int cpu)
-{
-	return sched_clock();
-}
-
-static inline u64 local_clock(void)
-{
-	return sched_clock();
-}
-#else
-extern void sched_clock_init_late(void);
-/*
- * Architectures can set this to 1 if they have specified
- * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
- * but then during bootup it turns out that sched_clock()
- * is reliable after all:
- */
-extern int sched_clock_stable(void);
-extern void clear_sched_clock_stable(void);
-
-extern void sched_clock_tick(void);
-extern void sched_clock_idle_sleep_event(void);
-extern void sched_clock_idle_wakeup_event(u64 delta_ns);
-
-/*
- * As outlined in clock.c, provides a fast, high resolution, nanosecond
- * time source that is monotonic per cpu argument and has bounded drift
- * between cpus.
- *
- * ######################### BIG FAT WARNING ##########################
- * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
- * # go backwards !!                                                  #
- * ####################################################################
- */
-static inline u64 cpu_clock(int cpu)
-{
-	return sched_clock_cpu(cpu);
-}
-
-static inline u64 local_clock(void)
-{
-	return sched_clock_cpu(raw_smp_processor_id());
-}
-#endif
-
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-/*
- * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
- * The reason for this explicit opt-in is not to have perf penalty with
- * slow sched_clocks.
- */
-extern void enable_sched_clock_irqtime(void);
-extern void disable_sched_clock_irqtime(void);
-#else
-static inline void enable_sched_clock_irqtime(void) {}
-static inline void disable_sched_clock_irqtime(void) {}
-#endif
-
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 
@@ -2297,9 +2200,6 @@ extern void sched_exec(void);
 #define sched_exec()   {}
 #endif
 
-extern void sched_clock_idle_sleep_event(void);
-extern void sched_clock_idle_wakeup_event(u64 delta_ns);
-
 #ifdef CONFIG_HOTPLUG_CPU
 extern void idle_task_exit(void);
 #else
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 7cb7d79b2cf9..ac12f71d359c 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -3,4 +3,102 @@
 
 #include <linux/sched.h>
 
+/*
+ * Do not use outside of architecture code which knows its limitations.
+ *
+ * sched_clock() has no promise of monotonicity or bounded drift between
+ * CPUs, use (which you should not) requires disabling IRQs.
+ *
+ * Please use one of the three interfaces below.
+ */
+extern unsigned long long notrace sched_clock(void);
+
+/*
+ * See the comment in kernel/sched/clock.c
+ */
+extern u64 running_clock(void);
+extern u64 sched_clock_cpu(int cpu);
+
+
+extern void sched_clock_init(void);
+
+#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline void sched_clock_init_late(void)
+{
+}
+
+static inline void sched_clock_tick(void)
+{
+}
+
+static inline void clear_sched_clock_stable(void)
+{
+}
+
+static inline void sched_clock_idle_sleep_event(void)
+{
+}
+
+static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
+{
+}
+
+static inline u64 cpu_clock(int cpu)
+{
+	return sched_clock();
+}
+
+static inline u64 local_clock(void)
+{
+	return sched_clock();
+}
+#else
+extern void sched_clock_init_late(void);
+/*
+ * Architectures can set this to 1 if they have specified
+ * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
+ * but then during bootup it turns out that sched_clock()
+ * is reliable after all:
+ */
+extern int sched_clock_stable(void);
+extern void clear_sched_clock_stable(void);
+
+extern void sched_clock_tick(void);
+extern void sched_clock_idle_sleep_event(void);
+extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+
+/*
+ * As outlined in clock.c, provides a fast, high resolution, nanosecond
+ * time source that is monotonic per cpu argument and has bounded drift
+ * between cpus.
+ *
+ * ######################### BIG FAT WARNING ##########################
+ * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
+ * # go backwards !!                                                  #
+ * ####################################################################
+ */
+static inline u64 cpu_clock(int cpu)
+{
+	return sched_clock_cpu(cpu);
+}
+
+static inline u64 local_clock(void)
+{
+	return sched_clock_cpu(raw_smp_processor_id());
+}
+#endif
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
+ * The reason for this explicit opt-in is not to have perf penalty with
+ * slow sched_clocks.
+ */
+extern void enable_sched_clock_irqtime(void);
+extern void disable_sched_clock_irqtime(void);
+#else
+static inline void enable_sched_clock_irqtime(void) {}
+static inline void disable_sched_clock_irqtime(void) {}
+#endif
+
 #endif /* _LINUX_SCHED_CLOCK_H */
-- 
GitLab


From 47913d4ebd99c827c82c4f29eb282a119c3f2aeb Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 18:00:26 +0100
Subject: [PATCH 528/898] sched/headers, delayacct: Move the 'struct
 task_delay_info' definition from <linux/sched.h> to <linux/delayacct.h>

The 'struct task_delay_info' definition does not have to be in sched.h,
because task_struct only has a pointer to it.

So move it to <linux/delayacct.h> to reduce the size of <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/delayacct.h | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/sched.h     | 39 ++++-----------------------------------
 2 files changed, 40 insertions(+), 35 deletions(-)

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 00e60f79a9cc..6b769cbd1000 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -30,7 +30,43 @@
 #define DELAYACCT_PF_BLKIO	0x00000002	/* I am waiting on IO */
 
 #ifdef CONFIG_TASK_DELAY_ACCT
+struct task_delay_info {
+	spinlock_t	lock;
+	unsigned int	flags;	/* Private per-task flags */
+
+	/* For each stat XXX, add following, aligned appropriately
+	 *
+	 * struct timespec XXX_start, XXX_end;
+	 * u64 XXX_delay;
+	 * u32 XXX_count;
+	 *
+	 * Atomicity of updates to XXX_delay, XXX_count protected by
+	 * single lock above (split into XXX_lock if contention is an issue).
+	 */
+
+	/*
+	 * XXX_count is incremented on every XXX operation, the delay
+	 * associated with the operation is added to XXX_delay.
+	 * XXX_delay contains the accumulated delay time in nanoseconds.
+	 */
+	u64 blkio_start;	/* Shared by blkio, swapin */
+	u64 blkio_delay;	/* wait for sync block io completion */
+	u64 swapin_delay;	/* wait for swapin block io completion */
+	u32 blkio_count;	/* total count of the number of sync block */
+				/* io operations performed */
+	u32 swapin_count;	/* total count of the number of swapin block */
+				/* io operations performed */
+
+	u64 freepages_start;
+	u64 freepages_delay;	/* wait for memory reclaim */
+	u32 freepages_count;	/* total count of memory reclaim */
+};
+#endif
 
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#ifdef CONFIG_TASK_DELAY_ACCT
 extern int delayacct_on;	/* Delay accounting turned on/off */
 extern struct kmem_cache *delayacct_cache;
 extern void delayacct_init(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b42d2f9d673a..7d6998858fa3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -893,39 +893,7 @@ struct sched_info {
 };
 #endif /* CONFIG_SCHED_INFO */
 
-#ifdef CONFIG_TASK_DELAY_ACCT
-struct task_delay_info {
-	spinlock_t	lock;
-	unsigned int	flags;	/* Private per-task flags */
-
-	/* For each stat XXX, add following, aligned appropriately
-	 *
-	 * struct timespec XXX_start, XXX_end;
-	 * u64 XXX_delay;
-	 * u32 XXX_count;
-	 *
-	 * Atomicity of updates to XXX_delay, XXX_count protected by
-	 * single lock above (split into XXX_lock if contention is an issue).
-	 */
-
-	/*
-	 * XXX_count is incremented on every XXX operation, the delay
-	 * associated with the operation is added to XXX_delay.
-	 * XXX_delay contains the accumulated delay time in nanoseconds.
-	 */
-	u64 blkio_start;	/* Shared by blkio, swapin */
-	u64 blkio_delay;	/* wait for sync block io completion */
-	u64 swapin_delay;	/* wait for swapin block io completion */
-	u32 blkio_count;	/* total count of the number of sync block */
-				/* io operations performed */
-	u32 swapin_count;	/* total count of the number of swapin block */
-				/* io operations performed */
-
-	u64 freepages_start;
-	u64 freepages_delay;	/* wait for memory reclaim */
-	u32 freepages_count;	/* total count of memory reclaim */
-};
-#endif	/* CONFIG_TASK_DELAY_ACCT */
+struct task_delay_info;
 
 static inline int sched_info_on(void)
 {
@@ -1612,9 +1580,10 @@ struct task_struct {
 
 	struct page_frag task_frag;
 
-#ifdef	CONFIG_TASK_DELAY_ACCT
-	struct task_delay_info *delays;
+#ifdef CONFIG_TASK_DELAY_ACCT
+	struct task_delay_info		*delays;
 #endif
+
 #ifdef CONFIG_FAULT_INJECTION
 	int make_it_fail;
 #endif
-- 
GitLab


From e2d1e2aec572a2138dea74d53be54a1406d419c0 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 18:07:51 +0100
Subject: [PATCH 529/898] sched/headers: Move various ABI definitions to
 <uapi/linux/sched/types.h>

Move scheduler ABI types (struct sched_attr, struct sched_param, etc.) into
the new UAPI header.

This further reduces the size and complexity of <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h            | 70 +-------------------------------
 include/uapi/linux/sched/types.h | 68 +++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+), 68 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7d6998858fa3..5c481906e835 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -5,11 +5,6 @@
 
 #include <linux/sched/prio.h>
 
-
-struct sched_param {
-	int sched_priority;
-};
-
 #include <asm/param.h>	/* for HZ */
 
 #include <linux/capability.h>
@@ -64,69 +59,8 @@ struct sched_param {
 
 #include <asm/processor.h>
 
-#define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
-
-/*
- * Extended scheduling parameters data structure.
- *
- * This is needed because the original struct sched_param can not be
- * altered without introducing ABI issues with legacy applications
- * (e.g., in sched_getparam()).
- *
- * However, the possibility of specifying more than just a priority for
- * the tasks may be useful for a wide variety of application fields, e.g.,
- * multimedia, streaming, automation and control, and many others.
- *
- * This variant (sched_attr) is meant at describing a so-called
- * sporadic time-constrained task. In such model a task is specified by:
- *  - the activation period or minimum instance inter-arrival time;
- *  - the maximum (or average, depending on the actual scheduling
- *    discipline) computation time of all instances, a.k.a. runtime;
- *  - the deadline (relative to the actual activation time) of each
- *    instance.
- * Very briefly, a periodic (sporadic) task asks for the execution of
- * some specific computation --which is typically called an instance--
- * (at most) every period. Moreover, each instance typically lasts no more
- * than the runtime and must be completed by time instant t equal to
- * the instance activation time + the deadline.
- *
- * This is reflected by the actual fields of the sched_attr structure:
- *
- *  @size		size of the structure, for fwd/bwd compat.
- *
- *  @sched_policy	task's scheduling policy
- *  @sched_flags	for customizing the scheduler behaviour
- *  @sched_nice		task's nice value      (SCHED_NORMAL/BATCH)
- *  @sched_priority	task's static priority (SCHED_FIFO/RR)
- *  @sched_deadline	representative of the task's deadline
- *  @sched_runtime	representative of the task's runtime
- *  @sched_period	representative of the task's period
- *
- * Given this task model, there are a multiplicity of scheduling algorithms
- * and policies, that can be used to ensure all the tasks will make their
- * timing constraints.
- *
- * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
- * only user of this new interface. More information about the algorithm
- * available in the scheduling class file or in Documentation/.
- */
-struct sched_attr {
-	u32 size;
-
-	u32 sched_policy;
-	u64 sched_flags;
-
-	/* SCHED_NORMAL, SCHED_BATCH */
-	s32 sched_nice;
-
-	/* SCHED_FIFO, SCHED_RR */
-	u32 sched_priority;
-
-	/* SCHED_DEADLINE */
-	u64 sched_runtime;
-	u64 sched_deadline;
-	u64 sched_period;
-};
+struct sched_attr;
+struct sched_param;
 
 struct futex_pi_state;
 struct robust_list_head;
diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h
index d162d315f4b5..307acbc82d80 100644
--- a/include/uapi/linux/sched/types.h
+++ b/include/uapi/linux/sched/types.h
@@ -3,4 +3,72 @@
 
 #include <linux/types.h>
 
+struct sched_param {
+	int sched_priority;
+};
+
+#define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
+
+/*
+ * Extended scheduling parameters data structure.
+ *
+ * This is needed because the original struct sched_param can not be
+ * altered without introducing ABI issues with legacy applications
+ * (e.g., in sched_getparam()).
+ *
+ * However, the possibility of specifying more than just a priority for
+ * the tasks may be useful for a wide variety of application fields, e.g.,
+ * multimedia, streaming, automation and control, and many others.
+ *
+ * This variant (sched_attr) is meant at describing a so-called
+ * sporadic time-constrained task. In such model a task is specified by:
+ *  - the activation period or minimum instance inter-arrival time;
+ *  - the maximum (or average, depending on the actual scheduling
+ *    discipline) computation time of all instances, a.k.a. runtime;
+ *  - the deadline (relative to the actual activation time) of each
+ *    instance.
+ * Very briefly, a periodic (sporadic) task asks for the execution of
+ * some specific computation --which is typically called an instance--
+ * (at most) every period. Moreover, each instance typically lasts no more
+ * than the runtime and must be completed by time instant t equal to
+ * the instance activation time + the deadline.
+ *
+ * This is reflected by the actual fields of the sched_attr structure:
+ *
+ *  @size		size of the structure, for fwd/bwd compat.
+ *
+ *  @sched_policy	task's scheduling policy
+ *  @sched_flags	for customizing the scheduler behaviour
+ *  @sched_nice		task's nice value      (SCHED_NORMAL/BATCH)
+ *  @sched_priority	task's static priority (SCHED_FIFO/RR)
+ *  @sched_deadline	representative of the task's deadline
+ *  @sched_runtime	representative of the task's runtime
+ *  @sched_period	representative of the task's period
+ *
+ * Given this task model, there are a multiplicity of scheduling algorithms
+ * and policies, that can be used to ensure all the tasks will make their
+ * timing constraints.
+ *
+ * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
+ * only user of this new interface. More information about the algorithm
+ * available in the scheduling class file or in Documentation/.
+ */
+struct sched_attr {
+	u32 size;
+
+	u32 sched_policy;
+	u64 sched_flags;
+
+	/* SCHED_NORMAL, SCHED_BATCH */
+	s32 sched_nice;
+
+	/* SCHED_FIFO, SCHED_RR */
+	u32 sched_priority;
+
+	/* SCHED_DEADLINE */
+	u64 sched_runtime;
+	u64 sched_deadline;
+	u64 sched_period;
+};
+
 #endif /* _UAPI_LINUX_SCHED_TYPES_H */
-- 
GitLab


From dea38c74cb9205341f52b8d8ae18f61247a43ea8 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 18:25:37 +0100
Subject: [PATCH 530/898] sched/headers: Move loadavg related definitions from
 <linux/sched.h> to <linux/sched/loadavg.h>

Move these bits to <linux/sched/loadavg.h>, to reduce the size and
complexity of <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h         | 27 ---------------------------
 include/linux/sched/loadavg.h | 27 +++++++++++++++++++++++++++
 2 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c481906e835..78adf7a0cac1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -71,31 +71,6 @@ struct blk_plug;
 struct filename;
 struct nameidata;
 
-/*
- * These are the constant used to fake the fixed-point load-average
- * counting. Some notes:
- *  - 11 bit fractions expand to 22 bits by the multiplies: this gives
- *    a load-average precision of 10 bits integer + 11 bits fractional
- *  - if you want to count load-averages more often, you need more
- *    precision, or rounding will get you. With 2-second counting freq,
- *    the EXP_n values would be 1981, 2034 and 2043 if still using only
- *    11 bit fractions.
- */
-extern unsigned long avenrun[];		/* Load averages */
-extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
-
-#define FSHIFT		11		/* nr of bits of precision */
-#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
-#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
-#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
-#define EXP_5		2014		/* 1/exp(5sec/5min) */
-#define EXP_15		2037		/* 1/exp(5sec/15min) */
-
-#define CALC_LOAD(load,exp,n) \
-	load *= exp; \
-	load += n*(FIXED_1-exp); \
-	load >>= FSHIFT;
-
 extern unsigned long total_forks;
 extern int nr_threads;
 DECLARE_PER_CPU(unsigned long, process_counts);
@@ -106,8 +81,6 @@ extern unsigned long nr_iowait(void);
 extern unsigned long nr_iowait_cpu(int cpu);
 extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
-extern void calc_global_load(unsigned long ticks);
-
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void cpu_load_update_nohz_start(void);
 extern void cpu_load_update_nohz_stop(void);
diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index 3ae74be327e8..c392e28ce0ac 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -3,4 +3,31 @@
 
 #include <linux/sched.h>
 
+/*
+ * These are the constant used to fake the fixed-point load-average
+ * counting. Some notes:
+ *  - 11 bit fractions expand to 22 bits by the multiplies: this gives
+ *    a load-average precision of 10 bits integer + 11 bits fractional
+ *  - if you want to count load-averages more often, you need more
+ *    precision, or rounding will get you. With 2-second counting freq,
+ *    the EXP_n values would be 1981, 2034 and 2043 if still using only
+ *    11 bit fractions.
+ */
+extern unsigned long avenrun[];		/* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
+
+#define FSHIFT		11		/* nr of bits of precision */
+#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
+#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
+#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
+#define EXP_5		2014		/* 1/exp(5sec/5min) */
+#define EXP_15		2037		/* 1/exp(5sec/15min) */
+
+#define CALC_LOAD(load,exp,n) \
+	load *= exp; \
+	load += n*(FIXED_1-exp); \
+	load >>= FSHIFT;
+
+extern void calc_global_load(unsigned long ticks);
+
 #endif /* _LINUX_SCHED_LOADAVG_H */
-- 
GitLab


From de8f1c77313d8c908b2897f268d466c13df161d4 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 18:41:24 +0100
Subject: [PATCH 531/898] sched/headers: Move autogroup APIs into
 <linux/sched/autogroup.h>

Further reduce the size of sched.h.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h           | 18 ------------------
 include/linux/sched/autogroup.h | 21 +++++++++++++++++++++
 2 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 78adf7a0cac1..042620729230 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2092,24 +2092,6 @@ static inline void wake_up_nohz_cpu(int cpu) { }
 extern u64 scheduler_tick_max_deferment(void);
 #endif
 
-#ifdef CONFIG_SCHED_AUTOGROUP
-extern void sched_autogroup_create_attach(struct task_struct *p);
-extern void sched_autogroup_detach(struct task_struct *p);
-extern void sched_autogroup_fork(struct signal_struct *sig);
-extern void sched_autogroup_exit(struct signal_struct *sig);
-extern void sched_autogroup_exit_task(struct task_struct *p);
-#ifdef CONFIG_PROC_FS
-extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
-extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
-#endif
-#else
-static inline void sched_autogroup_create_attach(struct task_struct *p) { }
-static inline void sched_autogroup_detach(struct task_struct *p) { }
-static inline void sched_autogroup_fork(struct signal_struct *sig) { }
-static inline void sched_autogroup_exit(struct signal_struct *sig) { }
-static inline void sched_autogroup_exit_task(struct task_struct *p) { }
-#endif
-
 extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
diff --git a/include/linux/sched/autogroup.h b/include/linux/sched/autogroup.h
index d745f22e57dc..586bdf37330d 100644
--- a/include/linux/sched/autogroup.h
+++ b/include/linux/sched/autogroup.h
@@ -3,4 +3,25 @@
 
 #include <linux/sched.h>
 
+struct signal_struct;
+struct seq_file;
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+extern void sched_autogroup_create_attach(struct task_struct *p);
+extern void sched_autogroup_detach(struct task_struct *p);
+extern void sched_autogroup_fork(struct signal_struct *sig);
+extern void sched_autogroup_exit(struct signal_struct *sig);
+extern void sched_autogroup_exit_task(struct task_struct *p);
+#ifdef CONFIG_PROC_FS
+extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
+#endif
+#else
+static inline void sched_autogroup_create_attach(struct task_struct *p) { }
+static inline void sched_autogroup_detach(struct task_struct *p) { }
+static inline void sched_autogroup_fork(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit_task(struct task_struct *p) { }
+#endif
+
 #endif /* _LINUX_SCHED_AUTOGROUP_H */
-- 
GitLab


From 4c77b18cf8b7ab37c7d5737b4609010d2ceec5f0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 1 Mar 2017 11:24:35 +0100
Subject: [PATCH 532/898] sched/fair: Make select_idle_cpu() more aggressive

Kitsunyan reported desktop latency issues on his Celeron 887 because
of commit:

  1b568f0aabf2 ("sched/core: Optimize SCHED_SMT")

... even though his CPU doesn't do SMT.

The effect of running the SMT code on a !SMT part is basically a more
aggressive select_idle_cpu(). Removing the avg condition fixed things
for him.

I also know FB likes this test gone, even though other workloads like
having it.

For now, take it out by default, until we get a better idea.

Reported-by: kitsunyan <kitsunyan@inbox.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Mason <clm@fb.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c     | 2 +-
 kernel/sched/features.h | 5 +++++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 274c747a01ce..b3ee10dd3e85 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5797,7 +5797,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
 	 */
-	if ((avg_idle / 512) < avg_cost)
+	if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
 		return -1;
 
 	time = local_clock();
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 69631fa46c2f..1b3c8189b286 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
  */
 SCHED_FEAT(TTWU_QUEUE, true)
 
+/*
+ * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
+ */
+SCHED_FEAT(SIS_AVG_CPU, false)
+
 #ifdef HAVE_RT_PUSH_IPI
 /*
  * In order to avoid a thundering herd attack of CPUs that are
-- 
GitLab


From 0ba87bb27d66b78e278167ac7e20c66520b8a612 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 1 Mar 2017 10:51:47 +0100
Subject: [PATCH 533/898] sched/core: Fix pick_next_task() for RT,DL

Pavan noticed that the following commit:

  49ee576809d8 ("sched/core: Optimize pick_next_task() for idle_sched_class")

... broke RT,DL balancing by robbing them of the opportinty to do new-'idle'
balancing when their last runnable task (on that runqueue) goes away.

Reported-by: Pavan Kondeti <pkondeti@codeaurora.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Fixes: 49ee576809d8 ("sched/core: Optimize pick_next_task() for idle_sched_class")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bbfb917a9b49..6699d43a8843 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3273,10 +3273,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	struct task_struct *p;
 
 	/*
-	 * Optimization: we know that if all tasks are in
-	 * the fair class we can call that function directly:
+	 * Optimization: we know that if all tasks are in the fair class we can
+	 * call that function directly, but only if the @prev task wasn't of a
+	 * higher scheduling class, because otherwise those loose the
+	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+	if (likely((prev->sched_class == &idle_sched_class ||
+		    prev->sched_class == &fair_sched_class) &&
+		   rq->nr_running == rq->cfs.h_nr_running)) {
+
 		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto again;
-- 
GitLab


From f94c8d116997597fc00f0812b0ab9256e7b0c58f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 1 Mar 2017 15:53:38 +0100
Subject: [PATCH 534/898] sched/clock, x86/tsc: Rework the x86 'unstable'
 sched_clock() interface

Wanpeng Li reported that since the following commit:

  acb04058de49 ("sched/clock: Fix hotplug crash")

... KVM always runs with unstable sched-clock even though KVM's
kvm_clock _is_ stable.

The problem is that we've tied clear_sched_clock_stable() to the TSC
state, and overlooked that sched_clock() is a paravirt function.

Solve this by doing two things:

 - tie the sched_clock() stable state more clearly to the TSC stable
   state for the normal (!paravirt) case.

 - only call clear_sched_clock_stable() when we mark TSC unstable
   when we use native_sched_clock().

The first means we can actually run with stable sched_clock in more
situations then before, which is good. And since commit:

  12907fbb1a69 ("sched/clock, clocksource: Add optional cs::mark_unstable() method")

... this should be reliable. Since any detection of TSC fail now results
in marking the TSC unstable.

Reported-by: Wanpeng Li <kernellwp@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Fixes: acb04058de49 ("sched/clock: Fix hotplug crash")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/amd.c       |  4 ----
 arch/x86/kernel/cpu/centaur.c   |  2 --
 arch/x86/kernel/cpu/common.c    |  3 ---
 arch/x86/kernel/cpu/cyrix.c     |  1 -
 arch/x86/kernel/cpu/intel.c     |  4 ----
 arch/x86/kernel/cpu/transmeta.c |  2 --
 arch/x86/kernel/tsc.c           | 35 ++++++++++++++++++++++-----------
 7 files changed, 23 insertions(+), 28 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4e95b2e0d95f..30d924ae5c34 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -555,10 +555,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (check_tsc_unstable())
-			clear_sched_clock_stable();
-	} else {
-		clear_sched_clock_stable();
 	}
 
 	/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 2c234a6d94c4..bad8ff078a21 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -104,8 +104,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #endif
-
-	clear_sched_clock_stable();
 }
 
 static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c64ca5929cb5..9d98e2e15d54 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -86,7 +86,6 @@ static void default_init(struct cpuinfo_x86 *c)
 			strcpy(c->x86_model_id, "386");
 	}
 #endif
-	clear_sched_clock_stable();
 }
 
 static const struct cpu_dev default_cpu = {
@@ -1075,8 +1074,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (this_cpu->c_init)
 		this_cpu->c_init(c);
-	else
-		clear_sched_clock_stable();
 
 	/* Disable the PN if appropriate */
 	squash_the_stupid_serial_number(c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 47416f959a48..31e679238e8d 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -184,7 +184,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
 		break;
 	}
-	clear_sched_clock_stable();
 }
 
 static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 017ecd3bb553..2388bafe5c37 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -161,10 +161,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (check_tsc_unstable())
-			clear_sched_clock_stable();
-	} else {
-		clear_sched_clock_stable();
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index c1ea5b999839..6a9ad73a2c54 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -15,8 +15,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
 		if (xlvl >= 0x80860001)
 			c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
 	}
-
-	clear_sched_clock_stable();
 }
 
 static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2724dc82f992..911129fda2f9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -326,9 +326,16 @@ unsigned long long sched_clock(void)
 {
 	return paravirt_sched_clock();
 }
+
+static inline bool using_native_sched_clock(void)
+{
+	return pv_time_ops.sched_clock == native_sched_clock;
+}
 #else
 unsigned long long
 sched_clock(void) __attribute__((alias("native_sched_clock")));
+
+static inline bool using_native_sched_clock(void) { return true; }
 #endif
 
 int check_tsc_unstable(void)
@@ -1111,8 +1118,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs)
 {
 	if (tsc_unstable)
 		return;
+
 	tsc_unstable = 1;
-	clear_sched_clock_stable();
+	if (using_native_sched_clock())
+		clear_sched_clock_stable();
 	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to clocksource watchdog\n");
 }
@@ -1134,18 +1143,20 @@ static struct clocksource clocksource_tsc = {
 
 void mark_tsc_unstable(char *reason)
 {
-	if (!tsc_unstable) {
-		tsc_unstable = 1;
+	if (tsc_unstable)
+		return;
+
+	tsc_unstable = 1;
+	if (using_native_sched_clock())
 		clear_sched_clock_stable();
-		disable_sched_clock_irqtime();
-		pr_info("Marking TSC unstable due to %s\n", reason);
-		/* Change only the rating, when not registered */
-		if (clocksource_tsc.mult)
-			clocksource_mark_unstable(&clocksource_tsc);
-		else {
-			clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
-			clocksource_tsc.rating = 0;
-		}
+	disable_sched_clock_irqtime();
+	pr_info("Marking TSC unstable due to %s\n", reason);
+	/* Change only the rating, when not registered */
+	if (clocksource_tsc.mult) {
+		clocksource_mark_unstable(&clocksource_tsc);
+	} else {
+		clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
+		clocksource_tsc.rating = 0;
 	}
 }
 
-- 
GitLab


From 2b232e0c3b3a09f3e33750aa20e314f1b80e5361 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 28 Feb 2017 09:40:11 +0000
Subject: [PATCH 535/898] locking/ww_mutex: Replace cpu_relax() with
 cond_resched() for tests

When busy-spinning on a ww_mutex_trylock(), we depend upon the other
thread advancing and releasing the lock. This can not happen on a single
CPU unless we relinquish it:

  [ ] NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [kworker/0:1:18]
  ...
  [ ] Call Trace:
  [ ]  mutex_trylock()
  [ ]  test_mutex_work+0x31/0x56
  [ ]  process_one_work+0x1b4/0x2f9
  [ ]  worker_thread+0x1b0/0x27c
  [ ]  kthread+0xd1/0xd3
  [ ]  ret_from_fork+0x19/0x30

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: f2a5fec17395 ("locking/ww_mutex: Begin kselftests for ww_mutex")
Link: http://lkml.kernel.org/r/20170228094011.2595-1-chris@chris-wilson.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/locking/test-ww_mutex.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index da6c9a34f62f..3eb39c588397 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work)
 
 	if (mtx->flags & TEST_MTX_TRY) {
 		while (!ww_mutex_trylock(&mtx->mutex))
-			cpu_relax();
+			cond_resched();
 	} else {
 		ww_mutex_lock(&mtx->mutex, NULL);
 	}
@@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags)
 				ret = -EINVAL;
 				break;
 			}
-			cpu_relax();
+			cond_resched();
 		} while (time_before(jiffies, timeout));
 	} else {
 		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
-- 
GitLab


From 7fb4a2cea6b18dab56d609530d077f168169ed6b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 1 Mar 2017 16:23:30 +0100
Subject: [PATCH 536/898] locking/lockdep: Add nest_lock integrity test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Boqun reported that hlock->references can overflow. Add a debug test
for that to generate a clear error when this happens.

Without this, lockdep is likely to report a mysterious failure on
unlock.

Reported-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicolai Hähnle <Nicolai.Haehnle@amd.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/locking/lockdep.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 9812e5dd409e..c0ee8607c11e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3260,10 +3260,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (depth) {
 		hlock = curr->held_locks + depth - 1;
 		if (hlock->class_idx == class_idx && nest_lock) {
-			if (hlock->references)
+			if (hlock->references) {
+				/*
+				 * Check: unsigned int references:12, overflow.
+				 */
+				if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
+					return 0;
+
 				hlock->references++;
-			else
+			} else {
 				hlock->references = 2;
+			}
 
 			return 1;
 		}
-- 
GitLab


From 857811a37129f5d2ba162d7be3986eff44724014 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 1 Mar 2017 23:01:38 +0800
Subject: [PATCH 537/898] locking/ww_mutex: Adjust the lock number for stress
 test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Because there are only 12 bits in held_lock::references, so we only
support 4095 nested lock held in the same time, adjust the lock number
for ww_mutex stress test to kill one lockdep splat:

  [ ] [ BUG: bad unlock balance detected! ]
  [ ] kworker/u2:0/5 is trying to release lock (ww_class_mutex) at:
  [ ] ww_mutex_unlock()
  [ ] but there are no more locks to release!
  ...

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicolai Hähnle <Nicolai.Haehnle@amd.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170301150138.hdixnmafzfsox7nn@tardis.cn.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/locking/test-ww_mutex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 3eb39c588397..6b7abb334ca6 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -627,7 +627,7 @@ static int __init test_ww_mutex_init(void)
 	if (ret)
 		return ret;
 
-	ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+	ret = stress(4095, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
 	if (ret)
 		return ret;
 
-- 
GitLab


From bb1a2c26165640ba2cbcfe06c81e9f9d6db4e643 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 1 Mar 2017 21:10:17 +0100
Subject: [PATCH 538/898] x86/hpet: Prevent might sleep splat on resume

Sergey reported a might sleep warning triggered from the hpet resume
path. It's caused by the call to disable_irq() from interrupt disabled
context.

The problem with the low level resume code is that it is not accounted as a
special system_state like we do during the boot process. Calling the same
code during system boot would not trigger the warning. That's inconsistent
at best.

In this particular case it's trivial to replace the disable_irq() with
disable_hardirq() because this particular code path is solely used from
system resume and the involved hpet interrupts can never be force threaded.


Reported-and-tested-by: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Borislav Petkov <bp@alien8.de>
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1703012108460.3684@nanos
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/hpet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index dc6ba5bda9fc..89ff7af2de50 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 
 		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-		disable_irq(hdev->irq);
+		disable_hardirq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 		enable_irq(hdev->irq);
 	}
-- 
GitLab


From 1657b8f84ed9fc1d2a100671f1d42d6286f20073 Mon Sep 17 00:00:00 2001
From: Waldemar Rymarkiewicz <ext.waldemar.rymarkiewicz@tieto.com>
Date: Fri, 24 Feb 2017 23:30:03 +0100
Subject: [PATCH 539/898] ath10k: search SMBIOS for OEM board file extension

Board Data File (BDF) is loaded upon driver boot-up procedure. The right
board data file is identified, among others, by device and sybsystem ids.

The problem, however, can occur when the (default) board data file cannot
fulfill with the vendor requirements and it is necessary to use a different
board data file.

To solve the issue QCA uses SMBIOS type 0xF8 to store Board Data File Name
Extension to specify the extension/variant name. The driver will take the
extension suffix into consideration and will load the right (non-default)
board data file if necessary.

If it is unnecessary to use extension board data file, please leave the
SMBIOS field blank and default configuration will be used.

Example:
If a default board data file for a specific board is identified by a string
      "bus=pci,vendor=168c,device=003e,subsystem-vendor=1028,
       subsystem-device=0310"
then the OEM specific data file, if used, could be identified by variant
suffix:
      "bus=pci,vendor=168c,device=003e,subsystem-vendor=1028,
       subsystem-device=0310,variant=DE_1AB"

If board data file name extension is set but board-2.bin does not contain
board data file for the variant, the driver will fallback to the default
board data file not to break backward compatibility.

This was first applied in commit f2593cb1b291 ("ath10k: Search SMBIOS for OEM
board file extension") but later reverted in commit 005c3490e9db ("Revert
"ath10k: Search SMBIOS for OEM board file extension"". This patch is now
otherwise the same as commit f2593cb1b291 except the regression fixed.

Signed-off-by: Waldemar Rymarkiewicz <ext.waldemar.rymarkiewicz@tieto.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c | 101 ++++++++++++++++++++++++-
 drivers/net/wireless/ath/ath10k/core.h |  19 +++++
 2 files changed, 117 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index dd902b43f8f7..0a8e29e9a0eb 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -18,6 +18,8 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/of.h>
+#include <linux/dmi.h>
+#include <linux/ctype.h>
 #include <asm/byteorder.h>
 
 #include "core.h"
@@ -711,6 +713,72 @@ static int ath10k_core_get_board_id_from_otp(struct ath10k *ar)
 	return 0;
 }
 
+static void ath10k_core_check_bdfext(const struct dmi_header *hdr, void *data)
+{
+	struct ath10k *ar = data;
+	const char *bdf_ext;
+	const char *magic = ATH10K_SMBIOS_BDF_EXT_MAGIC;
+	u8 bdf_enabled;
+	int i;
+
+	if (hdr->type != ATH10K_SMBIOS_BDF_EXT_TYPE)
+		return;
+
+	if (hdr->length != ATH10K_SMBIOS_BDF_EXT_LENGTH) {
+		ath10k_dbg(ar, ATH10K_DBG_BOOT,
+			   "wrong smbios bdf ext type length (%d).\n",
+			   hdr->length);
+		return;
+	}
+
+	bdf_enabled = *((u8 *)hdr + ATH10K_SMBIOS_BDF_EXT_OFFSET);
+	if (!bdf_enabled) {
+		ath10k_dbg(ar, ATH10K_DBG_BOOT, "bdf variant name not found.\n");
+		return;
+	}
+
+	/* Only one string exists (per spec) */
+	bdf_ext = (char *)hdr + hdr->length;
+
+	if (memcmp(bdf_ext, magic, strlen(magic)) != 0) {
+		ath10k_dbg(ar, ATH10K_DBG_BOOT,
+			   "bdf variant magic does not match.\n");
+		return;
+	}
+
+	for (i = 0; i < strlen(bdf_ext); i++) {
+		if (!isascii(bdf_ext[i]) || !isprint(bdf_ext[i])) {
+			ath10k_dbg(ar, ATH10K_DBG_BOOT,
+				   "bdf variant name contains non ascii chars.\n");
+			return;
+		}
+	}
+
+	/* Copy extension name without magic suffix */
+	if (strscpy(ar->id.bdf_ext, bdf_ext + strlen(magic),
+		    sizeof(ar->id.bdf_ext)) < 0) {
+		ath10k_dbg(ar, ATH10K_DBG_BOOT,
+			   "bdf variant string is longer than the buffer can accommodate (variant: %s)\n",
+			    bdf_ext);
+		return;
+	}
+
+	ath10k_dbg(ar, ATH10K_DBG_BOOT,
+		   "found and validated bdf variant smbios_type 0x%x bdf %s\n",
+		   ATH10K_SMBIOS_BDF_EXT_TYPE, bdf_ext);
+}
+
+static int ath10k_core_check_smbios(struct ath10k *ar)
+{
+	ar->id.bdf_ext[0] = '\0';
+	dmi_walk(ath10k_core_check_bdfext, ar);
+
+	if (ar->id.bdf_ext[0] == '\0')
+		return -ENODATA;
+
+	return 0;
+}
+
 static int ath10k_download_and_run_otp(struct ath10k *ar)
 {
 	u32 result, address = ar->hw_params.patch_load_addr;
@@ -1020,6 +1088,23 @@ static int ath10k_core_fetch_board_data_api_n(struct ath10k *ar,
 		case ATH10K_BD_IE_BOARD:
 			ret = ath10k_core_parse_bd_ie_board(ar, data, ie_len,
 							    boardname);
+			if (ret == -ENOENT && ar->id.bdf_ext[0] != '\0') {
+				/* try default bdf if variant was not found */
+				char *s, *v = ",variant=";
+				char boardname2[100];
+
+				strlcpy(boardname2, boardname,
+					sizeof(boardname2));
+
+				s = strstr(boardname2, v);
+				if (s)
+					*s = '\0';  /* strip ",variant=%s" */
+
+				ret = ath10k_core_parse_bd_ie_board(ar, data,
+								    ie_len,
+								    boardname2);
+			}
+
 			if (ret == -ENOENT)
 				/* no match found, continue */
 				break;
@@ -1057,6 +1142,9 @@ static int ath10k_core_fetch_board_data_api_n(struct ath10k *ar,
 static int ath10k_core_create_board_name(struct ath10k *ar, char *name,
 					 size_t name_len)
 {
+	/* strlen(',variant=') + strlen(ar->id.bdf_ext) */
+	char variant[9 + ATH10K_SMBIOS_BDF_EXT_STR_LENGTH] = { 0 };
+
 	if (ar->id.bmi_ids_valid) {
 		scnprintf(name, name_len,
 			  "bus=%s,bmi-chip-id=%d,bmi-board-id=%d",
@@ -1066,12 +1154,15 @@ static int ath10k_core_create_board_name(struct ath10k *ar, char *name,
 		goto out;
 	}
 
+	if (ar->id.bdf_ext[0] != '\0')
+		scnprintf(variant, sizeof(variant), ",variant=%s",
+			  ar->id.bdf_ext);
+
 	scnprintf(name, name_len,
-		  "bus=%s,vendor=%04x,device=%04x,subsystem-vendor=%04x,subsystem-device=%04x",
+		  "bus=%s,vendor=%04x,device=%04x,subsystem-vendor=%04x,subsystem-device=%04x%s",
 		  ath10k_bus_str(ar->hif.bus),
 		  ar->id.vendor, ar->id.device,
-		  ar->id.subsystem_vendor, ar->id.subsystem_device);
-
+		  ar->id.subsystem_vendor, ar->id.subsystem_device, variant);
 out:
 	ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot using board name '%s'\n", name);
 
@@ -2128,6 +2219,10 @@ static int ath10k_core_probe_fw(struct ath10k *ar)
 		goto err_free_firmware_files;
 	}
 
+	ret = ath10k_core_check_smbios(ar);
+	if (ret)
+		ath10k_dbg(ar, ATH10K_DBG_BOOT, "bdf variant name not set.\n");
+
 	ret = ath10k_core_fetch_board_file(ar);
 	if (ret) {
 		ath10k_err(ar, "failed to fetch board file: %d\n", ret);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 757242ef52ac..88d14be7fcce 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -69,6 +69,23 @@
 #define ATH10K_NAPI_BUDGET      64
 #define ATH10K_NAPI_QUOTA_LIMIT 60
 
+/* SMBIOS type containing Board Data File Name Extension */
+#define ATH10K_SMBIOS_BDF_EXT_TYPE 0xF8
+
+/* SMBIOS type structure length (excluding strings-set) */
+#define ATH10K_SMBIOS_BDF_EXT_LENGTH 0x9
+
+/* Offset pointing to Board Data File Name Extension */
+#define ATH10K_SMBIOS_BDF_EXT_OFFSET 0x8
+
+/* Board Data File Name Extension string length.
+ * String format: BDF_<Customer ID>_<Extension>\0
+ */
+#define ATH10K_SMBIOS_BDF_EXT_STR_LENGTH 0x20
+
+/* The magic used by QCA spec */
+#define ATH10K_SMBIOS_BDF_EXT_MAGIC "BDF_"
+
 struct ath10k;
 
 enum ath10k_bus {
@@ -798,6 +815,8 @@ struct ath10k {
 		bool bmi_ids_valid;
 		u8 bmi_board_id;
 		u8 bmi_chip_id;
+
+		char bdf_ext[ATH10K_SMBIOS_BDF_EXT_STR_LENGTH];
 	} id;
 
 	int fw_api;
-- 
GitLab


From c96d0a1c47abd5c4fa544dcedb5fac4d020ac58b Mon Sep 17 00:00:00 2001
From: Paulo Flabiano Smorigo <pfsmorigo@linux.vnet.ibm.com>
Date: Wed, 1 Mar 2017 10:58:20 -0300
Subject: [PATCH 540/898] crypto: vmx - Use skcipher for cbc fallback

Cc: stable@vger.kernel.org #4.10
Signed-off-by: Paulo Flabiano Smorigo <pfsmorigo@linux.vnet.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/vmx/aes_cbc.c | 47 ++++++++++++++++++------------------
 1 file changed, 24 insertions(+), 23 deletions(-)

diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 94ad5c0adbcb..72a26eb4e954 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -27,11 +27,12 @@
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/skcipher.h>
 
 #include "aesp8-ppc.h"
 
 struct p8_aes_cbc_ctx {
-	struct crypto_blkcipher *fallback;
+	struct crypto_skcipher *fallback;
 	struct aes_key enc_key;
 	struct aes_key dec_key;
 };
@@ -39,7 +40,7 @@ struct p8_aes_cbc_ctx {
 static int p8_aes_cbc_init(struct crypto_tfm *tfm)
 {
 	const char *alg;
-	struct crypto_blkcipher *fallback;
+	struct crypto_skcipher *fallback;
 	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (!(alg = crypto_tfm_alg_name(tfm))) {
@@ -47,8 +48,9 @@ static int p8_aes_cbc_init(struct crypto_tfm *tfm)
 		return -ENOENT;
 	}
 
-	fallback =
-	    crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	fallback = crypto_alloc_skcipher(alg, 0,
+			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+
 	if (IS_ERR(fallback)) {
 		printk(KERN_ERR
 		       "Failed to allocate transformation for '%s': %ld\n",
@@ -56,11 +58,12 @@ static int p8_aes_cbc_init(struct crypto_tfm *tfm)
 		return PTR_ERR(fallback);
 	}
 	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+		crypto_skcipher_driver_name(fallback));
+
 
-	crypto_blkcipher_set_flags(
+	crypto_skcipher_set_flags(
 		fallback,
-		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+		crypto_skcipher_get_flags((struct crypto_skcipher *)tfm));
 	ctx->fallback = fallback;
 
 	return 0;
@@ -71,7 +74,7 @@ static void p8_aes_cbc_exit(struct crypto_tfm *tfm)
 	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (ctx->fallback) {
-		crypto_free_blkcipher(ctx->fallback);
+		crypto_free_skcipher(ctx->fallback);
 		ctx->fallback = NULL;
 	}
 }
@@ -91,7 +94,7 @@ static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key,
 	pagefault_enable();
 	preempt_enable();
 
-	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	ret += crypto_skcipher_setkey(ctx->fallback, key, keylen);
 	return ret;
 }
 
@@ -103,15 +106,14 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
 	struct blkcipher_walk walk;
 	struct p8_aes_cbc_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
-	struct blkcipher_desc fallback_desc = {
-		.tfm = ctx->fallback,
-		.info = desc->info,
-		.flags = desc->flags
-	};
 
 	if (in_interrupt()) {
-		ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src,
-					       nbytes);
+		SKCIPHER_REQUEST_ON_STACK(req, ctx->fallback);
+		skcipher_request_set_tfm(req, ctx->fallback);
+		skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+		skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
+		ret = crypto_skcipher_encrypt(req);
+		skcipher_request_zero(req);
 	} else {
 		preempt_disable();
 		pagefault_disable();
@@ -144,15 +146,14 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
 	struct blkcipher_walk walk;
 	struct p8_aes_cbc_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
-	struct blkcipher_desc fallback_desc = {
-		.tfm = ctx->fallback,
-		.info = desc->info,
-		.flags = desc->flags
-	};
 
 	if (in_interrupt()) {
-		ret = crypto_blkcipher_decrypt(&fallback_desc, dst, src,
-					       nbytes);
+		SKCIPHER_REQUEST_ON_STACK(req, ctx->fallback);
+		skcipher_request_set_tfm(req, ctx->fallback);
+		skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+		skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
+		ret = crypto_skcipher_decrypt(req);
+		skcipher_request_zero(req);
 	} else {
 		preempt_disable();
 		pagefault_disable();
-- 
GitLab


From 5839f555fa576be57371686265206398d9ea1480 Mon Sep 17 00:00:00 2001
From: Paulo Flabiano Smorigo <pfsmorigo@linux.vnet.ibm.com>
Date: Wed, 1 Mar 2017 11:00:00 -0300
Subject: [PATCH 541/898] crypto: vmx - Use skcipher for xts fallback

Cc: stable@vger.kernel.org #4.10
Signed-off-by: Paulo Flabiano Smorigo <pfsmorigo@linux.vnet.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/vmx/aes_xts.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c
index 24353ec336c5..6adc9290557a 100644
--- a/drivers/crypto/vmx/aes_xts.c
+++ b/drivers/crypto/vmx/aes_xts.c
@@ -28,11 +28,12 @@
 #include <crypto/aes.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/xts.h>
+#include <crypto/skcipher.h>
 
 #include "aesp8-ppc.h"
 
 struct p8_aes_xts_ctx {
-	struct crypto_blkcipher *fallback;
+	struct crypto_skcipher *fallback;
 	struct aes_key enc_key;
 	struct aes_key dec_key;
 	struct aes_key tweak_key;
@@ -41,7 +42,7 @@ struct p8_aes_xts_ctx {
 static int p8_aes_xts_init(struct crypto_tfm *tfm)
 {
 	const char *alg;
-	struct crypto_blkcipher *fallback;
+	struct crypto_skcipher *fallback;
 	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (!(alg = crypto_tfm_alg_name(tfm))) {
@@ -49,8 +50,8 @@ static int p8_aes_xts_init(struct crypto_tfm *tfm)
 		return -ENOENT;
 	}
 
-	fallback =
-		crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	fallback = crypto_alloc_skcipher(alg, 0,
+			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(fallback)) {
 		printk(KERN_ERR
 			"Failed to allocate transformation for '%s': %ld\n",
@@ -58,11 +59,11 @@ static int p8_aes_xts_init(struct crypto_tfm *tfm)
 		return PTR_ERR(fallback);
 	}
 	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-		crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+		crypto_skcipher_driver_name(fallback));
 
-	crypto_blkcipher_set_flags(
+	crypto_skcipher_set_flags(
 		fallback,
-		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+		crypto_skcipher_get_flags((struct crypto_skcipher *)tfm));
 	ctx->fallback = fallback;
 
 	return 0;
@@ -73,7 +74,7 @@ static void p8_aes_xts_exit(struct crypto_tfm *tfm)
 	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (ctx->fallback) {
-		crypto_free_blkcipher(ctx->fallback);
+		crypto_free_skcipher(ctx->fallback);
 		ctx->fallback = NULL;
 	}
 }
@@ -98,7 +99,7 @@ static int p8_aes_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
 	pagefault_enable();
 	preempt_enable();
 
-	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	ret += crypto_skcipher_setkey(ctx->fallback, key, keylen);
 	return ret;
 }
 
@@ -113,15 +114,14 @@ static int p8_aes_xts_crypt(struct blkcipher_desc *desc,
 	struct blkcipher_walk walk;
 	struct p8_aes_xts_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
-	struct blkcipher_desc fallback_desc = {
-		.tfm = ctx->fallback,
-		.info = desc->info,
-		.flags = desc->flags
-	};
 
 	if (in_interrupt()) {
-		ret = enc ? crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes) :
-                            crypto_blkcipher_decrypt(&fallback_desc, dst, src, nbytes);
+		SKCIPHER_REQUEST_ON_STACK(req, ctx->fallback);
+		skcipher_request_set_tfm(req, ctx->fallback);
+		skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+		skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
+		ret = enc? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req);
+		skcipher_request_zero(req);
 	} else {
 		preempt_disable();
 		pagefault_disable();
-- 
GitLab


From 0695d7dc1d9f19b82ec2cae24856bddce278cfe6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 24 Feb 2017 16:43:36 +0100
Subject: [PATCH 542/898] orangefs: Use RCU for destroy_inode

freeing of inodes must be RCU-delayed on all filesystems

Cc: stable@vger.kernel.org
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/orangefs/super.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index c48859f16e7b..67c24351a67f 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -115,6 +115,13 @@ static struct inode *orangefs_alloc_inode(struct super_block *sb)
 	return &orangefs_inode->vfs_inode;
 }
 
+static void orangefs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+}
+
 static void orangefs_destroy_inode(struct inode *inode)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
@@ -123,7 +130,7 @@ static void orangefs_destroy_inode(struct inode *inode)
 			"%s: deallocated %p destroying inode %pU\n",
 			__func__, orangefs_inode, get_khandle_from_ino(inode));
 
-	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+	call_rcu(&inode->i_rcu, orangefs_i_callback);
 }
 
 /*
-- 
GitLab


From e53aff45c490ea04aa5d9e3cffa65b6b54397455 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuahkh@osg.samsung.com>
Date: Wed, 1 Mar 2017 15:15:07 -0700
Subject: [PATCH 543/898] selftests: lib.mk Fix individual test builds

In commit a8ba798bc8ec ("selftests: enable O and KBUILD_OUTPUT"), added
support to generate compile targets in a user specified directory. OUTPUT
variable controls the location which is undefined when tests are built in
the test directory or with "make -C tools/testing/selftests/x86".

make -C tools/testing/selftests/x86/
make: Entering directory '/lkml/linux_4.11/tools/testing/selftests/x86'
Makefile:44: warning: overriding recipe for target 'clean'
../lib.mk:51: warning: ignoring old recipe for target 'clean'
gcc -m64 -o /single_step_syscall_64 -O2 -g -std=gnu99 -pthread -Wall  single_step_syscall.c -lrt -ldl
/usr/bin/ld: cannot open output file /single_step_syscall_64: Permission denied
collect2: error: ld returned 1 exit status
Makefile:50: recipe for target '/single_step_syscall_64' failed
make: *** [/single_step_syscall_64] Error 1
make: Leaving directory '/lkml/linux_4.11/tools/testing/selftests/x86'

Same failure with "cd tools/testing/selftests/x86/;make" run.

Fix this with a change to lib.mk to define OUTPUT to be the pwd when
MAKELEVEL is 0. This covers both cases mentioned above.

Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 tools/testing/selftests/lib.mk | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index ce96d80ad64f..775c589ac3c0 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -2,6 +2,10 @@
 # Makefile can operate with or without the kbuild infrastructure.
 CC := $(CROSS_COMPILE)gcc
 
+ifeq (0,$(MAKELEVEL))
+OUTPUT := $(shell pwd)
+endif
+
 TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
-- 
GitLab


From 59f082e464ae0533813d5a1c3149b22563da93d7 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Wed, 1 Feb 2017 09:53:14 -0800
Subject: [PATCH 544/898] blk-mq: allocate blk_mq_tags and requests in correct
 node

blk_mq_tags/requests of specific hardware queue are mostly used in
specific cpus, which might not be in the same numa node as disk. For
example, a nvme card is in node 0. half hardware queue will be used by
node 0, the other node 1.

Signed-off-by: Shaohua Li <shli@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9e6b064e5339..d84c66fb37b7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1713,16 +1713,20 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 					unsigned int reserved_tags)
 {
 	struct blk_mq_tags *tags;
+	int node;
+
+	node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+	if (node == NUMA_NO_NODE)
+		node = set->numa_node;
 
-	tags = blk_mq_init_tags(nr_tags, reserved_tags,
-				set->numa_node,
+	tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
 				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
 	if (!tags)
 		return NULL;
 
 	tags->rqs = kzalloc_node(nr_tags * sizeof(struct request *),
 				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-				 set->numa_node);
+				 node);
 	if (!tags->rqs) {
 		blk_mq_free_tags(tags);
 		return NULL;
@@ -1730,7 +1734,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 
 	tags->static_rqs = kzalloc_node(nr_tags * sizeof(struct request *),
 				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
-				 set->numa_node);
+				 node);
 	if (!tags->static_rqs) {
 		kfree(tags->rqs);
 		blk_mq_free_tags(tags);
@@ -1750,6 +1754,11 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 {
 	unsigned int i, j, entries_per_page, max_order = 4;
 	size_t rq_size, left;
+	int node;
+
+	node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx);
+	if (node == NUMA_NO_NODE)
+		node = set->numa_node;
 
 	INIT_LIST_HEAD(&tags->page_list);
 
@@ -1771,7 +1780,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 			this_order--;
 
 		do {
-			page = alloc_pages_node(set->numa_node,
+			page = alloc_pages_node(node,
 				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
 				this_order);
 			if (page)
@@ -1804,7 +1813,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 			if (set->ops->init_request) {
 				if (set->ops->init_request(set->driver_data,
 						rq, hctx_idx, i,
-						set->numa_node)) {
+						node)) {
 					tags->static_rqs[i] = NULL;
 					goto fail;
 				}
-- 
GitLab


From 27ddb689909cd0bab30524a5f720ae3a3e55acac Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Wed, 1 Feb 2017 09:53:15 -0800
Subject: [PATCH 545/898] PCI: add an API to get node from vector

Next patch will use the API to get the node from vector for nvme device

Signed-off-by: Shaohua Li <shli@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/pci/msi.c   | 16 ++++++++++++++++
 include/linux/pci.h |  6 ++++++
 2 files changed, 22 insertions(+)

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 980eaf588281..d571bc330686 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1298,6 +1298,22 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr)
 }
 EXPORT_SYMBOL(pci_irq_get_affinity);
 
+/**
+ * pci_irq_get_node - return the numa node of a particular msi vector
+ * @pdev:	PCI device to operate on
+ * @vec:	device-relative interrupt vector index (0-based).
+ */
+int pci_irq_get_node(struct pci_dev *pdev, int vec)
+{
+	const struct cpumask *mask;
+
+	mask = pci_irq_get_affinity(pdev, vec);
+	if (mask)
+		return local_memory_node(cpu_to_node(cpumask_first(mask)));
+	return dev_to_node(&pdev->dev);
+}
+EXPORT_SYMBOL(pci_irq_get_node);
+
 struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
 {
 	return to_pci_dev(desc->dev);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 282ed32244ce..eb3da1a04e6c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1323,6 +1323,7 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
 void pci_free_irq_vectors(struct pci_dev *dev);
 int pci_irq_vector(struct pci_dev *dev, unsigned int nr);
 const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec);
+int pci_irq_get_node(struct pci_dev *pdev, int vec);
 
 #else
 static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; }
@@ -1370,6 +1371,11 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev,
 {
 	return cpu_possible_mask;
 }
+
+static inline int pci_irq_get_node(struct pci_dev *pdev, int vec)
+{
+	return first_online_node;
+}
 #endif
 
 static inline int
-- 
GitLab


From d3af3ecdc62c46fa67ce7a681f173acb1d750e33 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Wed, 1 Feb 2017 09:53:16 -0800
Subject: [PATCH 546/898] nvme: allocate nvme_queue in correct node

nvme_queue is per-cpu queue (mostly). Allocating it in node where blk-mq
will use it.

Signed-off-by: Shaohua Li <shli@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/nvme/host/pci.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 57a1af52b06e..eee8f8426ff2 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1038,9 +1038,10 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
-							int depth)
+							int depth, int node)
 {
-	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
+	struct nvme_queue *nvmeq = kzalloc_node(sizeof(*nvmeq), GFP_KERNEL,
+							node);
 	if (!nvmeq)
 		return NULL;
 
@@ -1217,7 +1218,8 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	nvmeq = dev->queues[0];
 	if (!nvmeq) {
-		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
+		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH,
+					dev_to_node(dev->dev));
 		if (!nvmeq)
 			return -ENOMEM;
 	}
@@ -1309,7 +1311,9 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	int ret = 0;
 
 	for (i = dev->queue_count; i <= dev->max_qid; i++) {
-		if (!nvme_alloc_queue(dev, i, dev->q_depth)) {
+		/* vector == qid - 1, match nvme_create_queue */
+		if (!nvme_alloc_queue(dev, i, dev->q_depth,
+		     pci_irq_get_node(to_pci_dev(dev->dev), i - 1))) {
 			ret = -ENOMEM;
 			break;
 		}
-- 
GitLab


From 415b806de5576b656f3ff94366589af9a161d0c8 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 27 Feb 2017 10:04:39 -0700
Subject: [PATCH 547/898] blk-mq-sched: Allocate sched reserved tags as
 specified in the original queue tagset

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

Modified by me to also check at driver tag allocation time if the
original request was reserved, so we can be sure to allocate a
properly reserved tag at that point in time, too.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq-sched.c | 3 ++-
 block/blk-mq-tag.c   | 2 +-
 block/blk-mq-tag.h   | 6 ++++++
 block/blk-mq.c       | 3 +++
 4 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 98c7b061781e..46ca965fff5c 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -454,7 +454,8 @@ int blk_mq_sched_setup(struct request_queue *q)
 	 */
 	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
-		hctx->sched_tags = blk_mq_alloc_rq_map(set, i, q->nr_requests, 0);
+		hctx->sched_tags = blk_mq_alloc_rq_map(set, i,
+				q->nr_requests, set->reserved_tags);
 		if (!hctx->sched_tags) {
 			ret = -ENOMEM;
 			break;
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 54c84363c1b2..e48bc2c72615 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -181,7 +181,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
 		    struct blk_mq_ctx *ctx, unsigned int tag)
 {
-	if (tag >= tags->nr_reserved_tags) {
+	if (!blk_mq_tag_is_reserved(tags, tag)) {
 		const int real_tag = tag - tags->nr_reserved_tags;
 
 		BUG_ON(real_tag >= tags->nr_tags);
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 63497423c5cd..5cb51e53cc03 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -85,4 +85,10 @@ static inline void blk_mq_tag_set_rq(struct blk_mq_hw_ctx *hctx,
 	hctx->tags->rqs[tag] = rq;
 }
 
+static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags,
+					  unsigned int tag)
+{
+	return tag < tags->nr_reserved_tags;
+}
+
 #endif
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d84c66fb37b7..4df5fb42c74f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -852,6 +852,9 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 		return true;
 	}
 
+	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
+		data.flags |= BLK_MQ_REQ_RESERVED;
+
 	rq->tag = blk_mq_get_tag(&data);
 	if (rq->tag >= 0) {
 		if (blk_mq_tag_busy(data.hctx)) {
-- 
GitLab


From 6d2809d51a5079f01a416d91dd63b0766cb685d0 Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Mon, 27 Feb 2017 10:28:27 -0800
Subject: [PATCH 548/898] blk-mq: make blk_mq_alloc_request_hctx() allocate a
 scheduler request

blk_mq_alloc_request_hctx() allocates a driver request directly, unlike
its blk_mq_alloc_request() counterpart. It also crashes because it
doesn't update the tags->rqs map.

Fix it by making it allocate a scheduler request.

Reported-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-by: Sagi Grimberg <sagi@grimberg.me>
---
 block/blk-mq-sched.c | 11 +++++------
 block/blk-mq.c       | 33 +++++++++++++++------------------
 2 files changed, 20 insertions(+), 24 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 46ca965fff5c..5697b23412a1 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -110,15 +110,14 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
 					 struct blk_mq_alloc_data *data)
 {
 	struct elevator_queue *e = q->elevator;
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
 	struct request *rq;
 
 	blk_queue_enter_live(q);
-	ctx = blk_mq_get_ctx(q);
-	hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	blk_mq_set_alloc_data(data, q, data->flags, ctx, hctx);
+	data->q = q;
+	if (likely(!data->ctx))
+		data->ctx = blk_mq_get_ctx(q);
+	if (likely(!data->hctx))
+		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
 
 	if (e) {
 		data->flags |= BLK_MQ_REQ_INTERNAL;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4df5fb42c74f..85a7047d8b03 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -273,10 +273,9 @@ EXPORT_SYMBOL(blk_mq_alloc_request);
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 		unsigned int flags, unsigned int hctx_idx)
 {
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
+	struct blk_mq_alloc_data alloc_data = { .flags = flags };
 	struct request *rq;
-	struct blk_mq_alloc_data alloc_data;
+	unsigned int cpu;
 	int ret;
 
 	/*
@@ -299,25 +298,23 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 	 * Check if the hardware context is actually mapped to anything.
 	 * If not tell the caller that it should skip this queue.
 	 */
-	hctx = q->queue_hw_ctx[hctx_idx];
-	if (!blk_mq_hw_queue_mapped(hctx)) {
-		ret = -EXDEV;
-		goto out_queue_exit;
+	alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
+	if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
+		blk_queue_exit(q);
+		return ERR_PTR(-EXDEV);
 	}
-	ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
+	cpu = cpumask_first(alloc_data.hctx->cpumask);
+	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
 
-	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
-	if (!rq) {
-		ret = -EWOULDBLOCK;
-		goto out_queue_exit;
-	}
-
-	return rq;
+	rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
 
-out_queue_exit:
+	blk_mq_put_ctx(alloc_data.ctx);
 	blk_queue_exit(q);
-	return ERR_PTR(ret);
+
+	if (!rq)
+		return ERR_PTR(-EWOULDBLOCK);
+
+	return rq;
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
 
-- 
GitLab


From 59748398992c9c3e9d600e56cb2a5c0c546fe129 Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Mon, 27 Feb 2017 09:47:54 -0800
Subject: [PATCH 549/898] blk-mq: kill blk_mq_set_alloc_data()

Nothing is using it anymore.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-by: Sagi Grimberg <sagi@grimberg.me>
---
 block/blk-mq.h | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/block/blk-mq.h b/block/blk-mq.h
index 24b2256186f3..088ced003c13 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -146,16 +146,6 @@ struct blk_mq_alloc_data {
 	struct blk_mq_hw_ctx *hctx;
 };
 
-static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
-		struct request_queue *q, unsigned int flags,
-		struct blk_mq_ctx *ctx, struct blk_mq_hw_ctx *hctx)
-{
-	data->q = q;
-	data->flags = flags;
-	data->ctx = ctx;
-	data->hctx = hctx;
-}
-
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
 	if (data->flags & BLK_MQ_REQ_INTERNAL)
-- 
GitLab


From 562bef4259776c19cb2423d43af1f99183910a4d Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Mon, 27 Feb 2017 09:47:55 -0800
Subject: [PATCH 550/898] blk-mq: move update of tags->rqs to
 __blk_mq_alloc_request()

No functional difference, it just makes a little more sense to update
the tag map where we actually allocate the tag.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-by: Sagi Grimberg <sagi@grimberg.me>
---
 block/blk-mq-sched.c | 2 --
 block/blk-mq.c       | 1 +
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 5697b23412a1..09af8ff18719 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -134,8 +134,6 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
 			rq = __blk_mq_alloc_request(data, op);
 	} else {
 		rq = __blk_mq_alloc_request(data, op);
-		if (rq)
-			data->hctx->tags->rqs[rq->tag] = rq;
 	}
 
 	if (rq) {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 85a7047d8b03..94593c6282d8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -234,6 +234,7 @@ struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
 			}
 			rq->tag = tag;
 			rq->internal_tag = -1;
+			data->hctx->tags->rqs[rq->tag] = rq;
 		}
 
 		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
-- 
GitLab


From 6a8a21546507a3ec88e81c2ec927a3fb63efa8ff Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Wed, 1 Mar 2017 11:47:22 -0500
Subject: [PATCH 551/898] nbd: stop leaking sockets

This was introduced in the multi-connection patch, we've been leaking
socket's ever since.

Fixes: 9561a7a ("nbd: add multi-connection support")
cc: stable@vger.kernel.org
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/nbd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 0bf2b21a62cb..c7e93f62366f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -689,8 +689,10 @@ static int nbd_clear_sock(struct nbd_device *nbd, struct block_device *bdev)
 	    nbd->num_connections) {
 		int i;
 
-		for (i = 0; i < nbd->num_connections; i++)
+		for (i = 0; i < nbd->num_connections; i++) {
+			sockfd_put(nbd->socks[i]->sock);
 			kfree(nbd->socks[i]);
+		}
 		kfree(nbd->socks);
 		nbd->socks = NULL;
 		nbd->num_connections = 0;
-- 
GitLab


From 6bae363ee3057a14eec93440826813603559273a Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Wed, 1 Mar 2017 14:22:10 -0500
Subject: [PATCH 552/898] blk-mq: Export blk_mq_freeze_queue_wait

Drivers can start a freeze, so this provides a way to wait for frozen.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c         | 3 ++-
 include/linux/blk-mq.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 94593c6282d8..8da2c04bb88f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -75,10 +75,11 @@ void blk_mq_freeze_queue_start(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
 
-static void blk_mq_freeze_queue_wait(struct request_queue *q)
+void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
 	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
 }
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);
 
 /*
  * Guarantee no request is in use, so we can change any data structure of
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 001d30d727c5..8dacf680c851 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -245,6 +245,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);
+void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_reinit_tagset(struct blk_mq_tag_set *set);
 
 int blk_mq_map_queues(struct blk_mq_tag_set *set);
-- 
GitLab


From f91328c40a559362b6e7b7bfee01ca17fda87592 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Wed, 1 Mar 2017 14:22:11 -0500
Subject: [PATCH 553/898] blk-mq: Provide freeze queue timeout

A driver may wish to take corrective action if queued requests do not
complete within a set time.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c         | 9 +++++++++
 include/linux/blk-mq.h | 2 ++
 2 files changed, 11 insertions(+)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 8da2c04bb88f..a5e66a7a3506 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -81,6 +81,15 @@ void blk_mq_freeze_queue_wait(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);
 
+int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
+				     unsigned long timeout)
+{
+	return wait_event_timeout(q->mq_freeze_wq,
+					percpu_ref_is_zero(&q->q_usage_counter),
+					timeout);
+}
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
+
 /*
  * Guarantee no request is in use, so we can change any data structure of
  * the queue afterward.
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8dacf680c851..b296a9006117 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -246,6 +246,8 @@ void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
+int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
+				     unsigned long timeout);
 int blk_mq_reinit_tagset(struct blk_mq_tag_set *set);
 
 int blk_mq_map_queues(struct blk_mq_tag_set *set);
-- 
GitLab


From 302ad8cc09339ea261eef58a8d5f4a116a8ffda5 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Wed, 1 Mar 2017 14:22:12 -0500
Subject: [PATCH 554/898] nvme: Complete all stuck requests

If the nvme driver is shutting down its controller, the drievr will not
start the queues up again, preventing blk-mq's hot CPU notifier from
making forward progress.

To fix that, this patch starts a request_queue freeze when the driver
resets a controller so no new requests may enter. The driver will wait
for frozen after IO queues are restarted to ensure the queue reference
can be reinitialized when nvme requests to unfreeze the queues.

If the driver is doing a safe shutdown, the driver will wait for the
controller to successfully complete all inflight requests so that we
don't unnecessarily fail them. Once the controller has been disabled,
the queues will be restarted to force remaining entered requests to end
in failure so that blk-mq's hot cpu notifier may progress.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/nvme/host/core.c | 47 ++++++++++++++++++++++++++++++++++++++++
 drivers/nvme/host/nvme.h |  4 ++++
 drivers/nvme/host/pci.c  | 33 +++++++++++++++++++++++-----
 3 files changed, 79 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 25ec4e585220..9b3b57fef446 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2344,6 +2344,53 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);
 
+void nvme_unfreeze(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->namespaces_mutex);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		blk_mq_unfreeze_queue(ns->queue);
+	mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_unfreeze);
+
+void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->namespaces_mutex);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
+		if (timeout <= 0)
+			break;
+	}
+	mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
+
+void nvme_wait_freeze(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->namespaces_mutex);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		blk_mq_freeze_queue_wait(ns->queue);
+	mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_wait_freeze);
+
+void nvme_start_freeze(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->namespaces_mutex);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		blk_mq_freeze_queue_start(ns->queue);
+	mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_start_freeze);
+
 void nvme_stop_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index a3da1e90b99d..2aa20e3e5675 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -294,6 +294,10 @@ void nvme_queue_async_events(struct nvme_ctrl *ctrl);
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
+void nvme_unfreeze(struct nvme_ctrl *ctrl);
+void nvme_wait_freeze(struct nvme_ctrl *ctrl);
+void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
+void nvme_start_freeze(struct nvme_ctrl *ctrl);
 
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index eee8f8426ff2..26a5fd05fe88 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1675,21 +1675,34 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
 	int i, queues;
-	u32 csts = -1;
+	bool dead = true;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	del_timer_sync(&dev->watchdog_timer);
 
 	mutex_lock(&dev->shutdown_lock);
-	if (pci_is_enabled(to_pci_dev(dev->dev))) {
-		nvme_stop_queues(&dev->ctrl);
-		csts = readl(dev->bar + NVME_REG_CSTS);
+	if (pci_is_enabled(pdev)) {
+		u32 csts = readl(dev->bar + NVME_REG_CSTS);
+
+		if (dev->ctrl.state == NVME_CTRL_LIVE)
+			nvme_start_freeze(&dev->ctrl);
+		dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) ||
+			pdev->error_state  != pci_channel_io_normal);
 	}
 
+	/*
+	 * Give the controller a chance to complete all entered requests if
+	 * doing a safe shutdown.
+	 */
+	if (!dead && shutdown)
+		nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
+	nvme_stop_queues(&dev->ctrl);
+
 	queues = dev->online_queues - 1;
 	for (i = dev->queue_count - 1; i > 0; i--)
 		nvme_suspend_queue(dev->queues[i]);
 
-	if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
+	if (dead) {
 		/* A device might become IO incapable very soon during
 		 * probe, before the admin queue is configured. Thus,
 		 * queue_count can be 0 here.
@@ -1704,6 +1717,14 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 
 	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
 	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
+
+	/*
+	 * The driver will not be starting up queues again if shutting down so
+	 * must flush all entered requests to their failed completion to avoid
+	 * deadlocking blk-mq hot-cpu notifier.
+	 */
+	if (shutdown)
+		nvme_start_queues(&dev->ctrl);
 	mutex_unlock(&dev->shutdown_lock);
 }
 
@@ -1826,7 +1847,9 @@ static void nvme_reset_work(struct work_struct *work)
 		nvme_remove_namespaces(&dev->ctrl);
 	} else {
 		nvme_start_queues(&dev->ctrl);
+		nvme_wait_freeze(&dev->ctrl);
 		nvme_dev_add(dev);
+		nvme_unfreeze(&dev->ctrl);
 	}
 
 	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
-- 
GitLab


From e02898b423802b1f3a3aaa7f16e896da069ba8f7 Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Wed, 1 Mar 2017 10:42:38 -0800
Subject: [PATCH 555/898] loop: fix LO_FLAGS_PARTSCAN hang

loop_reread_partitions() needs to do I/O, but we just froze the queue,
so we end up waiting forever. This can easily be reproduced with losetup
-P. Fix it by moving the reread to after we unfreeze the queue.

Fixes: ecdd09597a57 ("block/loop: fix race between I/O and set_status")
Reported-by: Tejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/loop.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4b52a1690329..132c9f371dce 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1142,13 +1142,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	     (info->lo_flags & LO_FLAGS_AUTOCLEAR))
 		lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;
 
-	if ((info->lo_flags & LO_FLAGS_PARTSCAN) &&
-	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
-		lo->lo_flags |= LO_FLAGS_PARTSCAN;
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
-		loop_reread_partitions(lo, lo->lo_device);
-	}
-
 	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
 	lo->lo_init[0] = info->lo_init[0];
 	lo->lo_init[1] = info->lo_init[1];
@@ -1163,6 +1156,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 
  exit:
 	blk_mq_unfreeze_queue(lo->lo_queue);
+
+	if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
+	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
+		lo->lo_flags |= LO_FLAGS_PARTSCAN;
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+		loop_reread_partitions(lo, lo->lo_device);
+	}
+
 	return err;
 }
 
-- 
GitLab


From a5a79d00017c9eee68a9bcb40d5dfd6f45f17461 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 2 Mar 2017 16:50:13 +0100
Subject: [PATCH 556/898] block: Initialize bd_bdi on inode initialization

So far we initialized bd_bdi only in bdget(). That is fine for normal
bdev inodes however for the special case of the root inode of
blockdev_superblock that function is never called and thus bd_bdi is
left uninitialized. As a result bdev_evict_inode() may oops doing
bdi_put(root->bd_bdi) on that inode as can be seen when doing:

mount -t bdev none /mnt

Fix the problem by initializing bd_bdi when first allocating the inode
and then reinitializing bd_bdi in bdev_evict_inode().

Thanks to syzkaller team for finding the problem.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: b1d2dc5659b4 ("block: Make blk_get_backing_dev_info() safe without open bdev")
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 fs/block_dev.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 77c30f15a02c..2eca00ec4370 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -870,6 +870,7 @@ static void init_once(void *foo)
 #ifdef CONFIG_SYSFS
 	INIT_LIST_HEAD(&bdev->bd_holder_disks);
 #endif
+	bdev->bd_bdi = &noop_backing_dev_info;
 	inode_init_once(&ei->vfs_inode);
 	/* Initialize mutex for freeze. */
 	mutex_init(&bdev->bd_fsfreeze_mutex);
@@ -884,8 +885,10 @@ static void bdev_evict_inode(struct inode *inode)
 	spin_lock(&bdev_lock);
 	list_del_init(&bdev->bd_list);
 	spin_unlock(&bdev_lock);
-	if (bdev->bd_bdi != &noop_backing_dev_info)
+	if (bdev->bd_bdi != &noop_backing_dev_info) {
 		bdi_put(bdev->bd_bdi);
+		bdev->bd_bdi = &noop_backing_dev_info;
+	}
 }
 
 static const struct super_operations bdev_sops = {
@@ -988,7 +991,6 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
-		bdev->bd_bdi = &noop_backing_dev_info;
 		bdev->bd_block_size = i_blocksize(inode);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
-- 
GitLab


From 7afbeb6df2aa5f9e3a0fc228817a85c16dea0faa Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 24 Feb 2017 12:56:12 +0100
Subject: [PATCH 557/898] s390/ipl: always use load normal for CCW-type re-IPL

commit 14890678687c ("s390/ipl: use load normal for LPAR re-ipl")
missed to convert one code path to use load normal semantics for
re-IPL. Convert the missing code path as well.

Fixes: 14890678687c ("s390/ipl: use load normal for LPAR re-ipl")
Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/ipl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index b67dafb7b7cf..e545ffe5155a 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -564,6 +564,8 @@ static struct kset *ipl_kset;
 
 static void __ipl_run(void *unused)
 {
+	if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW)
+		diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
 	diag308(DIAG308_LOAD_CLEAR, NULL);
 	if (MACHINE_IS_VM)
 		__cpcmd("IPL", NULL, 0, NULL);
-- 
GitLab


From 2e4d88009f57057df7672fa69a32b5224af54d37 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.vnet.ibm.com>
Date: Thu, 2 Mar 2017 15:23:42 +0100
Subject: [PATCH 558/898] KVM: s390: Fix guest migration for huge guests
 resulting in panic

While we can technically not run huge page guests right now, we can
setup a guest with huge pages. Trying to migrate it will trigger a
VM_BUG_ON and, if the kernel is not configured to panic on a BUG, it
will happily try to work on non-existing page table entries.

With this patch, we always return "dirty" if we encounter a large page
when migrating. This at least fixes the immediate problem until we
have proper handling for both kind of pages.

Fixes: 15f36eb ("KVM: s390: Add proper dirty bitmap support to S390 kvm.")
Cc: <stable@vger.kernel.org> # 3.16+

Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/pgtable.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b48dc5f1900b..463e5ef02304 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -608,12 +608,29 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 {
 	spinlock_t *ptl;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
 	pgste_t pgste;
 	pte_t *ptep;
 	pte_t pte;
 	bool dirty;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (!pud)
+		return false;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return false;
+	/* We can't run guests backed by huge pages, but userspace can
+	 * still set them up and then try to migrate them without any
+	 * migration support.
+	 */
+	if (pmd_large(*pmd))
+		return true;
+
+	ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (unlikely(!ptep))
 		return false;
 
-- 
GitLab


From 3131d970f0d86bea41811766d55fc638e382daf3 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 27 Feb 2017 10:13:38 +0100
Subject: [PATCH 559/898] ARM: ux500: resume the second core properly

The pen hold/release scheme was copied over to Ux500 from the ARM
reference designs like most of these at the time. It is not needed
at all, and was mostly removed in commit c00def71efd9
"ARM: ux500: simplify secondary CPU boot".

However on the suspend/resume path and hot plug/unplug of CPUs,
the .cpu_die() callback was still waiting for the pen to be
released which made it spin forever and the second core never come
back online after suspend/resume.

Fix this by simply replacing the strange custom .cpu_die() with
a oneline wfi() just like e.g. the qcom platform does. This fixes
the issue and makes the second core come up properly after
suspend/resume.

As a side effect, this rids us of the completely surplus local
setup.h and hotplug.c files, and we just compile this into platsmp.c
with everything else SMP.

Cc: stable@vger.kernel.org
Fixes: c00def71efd9 ("ARM: ux500: simplify secondary CPU boot")
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-ux500/Makefile     |  3 ---
 arch/arm/mach-ux500/cpu-db8500.c |  2 --
 arch/arm/mach-ux500/hotplug.c    | 37 --------------------------------
 arch/arm/mach-ux500/platsmp.c    |  9 ++++++--
 arch/arm/mach-ux500/setup.h      | 16 --------------
 5 files changed, 7 insertions(+), 60 deletions(-)
 delete mode 100644 arch/arm/mach-ux500/hotplug.c
 delete mode 100644 arch/arm/mach-ux500/setup.h

diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile
index c2499bff4986..a9a3453548f4 100644
--- a/arch/arm/mach-ux500/Makefile
+++ b/arch/arm/mach-ux500/Makefile
@@ -5,7 +5,4 @@
 obj-y				:= pm.o
 obj-$(CONFIG_UX500_SOC_DB8500)	+= cpu-db8500.o
 obj-$(CONFIG_SMP)		+= platsmp.o
-obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS) += pm_domains.o
-
-CFLAGS_hotplug.o		+= -march=armv7-a
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 24529cf58df6..28083ef72819 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -31,8 +31,6 @@
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
 
-#include "setup.h"
-
 #include "db8500-regs.h"
 
 static int __init ux500_l2x0_unlock(void)
diff --git a/arch/arm/mach-ux500/hotplug.c b/arch/arm/mach-ux500/hotplug.c
deleted file mode 100644
index 1cbed0331fd3..000000000000
--- a/arch/arm/mach-ux500/hotplug.c
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License Terms: GNU General Public License v2
- *	Based on ARM realview platform
- *
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- *
- */
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/smp.h>
-
-#include <asm/smp_plat.h>
-
-#include "setup.h"
-
-/*
- * platform-specific code to shutdown a CPU
- *
- * Called with IRQs disabled
- */
-void ux500_cpu_die(unsigned int cpu)
-{
-	/* directly enter low power state, skipping secure registers */
-	for (;;) {
-		__asm__ __volatile__("dsb\n\t" "wfi\n\t"
-				: : : "memory");
-		if (pen_release == cpu_logical_map(cpu)) {
-			/*
-			 * OK, proper wakeup, we're done
-			 */
-			break;
-		}
-	}
-}
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index e0ee139fdebf..19c165aeecd2 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -23,8 +23,6 @@
 #include <asm/smp_plat.h>
 #include <asm/smp_scu.h>
 
-#include "setup.h"
-
 #include "db8500-regs.h"
 
 /* Magic triggers in backup RAM */
@@ -90,6 +88,13 @@ static int ux500_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+void ux500_cpu_die(unsigned int cpu)
+{
+	wfi();
+}
+#endif
+
 static const struct smp_operations ux500_smp_ops __initconst = {
 	.smp_prepare_cpus	= ux500_smp_prepare_cpus,
 	.smp_boot_secondary	= ux500_boot_secondary,
diff --git a/arch/arm/mach-ux500/setup.h b/arch/arm/mach-ux500/setup.h
deleted file mode 100644
index 988e7c77068d..000000000000
--- a/arch/arm/mach-ux500/setup.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright (C) 2009 ST-Ericsson.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * These symbols are needed for board-specific files to call their
- * own cpu-specific files
- */
-#ifndef __ASM_ARCH_SETUP_H
-#define __ASM_ARCH_SETUP_H
-
-extern void ux500_cpu_die(unsigned int cpu);
-
-#endif /*  __ASM_ARCH_SETUP_H */
-- 
GitLab


From 474c90156c8dcc2fa815e6716cc9394d7930cb9c Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 2 Mar 2017 12:17:22 -0800
Subject: [PATCH 560/898] give up on gcc ilog2() constant optimizations

gcc-7 has an "optimization" pass that completely screws up, and
generates the code expansion for the (impossible) case of calling
ilog2() with a zero constant, even when the code gcc compiles does not
actually have a zero constant.

And we try to generate a compile-time error for anybody doing ilog2() on
a constant where that doesn't make sense (be it zero or negative).  So
now gcc7 will fail the build due to our sanity checking, because it
created that constant-zero case that didn't actually exist in the source
code.

There's a whole long discussion on the kernel mailing about how to work
around this gcc bug.  The gcc people themselevs have discussed their
"feature" in

   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=72785

but it's all water under the bridge, because while it looked at one
point like it would be solved by the time gcc7 was released, that was
not to be.

So now we have to deal with this compiler braindamage.

And the only simple approach seems to be to just delete the code that
tries to warn about bad uses of ilog2().

So now "ilog2()" will just return 0 not just for the value 1, but for
any non-positive value too.

It's not like I can recall anybody having ever actually tried to use
this function on any invalid value, but maybe the sanity check just
meant that such code never made it out in public.

Reported-by: Laura Abbott <labbott@redhat.com>
Cc: John Stultz <john.stultz@linaro.org>,
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/log2.h       | 13 ++-----------
 tools/include/linux/log2.h | 13 ++-----------
 2 files changed, 4 insertions(+), 22 deletions(-)

diff --git a/include/linux/log2.h b/include/linux/log2.h
index ef3d4f67118c..c373295f359f 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -15,12 +15,6 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 
-/*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
 /*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
@@ -85,7 +79,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n)				\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n) < 1 ? ____ilog2_NaN() :	\
+		(n) < 2 ? 0 :			\
 		(n) & (1ULL << 63) ? 63 :	\
 		(n) & (1ULL << 62) ? 62 :	\
 		(n) & (1ULL << 61) ? 61 :	\
@@ -148,10 +142,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 		(n) & (1ULL <<  4) ?  4 :	\
 		(n) & (1ULL <<  3) ?  3 :	\
 		(n) & (1ULL <<  2) ?  2 :	\
-		(n) & (1ULL <<  1) ?  1 :	\
-		(n) & (1ULL <<  0) ?  0 :	\
-		____ilog2_NaN()			\
-				   ) :		\
+		1 ) :				\
 	(sizeof(n) <= 4) ?			\
 	__ilog2_u32(n) :			\
 	__ilog2_u64(n)				\
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
index 41446668ccce..d5677d39c1e4 100644
--- a/tools/include/linux/log2.h
+++ b/tools/include/linux/log2.h
@@ -12,12 +12,6 @@
 #ifndef _TOOLS_LINUX_LOG2_H
 #define _TOOLS_LINUX_LOG2_H
 
-/*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
 /*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
@@ -78,7 +72,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n)				\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n) < 1 ? ____ilog2_NaN() :	\
+		(n) < 2 ? 0 :			\
 		(n) & (1ULL << 63) ? 63 :	\
 		(n) & (1ULL << 62) ? 62 :	\
 		(n) & (1ULL << 61) ? 61 :	\
@@ -141,10 +135,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 		(n) & (1ULL <<  4) ?  4 :	\
 		(n) & (1ULL <<  3) ?  3 :	\
 		(n) & (1ULL <<  2) ?  2 :	\
-		(n) & (1ULL <<  1) ?  1 :	\
-		(n) & (1ULL <<  0) ?  0 :	\
-		____ilog2_NaN()			\
-				   ) :		\
+		1 ) :				\
 	(sizeof(n) <= 4) ?			\
 	__ilog2_u32(n) :			\
 	__ilog2_u64(n)				\
-- 
GitLab


From e3330039ea28dc199e3b2da993895ff742a91adf Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 27 Feb 2017 16:07:43 -0800
Subject: [PATCH 561/898] ipv6: check for ip6_null_entry in
 __ip6_del_rt_siblings()

Andrey reported a NULL pointer deref bug in ipv6_route_ioctl()
-> ip6_route_del() -> __ip6_del_rt_siblings() code path. This is
because ip6_null_entry is returned in this path since ip6_null_entry
is kinda default for a ipv6 route table root node. Quote from
David Ahern:

 ip6_null_entry is the root of all ipv6 fib tables making it integrated
 into the table ...

We should ignore any attempt of trying to delete it, like we do in
__ip6_del_rt() path and several others.

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Fixes: 0ae8133586ad ("net: ipv6: Allow shorthand delete of all nexthops in multipath route")
Cc: David Ahern <dsa@cumulusnetworks.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d94f1dfa54c8..43ca90d50ae9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2169,10 +2169,13 @@ int ip6_del_rt(struct rt6_info *rt)
 static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 {
 	struct nl_info *info = &cfg->fc_nlinfo;
+	struct net *net = info->nl_net;
 	struct sk_buff *skb = NULL;
 	struct fib6_table *table;
-	int err;
+	int err = -ENOENT;
 
+	if (rt == net->ipv6.ip6_null_entry)
+		goto out_put;
 	table = rt->rt6i_table;
 	write_lock_bh(&table->tb6_lock);
 
@@ -2184,7 +2187,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 		if (skb) {
 			u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
-			if (rt6_fill_node(info->nl_net, skb, rt,
+			if (rt6_fill_node(net, skb, rt,
 					  NULL, NULL, 0, RTM_DELROUTE,
 					  info->portid, seq, 0) < 0) {
 				kfree_skb(skb);
@@ -2198,17 +2201,18 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 					 rt6i_siblings) {
 			err = fib6_del(sibling, info);
 			if (err)
-				goto out;
+				goto out_unlock;
 		}
 	}
 
 	err = fib6_del(rt, info);
-out:
+out_unlock:
 	write_unlock_bh(&table->tb6_lock);
+out_put:
 	ip6_rt_put(rt);
 
 	if (skb) {
-		rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV6_ROUTE,
+		rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
 			    info->nlh, gfp_any());
 	}
 	return err;
-- 
GitLab


From 9aea7779b764a11e357d3c74af6aee3cf90f2045 Mon Sep 17 00:00:00 2001
From: Alban Bedel <alban.bedel@avionic-design.de>
Date: Tue, 28 Feb 2017 18:08:55 +0100
Subject: [PATCH 562/898] drivers: net: xgene: Fix crash on DT systems

On DT systems the driver require a clock, but the probe just print a
warning and continue, leading to a crash when resetting the device.
To fix this crash and properly handle probe deferals only ignore the
missing clock if DT isn't used or if the clock doesn't exist.

Signed-off-by: Alban Bedel <alban.bedel@avionic-design.de>
Acked-by: Iyappan Subramanian <isubramanian@apm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index e536301acfde..b3568c453b14 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -1749,6 +1749,12 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata)
 
 	pdata->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pdata->clk)) {
+		/* Abort if the clock is defined but couldn't be retrived.
+		 * Always abort if the clock is missing on DT system as
+		 * the driver can't cope with this case.
+		 */
+		if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node)
+			return PTR_ERR(pdata->clk);
 		/* Firmware may have set up the clock already. */
 		dev_info(dev, "clocks have been setup already\n");
 	}
-- 
GitLab


From 402168b4c2dc0734b8fbd282eff77da0275c5129 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Tue, 28 Feb 2017 15:02:51 -0600
Subject: [PATCH 563/898] amd-xgbe: Stop the PHY before releasing interrupts

Some configurations require the use of the hardware's MDIO support to
communicate with external PHYs. The MDIO commands indicate completion
through the device interrupt. When bringing down the device the interrupts
were released before stopping the external PHY, resulting in MDIO command
timeouts. Move the stopping of the PHY to before the releasing of the
interrupts.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 3aa457c8ca21..248f60d171a5 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1131,12 +1131,12 @@ static void xgbe_stop(struct xgbe_prv_data *pdata)
 	hw_if->disable_tx(pdata);
 	hw_if->disable_rx(pdata);
 
+	phy_if->phy_stop(pdata);
+
 	xgbe_free_irqs(pdata);
 
 	xgbe_napi_disable(pdata, 1);
 
-	phy_if->phy_stop(pdata);
-
 	hw_if->exit(pdata);
 
 	channel = pdata->channel;
-- 
GitLab


From b42c6761fd1651f564491b53016046c9ebf0b2a9 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Tue, 28 Feb 2017 15:03:01 -0600
Subject: [PATCH 564/898] amd-xgbe: Be sure to set MDIO modes on device
 (re)start

The MDIO register mode is set when the device is probed. But when the
device is brought down and then back up, the MDIO register mode has been
reset.  Be sure to reset the mode during device startup and only change
the mode of the address specified.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c    |  2 +-
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 22 +++++++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index a7d16db5c4b2..937f37a5dcb2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1323,7 +1323,7 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 static int xgbe_set_ext_mii_mode(struct xgbe_prv_data *pdata, unsigned int port,
 				 enum xgbe_mdio_mode mode)
 {
-	unsigned int reg_val = 0;
+	unsigned int reg_val = XGMAC_IOREAD(pdata, MAC_MDIOCL22R);
 
 	switch (mode) {
 	case XGBE_MDIO_MODE_CL22:
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 9d8c953083b4..04804cbb7dc1 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -875,6 +875,16 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
 	    !phy_data->sfp_phy_avail)
 		return 0;
 
+	/* Set the proper MDIO mode for the PHY */
+	ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->mdio_addr,
+					    phy_data->phydev_mode);
+	if (ret) {
+		netdev_err(pdata->netdev,
+			   "mdio port/clause not compatible (%u/%u)\n",
+			   phy_data->mdio_addr, phy_data->phydev_mode);
+		return ret;
+	}
+
 	/* Create and connect to the PHY device */
 	phydev = get_phy_device(phy_data->mii, phy_data->mdio_addr,
 				(phy_data->phydev_mode == XGBE_MDIO_MODE_CL45));
@@ -2722,6 +2732,18 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
 	if (ret)
 		return ret;
 
+	/* Set the proper MDIO mode for the re-driver */
+	if (phy_data->redrv && !phy_data->redrv_if) {
+		ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->redrv_addr,
+						    XGBE_MDIO_MODE_CL22);
+		if (ret) {
+			netdev_err(pdata->netdev,
+				   "redriver mdio port not compatible (%u)\n",
+				   phy_data->redrv_addr);
+			return ret;
+		}
+	}
+
 	/* Start in highest supported mode */
 	xgbe_phy_set_mode(pdata, phy_data->start_mode);
 
-- 
GitLab


From 2697ea5a859b83ca49511dcfd98daf42584eb3cf Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Tue, 28 Feb 2017 15:03:10 -0600
Subject: [PATCH 565/898] amd-xgbe: Don't overwrite SFP PHY mod_absent settings

If an SFP module is not present, xgbe_phy_sfp_phy_settings() should
return after applying the default settings. Currently there is no return
statement and the default settings are overwritten.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 04804cbb7dc1..e707c49cc55a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -716,6 +716,8 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata)
 		pdata->phy.duplex = DUPLEX_UNKNOWN;
 		pdata->phy.autoneg = AUTONEG_ENABLE;
 		pdata->phy.advertising = pdata->phy.supported;
+
+		return;
 	}
 
 	pdata->phy.advertising &= ~ADVERTISED_Autoneg;
-- 
GitLab


From 7b36a7189fc320f0b783dd51bd1f541db56cfbdd Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Thu, 2 Mar 2017 13:59:08 -0700
Subject: [PATCH 566/898] block: don't call ioc_exit_icq() with the queue lock
 held for blk-mq

For legacy scheduling, we always call ioc_exit_icq() with both the
ioc and queue lock held. This poses a problem for blk-mq with
scheduling, since the queue lock isn't what we use in the scheduler.
And since we don't need the queue lock held for ioc exit there,
don't grab it and leave any extra locking up to the blk-mq scheduler.

Reported-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Paolo Valente <paolo.valente@linaro.org>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-ioc.c   | 44 +++++++++++++++++++++++++++++++-------------
 block/blk-sysfs.c |  2 --
 block/elevator.c  |  2 --
 3 files changed, 31 insertions(+), 17 deletions(-)

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index b12f9c87b4c3..0d7c96c0ba71 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -36,8 +36,8 @@ static void icq_free_icq_rcu(struct rcu_head *head)
 }
 
 /*
- * Exit an icq. Called with both ioc and q locked for sq, only ioc locked for
- * mq.
+ * Exit an icq. Called with ioc locked for blk-mq, and with both ioc
+ * and queue locked for legacy.
  */
 static void ioc_exit_icq(struct io_cq *icq)
 {
@@ -54,7 +54,10 @@ static void ioc_exit_icq(struct io_cq *icq)
 	icq->flags |= ICQ_EXITED;
 }
 
-/* Release an icq.  Called with both ioc and q locked. */
+/*
+ * Release an icq. Called with ioc locked for blk-mq, and with both ioc
+ * and queue locked for legacy.
+ */
 static void ioc_destroy_icq(struct io_cq *icq)
 {
 	struct io_context *ioc = icq->ioc;
@@ -62,7 +65,6 @@ static void ioc_destroy_icq(struct io_cq *icq)
 	struct elevator_type *et = q->elevator->type;
 
 	lockdep_assert_held(&ioc->lock);
-	lockdep_assert_held(q->queue_lock);
 
 	radix_tree_delete(&ioc->icq_tree, icq->q->id);
 	hlist_del_init(&icq->ioc_node);
@@ -222,24 +224,40 @@ void exit_io_context(struct task_struct *task)
 	put_io_context_active(ioc);
 }
 
+static void __ioc_clear_queue(struct list_head *icq_list)
+{
+	unsigned long flags;
+
+	while (!list_empty(icq_list)) {
+		struct io_cq *icq = list_entry(icq_list->next,
+					       struct io_cq, q_node);
+		struct io_context *ioc = icq->ioc;
+
+		spin_lock_irqsave(&ioc->lock, flags);
+		ioc_destroy_icq(icq);
+		spin_unlock_irqrestore(&ioc->lock, flags);
+	}
+}
+
 /**
  * ioc_clear_queue - break any ioc association with the specified queue
  * @q: request_queue being cleared
  *
- * Walk @q->icq_list and exit all io_cq's.  Must be called with @q locked.
+ * Walk @q->icq_list and exit all io_cq's.
  */
 void ioc_clear_queue(struct request_queue *q)
 {
-	lockdep_assert_held(q->queue_lock);
+	LIST_HEAD(icq_list);
 
-	while (!list_empty(&q->icq_list)) {
-		struct io_cq *icq = list_entry(q->icq_list.next,
-					       struct io_cq, q_node);
-		struct io_context *ioc = icq->ioc;
+	spin_lock_irq(q->queue_lock);
+	list_splice_init(&q->icq_list, &icq_list);
 
-		spin_lock(&ioc->lock);
-		ioc_destroy_icq(icq);
-		spin_unlock(&ioc->lock);
+	if (q->mq_ops) {
+		spin_unlock_irq(q->queue_lock);
+		__ioc_clear_queue(&icq_list);
+	} else {
+		__ioc_clear_queue(&icq_list);
+		spin_unlock_irq(q->queue_lock);
 	}
 }
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 002af836aa87..c44b321335f3 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -815,9 +815,7 @@ static void blk_release_queue(struct kobject *kobj)
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {
-		spin_lock_irq(q->queue_lock);
 		ioc_clear_queue(q);
-		spin_unlock_irq(q->queue_lock);
 		elevator_exit(q->elevator);
 	}
 
diff --git a/block/elevator.c b/block/elevator.c
index ac1c9f481a98..01139f549b5b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -983,9 +983,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 		if (old_registered)
 			elv_unregister_queue(q);
 
-		spin_lock_irq(q->queue_lock);
 		ioc_clear_queue(q);
-		spin_unlock_irq(q->queue_lock);
 	}
 
 	/* allocate, init and register new elevator */
-- 
GitLab


From 11bd44f62d86115796109b0349e6e191bc99b45a Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Wed, 1 Mar 2017 11:18:53 +0530
Subject: [PATCH 567/898] cxgb4: update latest firmware version supported

Change t4fw_version.h to update latest firmware version
number to 1.16.33.0.

Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index 5fdaa16426c5..fa376444e57c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -37,7 +37,7 @@
 
 #define T4FW_VERSION_MAJOR 0x01
 #define T4FW_VERSION_MINOR 0x10
-#define T4FW_VERSION_MICRO 0x1A
+#define T4FW_VERSION_MICRO 0x21
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -46,7 +46,7 @@
 
 #define T5FW_VERSION_MAJOR 0x01
 #define T5FW_VERSION_MINOR 0x10
-#define T5FW_VERSION_MICRO 0x1A
+#define T5FW_VERSION_MICRO 0x21
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -55,7 +55,7 @@
 
 #define T6FW_VERSION_MAJOR 0x01
 #define T6FW_VERSION_MINOR 0x10
-#define T6FW_VERSION_MICRO 0x1A
+#define T6FW_VERSION_MICRO 0x21
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
-- 
GitLab


From f1304f7ba3981e71dcf2ac7db92949eeab49b1bf Mon Sep 17 00:00:00 2001
From: Peter Downs <padowns@gmail.com>
Date: Wed, 1 Mar 2017 01:01:17 -0800
Subject: [PATCH 568/898] openvswitch: actions: fixed a brace coding style
 warning

Fixed a brace coding style warning reported by checkpatch.pl

Signed-off-by: Peter Downs <padowns@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index b1beb2b94ec7..c82301ce3fff 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -796,9 +796,8 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		unsigned long orig_dst;
 		struct rt6_info ovs_rt;
 
-		if (!v6ops) {
+		if (!v6ops)
 			goto err;
-		}
 
 		prepare_frag(vport, skb, orig_network_offset,
 			     ovs_key_mac_proto(key));
-- 
GitLab


From d5afb6f9b6bb2c57bd0c05e76e12489dc0d037d9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 1 Mar 2017 16:35:07 -0300
Subject: [PATCH 569/898] dccp: Unlock sock before calling sk_free()

The code where sk_clone() came from created a new socket and locked it,
but then, on the error path didn't unlock it.

This problem stayed there for a long while, till b0691c8ee7c2 ("net:
Unlock sock before calling sk_free()") fixed it, but unfortunately the
callers of sk_clone() (now sk_clone_locked()) were not audited and the
one in dccp_create_openreq_child() remained.

Now in the age of the syskaller fuzzer, this was finally uncovered, as
reported by Dmitry:

 ---- 8< ----

I've got the following report while running syzkaller fuzzer on
86292b33d4b7 ("Merge branch 'akpm' (patches from Andrew)")

  [ BUG: held lock freed! ]
  4.10.0+ #234 Not tainted
  -------------------------
  syz-executor6/6898 is freeing memory
  ffff88006286cac0-ffff88006286d3b7, with a lock still held there!
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504
  5 locks held by syz-executor6/6898:
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>] lock_sock
  include/net/sock.h:1460 [inline]
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>]
  inet_stream_connect+0x44/0xa0 net/ipv4/af_inet.c:681
   #1:  (rcu_read_lock){......}, at: [<ffffffff83bc1c2a>]
  inet6_csk_xmit+0x12a/0x5d0 net/ipv6/inet6_connection_sock.c:126
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_unlink
  include/linux/skbuff.h:1767 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_dequeue
  include/linux/skbuff.h:1783 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>]
  process_backlog+0x264/0x730 net/core/dev.c:4835
   #3:  (rcu_read_lock){......}, at: [<ffffffff83aeb5c0>]
  ip6_input_finish+0x0/0x1700 net/ipv6/ip6_input.c:59
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504

Fix it just like was done by b0691c8ee7c2 ("net: Unlock sock before calling
sk_free()").

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170301153510.GE15145@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/minisocks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 53eddf99e4f6..d20d948a98ed 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
+			bh_unlock_sock(newsk);
 			sk_free(newsk);
 			return NULL;
 		}
-- 
GitLab


From 94352d45092c23874532221b4d1e4721df9d63df Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 1 Mar 2017 16:35:08 -0300
Subject: [PATCH 570/898] net: Introduce sk_clone_lock() error path routine

When handling problems in cloning a socket with the sk_clone_locked()
function we need to perform several steps that were open coded in it and
its callers, so introduce a routine to avoid this duplication:
sk_free_unlock_clone().

Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/net-ui6laqkotycunhtmqryl9bfx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h   |  1 +
 net/core/sock.c      | 16 +++++++++++-----
 net/dccp/minisocks.c |  6 +-----
 3 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 9ccefa5c5487..5e5997654db6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1526,6 +1526,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 void sk_free(struct sock *sk);
 void sk_destruct(struct sock *sk);
 struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
+void sk_free_unlock_clone(struct sock *sk);
 
 struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 			     gfp_t priority);
diff --git a/net/core/sock.c b/net/core/sock.c
index e7d74940e863..f6fd79f33097 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1539,11 +1539,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			is_charged = sk_filter_charge(newsk, filter);
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
-			/* It is still raw copy of parent, so invalidate
-			 * destructor and make plain sk_free() */
-			newsk->sk_destruct = NULL;
-			bh_unlock_sock(newsk);
-			sk_free(newsk);
+			sk_free_unlock_clone(newsk);
 			newsk = NULL;
 			goto out;
 		}
@@ -1592,6 +1588,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 }
 EXPORT_SYMBOL_GPL(sk_clone_lock);
 
+void sk_free_unlock_clone(struct sock *sk)
+{
+	/* It is still raw copy of parent, so invalidate
+	 * destructor and make plain sk_free() */
+	sk->sk_destruct = NULL;
+	bh_unlock_sock(sk);
+	sk_free(sk);
+}
+EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
+
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
 	u32 max_segs = 1;
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index d20d948a98ed..e267e6f4c9a5 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -119,11 +119,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
 		 * Activate features: initialise CCIDs, sequence windows etc.
 		 */
 		if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) {
-			/* It is still raw copy of parent, so invalidate
-			 * destructor and make plain sk_free() */
-			newsk->sk_destruct = NULL;
-			bh_unlock_sock(newsk);
-			sk_free(newsk);
+			sk_free_unlock_clone(newsk);
 			return NULL;
 		}
 		dccp_init_xmit_timers(newsk);
-- 
GitLab


From 113285b473824922498d07d7f82459507b9792eb Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Thu, 2 Mar 2017 13:26:04 -0700
Subject: [PATCH 571/898] blk-mq: ensure that bd->last is always set correctly

When drivers are called with a request in blk-mq, blk-mq flags the
state such that the driver knows if this is the last request in
this call chain or not. The driver can then use that information
to defer kicking off IO until bd->last is true. However, with blk-mq
and scheduling, we need to allocate a driver tag for a request before
it can be issued. If we fail to allocate such a tag, we could end up
in the situation where the last request issued did not have
bd->last == true set. This can then cause a driver hang.

This fixes a hang with virtio-blk, which uses bd->last as a hint
on whether to kick the queue or not.

Reported-by: Chris Mason <clm@fb.com>
Tested-by: Chris Mason <clm@fb.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c | 50 +++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 43 insertions(+), 7 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a5e66a7a3506..e797607dab89 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -876,12 +876,9 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 	return false;
 }
 
-static void blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
-				  struct request *rq)
+static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
+				    struct request *rq)
 {
-	if (rq->tag == -1 || rq->internal_tag == -1)
-		return;
-
 	blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
 	rq->tag = -1;
 
@@ -891,6 +888,26 @@ static void blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 	}
 }
 
+static void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
+				       struct request *rq)
+{
+	if (rq->tag == -1 || rq->internal_tag == -1)
+		return;
+
+	__blk_mq_put_driver_tag(hctx, rq);
+}
+
+static void blk_mq_put_driver_tag(struct request *rq)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	if (rq->tag == -1 || rq->internal_tag == -1)
+		return;
+
+	hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
+	__blk_mq_put_driver_tag(hctx, rq);
+}
+
 /*
  * If we fail getting a driver tag because all the driver tags are already
  * assigned and on the dispatch list, BUT the first entry does not have a
@@ -1000,7 +1017,19 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 
 		bd.rq = rq;
 		bd.list = dptr;
-		bd.last = list_empty(list);
+
+		/*
+		 * Flag last if we have no more requests, or if we have more
+		 * but can't assign a driver tag to it.
+		 */
+		if (list_empty(list))
+			bd.last = true;
+		else {
+			struct request *nxt;
+
+			nxt = list_first_entry(list, struct request, queuelist);
+			bd.last = !blk_mq_get_driver_tag(nxt, NULL, false);
+		}
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
 		switch (ret) {
@@ -1008,7 +1037,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 			queued++;
 			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
-			blk_mq_put_driver_tag(hctx, rq);
+			blk_mq_put_driver_tag_hctx(hctx, rq);
 			list_add(&rq->queuelist, list);
 			__blk_mq_requeue_request(rq);
 			break;
@@ -1038,6 +1067,13 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 	 * that is where we will continue on next queue run.
 	 */
 	if (!list_empty(list)) {
+		/*
+		 * If we got a driver tag for the next request already,
+		 * free it again.
+		 */
+		rq = list_first_entry(list, struct request, queuelist);
+		blk_mq_put_driver_tag(rq);
+
 		spin_lock(&hctx->lock);
 		list_splice_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
-- 
GitLab


From 7db92362d2fee5887f6b0c41653b8c9f8f5d6020 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 1 Mar 2017 13:29:48 -0800
Subject: [PATCH 572/898] tcp: fix potential double free issue for fastopen_req

tp->fastopen_req could potentially be double freed if a malicious
user does the following:
1. Enable TCP_FASTOPEN_CONNECT sockopt and do a connect() on the socket.
2. Call connect() with AF_UNSPEC to disconnect the socket.
3. Make this socket a listening socket by calling listen().
4. Accept incoming connections and generate child sockets. All child
   sockets will get a copy of the pointer of fastopen_req.
5. Call close() on all sockets. fastopen_req will get freed multiple
   times.

Fixes: 19f6d3f3c842 ("net/tcp-fastopen: Add new API support")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index da385ae997a3..cf4555581282 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1110,9 +1110,14 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags, 1);
-	inet->defer_connect = 0;
-	*copied = tp->fastopen_req->copied;
-	tcp_free_fastopen_req(tp);
+	/* fastopen_req could already be freed in __inet_stream_connect
+	 * if the connection times out or gets rst
+	 */
+	if (tp->fastopen_req) {
+		*copied = tp->fastopen_req->copied;
+		tcp_free_fastopen_req(tp);
+		inet->defer_connect = 0;
+	}
 	return err;
 }
 
@@ -2318,6 +2323,10 @@ int tcp_disconnect(struct sock *sk, int flags)
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
 
+	/* Clean up fastopen related fields */
+	tcp_free_fastopen_req(tp);
+	inet->defer_connect = 0;
+
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
 	sk->sk_error_report(sk);
-- 
GitLab


From 332524eaf739296bfc86c26d1b86a8c0040d7818 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 21 Feb 2017 21:42:30 +0100
Subject: [PATCH 573/898] ARM: deconfig: fix the moxart defconfig

The moxart defconfig wasn't even building a kernel for Moxart,
it was building a kernel for V4T on the nothing platform. Switch
to MULTI_V4 and keep the right drivers, update a few selections.
Now it (presumably) builds a minimalist Moxart kernel again.

Cc: Jonas Jensen <jonas.jensen@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/configs/moxart_defconfig | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig
index a3cb76cfb828..b2ddd534867f 100644
--- a/arch/arm/configs/moxart_defconfig
+++ b/arch/arm/configs/moxart_defconfig
@@ -18,9 +18,8 @@ CONFIG_EMBEDDED=y
 # CONFIG_LBDAF is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_ARCH_MULTI_V4T=y
+CONFIG_ARCH_MULTI_V4=y
 # CONFIG_ARCH_MULTI_V7 is not set
-CONFIG_KEYBOARD_GPIO_POLLED=y
 CONFIG_ARCH_MOXART=y
 CONFIG_MACH_UC7112LX=y
 CONFIG_PREEMPT=y
@@ -94,12 +93,10 @@ CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
-CONFIG_DEBUG_GPIO=y
-CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_MOXART=y
-CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_GPIO=y
+CONFIG_POWER_SUPPLY=y
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_CORE=y
@@ -107,10 +104,13 @@ CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_MOXART_WDT=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
-CONFIG_MMC_SDHCI_MOXART=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_MOXART=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_ONESHOT=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-- 
GitLab


From be12502e2e64854dbe0a2ddff6d26ec1143d6890 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 1 Mar 2017 17:24:47 -0800
Subject: [PATCH 574/898] drivers: net: ethernet: remove incorrect __exit
 markups

Even if bus is not hot-pluggable, devices can be unbound from the
driver via sysfs, so we should not be using __exit annotations on
remove() methods. The only exception is drivers registered with
platform_driver_probe() which specifically disables sysfs bind/unbind
attributes.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/declance.c        | 30 +++++++++++-----------
 drivers/net/ethernet/broadcom/sb1250-mac.c |  4 +--
 drivers/net/ethernet/faraday/ftgmac100.c   |  4 +--
 drivers/net/ethernet/faraday/ftmac100.c    |  4 +--
 drivers/net/ethernet/seeq/sgiseeq.c        |  4 +--
 drivers/net/ethernet/sgi/meth.c            |  4 +--
 6 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 76e5fc7adff5..6c98901f1b89 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -1276,18 +1276,6 @@ static int dec_lance_probe(struct device *bdev, const int type)
 	return ret;
 }
 
-static void __exit dec_lance_remove(struct device *bdev)
-{
-	struct net_device *dev = dev_get_drvdata(bdev);
-	resource_size_t start, len;
-
-	unregister_netdev(dev);
-	start = to_tc_dev(bdev)->resource.start;
-	len = to_tc_dev(bdev)->resource.end - start + 1;
-	release_mem_region(start, len);
-	free_netdev(dev);
-}
-
 /* Find all the lance cards on the system and initialize them */
 static int __init dec_lance_platform_probe(void)
 {
@@ -1320,7 +1308,7 @@ static void __exit dec_lance_platform_remove(void)
 
 #ifdef CONFIG_TC
 static int dec_lance_tc_probe(struct device *dev);
-static int __exit dec_lance_tc_remove(struct device *dev);
+static int dec_lance_tc_remove(struct device *dev);
 
 static const struct tc_device_id dec_lance_tc_table[] = {
 	{ "DEC     ", "PMAD-AA " },
@@ -1334,7 +1322,7 @@ static struct tc_driver dec_lance_tc_driver = {
 		.name	= "declance",
 		.bus	= &tc_bus_type,
 		.probe	= dec_lance_tc_probe,
-		.remove	= __exit_p(dec_lance_tc_remove),
+		.remove	= dec_lance_tc_remove,
 	},
 };
 
@@ -1346,7 +1334,19 @@ static int dec_lance_tc_probe(struct device *dev)
         return status;
 }
 
-static int __exit dec_lance_tc_remove(struct device *dev)
+static void dec_lance_remove(struct device *bdev)
+{
+	struct net_device *dev = dev_get_drvdata(bdev);
+	resource_size_t start, len;
+
+	unregister_netdev(dev);
+	start = to_tc_dev(bdev)->resource.start;
+	len = to_tc_dev(bdev)->resource.end - start + 1;
+	release_mem_region(start, len);
+	free_netdev(dev);
+}
+
+static int dec_lance_tc_remove(struct device *dev)
 {
         put_device(dev);
         dec_lance_remove(dev);
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 89d4feba1a9a..55c8e25b43d9 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -2617,7 +2617,7 @@ static int sbmac_probe(struct platform_device *pldev)
 	return err;
 }
 
-static int __exit sbmac_remove(struct platform_device *pldev)
+static int sbmac_remove(struct platform_device *pldev)
 {
 	struct net_device *dev = platform_get_drvdata(pldev);
 	struct sbmac_softc *sc = netdev_priv(dev);
@@ -2634,7 +2634,7 @@ static int __exit sbmac_remove(struct platform_device *pldev)
 
 static struct platform_driver sbmac_driver = {
 	.probe = sbmac_probe,
-	.remove = __exit_p(sbmac_remove),
+	.remove = sbmac_remove,
 	.driver = {
 		.name = sbmac_string,
 	},
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 262587240c86..928b0df2b8e0 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1456,7 +1456,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 	return err;
 }
 
-static int __exit ftgmac100_remove(struct platform_device *pdev)
+static int ftgmac100_remove(struct platform_device *pdev)
 {
 	struct net_device *netdev;
 	struct ftgmac100 *priv;
@@ -1483,7 +1483,7 @@ MODULE_DEVICE_TABLE(of, ftgmac100_of_match);
 
 static struct platform_driver ftgmac100_driver = {
 	.probe	= ftgmac100_probe,
-	.remove	= __exit_p(ftgmac100_remove),
+	.remove	= ftgmac100_remove,
 	.driver	= {
 		.name		= DRV_NAME,
 		.of_match_table	= ftgmac100_of_match,
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index c0ddbbe6c226..6ac336b546e6 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -1156,7 +1156,7 @@ static int ftmac100_probe(struct platform_device *pdev)
 	return err;
 }
 
-static int __exit ftmac100_remove(struct platform_device *pdev)
+static int ftmac100_remove(struct platform_device *pdev)
 {
 	struct net_device *netdev;
 	struct ftmac100 *priv;
@@ -1176,7 +1176,7 @@ static int __exit ftmac100_remove(struct platform_device *pdev)
 
 static struct platform_driver ftmac100_driver = {
 	.probe		= ftmac100_probe,
-	.remove		= __exit_p(ftmac100_remove),
+	.remove		= ftmac100_remove,
 	.driver		= {
 		.name	= DRV_NAME,
 	},
diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c
index ed34196028b8..70347720fdf9 100644
--- a/drivers/net/ethernet/seeq/sgiseeq.c
+++ b/drivers/net/ethernet/seeq/sgiseeq.c
@@ -807,7 +807,7 @@ static int sgiseeq_probe(struct platform_device *pdev)
 	return err;
 }
 
-static int __exit sgiseeq_remove(struct platform_device *pdev)
+static int sgiseeq_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct sgiseeq_private *sp = netdev_priv(dev);
@@ -822,7 +822,7 @@ static int __exit sgiseeq_remove(struct platform_device *pdev)
 
 static struct platform_driver sgiseeq_driver = {
 	.probe	= sgiseeq_probe,
-	.remove	= __exit_p(sgiseeq_remove),
+	.remove	= sgiseeq_remove,
 	.driver = {
 		.name	= "sgiseeq",
 	}
diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c
index 69d2d30e5ef1..ea55abd62ec7 100644
--- a/drivers/net/ethernet/sgi/meth.c
+++ b/drivers/net/ethernet/sgi/meth.c
@@ -854,7 +854,7 @@ static int meth_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __exit meth_remove(struct platform_device *pdev)
+static int meth_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
 
@@ -866,7 +866,7 @@ static int __exit meth_remove(struct platform_device *pdev)
 
 static struct platform_driver meth_driver = {
 	.probe	= meth_probe,
-	.remove	= __exit_p(meth_remove),
+	.remove	= meth_remove,
 	.driver = {
 		.name	= "meth",
 	}
-- 
GitLab


From 9d6acb3bc9058d1fd7a5297d71f14213679bb4bd Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 1 Mar 2017 20:48:39 -0800
Subject: [PATCH 575/898] ipv6: ignore null_entry in inet6_rtm_getroute() too

Like commit 1f17e2f2c8a8 ("net: ipv6: ignore null_entry on route dumps"),
we need to ignore null entry in inet6_rtm_getroute() too.

Return -ENETUNREACH here to sync with IPv4 behavior, as suggested by David.

Fixes: a1a22c1206 ("net: ipv6: Keep nexthop of multipath route on admin down")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 43ca90d50ae9..229bfcc451ef 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3632,6 +3632,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 		rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
 	}
 
+	if (rt == net->ipv6.ip6_null_entry) {
+		err = rt->dst.error;
+		ip6_rt_put(rt);
+		goto errout;
+	}
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb) {
 		ip6_rt_put(rt);
-- 
GitLab


From 152669bd3cd2407d6f556009b95ee249c0c1a462 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Thu, 2 Mar 2017 13:00:53 +0000
Subject: [PATCH 576/898] netvsc: fix use-after-free in netvsc_change_mtu()

'nvdev' is freed in rndis_filter_device_remove -> netvsc_device_remove ->
free_netvsc_device, so we mustn't access it, before it's re-created in
rndis_filter_device_add -> netvsc_device_add.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 2d3cdb026a99..bc05c895d958 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -859,15 +859,22 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	if (ret)
 		goto out;
 
+	memset(&device_info, 0, sizeof(device_info));
+	device_info.ring_size = ring_size;
+	device_info.num_chn = nvdev->num_chn;
+	device_info.max_num_vrss_chns = nvdev->num_chn;
+
 	ndevctx->start_remove = true;
 	rndis_filter_device_remove(hdev, nvdev);
 
+	/* 'nvdev' has been freed in rndis_filter_device_remove() ->
+	 * netvsc_device_remove () -> free_netvsc_device().
+	 * We mustn't access it before it's re-created in
+	 * rndis_filter_device_add() -> netvsc_device_add().
+	 */
+
 	ndev->mtu = mtu;
 
-	memset(&device_info, 0, sizeof(device_info));
-	device_info.ring_size = ring_size;
-	device_info.num_chn = nvdev->num_chn;
-	device_info.max_num_vrss_chns = nvdev->num_chn;
 	rndis_filter_device_add(hdev, &device_info);
 
 out:
-- 
GitLab


From 31c05415f5b471fd333fe42629788364faea8e0d Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 2 Mar 2017 12:24:36 -0800
Subject: [PATCH 577/898] bonding: use ETH_MAX_MTU as max mtu

This restores the ability of setting bond device's mtu to 9000.

Fixes: 91572088e3fd ("net: use core MTU range checking in core net infra")
Reported-by: daznis@gmail.com
Reported-by: Brad Campbell <lists2009@fnarfbargle.com>
Cc: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6321f12630c8..8a4ba8b88e52 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4179,6 +4179,7 @@ void bond_setup(struct net_device *bond_dev)
 
 	/* Initialize the device entry points */
 	ether_setup(bond_dev);
+	bond_dev->max_mtu = ETH_MAX_MTU;
 	bond_dev->netdev_ops = &bond_netdev_ops;
 	bond_dev->ethtool_ops = &bond_ethtool_ops;
 
-- 
GitLab


From 9f674e48c13dcbc31ac903433727837795b81efe Mon Sep 17 00:00:00 2001
From: Anoob Soman <anoob.soman@citrix.com>
Date: Thu, 2 Mar 2017 10:50:20 +0000
Subject: [PATCH 578/898] xen-netback: Use GFP_ATOMIC to allocate hash

Allocation of new_hash, inside xenvif_new_hash(), always happen
in softirq context, so use GFP_ATOMIC instead of GFP_KERNEL for new
hash allocation.

Signed-off-by: Anoob Soman <anoob.soman@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/hash.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
index e8c5dddc54ba..3c4c58b9fe76 100644
--- a/drivers/net/xen-netback/hash.c
+++ b/drivers/net/xen-netback/hash.c
@@ -39,7 +39,7 @@ static void xenvif_add_hash(struct xenvif *vif, const u8 *tag,
 	unsigned long flags;
 	bool found;
 
-	new = kmalloc(sizeof(*entry), GFP_KERNEL);
+	new = kmalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!new)
 		return;
 
-- 
GitLab


From f0712928be1a66c99c35f871b4df7fa23ec1574a Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Wed, 22 Feb 2017 14:47:17 +0100
Subject: [PATCH 579/898] CIFS: use DFS pathnames in SMB2+ Create requests

When connected to a DFS capable share, the client must set the
SMB2_FLAGS_DFS_OPERATIONS flag in the SMB2 header and use
DFS path names: "<server>\<share>\<path>" *without* leading \\.

Sources:

[MS-SMB2] 3.2.5.5 Receiving an SMB2 TREE_CONNECT Response
> TreeConnect.IsDfsShare MUST be set to TRUE, if the SMB2_SHARE_CAP_DFS
> bit is set in the Capabilities field of the response.

[MS-SMB2] 3.2.4.3 Application Requests Opening a File
> If TreeConnect.IsDfsShare is TRUE, the SMB2_FLAGS_DFS_OPERATIONS flag
> is set in the Flags field.

[MS-SMB2] 2.2.13 SMB2 CREATE Request, NameOffset:
> If SMB2_FLAGS_DFS_OPERATIONS is set in the Flags field of the SMB2
> header, the file name includes a prefix that will be processed during
> DFS name normalization as specified in section 3.3.5.9. Otherwise, the
> file name is relative to the share that is identified by the TreeId in
> the SMB2 header.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Acked-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/smb2pdu.c | 96 +++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 80 insertions(+), 16 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2fd93eeed15a..2069431b32e3 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1528,6 +1528,51 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec,
 	return 0;
 }
 
+static int
+alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
+			    const char *treename, const __le16 *path)
+{
+	int treename_len, path_len;
+	struct nls_table *cp;
+	const __le16 sep[] = {cpu_to_le16('\\'), cpu_to_le16(0x0000)};
+
+	/*
+	 * skip leading "\\"
+	 */
+	treename_len = strlen(treename);
+	if (treename_len < 2 || !(treename[0] == '\\' && treename[1] == '\\'))
+		return -EINVAL;
+
+	treename += 2;
+	treename_len -= 2;
+
+	path_len = UniStrnlen((wchar_t *)path, PATH_MAX);
+
+	/*
+	 * make room for one path separator between the treename and
+	 * path
+	 */
+	*out_len = treename_len + 1 + path_len;
+
+	/*
+	 * final path needs to be null-terminated UTF16 with a
+	 * size aligned to 8
+	 */
+
+	*out_size = roundup((*out_len+1)*2, 8);
+	*out_path = kzalloc(*out_size, GFP_KERNEL);
+	if (!*out_path)
+		return -ENOMEM;
+
+	cp = load_nls_default();
+	cifs_strtoUTF16(*out_path, treename, treename_len, cp);
+	UniStrcat(*out_path, sep);
+	UniStrcat(*out_path, path);
+	unload_nls(cp);
+
+	return 0;
+}
+
 int
 SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	  __u8 *oplock, struct smb2_file_all_info *buf,
@@ -1576,30 +1621,49 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	req->ShareAccess = FILE_SHARE_ALL_LE;
 	req->CreateDisposition = cpu_to_le32(oparms->disposition);
 	req->CreateOptions = cpu_to_le32(oparms->create_options & CREATE_OPTIONS_MASK);
-	uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
-	/* do not count rfc1001 len field */
-	req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req) - 4);
 
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
-
-	/* MUST set path len (NameLength) to 0 opening root of share */
-	req->NameLength = cpu_to_le16(uni_path_len - 2);
 	/* -1 since last byte is buf[0] which is sent below (path) */
 	iov[0].iov_len--;
-	if (uni_path_len % 8 != 0) {
-		copy_size = uni_path_len / 8 * 8;
-		if (copy_size < uni_path_len)
-			copy_size += 8;
-
-		copy_path = kzalloc(copy_size, GFP_KERNEL);
-		if (!copy_path)
-			return -ENOMEM;
-		memcpy((char *)copy_path, (const char *)path,
-			uni_path_len);
+
+	req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req) - 4);
+
+	/* [MS-SMB2] 2.2.13 NameOffset:
+	 * If SMB2_FLAGS_DFS_OPERATIONS is set in the Flags field of
+	 * the SMB2 header, the file name includes a prefix that will
+	 * be processed during DFS name normalization as specified in
+	 * section 3.3.5.9. Otherwise, the file name is relative to
+	 * the share that is identified by the TreeId in the SMB2
+	 * header.
+	 */
+	if (tcon->share_flags & SHI1005_FLAGS_DFS) {
+		int name_len;
+
+		req->hdr.sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
+		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
+						 &name_len,
+						 tcon->treeName, path);
+		if (rc)
+			return rc;
+		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
 		path = copy_path;
+	} else {
+		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
+		/* MUST set path len (NameLength) to 0 opening root of share */
+		req->NameLength = cpu_to_le16(uni_path_len - 2);
+		if (uni_path_len % 8 != 0) {
+			copy_size = roundup(uni_path_len, 8);
+			copy_path = kzalloc(copy_size, GFP_KERNEL);
+			if (!copy_path)
+				return -ENOMEM;
+			memcpy((char *)copy_path, (const char *)path,
+			       uni_path_len);
+			uni_path_len = copy_size;
+			path = copy_path;
+		}
 	}
 
 	iov[1].iov_len = uni_path_len;
-- 
GitLab


From 9d49640a21bffd730a6ebf2a0032e022f7caf84a Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Mon, 13 Feb 2017 16:16:49 +0100
Subject: [PATCH 580/898] CIFS: implement get_dfs_refer for SMB2+

in SMB2+ the get_dfs_refer operation uses a FSCTL. The request can be
made on any Tree Connection according to the specs. Since Samba only
accepted it on an IPC connection until recently, try that first.

https://lists.samba.org/archive/samba-technical/2017-February/118859.html

3.2.4.20.3 Application Requests DFS Referral Information:
> The client MUST search for an existing Session and TreeConnect to any
> share on the server identified by ServerName for the user identified by
> UserCredentials. If no Session and TreeConnect are found, the client
> MUST establish a new Session and TreeConnect to IPC$ on the target
> server as described in section 3.2.4.2 using the supplied ServerName and
> UserCredentials.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/smb2ops.c | 101 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/cifs/smb2pdu.h |   8 ++++
 2 files changed, 109 insertions(+)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index eba00cd3bd16..b360c381b00e 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1104,6 +1104,103 @@ smb2_new_lease_key(struct cifs_fid *fid)
 	generate_random_uuid(fid->lease_key);
 }
 
+static int
+smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
+		   const char *search_name,
+		   struct dfs_info3_param **target_nodes,
+		   unsigned int *num_of_nodes,
+		   const struct nls_table *nls_codepage, int remap)
+{
+	int rc;
+	__le16 *utf16_path = NULL;
+	int utf16_path_len = 0;
+	struct cifs_tcon *tcon;
+	struct fsctl_get_dfs_referral_req *dfs_req = NULL;
+	struct get_dfs_referral_rsp *dfs_rsp = NULL;
+	u32 dfs_req_size = 0, dfs_rsp_size = 0;
+
+	cifs_dbg(FYI, "smb2_get_dfs_refer path <%s>\n", search_name);
+
+	/*
+	 * Use any tcon from the current session. Here, the first one.
+	 */
+	spin_lock(&cifs_tcp_ses_lock);
+	tcon = list_first_entry_or_null(&ses->tcon_list, struct cifs_tcon,
+					tcon_list);
+	if (tcon)
+		tcon->tc_count++;
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	if (!tcon) {
+		cifs_dbg(VFS, "session %p has no tcon available for a dfs referral request\n",
+			 ses);
+		rc = -ENOTCONN;
+		goto out;
+	}
+
+	utf16_path = cifs_strndup_to_utf16(search_name, PATH_MAX,
+					   &utf16_path_len,
+					   nls_codepage, remap);
+	if (!utf16_path) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	dfs_req_size = sizeof(*dfs_req) + utf16_path_len;
+	dfs_req = kzalloc(dfs_req_size, GFP_KERNEL);
+	if (!dfs_req) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Highest DFS referral version understood */
+	dfs_req->MaxReferralLevel = DFS_VERSION;
+
+	/* Path to resolve in an UTF-16 null-terminated string */
+	memcpy(dfs_req->RequestFileName, utf16_path, utf16_path_len);
+
+	do {
+		/* try first with IPC */
+		rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
+				FSCTL_DFS_GET_REFERRALS,
+				true /* is_fsctl */, true /* use_ipc */,
+				(char *)dfs_req, dfs_req_size,
+				(char **)&dfs_rsp, &dfs_rsp_size);
+		if (rc == -ENOTCONN) {
+			/* try with normal tcon */
+			rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
+					FSCTL_DFS_GET_REFERRALS,
+					true /* is_fsctl */, false /*use_ipc*/,
+					(char *)dfs_req, dfs_req_size,
+					(char **)&dfs_rsp, &dfs_rsp_size);
+		}
+	} while (rc == -EAGAIN);
+
+	if (rc) {
+		cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc);
+		goto out;
+	}
+
+	rc = parse_dfs_referrals(dfs_rsp, dfs_rsp_size,
+				 num_of_nodes, target_nodes,
+				 nls_codepage, remap, search_name,
+				 true /* is_unicode */);
+	if (rc) {
+		cifs_dbg(VFS, "parse error in smb2_get_dfs_refer rc=%d\n", rc);
+		goto out;
+	}
+
+ out:
+	if (tcon) {
+		spin_lock(&cifs_tcp_ses_lock);
+		tcon->tc_count--;
+		spin_unlock(&cifs_tcp_ses_lock);
+	}
+	kfree(utf16_path);
+	kfree(dfs_req);
+	kfree(dfs_rsp);
+	return rc;
+}
 #define SMB2_SYMLINK_STRUCT_SIZE \
 	(sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp))
 
@@ -2283,6 +2380,7 @@ struct smb_version_operations smb20_operations = {
 	.clone_range = smb2_clone_range,
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
+	.get_dfs_refer = smb2_get_dfs_refer,
 };
 
 struct smb_version_operations smb21_operations = {
@@ -2364,6 +2462,7 @@ struct smb_version_operations smb21_operations = {
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.enum_snapshots = smb3_enum_snapshots,
+	.get_dfs_refer = smb2_get_dfs_refer,
 };
 
 struct smb_version_operations smb30_operations = {
@@ -2455,6 +2554,7 @@ struct smb_version_operations smb30_operations = {
 	.free_transform_rq = smb3_free_transform_rq,
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
+	.get_dfs_refer = smb2_get_dfs_refer,
 };
 
 #ifdef CONFIG_CIFS_SMB311
@@ -2547,6 +2647,7 @@ struct smb_version_operations smb311_operations = {
 	.free_transform_rq = smb3_free_transform_rq,
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
+	.get_dfs_refer = smb2_get_dfs_refer,
 };
 #endif /* CIFS_SMB311 */
 
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index c03b252501a1..18700fd25a0b 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -695,6 +695,14 @@ struct fsctl_get_integrity_information_rsp {
 /* Integrity flags for above */
 #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF	0x00000001
 
+/* See MS-DFSC 2.2.2 */
+struct fsctl_get_dfs_referral_req {
+	__le16 MaxReferralLevel;
+	__u8 RequestFileName[];
+} __packed;
+
+/* DFS response is struct get_dfs_refer_rsp */
+
 /* See MS-SMB2 2.2.31.3 */
 struct network_resiliency_req {
 	__le32 Timeout;
-- 
GitLab


From 165a5e22fafb127ecb5914e12e8c32a1f0d3f820 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Feb 2017 08:05:56 +0100
Subject: [PATCH 581/898] block: Move bdi_unregister() to del_gendisk()

Commit 6cd18e711dd8 "block: destroy bdi before blockdev is
unregistered." moved bdi unregistration (at that time through
bdi_destroy()) from blk_release_queue() to blk_cleanup_queue() because
it needs to happen before blk_unregister_region() call in del_gendisk()
for MD. SCSI though will free up the device number from sd_remove()
called through a maze of callbacks from device_del() in
__scsi_remove_device() before blk_cleanup_queue() and thus similar races
as described in 6cd18e711dd8 can happen for SCSI as well as reported by
Omar [1].

Moving bdi_unregister() to del_gendisk() works for MD and fixes the
problem for SCSI since del_gendisk() gets called from sd_remove() before
freeing the device number.

This also makes device_add_disk() (calling bdi_register_owner()) more
symmetric with del_gendisk().

[1] http://marc.info/?l=linux-block&m=148554717109098&w=2

Tested-by: Lekshmi Pillai <lekshmicpillai@in.ibm.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c | 1 -
 block/genhd.c    | 5 +++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index b9e857f4afe8..1086dac8724c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -578,7 +578,6 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
-	bdi_unregister(q->backing_dev_info);
 	put_disk_devt(q->disk_devt);
 
 	/* @q is and will stay empty, shutdown and put */
diff --git a/block/genhd.c b/block/genhd.c
index 2f444b87a5f2..b26a5ea115d0 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -681,6 +681,11 @@ void del_gendisk(struct gendisk *disk)
 	disk->flags &= ~GENHD_FL_UP;
 
 	sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
+	/*
+	 * Unregister bdi before releasing device numbers (as they can get
+	 * reused and we'd get clashes in sysfs).
+	 */
+	bdi_unregister(disk->queue->backing_dev_info);
 	blk_unregister_queue(disk);
 	blk_unregister_region(disk_devt(disk), disk->minors);
 
-- 
GitLab


From e148bd17f48bd17fca2f4f089ec879fa6e47e34c Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Date: Tue, 14 Feb 2017 14:46:42 +0530
Subject: [PATCH 582/898] powerpc: Emulation support for load/store
 instructions on LE

emulate_step() uses a number of underlying kernel functions that were
initially not enabled for LE. This has been rectified since. So, fix
emulate_step() for LE for the corresponding instructions.

Cc: stable@vger.kernel.org # v3.18+
Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/lib/sstep.c | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 846dba2c6360..9c542ec70c5b 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1799,8 +1799,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case LARX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1823,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case STCX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1849,8 +1845,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case LOAD:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
 		if (!err) {
 			if (op.type & SIGNEXT)
@@ -1862,8 +1856,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case LOAD_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
 		else
@@ -1872,15 +1864,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case LOAD_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
@@ -1903,8 +1891,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case STORE:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if ((op.type & UPDATE) && size == sizeof(long) &&
 		    op.reg == 1 && op.update_reg == 1 &&
 		    !(regs->msr & MSR_PR) &&
@@ -1917,8 +1903,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case STORE_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
 		else
@@ -1927,15 +1911,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case STORE_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
-- 
GitLab


From 4ceae137bdab2232e57b2e6fd5631a22a0160938 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Date: Tue, 14 Feb 2017 14:46:43 +0530
Subject: [PATCH 583/898] powerpc: emulate_step() tests for load/store
 instructions

Add new selftest that test emulate_step for Normal, Floating Point,
Vector and Vector Scalar - load/store instructions. Test should run
at boot time if CONFIG_KPROBES_SANITY_TEST and CONFIG_PPC64 is set.

Sample log:

  emulate_step_test: ld             : PASS
  emulate_step_test: lwz            : PASS
  emulate_step_test: lwzx           : PASS
  emulate_step_test: std            : PASS
  emulate_step_test: ldarx / stdcx. : PASS
  emulate_step_test: lfsx           : PASS
  emulate_step_test: stfsx          : PASS
  emulate_step_test: lfdx           : PASS
  emulate_step_test: stfdx          : PASS
  emulate_step_test: lvx            : PASS
  emulate_step_test: stvx           : PASS
  emulate_step_test: lxvd2x         : PASS
  emulate_step_test: stxvd2x        : PASS

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
[mpe: Drop start/complete lines, make it all __init]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/ppc-opcode.h |   7 +
 arch/powerpc/lib/Makefile             |   1 +
 arch/powerpc/lib/test_emulate_step.c  | 434 ++++++++++++++++++++++++++
 3 files changed, 442 insertions(+)
 create mode 100644 arch/powerpc/lib/test_emulate_step.c

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d99bd442aacb..e7d6d86563ee 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -284,6 +284,13 @@
 #define PPC_INST_BRANCH_COND		0x40800000
 #define PPC_INST_LBZCIX			0x7c0006aa
 #define PPC_INST_STBCIX			0x7c0007aa
+#define PPC_INST_LWZX			0x7c00002e
+#define PPC_INST_LFSX			0x7c00042e
+#define PPC_INST_STFSX			0x7c00052e
+#define PPC_INST_LFDX			0x7c0004ae
+#define PPC_INST_STFDX			0x7c0005ae
+#define PPC_INST_LVX			0x7c0000ce
+#define PPC_INST_STVX			0x7c0001ce
 
 /* macros to insert fields into opcodes */
 #define ___PPC_RA(a)	(((a) & 0x1f) << 16)
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 0e649d72fe8d..2b5e09020cfe 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -20,6 +20,7 @@ obj64-y	+= copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
 
 obj-y			+= checksum_$(BITS).o checksum_wrappers.o
 
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
new file mode 100644
index 000000000000..2534c1447554
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -0,0 +1,434 @@
+/*
+ * Simple sanity test for emulate_step load/store instructions.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * This program is free software;  you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "emulate_step_test: " fmt
+
+#include <linux/ptrace.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+
+#define IMM_L(i)		((uintptr_t)(i) & 0xffff)
+
+/*
+ * Defined with TEST_ prefix so it does not conflict with other
+ * definitions.
+ */
+#define TEST_LD(r, base, i)	(PPC_INST_LD | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZ(r, base, i)	(PPC_INST_LWZ | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZX(t, a, b)	(PPC_INST_LWZX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STD(r, base, i)	(PPC_INST_STD | ___PPC_RS(r) |		\
+					___PPC_RA(base) | ((i) & 0xfffc))
+#define TEST_LDARX(t, a, b, eh)	(PPC_INST_LDARX | ___PPC_RT(t) |	\
+					___PPC_RA(a) | ___PPC_RB(b) |	\
+					__PPC_EH(eh))
+#define TEST_STDCX(s, a, b)	(PPC_INST_STDCX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFSX(t, a, b)	(PPC_INST_LFSX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFSX(s, a, b)	(PPC_INST_STFSX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFDX(t, a, b)	(PPC_INST_LFDX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFDX(s, a, b)	(PPC_INST_STFDX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LVX(t, a, b)	(PPC_INST_LVX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STVX(s, a, b)	(PPC_INST_STVX | ___PPC_RS(s) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LXVD2X(s, a, b)	(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_STXVD2X(s, a, b)	(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+
+
+static void __init init_pt_regs(struct pt_regs *regs)
+{
+	static unsigned long msr;
+	static bool msr_cached;
+
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	if (likely(msr_cached)) {
+		regs->msr = msr;
+		return;
+	}
+
+	asm volatile("mfmsr %0" : "=r"(regs->msr));
+
+	regs->msr |= MSR_FP;
+	regs->msr |= MSR_VEC;
+	regs->msr |= MSR_VSX;
+
+	msr = regs->msr;
+	msr_cached = true;
+}
+
+static void __init show_result(char *ins, char *result)
+{
+	pr_info("%-14s : %s\n", ins, result);
+}
+
+static void __init test_ld(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x23;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* ld r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LD(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("ld", "PASS");
+	else
+		show_result("ld", "FAIL");
+}
+
+static void __init test_lwz(void)
+{
+	struct pt_regs regs;
+	unsigned int a = 0x4545;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* lwz r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LWZ(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("lwz", "PASS");
+	else
+		show_result("lwz", "FAIL");
+}
+
+static void __init test_lwzx(void)
+{
+	struct pt_regs regs;
+	unsigned int a[3] = {0x0, 0x0, 0x1234};
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) a;
+	regs.gpr[4] = 8;
+	regs.gpr[5] = 0x8765;
+
+	/* lwzx r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LWZX(5, 3, 4));
+	if (stepped == 1 && regs.gpr[5] == a[2])
+		show_result("lwzx", "PASS");
+	else
+		show_result("lwzx", "FAIL");
+}
+
+static void __init test_std(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[5] = 0x5678;
+
+	/* std r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
+	if (stepped == 1 || regs.gpr[5] == a)
+		show_result("std", "PASS");
+	else
+		show_result("std", "FAIL");
+}
+
+static void __init test_ldarx_stdcx(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+	unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */
+
+	init_pt_regs(&regs);
+	asm volatile("mfcr %0" : "=r"(regs.ccr));
+
+
+	/*** ldarx ***/
+
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[4] = 0;
+	regs.gpr[5] = 0x5678;
+
+	/* ldarx r5, r3, r4, 0 */
+	stepped = emulate_step(&regs, TEST_LDARX(5, 3, 4, 0));
+
+	/*
+	 * Don't touch 'a' here. Touching 'a' can do Load/store
+	 * of 'a' which result in failure of subsequent stdcx.
+	 * Instead, use hardcoded value for comparison.
+	 */
+	if (stepped <= 0 || regs.gpr[5] != 0x1234) {
+		show_result("ldarx / stdcx.", "FAIL (ldarx)");
+		return;
+	}
+
+
+	/*** stdcx. ***/
+
+	regs.gpr[5] = 0x9ABC;
+
+	/* stdcx. r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STDCX(5, 3, 4));
+
+	/*
+	 * Two possible scenarios that indicates successful emulation
+	 * of stdcx. :
+	 *  1. Reservation is active and store is performed. In this
+	 *     case cr0.eq bit will be set to 1.
+	 *  2. Reservation is not active and store is not performed.
+	 *     In this case cr0.eq bit will be set to 0.
+	 */
+	if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq))
+			|| (regs.gpr[5] != a && !(regs.ccr & cr0_eq))))
+		show_result("ldarx / stdcx.", "PASS");
+	else
+		show_result("ldarx / stdcx.", "FAIL (stdcx.)");
+}
+
+#ifdef CONFIG_PPC_FPU
+static void __init test_lfsx_stfsx(void)
+{
+	struct pt_regs regs;
+	union {
+		float a;
+		int b;
+	} c;
+	int cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfsx ***/
+
+	c.a = 123.45;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfsx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFSX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfsx", "PASS");
+	else
+		show_result("lfsx", "FAIL");
+
+
+	/*** stfsx ***/
+
+	c.a = 678.91;
+
+	/* stfsx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFSX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfsx", "PASS");
+	else
+		show_result("stfsx", "FAIL");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	struct pt_regs regs;
+	union {
+		double a;
+		long b;
+	} c;
+	long cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfdx ***/
+
+	c.a = 123456.78;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfdx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFDX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfdx", "PASS");
+	else
+		show_result("lfdx", "FAIL");
+
+
+	/*** stfdx ***/
+
+	c.a = 987654.32;
+
+	/* stfdx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFDX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfdx", "PASS");
+	else
+		show_result("stfdx", "FAIL");
+}
+#else
+static void __init test_lfsx_stfsx(void)
+{
+	show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __init test_lvx_stvx(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lvx ***/
+
+	cached_b[0] = c.b[0] = 923745;
+	cached_b[1] = c.b[1] = 2139478;
+	cached_b[2] = c.b[2] = 9012;
+	cached_b[3] = c.b[3] = 982134;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lvx vrt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LVX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lvx", "PASS");
+	else
+		show_result("lvx", "FAIL");
+
+
+	/*** stvx ***/
+
+	c.b[0] = 4987513;
+	c.b[1] = 84313948;
+	c.b[2] = 71;
+	c.b[3] = 498532;
+
+	/* stvx vrs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STVX(10, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stvx", "PASS");
+	else
+		show_result("stvx", "FAIL");
+}
+#else
+static void __init test_lvx_stvx(void)
+{
+	show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)");
+	show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)");
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lxvd2x ***/
+
+	cached_b[0] = c.b[0] = 18233;
+	cached_b[1] = c.b[1] = 34863571;
+	cached_b[2] = c.b[2] = 834;
+	cached_b[3] = c.b[3] = 6138911;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
+
+	if (stepped == 1)
+		show_result("lxvd2x", "PASS");
+	else
+		show_result("lxvd2x", "FAIL");
+
+
+	/*** stxvd2x ***/
+
+	c.b[0] = 21379463;
+	c.b[1] = 87;
+	c.b[2] = 374234;
+	c.b[3] = 4;
+
+	/* stxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STXVD2X(39, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stxvd2x", "PASS");
+	else
+		show_result("stxvd2x", "FAIL");
+}
+#else
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)");
+	show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+static int __init test_emulate_step(void)
+{
+	test_ld();
+	test_lwz();
+	test_lwzx();
+	test_std();
+	test_ldarx_stdcx();
+	test_lfsx_stfsx();
+	test_lfdx_stfdx();
+	test_lvx_stvx();
+	test_lxvd2x_stxvd2x();
+
+	return 0;
+}
+late_initcall(test_emulate_step);
-- 
GitLab


From 7a70d7288c926ae88e0c773fbb506aa374e99c2d Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@ozlabs.org>
Date: Mon, 27 Feb 2017 14:32:41 +1100
Subject: [PATCH 584/898] powerpc/64: Invalidate process table caching after
 setting process table

The POWER9 MMU reads and caches entries from the process table.
When we kexec from one kernel to another, the second kernel sets
its process table pointer but doesn't currently do anything to
make the CPU invalidate any cached entries from the old process table.
This adds a tlbie (TLB invalidate entry) instruction with parameters
to invalidate caching of the process table after the new process
table is installed.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/mm/pgtable-radix.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index feeda90cd06d..01c94f141164 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -186,6 +186,10 @@ static void __init radix_init_pgtable(void)
 	 */
 	register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
 	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
+	asm volatile("ptesync" : : : "memory");
+	asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+		     "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 
 static void __init radix_init_partition_table(void)
-- 
GitLab


From 424f8acd328a111319ae30bf384e5dfb9bc8f8cb Mon Sep 17 00:00:00 2001
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Date: Mon, 27 Feb 2017 11:10:07 +0530
Subject: [PATCH 585/898] powerpc/powernv: Fix bug due to labeling ambiguity in
 power_enter_stop

Commit 09206b600c76 ("powernv: Pass PSSCR value and mask to
power9_idle_stop") added additional code in power_enter_stop() to
distinguish between stop requests whose PSSCR had ESL=EC=1 from those
which did not. When ESL=EC=1, we do a forward-jump to a location
labelled by "1", which had the code to handle the ESL=EC=1 case.

Unfortunately just a couple of instructions before this label, is the
macro IDLE_STATE_ENTER_SEQ() which also has a label "1" in its
expansion.

As a result, the current code can result in directly executing stop
instruction for deep stop requests with PSSCR ESL=EC=1, without saving
the hypervisor state.

Fix this BUG by labeling the location that handles ESL=EC=1 case with
a more descriptive label ".Lhandle_esl_ec_set" (local label suggestion
a la .Lxx from Anton Blanchard).

While at it, rename the label "2" labelling the location of the code
handling entry into deep stop states with ".Lhandle_deep_stop".

For a good measure, change the label in IDLE_STATE_ENTER_SEQ() macro
to an not-so commonly used value in order to avoid similar mishaps in
the future.

Fixes: 09206b600c76 ("powernv: Pass PSSCR value and mask to power9_idle_stop")
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cpuidle.h |  4 ++--
 arch/powerpc/kernel/idle_book3s.S  | 10 ++++++----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index fd321eb423cb..155731557c9b 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -70,8 +70,8 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err)
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmpd	cr0,r0,r0;					\
-	bne	1b;						\
+236:	cmpd	cr0,r0,r0;					\
+	bne	236b;						\
 	IDLE_INST;						\
 
 #define	IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 5f61cc0349c0..995728736677 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -276,19 +276,21 @@ power_enter_stop:
  */
 	andis.   r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
 	clrldi   r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
-	bne	 1f
+	bne	 .Lhandle_esl_ec_set
 	IDLE_STATE_ENTER_SEQ(PPC_STOP)
 	li	r3,0  /* Since we didn't lose state, return 0 */
 	b 	pnv_wakeup_noloss
+
+.Lhandle_esl_ec_set:
 /*
  * Check if the requested state is a deep idle state.
  */
-1:	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
 	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
 	cmpd	r3,r4
-	bge	2f
+	bge	.Lhandle_deep_stop
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
-2:
+.Lhandle_deep_stop:
 /*
  * Entering deep idle state.
  * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
-- 
GitLab


From a6d8a21596df041f36f4c2ccc260c459e3e851f1 Mon Sep 17 00:00:00 2001
From: Sachin Sant <sachinp@linux.vnet.ibm.com>
Date: Sun, 26 Feb 2017 11:38:39 +0530
Subject: [PATCH 586/898] selftest/powerpc: Fix false failures for skipped
 tests

Tests under alignment subdirectory are skipped when executed on previous
generation hardware, but harness still marks them as failed.

  test: test_copy_unaligned
  tags: git_version:unknown
  [SKIP] Test skipped on line 26
  skip: test_copy_unaligned
  selftests: copy_unaligned [FAIL]

The MAGIC_SKIP_RETURN_VALUE value assigned to rc variable is retained till
the program exit which causes the test to be marked as failed.

This patch resets the value before returning to the main() routine.
With this patch the test o/p is as follows:

  test: test_copy_unaligned
  tags: git_version:unknown
  [SKIP] Test skipped on line 26
  skip: test_copy_unaligned
  selftests: copy_unaligned [PASS]

Signed-off-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/harness.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index 248a820048df..66d31de60b9a 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -114,9 +114,11 @@ int test_harness(int (test_function)(void), char *name)
 
 	rc = run_test(test_function, name);
 
-	if (rc == MAGIC_SKIP_RETURN_VALUE)
+	if (rc == MAGIC_SKIP_RETURN_VALUE) {
 		test_skip(name);
-	else
+		/* so that skipped test is not marked as failed */
+		rc = 0;
+	} else
 		test_finish(name, rc);
 
 	return rc;
-- 
GitLab


From 4dc831aa88132f835cefe876aa0206977c4d7710 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Sun, 27 Nov 2016 13:46:20 +1100
Subject: [PATCH 587/898] powerpc: Fix compiling a BE kernel with a powerpc64le
 toolchain

GCC can compile with either endian, but the default ABI version is set
based on the default endianness of the toolchain. Alan Modra says:

  you need both -mbig and -mabi=elfv1 to make a powerpc64le gcc
  generate powerpc64 code

The opposite is true for powerpc64 when generating -mlittle it
requires -mabi=elfv2 to generate v2 ABI, which we were already doing.

This change adds ABI annotations together with endianness for all cases,
LE and BE. This fixes the case of building a BE kernel with a toolchain
that is LE by default.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/Makefile | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 31286fa7873c..19b0d1a81959 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -72,8 +72,15 @@ GNUTARGET	:= powerpc
 MULTIPLEWORD	:= -mmultiple
 endif
 
-cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
+ifdef CONFIG_PPC64
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mcall-aixdesc)
+aflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mabi=elfv2
+endif
+
 cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mlittle-endian
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
 ifneq ($(cc-name),clang)
   cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mno-strict-align
 endif
@@ -113,7 +120,9 @@ ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
 AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
 else
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
-- 
GitLab


From 3fb66a70a4ae886445743354e4b60e54058bb3ff Mon Sep 17 00:00:00 2001
From: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Date: Thu, 16 Feb 2017 09:11:29 -0600
Subject: [PATCH 588/898] powerpc/booke: Fix boot crash due to null hugepd

On 32-bit book-e machines, hugepd_ok() no longer takes into account null
hugepd values, causing this crash at boot:

  Unable to handle kernel paging request for data at address 0x80000000
  ...
  NIP [c0018378] follow_huge_addr+0x38/0xf0
  LR [c001836c] follow_huge_addr+0x2c/0xf0
  Call Trace:
   follow_huge_addr+0x2c/0xf0 (unreliable)
   follow_page_mask+0x40/0x3e0
   __get_user_pages+0xc8/0x450
   get_user_pages_remote+0x8c/0x250
   copy_strings+0x110/0x390
   copy_strings_kernel+0x2c/0x50
   do_execveat_common+0x478/0x630
   do_execve+0x2c/0x40
   try_to_run_init_process+0x18/0x60
   kernel_init+0xbc/0x110
   ret_from_kernel_thread+0x5c/0x64

This impacts all nxp (ex-freescale) 32-bit booke platforms.

This was caused by the change of hugepd_t.pd from signed to unsigned,
and the update to the nohash version of hugepd_ok(). Previously
hugepd_ok() could exclude all non-huge and NULL pgds using > 0, whereas
now we need to explicitly check that the value is not zero and also that
PD_HUGE is *clear*.

This isn't protected by the pgd_none() check in __find_linux_pte_or_hugepte()
because on 32-bit we use pgtable-nopud.h, which causes the pgd_none()
check to be always false.

Fixes: 20717e1ff526 ("powerpc/mm: Fix little-endian 4K hugetlb")
Cc: stable@vger.kernel.org # v4.7+
Reported-by: Madalin-Cristian Bucur <madalin.bucur@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
[mpe: Flesh out change log details.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/nohash/pgtable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 0cd8a3852763..e5805ad78e12 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -230,7 +230,7 @@ static inline int hugepd_ok(hugepd_t hpd)
 	return ((hpd_val(hpd) & 0x4) != 0);
 #else
 	/* We clear the top bit to indicate hugepd */
-	return ((hpd_val(hpd) & PD_HUGE) ==  0);
+	return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
 #endif
 }
 
-- 
GitLab


From 68e21be2916b359fd8afb536c1911dc014cfd03e Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 19:08:20 +0100
Subject: [PATCH 589/898] sched/headers: Move task->mm handling methods to
 <linux/sched/mm.h>

Move the following task->mm helper APIs into a new header file,
<linux/sched/mm.h>, to further reduce the size and complexity
of <linux/sched.h>.

Here are how the APIs are used in various kernel files:

  # mm_alloc():
  arch/arm/mach-rpc/ecard.c
  fs/exec.c
  include/linux/sched/mm.h
  kernel/fork.c

  # __mmdrop():
  arch/arc/include/asm/mmu_context.h
  include/linux/sched/mm.h
  kernel/fork.c

  # mmdrop():
  arch/arm/mach-rpc/ecard.c
  arch/m68k/sun3/mmu_emu.c
  arch/x86/mm/tlb.c
  drivers/gpu/drm/amd/amdkfd/kfd_process.c
  drivers/gpu/drm/i915/i915_gem_userptr.c
  drivers/infiniband/hw/hfi1/file_ops.c
  drivers/vfio/vfio_iommu_spapr_tce.c
  fs/exec.c
  fs/proc/base.c
  fs/proc/task_mmu.c
  fs/proc/task_nommu.c
  fs/userfaultfd.c
  include/linux/mmu_notifier.h
  include/linux/sched/mm.h
  kernel/fork.c
  kernel/futex.c
  kernel/sched/core.c
  mm/khugepaged.c
  mm/ksm.c
  mm/mmu_context.c
  mm/mmu_notifier.c
  mm/oom_kill.c
  virt/kvm/kvm_main.c

  # mmdrop_async_fn():
  include/linux/sched/mm.h

  # mmdrop_async():
  include/linux/sched/mm.h
  kernel/fork.c

  # mmget_not_zero():
  fs/userfaultfd.c
  include/linux/sched/mm.h
  mm/oom_kill.c

  # mmput():
  arch/arc/include/asm/mmu_context.h
  arch/arc/kernel/troubleshoot.c
  arch/frv/mm/mmu-context.c
  arch/powerpc/platforms/cell/spufs/context.c
  arch/sparc/include/asm/mmu_context_32.h
  drivers/android/binder.c
  drivers/gpu/drm/etnaviv/etnaviv_gem.c
  drivers/gpu/drm/i915/i915_gem_userptr.c
  drivers/infiniband/core/umem.c
  drivers/infiniband/core/umem_odp.c
  drivers/infiniband/core/uverbs_main.c
  drivers/infiniband/hw/mlx4/main.c
  drivers/infiniband/hw/mlx5/main.c
  drivers/infiniband/hw/usnic/usnic_uiom.c
  drivers/iommu/amd_iommu_v2.c
  drivers/iommu/intel-svm.c
  drivers/lguest/lguest_user.c
  drivers/misc/cxl/fault.c
  drivers/misc/mic/scif/scif_rma.c
  drivers/oprofile/buffer_sync.c
  drivers/vfio/vfio_iommu_type1.c
  drivers/vhost/vhost.c
  drivers/xen/gntdev.c
  fs/exec.c
  fs/proc/array.c
  fs/proc/base.c
  fs/proc/task_mmu.c
  fs/proc/task_nommu.c
  fs/userfaultfd.c
  include/linux/sched/mm.h
  kernel/cpuset.c
  kernel/events/core.c
  kernel/events/uprobes.c
  kernel/exit.c
  kernel/fork.c
  kernel/ptrace.c
  kernel/sys.c
  kernel/trace/trace_output.c
  kernel/tsacct.c
  mm/memcontrol.c
  mm/memory.c
  mm/mempolicy.c
  mm/migrate.c
  mm/mmu_notifier.c
  mm/nommu.c
  mm/oom_kill.c
  mm/process_vm_access.c
  mm/rmap.c
  mm/swapfile.c
  mm/util.c
  virt/kvm/async_pf.c

  # mmput_async():
  include/linux/sched/mm.h
  kernel/fork.c
  mm/oom_kill.c

  # get_task_mm():
  arch/arc/kernel/troubleshoot.c
  arch/powerpc/platforms/cell/spufs/context.c
  drivers/android/binder.c
  drivers/gpu/drm/etnaviv/etnaviv_gem.c
  drivers/infiniband/core/umem.c
  drivers/infiniband/core/umem_odp.c
  drivers/infiniband/hw/mlx4/main.c
  drivers/infiniband/hw/mlx5/main.c
  drivers/infiniband/hw/usnic/usnic_uiom.c
  drivers/iommu/amd_iommu_v2.c
  drivers/iommu/intel-svm.c
  drivers/lguest/lguest_user.c
  drivers/misc/cxl/fault.c
  drivers/misc/mic/scif/scif_rma.c
  drivers/oprofile/buffer_sync.c
  drivers/vfio/vfio_iommu_type1.c
  drivers/vhost/vhost.c
  drivers/xen/gntdev.c
  fs/proc/array.c
  fs/proc/base.c
  fs/proc/task_mmu.c
  include/linux/sched/mm.h
  kernel/cpuset.c
  kernel/events/core.c
  kernel/exit.c
  kernel/fork.c
  kernel/ptrace.c
  kernel/sys.c
  kernel/trace/trace_output.c
  kernel/tsacct.c
  mm/memcontrol.c
  mm/memory.c
  mm/mempolicy.c
  mm/migrate.c
  mm/mmu_notifier.c
  mm/nommu.c
  mm/util.c

  # mm_access():
  fs/proc/base.c
  include/linux/sched/mm.h
  kernel/fork.c
  mm/process_vm_access.c

  # mm_release():
  arch/arc/include/asm/mmu_context.h
  fs/exec.c
  include/linux/sched/mm.h
  include/uapi/linux/sched.h
  kernel/exit.c
  kernel/fork.c

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/kernel/smp.c         |  2 +-
 arch/arc/kernel/smp.c           |  2 +-
 arch/arm/kernel/smp.c           |  2 +-
 arch/arm64/kernel/smp.c         |  2 +-
 arch/blackfin/mach-common/smp.c |  2 +-
 arch/hexagon/kernel/smp.c       |  2 +-
 arch/ia64/kernel/setup.c        |  2 +-
 arch/m32r/kernel/setup.c        |  2 +-
 arch/metag/kernel/smp.c         |  2 +-
 arch/mips/kernel/traps.c        |  2 +-
 arch/parisc/kernel/smp.c        |  2 +-
 arch/powerpc/kernel/smp.c       |  2 +-
 arch/s390/kernel/processor.c    |  2 +
 arch/score/kernel/traps.c       |  1 +
 arch/sh/kernel/smp.c            |  2 +-
 arch/sparc/kernel/leon_smp.c    |  2 +-
 arch/sparc/kernel/smp_64.c      |  2 +-
 arch/sparc/kernel/sun4d_smp.c   |  2 +-
 arch/sparc/kernel/sun4m_smp.c   |  2 +-
 arch/sparc/kernel/traps_32.c    |  2 +-
 arch/sparc/kernel/traps_64.c    |  2 +-
 arch/tile/kernel/smpboot.c      |  2 +-
 arch/x86/kernel/cpu/common.c    |  2 +-
 arch/xtensa/kernel/smp.c        |  1 +
 include/linux/sched.h           | 95 ---------------------------------
 include/linux/sched/mm.h        | 95 +++++++++++++++++++++++++++++++++
 26 files changed, 120 insertions(+), 116 deletions(-)

diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index acb4b146a607..9fc560459ebd 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -14,7 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/threads.h>
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index b8e8d3944481..f46267153ec2 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -13,7 +13,7 @@
  */
 
 #include <linux/spinlock.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/interrupt.h>
 #include <linux/profile.h>
 #include <linux/mm.h>
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b724cff7ad60..572a8df1b766 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -11,7 +11,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 83c0a839a6ad..ef1caae02110 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -21,7 +21,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 3ac98252d299..b32ddab7966c 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -11,7 +11,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
 #include <linux/cache.h>
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index 1f63e91a353b..5dbc15549e01 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -25,7 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/cpu.h>
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 63bef6fc0f3e..23e3fd61e335 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -32,7 +32,7 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/reboot.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/task_stack.h>
 #include <linux/seq_file.h>
diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c
index b18bc0bd6544..1a9e977287e6 100644
--- a/arch/m32r/kernel/setup.c
+++ b/arch/m32r/kernel/setup.c
@@ -11,7 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/stddef.h>
 #include <linux/fs.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/ioport.h>
 #include <linux/mm.h>
 #include <linux/bootmem.h>
diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index cab2aa64ca82..232a12bf3f99 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -12,7 +12,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/interrupt.h>
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 1a9366a157cb..c7d17cfb32f6 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -23,7 +23,7 @@
 #include <linux/module.h>
 #include <linux/extable.h>
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/debug.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 67b452b41ff6..63365106ea19 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -21,7 +21,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/smp.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index fce17789c675..46f89e66a273 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -19,7 +19,7 @@
 
 #include <linux/kernel.h>
 #include <linux/export.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/topology.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index bf7854523831..928b929a6261 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -8,11 +8,13 @@
 
 #include <linux/cpufeature.h>
 #include <linux/kernel.h>
+#include <linux/sched/mm.h>
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/mm_types.h>
 #include <linux/delay.h>
 #include <linux/cpu.h>
+
 #include <asm/diag.h>
 #include <asm/facility.h>
 #include <asm/elf.h>
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index fe68de6c746c..e359ec675869 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -24,6 +24,7 @@
  */
 
 #include <linux/extable.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
 #include <linux/mm_types.h>
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 4abf119c129c..c483422ea4d0 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -20,7 +20,7 @@
 #include <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/hotplug.h>
 #include <linux/atomic.h>
 #include <linux/clockchips.h>
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index b99d33797e1d..db7acf27bea2 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -9,7 +9,7 @@
 #include <asm/head.h>
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/threads.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 15052d364e04..b3bc0ac757cc 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -5,7 +5,7 @@
 
 #include <linux/export.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/hotplug.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index 7b55c50eabe5..af93b50e3ce4 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -10,7 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/profile.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/cpu.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/sparc/kernel/sun4m_smp.c b/arch/sparc/kernel/sun4m_smp.c
index 633c4cf6fdb0..5547fcb1d72d 100644
--- a/arch/sparc/kernel/sun4m_smp.c
+++ b/arch/sparc/kernel/sun4m_smp.c
@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/profile.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/cpu.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 2de72a49308a..466d4aed06c7 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -9,7 +9,7 @@
  * I hate traps on the sparc, grrr...
  */
 
-#include <linux/sched.h>  /* for jiffies */
+#include <linux/sched/mm.h>
 #include <linux/sched/debug.h>
 #include <linux/mm_types.h>
 #include <linux/kernel.h>
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4ff4c35f76b2..196ee5eb4d48 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/extable.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/debug.h>
 #include <linux/linkage.h>
 #include <linux/kernel.h>
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index f3fdd0c39b12..869c22e57561 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -16,7 +16,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/task.h>
 #include <linux/kernel_stat.h>
 #include <linux/bootmem.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f2fd8fefc589..b11b38c3b0bd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -7,7 +7,7 @@
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/delay.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/task.h>
 #include <linux/init.h>
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index fd894eaa63f3..932d64689bac 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/reboot.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 042620729230..d29bbe0ee41f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2379,101 +2379,6 @@ static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
 	return sp;
 }
 
-/*
- * Routines for handling mm_structs
- */
-extern struct mm_struct * mm_alloc(void);
-
-/**
- * mmgrab() - Pin a &struct mm_struct.
- * @mm: The &struct mm_struct to pin.
- *
- * Make sure that @mm will not get freed even after the owning task
- * exits. This doesn't guarantee that the associated address space
- * will still exist later on and mmget_not_zero() has to be used before
- * accessing it.
- *
- * This is a preferred way to to pin @mm for a longer/unbounded amount
- * of time.
- *
- * Use mmdrop() to release the reference acquired by mmgrab().
- *
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
- * of &mm_struct.mm_count vs &mm_struct.mm_users.
- */
-static inline void mmgrab(struct mm_struct *mm)
-{
-	atomic_inc(&mm->mm_count);
-}
-
-/* mmdrop drops the mm and the page tables */
-extern void __mmdrop(struct mm_struct *);
-static inline void mmdrop(struct mm_struct *mm)
-{
-	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
-		__mmdrop(mm);
-}
-
-static inline void mmdrop_async_fn(struct work_struct *work)
-{
-	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
-	__mmdrop(mm);
-}
-
-static inline void mmdrop_async(struct mm_struct *mm)
-{
-	if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
-		INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
-		schedule_work(&mm->async_put_work);
-	}
-}
-
-/**
- * mmget() - Pin the address space associated with a &struct mm_struct.
- * @mm: The address space to pin.
- *
- * Make sure that the address space of the given &struct mm_struct doesn't
- * go away. This does not protect against parts of the address space being
- * modified or freed, however.
- *
- * Never use this function to pin this address space for an
- * unbounded/indefinite amount of time.
- *
- * Use mmput() to release the reference acquired by mmget().
- *
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
- * of &mm_struct.mm_count vs &mm_struct.mm_users.
- */
-static inline void mmget(struct mm_struct *mm)
-{
-	atomic_inc(&mm->mm_users);
-}
-
-static inline bool mmget_not_zero(struct mm_struct *mm)
-{
-	return atomic_inc_not_zero(&mm->mm_users);
-}
-
-/* mmput gets rid of the mappings and all user-space */
-extern void mmput(struct mm_struct *);
-#ifdef CONFIG_MMU
-/* same as above but performs the slow path from the async context. Can
- * be called from the atomic context as well
- */
-extern void mmput_async(struct mm_struct *);
-#endif
-
-/* Grab a reference to a task's mm, if it is not already going away */
-extern struct mm_struct *get_task_mm(struct task_struct *task);
-/*
- * Grab a reference to a task's mm, if it is not already going away
- * and ptrace_may_access with the mode parameter passed to it
- * succeeds.
- */
-extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
-/* Remove the current tasks stale references to the old mm_struct */
-extern void mm_release(struct task_struct *, struct mm_struct *);
-
 #ifdef CONFIG_HAVE_COPY_THREAD_TLS
 extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
 			struct task_struct *, unsigned long);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d32e3932b2e3..be1ae55f5ab9 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -5,4 +5,99 @@
 #include <linux/mm_types.h>
 #include <linux/gfp.h>
 
+/*
+ * Routines for handling mm_structs
+ */
+extern struct mm_struct * mm_alloc(void);
+
+/**
+ * mmgrab() - Pin a &struct mm_struct.
+ * @mm: The &struct mm_struct to pin.
+ *
+ * Make sure that @mm will not get freed even after the owning task
+ * exits. This doesn't guarantee that the associated address space
+ * will still exist later on and mmget_not_zero() has to be used before
+ * accessing it.
+ *
+ * This is a preferred way to to pin @mm for a longer/unbounded amount
+ * of time.
+ *
+ * Use mmdrop() to release the reference acquired by mmgrab().
+ *
+ * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * of &mm_struct.mm_count vs &mm_struct.mm_users.
+ */
+static inline void mmgrab(struct mm_struct *mm)
+{
+	atomic_inc(&mm->mm_count);
+}
+
+/* mmdrop drops the mm and the page tables */
+extern void __mmdrop(struct mm_struct *);
+static inline void mmdrop(struct mm_struct *mm)
+{
+	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
+		__mmdrop(mm);
+}
+
+static inline void mmdrop_async_fn(struct work_struct *work)
+{
+	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+	__mmdrop(mm);
+}
+
+static inline void mmdrop_async(struct mm_struct *mm)
+{
+	if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
+		INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
+		schedule_work(&mm->async_put_work);
+	}
+}
+
+/**
+ * mmget() - Pin the address space associated with a &struct mm_struct.
+ * @mm: The address space to pin.
+ *
+ * Make sure that the address space of the given &struct mm_struct doesn't
+ * go away. This does not protect against parts of the address space being
+ * modified or freed, however.
+ *
+ * Never use this function to pin this address space for an
+ * unbounded/indefinite amount of time.
+ *
+ * Use mmput() to release the reference acquired by mmget().
+ *
+ * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * of &mm_struct.mm_count vs &mm_struct.mm_users.
+ */
+static inline void mmget(struct mm_struct *mm)
+{
+	atomic_inc(&mm->mm_users);
+}
+
+static inline bool mmget_not_zero(struct mm_struct *mm)
+{
+	return atomic_inc_not_zero(&mm->mm_users);
+}
+
+/* mmput gets rid of the mappings and all user-space */
+extern void mmput(struct mm_struct *);
+#ifdef CONFIG_MMU
+/* same as above but performs the slow path from the async context. Can
+ * be called from the atomic context as well
+ */
+extern void mmput_async(struct mm_struct *);
+#endif
+
+/* Grab a reference to a task's mm, if it is not already going away */
+extern struct mm_struct *get_task_mm(struct task_struct *task);
+/*
+ * Grab a reference to a task's mm, if it is not already going away
+ * and ptrace_may_access with the mode parameter passed to it
+ * succeeds.
+ */
+extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
+/* Remove the current tasks stale references to the old mm_struct */
+extern void mm_release(struct task_struct *, struct mm_struct *);
+
 #endif /* _LINUX_SCHED_MM_H */
-- 
GitLab


From 11701c6768367294c5086738d49196192aaf3d60 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 19:21:47 +0100
Subject: [PATCH 590/898] sched/headers: Move task->mm coredumping related
 defines and methods from <linux/sched.h> to <linux/sched/coredump.h>

This further reduces the size and complexity of <linux/sched.h>.

These are the definitions and APIs that are moved:

  # MMF_*:
  fs/binfmt_elf.c
  fs/binfmt_elf_fdpic.c
  fs/exec.c
  fs/proc/base.c
  include/linux/khugepaged.h
  include/linux/ksm.h
  include/linux/sched/coredump.h
  kernel/events/uprobes.c
  kernel/fork.c
  mm/huge_memory.c
  mm/khugepaged.c
  mm/ksm.c
  mm/memory.c
  mm/oom_kill.c

  # SUID_DUMP_*:
  arch/ia64/include/asm/processor.h
  fs/coredump.c
  fs/exec.c
  fs/proc/internal.h
  include/linux/sched/coredump.h
  kernel/ptrace.c
  kernel/sys.c
  kernel/sysctl.c

  # get_dumpable():
  arch/ia64/include/asm/processor.h
  fs/coredump.c
  fs/exec.c
  fs/proc/internal.h
  include/linux/sched/coredump.h
  kernel/ptrace.c
  kernel/sys.c

  # set_dumpable():
  fs/exec.c
  include/linux/sched/coredump.h
  kernel/cred.c
  kernel/sys.c

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h          | 68 ---------------------------------
 include/linux/sched/coredump.h | 69 ++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+), 68 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d29bbe0ee41f..7934cd0acbc7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -361,74 +361,6 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 #endif
 
-#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
-#define SUID_DUMP_USER		1	/* Dump as user of process */
-#define SUID_DUMP_ROOT		2	/* Dump as root */
-
-/* mm flags */
-
-/* for SUID_DUMP_* above */
-#define MMF_DUMPABLE_BITS 2
-#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
-
-extern void set_dumpable(struct mm_struct *mm, int value);
-/*
- * This returns the actual value of the suid_dumpable flag. For things
- * that are using this for checking for privilege transitions, it must
- * test against SUID_DUMP_USER rather than treating it as a boolean
- * value.
- */
-static inline int __get_dumpable(unsigned long mm_flags)
-{
-	return mm_flags & MMF_DUMPABLE_MASK;
-}
-
-static inline int get_dumpable(struct mm_struct *mm)
-{
-	return __get_dumpable(mm->flags);
-}
-
-/* coredump filter bits */
-#define MMF_DUMP_ANON_PRIVATE	2
-#define MMF_DUMP_ANON_SHARED	3
-#define MMF_DUMP_MAPPED_PRIVATE	4
-#define MMF_DUMP_MAPPED_SHARED	5
-#define MMF_DUMP_ELF_HEADERS	6
-#define MMF_DUMP_HUGETLB_PRIVATE 7
-#define MMF_DUMP_HUGETLB_SHARED  8
-#define MMF_DUMP_DAX_PRIVATE	9
-#define MMF_DUMP_DAX_SHARED	10
-
-#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
-#define MMF_DUMP_FILTER_BITS	9
-#define MMF_DUMP_FILTER_MASK \
-	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
-#define MMF_DUMP_FILTER_DEFAULT \
-	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
-	 (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
-
-#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
-# define MMF_DUMP_MASK_DEFAULT_ELF	(1 << MMF_DUMP_ELF_HEADERS)
-#else
-# define MMF_DUMP_MASK_DEFAULT_ELF	0
-#endif
-					/* leave room for more dump flags */
-#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
-#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
-/*
- * This one-shot flag is dropped due to necessity of changing exe once again
- * on NFS restore
- */
-//#define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */
-
-#define MMF_HAS_UPROBES		19	/* has uprobes */
-#define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
-#define MMF_OOM_SKIP		21	/* mm is of no interest for the OOM killer */
-#define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
-#define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
-
-#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
-
 struct sighand_struct {
 	atomic_t		count;
 	struct k_sigaction	action[_NSIG];
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ab81e564e076..f46912aa4f4c 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -2,5 +2,74 @@
 #define _LINUX_SCHED_COREDUMP_H
 
 #include <linux/sched.h>
+#include <linux/mm_types.h>
+
+#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
+#define SUID_DUMP_USER		1	/* Dump as user of process */
+#define SUID_DUMP_ROOT		2	/* Dump as root */
+
+/* mm flags */
+
+/* for SUID_DUMP_* above */
+#define MMF_DUMPABLE_BITS 2
+#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
+
+extern void set_dumpable(struct mm_struct *mm, int value);
+/*
+ * This returns the actual value of the suid_dumpable flag. For things
+ * that are using this for checking for privilege transitions, it must
+ * test against SUID_DUMP_USER rather than treating it as a boolean
+ * value.
+ */
+static inline int __get_dumpable(unsigned long mm_flags)
+{
+	return mm_flags & MMF_DUMPABLE_MASK;
+}
+
+static inline int get_dumpable(struct mm_struct *mm)
+{
+	return __get_dumpable(mm->flags);
+}
+
+/* coredump filter bits */
+#define MMF_DUMP_ANON_PRIVATE	2
+#define MMF_DUMP_ANON_SHARED	3
+#define MMF_DUMP_MAPPED_PRIVATE	4
+#define MMF_DUMP_MAPPED_SHARED	5
+#define MMF_DUMP_ELF_HEADERS	6
+#define MMF_DUMP_HUGETLB_PRIVATE 7
+#define MMF_DUMP_HUGETLB_SHARED  8
+#define MMF_DUMP_DAX_PRIVATE	9
+#define MMF_DUMP_DAX_SHARED	10
+
+#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
+#define MMF_DUMP_FILTER_BITS	9
+#define MMF_DUMP_FILTER_MASK \
+	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
+#define MMF_DUMP_FILTER_DEFAULT \
+	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
+	 (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
+
+#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
+# define MMF_DUMP_MASK_DEFAULT_ELF	(1 << MMF_DUMP_ELF_HEADERS)
+#else
+# define MMF_DUMP_MASK_DEFAULT_ELF	0
+#endif
+					/* leave room for more dump flags */
+#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
+#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
+/*
+ * This one-shot flag is dropped due to necessity of changing exe once again
+ * on NFS restore
+ */
+//#define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */
+
+#define MMF_HAS_UPROBES		19	/* has uprobes */
+#define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
+#define MMF_OOM_SKIP		21	/* mm is of no interest for the OOM killer */
+#define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
+#define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
+
+#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 
 #endif /* _LINUX_SCHED_COREDUMP_H */
-- 
GitLab


From c3edc4010e9d102eb7b8f17d15c2ebc425fed63c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 08:35:14 +0100
Subject: [PATCH 591/898] sched/headers: Move task_struct::signal and
 task_struct::sighand types and accessors into <linux/sched/signal.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

task_struct::signal and task_struct::sighand are pointers, which would normally make it
straightforward to not define those types in sched.h.

That is not so, because the types are accompanied by a myriad of APIs (macros and inline
functions) that dereference them.

Split the types and the APIs out of sched.h and move them into a new header, <linux/sched/signal.h>.

With this change sched.h does not know about 'struct signal' and 'struct sighand' anymore,
trying to put accessors into sched.h as a test fails the following way:

  ./include/linux/sched.h: In function ‘test_signal_types’:
  ./include/linux/sched.h:2461:18: error: dereferencing pointer to incomplete type ‘struct signal_struct’
                    ^

This reduces the size and complexity of sched.h significantly.

Update all headers and .c code that relied on getting the signal handling
functionality from <linux/sched.h> to include <linux/sched/signal.h>.

The list of affected files in the preparatory patch was partly generated by
grepping for the APIs, and partly by doing coverage build testing, both
all[yes|mod|def|no]config builds on 64-bit and 32-bit x86, and an array of
cross-architecture builds.

Nevertheless some (trivial) build breakage is still expected related to rare
Kconfig combinations and in-flight patches to various kernel code, but most
of it should be handled by this patch.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/nwfpe/fpmodule.c    |   2 +-
 arch/sh/kernel/cpu/sh4/fpu.c |   3 +-
 drivers/net/tap.c            |   2 +-
 include/linux/sched.h        | 499 +---------------------------------
 include/linux/sched/signal.h | 502 +++++++++++++++++++++++++++++++++++
 kernel/cgroup/cgroup-v1.c    |   1 +
 mm/vmalloc.c                 |   2 +-
 net/smc/af_smc.c             |   2 +
 net/smc/smc_clc.c            |   2 +
 net/smc/smc_close.c          |   2 +
 net/smc/smc_rx.c             |   2 +
 net/smc/smc_tx.c             |   2 +
 12 files changed, 520 insertions(+), 501 deletions(-)

diff --git a/arch/arm/nwfpe/fpmodule.c b/arch/arm/nwfpe/fpmodule.c
index ec717c190e2c..1365e8650843 100644
--- a/arch/arm/nwfpe/fpmodule.c
+++ b/arch/arm/nwfpe/fpmodule.c
@@ -31,7 +31,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/init.h>
 
 #include <asm/thread_notify.h>
diff --git a/arch/sh/kernel/cpu/sh4/fpu.c b/arch/sh/kernel/cpu/sh4/fpu.c
index 69ab4d3c8d41..95fd2dcb83da 100644
--- a/arch/sh/kernel/cpu/sh4/fpu.c
+++ b/arch/sh/kernel/cpu/sh4/fpu.c
@@ -10,8 +10,7 @@
  *
  * FIXME! These routines have not been tested for big endian case.
  */
-#include <linux/sched.h>
-#include <linux/signal.h>
+#include <linux/sched/signal.h>
 #include <linux/io.h>
 #include <cpu/fpu.h>
 #include <asm/processor.h>
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 35b55a2fa1a1..4d4173d25dd0 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/cache.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7934cd0acbc7..c1586104d4c0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -71,6 +71,9 @@ struct blk_plug;
 struct filename;
 struct nameidata;
 
+struct signal_struct;
+struct sighand_struct;
+
 extern unsigned long total_forks;
 extern int nr_threads;
 DECLARE_PER_CPU(unsigned long, process_counts);
@@ -361,13 +364,6 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 #endif
 
-struct sighand_struct {
-	atomic_t		count;
-	struct k_sigaction	action[_NSIG];
-	spinlock_t		siglock;
-	wait_queue_head_t	signalfd_wqh;
-};
-
 struct pacct_struct {
 	int			ac_flag;
 	long			ac_exitcode;
@@ -485,195 +481,6 @@ struct thread_group_cputimer {
 #include <linux/rwsem.h>
 struct autogroup;
 
-/*
- * NOTE! "signal_struct" does not have its own
- * locking, because a shared signal_struct always
- * implies a shared sighand_struct, so locking
- * sighand_struct is always a proper superset of
- * the locking of signal_struct.
- */
-struct signal_struct {
-	atomic_t		sigcnt;
-	atomic_t		live;
-	int			nr_threads;
-	struct list_head	thread_head;
-
-	wait_queue_head_t	wait_chldexit;	/* for wait4() */
-
-	/* current thread group signal load-balancing target: */
-	struct task_struct	*curr_target;
-
-	/* shared signal handling: */
-	struct sigpending	shared_pending;
-
-	/* thread group exit support */
-	int			group_exit_code;
-	/* overloaded:
-	 * - notify group_exit_task when ->count is equal to notify_count
-	 * - everyone except group_exit_task is stopped during signal delivery
-	 *   of fatal signals, group_exit_task processes the signal.
-	 */
-	int			notify_count;
-	struct task_struct	*group_exit_task;
-
-	/* thread group stop support, overloads group_exit_code too */
-	int			group_stop_count;
-	unsigned int		flags; /* see SIGNAL_* flags below */
-
-	/*
-	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
-	 * manager, to re-parent orphan (double-forking) child processes
-	 * to this process instead of 'init'. The service manager is
-	 * able to receive SIGCHLD signals and is able to investigate
-	 * the process until it calls wait(). All children of this
-	 * process will inherit a flag if they should look for a
-	 * child_subreaper process at exit.
-	 */
-	unsigned int		is_child_subreaper:1;
-	unsigned int		has_child_subreaper:1;
-
-#ifdef CONFIG_POSIX_TIMERS
-
-	/* POSIX.1b Interval Timers */
-	int			posix_timer_id;
-	struct list_head	posix_timers;
-
-	/* ITIMER_REAL timer for the process */
-	struct hrtimer real_timer;
-	ktime_t it_real_incr;
-
-	/*
-	 * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
-	 * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
-	 * values are defined to 0 and 1 respectively
-	 */
-	struct cpu_itimer it[2];
-
-	/*
-	 * Thread group totals for process CPU timers.
-	 * See thread_group_cputimer(), et al, for details.
-	 */
-	struct thread_group_cputimer cputimer;
-
-	/* Earliest-expiration cache. */
-	struct task_cputime cputime_expires;
-
-	struct list_head cpu_timers[3];
-
-#endif
-
-	struct pid *leader_pid;
-
-#ifdef CONFIG_NO_HZ_FULL
-	atomic_t tick_dep_mask;
-#endif
-
-	struct pid *tty_old_pgrp;
-
-	/* boolean value for session group leader */
-	int leader;
-
-	struct tty_struct *tty; /* NULL if no tty */
-
-#ifdef CONFIG_SCHED_AUTOGROUP
-	struct autogroup *autogroup;
-#endif
-	/*
-	 * Cumulative resource counters for dead threads in the group,
-	 * and for reaped dead child processes forked by this group.
-	 * Live threads maintain their own counters and add to these
-	 * in __exit_signal, except for the group leader.
-	 */
-	seqlock_t stats_lock;
-	u64 utime, stime, cutime, cstime;
-	u64 gtime;
-	u64 cgtime;
-	struct prev_cputime prev_cputime;
-	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
-	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
-	unsigned long inblock, oublock, cinblock, coublock;
-	unsigned long maxrss, cmaxrss;
-	struct task_io_accounting ioac;
-
-	/*
-	 * Cumulative ns of schedule CPU time fo dead threads in the
-	 * group, not including a zombie group leader, (This only differs
-	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
-	 * other than jiffies.)
-	 */
-	unsigned long long sum_sched_runtime;
-
-	/*
-	 * We don't bother to synchronize most readers of this at all,
-	 * because there is no reader checking a limit that actually needs
-	 * to get both rlim_cur and rlim_max atomically, and either one
-	 * alone is a single word that can safely be read normally.
-	 * getrlimit/setrlimit use task_lock(current->group_leader) to
-	 * protect this instead of the siglock, because they really
-	 * have no need to disable irqs.
-	 */
-	struct rlimit rlim[RLIM_NLIMITS];
-
-#ifdef CONFIG_BSD_PROCESS_ACCT
-	struct pacct_struct pacct;	/* per-process accounting information */
-#endif
-#ifdef CONFIG_TASKSTATS
-	struct taskstats *stats;
-#endif
-#ifdef CONFIG_AUDIT
-	unsigned audit_tty;
-	struct tty_audit_buf *tty_audit_buf;
-#endif
-
-	/*
-	 * Thread is the potential origin of an oom condition; kill first on
-	 * oom
-	 */
-	bool oom_flag_origin;
-	short oom_score_adj;		/* OOM kill score adjustment */
-	short oom_score_adj_min;	/* OOM kill score adjustment min value.
-					 * Only settable by CAP_SYS_RESOURCE. */
-	struct mm_struct *oom_mm;	/* recorded mm when the thread group got
-					 * killed by the oom killer */
-
-	struct mutex cred_guard_mutex;	/* guard against foreign influences on
-					 * credential calculations
-					 * (notably. ptrace) */
-};
-
-/*
- * Bits in flags field of signal_struct.
- */
-#define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
-#define SIGNAL_STOP_CONTINUED	0x00000002 /* SIGCONT since WCONTINUED reap */
-#define SIGNAL_GROUP_EXIT	0x00000004 /* group exit in progress */
-#define SIGNAL_GROUP_COREDUMP	0x00000008 /* coredump in progress */
-/*
- * Pending notifications to parent.
- */
-#define SIGNAL_CLD_STOPPED	0x00000010
-#define SIGNAL_CLD_CONTINUED	0x00000020
-#define SIGNAL_CLD_MASK		(SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
-
-#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */
-
-#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
-			  SIGNAL_STOP_CONTINUED)
-
-static inline void signal_set_stop_flags(struct signal_struct *sig,
-					 unsigned int flags)
-{
-	WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
-	sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
-}
-
-/* If true, all threads except ->group_exit_task have pending SIGKILL */
-static inline int signal_group_exit(const struct signal_struct *sig)
-{
-	return	(sig->flags & SIGNAL_GROUP_EXIT) ||
-		(sig->group_exit_task != NULL);
-}
-
 /*
  * Some day this will be a full-fledged user tracking system..
  */
@@ -2126,190 +1933,8 @@ extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
-extern void flush_signals(struct task_struct *);
-extern void ignore_signals(struct task_struct *);
-extern void flush_signal_handlers(struct task_struct *, int force_default);
-extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
-
-static inline int kernel_dequeue_signal(siginfo_t *info)
-{
-	struct task_struct *tsk = current;
-	siginfo_t __info;
-	int ret;
-
-	spin_lock_irq(&tsk->sighand->siglock);
-	ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
-	spin_unlock_irq(&tsk->sighand->siglock);
-
-	return ret;
-}
-
-static inline void kernel_signal_stop(void)
-{
-	spin_lock_irq(&current->sighand->siglock);
-	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
-		__set_current_state(TASK_STOPPED);
-	spin_unlock_irq(&current->sighand->siglock);
-
-	schedule();
-}
 
 extern void release_task(struct task_struct * p);
-extern int send_sig_info(int, struct siginfo *, struct task_struct *);
-extern int force_sigsegv(int, struct task_struct *);
-extern int force_sig_info(int, struct siginfo *, struct task_struct *);
-extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
-extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
-extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *,
-				const struct cred *, u32);
-extern int kill_pgrp(struct pid *pid, int sig, int priv);
-extern int kill_pid(struct pid *pid, int sig, int priv);
-extern int kill_proc_info(int, struct siginfo *, pid_t);
-extern __must_check bool do_notify_parent(struct task_struct *, int);
-extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
-extern void force_sig(int, struct task_struct *);
-extern int send_sig(int, struct task_struct *, int);
-extern int zap_other_threads(struct task_struct *p);
-extern struct sigqueue *sigqueue_alloc(void);
-extern void sigqueue_free(struct sigqueue *);
-extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
-extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
-
-#ifdef TIF_RESTORE_SIGMASK
-/*
- * Legacy restore_sigmask accessors.  These are inefficient on
- * SMP architectures because they require atomic operations.
- */
-
-/**
- * set_restore_sigmask() - make sure saved_sigmask processing gets done
- *
- * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
- * will run before returning to user mode, to process the flag.  For
- * all callers, TIF_SIGPENDING is already set or it's no harm to set
- * it.  TIF_RESTORE_SIGMASK need not be in the set of bits that the
- * arch code will notice on return to user mode, in case those bits
- * are scarce.  We set TIF_SIGPENDING here to ensure that the arch
- * signal code always gets run when TIF_RESTORE_SIGMASK is set.
- */
-static inline void set_restore_sigmask(void)
-{
-	set_thread_flag(TIF_RESTORE_SIGMASK);
-	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
-}
-static inline void clear_restore_sigmask(void)
-{
-	clear_thread_flag(TIF_RESTORE_SIGMASK);
-}
-static inline bool test_restore_sigmask(void)
-{
-	return test_thread_flag(TIF_RESTORE_SIGMASK);
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
-}
-
-#else	/* TIF_RESTORE_SIGMASK */
-
-/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */
-static inline void set_restore_sigmask(void)
-{
-	current->restore_sigmask = true;
-	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current->restore_sigmask = false;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current->restore_sigmask;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	if (!current->restore_sigmask)
-		return false;
-	current->restore_sigmask = false;
-	return true;
-}
-#endif
-
-static inline void restore_saved_sigmask(void)
-{
-	if (test_and_clear_restore_sigmask())
-		__set_current_blocked(&current->saved_sigmask);
-}
-
-static inline sigset_t *sigmask_to_save(void)
-{
-	sigset_t *res = &current->blocked;
-	if (unlikely(test_restore_sigmask()))
-		res = &current->saved_sigmask;
-	return res;
-}
-
-static inline int kill_cad_pid(int sig, int priv)
-{
-	return kill_pid(cad_pid, sig, priv);
-}
-
-/* These can be the second arg to send_sig_info/send_group_sig_info.  */
-#define SEND_SIG_NOINFO ((struct siginfo *) 0)
-#define SEND_SIG_PRIV	((struct siginfo *) 1)
-#define SEND_SIG_FORCED	((struct siginfo *) 2)
-
-/*
- * True if we are on the alternate signal stack.
- */
-static inline int on_sig_stack(unsigned long sp)
-{
-	/*
-	 * If the signal stack is SS_AUTODISARM then, by construction, we
-	 * can't be on the signal stack unless user code deliberately set
-	 * SS_AUTODISARM when we were already on it.
-	 *
-	 * This improves reliability: if user state gets corrupted such that
-	 * the stack pointer points very close to the end of the signal stack,
-	 * then this check will enable the signal to be handled anyway.
-	 */
-	if (current->sas_ss_flags & SS_AUTODISARM)
-		return 0;
-
-#ifdef CONFIG_STACK_GROWSUP
-	return sp >= current->sas_ss_sp &&
-		sp - current->sas_ss_sp < current->sas_ss_size;
-#else
-	return sp > current->sas_ss_sp &&
-		sp - current->sas_ss_sp <= current->sas_ss_size;
-#endif
-}
-
-static inline int sas_ss_flags(unsigned long sp)
-{
-	if (!current->sas_ss_size)
-		return SS_DISABLE;
-
-	return on_sig_stack(sp) ? SS_ONSTACK : 0;
-}
-
-static inline void sas_ss_reset(struct task_struct *p)
-{
-	p->sas_ss_sp = 0;
-	p->sas_ss_size = 0;
-	p->sas_ss_flags = SS_DISABLE;
-}
-
-static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
-{
-	if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp))
-#ifdef CONFIG_STACK_GROWSUP
-		return current->sas_ss_sp;
-#else
-		return current->sas_ss_sp + current->sas_ss_size;
-#endif
-	return sp;
-}
 
 #ifdef CONFIG_HAVE_COPY_THREAD_TLS
 extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
@@ -2338,10 +1963,8 @@ static inline void exit_thread(struct task_struct *tsk)
 #endif
 
 extern void exit_files(struct task_struct *);
-extern void __cleanup_sighand(struct sighand_struct *);
 
 extern void exit_itimers(struct signal_struct *);
-extern void flush_itimer_signals(void);
 
 extern void do_group_exit(int);
 
@@ -2376,81 +1999,6 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
-#define tasklist_empty() \
-	list_empty(&init_task.tasks)
-
-#define next_task(p) \
-	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
-
-#define for_each_process(p) \
-	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
-
-extern bool current_is_single_threaded(void);
-
-/*
- * Careful: do_each_thread/while_each_thread is a double loop so
- *          'break' will not work as expected - use goto instead.
- */
-#define do_each_thread(g, t) \
-	for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
-
-#define while_each_thread(g, t) \
-	while ((t = next_thread(t)) != g)
-
-#define __for_each_thread(signal, t)	\
-	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
-
-#define for_each_thread(p, t)		\
-	__for_each_thread((p)->signal, t)
-
-/* Careful: this is a double loop, 'break' won't work as expected. */
-#define for_each_process_thread(p, t)	\
-	for_each_process(p) for_each_thread(p, t)
-
-typedef int (*proc_visitor)(struct task_struct *p, void *data);
-void walk_process_tree(struct task_struct *top, proc_visitor, void *);
-
-static inline int get_nr_threads(struct task_struct *tsk)
-{
-	return tsk->signal->nr_threads;
-}
-
-static inline bool thread_group_leader(struct task_struct *p)
-{
-	return p->exit_signal >= 0;
-}
-
-/* Do to the insanities of de_thread it is possible for a process
- * to have the pid of the thread group leader without actually being
- * the thread group leader.  For iteration through the pids in proc
- * all we care about is that we have a task with the appropriate
- * pid, we don't actually care if we have the right task.
- */
-static inline bool has_group_leader_pid(struct task_struct *p)
-{
-	return task_pid(p) == p->signal->leader_pid;
-}
-
-static inline
-bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
-{
-	return p1->signal == p2->signal;
-}
-
-static inline struct task_struct *next_thread(const struct task_struct *p)
-{
-	return list_entry_rcu(p->thread_group.next,
-			      struct task_struct, thread_group);
-}
-
-static inline int thread_group_empty(struct task_struct *p)
-{
-	return list_empty(&p->thread_group);
-}
-
-#define delay_group_leader(p) \
-		(thread_group_leader(p) && !thread_group_empty(p))
-
 /*
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
@@ -2471,25 +2019,6 @@ static inline void task_unlock(struct task_struct *p)
 	spin_unlock(&p->alloc_lock);
 }
 
-extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
-							unsigned long *flags);
-
-static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
-						       unsigned long *flags)
-{
-	struct sighand_struct *ret;
-
-	ret = __lock_task_sighand(tsk, flags);
-	(void)__cond_lock(&tsk->sighand->siglock, ret);
-	return ret;
-}
-
-static inline void unlock_task_sighand(struct task_struct *tsk,
-						unsigned long *flags)
-{
-	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
-}
-
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 
 static inline struct thread_info *task_thread_info(struct task_struct *task)
@@ -2862,28 +2391,6 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 }
 #endif /* CONFIG_MEMCG */
 
-static inline unsigned long task_rlimit(const struct task_struct *tsk,
-		unsigned int limit)
-{
-	return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
-}
-
-static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
-		unsigned int limit)
-{
-	return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
-}
-
-static inline unsigned long rlimit(unsigned int limit)
-{
-	return task_rlimit(current, limit);
-}
-
-static inline unsigned long rlimit_max(unsigned int limit)
-{
-	return task_rlimit_max(current, limit);
-}
-
 #define SCHED_CPUFREQ_RT	(1U << 0)
 #define SCHED_CPUFREQ_DL	(1U << 1)
 #define SCHED_CPUFREQ_IOWAIT	(1U << 2)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index c6958a53fef3..53fe5450f431 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -8,4 +8,506 @@
 #include <linux/sched/jobctl.h>
 #include <linux/sched/task.h>
 
+/*
+ * Types defining task->signal and task->sighand and APIs using them:
+ */
+
+struct sighand_struct {
+	atomic_t		count;
+	struct k_sigaction	action[_NSIG];
+	spinlock_t		siglock;
+	wait_queue_head_t	signalfd_wqh;
+};
+
+/*
+ * NOTE! "signal_struct" does not have its own
+ * locking, because a shared signal_struct always
+ * implies a shared sighand_struct, so locking
+ * sighand_struct is always a proper superset of
+ * the locking of signal_struct.
+ */
+struct signal_struct {
+	atomic_t		sigcnt;
+	atomic_t		live;
+	int			nr_threads;
+	struct list_head	thread_head;
+
+	wait_queue_head_t	wait_chldexit;	/* for wait4() */
+
+	/* current thread group signal load-balancing target: */
+	struct task_struct	*curr_target;
+
+	/* shared signal handling: */
+	struct sigpending	shared_pending;
+
+	/* thread group exit support */
+	int			group_exit_code;
+	/* overloaded:
+	 * - notify group_exit_task when ->count is equal to notify_count
+	 * - everyone except group_exit_task is stopped during signal delivery
+	 *   of fatal signals, group_exit_task processes the signal.
+	 */
+	int			notify_count;
+	struct task_struct	*group_exit_task;
+
+	/* thread group stop support, overloads group_exit_code too */
+	int			group_stop_count;
+	unsigned int		flags; /* see SIGNAL_* flags below */
+
+	/*
+	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
+	 * manager, to re-parent orphan (double-forking) child processes
+	 * to this process instead of 'init'. The service manager is
+	 * able to receive SIGCHLD signals and is able to investigate
+	 * the process until it calls wait(). All children of this
+	 * process will inherit a flag if they should look for a
+	 * child_subreaper process at exit.
+	 */
+	unsigned int		is_child_subreaper:1;
+	unsigned int		has_child_subreaper:1;
+
+#ifdef CONFIG_POSIX_TIMERS
+
+	/* POSIX.1b Interval Timers */
+	int			posix_timer_id;
+	struct list_head	posix_timers;
+
+	/* ITIMER_REAL timer for the process */
+	struct hrtimer real_timer;
+	ktime_t it_real_incr;
+
+	/*
+	 * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
+	 * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
+	 * values are defined to 0 and 1 respectively
+	 */
+	struct cpu_itimer it[2];
+
+	/*
+	 * Thread group totals for process CPU timers.
+	 * See thread_group_cputimer(), et al, for details.
+	 */
+	struct thread_group_cputimer cputimer;
+
+	/* Earliest-expiration cache. */
+	struct task_cputime cputime_expires;
+
+	struct list_head cpu_timers[3];
+
+#endif
+
+	struct pid *leader_pid;
+
+#ifdef CONFIG_NO_HZ_FULL
+	atomic_t tick_dep_mask;
+#endif
+
+	struct pid *tty_old_pgrp;
+
+	/* boolean value for session group leader */
+	int leader;
+
+	struct tty_struct *tty; /* NULL if no tty */
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
+	/*
+	 * Cumulative resource counters for dead threads in the group,
+	 * and for reaped dead child processes forked by this group.
+	 * Live threads maintain their own counters and add to these
+	 * in __exit_signal, except for the group leader.
+	 */
+	seqlock_t stats_lock;
+	u64 utime, stime, cutime, cstime;
+	u64 gtime;
+	u64 cgtime;
+	struct prev_cputime prev_cputime;
+	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
+	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
+	unsigned long inblock, oublock, cinblock, coublock;
+	unsigned long maxrss, cmaxrss;
+	struct task_io_accounting ioac;
+
+	/*
+	 * Cumulative ns of schedule CPU time fo dead threads in the
+	 * group, not including a zombie group leader, (This only differs
+	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
+	 * other than jiffies.)
+	 */
+	unsigned long long sum_sched_runtime;
+
+	/*
+	 * We don't bother to synchronize most readers of this at all,
+	 * because there is no reader checking a limit that actually needs
+	 * to get both rlim_cur and rlim_max atomically, and either one
+	 * alone is a single word that can safely be read normally.
+	 * getrlimit/setrlimit use task_lock(current->group_leader) to
+	 * protect this instead of the siglock, because they really
+	 * have no need to disable irqs.
+	 */
+	struct rlimit rlim[RLIM_NLIMITS];
+
+#ifdef CONFIG_BSD_PROCESS_ACCT
+	struct pacct_struct pacct;	/* per-process accounting information */
+#endif
+#ifdef CONFIG_TASKSTATS
+	struct taskstats *stats;
+#endif
+#ifdef CONFIG_AUDIT
+	unsigned audit_tty;
+	struct tty_audit_buf *tty_audit_buf;
+#endif
+
+	/*
+	 * Thread is the potential origin of an oom condition; kill first on
+	 * oom
+	 */
+	bool oom_flag_origin;
+	short oom_score_adj;		/* OOM kill score adjustment */
+	short oom_score_adj_min;	/* OOM kill score adjustment min value.
+					 * Only settable by CAP_SYS_RESOURCE. */
+	struct mm_struct *oom_mm;	/* recorded mm when the thread group got
+					 * killed by the oom killer */
+
+	struct mutex cred_guard_mutex;	/* guard against foreign influences on
+					 * credential calculations
+					 * (notably. ptrace) */
+};
+
+/*
+ * Bits in flags field of signal_struct.
+ */
+#define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
+#define SIGNAL_STOP_CONTINUED	0x00000002 /* SIGCONT since WCONTINUED reap */
+#define SIGNAL_GROUP_EXIT	0x00000004 /* group exit in progress */
+#define SIGNAL_GROUP_COREDUMP	0x00000008 /* coredump in progress */
+/*
+ * Pending notifications to parent.
+ */
+#define SIGNAL_CLD_STOPPED	0x00000010
+#define SIGNAL_CLD_CONTINUED	0x00000020
+#define SIGNAL_CLD_MASK		(SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
+
+#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */
+
+#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
+			  SIGNAL_STOP_CONTINUED)
+
+static inline void signal_set_stop_flags(struct signal_struct *sig,
+					 unsigned int flags)
+{
+	WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
+	sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
+}
+
+/* If true, all threads except ->group_exit_task have pending SIGKILL */
+static inline int signal_group_exit(const struct signal_struct *sig)
+{
+	return	(sig->flags & SIGNAL_GROUP_EXIT) ||
+		(sig->group_exit_task != NULL);
+}
+
+extern void flush_signals(struct task_struct *);
+extern void ignore_signals(struct task_struct *);
+extern void flush_signal_handlers(struct task_struct *, int force_default);
+extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
+
+static inline int kernel_dequeue_signal(siginfo_t *info)
+{
+	struct task_struct *tsk = current;
+	siginfo_t __info;
+	int ret;
+
+	spin_lock_irq(&tsk->sighand->siglock);
+	ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	return ret;
+}
+
+static inline void kernel_signal_stop(void)
+{
+	spin_lock_irq(&current->sighand->siglock);
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+		__set_current_state(TASK_STOPPED);
+	spin_unlock_irq(&current->sighand->siglock);
+
+	schedule();
+}
+extern int send_sig_info(int, struct siginfo *, struct task_struct *);
+extern int force_sigsegv(int, struct task_struct *);
+extern int force_sig_info(int, struct siginfo *, struct task_struct *);
+extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
+extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
+extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *,
+				const struct cred *, u32);
+extern int kill_pgrp(struct pid *pid, int sig, int priv);
+extern int kill_pid(struct pid *pid, int sig, int priv);
+extern int kill_proc_info(int, struct siginfo *, pid_t);
+extern __must_check bool do_notify_parent(struct task_struct *, int);
+extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
+extern void force_sig(int, struct task_struct *);
+extern int send_sig(int, struct task_struct *, int);
+extern int zap_other_threads(struct task_struct *p);
+extern struct sigqueue *sigqueue_alloc(void);
+extern void sigqueue_free(struct sigqueue *);
+extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
+extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
+
+#ifdef TIF_RESTORE_SIGMASK
+/*
+ * Legacy restore_sigmask accessors.  These are inefficient on
+ * SMP architectures because they require atomic operations.
+ */
+
+/**
+ * set_restore_sigmask() - make sure saved_sigmask processing gets done
+ *
+ * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
+ * will run before returning to user mode, to process the flag.  For
+ * all callers, TIF_SIGPENDING is already set or it's no harm to set
+ * it.  TIF_RESTORE_SIGMASK need not be in the set of bits that the
+ * arch code will notice on return to user mode, in case those bits
+ * are scarce.  We set TIF_SIGPENDING here to ensure that the arch
+ * signal code always gets run when TIF_RESTORE_SIGMASK is set.
+ */
+static inline void set_restore_sigmask(void)
+{
+	set_thread_flag(TIF_RESTORE_SIGMASK);
+	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+	clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_restore_sigmask(void)
+{
+	return test_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+	return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+
+#else	/* TIF_RESTORE_SIGMASK */
+
+/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */
+static inline void set_restore_sigmask(void)
+{
+	current->restore_sigmask = true;
+	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+	current->restore_sigmask = false;
+}
+static inline bool test_restore_sigmask(void)
+{
+	return current->restore_sigmask;
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+	if (!current->restore_sigmask)
+		return false;
+	current->restore_sigmask = false;
+	return true;
+}
+#endif
+
+static inline void restore_saved_sigmask(void)
+{
+	if (test_and_clear_restore_sigmask())
+		__set_current_blocked(&current->saved_sigmask);
+}
+
+static inline sigset_t *sigmask_to_save(void)
+{
+	sigset_t *res = &current->blocked;
+	if (unlikely(test_restore_sigmask()))
+		res = &current->saved_sigmask;
+	return res;
+}
+
+static inline int kill_cad_pid(int sig, int priv)
+{
+	return kill_pid(cad_pid, sig, priv);
+}
+
+/* These can be the second arg to send_sig_info/send_group_sig_info.  */
+#define SEND_SIG_NOINFO ((struct siginfo *) 0)
+#define SEND_SIG_PRIV	((struct siginfo *) 1)
+#define SEND_SIG_FORCED	((struct siginfo *) 2)
+
+/*
+ * True if we are on the alternate signal stack.
+ */
+static inline int on_sig_stack(unsigned long sp)
+{
+	/*
+	 * If the signal stack is SS_AUTODISARM then, by construction, we
+	 * can't be on the signal stack unless user code deliberately set
+	 * SS_AUTODISARM when we were already on it.
+	 *
+	 * This improves reliability: if user state gets corrupted such that
+	 * the stack pointer points very close to the end of the signal stack,
+	 * then this check will enable the signal to be handled anyway.
+	 */
+	if (current->sas_ss_flags & SS_AUTODISARM)
+		return 0;
+
+#ifdef CONFIG_STACK_GROWSUP
+	return sp >= current->sas_ss_sp &&
+		sp - current->sas_ss_sp < current->sas_ss_size;
+#else
+	return sp > current->sas_ss_sp &&
+		sp - current->sas_ss_sp <= current->sas_ss_size;
+#endif
+}
+
+static inline int sas_ss_flags(unsigned long sp)
+{
+	if (!current->sas_ss_size)
+		return SS_DISABLE;
+
+	return on_sig_stack(sp) ? SS_ONSTACK : 0;
+}
+
+static inline void sas_ss_reset(struct task_struct *p)
+{
+	p->sas_ss_sp = 0;
+	p->sas_ss_size = 0;
+	p->sas_ss_flags = SS_DISABLE;
+}
+
+static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
+{
+	if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp))
+#ifdef CONFIG_STACK_GROWSUP
+		return current->sas_ss_sp;
+#else
+		return current->sas_ss_sp + current->sas_ss_size;
+#endif
+	return sp;
+}
+
+extern void __cleanup_sighand(struct sighand_struct *);
+extern void flush_itimer_signals(void);
+
+#define tasklist_empty() \
+	list_empty(&init_task.tasks)
+
+#define next_task(p) \
+	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
+
+#define for_each_process(p) \
+	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
+
+extern bool current_is_single_threaded(void);
+
+/*
+ * Careful: do_each_thread/while_each_thread is a double loop so
+ *          'break' will not work as expected - use goto instead.
+ */
+#define do_each_thread(g, t) \
+	for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
+
+#define while_each_thread(g, t) \
+	while ((t = next_thread(t)) != g)
+
+#define __for_each_thread(signal, t)	\
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t)		\
+	__for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t)	\
+	for_each_process(p) for_each_thread(p, t)
+
+typedef int (*proc_visitor)(struct task_struct *p, void *data);
+void walk_process_tree(struct task_struct *top, proc_visitor, void *);
+
+static inline int get_nr_threads(struct task_struct *tsk)
+{
+	return tsk->signal->nr_threads;
+}
+
+static inline bool thread_group_leader(struct task_struct *p)
+{
+	return p->exit_signal >= 0;
+}
+
+/* Do to the insanities of de_thread it is possible for a process
+ * to have the pid of the thread group leader without actually being
+ * the thread group leader.  For iteration through the pids in proc
+ * all we care about is that we have a task with the appropriate
+ * pid, we don't actually care if we have the right task.
+ */
+static inline bool has_group_leader_pid(struct task_struct *p)
+{
+	return task_pid(p) == p->signal->leader_pid;
+}
+
+static inline
+bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
+{
+	return p1->signal == p2->signal;
+}
+
+static inline struct task_struct *next_thread(const struct task_struct *p)
+{
+	return list_entry_rcu(p->thread_group.next,
+			      struct task_struct, thread_group);
+}
+
+static inline int thread_group_empty(struct task_struct *p)
+{
+	return list_empty(&p->thread_group);
+}
+
+#define delay_group_leader(p) \
+		(thread_group_leader(p) && !thread_group_empty(p))
+
+extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
+							unsigned long *flags);
+
+static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+						       unsigned long *flags)
+{
+	struct sighand_struct *ret;
+
+	ret = __lock_task_sighand(tsk, flags);
+	(void)__cond_lock(&tsk->sighand->siglock, ret);
+	return ret;
+}
+
+static inline void unlock_task_sighand(struct task_struct *tsk,
+						unsigned long *flags)
+{
+	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
+}
+
+static inline unsigned long task_rlimit(const struct task_struct *tsk,
+		unsigned int limit)
+{
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
+}
+
+static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
+		unsigned int limit)
+{
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
+}
+
+static inline unsigned long rlimit(unsigned int limit)
+{
+	return task_rlimit(current, limit);
+}
+
+static inline unsigned long rlimit_max(unsigned int limit)
+{
+	return task_rlimit_max(current, limit);
+}
+
 #endif /* _LINUX_SCHED_SIGNAL_H */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index fc34bcf2329f..08d2cb605101 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -5,6 +5,7 @@
 #include <linux/sort.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/delayacct.h>
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index be93949b4885..b4024d688f38 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -12,7 +12,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/highmem.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5d4208ad029e..85837ab90e89 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -27,6 +27,8 @@
 #include <linux/inetdevice.h>
 #include <linux/workqueue.h>
 #include <linux/in.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <net/smc.h>
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index cc6b6f8651eb..e41f594a1e1d 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -11,6 +11,8 @@
 
 #include <linux/in.h>
 #include <linux/if_ether.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include <net/tcp.h>
 
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 03dfcc6b7661..67a71d170bed 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -9,6 +9,8 @@
  */
 
 #include <linux/workqueue.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 
 #include "smc.h"
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 5d1878732f46..c4ef9a4ec569 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -11,6 +11,8 @@
 
 #include <linux/net.h>
 #include <linux/rcupdate.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 
 #include "smc.h"
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 6e73b28915ea..69a0013dd25c 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -15,6 +15,8 @@
 #include <linux/net.h>
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 
 #include "smc.h"
-- 
GitLab


From bcbb6a5bf7df6e37ba652d1f426eab042ec4f56b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 10:22:42 +0100
Subject: [PATCH 592/898] sched/headers: Move 'struct user_struct' definition
 and APIs to the new <linux/sched/user.h> header

'struct user_struct' was added to sched.h historically, but it's actually
entirely independent of task_struct and of scheduler details, so move
it to its own header.

Fix up .c files using those facilities.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 53 -------------------------------------
 include/linux/sched/user.h | 54 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+), 53 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c1586104d4c0..71efbcafaa31 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -349,7 +349,6 @@ extern void io_schedule(void);
 void __noreturn do_task_dead(void);
 
 struct nsproxy;
-struct user_namespace;
 
 #ifdef CONFIG_MMU
 extern void arch_pick_mmap_layout(struct mm_struct *mm);
@@ -481,49 +480,6 @@ struct thread_group_cputimer {
 #include <linux/rwsem.h>
 struct autogroup;
 
-/*
- * Some day this will be a full-fledged user tracking system..
- */
-struct user_struct {
-	atomic_t __count;	/* reference count */
-	atomic_t processes;	/* How many processes does this user have? */
-	atomic_t sigpending;	/* How many pending signals does this user have? */
-#ifdef CONFIG_FANOTIFY
-	atomic_t fanotify_listeners;
-#endif
-#ifdef CONFIG_EPOLL
-	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
-#endif
-#ifdef CONFIG_POSIX_MQUEUE
-	/* protected by mq_lock	*/
-	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
-#endif
-	unsigned long locked_shm; /* How many pages of mlocked shm ? */
-	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
-	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
-
-#ifdef CONFIG_KEYS
-	struct key *uid_keyring;	/* UID specific keyring */
-	struct key *session_keyring;	/* UID's default session keyring */
-#endif
-
-	/* Hash table maintenance information */
-	struct hlist_node uidhash_node;
-	kuid_t uid;
-
-#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL)
-	atomic_long_t locked_vm;
-#endif
-};
-
-extern int uids_sysfs_init(void);
-
-extern struct user_struct *find_user(kuid_t);
-
-extern struct user_struct root_user;
-#define INIT_USER (&root_user)
-
-
 struct backing_dev_info;
 struct reclaim_state;
 
@@ -1908,15 +1864,6 @@ extern struct task_struct *find_task_by_vpid(pid_t nr);
 extern struct task_struct *find_task_by_pid_ns(pid_t nr,
 		struct pid_namespace *ns);
 
-/* per-UID process charging. */
-extern struct user_struct * alloc_uid(kuid_t);
-static inline struct user_struct *get_uid(struct user_struct *u)
-{
-	atomic_inc(&u->__count);
-	return u;
-}
-extern void free_uid(struct user_struct *);
-
 #include <asm/current.h>
 
 extern void xtime_update(unsigned long ticks);
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 83238e5ddadd..40c6363da5ef 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -3,4 +3,58 @@
 
 #include <linux/sched.h>
 
+struct key;
+
+/*
+ * Some day this will be a full-fledged user tracking system..
+ */
+struct user_struct {
+	atomic_t __count;	/* reference count */
+	atomic_t processes;	/* How many processes does this user have? */
+	atomic_t sigpending;	/* How many pending signals does this user have? */
+#ifdef CONFIG_FANOTIFY
+	atomic_t fanotify_listeners;
+#endif
+#ifdef CONFIG_EPOLL
+	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
+#endif
+#ifdef CONFIG_POSIX_MQUEUE
+	/* protected by mq_lock	*/
+	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
+#endif
+	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
+	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
+
+#ifdef CONFIG_KEYS
+	struct key *uid_keyring;	/* UID specific keyring */
+	struct key *session_keyring;	/* UID's default session keyring */
+#endif
+
+	/* Hash table maintenance information */
+	struct hlist_node uidhash_node;
+	kuid_t uid;
+
+#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL)
+	atomic_long_t locked_vm;
+#endif
+};
+
+extern int uids_sysfs_init(void);
+
+extern struct user_struct *find_user(kuid_t);
+
+extern struct user_struct root_user;
+#define INIT_USER (&root_user)
+
+
+/* per-UID process charging. */
+extern struct user_struct * alloc_uid(kuid_t);
+static inline struct user_struct *get_uid(struct user_struct *u)
+{
+	atomic_inc(&u->__count);
+	return u;
+}
+extern void free_uid(struct user_struct *);
+
 #endif /* _LINUX_SCHED_USER_H */
-- 
GitLab


From d151b27d3f86589308cd8c891fdfd2db5f8e80d6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 11:17:23 +0100
Subject: [PATCH 593/898] sched/headers: Move softlockup detector watchdog
 methods to <linux/nmi.h>

These methods don't belong into <linux/sched.h>, they are neither directly
related to task_struct or are scheduler functionality.

Put them next to the other watchdog methods in <linux/nmi.h>.

( Arguably that header's name is a misnomer, and this patch makes it
  more so - but it should be renamed in another patch. )

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/nmi.h   | 37 +++++++++++++++++++++++++++++++++++++
 include/linux/sched.h | 37 -------------------------------------
 2 files changed, 37 insertions(+), 37 deletions(-)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 0a3fadc32693..aa3cd0878270 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -7,6 +7,43 @@
 #include <linux/sched.h>
 #include <asm/irq.h>
 
+#ifdef CONFIG_LOCKUP_DETECTOR
+extern void touch_softlockup_watchdog_sched(void);
+extern void touch_softlockup_watchdog(void);
+extern void touch_softlockup_watchdog_sync(void);
+extern void touch_all_softlockup_watchdogs(void);
+extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
+				  void __user *buffer,
+				  size_t *lenp, loff_t *ppos);
+extern unsigned int  softlockup_panic;
+extern unsigned int  hardlockup_panic;
+void lockup_detector_init(void);
+#else
+static inline void touch_softlockup_watchdog_sched(void)
+{
+}
+static inline void touch_softlockup_watchdog(void)
+{
+}
+static inline void touch_softlockup_watchdog_sync(void)
+{
+}
+static inline void touch_all_softlockup_watchdogs(void)
+{
+}
+static inline void lockup_detector_init(void)
+{
+}
+#endif
+
+#ifdef CONFIG_DETECT_HUNG_TASK
+void reset_hung_task_detector(void);
+#else
+static inline void reset_hung_task_detector(void)
+{
+}
+#endif
+
 /*
  * The run state of the lockup detectors is controlled by the content of the
  * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 71efbcafaa31..8a1d296c53a0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -286,43 +286,6 @@ extern int sched_cpu_dying(unsigned int cpu);
 
 extern void sched_show_task(struct task_struct *p);
 
-#ifdef CONFIG_LOCKUP_DETECTOR
-extern void touch_softlockup_watchdog_sched(void);
-extern void touch_softlockup_watchdog(void);
-extern void touch_softlockup_watchdog_sync(void);
-extern void touch_all_softlockup_watchdogs(void);
-extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
-				  void __user *buffer,
-				  size_t *lenp, loff_t *ppos);
-extern unsigned int  softlockup_panic;
-extern unsigned int  hardlockup_panic;
-void lockup_detector_init(void);
-#else
-static inline void touch_softlockup_watchdog_sched(void)
-{
-}
-static inline void touch_softlockup_watchdog(void)
-{
-}
-static inline void touch_softlockup_watchdog_sync(void)
-{
-}
-static inline void touch_all_softlockup_watchdogs(void)
-{
-}
-static inline void lockup_detector_init(void)
-{
-}
-#endif
-
-#ifdef CONFIG_DETECT_HUNG_TASK
-void reset_hung_task_detector(void);
-#else
-static inline void reset_hung_task_detector(void)
-{
-}
-#endif
-
 /* Attach to any functions which should be ignored in wchan output. */
 #define __sched		__attribute__((__section__(".sched.text")))
 
-- 
GitLab


From 8d88460edc05224b8d7ae3372173153876a02825 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 12:06:10 +0100
Subject: [PATCH 594/898] sched/headers: Move 'struct pacct_struct' and 'struct
 cpu_itimer' form <linux/sched.h> to <linux/sched/signal.h>

These structures are actually part of 'struct signal', so move them to <linux/sched/signal.h>
where they belong.

This further decreases the size and complexity of <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h        | 13 -------------
 include/linux/sched/signal.h | 16 ++++++++++++++++
 2 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8a1d296c53a0..8bf111efe98e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -326,19 +326,6 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 #endif
 
-struct pacct_struct {
-	int			ac_flag;
-	long			ac_exitcode;
-	unsigned long		ac_mem;
-	u64			ac_utime, ac_stime;
-	unsigned long		ac_minflt, ac_majflt;
-};
-
-struct cpu_itimer {
-	u64 expires;
-	u64 incr;
-};
-
 /**
  * struct prev_cputime - snaphsot of system and user cputime
  * @utime: time spent in user mode
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 53fe5450f431..30e7ceed3ef6 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -19,6 +19,22 @@ struct sighand_struct {
 	wait_queue_head_t	signalfd_wqh;
 };
 
+/*
+ * Per-process accounting stats:
+ */
+struct pacct_struct {
+	int			ac_flag;
+	long			ac_exitcode;
+	unsigned long		ac_mem;
+	u64			ac_utime, ac_stime;
+	unsigned long		ac_minflt, ac_majflt;
+};
+
+struct cpu_itimer {
+	u64 expires;
+	u64 incr;
+};
+
 /*
  * NOTE! "signal_struct" does not have its own
  * locking, because a shared signal_struct always
-- 
GitLab


From 7284c6d419b5a6ae9806927f1fd4f0cfd19a16f5 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 12:14:19 +0100
Subject: [PATCH 595/898] sched/headers: Move the cpufreq interfaces to
 <linux/sched/cpufreq.h>

No need to have this in the generic <linux/sched.h> header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h         | 17 -----------------
 include/linux/sched/cpufreq.h | 21 +++++++++++++++++++++
 2 files changed, 21 insertions(+), 17 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8bf111efe98e..aae79706ec4f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2288,21 +2288,4 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 }
 #endif /* CONFIG_MEMCG */
 
-#define SCHED_CPUFREQ_RT	(1U << 0)
-#define SCHED_CPUFREQ_DL	(1U << 1)
-#define SCHED_CPUFREQ_IOWAIT	(1U << 2)
-
-#define SCHED_CPUFREQ_RT_DL	(SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL)
-
-#ifdef CONFIG_CPU_FREQ
-struct update_util_data {
-       void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
-};
-
-void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
-                       void (*func)(struct update_util_data *data, u64 time,
-				    unsigned int flags));
-void cpufreq_remove_update_util_hook(int cpu);
-#endif /* CONFIG_CPU_FREQ */
-
 #endif
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 07ed9664fa20..2bdcfbfc4c30 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -3,4 +3,25 @@
 
 #include <linux/sched.h>
 
+/*
+ * Interface between cpufreq drivers and the scheduler:
+ */
+
+#define SCHED_CPUFREQ_RT	(1U << 0)
+#define SCHED_CPUFREQ_DL	(1U << 1)
+#define SCHED_CPUFREQ_IOWAIT	(1U << 2)
+
+#define SCHED_CPUFREQ_RT_DL	(SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL)
+
+#ifdef CONFIG_CPU_FREQ
+struct update_util_data {
+       void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
+};
+
+void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
+                       void (*func)(struct update_util_data *data, u64 time,
+				    unsigned int flags));
+void cpufreq_remove_update_util_hook(int cpu);
+#endif /* CONFIG_CPU_FREQ */
+
 #endif /* _LINUX_SCHED_CPUFREQ_H */
-- 
GitLab


From 4240c8bf877f1145571106a2934c5cea0b51b178 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 12:18:24 +0100
Subject: [PATCH 596/898] sched/headers: Move more mm_struct related
 functionality from <linux/sched.h> to <linux/sched/mm.h>

Neither the mmap_layout nor the mm_update_next_owner() methods need to be
in <linux/sched.h> - move them to the more appropriate <linux/sched/mm.h> header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h    | 21 ---------------------
 include/linux/sched/mm.h | 21 +++++++++++++++++++++
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index aae79706ec4f..1ddb82be6b50 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -313,19 +313,6 @@ void __noreturn do_task_dead(void);
 
 struct nsproxy;
 
-#ifdef CONFIG_MMU
-extern void arch_pick_mmap_layout(struct mm_struct *mm);
-extern unsigned long
-arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
-		       unsigned long, unsigned long);
-extern unsigned long
-arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
-			  unsigned long len, unsigned long pgoff,
-			  unsigned long flags);
-#else
-static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
-#endif
-
 /**
  * struct prev_cputime - snaphsot of system and user cputime
  * @utime: time spent in user mode
@@ -2280,12 +2267,4 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
-#ifdef CONFIG_MEMCG
-extern void mm_update_next_owner(struct mm_struct *mm);
-#else
-static inline void mm_update_next_owner(struct mm_struct *mm)
-{
-}
-#endif /* CONFIG_MEMCG */
-
 #endif
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index be1ae55f5ab9..93fad9f0f466 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -100,4 +100,25 @@ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
 /* Remove the current tasks stale references to the old mm_struct */
 extern void mm_release(struct task_struct *, struct mm_struct *);
 
+#ifdef CONFIG_MEMCG
+extern void mm_update_next_owner(struct mm_struct *mm);
+#else
+static inline void mm_update_next_owner(struct mm_struct *mm)
+{
+}
+#endif /* CONFIG_MEMCG */
+
+#ifdef CONFIG_MMU
+extern void arch_pick_mmap_layout(struct mm_struct *mm);
+extern unsigned long
+arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
+		       unsigned long, unsigned long);
+extern unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags);
+#else
+static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
+#endif
+
 #endif /* _LINUX_SCHED_MM_H */
-- 
GitLab


From abe722a1c59728c6c0ea4e4d5efcfe397c8abebc Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 12:27:56 +0100
Subject: [PATCH 597/898] sched/headers: Move the 'init_mm' declaration from
 <linux/sched.h> to <linux/mm_types.h>

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm_types.h | 2 ++
 include/linux/sched.h    | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6daaf0a51968..28bc710d3467 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -546,6 +546,8 @@ struct mm_struct {
 	struct work_struct async_put_work;
 };
 
+extern struct mm_struct init_mm;
+
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
 #ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1ddb82be6b50..253d8ab6256c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1782,8 +1782,6 @@ static inline int kstack_end(void *addr)
 extern union thread_union init_thread_union;
 extern struct task_struct init_task;
 
-extern struct   mm_struct init_mm;
-
 extern struct pid_namespace init_pid_ns;
 
 /*
-- 
GitLab


From d026ce796cbca3c49678a68bb4a39fb4b9cf8192 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 12:32:21 +0100
Subject: [PATCH 598/898] sched/headers: Move in_vfork() from <linux/sched.h>
 to <linux/sched/mm.h>

The in_vfork() function deals with task->mm, so it better belongs
into <linux/sched/mm.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h    | 26 --------------------------
 include/linux/sched/mm.h | 26 ++++++++++++++++++++++++++
 2 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 253d8ab6256c..aa60812b4b7a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1242,32 +1242,6 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
 #define TNF_FAULT_LOCAL	0x08
 #define TNF_MIGRATE_FAIL 0x10
 
-static inline bool in_vfork(struct task_struct *tsk)
-{
-	bool ret;
-
-	/*
-	 * need RCU to access ->real_parent if CLONE_VM was used along with
-	 * CLONE_PARENT.
-	 *
-	 * We check real_parent->mm == tsk->mm because CLONE_VFORK does not
-	 * imply CLONE_VM
-	 *
-	 * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
-	 * ->real_parent is not necessarily the task doing vfork(), so in
-	 * theory we can't rely on task_lock() if we want to dereference it.
-	 *
-	 * And in this case we can't trust the real_parent->mm == tsk->mm
-	 * check, it can be false negative. But we do not care, if init or
-	 * another oom-unkillable task does this it should blame itself.
-	 */
-	rcu_read_lock();
-	ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
-	rcu_read_unlock();
-
-	return ret;
-}
-
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 93fad9f0f466..64d83fa8d93a 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -121,4 +121,30 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 #endif
 
+static inline bool in_vfork(struct task_struct *tsk)
+{
+	bool ret;
+
+	/*
+	 * need RCU to access ->real_parent if CLONE_VM was used along with
+	 * CLONE_PARENT.
+	 *
+	 * We check real_parent->mm == tsk->mm because CLONE_VFORK does not
+	 * imply CLONE_VM
+	 *
+	 * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
+	 * ->real_parent is not necessarily the task doing vfork(), so in
+	 * theory we can't rely on task_lock() if we want to dereference it.
+	 *
+	 * And in this case we can't trust the real_parent->mm == tsk->mm
+	 * check, it can be false negative. But we do not care, if init or
+	 * another oom-unkillable task does this it should blame itself.
+	 */
+	rcu_read_lock();
+	ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #endif /* _LINUX_SCHED_MM_H */
-- 
GitLab


From 5647028d550c959577527cec9c0f29fbcea029ea Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 12:39:17 +0100
Subject: [PATCH 599/898] sched/headers: Move the NUMA balancing interfaces
 from <linux/sched.h> to <linux/sched/numa_balancing.h>

Split out the interface between the scheduler and the MM which
deals with page fault driven NUMA balancing, into the new
<linux/sched/numa_balancing.h> header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h                | 35 ------------------------
 include/linux/sched/numa_balancing.h | 40 ++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+), 35 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index aa60812b4b7a..fcaea1e7b08a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1236,41 +1236,6 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
 }
 #endif
 
-#define TNF_MIGRATED	0x01
-#define TNF_NO_GROUP	0x02
-#define TNF_SHARED	0x04
-#define TNF_FAULT_LOCAL	0x08
-#define TNF_MIGRATE_FAIL 0x10
-
-#ifdef CONFIG_NUMA_BALANCING
-extern void task_numa_fault(int last_node, int node, int pages, int flags);
-extern pid_t task_numa_group_id(struct task_struct *p);
-extern void set_numabalancing_state(bool enabled);
-extern void task_numa_free(struct task_struct *p);
-extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
-					int src_nid, int dst_cpu);
-#else
-static inline void task_numa_fault(int last_node, int node, int pages,
-				   int flags)
-{
-}
-static inline pid_t task_numa_group_id(struct task_struct *p)
-{
-	return 0;
-}
-static inline void set_numabalancing_state(bool enabled)
-{
-}
-static inline void task_numa_free(struct task_struct *p)
-{
-}
-static inline bool should_numa_migrate_memory(struct task_struct *p,
-				struct page *page, int src_nid, int dst_cpu)
-{
-	return true;
-}
-#endif
-
 static inline struct pid *task_pid(struct task_struct *task)
 {
 	return task->pids[PIDTYPE_PID].pid;
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index 999182279f78..35d5fc77b4be 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -1,6 +1,46 @@
 #ifndef _LINUX_SCHED_NUMA_BALANCING_H
 #define _LINUX_SCHED_NUMA_BALANCING_H
 
+/*
+ * This is the interface between the scheduler and the MM that
+ * implements memory access pattern based NUMA-balancing:
+ */
+
 #include <linux/sched.h>
 
+#define TNF_MIGRATED	0x01
+#define TNF_NO_GROUP	0x02
+#define TNF_SHARED	0x04
+#define TNF_FAULT_LOCAL	0x08
+#define TNF_MIGRATE_FAIL 0x10
+
+#ifdef CONFIG_NUMA_BALANCING
+extern void task_numa_fault(int last_node, int node, int pages, int flags);
+extern pid_t task_numa_group_id(struct task_struct *p);
+extern void set_numabalancing_state(bool enabled);
+extern void task_numa_free(struct task_struct *p);
+extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
+					int src_nid, int dst_cpu);
+#else
+static inline void task_numa_fault(int last_node, int node, int pages,
+				   int flags)
+{
+}
+static inline pid_t task_numa_group_id(struct task_struct *p)
+{
+	return 0;
+}
+static inline void set_numabalancing_state(bool enabled)
+{
+}
+static inline void task_numa_free(struct task_struct *p)
+{
+}
+static inline bool should_numa_migrate_memory(struct task_struct *p,
+				struct page *page, int src_nid, int dst_cpu)
+{
+	return true;
+}
+#endif
+
 #endif /* _LINUX_SCHED_NUMA_BALANCING_H */
-- 
GitLab


From c41cfc6c5ba46050b416c0b0b2621cbe68c4669c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 12:45:58 +0100
Subject: [PATCH 600/898] sched/headers: Move the JOBCTL_ defines and methods
 from <linux/sched.h> to <linux/sched/jobctl.h>

Only a small fraction of sched.h users actually utilizes these defines,
and they are not scheduler functionality in any case, so move them
into their separate header.

(Also make <linux/sched/jobctl.h> a self-contained header.)

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h        | 30 ------------------------------
 include/linux/sched/jobctl.h | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 30 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index fcaea1e7b08a..46ba8f1b5f1f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1549,36 +1549,6 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 TASK_PFA_TEST(LMK_WAITING, lmk_waiting)
 TASK_PFA_SET(LMK_WAITING, lmk_waiting)
 
-/*
- * task->jobctl flags
- */
-#define JOBCTL_STOP_SIGMASK	0xffff	/* signr of the last group stop */
-
-#define JOBCTL_STOP_DEQUEUED_BIT 16	/* stop signal dequeued */
-#define JOBCTL_STOP_PENDING_BIT	17	/* task should stop for group stop */
-#define JOBCTL_STOP_CONSUME_BIT	18	/* consume group stop count */
-#define JOBCTL_TRAP_STOP_BIT	19	/* trap for STOP */
-#define JOBCTL_TRAP_NOTIFY_BIT	20	/* trap for NOTIFY */
-#define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
-#define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
-
-#define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
-#define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
-#define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
-#define JOBCTL_TRAP_STOP	(1UL << JOBCTL_TRAP_STOP_BIT)
-#define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
-#define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
-#define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
-
-#define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
-#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
-
-extern bool task_set_jobctl_pending(struct task_struct *task,
-				    unsigned long mask);
-extern void task_clear_jobctl_trapping(struct task_struct *task);
-extern void task_clear_jobctl_pending(struct task_struct *task,
-				      unsigned long mask);
-
 static inline void rcu_copy_process(struct task_struct *p)
 {
 #ifdef CONFIG_PREEMPT_RCU
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index 228e4644937b..016afa0fb3bb 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -1,4 +1,36 @@
 #ifndef _LINUX_SCHED_JOBCTL_H
 #define _LINUX_SCHED_JOBCTL_H
 
+#include <linux/types.h>
+
+struct task_struct;
+
+/*
+ * task->jobctl flags
+ */
+#define JOBCTL_STOP_SIGMASK	0xffff	/* signr of the last group stop */
+
+#define JOBCTL_STOP_DEQUEUED_BIT 16	/* stop signal dequeued */
+#define JOBCTL_STOP_PENDING_BIT	17	/* task should stop for group stop */
+#define JOBCTL_STOP_CONSUME_BIT	18	/* consume group stop count */
+#define JOBCTL_TRAP_STOP_BIT	19	/* trap for STOP */
+#define JOBCTL_TRAP_NOTIFY_BIT	20	/* trap for NOTIFY */
+#define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
+#define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
+
+#define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP	(1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
+
+#define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
+
+extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
+extern void task_clear_jobctl_trapping(struct task_struct *task);
+extern void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask);
+
 #endif /* _LINUX_SCHED_JOBCTL_H */
-- 
GitLab


From 30a1baab81189f01c427c4939610b2dde2dbec37 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 10:06:45 +0100
Subject: [PATCH 601/898] sched/headers: Remove various unrelated headers from
 <linux/sched.h>

Remove the following header inclusions from <linux/sched.h>:

	#include <asm/param.h>
	#include <linux/threads.h>
	#include <linux/kernel.h>
	#include <linux/types.h>
	#include <linux/timex.h>
	#include <linux/jiffies.h>
	#include <linux/rbtree.h>
	#include <linux/thread_info.h>
	#include <linux/cpumask.h>
	#include <linux/errno.h>
	#include <linux/nodemask.h>
	#include <linux/preempt.h>
	#include <asm/page.h>
	#include <linux/smp.h>
	#include <linux/compiler.h>
	#include <linux/completion.h>
	#include <linux/percpu.h>
	#include <linux/topology.h>
	#include <linux/rcupdate.h>
	#include <linux/time.h>
	#include <linux/timer.h>
	#include <linux/llist.h>
	#include <linux/uidgid.h>
	#include <asm/processor.h>

because they are either not required, or are already included
naturally as part of the remaining headers.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 28 ----------------------------
 1 file changed, 28 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 46ba8f1b5f1f..7752025679c0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -5,60 +5,32 @@
 
 #include <linux/sched/prio.h>
 
-#include <asm/param.h>	/* for HZ */
-
 #include <linux/capability.h>
-#include <linux/threads.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/timex.h>
-#include <linux/jiffies.h>
 #include <linux/mutex.h>
 #include <linux/plist.h>
-#include <linux/rbtree.h>
-#include <linux/thread_info.h>
-#include <linux/cpumask.h>
-#include <linux/errno.h>
-#include <linux/nodemask.h>
 #include <linux/mm_types.h>
-#include <linux/preempt.h>
-
-#include <asm/page.h>
 #include <asm/ptrace.h>
 
-#include <linux/smp.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
 #include <linux/signal.h>
-#include <linux/compiler.h>
-#include <linux/completion.h>
 #include <linux/signal_types.h>
 #include <linux/pid.h>
-#include <linux/percpu.h>
-#include <linux/topology.h>
 #include <linux/seccomp.h>
-#include <linux/rcupdate.h>
 #include <linux/rculist.h>
 #include <linux/rtmutex.h>
 
-#include <linux/time.h>
-#include <linux/param.h>
 #include <linux/resource.h>
-#include <linux/timer.h>
 #include <linux/hrtimer.h>
 #include <linux/kcov.h>
 #include <linux/task_io_accounting.h>
 #include <linux/latencytop.h>
 #include <linux/cred.h>
-#include <linux/llist.h>
-#include <linux/uidgid.h>
 #include <linux/gfp.h>
 #include <linux/topology.h>
 #include <linux/magic.h>
 #include <linux/cgroup-defs.h>
 
-#include <asm/processor.h>
-
 struct sched_attr;
 struct sched_param;
 
-- 
GitLab


From 9a07000400c853c57477c2a5138ae9f556c40897 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 19:10:05 +0100
Subject: [PATCH 602/898] sched/headers: Move CONFIG_TASK_XACCT bits from
 <linux/sched.h> to <linux/sched/xacct.h>

The CONFIG_TASK_XACCT=y accounting inline functions are only used by
fs/read_write.c, so move them into their separate header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h       | 38 ---------------------------------
 include/linux/sched/xacct.h | 42 +++++++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 38 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7752025679c0..1201312e111e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2104,44 +2104,6 @@ extern struct task_group root_task_group;
 extern int task_can_switch_user(struct user_struct *up,
 					struct task_struct *tsk);
 
-#ifdef CONFIG_TASK_XACCT
-static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
-{
-	tsk->ioac.rchar += amt;
-}
-
-static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
-{
-	tsk->ioac.wchar += amt;
-}
-
-static inline void inc_syscr(struct task_struct *tsk)
-{
-	tsk->ioac.syscr++;
-}
-
-static inline void inc_syscw(struct task_struct *tsk)
-{
-	tsk->ioac.syscw++;
-}
-#else
-static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
-{
-}
-
-static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
-{
-}
-
-static inline void inc_syscr(struct task_struct *tsk)
-{
-}
-
-static inline void inc_syscw(struct task_struct *tsk)
-{
-}
-#endif
-
 #ifndef TASK_SIZE_OF
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
diff --git a/include/linux/sched/xacct.h b/include/linux/sched/xacct.h
index 890f7ce5cd27..a28156a0d34a 100644
--- a/include/linux/sched/xacct.h
+++ b/include/linux/sched/xacct.h
@@ -1,6 +1,48 @@
 #ifndef _LINUX_SCHED_XACCT_H
 #define _LINUX_SCHED_XACCT_H
 
+/*
+ * Extended task accounting methods:
+ */
+
 #include <linux/sched.h>
 
+#ifdef CONFIG_TASK_XACCT
+static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
+{
+	tsk->ioac.rchar += amt;
+}
+
+static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
+{
+	tsk->ioac.wchar += amt;
+}
+
+static inline void inc_syscr(struct task_struct *tsk)
+{
+	tsk->ioac.syscr++;
+}
+
+static inline void inc_syscw(struct task_struct *tsk)
+{
+	tsk->ioac.syscw++;
+}
+#else
+static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
+{
+}
+
+static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
+{
+}
+
+static inline void inc_syscr(struct task_struct *tsk)
+{
+}
+
+static inline void inc_syscw(struct task_struct *tsk)
+{
+}
+#endif
+
 #endif /* _LINUX_SCHED_XACCT_H */
-- 
GitLab


From 2a1f062a4acf0be50516ceece92a7182a173d55a Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 19:15:33 +0100
Subject: [PATCH 603/898] sched/headers: Move signal wakeup & sigpending
 methods from <linux/sched.h> into <linux/sched/signal.h>

This reduces the size of <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h        | 51 ----------------------------------
 include/linux/sched/signal.h | 53 +++++++++++++++++++++++++++++++++++-
 2 files changed, 52 insertions(+), 52 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1201312e111e..1e0400069e95 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1931,37 +1931,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
-static inline int restart_syscall(void)
-{
-	set_tsk_thread_flag(current, TIF_SIGPENDING);
-	return -ERESTARTNOINTR;
-}
-
-static inline int signal_pending(struct task_struct *p)
-{
-	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
-}
-
-static inline int __fatal_signal_pending(struct task_struct *p)
-{
-	return unlikely(sigismember(&p->pending.signal, SIGKILL));
-}
-
-static inline int fatal_signal_pending(struct task_struct *p)
-{
-	return signal_pending(p) && __fatal_signal_pending(p);
-}
-
-static inline int signal_pending_state(long state, struct task_struct *p)
-{
-	if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
-		return 0;
-	if (!signal_pending(p))
-		return 0;
-
-	return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
-}
-
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
@@ -2028,26 +1997,6 @@ static __always_inline bool need_resched(void)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
 void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
 
-/*
- * Reevaluate whether the task has signals pending delivery.
- * Wake the task if so.
- * This is required every time the blocked sigset_t changes.
- * callers must hold sighand->siglock.
- */
-extern void recalc_sigpending_and_wake(struct task_struct *t);
-extern void recalc_sigpending(void);
-
-extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
-
-static inline void signal_wake_up(struct task_struct *t, bool resume)
-{
-	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
-}
-static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
-{
-	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
-}
-
 /*
  * Wrappers for p->thread_info->cpu access. No-op on UP.
  */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 30e7ceed3ef6..b3545fb4333a 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -3,10 +3,10 @@
 
 #include <linux/rculist.h>
 #include <linux/signal.h>
-#include <linux/cred.h>
 #include <linux/sched.h>
 #include <linux/sched/jobctl.h>
 #include <linux/sched/task.h>
+#include <linux/cred.h>
 
 /*
  * Types defining task->signal and task->sighand and APIs using them:
@@ -271,6 +271,57 @@ extern void sigqueue_free(struct sigqueue *);
 extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
 extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
 
+static inline int restart_syscall(void)
+{
+	set_tsk_thread_flag(current, TIF_SIGPENDING);
+	return -ERESTARTNOINTR;
+}
+
+static inline int signal_pending(struct task_struct *p)
+{
+	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
+}
+
+static inline int __fatal_signal_pending(struct task_struct *p)
+{
+	return unlikely(sigismember(&p->pending.signal, SIGKILL));
+}
+
+static inline int fatal_signal_pending(struct task_struct *p)
+{
+	return signal_pending(p) && __fatal_signal_pending(p);
+}
+
+static inline int signal_pending_state(long state, struct task_struct *p)
+{
+	if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
+		return 0;
+	if (!signal_pending(p))
+		return 0;
+
+	return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
+}
+
+/*
+ * Reevaluate whether the task has signals pending delivery.
+ * Wake the task if so.
+ * This is required every time the blocked sigset_t changes.
+ * callers must hold sighand->siglock.
+ */
+extern void recalc_sigpending_and_wake(struct task_struct *t);
+extern void recalc_sigpending(void);
+
+extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
+
+static inline void signal_wake_up(struct task_struct *t, bool resume)
+{
+	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+}
+static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
+{
+	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+}
+
 #ifdef TIF_RESTORE_SIGMASK
 /*
  * Legacy restore_sigmask accessors.  These are inefficient on
-- 
GitLab


From 74444edaa0b2ef946e846d5ddf1ba90efcd7c200 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 20:43:54 +0100
Subject: [PATCH 604/898] sched/headers: Move the memalloc_noio_*() APIs to
 <linux/sched/mm.h>

In preparation to remove the <linux/gfp.h> include from <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h    | 22 ----------------------
 include/linux/sched/mm.h | 22 ++++++++++++++++++++++
 2 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1e0400069e95..dbc3ff04750a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1468,28 +1468,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *s
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
- * __GFP_FS is also cleared as it implies __GFP_IO.
- */
-static inline gfp_t memalloc_noio_flags(gfp_t flags)
-{
-	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-		flags &= ~(__GFP_IO | __GFP_FS);
-	return flags;
-}
-
-static inline unsigned int memalloc_noio_save(void)
-{
-	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
-	current->flags |= PF_MEMALLOC_NOIO;
-	return flags;
-}
-
-static inline void memalloc_noio_restore(unsigned int flags)
-{
-	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
-}
-
 /* Per-process atomic flags. */
 #define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */
 #define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 64d83fa8d93a..62dca4e0b4e0 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -147,4 +147,26 @@ static inline bool in_vfork(struct task_struct *tsk)
 	return ret;
 }
 
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
+static inline gfp_t memalloc_noio_flags(gfp_t flags)
+{
+	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
+		flags &= ~(__GFP_IO | __GFP_FS);
+	return flags;
+}
+
+static inline unsigned int memalloc_noio_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
+	current->flags |= PF_MEMALLOC_NOIO;
+	return flags;
+}
+
+static inline void memalloc_noio_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+}
+
 #endif /* _LINUX_SCHED_MM_H */
-- 
GitLab


From 3605df49556ebb7641d1f8ec2e7eeecf4dd734bf Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 11:03:12 +0100
Subject: [PATCH 605/898] sched/headers: Move task statistics APIs from
 <linux/sched.h> to <linux/sched/stat.h>

There are a number of task statistics related variables and methods exported
via sched.h - collect them into <linux/sched/stat.h> and include it from
their usage sites.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/s390/appldata/appldata_base.c |  1 +
 include/linux/sched.h              | 10 ----------
 include/linux/sched/stat.h         | 18 ++++++++++++++++++
 3 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 5a8dfa22da7c..ef3fb1b9201f 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -12,6 +12,7 @@
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
 #include <linux/module.h>
+#include <linux/sched/stat.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dbc3ff04750a..415baf253517 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -46,16 +46,6 @@ struct nameidata;
 struct signal_struct;
 struct sighand_struct;
 
-extern unsigned long total_forks;
-extern int nr_threads;
-DECLARE_PER_CPU(unsigned long, process_counts);
-extern int nr_processes(void);
-extern unsigned long nr_running(void);
-extern bool single_task_running(void);
-extern unsigned long nr_iowait(void);
-extern unsigned long nr_iowait_cpu(int cpu);
-extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
-
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void cpu_load_update_nohz_start(void);
 extern void cpu_load_update_nohz_stop(void);
diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
index 30fe012aecb0..0d52ceb6d3ae 100644
--- a/include/linux/sched/stat.h
+++ b/include/linux/sched/stat.h
@@ -3,4 +3,22 @@
 
 #include <linux/sched.h>
 
+/*
+ * Various counters maintained by the scheduler and fork(),
+ * exposed via /proc, sys.c or used by drivers via these APIs.
+ *
+ * ( Note that all these values are aquired without locking,
+ *   so they can only be relied on in narrow circumstances. )
+ */
+
+extern unsigned long total_forks;
+extern int nr_threads;
+DECLARE_PER_CPU(unsigned long, process_counts);
+extern int nr_processes(void);
+extern unsigned long nr_running(void);
+extern bool single_task_running(void);
+extern unsigned long nr_iowait(void);
+extern unsigned long nr_iowait_cpu(int cpu);
+extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
+
 #endif /* _LINUX_SCHED_STAT_H */
-- 
GitLab


From 752b3ca734cbc17c0456b846ae886c0ed39c5703 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 11:12:59 +0100
Subject: [PATCH 606/898] sched/headers: Move the NOHZ APIs from
 <linux/sched.h> to <linux/sched/nohz.h>

There's a number of NOHZ/dyntics related functionality in <linux/sched.h>,
but only a handful of timer files are making use of them.

Move them into their own header. This better documents these APIs
and unclutters <linux/sched.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 35 ----------------------------------
 include/linux/sched/nohz.h | 39 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 35 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 415baf253517..5f9bfc603d19 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -46,14 +46,6 @@ struct nameidata;
 struct signal_struct;
 struct sighand_struct;
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void cpu_load_update_nohz_start(void);
-extern void cpu_load_update_nohz_stop(void);
-#else
-static inline void cpu_load_update_nohz_start(void) { }
-static inline void cpu_load_update_nohz_stop(void) { }
-#endif
-
 extern void dump_cpu_task(int cpu);
 
 struct seq_file;
@@ -204,15 +196,6 @@ extern cpumask_var_t cpu_isolated_map;
 
 extern int runqueue_is_locked(int cpu);
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void nohz_balance_enter_idle(int cpu);
-extern void set_cpu_sd_state_idle(void);
-extern int get_nohz_timer_target(void);
-#else
-static inline void nohz_balance_enter_idle(int cpu) { }
-static inline void set_cpu_sd_state_idle(void) { }
-#endif
-
 /*
  * Only dump TASK_* tasks. (0 for all tasks)
  */
@@ -1535,14 +1518,6 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 }
 #endif
 
-#ifdef CONFIG_NO_HZ_COMMON
-void calc_load_enter_idle(void);
-void calc_load_exit_idle(void);
-#else
-static inline void calc_load_enter_idle(void) { }
-static inline void calc_load_exit_idle(void) { }
-#endif /* CONFIG_NO_HZ_COMMON */
-
 #ifndef cpu_relax_yield
 #define cpu_relax_yield() cpu_relax()
 #endif
@@ -1563,16 +1538,6 @@ extern void idle_task_exit(void);
 static inline void idle_task_exit(void) {}
 #endif
 
-#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
-extern void wake_up_nohz_cpu(int cpu);
-#else
-static inline void wake_up_nohz_cpu(int cpu) { }
-#endif
-
-#ifdef CONFIG_NO_HZ_FULL
-extern u64 scheduler_tick_max_deferment(void);
-#endif
-
 extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index fe6caf0dab10..9471f0736a3a 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -3,4 +3,43 @@
 
 #include <linux/sched.h>
 
+/*
+ * This is the interface between the scheduler and nohz/dyntics:
+ */
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void cpu_load_update_nohz_start(void);
+extern void cpu_load_update_nohz_stop(void);
+#else
+static inline void cpu_load_update_nohz_start(void) { }
+static inline void cpu_load_update_nohz_stop(void) { }
+#endif
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void nohz_balance_enter_idle(int cpu);
+extern void set_cpu_sd_state_idle(void);
+extern int get_nohz_timer_target(void);
+#else
+static inline void nohz_balance_enter_idle(int cpu) { }
+static inline void set_cpu_sd_state_idle(void) { }
+#endif
+
+#ifdef CONFIG_NO_HZ_COMMON
+void calc_load_enter_idle(void);
+void calc_load_exit_idle(void);
+#else
+static inline void calc_load_enter_idle(void) { }
+static inline void calc_load_exit_idle(void) { }
+#endif /* CONFIG_NO_HZ_COMMON */
+
+#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
+extern void wake_up_nohz_cpu(int cpu);
+#else
+static inline void wake_up_nohz_cpu(int cpu) { }
+#endif
+
+#ifdef CONFIG_NO_HZ_FULL
+extern u64 scheduler_tick_max_deferment(void);
+#endif
+
 #endif /* _LINUX_SCHED_NOHZ_H */
-- 
GitLab


From d3d1e320d43a7bad9603acf0214406a1e8795c63 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 11:16:09 +0100
Subject: [PATCH 607/898] sched/headers: Move debugging functions from
 <linux/sched.h> to <linux/sched/debug.h>

Collect the various scheduler and task state debugging APIs scattered
around <linux/sched.h> into the new <linux/sched/debug.h> header.

In particular the show_regs() and show_stack() prototype affects many files,
update them.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h       | 36 -----------------------------
 include/linux/sched/debug.h | 46 +++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 36 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5f9bfc603d19..76a2e522be29 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -46,15 +46,9 @@ struct nameidata;
 struct signal_struct;
 struct sighand_struct;
 
-extern void dump_cpu_task(int cpu);
-
 struct seq_file;
 struct cfs_rq;
 struct task_group;
-#ifdef CONFIG_SCHED_DEBUG
-extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
-extern void proc_sched_set_task(struct task_struct *p);
-#endif
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -196,25 +190,6 @@ extern cpumask_var_t cpu_isolated_map;
 
 extern int runqueue_is_locked(int cpu);
 
-/*
- * Only dump TASK_* tasks. (0 for all tasks)
- */
-extern void show_state_filter(unsigned long state_filter);
-
-static inline void show_state(void)
-{
-	show_state_filter(0);
-}
-
-extern void show_regs(struct pt_regs *);
-
-/*
- * TASK is a pointer to the task whose backtrace we want to see (or NULL for current
- * task), SP is the stack pointer of the first frame that should be shown in the back
- * trace (or NULL if the entire call-chain of the task should be shown).
- */
-extern void show_stack(struct task_struct *task, unsigned long *sp);
-
 extern void cpu_init (void);
 extern void trap_init(void);
 extern void update_process_times(int user);
@@ -229,17 +204,6 @@ extern int sched_cpu_dying(unsigned int cpu);
 # define sched_cpu_dying	NULL
 #endif
 
-extern void sched_show_task(struct task_struct *p);
-
-/* Attach to any functions which should be ignored in wchan output. */
-#define __sched		__attribute__((__section__(".sched.text")))
-
-/* Linker adds these: start and end of __sched functions */
-extern char __sched_text_start[], __sched_text_end[];
-
-/* Is this address in the __sched functions? */
-extern int in_sched_functions(unsigned long addr);
-
 #define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
 extern signed long schedule_timeout(signed long timeout);
 extern signed long schedule_timeout_interruptible(signed long timeout);
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index 55bc0cd35fd5..853bbef0b47b 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -3,4 +3,50 @@
 
 #include <linux/sched.h>
 
+/*
+ * Various scheduler/task debugging interfaces:
+ */
+
+struct task_struct;
+
+extern void dump_cpu_task(int cpu);
+
+/*
+ * Only dump TASK_* tasks. (0 for all tasks)
+ */
+extern void show_state_filter(unsigned long state_filter);
+
+static inline void show_state(void)
+{
+	show_state_filter(0);
+}
+
+struct pt_regs;
+
+extern void show_regs(struct pt_regs *);
+
+/*
+ * TASK is a pointer to the task whose backtrace we want to see (or NULL for current
+ * task), SP is the stack pointer of the first frame that should be shown in the back
+ * trace (or NULL if the entire call-chain of the task should be shown).
+ */
+extern void show_stack(struct task_struct *task, unsigned long *sp);
+
+extern void sched_show_task(struct task_struct *p);
+
+#ifdef CONFIG_SCHED_DEBUG
+struct seq_file;
+extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
+extern void proc_sched_set_task(struct task_struct *p);
+#endif
+
+/* Attach to any functions which should be ignored in wchan output. */
+#define __sched		__attribute__((__section__(".sched.text")))
+
+/* Linker adds these: start and end of __sched functions */
+extern char __sched_text_start[], __sched_text_end[];
+
+/* Is this address in the __sched functions? */
+extern int in_sched_functions(unsigned long addr);
+
 #endif /* _LINUX_SCHED_DEBUG_H */
-- 
GitLab


From 63cc9d6fca8c220c2406f1376100a9acb55197af Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 12:04:39 +0100
Subject: [PATCH 608/898] sched/headers, time/timekeeping: Move the
 xtime_update() prototype from <linux/sched.h> to <linux/time.h>

This was in <linux/sched.h> only for hysterical raisins.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 2 --
 include/linux/time.h  | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 76a2e522be29..5a4fbc76feb4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1579,8 +1579,6 @@ extern struct task_struct *find_task_by_pid_ns(pid_t nr,
 
 #include <asm/current.h>
 
-extern void xtime_update(unsigned long ticks);
-
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
diff --git a/include/linux/time.h b/include/linux/time.h
index 23f0f5ce3090..4f4ab65b6e61 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -167,6 +167,8 @@ static inline bool timespec_inject_offset_valid(const struct timespec *ts)
 extern u32 (*arch_gettimeoffset)(void);
 #endif
 
+extern void xtime_update(unsigned long ticks);
+
 struct itimerval;
 extern int do_setitimer(int which, struct itimerval *value,
 			struct itimerval *ovalue);
-- 
GitLab


From 70b8157e61d0143fb44ae9482557d7aca365da3d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 12:11:00 +0100
Subject: [PATCH 609/898] sched/headers: Move <asm/current.h> include from the
 middle of <linux/sched.h> to the header portion

Linux-0.01 already defined 'current' in the middle of sched.h, so this
is an ancient historical precedent - but still in a modern kernel it
looks a bit weird that we have:

	#include <asm/current.h>

in the middle of the header.

Move it further up. If this was done for some obscure dependency
reasons then we'll trigger and document it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5a4fbc76feb4..ac0fed4c3130 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -31,6 +31,8 @@
 #include <linux/magic.h>
 #include <linux/cgroup-defs.h>
 
+#include <asm/current.h>
+
 struct sched_attr;
 struct sched_param;
 
@@ -1577,8 +1579,6 @@ extern struct task_struct *find_task_by_vpid(pid_t nr);
 extern struct task_struct *find_task_by_pid_ns(pid_t nr,
 		struct pid_namespace *ns);
 
-#include <asm/current.h>
-
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
-- 
GitLab


From 0ca0156973a47e689f3bc817e26e15fff3f84eec Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 14:52:01 +0100
Subject: [PATCH 610/898] sched/headers: Split hotplug CPU interfaces out of
 <linux/sched.h> into <linux/sched/hotplug.h>

Split the CPU hotplug scheduler APIs out of the common header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h         | 15 ---------------
 include/linux/sched/hotplug.h | 20 ++++++++++++++++++++
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ac0fed4c3130..25cc0adb3e08 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -196,15 +196,6 @@ extern void cpu_init (void);
 extern void trap_init(void);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
-extern int sched_cpu_starting(unsigned int cpu);
-extern int sched_cpu_activate(unsigned int cpu);
-extern int sched_cpu_deactivate(unsigned int cpu);
-
-#ifdef CONFIG_HOTPLUG_CPU
-extern int sched_cpu_dying(unsigned int cpu);
-#else
-# define sched_cpu_dying	NULL
-#endif
 
 #define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
 extern signed long schedule_timeout(signed long timeout);
@@ -1498,12 +1489,6 @@ extern void sched_exec(void);
 #define sched_exec()   {}
 #endif
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern void idle_task_exit(void);
-#else
-static inline void idle_task_exit(void) {}
-#endif
-
 extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
index 34670ed24894..c608d3c1ddb8 100644
--- a/include/linux/sched/hotplug.h
+++ b/include/linux/sched/hotplug.h
@@ -3,4 +3,24 @@
 
 #include <linux/sched.h>
 
+/*
+ * Scheduler interfaces for hotplug CPU support:
+ */
+
+extern int sched_cpu_starting(unsigned int cpu);
+extern int sched_cpu_activate(unsigned int cpu);
+extern int sched_cpu_deactivate(unsigned int cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern int sched_cpu_dying(unsigned int cpu);
+#else
+# define sched_cpu_dying	NULL
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern void idle_task_exit(void);
+#else
+static inline void idle_task_exit(void) {}
+#endif
+
 #endif /* _LINUX_SCHED_HOTPLUG_H */
-- 
GitLab


From 901b14bd946a8b7ea211105b6207e082ddd36846 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 15:24:12 +0100
Subject: [PATCH 611/898] sched/headers: Move task lifetime APIs from
 <linux/sched.h> to <linux/sched/task.h>

There's a fair amount of task lifetime management (a.k.a fork()/exit())
related APIs in <linux/sched.h>, but only a small fraction of
the users of the generic sched.h header make use of them.

Move these functions to the <linux/sched/task.h> header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 91 -----------------------------------
 include/linux/sched/task.h | 97 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+), 91 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 25cc0adb3e08..b1677c8db03f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -165,28 +165,10 @@ struct task_group;
 /* Task command name length */
 #define TASK_COMM_LEN 16
 
-#include <linux/spinlock.h>
-
-/*
- * This serializes "schedule()" and also protects
- * the run-queue from deletions/modifications (but
- * _adding_ to the beginning of the run-queue has
- * a separate lock).
- */
-extern rwlock_t tasklist_lock;
-extern spinlock_t mmlist_lock;
-
 struct task_struct;
 
-#ifdef CONFIG_PROVE_RCU
-extern int lockdep_tasklist_lock_is_held(void);
-#endif /* #ifdef CONFIG_PROVE_RCU */
-
 extern void sched_init(void);
 extern void sched_init_smp(void);
-extern asmlinkage void schedule_tail(struct task_struct *prev);
-extern void init_idle(struct task_struct *idle, int cpu);
-extern void init_idle_bootup_task(struct task_struct *idle);
 
 extern cpumask_var_t cpu_isolated_map;
 
@@ -211,8 +193,6 @@ extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
 
-void __noreturn do_task_dead(void);
-
 struct nsproxy;
 
 /**
@@ -1120,24 +1100,6 @@ struct task_struct {
  */
 };
 
-#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
-extern int arch_task_struct_size __read_mostly;
-#else
-# define arch_task_struct_size (sizeof(struct task_struct))
-#endif
-
-#ifdef CONFIG_VMAP_STACK
-static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
-{
-	return t->stack_vm_area;
-}
-#else
-static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
-{
-	return NULL;
-}
-#endif
-
 static inline struct pid *task_pid(struct task_struct *task)
 {
 	return task->pids[PIDTYPE_PID].pid;
@@ -1429,21 +1391,6 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 TASK_PFA_TEST(LMK_WAITING, lmk_waiting)
 TASK_PFA_SET(LMK_WAITING, lmk_waiting)
 
-static inline void rcu_copy_process(struct task_struct *p)
-{
-#ifdef CONFIG_PREEMPT_RCU
-	p->rcu_read_lock_nesting = 0;
-	p->rcu_read_unlock_special.s = 0;
-	p->rcu_blocked_node = NULL;
-	INIT_LIST_HEAD(&p->rcu_node_entry);
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_TASKS_RCU
-	p->rcu_tasks_holdout = false;
-	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
-	p->rcu_tasks_idle_cpu = -1;
-#endif /* #ifdef CONFIG_TASKS_RCU */
-}
-
 static inline void tsk_restore_flags(struct task_struct *task,
 				unsigned long orig_flags, unsigned long flags)
 {
@@ -1572,45 +1519,11 @@ extern void wake_up_new_task(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
-extern void sched_dead(struct task_struct *p);
-
-extern void proc_caches_init(void);
-
-extern void release_task(struct task_struct * p);
-
-#ifdef CONFIG_HAVE_COPY_THREAD_TLS
-extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
-			struct task_struct *, unsigned long);
-#else
-extern int copy_thread(unsigned long, unsigned long, unsigned long,
-			struct task_struct *);
-
-/* Architectures that haven't opted into copy_thread_tls get the tls argument
- * via pt_regs, so ignore the tls argument passed via C. */
-static inline int copy_thread_tls(
-		unsigned long clone_flags, unsigned long sp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
-{
-	return copy_thread(clone_flags, sp, arg, p);
-}
-#endif
-extern void flush_thread(void);
-
-#ifdef CONFIG_HAVE_EXIT_THREAD
-extern void exit_thread(struct task_struct *tsk);
-#else
-static inline void exit_thread(struct task_struct *tsk)
-{
-}
-#endif
 
 extern void exit_files(struct task_struct *);
 
 extern void exit_itimers(struct signal_struct *);
 
-extern void do_group_exit(int);
-
 extern int do_execve(struct filename *,
 		     const char __user * const __user *,
 		     const char __user * const __user *);
@@ -1618,10 +1531,6 @@ extern int do_execveat(int, struct filename *,
 		       const char __user * const __user *,
 		       const char __user * const __user *,
 		       int);
-extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
-extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
-struct task_struct *fork_idle(int);
-extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
 extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
 static inline void set_task_comm(struct task_struct *tsk, const char *from)
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 0023c91ff821..e93638a03515 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -1,6 +1,103 @@
 #ifndef _LINUX_SCHED_TASK_H
 #define _LINUX_SCHED_TASK_H
 
+/*
+ * Interface between the scheduler and various task lifetime (fork()/exit())
+ * functionality:
+ */
+
 #include <linux/sched.h>
 
+/*
+ * This serializes "schedule()" and also protects
+ * the run-queue from deletions/modifications (but
+ * _adding_ to the beginning of the run-queue has
+ * a separate lock).
+ */
+extern rwlock_t tasklist_lock;
+extern spinlock_t mmlist_lock;
+
+#ifdef CONFIG_PROVE_RCU
+extern int lockdep_tasklist_lock_is_held(void);
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
+extern asmlinkage void schedule_tail(struct task_struct *prev);
+extern void init_idle(struct task_struct *idle, int cpu);
+extern void init_idle_bootup_task(struct task_struct *idle);
+
+static inline void rcu_copy_process(struct task_struct *p)
+{
+#ifdef CONFIG_PREEMPT_RCU
+	p->rcu_read_lock_nesting = 0;
+	p->rcu_read_unlock_special.s = 0;
+	p->rcu_blocked_node = NULL;
+	INIT_LIST_HEAD(&p->rcu_node_entry);
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	p->rcu_tasks_holdout = false;
+	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
+	p->rcu_tasks_idle_cpu = -1;
+#endif /* #ifdef CONFIG_TASKS_RCU */
+}
+
+extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
+extern void sched_dead(struct task_struct *p);
+
+void __noreturn do_task_dead(void);
+
+extern void proc_caches_init(void);
+
+extern void release_task(struct task_struct * p);
+
+#ifdef CONFIG_HAVE_COPY_THREAD_TLS
+extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
+			struct task_struct *, unsigned long);
+#else
+extern int copy_thread(unsigned long, unsigned long, unsigned long,
+			struct task_struct *);
+
+/* Architectures that haven't opted into copy_thread_tls get the tls argument
+ * via pt_regs, so ignore the tls argument passed via C. */
+static inline int copy_thread_tls(
+		unsigned long clone_flags, unsigned long sp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
+{
+	return copy_thread(clone_flags, sp, arg, p);
+}
+#endif
+extern void flush_thread(void);
+
+#ifdef CONFIG_HAVE_EXIT_THREAD
+extern void exit_thread(struct task_struct *tsk);
+#else
+static inline void exit_thread(struct task_struct *tsk)
+{
+}
+#endif
+extern void do_group_exit(int);
+
+extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
+extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
+struct task_struct *fork_idle(int);
+extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
+
+
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+extern int arch_task_struct_size __read_mostly;
+#else
+# define arch_task_struct_size (sizeof(struct task_struct))
+#endif
+
+#ifdef CONFIG_VMAP_STACK
+static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
+{
+	return t->stack_vm_area;
+}
+#else
+static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
+{
+	return NULL;
+}
+#endif
+
 #endif /* _LINUX_SCHED_TASK_H */
-- 
GitLab


From 6bfbaa51ed47774492d83d182a86068cc35aa4c6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 21:37:49 +0100
Subject: [PATCH 612/898] sched/headers, RCU: Move rcu_copy_process() from
 <linux/sched/task.h> to kernel/fork.c

Move rcu_copy_process() into kernel/fork.c, which is the only
user of this inline function.

This simplifies <linux/sched/task.h> to the level that <linux/sched.h>
does not have to be included in it anymore - which change is done
in a subsequent patch.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/task.h | 15 ---------------
 kernel/fork.c              | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index e93638a03515..20ed9108f261 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -25,21 +25,6 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 extern void init_idle_bootup_task(struct task_struct *idle);
 
-static inline void rcu_copy_process(struct task_struct *p)
-{
-#ifdef CONFIG_PREEMPT_RCU
-	p->rcu_read_lock_nesting = 0;
-	p->rcu_read_unlock_special.s = 0;
-	p->rcu_blocked_node = NULL;
-	INIT_LIST_HEAD(&p->rcu_node_entry);
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_TASKS_RCU
-	p->rcu_tasks_holdout = false;
-	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
-	p->rcu_tasks_idle_cpu = -1;
-#endif /* #ifdef CONFIG_TASKS_RCU */
-}
-
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 916e78004b8f..6c463c80e93d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1465,6 +1465,21 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
 	 task->pids[type].pid = pid;
 }
 
+static inline void rcu_copy_process(struct task_struct *p)
+{
+#ifdef CONFIG_PREEMPT_RCU
+	p->rcu_read_lock_nesting = 0;
+	p->rcu_read_unlock_special.s = 0;
+	p->rcu_blocked_node = NULL;
+	INIT_LIST_HEAD(&p->rcu_node_entry);
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	p->rcu_tasks_holdout = false;
+	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
+	p->rcu_tasks_idle_cpu = -1;
+#endif /* #ifdef CONFIG_TASKS_RCU */
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
-- 
GitLab


From c7af7877eeacfeaaf6a1b6f54c481292ef116837 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 22:01:58 +0100
Subject: [PATCH 613/898] sched/core: Move, sort and clean up <linux/sched.h>
 structure predeclarations

Most of the structure predeclarations were at the head of sched.h, but not
all of them - there were a number of lines spread around sched.h, in
random places.

Move them to the head, and also sort them alphabetically.

Remove unused entries.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 56 ++++++++++++++++++-------------------------
 1 file changed, 23 insertions(+), 33 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b1677c8db03f..5398356e33c7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -33,24 +33,35 @@
 
 #include <asm/current.h>
 
-struct sched_attr;
-struct sched_param;
-
-struct futex_pi_state;
-struct robust_list_head;
+/* task_struct member predeclarations: */
+struct audit_context;
+struct autogroup;
+struct backing_dev_info;
 struct bio_list;
-struct fs_struct;
-struct perf_event_context;
 struct blk_plug;
+struct cfs_rq;
 struct filename;
+struct fs_struct;
+struct futex_pi_state;
+struct io_context;
+struct mempolicy;
 struct nameidata;
-
-struct signal_struct;
-struct sighand_struct;
-
+struct nsproxy;
+struct perf_event_context;
+struct pid_namespace;
+struct pipe_inode_info;
+struct rcu_node;
+struct reclaim_state;
+struct robust_list_head;
+struct sched_attr;
+struct sched_param;
 struct seq_file;
-struct cfs_rq;
+struct sighand_struct;
+struct signal_struct;
+struct task_delay_info;
 struct task_group;
+struct task_struct;
+struct uts_namespace;
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -165,8 +176,6 @@ struct task_group;
 /* Task command name length */
 #define TASK_COMM_LEN 16
 
-struct task_struct;
-
 extern void sched_init(void);
 extern void sched_init_smp(void);
 
@@ -193,8 +202,6 @@ extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
 
-struct nsproxy;
-
 /**
  * struct prev_cputime - snaphsot of system and user cputime
  * @utime: time spent in user mode
@@ -297,10 +304,6 @@ struct thread_group_cputimer {
 };
 
 #include <linux/rwsem.h>
-struct autogroup;
-
-struct backing_dev_info;
-struct reclaim_state;
 
 #ifdef CONFIG_SCHED_INFO
 struct sched_info {
@@ -314,8 +317,6 @@ struct sched_info {
 };
 #endif /* CONFIG_SCHED_INFO */
 
-struct task_delay_info;
-
 static inline int sched_info_on(void)
 {
 #ifdef CONFIG_SCHEDSTATS
@@ -342,20 +343,12 @@ void force_schedstat_enabled(void);
 # define SCHED_FIXEDPOINT_SHIFT	10
 # define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)
 
-struct io_context;			/* See blkdev.h */
-
-
 #ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
 extern void prefetch_stack(struct task_struct *t);
 #else
 static inline void prefetch_stack(struct task_struct *t) { }
 #endif
 
-struct audit_context;		/* See audit.c */
-struct mempolicy;
-struct pipe_inode_info;
-struct uts_namespace;
-
 struct load_weight {
 	unsigned long weight;
 	u32 inv_weight;
@@ -564,7 +557,6 @@ union rcu_special {
 	} b; /* Bits. */
 	u32 s; /* Set of bits. */
 };
-struct rcu_node;
 
 enum perf_event_task_context {
 	perf_invalid_context = -1,
@@ -1125,8 +1117,6 @@ static inline struct pid *task_session(struct task_struct *task)
 	return task->group_leader->pids[PIDTYPE_SID].pid;
 }
 
-struct pid_namespace;
-
 /*
  * the helpers to get the task's different pids as they are seen
  * from various namespaces
-- 
GitLab


From d04b0ad37e4b6ac39a56c823ae76ab37cd044dc7 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 22:07:57 +0100
Subject: [PATCH 614/898] sched/headers: Move the PREEMPT_COUNT defines from
 <linux/sched.h> to <linux/preempt.h>

These defines are not really part of the scheduler's driver API, but are
related to the preempt count - so move them to <linux/preempt.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/preempt.h | 21 +++++++++++++++++++++
 include/linux/sched.h   | 21 ---------------------
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 7eeceac52dea..cae461224948 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -55,6 +55,27 @@
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
+#define PREEMPT_DISABLED	(PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
+
+/*
+ * Disable preemption until the scheduler is running -- use an unconditional
+ * value so that it also works on !PREEMPT_COUNT kernels.
+ *
+ * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
+ */
+#define INIT_PREEMPT_COUNT	PREEMPT_OFFSET
+
+/*
+ * Initial preempt_count value; reflects the preempt_count schedule invariant
+ * which states that during context switches:
+ *
+ *    preempt_count() == 2*PREEMPT_DISABLE_OFFSET
+ *
+ * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
+ * Note: See finish_task_switch().
+ */
+#define FORK_PREEMPT_COUNT	(2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
+
 /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
 #include <asm/preempt.h>
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5398356e33c7..3b3e31da416e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -265,27 +265,6 @@ struct task_cputime_atomic {
 		.sum_exec_runtime = ATOMIC64_INIT(0),		\
 	}
 
-#define PREEMPT_DISABLED	(PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
-
-/*
- * Disable preemption until the scheduler is running -- use an unconditional
- * value so that it also works on !PREEMPT_COUNT kernels.
- *
- * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
- */
-#define INIT_PREEMPT_COUNT	PREEMPT_OFFSET
-
-/*
- * Initial preempt_count value; reflects the preempt_count schedule invariant
- * which states that during context switches:
- *
- *    preempt_count() == 2*PREEMPT_DISABLE_OFFSET
- *
- * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
- * Note: See finish_task_switch().
- */
-#define FORK_PREEMPT_COUNT	(2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
-
 /**
  * struct thread_group_cputimer - thread group interval timer counts
  * @cputime_atomic:	atomic thread group interval timers.
-- 
GitLab


From f3ac60671954c8d413532627b1be13a76f394c49 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 22:59:33 +0100
Subject: [PATCH 615/898] sched/headers: Move task-stack related APIs from
 <linux/sched.h> to <linux/sched/task_stack.h>

Split out the task->stack related functionality, which is not really
part of the core scheduler APIs.

Only keep task_thread_info() because it's used by sched.h.

Update the code that uses those facilities.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/kernel/smp-cps.c       |   2 +-
 arch/mips/sibyte/sb1250/smp.c    |   2 +-
 include/linux/sched.h            | 115 +++----------------------------
 include/linux/sched/task_stack.h | 104 ++++++++++++++++++++++++++++
 4 files changed, 115 insertions(+), 108 deletions(-)

diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 1d3188c23bb8..6d45f05538c8 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -11,7 +11,7 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/irqchip/mips-gic.h>
-#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/sched/hotplug.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index 1cf66f5ff23d..0a4a2c3982d8 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -21,7 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
-#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3b3e31da416e..af9590c8bfb0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1450,6 +1450,15 @@ union thread_union {
 	unsigned long stack[THREAD_SIZE/sizeof(long)];
 };
 
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+static inline struct thread_info *task_thread_info(struct task_struct *task)
+{
+	return &task->thread_info;
+}
+#elif !defined(__HAVE_THREAD_FUNCTIONS)
+# define task_thread_info(task)	((struct thread_info *)(task)->stack)
+#endif
+
 #ifndef __HAVE_ARCH_KSTACK_END
 static inline int kstack_end(void *addr)
 {
@@ -1540,112 +1549,6 @@ static inline void task_unlock(struct task_struct *p)
 	spin_unlock(&p->alloc_lock);
 }
 
-#ifdef CONFIG_THREAD_INFO_IN_TASK
-
-static inline struct thread_info *task_thread_info(struct task_struct *task)
-{
-	return &task->thread_info;
-}
-
-/*
- * When accessing the stack of a non-current task that might exit, use
- * try_get_task_stack() instead.  task_stack_page will return a pointer
- * that could get freed out from under you.
- */
-static inline void *task_stack_page(const struct task_struct *task)
-{
-	return task->stack;
-}
-
-#define setup_thread_stack(new,old)	do { } while(0)
-
-static inline unsigned long *end_of_stack(const struct task_struct *task)
-{
-	return task->stack;
-}
-
-#elif !defined(__HAVE_THREAD_FUNCTIONS)
-
-#define task_thread_info(task)	((struct thread_info *)(task)->stack)
-#define task_stack_page(task)	((void *)(task)->stack)
-
-static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
-{
-	*task_thread_info(p) = *task_thread_info(org);
-	task_thread_info(p)->task = p;
-}
-
-/*
- * Return the address of the last usable long on the stack.
- *
- * When the stack grows down, this is just above the thread
- * info struct. Going any lower will corrupt the threadinfo.
- *
- * When the stack grows up, this is the highest address.
- * Beyond that position, we corrupt data on the next page.
- */
-static inline unsigned long *end_of_stack(struct task_struct *p)
-{
-#ifdef CONFIG_STACK_GROWSUP
-	return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1;
-#else
-	return (unsigned long *)(task_thread_info(p) + 1);
-#endif
-}
-
-#endif
-
-#ifdef CONFIG_THREAD_INFO_IN_TASK
-static inline void *try_get_task_stack(struct task_struct *tsk)
-{
-	return atomic_inc_not_zero(&tsk->stack_refcount) ?
-		task_stack_page(tsk) : NULL;
-}
-
-extern void put_task_stack(struct task_struct *tsk);
-#else
-static inline void *try_get_task_stack(struct task_struct *tsk)
-{
-	return task_stack_page(tsk);
-}
-
-static inline void put_task_stack(struct task_struct *tsk) {}
-#endif
-
-#define task_stack_end_corrupted(task) \
-		(*(end_of_stack(task)) != STACK_END_MAGIC)
-
-static inline int object_is_on_stack(void *obj)
-{
-	void *stack = task_stack_page(current);
-
-	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
-}
-
-extern void thread_stack_cache_init(void);
-
-#ifdef CONFIG_DEBUG_STACK_USAGE
-static inline unsigned long stack_not_used(struct task_struct *p)
-{
-	unsigned long *n = end_of_stack(p);
-
-	do { 	/* Skip over canary */
-# ifdef CONFIG_STACK_GROWSUP
-		n--;
-# else
-		n++;
-# endif
-	} while (!*n);
-
-# ifdef CONFIG_STACK_GROWSUP
-	return (unsigned long)end_of_stack(p) - (unsigned long)n;
-# else
-	return (unsigned long)n - (unsigned long)end_of_stack(p);
-# endif
-}
-#endif
-extern void set_task_stack_end_magic(struct task_struct *tsk);
-
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index d2d578e85f7d..aaa5c2a6a0e9 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -1,7 +1,111 @@
 #ifndef _LINUX_SCHED_TASK_STACK_H
 #define _LINUX_SCHED_TASK_STACK_H
 
+/*
+ * task->stack (kernel stack) handling interfaces:
+ */
+
 #include <linux/sched.h>
 #include <linux/magic.h>
 
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+
+/*
+ * When accessing the stack of a non-current task that might exit, use
+ * try_get_task_stack() instead.  task_stack_page will return a pointer
+ * that could get freed out from under you.
+ */
+static inline void *task_stack_page(const struct task_struct *task)
+{
+	return task->stack;
+}
+
+#define setup_thread_stack(new,old)	do { } while(0)
+
+static inline unsigned long *end_of_stack(const struct task_struct *task)
+{
+	return task->stack;
+}
+
+#elif !defined(__HAVE_THREAD_FUNCTIONS)
+
+#define task_stack_page(task)	((void *)(task)->stack)
+
+static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
+{
+	*task_thread_info(p) = *task_thread_info(org);
+	task_thread_info(p)->task = p;
+}
+
+/*
+ * Return the address of the last usable long on the stack.
+ *
+ * When the stack grows down, this is just above the thread
+ * info struct. Going any lower will corrupt the threadinfo.
+ *
+ * When the stack grows up, this is the highest address.
+ * Beyond that position, we corrupt data on the next page.
+ */
+static inline unsigned long *end_of_stack(struct task_struct *p)
+{
+#ifdef CONFIG_STACK_GROWSUP
+	return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1;
+#else
+	return (unsigned long *)(task_thread_info(p) + 1);
+#endif
+}
+
+#endif
+
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+static inline void *try_get_task_stack(struct task_struct *tsk)
+{
+	return atomic_inc_not_zero(&tsk->stack_refcount) ?
+		task_stack_page(tsk) : NULL;
+}
+
+extern void put_task_stack(struct task_struct *tsk);
+#else
+static inline void *try_get_task_stack(struct task_struct *tsk)
+{
+	return task_stack_page(tsk);
+}
+
+static inline void put_task_stack(struct task_struct *tsk) {}
+#endif
+
+#define task_stack_end_corrupted(task) \
+		(*(end_of_stack(task)) != STACK_END_MAGIC)
+
+static inline int object_is_on_stack(void *obj)
+{
+	void *stack = task_stack_page(current);
+
+	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
+}
+
+extern void thread_stack_cache_init(void);
+
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+	unsigned long *n = end_of_stack(p);
+
+	do { 	/* Skip over canary */
+# ifdef CONFIG_STACK_GROWSUP
+		n--;
+# else
+		n++;
+# endif
+	} while (!*n);
+
+# ifdef CONFIG_STACK_GROWSUP
+	return (unsigned long)end_of_stack(p) - (unsigned long)n;
+# else
+	return (unsigned long)n - (unsigned long)end_of_stack(p);
+# endif
+}
+#endif
+extern void set_task_stack_end_magic(struct task_struct *tsk);
+
 #endif /* _LINUX_SCHED_TASK_STACK_H */
-- 
GitLab


From 70806b21e4d64f01193a2b64a053b75ff53a2b10 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 23:15:21 +0100
Subject: [PATCH 616/898] sched/headers: Move the 'root_task_group' declaration
 to <linux/sched/autogroup.h>

Also remove the duplicate declaration from <linux/init_task.h>.

( That declaration was originally duplicated for dependency hell reasons,
  but there's no problem including the much smaller <linux/sched/autogroup.h>
  header now, to pick up the right prototype. )

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/init_task.h       | 2 --
 include/linux/sched.h           | 4 ----
 include/linux/sched/autogroup.h | 5 +++++
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f6841c19c913..91d9049f0039 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -151,8 +151,6 @@ extern struct group_info init_groups;
 
 extern struct cred init_cred;
 
-extern struct task_group root_task_group;
-
 #ifdef CONFIG_CGROUP_SCHED
 # define INIT_CGROUP_SCHED(tsk)						\
 	.sched_task_group = &root_task_group,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index af9590c8bfb0..4934733bd6cb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1707,10 +1707,6 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
-#ifdef CONFIG_CGROUP_SCHED
-extern struct task_group root_task_group;
-#endif /* CONFIG_CGROUP_SCHED */
-
 extern int task_can_switch_user(struct user_struct *up,
 					struct task_struct *tsk);
 
diff --git a/include/linux/sched/autogroup.h b/include/linux/sched/autogroup.h
index 586bdf37330d..fd6855548d0c 100644
--- a/include/linux/sched/autogroup.h
+++ b/include/linux/sched/autogroup.h
@@ -4,6 +4,7 @@
 #include <linux/sched.h>
 
 struct signal_struct;
+struct task_group;
 struct seq_file;
 
 #ifdef CONFIG_SCHED_AUTOGROUP
@@ -24,4 +25,8 @@ static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 static inline void sched_autogroup_exit_task(struct task_struct *p) { }
 #endif
 
+#ifdef CONFIG_CGROUP_SCHED
+extern struct task_group root_task_group;
+#endif /* CONFIG_CGROUP_SCHED */
+
 #endif /* _LINUX_SCHED_AUTOGROUP_H */
-- 
GitLab


From 76960dbf9b235b957d9d730be2c6c2a70f709026 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 23:43:50 +0100
Subject: [PATCH 617/898] signals: Move signal data types from <linux/signal.h>
 to <linux/signal_types.h>

Separate out just the pure data types - sched.h will be able to use
this reduced size header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/signal.h       | 54 ---------------------------------
 include/linux/signal_types.h | 59 ++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+), 54 deletions(-)

diff --git a/include/linux/signal.h b/include/linux/signal.h
index d1c2b05a7a55..94ad6eea9550 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -8,24 +8,6 @@ struct task_struct;
 
 /* for sysctl */
 extern int print_fatal_signals;
-/*
- * Real Time signals may be queued.
- */
-
-struct sigqueue {
-	struct list_head list;
-	int flags;
-	siginfo_t info;
-	struct user_struct *user;
-};
-
-/* flags values. */
-#define SIGQUEUE_PREALLOC	1
-
-struct sigpending {
-	struct list_head list;
-	sigset_t signal;
-};
 
 #ifndef HAVE_ARCH_COPY_SIGINFO
 
@@ -271,42 +253,6 @@ extern void set_current_blocked(sigset_t *);
 extern void __set_current_blocked(const sigset_t *);
 extern int show_unhandled_signals;
 
-struct sigaction {
-#ifndef __ARCH_HAS_IRIX_SIGACTION
-	__sighandler_t	sa_handler;
-	unsigned long	sa_flags;
-#else
-	unsigned int	sa_flags;
-	__sighandler_t	sa_handler;
-#endif
-#ifdef __ARCH_HAS_SA_RESTORER
-	__sigrestore_t sa_restorer;
-#endif
-	sigset_t	sa_mask;	/* mask last for extensibility */
-};
-
-struct k_sigaction {
-	struct sigaction sa;
-#ifdef __ARCH_HAS_KA_RESTORER
-	__sigrestore_t ka_restorer;
-#endif
-};
- 
-#ifdef CONFIG_OLD_SIGACTION
-struct old_sigaction {
-	__sighandler_t sa_handler;
-	old_sigset_t sa_mask;
-	unsigned long sa_flags;
-	__sigrestore_t sa_restorer;
-};
-#endif
-
-struct ksignal {
-	struct k_sigaction ka;
-	siginfo_t info;
-	int sig;
-};
-
 extern int get_signal(struct ksignal *ksig);
 extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping);
 extern void exit_signals(struct task_struct *tsk);
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index 28799c88f490..16d862a3d8f3 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -1,7 +1,66 @@
 #ifndef _LINUX_SIGNAL_TYPES_H
 #define _LINUX_SIGNAL_TYPES_H
 
+/*
+ * Basic signal handling related data type definitions:
+ */
+
 #include <linux/list.h>
 #include <uapi/linux/signal.h>
 
+/*
+ * Real Time signals may be queued.
+ */
+
+struct sigqueue {
+	struct list_head list;
+	int flags;
+	siginfo_t info;
+	struct user_struct *user;
+};
+
+/* flags values. */
+#define SIGQUEUE_PREALLOC	1
+
+struct sigpending {
+	struct list_head list;
+	sigset_t signal;
+};
+
+struct sigaction {
+#ifndef __ARCH_HAS_IRIX_SIGACTION
+	__sighandler_t	sa_handler;
+	unsigned long	sa_flags;
+#else
+	unsigned int	sa_flags;
+	__sighandler_t	sa_handler;
+#endif
+#ifdef __ARCH_HAS_SA_RESTORER
+	__sigrestore_t sa_restorer;
+#endif
+	sigset_t	sa_mask;	/* mask last for extensibility */
+};
+
+struct k_sigaction {
+	struct sigaction sa;
+#ifdef __ARCH_HAS_KA_RESTORER
+	__sigrestore_t ka_restorer;
+#endif
+};
+
+#ifdef CONFIG_OLD_SIGACTION
+struct old_sigaction {
+	__sighandler_t sa_handler;
+	old_sigset_t sa_mask;
+	unsigned long sa_flags;
+	__sigrestore_t sa_restorer;
+};
+#endif
+
+struct ksignal {
+	struct k_sigaction ka;
+	siginfo_t info;
+	int sig;
+};
+
 #endif /* _LINUX_SIGNAL_TYPES_H */
-- 
GitLab


From 9e7d2e44dd88ba7e29c165b6fca428e384afa5a8 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 00:12:19 +0100
Subject: [PATCH 618/898] mm/headers, sched/headers: Move task related MM types
 from <linux/mm_types.> to <linux/mm_types_task.h>

Separate all the MM types that are embedded directly in 'struct task_struct'
into the <linux/mm_types_task.h> header.

The goal is to include this header in <linux/sched.h>, not the full <linux/mm_types.h>
header, to reduce the size, complexity and coupling of <linux/sched.h>.

(This patch does not change <linux/sched.h> yet.)

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm_types.h      | 49 -------------------------------
 include/linux/mm_types_task.h | 55 +++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+), 49 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 28bc710d3467..f60f45fe226f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -24,11 +24,6 @@
 struct address_space;
 struct mem_cgroup;
 
-#define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
-#define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
-		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
-#define ALLOC_SPLIT_PTLOCKS	(SPINLOCK_SIZE > BITS_PER_LONG/8)
-
 /*
  * Each physical page in the system has a struct page associated with
  * it to keep track of whatever it is we are using the page for at the
@@ -231,17 +226,6 @@ struct page {
 #endif
 ;
 
-struct page_frag {
-	struct page *page;
-#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
-	__u32 offset;
-	__u32 size;
-#else
-	__u16 offset;
-	__u16 size;
-#endif
-};
-
 #define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
 #define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
 
@@ -360,18 +344,6 @@ struct vm_area_struct {
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 };
 
-/*
- * The per task VMA cache array:
- */
-#define VMACACHE_BITS 2
-#define VMACACHE_SIZE (1U << VMACACHE_BITS)
-#define VMACACHE_MASK (VMACACHE_SIZE - 1)
-
-struct vmacache {
-	u32 seqnum;
-	struct vm_area_struct *vmas[VMACACHE_SIZE];
-};
-
 struct core_thread {
 	struct task_struct *task;
 	struct core_thread *next;
@@ -383,27 +355,6 @@ struct core_state {
 	struct completion startup;
 };
 
-enum {
-	MM_FILEPAGES,	/* Resident file mapping pages */
-	MM_ANONPAGES,	/* Resident anonymous pages */
-	MM_SWAPENTS,	/* Anonymous swap entries */
-	MM_SHMEMPAGES,	/* Resident shared memory pages */
-	NR_MM_COUNTERS
-};
-
-#if USE_SPLIT_PTE_PTLOCKS && defined(CONFIG_MMU)
-#define SPLIT_RSS_COUNTING
-/* per-thread cached information, */
-struct task_rss_stat {
-	int events;	/* for synchronization threshold */
-	int count[NR_MM_COUNTERS];
-};
-#endif /* USE_SPLIT_PTE_PTLOCKS */
-
-struct mm_rss_stat {
-	atomic_long_t count[NR_MM_COUNTERS];
-};
-
 struct kioctx_table;
 struct mm_struct {
 	struct vm_area_struct *mmap;		/* list of VMAs */
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index 2419d302f03c..9526d8b9fe0e 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -1,10 +1,65 @@
 #ifndef _LINUX_MM_TYPES_TASK_H
 #define _LINUX_MM_TYPES_TASK_H
 
+/*
+ * Here are the definitions of the MM data types that are embedded in 'struct task_struct'.
+ *
+ * (These are defined separately to decouple sched.h from mm_types.h as much as possible.)
+ */
+
 #include <linux/types.h>
 #include <linux/threads.h>
 #include <linux/atomic.h>
 
 #include <asm/page.h>
 
+#define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
+#define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
+		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
+#define ALLOC_SPLIT_PTLOCKS	(SPINLOCK_SIZE > BITS_PER_LONG/8)
+
+/*
+ * The per task VMA cache array:
+ */
+#define VMACACHE_BITS 2
+#define VMACACHE_SIZE (1U << VMACACHE_BITS)
+#define VMACACHE_MASK (VMACACHE_SIZE - 1)
+
+struct vmacache {
+	u32 seqnum;
+	struct vm_area_struct *vmas[VMACACHE_SIZE];
+};
+
+enum {
+	MM_FILEPAGES,	/* Resident file mapping pages */
+	MM_ANONPAGES,	/* Resident anonymous pages */
+	MM_SWAPENTS,	/* Anonymous swap entries */
+	MM_SHMEMPAGES,	/* Resident shared memory pages */
+	NR_MM_COUNTERS
+};
+
+#if USE_SPLIT_PTE_PTLOCKS && defined(CONFIG_MMU)
+#define SPLIT_RSS_COUNTING
+/* per-thread cached information, */
+struct task_rss_stat {
+	int events;	/* for synchronization threshold */
+	int count[NR_MM_COUNTERS];
+};
+#endif /* USE_SPLIT_PTE_PTLOCKS */
+
+struct mm_rss_stat {
+	atomic_long_t count[NR_MM_COUNTERS];
+};
+
+struct page_frag {
+	struct page *page;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 offset;
+	__u32 size;
+#else
+	__u16 offset;
+	__u16 size;
+#endif
+};
+
 #endif /* _LINUX_MM_TYPES_TASK_H */
-- 
GitLab


From 77ba809e8b39b4e384df0433e2bd3dd0907dad29 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 00:16:44 +0100
Subject: [PATCH 619/898] sched/headers: Remove the <linux/mm_types.h>
 dependency from <linux/sched.h>

Use the freshly introduced, reduced size <linux/mm_types_task.h> header instead.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/video/fbdev/auo_k190x.c | 1 +
 include/linux/sched.h           | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/auo_k190x.c b/drivers/video/fbdev/auo_k190x.c
index 9580374667ba..0d06038324e0 100644
--- a/drivers/video/fbdev/auo_k190x.c
+++ b/drivers/video/fbdev/auo_k190x.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/sched/mm.h>
 #include <linux/kernel.h>
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4934733bd6cb..3eb284741790 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -8,7 +8,7 @@
 #include <linux/capability.h>
 #include <linux/mutex.h>
 #include <linux/plist.h>
-#include <linux/mm_types.h>
+#include <linux/mm_types_task.h>
 #include <asm/ptrace.h>
 
 #include <linux/sem.h>
-- 
GitLab


From cdc75e9f7b14f29efcf4b162a3c673733e96db79 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 01:20:53 +0100
Subject: [PATCH 620/898] sched/headers: Move 'init_task' and
 'init_thread_union' from <linux/sched.h> to <linux/sched/task.h>

'init_task' is really not part of core scheduler APIs but part of
the fork() interface between the scheduler and process management.

So move the declarations.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 3 ---
 include/linux/sched/task.h | 6 ++++++
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3eb284741790..4ab105a2a8f9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1469,9 +1469,6 @@ static inline int kstack_end(void *addr)
 }
 #endif
 
-extern union thread_union init_thread_union;
-extern struct task_struct init_task;
-
 extern struct pid_namespace init_pid_ns;
 
 /*
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 20ed9108f261..1be049a18d1b 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -8,6 +8,9 @@
 
 #include <linux/sched.h>
 
+struct task_struct;
+union thread_union;
+
 /*
  * This serializes "schedule()" and also protects
  * the run-queue from deletions/modifications (but
@@ -17,6 +20,9 @@
 extern rwlock_t tasklist_lock;
 extern spinlock_t mmlist_lock;
 
+extern union thread_union init_thread_union;
+extern struct task_struct init_task;
+
 #ifdef CONFIG_PROVE_RCU
 extern int lockdep_tasklist_lock_is_held(void);
 #endif /* #ifdef CONFIG_PROVE_RCU */
-- 
GitLab


From 56cd697366b6d6f67acb6c58ac7f3b185d11ef07 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 10:57:33 +0100
Subject: [PATCH 621/898] sched/headers: Move the task_lock()/unlock() APIs to
 <linux/sched/task.h>

The task_lock()/task_unlock() APIs are not realated to core scheduling,
they are task lifetime APIs, i.e. they belong into <linux/sched/task.h>.

Move them.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 20 --------------------
 include/linux/sched/task.h | 20 ++++++++++++++++++++
 kernel/cgroup/cgroup-v1.c  |  1 +
 kernel/cgroup/namespace.c  |  2 +-
 4 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4ab105a2a8f9..d481c129a822 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1526,26 +1526,6 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
-/*
- * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
- * subscriptions and synchronises with wait4().  Also used in procfs.  Also
- * pins the final release of task.io_context.  Also protects ->cpuset and
- * ->cgroup.subsys[]. And ->vfork_done.
- *
- * Nests both inside and outside of read_lock(&tasklist_lock).
- * It must not be nested with write_lock_irq(&tasklist_lock),
- * neither inside nor outside.
- */
-static inline void task_lock(struct task_struct *p)
-{
-	spin_lock(&p->alloc_lock);
-}
-
-static inline void task_unlock(struct task_struct *p)
-{
-	spin_unlock(&p->alloc_lock);
-}
-
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 1be049a18d1b..2be9fde588a7 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -91,4 +91,24 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
 }
 #endif
 
+/*
+ * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
+ * subscriptions and synchronises with wait4().  Also used in procfs.  Also
+ * pins the final release of task.io_context.  Also protects ->cpuset and
+ * ->cgroup.subsys[]. And ->vfork_done.
+ *
+ * Nests both inside and outside of read_lock(&tasklist_lock).
+ * It must not be nested with write_lock_irq(&tasklist_lock),
+ * neither inside nor outside.
+ */
+static inline void task_lock(struct task_struct *p)
+{
+	spin_lock(&p->alloc_lock);
+}
+
+static inline void task_unlock(struct task_struct *p)
+{
+	spin_unlock(&p->alloc_lock);
+}
+
 #endif /* _LINUX_SCHED_TASK_H */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 08d2cb605101..abc585858685 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -6,6 +6,7 @@
 #include <linux/delay.h>
 #include <linux/mm.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/delayacct.h>
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index cff7ea62c38f..96d38dab6fb2 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -1,6 +1,6 @@
 #include "cgroup-internal.h"
 
-#include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/nsproxy.h>
 #include <linux/proc_ns.h>
-- 
GitLab


From 1050b27c52f615bc0e772b3119881e5304ccde6b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 11:48:36 +0100
Subject: [PATCH 622/898] sched/headers: Move cputime functionality from
 <linux/sched.h> and <linux/cputime.h> into <linux/sched/cputime.h>

Move cputime related functionality out of <linux/sched.h>, as most code
that includes <linux/sched.h> does not use that functionality.

Move data types that are not included in task_struct directly to
the signal definitions, into <linux/sched/signal.h>.

Also merge the (small) existing <linux/cputime.h> header into <linux/sched/cputime.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/cputime.h       |  13 ---
 include/linux/sched.h         |  89 -----------------
 include/linux/sched/cputime.h | 182 +++++++++++++++++++++++++++++++++-
 include/linux/sched/signal.h  |  33 ++++++
 kernel/sched/stats.h          | 111 ---------------------
 5 files changed, 214 insertions(+), 214 deletions(-)
 delete mode 100644 include/linux/cputime.h

diff --git a/include/linux/cputime.h b/include/linux/cputime.h
deleted file mode 100644
index a691dc4ddc13..000000000000
--- a/include/linux/cputime.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __LINUX_CPUTIME_H
-#define __LINUX_CPUTIME_H
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#include <asm/cputime.h>
-
-#ifndef cputime_to_nsecs
-# define cputime_to_nsecs(__ct)	\
-	(cputime_to_usecs(__ct) * NSEC_PER_USEC)
-#endif
-
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-#endif /* __LINUX_CPUTIME_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d481c129a822..2b43f55e4956 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -219,14 +219,6 @@ struct prev_cputime {
 #endif
 };
 
-static inline void prev_cputime_init(struct prev_cputime *prev)
-{
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	prev->utime = prev->stime = 0;
-	raw_spin_lock_init(&prev->lock);
-#endif
-}
-
 /**
  * struct task_cputime - collected CPU time counts
  * @utime:		time spent in user mode, in nanoseconds
@@ -248,40 +240,6 @@ struct task_cputime {
 #define prof_exp	stime
 #define sched_exp	sum_exec_runtime
 
-/*
- * This is the atomic variant of task_cputime, which can be used for
- * storing and updating task_cputime statistics without locking.
- */
-struct task_cputime_atomic {
-	atomic64_t utime;
-	atomic64_t stime;
-	atomic64_t sum_exec_runtime;
-};
-
-#define INIT_CPUTIME_ATOMIC \
-	(struct task_cputime_atomic) {				\
-		.utime = ATOMIC64_INIT(0),			\
-		.stime = ATOMIC64_INIT(0),			\
-		.sum_exec_runtime = ATOMIC64_INIT(0),		\
-	}
-
-/**
- * struct thread_group_cputimer - thread group interval timer counts
- * @cputime_atomic:	atomic thread group interval timers.
- * @running:		true when there are timers running and
- *			@cputime_atomic receives updates.
- * @checking_timer:	true when a thread in the group is in the
- *			process of checking for thread group timers.
- *
- * This structure contains the version of task_cputime, above, that is
- * used for thread group CPU timer calculations.
- */
-struct thread_group_cputimer {
-	struct task_cputime_atomic cputime_atomic;
-	bool running;
-	bool checking_timer;
-};
-
 #include <linux/rwsem.h>
 
 #ifdef CONFIG_SCHED_INFO
@@ -1234,44 +1192,6 @@ static inline void put_task_struct(struct task_struct *t)
 struct task_struct *task_rcu_dereference(struct task_struct **ptask);
 struct task_struct *try_get_task_struct(struct task_struct **ptask);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern void task_cputime(struct task_struct *t,
-			 u64 *utime, u64 *stime);
-extern u64 task_gtime(struct task_struct *t);
-#else
-static inline void task_cputime(struct task_struct *t,
-				u64 *utime, u64 *stime)
-{
-	*utime = t->utime;
-	*stime = t->stime;
-}
-
-static inline u64 task_gtime(struct task_struct *t)
-{
-	return t->gtime;
-}
-#endif
-
-#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
-static inline void task_cputime_scaled(struct task_struct *t,
-				       u64 *utimescaled,
-				       u64 *stimescaled)
-{
-	*utimescaled = t->utimescaled;
-	*stimescaled = t->stimescaled;
-}
-#else
-static inline void task_cputime_scaled(struct task_struct *t,
-				       u64 *utimescaled,
-				       u64 *stimescaled)
-{
-	task_cputime(t, utimescaled, stimescaled);
-}
-#endif
-
-extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
-extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
-
 /*
  * Per process flags
  */
@@ -1395,9 +1315,6 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 #define cpu_relax_yield() cpu_relax()
 #endif
 
-extern unsigned long long
-task_sched_runtime(struct task_struct *task);
-
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
 extern void sched_exec(void);
@@ -1629,12 +1546,6 @@ static __always_inline bool need_resched(void)
 	return unlikely(tif_need_resched());
 }
 
-/*
- * Thread group CPU time accounting.
- */
-void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
-void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
-
 /*
  * Wrappers for p->thread_info->cpu access. No-op on UP.
  */
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 6ed4fe43de28..4c5b9735c1ae 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -2,6 +2,186 @@
 #define _LINUX_SCHED_CPUTIME_H
 
 #include <linux/sched/signal.h>
-#include <linux/cputime.h>
+
+/*
+ * cputime accounting APIs:
+ */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+#include <asm/cputime.h>
+
+#ifndef cputime_to_nsecs
+# define cputime_to_nsecs(__ct)	\
+	(cputime_to_usecs(__ct) * NSEC_PER_USEC)
+#endif
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern void task_cputime(struct task_struct *t,
+			 u64 *utime, u64 *stime);
+extern u64 task_gtime(struct task_struct *t);
+#else
+static inline void task_cputime(struct task_struct *t,
+				u64 *utime, u64 *stime)
+{
+	*utime = t->utime;
+	*stime = t->stime;
+}
+
+static inline u64 task_gtime(struct task_struct *t)
+{
+	return t->gtime;
+}
+#endif
+
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+static inline void task_cputime_scaled(struct task_struct *t,
+				       u64 *utimescaled,
+				       u64 *stimescaled)
+{
+	*utimescaled = t->utimescaled;
+	*stimescaled = t->stimescaled;
+}
+#else
+static inline void task_cputime_scaled(struct task_struct *t,
+				       u64 *utimescaled,
+				       u64 *stimescaled)
+{
+	task_cputime(t, utimescaled, stimescaled);
+}
+#endif
+
+extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+
+
+/*
+ * Thread group CPU time accounting.
+ */
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
+
+
+/*
+ * The following are functions that support scheduler-internal time accounting.
+ * These functions are generally called at the timer tick.  None of this depends
+ * on CONFIG_SCHEDSTATS.
+ */
+
+/**
+ * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
+ *
+ * @tsk:	Pointer to target task.
+ */
+#ifdef CONFIG_POSIX_TIMERS
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+
+	/* Check if cputimer isn't running. This is accessed without locking. */
+	if (!READ_ONCE(cputimer->running))
+		return NULL;
+
+	/*
+	 * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime
+	 * in __exit_signal(), we won't account to the signal struct further
+	 * cputime consumed by that task, even though the task can still be
+	 * ticking after __exit_signal().
+	 *
+	 * In order to keep a consistent behaviour between thread group cputime
+	 * and thread group cputimer accounting, lets also ignore the cputime
+	 * elapsing after __exit_signal() in any thread group timer running.
+	 *
+	 * This makes sure that POSIX CPU clocks and timers are synchronized, so
+	 * that a POSIX CPU timer won't expire while the corresponding POSIX CPU
+	 * clock delta is behind the expiring timer value.
+	 */
+	if (unlikely(!tsk->sighand))
+		return NULL;
+
+	return cputimer;
+}
+#else
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
+{
+	return NULL;
+}
+#endif
+
+/**
+ * account_group_user_time - Maintain utime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the utime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void account_group_user_time(struct task_struct *tsk,
+					   u64 cputime)
+{
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
+
+	if (!cputimer)
+		return;
+
+	atomic64_add(cputime, &cputimer->cputime_atomic.utime);
+}
+
+/**
+ * account_group_system_time - Maintain stime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the stime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void account_group_system_time(struct task_struct *tsk,
+					     u64 cputime)
+{
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
+
+	if (!cputimer)
+		return;
+
+	atomic64_add(cputime, &cputimer->cputime_atomic.stime);
+}
+
+/**
+ * account_group_exec_runtime - Maintain exec runtime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @ns:		Time value by which to increment the sum_exec_runtime field
+ *		of the thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					      unsigned long long ns)
+{
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
+
+	if (!cputimer)
+		return;
+
+	atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime);
+}
+
+static inline void prev_cputime_init(struct prev_cputime *prev)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	prev->utime = prev->stime = 0;
+	raw_spin_lock_init(&prev->lock);
+#endif
+}
+
+extern unsigned long long
+task_sched_runtime(struct task_struct *task);
 
 #endif /* _LINUX_SCHED_CPUTIME_H */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index b3545fb4333a..2cf446704cd4 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -35,6 +35,39 @@ struct cpu_itimer {
 	u64 incr;
 };
 
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+	atomic64_t utime;
+	atomic64_t stime;
+	atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+	(struct task_cputime_atomic) {				\
+		.utime = ATOMIC64_INIT(0),			\
+		.stime = ATOMIC64_INIT(0),			\
+		.sum_exec_runtime = ATOMIC64_INIT(0),		\
+	}
+/**
+ * struct thread_group_cputimer - thread group interval timer counts
+ * @cputime_atomic:	atomic thread group interval timers.
+ * @running:		true when there are timers running and
+ *			@cputime_atomic receives updates.
+ * @checking_timer:	true when a thread in the group is in the
+ *			process of checking for thread group timers.
+ *
+ * This structure contains the version of task_cputime, above, that is
+ * used for thread group CPU timer calculations.
+ */
+struct thread_group_cputimer {
+	struct task_cputime_atomic cputime_atomic;
+	bool running;
+	bool checking_timer;
+};
+
 /*
  * NOTE! "signal_struct" does not have its own
  * locking, because a shared signal_struct always
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index bf0da0aa0a14..d5710651043b 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -164,114 +164,3 @@ sched_info_switch(struct rq *rq,
 #define sched_info_arrive(rq, next)		do { } while (0)
 #define sched_info_switch(rq, t, next)		do { } while (0)
 #endif /* CONFIG_SCHED_INFO */
-
-/*
- * The following are functions that support scheduler-internal time accounting.
- * These functions are generally called at the timer tick.  None of this depends
- * on CONFIG_SCHEDSTATS.
- */
-
-/**
- * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
- *
- * @tsk:	Pointer to target task.
- */
-#ifdef CONFIG_POSIX_TIMERS
-static inline
-struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
-{
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
-
-	/* Check if cputimer isn't running. This is accessed without locking. */
-	if (!READ_ONCE(cputimer->running))
-		return NULL;
-
-	/*
-	 * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime
-	 * in __exit_signal(), we won't account to the signal struct further
-	 * cputime consumed by that task, even though the task can still be
-	 * ticking after __exit_signal().
-	 *
-	 * In order to keep a consistent behaviour between thread group cputime
-	 * and thread group cputimer accounting, lets also ignore the cputime
-	 * elapsing after __exit_signal() in any thread group timer running.
-	 *
-	 * This makes sure that POSIX CPU clocks and timers are synchronized, so
-	 * that a POSIX CPU timer won't expire while the corresponding POSIX CPU
-	 * clock delta is behind the expiring timer value.
-	 */
-	if (unlikely(!tsk->sighand))
-		return NULL;
-
-	return cputimer;
-}
-#else
-static inline
-struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
-{
-	return NULL;
-}
-#endif
-
-/**
- * account_group_user_time - Maintain utime for a thread group.
- *
- * @tsk:	Pointer to task structure.
- * @cputime:	Time value by which to increment the utime field of the
- *		thread_group_cputime structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the utime field there.
- */
-static inline void account_group_user_time(struct task_struct *tsk,
-					   u64 cputime)
-{
-	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
-
-	if (!cputimer)
-		return;
-
-	atomic64_add(cputime, &cputimer->cputime_atomic.utime);
-}
-
-/**
- * account_group_system_time - Maintain stime for a thread group.
- *
- * @tsk:	Pointer to task structure.
- * @cputime:	Time value by which to increment the stime field of the
- *		thread_group_cputime structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the stime field there.
- */
-static inline void account_group_system_time(struct task_struct *tsk,
-					     u64 cputime)
-{
-	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
-
-	if (!cputimer)
-		return;
-
-	atomic64_add(cputime, &cputimer->cputime_atomic.stime);
-}
-
-/**
- * account_group_exec_runtime - Maintain exec runtime for a thread group.
- *
- * @tsk:	Pointer to task structure.
- * @ns:		Time value by which to increment the sum_exec_runtime field
- *		of the thread_group_cputime structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the sum_exec_runtime field there.
- */
-static inline void account_group_exec_runtime(struct task_struct *tsk,
-					      unsigned long long ns)
-{
-	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
-
-	if (!cputimer)
-		return;
-
-	atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime);
-}
-- 
GitLab


From a2d7a7463c38dd14b845721aac3583a26a97c66d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 12:07:04 +0100
Subject: [PATCH 623/898] sched/headers: Move sched_info_on() and
 force_schedstat_enabled() from <linux/sched.h> to <linux/sched/stat.h>

These APIs are not core scheduler but scheduler statistics related.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 16 ----------------
 include/linux/sched/stat.h | 16 ++++++++++++++++
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b43f55e4956..707eee099332 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -254,22 +254,6 @@ struct sched_info {
 };
 #endif /* CONFIG_SCHED_INFO */
 
-static inline int sched_info_on(void)
-{
-#ifdef CONFIG_SCHEDSTATS
-	return 1;
-#elif defined(CONFIG_TASK_DELAY_ACCT)
-	extern int delayacct_on;
-	return delayacct_on;
-#else
-	return 0;
-#endif
-}
-
-#ifdef CONFIG_SCHEDSTATS
-void force_schedstat_enabled(void);
-#endif
-
 /*
  * Integer metrics need fixed point arithmetic, e.g., sched/fair
  * has a few: load, load_avg, util_avg, freq, and capacity.
diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
index 0d52ceb6d3ae..d8cedf27083e 100644
--- a/include/linux/sched/stat.h
+++ b/include/linux/sched/stat.h
@@ -21,4 +21,20 @@ extern unsigned long nr_iowait(void);
 extern unsigned long nr_iowait_cpu(int cpu);
 extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
+static inline int sched_info_on(void)
+{
+#ifdef CONFIG_SCHEDSTATS
+	return 1;
+#elif defined(CONFIG_TASK_DELAY_ACCT)
+	extern int delayacct_on;
+	return delayacct_on;
+#else
+	return 0;
+#endif
+}
+
+#ifdef CONFIG_SCHEDSTATS
+void force_schedstat_enabled(void);
+#endif
+
 #endif /* _LINUX_SCHED_STAT_H */
-- 
GitLab


From 28851755990c832d7050d5e1e2c91ed9d9e6fe59 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:24:31 +0100
Subject: [PATCH 624/898] sched/headers, vfs/execve: Move the do_execve*()
 prototypes from <linux/sched.h> to <linux/binfmts.h>

These are not scheduler related.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/binfmts.h | 10 ++++++++++
 include/linux/sched.h   |  8 --------
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 1303b570b18c..05488da3aee9 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -6,6 +6,8 @@
 #include <asm/exec.h>
 #include <uapi/linux/binfmts.h>
 
+struct filename;
+
 #define CORENAME_MAX_SIZE 128
 
 /*
@@ -123,4 +125,12 @@ extern void install_exec_creds(struct linux_binprm *bprm);
 extern void set_binfmt(struct linux_binfmt *new);
 extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t);
 
+extern int do_execve(struct filename *,
+		     const char __user * const __user *,
+		     const char __user * const __user *);
+extern int do_execveat(int, struct filename *,
+		       const char __user * const __user *,
+		       const char __user * const __user *,
+		       int);
+
 #endif /* _LINUX_BINFMTS_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 707eee099332..5f2267e41fde 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1400,14 +1400,6 @@ extern void exit_files(struct task_struct *);
 
 extern void exit_itimers(struct signal_struct *);
 
-extern int do_execve(struct filename *,
-		     const char __user * const __user *,
-		     const char __user * const __user *);
-extern int do_execveat(int, struct filename *,
-		       const char __user * const __user *,
-		       const char __user * const __user *,
-		       int);
-
 extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
 static inline void set_task_comm(struct task_struct *tsk, const char *from)
 {
-- 
GitLab


From 9049863a32fad5d7158318e45f0a41a0f2192c0c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:31:22 +0100
Subject: [PATCH 625/898] sched/headers: Move kstack_end() from <linux/sched.h>
 to <linux/sched/task_stack.h>

This is a task-stack related API, not core scheduler functionality.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h            | 10 ----------
 include/linux/sched/task_stack.h | 10 ++++++++++
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5f2267e41fde..309eb76b7eab 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1360,16 +1360,6 @@ static inline struct thread_info *task_thread_info(struct task_struct *task)
 # define task_thread_info(task)	((struct thread_info *)(task)->stack)
 #endif
 
-#ifndef __HAVE_ARCH_KSTACK_END
-static inline int kstack_end(void *addr)
-{
-	/* Reliable end of stack detection:
-	 * Some APM bios versions misalign the stack
-	 */
-	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
-}
-#endif
-
 extern struct pid_namespace init_pid_ns;
 
 /*
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index aaa5c2a6a0e9..df6ea6665b31 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -108,4 +108,14 @@ static inline unsigned long stack_not_used(struct task_struct *p)
 #endif
 extern void set_task_stack_end_magic(struct task_struct *tsk);
 
+#ifndef __HAVE_ARCH_KSTACK_END
+static inline int kstack_end(void *addr)
+{
+	/* Reliable end of stack detection:
+	 * Some APM bios versions misalign the stack
+	 */
+	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
+}
+#endif
+
 #endif /* _LINUX_SCHED_TASK_STACK_H */
-- 
GitLab


From 42011db0ed5a9c92b1281e1300eb3d026f3764a8 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:35:41 +0100
Subject: [PATCH 626/898] sched/headers: Move exit_files() and exit_itimers()
 from <linux/sched.h> to <linux/sched/task.h>

These two functions are task management related, not core scheduler APIs.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 4 ----
 include/linux/sched/task.h | 3 +++
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 309eb76b7eab..4a03c49e3bcc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1386,10 +1386,6 @@ extern void wake_up_new_task(struct task_struct *tsk);
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
 
-extern void exit_files(struct task_struct *);
-
-extern void exit_itimers(struct signal_struct *);
-
 extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
 static inline void set_task_comm(struct task_struct *tsk, const char *from)
 {
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 2be9fde588a7..a33a8121da9a 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -67,6 +67,9 @@ static inline void exit_thread(struct task_struct *tsk)
 #endif
 extern void do_group_exit(int);
 
+extern void exit_files(struct task_struct *);
+extern void exit_itimers(struct signal_struct *);
+
 extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
-- 
GitLab


From c5a21921d55a2aee9d1e031a78cef6cda3eab78b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:47:12 +0100
Subject: [PATCH 627/898] sched/headers: Move _init() prototypes from
 <linux/sched.h> to <linux/sched/init.h>

trap_init() and cpu_init() belong into <linux/cpu.h>, sched_init*() into <linux/sched/init.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 5 -----
 include/linux/sched/init.h | 7 +++++++
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4a03c49e3bcc..0fb56ae0abc7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -176,15 +176,10 @@ struct uts_namespace;
 /* Task command name length */
 #define TASK_COMM_LEN 16
 
-extern void sched_init(void);
-extern void sched_init_smp(void);
-
 extern cpumask_var_t cpu_isolated_map;
 
 extern int runqueue_is_locked(int cpu);
 
-extern void cpu_init (void);
-extern void trap_init(void);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
 
diff --git a/include/linux/sched/init.h b/include/linux/sched/init.h
index 15e46313e55e..f31d16075857 100644
--- a/include/linux/sched/init.h
+++ b/include/linux/sched/init.h
@@ -3,4 +3,11 @@
 
 #include <linux/sched.h>
 
+/*
+ * Scheduler init related prototypes:
+ */
+
+extern void sched_init(void);
+extern void sched_init_smp(void);
+
 #endif /* _LINUX_SCHED_INIT_H */
-- 
GitLab


From 93b5a9a7051e51ce50109046af0235268a261ba0 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 14:53:36 +0100
Subject: [PATCH 628/898] sched/headers, timekeeping: Move the timer tick
 function prototypes to <linux/timekeeping.h>

Move the update_process_times() and xtime_update() prototypes to <linux/timekeeping.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h       | 1 -
 include/linux/time.h        | 2 --
 include/linux/timekeeping.h | 4 ++++
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0fb56ae0abc7..dc8d94dc140f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -180,7 +180,6 @@ extern cpumask_var_t cpu_isolated_map;
 
 extern int runqueue_is_locked(int cpu);
 
-extern void update_process_times(int user);
 extern void scheduler_tick(void);
 
 #define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
diff --git a/include/linux/time.h b/include/linux/time.h
index 4f4ab65b6e61..23f0f5ce3090 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -167,8 +167,6 @@ static inline bool timespec_inject_offset_valid(const struct timespec *ts)
 extern u32 (*arch_gettimeoffset)(void);
 #endif
 
-extern void xtime_update(unsigned long ticks);
-
 struct itimerval;
 extern int do_setitimer(int which, struct itimerval *value,
 			struct itimerval *ovalue);
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index d2e804e15c3e..b598cbc7b576 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -8,6 +8,10 @@
 void timekeeping_init(void);
 extern int timekeeping_suspended;
 
+/* Architecture timer tick functions: */
+extern void update_process_times(int user);
+extern void xtime_update(unsigned long ticks);
+
 /*
  * Get and set timeofday
  */
-- 
GitLab


From dcc2dc45f7cf267d37843059ff75b70260596c69 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 15:05:49 +0100
Subject: [PATCH 629/898] sched/headers, mm: Move 'struct tlbflush_unmap_batch'
 from <linux/sched.h> to <linux/mm_types_task.h>

Unclutter <linux/sched.h> some more.

Also move the CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH condition inside the
structure body definition, to remove a pair of #ifdefs from sched.h.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm_types_task.h | 22 ++++++++++++++++++++++
 include/linux/sched.h         | 21 ---------------------
 2 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index 9526d8b9fe0e..136dfdf63ba1 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <linux/threads.h>
 #include <linux/atomic.h>
+#include <linux/cpumask.h>
 
 #include <asm/page.h>
 
@@ -62,4 +63,25 @@ struct page_frag {
 #endif
 };
 
+/* Track pages that require TLB flushes */
+struct tlbflush_unmap_batch {
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	/*
+	 * Each bit set is a CPU that potentially has a TLB entry for one of
+	 * the PFNs being flushed. See set_tlb_ubc_flush_pending().
+	 */
+	struct cpumask cpumask;
+
+	/* True if any bit in cpumask is set */
+	bool flush_required;
+
+	/*
+	 * If true then the PTE was dirty when unmapped. The entry must be
+	 * flushed before IO is initiated or a stale TLB entry potentially
+	 * allows an update without redirtying the page.
+	 */
+	bool writable;
+#endif
+};
+
 #endif /* _LINUX_MM_TYPES_TASK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dc8d94dc140f..8d6b7aa7f3ac 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -484,25 +484,6 @@ struct wake_q_node {
 	struct wake_q_node *next;
 };
 
-/* Track pages that require TLB flushes */
-struct tlbflush_unmap_batch {
-	/*
-	 * Each bit set is a CPU that potentially has a TLB entry for one of
-	 * the PFNs being flushed. See set_tlb_ubc_flush_pending().
-	 */
-	struct cpumask cpumask;
-
-	/* True if any bit in cpumask is set */
-	bool flush_required;
-
-	/*
-	 * If true then the PTE was dirty when unmapped. The entry must be
-	 * flushed before IO is initiated or a stale TLB entry potentially
-	 * allows an update without redirtying the page.
-	 */
-	bool writable;
-};
-
 struct task_struct {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/*
@@ -895,9 +876,7 @@ struct task_struct {
 	unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
-#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	struct tlbflush_unmap_batch tlb_ubc;
-#endif
 
 	struct rcu_head rcu;
 
-- 
GitLab


From cda66725c1444db67127115d611c982b62b45d8c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 15:30:50 +0100
Subject: [PATCH 630/898] sched/headers: Move the
 get_task_struct()/put_task_struct() and related APIs from <linux/sched.h> to
 <linux/sched/task.h>

These belong into the task lifetime API header.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 14 --------------
 include/linux/sched/task.h | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8d6b7aa7f3ac..b68358c60560 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1135,20 +1135,6 @@ static inline int is_global_init(struct task_struct *tsk)
 
 extern struct pid *cad_pid;
 
-extern void free_task(struct task_struct *tsk);
-#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
-
-extern void __put_task_struct(struct task_struct *t);
-
-static inline void put_task_struct(struct task_struct *t)
-{
-	if (atomic_dec_and_test(&t->usage))
-		__put_task_struct(t);
-}
-
-struct task_struct *task_rcu_dereference(struct task_struct **ptask);
-struct task_struct *try_get_task_struct(struct task_struct **ptask);
-
 /*
  * Per process flags
  */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a33a8121da9a..3886ae64148f 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -75,6 +75,21 @@ extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, i
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
+extern void free_task(struct task_struct *tsk);
+
+#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
+
+extern void __put_task_struct(struct task_struct *t);
+
+static inline void put_task_struct(struct task_struct *t)
+{
+	if (atomic_dec_and_test(&t->usage))
+		__put_task_struct(t);
+}
+
+struct task_struct *task_rcu_dereference(struct task_struct **ptask);
+struct task_struct *try_get_task_struct(struct task_struct **ptask);
+
 
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
 extern int arch_task_struct_size __read_mostly;
-- 
GitLab


From 6f175fc9536355d8aa5c2d4854848a97c244a031 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 11:12:45 +0100
Subject: [PATCH 631/898] sched/headers: Move the sched_exec() prototype to
 <linux/sched/task.h>

sched_exec() better fits into the task lifetime APIs than into the core scheduler
APIs.

This reduces the size of <linux/sched.h> a bit.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h      | 7 -------
 include/linux/sched/task.h | 7 +++++++
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b68358c60560..bd89fc17767c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1258,13 +1258,6 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 #define cpu_relax_yield() cpu_relax()
 #endif
 
-/* sched_exec is called by processes performing an exec */
-#ifdef CONFIG_SMP
-extern void sched_exec(void);
-#else
-#define sched_exec()   {}
-#endif
-
 extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 3886ae64148f..a978d7189cfd 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -77,6 +77,13 @@ extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
 extern void free_task(struct task_struct *tsk);
 
+/* sched_exec is called by processes performing an exec */
+#ifdef CONFIG_SMP
+extern void sched_exec(void);
+#else
+#define sched_exec()   {}
+#endif
+
 #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
 
 extern void __put_task_struct(struct task_struct *t);
-- 
GitLab


From c03cb28e7c44055cd00d11b8581b9fa46a3e3764 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 632/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/topology.h>

The <linux/sched/topology.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/topology.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index b3550b36e65d..0d6fceff37bb 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -1,8 +1,6 @@
 #ifndef _LINUX_SCHED_TOPOLOGY_H
 #define _LINUX_SCHED_TOPOLOGY_H
 
-#include <linux/sched.h>
-
 #include <linux/sched/idle.h>
 
 /*
-- 
GitLab


From f411229e1dd623a3dee623824d094546789977e0 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 18:49:05 +0100
Subject: [PATCH 633/898] sched/headers: Remove tsk_is_polling()

It's not used by anything.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/idle.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index 66ee32f87f0b..5ca63ebad6b4 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -17,10 +17,6 @@ extern void wake_up_if_idle(int cpu);
  * polling state.
  */
 #ifdef TIF_POLLING_NRFLAG
-static inline int tsk_is_polling(struct task_struct *p)
-{
-	return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
-}
 
 static inline void __current_set_polling(void)
 {
@@ -59,7 +55,6 @@ static inline bool __must_check current_clr_polling_and_test(void)
 }
 
 #else
-static inline int tsk_is_polling(struct task_struct *p) { return 0; }
 static inline void __current_set_polling(void) { }
 static inline void __current_clr_polling(void) { }
 
-- 
GitLab


From ea94763950e49d1aa622c59218ee2fc3b434ba6b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 634/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/clock.h>

The <linux/sched/clock.h> file is a largely self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/clock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index ac12f71d359c..4a68c6791207 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_SCHED_CLOCK_H
 #define _LINUX_SCHED_CLOCK_H
 
-#include <linux/sched.h>
+#include <linux/smp.h>
 
 /*
  * Do not use outside of architecture code which knows its limitations.
-- 
GitLab


From cc689c5b352d4a7510b11c975c5c94d4785b37e7 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 1 Feb 2017 16:36:40 +0100
Subject: [PATCH 635/898] sched/headers: Remove <linux/sched.h> and
 <linux/slab.h> from <linux/delayacct.h>

The <linux/delayacct.h> file is a self-contained header and users of
it either don't need <linux/sched.h> and <linux/slab.h> - or have
already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/delayacct.h    | 2 --
 include/linux/fault-inject.h | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6b769cbd1000..4178d2493547 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -18,8 +18,6 @@
 #define _LINUX_DELAYACCT_H
 
 #include <uapi/linux/taskstats.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
 
 /*
  * Per-task flags relevant to delay accounting
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 9f4956d8601c..728d4e0292aa 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -61,6 +61,8 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name,
 
 #endif /* CONFIG_FAULT_INJECTION */
 
+struct kmem_cache;
+
 #ifdef CONFIG_FAILSLAB
 extern bool should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #else
-- 
GitLab


From 5a2d6880f461faa416c0d329d46a128cf342c1eb Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:54 +0100
Subject: [PATCH 636/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/loadavg.h>

The <linux/sched/loadavg.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/loadavg.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index c392e28ce0ac..4264bc6b2c27 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -1,8 +1,6 @@
 #ifndef _LINUX_SCHED_LOADAVG_H
 #define _LINUX_SCHED_LOADAVG_H
 
-#include <linux/sched.h>
-
 /*
  * These are the constant used to fake the fixed-point load-average
  * counting. Some notes:
-- 
GitLab


From 5fd73157bdfb57370b69be7c0067f08e610e7daa Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:54 +0100
Subject: [PATCH 637/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/autogroup.h>

The <linux/sched/autogroup.h> file is a largely self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

Add a 'task_struct' predeclaration to make it build standalone.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/autogroup.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/linux/sched/autogroup.h b/include/linux/sched/autogroup.h
index fd6855548d0c..55cd496df884 100644
--- a/include/linux/sched/autogroup.h
+++ b/include/linux/sched/autogroup.h
@@ -1,9 +1,8 @@
 #ifndef _LINUX_SCHED_AUTOGROUP_H
 #define _LINUX_SCHED_AUTOGROUP_H
 
-#include <linux/sched.h>
-
 struct signal_struct;
+struct task_struct;
 struct task_group;
 struct seq_file;
 
-- 
GitLab


From b8d6d80b37a98e3910f1b4e799f8ebea88e94bfa Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:54 +0100
Subject: [PATCH 638/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/mm.h>

The <linux/sched/mm.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

Include kernel.h and atomic.h.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/mm.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 62dca4e0b4e0..830953ebb391 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_SCHED_MM_H
 #define _LINUX_SCHED_MM_H
 
+#include <linux/kernel.h>
+#include <linux/atomic.h>
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/gfp.h>
-- 
GitLab


From ae1cc8823204bb938d039afa43c28a84591ada9f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:54 +0100
Subject: [PATCH 639/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/coredump.h>

The <linux/sched/coredump.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

Include <linux/mm_types.h>.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/coredump.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index f46912aa4f4c..69eedcef8f03 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -1,7 +1,6 @@
 #ifndef _LINUX_SCHED_COREDUMP_H
 #define _LINUX_SCHED_COREDUMP_H
 
-#include <linux/sched.h>
 #include <linux/mm_types.h>
 
 #define SUID_DUMP_DISABLE	0	/* No setuid dumping */
-- 
GitLab


From 556725839e543bc2b45bd73121c0b1c1d6c23714 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 10:31:24 +0100
Subject: [PATCH 640/898] sched/headers: Remove unused 'task_can_switch_user()'
 prototype

The function does not exist anymore.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index bd89fc17767c..43ed34ccb53a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1509,9 +1509,6 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
-extern int task_can_switch_user(struct user_struct *up,
-					struct task_struct *tsk);
-
 #ifndef TASK_SIZE_OF
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
-- 
GitLab


From de8deb0ad79f8a49cea5110c006c8676a11611f7 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:55 +0100
Subject: [PATCH 641/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/user.h>

If we add <linux/uidgid.h> then <linux/sched/user.h> becomes a
self-contained header and users of it either don't need <linux/sched.h>
or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/user.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 40c6363da5ef..5d5415e129d4 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -1,7 +1,8 @@
 #ifndef _LINUX_SCHED_USER_H
 #define _LINUX_SCHED_USER_H
 
-#include <linux/sched.h>
+#include <linux/uidgid.h>
+#include <linux/atomic.h>
 
 struct key;
 
-- 
GitLab


From ac4e620967bb72f86371154935aa8b67cf54e225 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 11:44:31 +0100
Subject: [PATCH 642/898] sched/headers: Remove #include <linux/capability.h>
 from <linux/sched.h>

The <linux/sched.h> header does not actually make use of any
types or APIs defined in <linux/capability.h>, so remove its inclusion.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 43ed34ccb53a..54eefb2ad603 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -5,7 +5,6 @@
 
 #include <linux/sched/prio.h>
 
-#include <linux/capability.h>
 #include <linux/mutex.h>
 #include <linux/plist.h>
 #include <linux/mm_types_task.h>
-- 
GitLab


From aa829c7679a13fca667f772db1f0ea03adc29122 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 11:54:05 +0100
Subject: [PATCH 643/898] sched/headers: Remove <linux/cgroup-defs.h> from
 <linux/sched.h>

It's not used by anything in <linux/sched.h> anymore.

This reduces the preprocessed size of <linux/sched.h> and
speeds up the build a bit.

Also fix code that implicitly relied on headers included by <linux/cgroup-defs.h>.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h             | 1 -
 include/target/target_core_base.h | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 54eefb2ad603..8991e4d7cd0f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -28,7 +28,6 @@
 #include <linux/gfp.h>
 #include <linux/topology.h>
 #include <linux/magic.h>
-#include <linux/cgroup-defs.h>
 
 #include <asm/current.h>
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 8be9ba73383d..774c29b57e82 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -4,6 +4,7 @@
 #include <linux/configfs.h>      /* struct config_group */
 #include <linux/dma-direction.h> /* enum dma_data_direction */
 #include <linux/percpu_ida.h>    /* struct percpu_ida */
+#include <linux/percpu-refcount.h>
 #include <linux/semaphore.h>     /* struct semaphore */
 #include <linux/completion.h>
 
-- 
GitLab


From ed53742d793bd92ed32114081370b199dc94467d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:55 +0100
Subject: [PATCH 644/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/cpufreq.h>

Make the <linux/sched/cpufreq.h> file a self-contained header and
remove the <linux/sched.h> dependency: users of it either don't
need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/cpufreq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 2bdcfbfc4c30..d2be2ccbb372 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_SCHED_CPUFREQ_H
 #define _LINUX_SCHED_CPUFREQ_H
 
-#include <linux/sched.h>
+#include <linux/types.h>
 
 /*
  * Interface between cpufreq drivers and the scheduler:
-- 
GitLab


From 71af2ed5eeea639339e3a1497a0196bab7de4b57 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 09:57:00 +0100
Subject: [PATCH 645/898] kasan, sched/headers: Remove <linux/sched.h> from
 <linux/kasan.h>

<linux/kasan.h> is a low level header that is included early
in affected kernel headers. But it includes <linux/sched.h>
which complicates the cleanup of sched.h dependencies.

Remove it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kasan.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 7793036eac80..ceb3fe78a0d3 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -1,7 +1,6 @@
 #ifndef _LINUX_KASAN_H
 #define _LINUX_KASAN_H
 
-#include <linux/sched.h>
 #include <linux/types.h>
 
 struct kmem_cache;
-- 
GitLab


From e26512fea5bcd6602dbf02a551ed073cd4529449 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 17:54:15 +0100
Subject: [PATCH 646/898] sched/headers: Remove <linux/cred.h> inclusion from
 <linux/sched.h>

This reduces header dependencies and speeds up the build.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8991e4d7cd0f..1be69735cef3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -24,7 +24,6 @@
 #include <linux/kcov.h>
 #include <linux/task_io_accounting.h>
 #include <linux/latencytop.h>
-#include <linux/cred.h>
 #include <linux/gfp.h>
 #include <linux/topology.h>
 #include <linux/magic.h>
-- 
GitLab


From f780d89a0e820a529cf91fb78b52565e1b37b774 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 10:03:42 +0100
Subject: [PATCH 647/898] sched/headers: Remove <asm/ptrace.h> from
 <linux/sched.h>

This reduces header dependencies.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sh/include/asm/fpu.h | 2 ++
 arch/sh/mm/extable_32.c   | 2 ++
 include/linux/sched.h     | 1 -
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/sh/include/asm/fpu.h b/arch/sh/include/asm/fpu.h
index 09fc2bc8a790..50921c7cc3f0 100644
--- a/arch/sh/include/asm/fpu.h
+++ b/arch/sh/include/asm/fpu.h
@@ -3,6 +3,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/ptrace.h>
+
 struct task_struct;
 
 #ifdef CONFIG_SH_FPU
diff --git a/arch/sh/mm/extable_32.c b/arch/sh/mm/extable_32.c
index 24a75d315dcb..940e871bc816 100644
--- a/arch/sh/mm/extable_32.c
+++ b/arch/sh/mm/extable_32.c
@@ -7,6 +7,8 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 
+#include <asm/ptrace.h>
+
 int fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *fixup;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1be69735cef3..9dfa9c113570 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -8,7 +8,6 @@
 #include <linux/mutex.h>
 #include <linux/plist.h>
 #include <linux/mm_types_task.h>
-#include <asm/ptrace.h>
 
 #include <linux/sem.h>
 #include <linux/shm.h>
-- 
GitLab


From 9c6da18109d603a99915b257929c0370c9d3ae40 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 10:08:30 +0100
Subject: [PATCH 648/898] sched/headers: Remove <linux/rtmutex.h> from
 <linux/sched.h>

This reduces header dependencies.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9dfa9c113570..cc5c99a27e21 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -16,7 +16,6 @@
 #include <linux/pid.h>
 #include <linux/seccomp.h>
 #include <linux/rculist.h>
-#include <linux/rtmutex.h>
 
 #include <linux/resource.h>
 #include <linux/hrtimer.h>
-- 
GitLab


From f0a0eb699967f4f51567b563818bafe4017bef73 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 2 Feb 2017 20:56:33 +0100
Subject: [PATCH 649/898] sched/headers: Remove the <linux/gfp.h> include from
 <linux/sched.h>

This reduces sched.h header dependencies.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index cc5c99a27e21..ab80596dddfd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -22,7 +22,6 @@
 #include <linux/kcov.h>
 #include <linux/task_io_accounting.h>
 #include <linux/latencytop.h>
-#include <linux/gfp.h>
 #include <linux/topology.h>
 #include <linux/magic.h>
 
-- 
GitLab


From dc1995392d79b0eeee147a792482b991f74c1494 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:57 +0100
Subject: [PATCH 650/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/stat.h>

The <linux/sched/stat.h> file is a largely self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

( Keep the <linux/percpu.h> dependency.)

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/stat.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
index d8cedf27083e..141b74c53fad 100644
--- a/include/linux/sched/stat.h
+++ b/include/linux/sched/stat.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_SCHED_STAT_H
 #define _LINUX_SCHED_STAT_H
 
-#include <linux/sched.h>
+#include <linux/percpu.h>
 
 /*
  * Various counters maintained by the scheduler and fork(),
-- 
GitLab


From b0145d9b332a5117bd0abbb980ab89586a1d5f6c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:57 +0100
Subject: [PATCH 651/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/nohz.h>

The <linux/sched/nohz.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/nohz.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index 9471f0736a3a..4995b717500b 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -1,8 +1,6 @@
 #ifndef _LINUX_SCHED_NOHZ_H
 #define _LINUX_SCHED_NOHZ_H
 
-#include <linux/sched.h>
-
 /*
  * This is the interface between the scheduler and nohz/dyntics:
  */
-- 
GitLab


From 4f079e98a0db5f067c0981a526ff8938e21c52e2 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:57 +0100
Subject: [PATCH 652/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/debug.h>

The <linux/sched/debug.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/debug.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index 853bbef0b47b..e0eaee54c5a4 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -1,8 +1,6 @@
 #ifndef _LINUX_SCHED_DEBUG_H
 #define _LINUX_SCHED_DEBUG_H
 
-#include <linux/sched.h>
-
 /*
  * Various scheduler/task debugging interfaces:
  */
-- 
GitLab


From a906086ef35129d522047a296e7c4237af75fdcb Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:57 +0100
Subject: [PATCH 653/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/hotplug.h>

The <linux/sched/hotplug.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/hotplug.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
index c608d3c1ddb8..752ac7e628d7 100644
--- a/include/linux/sched/hotplug.h
+++ b/include/linux/sched/hotplug.h
@@ -1,8 +1,6 @@
 #ifndef _LINUX_SCHED_HOTPLUG_H
 #define _LINUX_SCHED_HOTPLUG_H
 
-#include <linux/sched.h>
-
 /*
  * Scheduler interfaces for hotplug CPU support:
  */
-- 
GitLab


From fae3c30c2d1ae3ff93877f64e5d55e2443d8f82f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 12:00:08 +0100
Subject: [PATCH 654/898] sched/headers: Remove the runqueue_is_locked()
 prototype

Remove the runqueue_is_locked() prototype, the function does not exist anymore.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ab80596dddfd..ac98255d00fb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -172,8 +172,6 @@ struct uts_namespace;
 
 extern cpumask_var_t cpu_isolated_map;
 
-extern int runqueue_is_locked(int cpu);
-
 extern void scheduler_tick(void);
 
 #define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
-- 
GitLab


From cd9c513be34ceaae8bf211474b91b6897574efdd Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:58 +0100
Subject: [PATCH 655/898] sched/headers: Remove <linux/rwsem.h> from
 <linux/sched.h>

This is a stray header that is not needed by anything in sched.h,
so remove it.

Update files that relied on the stray inclusion.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h          | 2 --
 include/linux/user_namespace.h | 1 +
 kernel/utsname_sysctl.c        | 1 +
 3 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ac98255d00fb..b361f881fe44 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -226,8 +226,6 @@ struct task_cputime {
 #define prof_exp	stime
 #define sched_exp	sum_exec_runtime
 
-#include <linux/rwsem.h>
-
 #ifdef CONFIG_SCHED_INFO
 struct sched_info {
 	/* cumulative counters */
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 08264641b502..faa9bfb827da 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -5,6 +5,7 @@
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/sched.h>
+#include <linux/rwsem.h>
 #include <linux/sysctl.h>
 #include <linux/err.h>
 
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index c8eac43267e9..233cd8fc6910 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -14,6 +14,7 @@
 #include <linux/utsname.h>
 #include <linux/sysctl.h>
 #include <linux/wait.h>
+#include <linux/rwsem.h>
 
 #ifdef CONFIG_PROC_SYSCTL
 
-- 
GitLab


From 192c9414516e7178a44f9ed48d47501c4c19771c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 3 Feb 2017 23:47:37 +0100
Subject: [PATCH 656/898] sched/headers: Remove <linux/signal.h> from
 <linux/sched.h>

Instead of including the full <linux/signal.h>, only include the types-only
<linux/signal_types.h> header in <linux/sched.h>, to further decouple the
scheduler header from the signal headers.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b361f881fe44..905d4f148d65 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -11,7 +11,6 @@
 
 #include <linux/sem.h>
 #include <linux/shm.h>
-#include <linux/signal.h>
 #include <linux/signal_types.h>
 #include <linux/pid.h>
 #include <linux/seccomp.h>
-- 
GitLab


From 1d1954e038435765a623884b626731784cde768f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 01:16:15 +0100
Subject: [PATCH 657/898] sched/headers: Remove the 'init_pid_ns' prototype
 from <linux/sched.h>

pid.h already defines it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 905d4f148d65..057b2a85ecc7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1301,8 +1301,6 @@ static inline struct thread_info *task_thread_info(struct task_struct *task)
 # define task_thread_info(task)	((struct thread_info *)(task)->stack)
 #endif
 
-extern struct pid_namespace init_pid_ns;
-
 /*
  * find a task by one of its numerical ids
  *
-- 
GitLab


From b68070e146b9c2b4ece8d869a4fab9a4f14bbfb4 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 4 Feb 2017 01:27:20 +0100
Subject: [PATCH 658/898] sched/headers: Remove <linux/rculist.h> from
 <linux/sched.h>

We don't actually need the full rculist.h header anymore, include
the smaller rcupdate.h header instead.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 057b2a85ecc7..5720d11f3224 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -14,7 +14,7 @@
 #include <linux/signal_types.h>
 #include <linux/pid.h>
 #include <linux/seccomp.h>
-#include <linux/rculist.h>
+#include <linux/rcupdate.h>
 
 #include <linux/resource.h>
 #include <linux/hrtimer.h>
-- 
GitLab


From 2c873d55cd838deef8218b6d5fe9bd336cb3113a Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 12:11:03 +0100
Subject: [PATCH 659/898] sched/core: Remove unused prefetch_stack()

prefetch_stack() is defined by IA64, but not actually used anywhere anymore.

Remove it.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/ia64/include/asm/processor.h |  2 --
 arch/ia64/kernel/entry.S          | 23 -----------------------
 include/linux/sched.h             |  6 ------
 3 files changed, 31 deletions(-)

diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 03911a336406..26a63d69c599 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -19,8 +19,6 @@
 #include <asm/ptrace.h>
 #include <asm/ustack.h>
 
-#define ARCH_HAS_PREFETCH_SWITCH_STACK
-
 #define IA64_NUM_PHYS_STACK_REG	96
 #define IA64_NUM_DBG_REGS	8
 
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 6f27a663177c..e7a716b09350 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -455,29 +455,6 @@ GLOBAL_ENTRY(load_switch_stack)
 	br.cond.sptk.many b7
 END(load_switch_stack)
 
-GLOBAL_ENTRY(prefetch_stack)
-	add r14 = -IA64_SWITCH_STACK_SIZE, sp
-	add r15 = IA64_TASK_THREAD_KSP_OFFSET, in0
-	;;
-	ld8 r16 = [r15]				// load next's stack pointer
-	lfetch.fault.excl [r14], 128
-	;;
-	lfetch.fault.excl [r14], 128
-	lfetch.fault [r16], 128
-	;;
-	lfetch.fault.excl [r14], 128
-	lfetch.fault [r16], 128
-	;;
-	lfetch.fault.excl [r14], 128
-	lfetch.fault [r16], 128
-	;;
-	lfetch.fault.excl [r14], 128
-	lfetch.fault [r16], 128
-	;;
-	lfetch.fault [r16], 128
-	br.ret.sptk.many rp
-END(prefetch_stack)
-
 	/*
 	 * Invoke a system call, but do some tracing before and after the call.
 	 * We MUST preserve the current register frame throughout this routine
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5720d11f3224..bd0111a06aa2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -247,12 +247,6 @@ struct sched_info {
 # define SCHED_FIXEDPOINT_SHIFT	10
 # define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)
 
-#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
-extern void prefetch_stack(struct task_struct *t);
-#else
-static inline void prefetch_stack(struct task_struct *t) { }
-#endif
-
 struct load_weight {
 	unsigned long weight;
 	u32 inv_weight;
-- 
GitLab


From 5c0d0f36414f9f8a292b42e797f9284b127d79c2 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 8 Feb 2017 18:51:59 +0100
Subject: [PATCH 660/898] sched/headers: Remove <linux/sched.h> from
 <linux/sched/init.h>

The <linux/sched/init.h> file is a self-contained header and users of
it either don't need <linux/sched.h> - or have already included it.

This reduces the size of the header dependency graph.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/init.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/sched/init.h b/include/linux/sched/init.h
index f31d16075857..127215045285 100644
--- a/include/linux/sched/init.h
+++ b/include/linux/sched/init.h
@@ -1,8 +1,6 @@
 #ifndef _LINUX_SCHED_INIT_H
 #define _LINUX_SCHED_INIT_H
 
-#include <linux/sched.h>
-
 /*
  * Scheduler init related prototypes:
  */
-- 
GitLab


From 50ff9d130014f7b19541dbf607a615a72b75b778 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 5 Feb 2017 16:03:58 +0100
Subject: [PATCH 661/898] sched/headers: Remove <linux/magic.h> from
 <linux/sched/task_stack.h>

It's not used by any of the scheduler methods, but <linux/sched/task_stack.h>
needs it to pick up STACK_END_MAGIC.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h     | 1 -
 kernel/cgroup/cgroup-v1.c | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index bd0111a06aa2..559be4f1aee5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -22,7 +22,6 @@
 #include <linux/task_io_accounting.h>
 #include <linux/latencytop.h>
 #include <linux/topology.h>
-#include <linux/magic.h>
 
 #include <asm/current.h>
 
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index abc585858685..56eba9caa632 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
+#include <linux/magic.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/delayacct.h>
-- 
GitLab


From b2d5bfea2d00a0000da18f7667c2b0e2c2f168d9 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 09:56:40 +0100
Subject: [PATCH 662/898] sched/headers, timers: Remove the <linux/sysctl.h>
 include from <linux/timer.h>

So we want to simplify <linux/sched.h>'s header dependencies, but one
roadblock of that is <linux/timer.h>'s inclusion of sysctl.h,
which brings in other, problematic headers.

Note that timer.h's inclusion of sysctl.h can be avoided if we
pre-declare ctl_table - so do that.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/timer.h          | 2 +-
 include/linux/user_namespace.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/timer.h b/include/linux/timer.h
index c7bdf895179c..e6789b8757d5 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -212,7 +212,7 @@ struct hrtimer;
 extern enum hrtimer_restart it_real_fn(struct hrtimer *);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-#include <linux/sysctl.h>
+struct ctl_table;
 
 extern unsigned int sysctl_timer_migration;
 int timer_migration_handler(struct ctl_table *table, int write,
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index faa9bfb827da..be765234c0a2 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -5,6 +5,7 @@
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/sched.h>
+#include <linux/workqueue.h>
 #include <linux/rwsem.h>
 #include <linux/sysctl.h>
 #include <linux/err.h>
-- 
GitLab


From 1a79a72c65b8f1b4f44e166d1fb5cad560461b26 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 09:58:35 +0100
Subject: [PATCH 663/898] sched/headers, x86/apic: Remove the <linux/pm.h>
 header inclusion from <asm/apic.h>

We want to simplify <linux/sched.h>'s header dependencies, but one
roadblock to that is <asm/apic.h>'s inclusion of pm.h,
which brings in other, problematic headers.

Remove it, as it appears to be entirely spurious, apic.h does not
actually make use of any PM facilities.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/apic.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index eff8e36aaf72..730ef65e8393 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_APIC_H
 
 #include <linux/cpumask.h>
-#include <linux/pm.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
-- 
GitLab


From 283cb90305cf1686594ed537c7a8cb188eba1a4d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 09:59:47 +0100
Subject: [PATCH 664/898] sched/headers, hrtimer: Remove the <linux/wait.h>
 include from <linux/hrtimer.h>

In our quest to simplify <linux/sched.h>'s header dependencies, remove
the <linux/wait.h> inclusion from <linux/hrtimer.h> - which does
not appear to be necessary, as hrtimer.h does not use waitqueues.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/hrtimer.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index e52b427223ba..249e579ecd4c 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -19,7 +19,6 @@
 #include <linux/ktime.h>
 #include <linux/init.h>
 #include <linux/list.h>
-#include <linux/wait.h>
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <linux/timerqueue.h>
-- 
GitLab


From ee6a3d19f15b9b10075481088b8d4537f286d7b4 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 10:01:09 +0100
Subject: [PATCH 665/898] sched/headers: Remove the <linux/topology.h> include
 from <linux/sched.h>

It's used only by a single (rarely used) inline function (task_node(p)),
which we can move to <linux/sched/topology.h>.

( Add <linux/nodemask.h>, because we rely on that. )

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/sgi-ip27/ip27-smp.c  | 1 +
 include/linux/sched.h          | 7 +------
 include/linux/sched/topology.h | 7 +++++++
 3 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index f9ae6a8fa7c7..f5ed45e8f442 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -8,6 +8,7 @@
  */
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/topology.h>
 #include <linux/nodemask.h>
 #include <asm/page.h>
 #include <asm/processor.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 559be4f1aee5..f9dc9cfaf079 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -4,6 +4,7 @@
 #include <uapi/linux/sched.h>
 
 #include <linux/sched/prio.h>
+#include <linux/nodemask.h>
 
 #include <linux/mutex.h>
 #include <linux/plist.h>
@@ -21,7 +22,6 @@
 #include <linux/kcov.h>
 #include <linux/task_io_accounting.h>
 #include <linux/latencytop.h>
-#include <linux/topology.h>
 
 #include <asm/current.h>
 
@@ -1454,11 +1454,6 @@ static inline unsigned int task_cpu(const struct task_struct *p)
 #endif
 }
 
-static inline int task_node(const struct task_struct *p)
-{
-	return cpu_to_node(task_cpu(p));
-}
-
 extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
 
 #else
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 0d6fceff37bb..7d065abc7a47 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_SCHED_TOPOLOGY_H
 #define _LINUX_SCHED_TOPOLOGY_H
 
+#include <linux/topology.h>
+
 #include <linux/sched/idle.h>
 
 /*
@@ -216,4 +218,9 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 
 #endif	/* !CONFIG_SMP */
 
+static inline int task_node(const struct task_struct *p)
+{
+	return cpu_to_node(task_cpu(p));
+}
+
 #endif /* _LINUX_SCHED_TOPOLOGY_H */
-- 
GitLab


From 7f5f8e8d97d77edf33f2836259d1f19c6f4d94f5 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 11:44:12 +0100
Subject: [PATCH 666/898] sched/headers: Remove #ifdefs from <linux/sched.h>

We can remove two pairs of #ifdefs by defining structures in a smarter way.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index f9dc9cfaf079..341f5792fbe0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -224,8 +224,8 @@ struct task_cputime {
 #define prof_exp	stime
 #define sched_exp	sum_exec_runtime
 
-#ifdef CONFIG_SCHED_INFO
 struct sched_info {
+#ifdef CONFIG_SCHED_INFO
 	/* cumulative counters */
 	unsigned long pcount;	      /* # of times run on this cpu */
 	unsigned long long run_delay; /* time spent waiting on a runqueue */
@@ -233,8 +233,8 @@ struct sched_info {
 	/* timestamps */
 	unsigned long long last_arrival,/* when we last ran on a cpu */
 			   last_queued;	/* when we were last queued to run */
-};
 #endif /* CONFIG_SCHED_INFO */
+};
 
 /*
  * Integer metrics need fixed point arithmetic, e.g., sched/fair
@@ -309,8 +309,8 @@ struct sched_avg {
 	unsigned long load_avg, util_avg;
 };
 
-#ifdef CONFIG_SCHEDSTATS
 struct sched_statistics {
+#ifdef CONFIG_SCHEDSTATS
 	u64			wait_start;
 	u64			wait_max;
 	u64			wait_count;
@@ -342,8 +342,8 @@ struct sched_statistics {
 	u64			nr_wakeups_affine_attempts;
 	u64			nr_wakeups_passive;
 	u64			nr_wakeups_idle;
-};
 #endif
+};
 
 struct sched_entity {
 	struct load_weight	load;		/* for load-balancing */
@@ -358,9 +358,7 @@ struct sched_entity {
 
 	u64			nr_migrations;
 
-#ifdef CONFIG_SCHEDSTATS
 	struct sched_statistics statistics;
-#endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	int			depth;
@@ -530,9 +528,7 @@ struct task_struct {
 	int rcu_tasks_idle_cpu;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
-#ifdef CONFIG_SCHED_INFO
 	struct sched_info sched_info;
-#endif
 
 	struct list_head tasks;
 #ifdef CONFIG_SMP
-- 
GitLab


From 5eca1c10cbaa9c366c18ca79f81f21c731e3dcc7 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 6 Feb 2017 22:06:35 +0100
Subject: [PATCH 667/898] sched/headers: Clean up <linux/sched.h>

Now that <linux/sched.h> dependencies have been sorted out,
do various trivial cleanups:

 - remove unnecessary structure predeclarations
 - fix various typos
 - update comments where necessary
 - remove pointless comments
 - use consistent types
 - tabulate consistently
 - use a consistent comment style
 - clean up the header section a bit
 - use a consistent style of a single field per line
 - remove line-breaks where they make the code look worse
 - etc ...

No change in functionality.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 1222 ++++++++++++++++++++++-------------------
 1 file changed, 651 insertions(+), 571 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 341f5792fbe0..d67eee84fd43 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1,38 +1,38 @@
 #ifndef _LINUX_SCHED_H
 #define _LINUX_SCHED_H
 
-#include <uapi/linux/sched.h>
+/*
+ * Define 'struct task_struct' and provide the main scheduler
+ * APIs (schedule(), wakeup variants, etc.)
+ */
 
-#include <linux/sched/prio.h>
-#include <linux/nodemask.h>
+#include <uapi/linux/sched.h>
 
-#include <linux/mutex.h>
-#include <linux/plist.h>
-#include <linux/mm_types_task.h>
+#include <asm/current.h>
 
+#include <linux/pid.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
-#include <linux/signal_types.h>
-#include <linux/pid.h>
+#include <linux/kcov.h>
+#include <linux/mutex.h>
+#include <linux/plist.h>
+#include <linux/hrtimer.h>
 #include <linux/seccomp.h>
+#include <linux/nodemask.h>
 #include <linux/rcupdate.h>
-
 #include <linux/resource.h>
-#include <linux/hrtimer.h>
-#include <linux/kcov.h>
-#include <linux/task_io_accounting.h>
 #include <linux/latencytop.h>
+#include <linux/sched/prio.h>
+#include <linux/signal_types.h>
+#include <linux/mm_types_task.h>
+#include <linux/task_io_accounting.h>
 
-#include <asm/current.h>
-
-/* task_struct member predeclarations: */
+/* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
-struct autogroup;
 struct backing_dev_info;
 struct bio_list;
 struct blk_plug;
 struct cfs_rq;
-struct filename;
 struct fs_struct;
 struct futex_pi_state;
 struct io_context;
@@ -52,8 +52,6 @@ struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
-struct task_struct;
-struct uts_namespace;
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -65,50 +63,53 @@ struct uts_namespace;
  * modifying one set can't modify the other one by
  * mistake.
  */
-#define TASK_RUNNING		0
-#define TASK_INTERRUPTIBLE	1
-#define TASK_UNINTERRUPTIBLE	2
-#define __TASK_STOPPED		4
-#define __TASK_TRACED		8
-/* in tsk->exit_state */
-#define EXIT_DEAD		16
-#define EXIT_ZOMBIE		32
-#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
-/* in tsk->state again */
-#define TASK_DEAD		64
-#define TASK_WAKEKILL		128
-#define TASK_WAKING		256
-#define TASK_PARKED		512
-#define TASK_NOLOAD		1024
-#define TASK_NEW		2048
-#define TASK_STATE_MAX		4096
-
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn"
-
-/* Convenience macros for the sake of set_current_state */
-#define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
-#define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
-#define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
-
-#define TASK_IDLE		(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
-
-/* Convenience macros for the sake of wake_up */
-#define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
-#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
-
-/* get_task_state() */
-#define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
-				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
-				 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
-
-#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
-#define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
-#define task_is_stopped_or_traced(task)	\
-			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
-#define task_contributes_to_load(task)	\
-				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-				 (task->flags & PF_FROZEN) == 0 && \
-				 (task->state & TASK_NOLOAD) == 0)
+
+/* Used in tsk->state: */
+#define TASK_RUNNING			0
+#define TASK_INTERRUPTIBLE		1
+#define TASK_UNINTERRUPTIBLE		2
+#define __TASK_STOPPED			4
+#define __TASK_TRACED			8
+/* Used in tsk->exit_state: */
+#define EXIT_DEAD			16
+#define EXIT_ZOMBIE			32
+#define EXIT_TRACE			(EXIT_ZOMBIE | EXIT_DEAD)
+/* Used in tsk->state again: */
+#define TASK_DEAD			64
+#define TASK_WAKEKILL			128
+#define TASK_WAKING			256
+#define TASK_PARKED			512
+#define TASK_NOLOAD			1024
+#define TASK_NEW			2048
+#define TASK_STATE_MAX			4096
+
+#define TASK_STATE_TO_CHAR_STR		"RSDTtXZxKWPNn"
+
+/* Convenience macros for the sake of set_current_state: */
+#define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
+#define TASK_STOPPED			(TASK_WAKEKILL | __TASK_STOPPED)
+#define TASK_TRACED			(TASK_WAKEKILL | __TASK_TRACED)
+
+#define TASK_IDLE			(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
+/* Convenience macros for the sake of wake_up(): */
+#define TASK_NORMAL			(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
+#define TASK_ALL			(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
+
+/* get_task_state(): */
+#define TASK_REPORT			(TASK_RUNNING | TASK_INTERRUPTIBLE | \
+					 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
+					 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
+
+#define task_is_traced(task)		((task->state & __TASK_TRACED) != 0)
+
+#define task_is_stopped(task)		((task->state & __TASK_STOPPED) != 0)
+
+#define task_is_stopped_or_traced(task)	((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
+
+#define task_contributes_to_load(task)	((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
+					 (task->flags & PF_FROZEN) == 0 && \
+					 (task->state & TASK_NOLOAD) == 0)
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
@@ -158,26 +159,24 @@ struct uts_namespace;
  *
  * Also see the comments of try_to_wake_up().
  */
-#define __set_current_state(state_value)		\
-	do { current->state = (state_value); } while (0)
-#define set_current_state(state_value)			\
-	smp_store_mb(current->state, (state_value))
-
+#define __set_current_state(state_value) do { current->state = (state_value); } while (0)
+#define set_current_state(state_value)	 smp_store_mb(current->state, (state_value))
 #endif
 
-/* Task command name length */
-#define TASK_COMM_LEN 16
+/* Task command name length: */
+#define TASK_COMM_LEN			16
 
-extern cpumask_var_t cpu_isolated_map;
+extern cpumask_var_t			cpu_isolated_map;
 
 extern void scheduler_tick(void);
 
-#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
-extern signed long schedule_timeout(signed long timeout);
-extern signed long schedule_timeout_interruptible(signed long timeout);
-extern signed long schedule_timeout_killable(signed long timeout);
-extern signed long schedule_timeout_uninterruptible(signed long timeout);
-extern signed long schedule_timeout_idle(signed long timeout);
+#define	MAX_SCHEDULE_TIMEOUT		LONG_MAX
+
+extern long schedule_timeout(long timeout);
+extern long schedule_timeout_interruptible(long timeout);
+extern long schedule_timeout_killable(long timeout);
+extern long schedule_timeout_uninterruptible(long timeout);
+extern long schedule_timeout_idle(long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
 
@@ -197,9 +196,9 @@ extern void io_schedule(void);
  */
 struct prev_cputime {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	u64 utime;
-	u64 stime;
-	raw_spinlock_t lock;
+	u64				utime;
+	u64				stime;
+	raw_spinlock_t			lock;
 #endif
 };
 
@@ -214,25 +213,34 @@ struct prev_cputime {
  * these counts together and treat all three of them in parallel.
  */
 struct task_cputime {
-	u64 utime;
-	u64 stime;
-	unsigned long long sum_exec_runtime;
+	u64				utime;
+	u64				stime;
+	unsigned long long		sum_exec_runtime;
 };
 
-/* Alternate field names when used to cache expirations. */
-#define virt_exp	utime
-#define prof_exp	stime
-#define sched_exp	sum_exec_runtime
+/* Alternate field names when used on cache expirations: */
+#define virt_exp			utime
+#define prof_exp			stime
+#define sched_exp			sum_exec_runtime
 
 struct sched_info {
 #ifdef CONFIG_SCHED_INFO
-	/* cumulative counters */
-	unsigned long pcount;	      /* # of times run on this cpu */
-	unsigned long long run_delay; /* time spent waiting on a runqueue */
+	/* Cumulative counters: */
+
+	/* # of times we have run on this CPU: */
+	unsigned long			pcount;
+
+	/* Time spent waiting on a runqueue: */
+	unsigned long long		run_delay;
+
+	/* Timestamps: */
+
+	/* When did we last run on a CPU? */
+	unsigned long long		last_arrival;
+
+	/* When were we last queued to run? */
+	unsigned long long		last_queued;
 
-	/* timestamps */
-	unsigned long long last_arrival,/* when we last ran on a cpu */
-			   last_queued;	/* when we were last queued to run */
 #endif /* CONFIG_SCHED_INFO */
 };
 
@@ -243,12 +251,12 @@ struct sched_info {
  * We define a basic fixed point arithmetic range, and then formalize
  * all these metrics based on that basic range.
  */
-# define SCHED_FIXEDPOINT_SHIFT	10
-# define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)
+# define SCHED_FIXEDPOINT_SHIFT		10
+# define SCHED_FIXEDPOINT_SCALE		(1L << SCHED_FIXEDPOINT_SHIFT)
 
 struct load_weight {
-	unsigned long weight;
-	u32 inv_weight;
+	unsigned long			weight;
+	u32				inv_weight;
 };
 
 /*
@@ -304,69 +312,73 @@ struct load_weight {
  * issues.
  */
 struct sched_avg {
-	u64 last_update_time, load_sum;
-	u32 util_sum, period_contrib;
-	unsigned long load_avg, util_avg;
+	u64				last_update_time;
+	u64				load_sum;
+	u32				util_sum;
+	u32				period_contrib;
+	unsigned long			load_avg;
+	unsigned long			util_avg;
 };
 
 struct sched_statistics {
 #ifdef CONFIG_SCHEDSTATS
-	u64			wait_start;
-	u64			wait_max;
-	u64			wait_count;
-	u64			wait_sum;
-	u64			iowait_count;
-	u64			iowait_sum;
-
-	u64			sleep_start;
-	u64			sleep_max;
-	s64			sum_sleep_runtime;
-
-	u64			block_start;
-	u64			block_max;
-	u64			exec_max;
-	u64			slice_max;
-
-	u64			nr_migrations_cold;
-	u64			nr_failed_migrations_affine;
-	u64			nr_failed_migrations_running;
-	u64			nr_failed_migrations_hot;
-	u64			nr_forced_migrations;
-
-	u64			nr_wakeups;
-	u64			nr_wakeups_sync;
-	u64			nr_wakeups_migrate;
-	u64			nr_wakeups_local;
-	u64			nr_wakeups_remote;
-	u64			nr_wakeups_affine;
-	u64			nr_wakeups_affine_attempts;
-	u64			nr_wakeups_passive;
-	u64			nr_wakeups_idle;
+	u64				wait_start;
+	u64				wait_max;
+	u64				wait_count;
+	u64				wait_sum;
+	u64				iowait_count;
+	u64				iowait_sum;
+
+	u64				sleep_start;
+	u64				sleep_max;
+	s64				sum_sleep_runtime;
+
+	u64				block_start;
+	u64				block_max;
+	u64				exec_max;
+	u64				slice_max;
+
+	u64				nr_migrations_cold;
+	u64				nr_failed_migrations_affine;
+	u64				nr_failed_migrations_running;
+	u64				nr_failed_migrations_hot;
+	u64				nr_forced_migrations;
+
+	u64				nr_wakeups;
+	u64				nr_wakeups_sync;
+	u64				nr_wakeups_migrate;
+	u64				nr_wakeups_local;
+	u64				nr_wakeups_remote;
+	u64				nr_wakeups_affine;
+	u64				nr_wakeups_affine_attempts;
+	u64				nr_wakeups_passive;
+	u64				nr_wakeups_idle;
 #endif
 };
 
 struct sched_entity {
-	struct load_weight	load;		/* for load-balancing */
-	struct rb_node		run_node;
-	struct list_head	group_node;
-	unsigned int		on_rq;
+	/* For load-balancing: */
+	struct load_weight		load;
+	struct rb_node			run_node;
+	struct list_head		group_node;
+	unsigned int			on_rq;
 
-	u64			exec_start;
-	u64			sum_exec_runtime;
-	u64			vruntime;
-	u64			prev_sum_exec_runtime;
+	u64				exec_start;
+	u64				sum_exec_runtime;
+	u64				vruntime;
+	u64				prev_sum_exec_runtime;
 
-	u64			nr_migrations;
+	u64				nr_migrations;
 
-	struct sched_statistics statistics;
+	struct sched_statistics		statistics;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	int			depth;
-	struct sched_entity	*parent;
+	int				depth;
+	struct sched_entity		*parent;
 	/* rq on which this entity is (to be) queued: */
-	struct cfs_rq		*cfs_rq;
+	struct cfs_rq			*cfs_rq;
 	/* rq "owned" by this entity/group: */
-	struct cfs_rq		*my_q;
+	struct cfs_rq			*my_q;
 #endif
 
 #ifdef CONFIG_SMP
@@ -376,49 +388,49 @@ struct sched_entity {
 	 * Put into separate cache line so it does not
 	 * collide with read-mostly values above.
 	 */
-	struct sched_avg	avg ____cacheline_aligned_in_smp;
+	struct sched_avg		avg ____cacheline_aligned_in_smp;
 #endif
 };
 
 struct sched_rt_entity {
-	struct list_head run_list;
-	unsigned long timeout;
-	unsigned long watchdog_stamp;
-	unsigned int time_slice;
-	unsigned short on_rq;
-	unsigned short on_list;
-
-	struct sched_rt_entity *back;
+	struct list_head		run_list;
+	unsigned long			timeout;
+	unsigned long			watchdog_stamp;
+	unsigned int			time_slice;
+	unsigned short			on_rq;
+	unsigned short			on_list;
+
+	struct sched_rt_entity		*back;
 #ifdef CONFIG_RT_GROUP_SCHED
-	struct sched_rt_entity	*parent;
+	struct sched_rt_entity		*parent;
 	/* rq on which this entity is (to be) queued: */
-	struct rt_rq		*rt_rq;
+	struct rt_rq			*rt_rq;
 	/* rq "owned" by this entity/group: */
-	struct rt_rq		*my_q;
+	struct rt_rq			*my_q;
 #endif
 };
 
 struct sched_dl_entity {
-	struct rb_node	rb_node;
+	struct rb_node			rb_node;
 
 	/*
 	 * Original scheduling parameters. Copied here from sched_attr
 	 * during sched_setattr(), they will remain the same until
 	 * the next sched_setattr().
 	 */
-	u64 dl_runtime;		/* maximum runtime for each instance	*/
-	u64 dl_deadline;	/* relative deadline of each instance	*/
-	u64 dl_period;		/* separation of two instances (period) */
-	u64 dl_bw;		/* dl_runtime / dl_deadline		*/
+	u64				dl_runtime;	/* Maximum runtime for each instance	*/
+	u64				dl_deadline;	/* Relative deadline of each instance	*/
+	u64				dl_period;	/* Separation of two instances (period) */
+	u64				dl_bw;		/* dl_runtime / dl_deadline		*/
 
 	/*
 	 * Actual scheduling parameters. Initialized with the values above,
 	 * they are continously updated during task execution. Note that
 	 * the remaining runtime could be < 0 in case we are in overrun.
 	 */
-	s64 runtime;		/* remaining runtime for this instance	*/
-	u64 deadline;		/* absolute deadline for this instance	*/
-	unsigned int flags;	/* specifying the scheduler behaviour	*/
+	s64				runtime;	/* Remaining runtime for this instance	*/
+	u64				deadline;	/* Absolute deadline for this instance	*/
+	unsigned int			flags;		/* Specifying the scheduler behaviour	*/
 
 	/*
 	 * Some bool flags:
@@ -431,24 +443,28 @@ struct sched_dl_entity {
 	 * outside bandwidth enforcement mechanism (but only until we
 	 * exit the critical section);
 	 *
-	 * @dl_yielded tells if task gave up the cpu before consuming
+	 * @dl_yielded tells if task gave up the CPU before consuming
 	 * all its available runtime during the last job.
 	 */
-	int dl_throttled, dl_boosted, dl_yielded;
+	int				dl_throttled;
+	int				dl_boosted;
+	int				dl_yielded;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
 	 * own bandwidth to be enforced, thus we need one timer per task.
 	 */
-	struct hrtimer dl_timer;
+	struct hrtimer			dl_timer;
 };
 
 union rcu_special {
 	struct {
-		u8 blocked;
-		u8 need_qs;
-		u8 exp_need_qs;
-		u8 pad;	/* Otherwise the compiler can store garbage here. */
+		u8			blocked;
+		u8			need_qs;
+		u8			exp_need_qs;
+
+		/* Otherwise the compiler can store garbage here: */
+		u8			pad;
 	} b; /* Bits. */
 	u32 s; /* Set of bits. */
 };
@@ -470,361 +486,417 @@ struct task_struct {
 	 * For reasons of header soup (see current_thread_info()), this
 	 * must be the first element of task_struct.
 	 */
-	struct thread_info thread_info;
+	struct thread_info		thread_info;
 #endif
-	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
-	void *stack;
-	atomic_t usage;
-	unsigned int flags;	/* per process flags, defined below */
-	unsigned int ptrace;
+	/* -1 unrunnable, 0 runnable, >0 stopped: */
+	volatile long			state;
+	void				*stack;
+	atomic_t			usage;
+	/* Per task flags (PF_*), defined further below: */
+	unsigned int			flags;
+	unsigned int			ptrace;
 
 #ifdef CONFIG_SMP
-	struct llist_node wake_entry;
-	int on_cpu;
+	struct llist_node		wake_entry;
+	int				on_cpu;
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-	unsigned int cpu;	/* current CPU */
+	/* Current CPU: */
+	unsigned int			cpu;
 #endif
-	unsigned int wakee_flips;
-	unsigned long wakee_flip_decay_ts;
-	struct task_struct *last_wakee;
+	unsigned int			wakee_flips;
+	unsigned long			wakee_flip_decay_ts;
+	struct task_struct		*last_wakee;
 
-	int wake_cpu;
+	int				wake_cpu;
 #endif
-	int on_rq;
+	int				on_rq;
+
+	int				prio;
+	int				static_prio;
+	int				normal_prio;
+	unsigned int			rt_priority;
 
-	int prio, static_prio, normal_prio;
-	unsigned int rt_priority;
-	const struct sched_class *sched_class;
-	struct sched_entity se;
-	struct sched_rt_entity rt;
+	const struct sched_class	*sched_class;
+	struct sched_entity		se;
+	struct sched_rt_entity		rt;
 #ifdef CONFIG_CGROUP_SCHED
-	struct task_group *sched_task_group;
+	struct task_group		*sched_task_group;
 #endif
-	struct sched_dl_entity dl;
+	struct sched_dl_entity		dl;
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
-	/* list of struct preempt_notifier: */
-	struct hlist_head preempt_notifiers;
+	/* List of struct preempt_notifier: */
+	struct hlist_head		preempt_notifiers;
 #endif
 
 #ifdef CONFIG_BLK_DEV_IO_TRACE
-	unsigned int btrace_seq;
+	unsigned int			btrace_seq;
 #endif
 
-	unsigned int policy;
-	int nr_cpus_allowed;
-	cpumask_t cpus_allowed;
+	unsigned int			policy;
+	int				nr_cpus_allowed;
+	cpumask_t			cpus_allowed;
 
 #ifdef CONFIG_PREEMPT_RCU
-	int rcu_read_lock_nesting;
-	union rcu_special rcu_read_unlock_special;
-	struct list_head rcu_node_entry;
-	struct rcu_node *rcu_blocked_node;
+	int				rcu_read_lock_nesting;
+	union rcu_special		rcu_read_unlock_special;
+	struct list_head		rcu_node_entry;
+	struct rcu_node			*rcu_blocked_node;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
+
 #ifdef CONFIG_TASKS_RCU
-	unsigned long rcu_tasks_nvcsw;
-	bool rcu_tasks_holdout;
-	struct list_head rcu_tasks_holdout_list;
-	int rcu_tasks_idle_cpu;
+	unsigned long			rcu_tasks_nvcsw;
+	bool				rcu_tasks_holdout;
+	struct list_head		rcu_tasks_holdout_list;
+	int				rcu_tasks_idle_cpu;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
-	struct sched_info sched_info;
+	struct sched_info		sched_info;
 
-	struct list_head tasks;
+	struct list_head		tasks;
 #ifdef CONFIG_SMP
-	struct plist_node pushable_tasks;
-	struct rb_node pushable_dl_tasks;
+	struct plist_node		pushable_tasks;
+	struct rb_node			pushable_dl_tasks;
 #endif
 
-	struct mm_struct *mm, *active_mm;
+	struct mm_struct		*mm;
+	struct mm_struct		*active_mm;
 
 	/* Per-thread vma caching: */
-	struct vmacache vmacache;
-
-#if defined(SPLIT_RSS_COUNTING)
-	struct task_rss_stat	rss_stat;
-#endif
-/* task state */
-	int exit_state;
-	int exit_code, exit_signal;
-	int pdeath_signal;  /*  The signal sent when the parent dies  */
-	unsigned long jobctl;	/* JOBCTL_*, siglock protected */
-
-	/* Used for emulating ABI behavior of previous Linux versions */
-	unsigned int personality;
-
-	/* scheduler bits, serialized by scheduler locks */
-	unsigned sched_reset_on_fork:1;
-	unsigned sched_contributes_to_load:1;
-	unsigned sched_migrated:1;
-	unsigned sched_remote_wakeup:1;
-	unsigned :0; /* force alignment to the next boundary */
-
-	/* unserialized, strictly 'current' */
-	unsigned in_execve:1; /* bit to tell LSMs we're in execve */
-	unsigned in_iowait:1;
-#if !defined(TIF_RESTORE_SIGMASK)
-	unsigned restore_sigmask:1;
+	struct vmacache			vmacache;
+
+#ifdef SPLIT_RSS_COUNTING
+	struct task_rss_stat		rss_stat;
+#endif
+	int				exit_state;
+	int				exit_code;
+	int				exit_signal;
+	/* The signal sent when the parent dies: */
+	int				pdeath_signal;
+	/* JOBCTL_*, siglock protected: */
+	unsigned long			jobctl;
+
+	/* Used for emulating ABI behavior of previous Linux versions: */
+	unsigned int			personality;
+
+	/* Scheduler bits, serialized by scheduler locks: */
+	unsigned			sched_reset_on_fork:1;
+	unsigned			sched_contributes_to_load:1;
+	unsigned			sched_migrated:1;
+	unsigned			sched_remote_wakeup:1;
+	/* Force alignment to the next boundary: */
+	unsigned			:0;
+
+	/* Unserialized, strictly 'current' */
+
+	/* Bit to tell LSMs we're in execve(): */
+	unsigned			in_execve:1;
+	unsigned			in_iowait:1;
+#ifndef TIF_RESTORE_SIGMASK
+	unsigned			restore_sigmask:1;
 #endif
 #ifdef CONFIG_MEMCG
-	unsigned memcg_may_oom:1;
+	unsigned			memcg_may_oom:1;
 #ifndef CONFIG_SLOB
-	unsigned memcg_kmem_skip_account:1;
+	unsigned			memcg_kmem_skip_account:1;
 #endif
 #endif
 #ifdef CONFIG_COMPAT_BRK
-	unsigned brk_randomized:1;
+	unsigned			brk_randomized:1;
 #endif
 
-	unsigned long atomic_flags; /* Flags needing atomic access. */
+	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
-	struct restart_block restart_block;
+	struct restart_block		restart_block;
 
-	pid_t pid;
-	pid_t tgid;
+	pid_t				pid;
+	pid_t				tgid;
 
 #ifdef CONFIG_CC_STACKPROTECTOR
-	/* Canary value for the -fstack-protector gcc feature */
-	unsigned long stack_canary;
+	/* Canary value for the -fstack-protector GCC feature: */
+	unsigned long			stack_canary;
 #endif
 	/*
-	 * pointers to (original) parent process, youngest child, younger sibling,
+	 * Pointers to the (original) parent process, youngest child, younger sibling,
 	 * older sibling, respectively.  (p->father can be replaced with
 	 * p->real_parent->pid)
 	 */
-	struct task_struct __rcu *real_parent; /* real parent process */
-	struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
+
+	/* Real parent process: */
+	struct task_struct __rcu	*real_parent;
+
+	/* Recipient of SIGCHLD, wait4() reports: */
+	struct task_struct __rcu	*parent;
+
 	/*
-	 * children/sibling forms the list of my natural children
+	 * Children/sibling form the list of natural children:
 	 */
-	struct list_head children;	/* list of my children */
-	struct list_head sibling;	/* linkage in my parent's children list */
-	struct task_struct *group_leader;	/* threadgroup leader */
+	struct list_head		children;
+	struct list_head		sibling;
+	struct task_struct		*group_leader;
 
 	/*
-	 * ptraced is the list of tasks this task is using ptrace on.
+	 * 'ptraced' is the list of tasks this task is using ptrace() on.
+	 *
 	 * This includes both natural children and PTRACE_ATTACH targets.
-	 * p->ptrace_entry is p's link on the p->parent->ptraced list.
+	 * 'ptrace_entry' is this task's link on the p->parent->ptraced list.
 	 */
-	struct list_head ptraced;
-	struct list_head ptrace_entry;
+	struct list_head		ptraced;
+	struct list_head		ptrace_entry;
 
 	/* PID/PID hash table linkage. */
-	struct pid_link pids[PIDTYPE_MAX];
-	struct list_head thread_group;
-	struct list_head thread_node;
+	struct pid_link			pids[PIDTYPE_MAX];
+	struct list_head		thread_group;
+	struct list_head		thread_node;
+
+	struct completion		*vfork_done;
 
-	struct completion *vfork_done;		/* for vfork() */
-	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
-	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */
+	/* CLONE_CHILD_SETTID: */
+	int __user			*set_child_tid;
 
-	u64 utime, stime;
+	/* CLONE_CHILD_CLEARTID: */
+	int __user			*clear_child_tid;
+
+	u64				utime;
+	u64				stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
-	u64 utimescaled, stimescaled;
+	u64				utimescaled;
+	u64				stimescaled;
 #endif
-	u64 gtime;
-	struct prev_cputime prev_cputime;
+	u64				gtime;
+	struct prev_cputime		prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqcount_t vtime_seqcount;
-	unsigned long long vtime_snap;
+	seqcount_t			vtime_seqcount;
+	unsigned long long		vtime_snap;
 	enum {
-		/* Task is sleeping or running in a CPU with VTIME inactive */
+		/* Task is sleeping or running in a CPU with VTIME inactive: */
 		VTIME_INACTIVE = 0,
-		/* Task runs in userspace in a CPU with VTIME active */
+		/* Task runs in userspace in a CPU with VTIME active: */
 		VTIME_USER,
-		/* Task runs in kernelspace in a CPU with VTIME active */
+		/* Task runs in kernelspace in a CPU with VTIME active: */
 		VTIME_SYS,
 	} vtime_snap_whence;
 #endif
 
 #ifdef CONFIG_NO_HZ_FULL
-	atomic_t tick_dep_mask;
+	atomic_t			tick_dep_mask;
 #endif
-	unsigned long nvcsw, nivcsw; /* context switch counts */
-	u64 start_time;		/* monotonic time in nsec */
-	u64 real_start_time;	/* boot based time in nsec */
-/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
-	unsigned long min_flt, maj_flt;
+	/* Context switch counts: */
+	unsigned long			nvcsw;
+	unsigned long			nivcsw;
+
+	/* Monotonic time in nsecs: */
+	u64				start_time;
+
+	/* Boot based time in nsecs: */
+	u64				real_start_time;
+
+	/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
+	unsigned long			min_flt;
+	unsigned long			maj_flt;
 
 #ifdef CONFIG_POSIX_TIMERS
-	struct task_cputime cputime_expires;
-	struct list_head cpu_timers[3];
-#endif
-
-/* process credentials */
-	const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */
-	const struct cred __rcu *real_cred; /* objective and real subjective task
-					 * credentials (COW) */
-	const struct cred __rcu *cred;	/* effective (overridable) subjective task
-					 * credentials (COW) */
-	char comm[TASK_COMM_LEN]; /* executable name excluding path
-				     - access with [gs]et_task_comm (which lock
-				       it with task_lock())
-				     - initialized normally by setup_new_exec */
-/* file system info */
-	struct nameidata *nameidata;
+	struct task_cputime		cputime_expires;
+	struct list_head		cpu_timers[3];
+#endif
+
+	/* Process credentials: */
+
+	/* Tracer's credentials at attach: */
+	const struct cred __rcu		*ptracer_cred;
+
+	/* Objective and real subjective task credentials (COW): */
+	const struct cred __rcu		*real_cred;
+
+	/* Effective (overridable) subjective task credentials (COW): */
+	const struct cred __rcu		*cred;
+
+	/*
+	 * executable name, excluding path.
+	 *
+	 * - normally initialized setup_new_exec()
+	 * - access it with [gs]et_task_comm()
+	 * - lock it with task_lock()
+	 */
+	char				comm[TASK_COMM_LEN];
+
+	struct nameidata		*nameidata;
+
 #ifdef CONFIG_SYSVIPC
-/* ipc stuff */
-	struct sysv_sem sysvsem;
-	struct sysv_shm sysvshm;
+	struct sysv_sem			sysvsem;
+	struct sysv_shm			sysvshm;
 #endif
 #ifdef CONFIG_DETECT_HUNG_TASK
-/* hung task detection */
-	unsigned long last_switch_count;
-#endif
-/* filesystem information */
-	struct fs_struct *fs;
-/* open file information */
-	struct files_struct *files;
-/* namespaces */
-	struct nsproxy *nsproxy;
-/* signal handlers */
-	struct signal_struct *signal;
-	struct sighand_struct *sighand;
-
-	sigset_t blocked, real_blocked;
-	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
-	struct sigpending pending;
-
-	unsigned long sas_ss_sp;
-	size_t sas_ss_size;
-	unsigned sas_ss_flags;
-
-	struct callback_head *task_works;
-
-	struct audit_context *audit_context;
+	unsigned long			last_switch_count;
+#endif
+	/* Filesystem information: */
+	struct fs_struct		*fs;
+
+	/* Open file information: */
+	struct files_struct		*files;
+
+	/* Namespaces: */
+	struct nsproxy			*nsproxy;
+
+	/* Signal handlers: */
+	struct signal_struct		*signal;
+	struct sighand_struct		*sighand;
+	sigset_t			blocked;
+	sigset_t			real_blocked;
+	/* Restored if set_restore_sigmask() was used: */
+	sigset_t			saved_sigmask;
+	struct sigpending		pending;
+	unsigned long			sas_ss_sp;
+	size_t				sas_ss_size;
+	unsigned int			sas_ss_flags;
+
+	struct callback_head		*task_works;
+
+	struct audit_context		*audit_context;
 #ifdef CONFIG_AUDITSYSCALL
-	kuid_t loginuid;
-	unsigned int sessionid;
+	kuid_t				loginuid;
+	unsigned int			sessionid;
 #endif
-	struct seccomp seccomp;
+	struct seccomp			seccomp;
 
-/* Thread group tracking */
-   	u32 parent_exec_id;
-   	u32 self_exec_id;
-/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
- * mempolicy */
-	spinlock_t alloc_lock;
+	/* Thread group tracking: */
+	u32				parent_exec_id;
+	u32				self_exec_id;
+
+	/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
+	spinlock_t			alloc_lock;
 
 	/* Protection of the PI data structures: */
-	raw_spinlock_t pi_lock;
+	raw_spinlock_t			pi_lock;
 
-	struct wake_q_node wake_q;
+	struct wake_q_node		wake_q;
 
 #ifdef CONFIG_RT_MUTEXES
-	/* PI waiters blocked on a rt_mutex held by this task */
-	struct rb_root pi_waiters;
-	struct rb_node *pi_waiters_leftmost;
-	/* Deadlock detection and priority inheritance handling */
-	struct rt_mutex_waiter *pi_blocked_on;
+	/* PI waiters blocked on a rt_mutex held by this task: */
+	struct rb_root			pi_waiters;
+	struct rb_node			*pi_waiters_leftmost;
+	/* Deadlock detection and priority inheritance handling: */
+	struct rt_mutex_waiter		*pi_blocked_on;
 #endif
 
 #ifdef CONFIG_DEBUG_MUTEXES
-	/* mutex deadlock detection */
-	struct mutex_waiter *blocked_on;
+	/* Mutex deadlock detection: */
+	struct mutex_waiter		*blocked_on;
 #endif
+
 #ifdef CONFIG_TRACE_IRQFLAGS
-	unsigned int irq_events;
-	unsigned long hardirq_enable_ip;
-	unsigned long hardirq_disable_ip;
-	unsigned int hardirq_enable_event;
-	unsigned int hardirq_disable_event;
-	int hardirqs_enabled;
-	int hardirq_context;
-	unsigned long softirq_disable_ip;
-	unsigned long softirq_enable_ip;
-	unsigned int softirq_disable_event;
-	unsigned int softirq_enable_event;
-	int softirqs_enabled;
-	int softirq_context;
+	unsigned int			irq_events;
+	unsigned long			hardirq_enable_ip;
+	unsigned long			hardirq_disable_ip;
+	unsigned int			hardirq_enable_event;
+	unsigned int			hardirq_disable_event;
+	int				hardirqs_enabled;
+	int				hardirq_context;
+	unsigned long			softirq_disable_ip;
+	unsigned long			softirq_enable_ip;
+	unsigned int			softirq_disable_event;
+	unsigned int			softirq_enable_event;
+	int				softirqs_enabled;
+	int				softirq_context;
 #endif
+
 #ifdef CONFIG_LOCKDEP
-# define MAX_LOCK_DEPTH 48UL
-	u64 curr_chain_key;
-	int lockdep_depth;
-	unsigned int lockdep_recursion;
-	struct held_lock held_locks[MAX_LOCK_DEPTH];
-	gfp_t lockdep_reclaim_gfp;
+# define MAX_LOCK_DEPTH			48UL
+	u64				curr_chain_key;
+	int				lockdep_depth;
+	unsigned int			lockdep_recursion;
+	struct held_lock		held_locks[MAX_LOCK_DEPTH];
+	gfp_t				lockdep_reclaim_gfp;
 #endif
+
 #ifdef CONFIG_UBSAN
-	unsigned int in_ubsan;
+	unsigned int			in_ubsan;
 #endif
 
-/* journalling filesystem info */
-	void *journal_info;
+	/* Journalling filesystem info: */
+	void				*journal_info;
 
-/* stacked block device info */
-	struct bio_list *bio_list;
+	/* Stacked block device info: */
+	struct bio_list			*bio_list;
 
 #ifdef CONFIG_BLOCK
-/* stack plugging */
-	struct blk_plug *plug;
+	/* Stack plugging: */
+	struct blk_plug			*plug;
 #endif
 
-/* VM state */
-	struct reclaim_state *reclaim_state;
+	/* VM state: */
+	struct reclaim_state		*reclaim_state;
+
+	struct backing_dev_info		*backing_dev_info;
 
-	struct backing_dev_info *backing_dev_info;
+	struct io_context		*io_context;
 
-	struct io_context *io_context;
+	/* Ptrace state: */
+	unsigned long			ptrace_message;
+	siginfo_t			*last_siginfo;
 
-	unsigned long ptrace_message;
-	siginfo_t *last_siginfo; /* For ptrace use.  */
-	struct task_io_accounting ioac;
-#if defined(CONFIG_TASK_XACCT)
-	u64 acct_rss_mem1;	/* accumulated rss usage */
-	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
-	u64 acct_timexpd;	/* stime + utime since last update */
+	struct task_io_accounting	ioac;
+#ifdef CONFIG_TASK_XACCT
+	/* Accumulated RSS usage: */
+	u64				acct_rss_mem1;
+	/* Accumulated virtual memory usage: */
+	u64				acct_vm_mem1;
+	/* stime + utime since last update: */
+	u64				acct_timexpd;
 #endif
 #ifdef CONFIG_CPUSETS
-	nodemask_t mems_allowed;	/* Protected by alloc_lock */
-	seqcount_t mems_allowed_seq;	/* Seqence no to catch updates */
-	int cpuset_mem_spread_rotor;
-	int cpuset_slab_spread_rotor;
+	/* Protected by ->alloc_lock: */
+	nodemask_t			mems_allowed;
+	/* Seqence number to catch updates: */
+	seqcount_t			mems_allowed_seq;
+	int				cpuset_mem_spread_rotor;
+	int				cpuset_slab_spread_rotor;
 #endif
 #ifdef CONFIG_CGROUPS
-	/* Control Group info protected by css_set_lock */
-	struct css_set __rcu *cgroups;
-	/* cg_list protected by css_set_lock and tsk->alloc_lock */
-	struct list_head cg_list;
+	/* Control Group info protected by css_set_lock: */
+	struct css_set __rcu		*cgroups;
+	/* cg_list protected by css_set_lock and tsk->alloc_lock: */
+	struct list_head		cg_list;
 #endif
 #ifdef CONFIG_INTEL_RDT_A
-	int closid;
+	int				closid;
 #endif
 #ifdef CONFIG_FUTEX
-	struct robust_list_head __user *robust_list;
+	struct robust_list_head __user	*robust_list;
 #ifdef CONFIG_COMPAT
 	struct compat_robust_list_head __user *compat_robust_list;
 #endif
-	struct list_head pi_state_list;
-	struct futex_pi_state *pi_state_cache;
+	struct list_head		pi_state_list;
+	struct futex_pi_state		*pi_state_cache;
 #endif
 #ifdef CONFIG_PERF_EVENTS
-	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
-	struct mutex perf_event_mutex;
-	struct list_head perf_event_list;
+	struct perf_event_context	*perf_event_ctxp[perf_nr_task_contexts];
+	struct mutex			perf_event_mutex;
+	struct list_head		perf_event_list;
 #endif
 #ifdef CONFIG_DEBUG_PREEMPT
-	unsigned long preempt_disable_ip;
+	unsigned long			preempt_disable_ip;
 #endif
 #ifdef CONFIG_NUMA
-	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
-	short il_next;
-	short pref_node_fork;
+	/* Protected by alloc_lock: */
+	struct mempolicy		*mempolicy;
+	short				il_next;
+	short				pref_node_fork;
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	int numa_scan_seq;
-	unsigned int numa_scan_period;
-	unsigned int numa_scan_period_max;
-	int numa_preferred_nid;
-	unsigned long numa_migrate_retry;
-	u64 node_stamp;			/* migration stamp  */
-	u64 last_task_numa_placement;
-	u64 last_sum_exec_runtime;
-	struct callback_head numa_work;
-
-	struct list_head numa_entry;
-	struct numa_group *numa_group;
+	int				numa_scan_seq;
+	unsigned int			numa_scan_period;
+	unsigned int			numa_scan_period_max;
+	int				numa_preferred_nid;
+	unsigned long			numa_migrate_retry;
+	/* Migration stamp: */
+	u64				node_stamp;
+	u64				last_task_numa_placement;
+	u64				last_sum_exec_runtime;
+	struct callback_head		numa_work;
+
+	struct list_head		numa_entry;
+	struct numa_group		*numa_group;
 
 	/*
 	 * numa_faults is an array split into four regions:
@@ -840,8 +912,8 @@ struct task_struct {
 	 * during the current scan window. When the scan completes, the counts
 	 * in faults_memory and faults_cpu decay and these values are copied.
 	 */
-	unsigned long *numa_faults;
-	unsigned long total_numa_faults;
+	unsigned long			*numa_faults;
+	unsigned long			total_numa_faults;
 
 	/*
 	 * numa_faults_locality tracks if faults recorded during the last
@@ -849,119 +921,132 @@ struct task_struct {
 	 * period is adapted based on the locality of the faults with different
 	 * weights depending on whether they were shared or private faults
 	 */
-	unsigned long numa_faults_locality[3];
+	unsigned long			numa_faults_locality[3];
 
-	unsigned long numa_pages_migrated;
+	unsigned long			numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
-	struct tlbflush_unmap_batch tlb_ubc;
+	struct tlbflush_unmap_batch	tlb_ubc;
 
-	struct rcu_head rcu;
+	struct rcu_head			rcu;
 
-	/*
-	 * cache last used pipe for splice
-	 */
-	struct pipe_inode_info *splice_pipe;
+	/* Cache last used pipe for splice(): */
+	struct pipe_inode_info		*splice_pipe;
 
-	struct page_frag task_frag;
+	struct page_frag		task_frag;
 
 #ifdef CONFIG_TASK_DELAY_ACCT
 	struct task_delay_info		*delays;
 #endif
 
 #ifdef CONFIG_FAULT_INJECTION
-	int make_it_fail;
+	int				make_it_fail;
 #endif
 	/*
-	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
-	 * balance_dirty_pages() for some dirty throttling pause
+	 * When (nr_dirtied >= nr_dirtied_pause), it's time to call
+	 * balance_dirty_pages() for a dirty throttling pause:
 	 */
-	int nr_dirtied;
-	int nr_dirtied_pause;
-	unsigned long dirty_paused_when; /* start of a write-and-pause period */
+	int				nr_dirtied;
+	int				nr_dirtied_pause;
+	/* Start of a write-and-pause period: */
+	unsigned long			dirty_paused_when;
 
 #ifdef CONFIG_LATENCYTOP
-	int latency_record_count;
-	struct latency_record latency_record[LT_SAVECOUNT];
+	int				latency_record_count;
+	struct latency_record		latency_record[LT_SAVECOUNT];
 #endif
 	/*
-	 * time slack values; these are used to round up poll() and
+	 * Time slack values; these are used to round up poll() and
 	 * select() etc timeout values. These are in nanoseconds.
 	 */
-	u64 timer_slack_ns;
-	u64 default_timer_slack_ns;
+	u64				timer_slack_ns;
+	u64				default_timer_slack_ns;
 
 #ifdef CONFIG_KASAN
-	unsigned int kasan_depth;
+	unsigned int			kasan_depth;
 #endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* Index of current stored address in ret_stack */
-	int curr_ret_stack;
-	/* Stack of return addresses for return function tracing */
-	struct ftrace_ret_stack	*ret_stack;
-	/* time stamp for last schedule */
-	unsigned long long ftrace_timestamp;
+	/* Index of current stored address in ret_stack: */
+	int				curr_ret_stack;
+
+	/* Stack of return addresses for return function tracing: */
+	struct ftrace_ret_stack		*ret_stack;
+
+	/* Timestamp for last schedule: */
+	unsigned long long		ftrace_timestamp;
+
 	/*
 	 * Number of functions that haven't been traced
-	 * because of depth overrun.
+	 * because of depth overrun:
 	 */
-	atomic_t trace_overrun;
-	/* Pause for the tracing */
-	atomic_t tracing_graph_pause;
+	atomic_t			trace_overrun;
+
+	/* Pause tracing: */
+	atomic_t			tracing_graph_pause;
 #endif
+
 #ifdef CONFIG_TRACING
-	/* state flags for use by tracers */
-	unsigned long trace;
-	/* bitmask and counter of trace recursion */
-	unsigned long trace_recursion;
+	/* State flags for use by tracers: */
+	unsigned long			trace;
+
+	/* Bitmask and counter of trace recursion: */
+	unsigned long			trace_recursion;
 #endif /* CONFIG_TRACING */
+
 #ifdef CONFIG_KCOV
-	/* Coverage collection mode enabled for this task (0 if disabled). */
-	enum kcov_mode kcov_mode;
-	/* Size of the kcov_area. */
-	unsigned	kcov_size;
-	/* Buffer for coverage collection. */
-	void		*kcov_area;
-	/* kcov desciptor wired with this task or NULL. */
-	struct kcov	*kcov;
+	/* Coverage collection mode enabled for this task (0 if disabled): */
+	enum kcov_mode			kcov_mode;
+
+	/* Size of the kcov_area: */
+	unsigned int			kcov_size;
+
+	/* Buffer for coverage collection: */
+	void				*kcov_area;
+
+	/* KCOV descriptor wired with this task or NULL: */
+	struct kcov			*kcov;
 #endif
+
 #ifdef CONFIG_MEMCG
-	struct mem_cgroup *memcg_in_oom;
-	gfp_t memcg_oom_gfp_mask;
-	int memcg_oom_order;
+	struct mem_cgroup		*memcg_in_oom;
+	gfp_t				memcg_oom_gfp_mask;
+	int				memcg_oom_order;
 
-	/* number of pages to reclaim on returning to userland */
-	unsigned int memcg_nr_pages_over_high;
+	/* Number of pages to reclaim on returning to userland: */
+	unsigned int			memcg_nr_pages_over_high;
 #endif
+
 #ifdef CONFIG_UPROBES
-	struct uprobe_task *utask;
+	struct uprobe_task		*utask;
 #endif
 #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
-	unsigned int	sequential_io;
-	unsigned int	sequential_io_avg;
+	unsigned int			sequential_io;
+	unsigned int			sequential_io_avg;
 #endif
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-	unsigned long	task_state_change;
+	unsigned long			task_state_change;
 #endif
-	int pagefault_disabled;
+	int				pagefault_disabled;
 #ifdef CONFIG_MMU
-	struct task_struct *oom_reaper_list;
+	struct task_struct		*oom_reaper_list;
 #endif
 #ifdef CONFIG_VMAP_STACK
-	struct vm_struct *stack_vm_area;
+	struct vm_struct		*stack_vm_area;
 #endif
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-	/* A live task holds one reference. */
-	atomic_t stack_refcount;
+	/* A live task holds one reference: */
+	atomic_t			stack_refcount;
 #endif
-/* CPU-specific state of this task */
-	struct thread_struct thread;
-/*
- * WARNING: on x86, 'thread_struct' contains a variable-sized
- * structure.  It *MUST* be at the end of 'task_struct'.
- *
- * Do not put anything below here!
- */
+	/* CPU-specific state of this task: */
+	struct thread_struct		thread;
+
+	/*
+	 * WARNING: on x86, 'thread_struct' contains a variable-sized
+	 * structure.  It *MUST* be at the end of 'task_struct'.
+	 *
+	 * Do not put anything below here!
+	 */
 };
 
 static inline struct pid *task_pid(struct task_struct *task)
@@ -975,7 +1060,7 @@ static inline struct pid *task_tgid(struct task_struct *task)
 }
 
 /*
- * Without tasklist or rcu lock it is not safe to dereference
+ * Without tasklist or RCU lock it is not safe to dereference
  * the result of task_pgrp/task_session even if task == current,
  * we can race with another thread doing sys_setsid/sys_setpgid.
  */
@@ -1002,16 +1087,14 @@ static inline struct pid *task_session(struct task_struct *task)
  *
  * see also pid_nr() etc in include/linux/pid.h
  */
-pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
-			struct pid_namespace *ns);
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
 
 static inline pid_t task_pid_nr(struct task_struct *tsk)
 {
 	return tsk->pid;
 }
 
-static inline pid_t task_pid_nr_ns(struct task_struct *tsk,
-					struct pid_namespace *ns)
+static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
 	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
 }
@@ -1027,15 +1110,28 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk)
 	return tsk->tgid;
 }
 
-pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
+extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
 
 static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 {
 	return pid_vnr(task_tgid(tsk));
 }
 
+/**
+ * pid_alive - check that a task structure is not stale
+ * @p: Task structure to be checked.
+ *
+ * Test if a process is not yet dead (at most zombie state)
+ * If pid_alive fails, then pointers within the task structure
+ * can be stale and must not be dereferenced.
+ *
+ * Return: 1 if the process is alive. 0 otherwise.
+ */
+static inline int pid_alive(const struct task_struct *p)
+{
+	return p->pids[PIDTYPE_PID].pid != NULL;
+}
 
-static inline int pid_alive(const struct task_struct *p);
 static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
 {
 	pid_t pid = 0;
@@ -1053,8 +1149,7 @@ static inline pid_t task_ppid_nr(const struct task_struct *tsk)
 	return task_ppid_nr_ns(tsk, &init_pid_ns);
 }
 
-static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
-					struct pid_namespace *ns)
+static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
 	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
 }
@@ -1065,8 +1160,7 @@ static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
 }
 
 
-static inline pid_t task_session_nr_ns(struct task_struct *tsk,
-					struct pid_namespace *ns)
+static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
 	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
 }
@@ -1076,27 +1170,12 @@ static inline pid_t task_session_vnr(struct task_struct *tsk)
 	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
 }
 
-/* obsolete, do not use */
+/* Obsolete, do not use: */
 static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 {
 	return task_pgrp_nr_ns(tsk, &init_pid_ns);
 }
 
-/**
- * pid_alive - check that a task structure is not stale
- * @p: Task structure to be checked.
- *
- * Test if a process is not yet dead (at most zombie state)
- * If pid_alive fails, then pointers within the task structure
- * can be stale and must not be dereferenced.
- *
- * Return: 1 if the process is alive. 0 otherwise.
- */
-static inline int pid_alive(const struct task_struct *p)
-{
-	return p->pids[PIDTYPE_PID].pid != NULL;
-}
-
 /**
  * is_global_init - check if a task structure is init. Since init
  * is free to have sub-threads we need to check tgid.
@@ -1116,34 +1195,34 @@ extern struct pid *cad_pid;
 /*
  * Per process flags
  */
-#define PF_IDLE		0x00000002	/* I am an IDLE thread */
-#define PF_EXITING	0x00000004	/* getting shut down */
-#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
-#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
-#define PF_WQ_WORKER	0x00000020	/* I'm a workqueue worker */
-#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
-#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
-#define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
-#define PF_DUMPCORE	0x00000200	/* dumped core */
-#define PF_SIGNALED	0x00000400	/* killed by a signal */
-#define PF_MEMALLOC	0x00000800	/* Allocating memory */
-#define PF_NPROC_EXCEEDED 0x00001000	/* set_user noticed that RLIMIT_NPROC was exceeded */
-#define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
-#define PF_USED_ASYNC	0x00004000	/* used async_schedule*(), used by module init */
-#define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
-#define PF_FROZEN	0x00010000	/* frozen for system suspend */
-#define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
-#define PF_KSWAPD	0x00040000	/* I am kswapd */
-#define PF_MEMALLOC_NOIO 0x00080000	/* Allocating memory without IO involved */
-#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
-#define PF_KTHREAD	0x00200000	/* I am a kernel thread */
-#define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */
-#define PF_SWAPWRITE	0x00800000	/* Allowed to write to swap */
-#define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
-#define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
-#define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
-#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
-#define PF_SUSPEND_TASK 0x80000000      /* this thread called freeze_processes and should not be frozen */
+#define PF_IDLE			0x00000002	/* I am an IDLE thread */
+#define PF_EXITING		0x00000004	/* Getting shut down */
+#define PF_EXITPIDONE		0x00000008	/* PI exit done on shut down */
+#define PF_VCPU			0x00000010	/* I'm a virtual CPU */
+#define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
+#define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */
+#define PF_MCE_PROCESS		0x00000080      /* Process policy on mce errors */
+#define PF_SUPERPRIV		0x00000100	/* Used super-user privileges */
+#define PF_DUMPCORE		0x00000200	/* Dumped core */
+#define PF_SIGNALED		0x00000400	/* Killed by a signal */
+#define PF_MEMALLOC		0x00000800	/* Allocating memory */
+#define PF_NPROC_EXCEEDED	0x00001000	/* set_user() noticed that RLIMIT_NPROC was exceeded */
+#define PF_USED_MATH		0x00002000	/* If unset the fpu must be initialized before use */
+#define PF_USED_ASYNC		0x00004000	/* Used async_schedule*(), used by module init */
+#define PF_NOFREEZE		0x00008000	/* This thread should not be frozen */
+#define PF_FROZEN		0x00010000	/* Frozen for system suspend */
+#define PF_FSTRANS		0x00020000	/* Inside a filesystem transaction */
+#define PF_KSWAPD		0x00040000	/* I am kswapd */
+#define PF_MEMALLOC_NOIO	0x00080000	/* Allocating memory without IO involved */
+#define PF_LESS_THROTTLE	0x00100000	/* Throttle me less: I clean memory */
+#define PF_KTHREAD		0x00200000	/* I am a kernel thread */
+#define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
+#define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
+#define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
+#define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
+#define PF_MUTEX_TESTER		0x20000000	/* Thread belongs to the rt mutex tester */
+#define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
+#define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
 /*
  * Only the _current_ task can read/write to tsk->flags, but other
@@ -1156,33 +1235,38 @@ extern struct pid *cad_pid;
  * child is not running and in turn not changing child->flags
  * at the same time the parent does it.
  */
-#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0)
-#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0)
-#define clear_used_math() clear_stopped_child_used_math(current)
-#define set_used_math() set_stopped_child_used_math(current)
+#define clear_stopped_child_used_math(child)	do { (child)->flags &= ~PF_USED_MATH; } while (0)
+#define set_stopped_child_used_math(child)	do { (child)->flags |= PF_USED_MATH; } while (0)
+#define clear_used_math()			clear_stopped_child_used_math(current)
+#define set_used_math()				set_stopped_child_used_math(current)
+
 #define conditional_stopped_child_used_math(condition, child) \
 	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
-#define conditional_used_math(condition) \
-	conditional_stopped_child_used_math(condition, current)
+
+#define conditional_used_math(condition)	conditional_stopped_child_used_math(condition, current)
+
 #define copy_to_stopped_child_used_math(child) \
 	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
+
 /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
-#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
-#define used_math() tsk_used_math(current)
+#define tsk_used_math(p)			((p)->flags & PF_USED_MATH)
+#define used_math()				tsk_used_math(current)
 
 /* Per-process atomic flags. */
-#define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */
-#define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */
-#define PFA_SPREAD_SLAB  2      /* Spread some slab caches over cpuset */
-#define PFA_LMK_WAITING  3      /* Lowmemorykiller is waiting */
+#define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
+#define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
+#define PFA_SPREAD_SLAB			2	/* Spread some slab caches over cpuset */
+#define PFA_LMK_WAITING			3	/* Lowmemorykiller is waiting */
 
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
 	{ return test_bit(PFA_##name, &p->atomic_flags); }
+
 #define TASK_PFA_SET(name, func)					\
 	static inline void task_set_##func(struct task_struct *p)	\
 	{ set_bit(PFA_##name, &p->atomic_flags); }
+
 #define TASK_PFA_CLEAR(name, func)					\
 	static inline void task_clear_##func(struct task_struct *p)	\
 	{ clear_bit(PFA_##name, &p->atomic_flags); }
@@ -1201,30 +1285,23 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 TASK_PFA_TEST(LMK_WAITING, lmk_waiting)
 TASK_PFA_SET(LMK_WAITING, lmk_waiting)
 
-static inline void tsk_restore_flags(struct task_struct *task,
-				unsigned long orig_flags, unsigned long flags)
+static inline void
+tsk_restore_flags(struct task_struct *task, unsigned long orig_flags, unsigned long flags)
 {
 	task->flags &= ~flags;
 	task->flags |= orig_flags & flags;
 }
 
-extern int cpuset_cpumask_can_shrink(const struct cpumask *cur,
-				     const struct cpumask *trial);
-extern int task_can_attach(struct task_struct *p,
-			   const struct cpumask *cs_cpus_allowed);
+extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
+extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
 #ifdef CONFIG_SMP
-extern void do_set_cpus_allowed(struct task_struct *p,
-			       const struct cpumask *new_mask);
-
-extern int set_cpus_allowed_ptr(struct task_struct *p,
-				const struct cpumask *new_mask);
+extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
+extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
 #else
-static inline void do_set_cpus_allowed(struct task_struct *p,
-				      const struct cpumask *new_mask)
+static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
 }
-static inline int set_cpus_allowed_ptr(struct task_struct *p,
-				       const struct cpumask *new_mask)
+static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
 	if (!cpumask_test_cpu(0, new_mask))
 		return -EINVAL;
@@ -1239,6 +1316,7 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
+
 /**
  * task_nice - return the nice value of a given task.
  * @p: the task in question.
@@ -1249,16 +1327,15 @@ static inline int task_nice(const struct task_struct *p)
 {
 	return PRIO_TO_NICE((p)->static_prio);
 }
+
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
-extern int sched_setscheduler(struct task_struct *, int,
-			      const struct sched_param *);
-extern int sched_setscheduler_nocheck(struct task_struct *, int,
-				      const struct sched_param *);
-extern int sched_setattr(struct task_struct *,
-			 const struct sched_attr *);
+extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
+extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
+extern int sched_setattr(struct task_struct *, const struct sched_attr *);
 extern struct task_struct *idle_task(int cpu);
+
 /**
  * is_idle_task - is the specified task an idle task?
  * @p: the task in question.
@@ -1269,6 +1346,7 @@ static inline bool is_idle_task(const struct task_struct *p)
 {
 	return !!(p->flags & PF_IDLE);
 }
+
 extern struct task_struct *curr_task(int cpu);
 extern void ia64_set_curr_task(int cpu, struct task_struct *p);
 
@@ -1302,23 +1380,25 @@ static inline struct thread_info *task_thread_info(struct task_struct *task)
  */
 
 extern struct task_struct *find_task_by_vpid(pid_t nr);
-extern struct task_struct *find_task_by_pid_ns(pid_t nr,
-		struct pid_namespace *ns);
+extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
+
 #ifdef CONFIG_SMP
- extern void kick_process(struct task_struct *tsk);
+extern void kick_process(struct task_struct *tsk);
 #else
- static inline void kick_process(struct task_struct *tsk) { }
+static inline void kick_process(struct task_struct *tsk) { }
 #endif
 
 extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
+
 static inline void set_task_comm(struct task_struct *tsk, const char *from)
 {
 	__set_task_comm(tsk, from, false);
 }
+
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
@@ -1326,15 +1406,15 @@ void scheduler_ipi(void);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
 static inline void scheduler_ipi(void) { }
-static inline unsigned long wait_task_inactive(struct task_struct *p,
-					       long match_state)
+static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 {
 	return 1;
 }
 #endif
 
-/* set thread flags in other task's structures
- * - see asm/thread_info.h for TIF_xxxx flags available
+/*
+ * Set thread flags in other task's structures.
+ * See asm/thread_info.h for TIF_xxxx flags available:
  */
 static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
-- 
GitLab


From d3aa9c9f212a729e46653d4c1eb6a9ab190efe3a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 15 Dec 2016 15:20:34 +0100
Subject: [PATCH 668/898] ixgbe: update the rss key on h/w, when ethtool ask
 for it

Currently ixgbe_set_rxfh() updates the rss_key copy in the driver
memory, but does not push the new value into the h/w. This commit
add a new helper for the latter operation and call it in
ixgbe_set_rxfh(), so that the h/w rss key value can be really
updated via ethtool.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h      |  1 +
 .../net/ethernet/intel/ixgbe/ixgbe_ethtool.c  |  4 +++-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 19 ++++++++++++++++---
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index a2cc43d28888..7a951b116821 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -929,6 +929,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 				  struct ixgbe_adapter *adapter,
 				  struct ixgbe_ring *tx_ring);
 u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter);
+void ixgbe_store_key(struct ixgbe_adapter *adapter);
 void ixgbe_store_reta(struct ixgbe_adapter *adapter);
 s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
 		       u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index a7574c7b12af..90fa5bf23d1b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2998,8 +2998,10 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
 	}
 
 	/* Fill out the rss hash key */
-	if (key)
+	if (key) {
 		memcpy(adapter->rss_key, key, ixgbe_get_rxfh_key_size(netdev));
+		ixgbe_store_key(adapter);
+	}
 
 	ixgbe_store_reta(adapter);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 060cdce8058f..67ab13fd163c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3473,6 +3473,21 @@ u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter)
 		return 512;
 }
 
+/**
+ * ixgbe_store_key - Write the RSS key to HW
+ * @adapter: device handle
+ *
+ * Write the RSS key stored in adapter.rss_key to HW.
+ */
+void ixgbe_store_key(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i;
+
+	for (i = 0; i < 10; i++)
+		IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), adapter->rss_key[i]);
+}
+
 /**
  * ixgbe_store_reta - Write the RETA table to HW
  * @adapter: device handle
@@ -3538,7 +3553,6 @@ static void ixgbe_store_vfreta(struct ixgbe_adapter *adapter)
 
 static void ixgbe_setup_reta(struct ixgbe_adapter *adapter)
 {
-	struct ixgbe_hw *hw = &adapter->hw;
 	u32 i, j;
 	u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
 	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
@@ -3551,8 +3565,7 @@ static void ixgbe_setup_reta(struct ixgbe_adapter *adapter)
 		rss_i = 4;
 
 	/* Fill out hash function seeds */
-	for (i = 0; i < 10; i++)
-		IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), adapter->rss_key[i]);
+	ixgbe_store_key(adapter);
 
 	/* Fill out redirection table */
 	memset(adapter->rss_indir_tbl, 0, sizeof(adapter->rss_indir_tbl));
-- 
GitLab


From a528d35e8bfcc521d7cb70aaf03e1bd296c8493f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 31 Jan 2017 16:46:22 +0000
Subject: [PATCH 669/898] statx: Add a system call to make enhanced file info
 available

Add a system call to make extended file information available, including
file creation and some attribute flags where available through the
underlying filesystem.

The getattr inode operation is altered to take two additional arguments: a
u32 request_mask and an unsigned int flags that indicate the
synchronisation mode.  This change is propagated to the vfs_getattr*()
function.

Functions like vfs_stat() are now inline wrappers around new functions
vfs_statx() and vfs_statx_fd() to reduce stack usage.

========
OVERVIEW
========

The idea was initially proposed as a set of xattrs that could be retrieved
with getxattr(), but the general preference proved to be for a new syscall
with an extended stat structure.

A number of requests were gathered for features to be included.  The
following have been included:

 (1) Make the fields a consistent size on all arches and make them large.

 (2) Spare space, request flags and information flags are provided for
     future expansion.

 (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an
     __s64).

 (4) Creation time: The SMB protocol carries the creation time, which could
     be exported by Samba, which will in turn help CIFS make use of
     FS-Cache as that can be used for coherency data (stx_btime).

     This is also specified in NFSv4 as a recommended attribute and could
     be exported by NFSD [Steve French].

 (5) Lightweight stat: Ask for just those details of interest, and allow a
     netfs (such as NFS) to approximate anything not of interest, possibly
     without going to the server [Trond Myklebust, Ulrich Drepper, Andreas
     Dilger] (AT_STATX_DONT_SYNC).

 (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks
     its cached attributes are up to date [Trond Myklebust]
     (AT_STATX_FORCE_SYNC).

And the following have been left out for future extension:

 (7) Data version number: Could be used by userspace NFS servers [Aneesh
     Kumar].

     Can also be used to modify fill_post_wcc() in NFSD which retrieves
     i_version directly, but has just called vfs_getattr().  It could get
     it from the kstat struct if it used vfs_xgetattr() instead.

     (There's disagreement on the exact semantics of a single field, since
     not all filesystems do this the same way).

 (8) BSD stat compatibility: Including more fields from the BSD stat such
     as creation time (st_btime) and inode generation number (st_gen)
     [Jeremy Allison, Bernd Schubert].

 (9) Inode generation number: Useful for FUSE and userspace NFS servers
     [Bernd Schubert].

     (This was asked for but later deemed unnecessary with the
     open-by-handle capability available and caused disagreement as to
     whether it's a security hole or not).

(10) Extra coherency data may be useful in making backups [Andreas Dilger].

     (No particular data were offered, but things like last backup
     timestamp, the data version number and the DOS archive bit would come
     into this category).

(11) Allow the filesystem to indicate what it can/cannot provide: A
     filesystem can now say it doesn't support a standard stat feature if
     that isn't available, so if, for instance, inode numbers or UIDs don't
     exist or are fabricated locally...

     (This requires a separate system call - I have an fsinfo() call idea
     for this).

(12) Store a 16-byte volume ID in the superblock that can be returned in
     struct xstat [Steve French].

     (Deferred to fsinfo).

(13) Include granularity fields in the time data to indicate the
     granularity of each of the times (NFSv4 time_delta) [Steve French].

     (Deferred to fsinfo).

(14) FS_IOC_GETFLAGS value.  These could be translated to BSD's st_flags.
     Note that the Linux IOC flags are a mess and filesystems such as Ext4
     define flags that aren't in linux/fs.h, so translation in the kernel
     may be a necessity (or, possibly, we provide the filesystem type too).

     (Some attributes are made available in stx_attributes, but the general
     feeling was that the IOC flags were to ext[234]-specific and shouldn't
     be exposed through statx this way).

(15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer,
     Michael Kerrisk].

     (Deferred, probably to fsinfo.  Finding out if there's an ACL or
     seclabal might require extra filesystem operations).

(16) Femtosecond-resolution timestamps [Dave Chinner].

     (A __reserved field has been left in the statx_timestamp struct for
     this - if there proves to be a need).

(17) A set multiple attributes syscall to go with this.

===============
NEW SYSTEM CALL
===============

The new system call is:

	int ret = statx(int dfd,
			const char *filename,
			unsigned int flags,
			unsigned int mask,
			struct statx *buffer);

The dfd, filename and flags parameters indicate the file to query, in a
similar way to fstatat().  There is no equivalent of lstat() as that can be
emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags.  There is
also no equivalent of fstat() as that can be emulated by passing a NULL
filename to statx() with the fd of interest in dfd.

Whether or not statx() synchronises the attributes with the backing store
can be controlled by OR'ing a value into the flags argument (this typically
only affects network filesystems):

 (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this
     respect.

 (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise
     its attributes with the server - which might require data writeback to
     occur to get the timestamps correct.

 (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a
     network filesystem.  The resulting values should be considered
     approximate.

mask is a bitmask indicating the fields in struct statx that are of
interest to the caller.  The user should set this to STATX_BASIC_STATS to
get the basic set returned by stat().  It should be noted that asking for
more information may entail extra I/O operations.

buffer points to the destination for the data.  This must be 256 bytes in
size.

======================
MAIN ATTRIBUTES RECORD
======================

The following structures are defined in which to return the main attribute
set:

	struct statx_timestamp {
		__s64	tv_sec;
		__s32	tv_nsec;
		__s32	__reserved;
	};

	struct statx {
		__u32	stx_mask;
		__u32	stx_blksize;
		__u64	stx_attributes;
		__u32	stx_nlink;
		__u32	stx_uid;
		__u32	stx_gid;
		__u16	stx_mode;
		__u16	__spare0[1];
		__u64	stx_ino;
		__u64	stx_size;
		__u64	stx_blocks;
		__u64	__spare1[1];
		struct statx_timestamp	stx_atime;
		struct statx_timestamp	stx_btime;
		struct statx_timestamp	stx_ctime;
		struct statx_timestamp	stx_mtime;
		__u32	stx_rdev_major;
		__u32	stx_rdev_minor;
		__u32	stx_dev_major;
		__u32	stx_dev_minor;
		__u64	__spare2[14];
	};

The defined bits in request_mask and stx_mask are:

	STATX_TYPE		Want/got stx_mode & S_IFMT
	STATX_MODE		Want/got stx_mode & ~S_IFMT
	STATX_NLINK		Want/got stx_nlink
	STATX_UID		Want/got stx_uid
	STATX_GID		Want/got stx_gid
	STATX_ATIME		Want/got stx_atime{,_ns}
	STATX_MTIME		Want/got stx_mtime{,_ns}
	STATX_CTIME		Want/got stx_ctime{,_ns}
	STATX_INO		Want/got stx_ino
	STATX_SIZE		Want/got stx_size
	STATX_BLOCKS		Want/got stx_blocks
	STATX_BASIC_STATS	[The stuff in the normal stat struct]
	STATX_BTIME		Want/got stx_btime{,_ns}
	STATX_ALL		[All currently available stuff]

stx_btime is the file creation time, stx_mask is a bitmask indicating the
data provided and __spares*[] are where as-yet undefined fields can be
placed.

Time fields are structures with separate seconds and nanoseconds fields
plus a reserved field in case we want to add even finer resolution.  Note
that times will be negative if before 1970; in such a case, the nanosecond
fields will also be negative if not zero.

The bits defined in the stx_attributes field convey information about a
file, how it is accessed, where it is and what it does.  The following
attributes map to FS_*_FL flags and are the same numerical value:

	STATX_ATTR_COMPRESSED		File is compressed by the fs
	STATX_ATTR_IMMUTABLE		File is marked immutable
	STATX_ATTR_APPEND		File is append-only
	STATX_ATTR_NODUMP		File is not to be dumped
	STATX_ATTR_ENCRYPTED		File requires key to decrypt in fs

Within the kernel, the supported flags are listed by:

	KSTAT_ATTR_FS_IOC_FLAGS

[Are any other IOC flags of sufficient general interest to be exposed
through this interface?]

New flags include:

	STATX_ATTR_AUTOMOUNT		Object is an automount trigger

These are for the use of GUI tools that might want to mark files specially,
depending on what they are.

Fields in struct statx come in a number of classes:

 (0) stx_dev_*, stx_blksize.

     These are local system information and are always available.

 (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino,
     stx_size, stx_blocks.

     These will be returned whether the caller asks for them or not.  The
     corresponding bits in stx_mask will be set to indicate whether they
     actually have valid values.

     If the caller didn't ask for them, then they may be approximated.  For
     example, NFS won't waste any time updating them from the server,
     unless as a byproduct of updating something requested.

     If the values don't actually exist for the underlying object (such as
     UID or GID on a DOS file), then the bit won't be set in the stx_mask,
     even if the caller asked for the value.  In such a case, the returned
     value will be a fabrication.

     Note that there are instances where the type might not be valid, for
     instance Windows reparse points.

 (2) stx_rdev_*.

     This will be set only if stx_mode indicates we're looking at a
     blockdev or a chardev, otherwise will be 0.

 (3) stx_btime.

     Similar to (1), except this will be set to 0 if it doesn't exist.

=======
TESTING
=======

The following test program can be used to test the statx system call:

	samples/statx/test-statx.c

Just compile and run, passing it paths to the files you want to examine.
The file is built automatically if CONFIG_SAMPLES is enabled.

Here's some example output.  Firstly, an NFS directory that crosses to
another FSID.  Note that the AUTOMOUNT attribute is set because transiting
this directory will cause d_automount to be invoked by the VFS.

	[root@andromeda ~]# /tmp/test-statx -A /warthog/data
	statx(/warthog/data) = 0
	results=7ff
	  Size: 4096            Blocks: 8          IO Block: 1048576  directory
	Device: 00:26           Inode: 1703937     Links: 125
	Access: (3777/drwxrwxrwx)  Uid:     0   Gid:  4041
	Access: 2016-11-24 09:02:12.219699527+0000
	Modify: 2016-11-17 10:44:36.225653653+0000
	Change: 2016-11-17 10:44:36.225653653+0000
	Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------)

Secondly, the result of automounting on that directory.

	[root@andromeda ~]# /tmp/test-statx /warthog/data
	statx(/warthog/data) = 0
	results=7ff
	  Size: 4096            Blocks: 8          IO Block: 1048576  directory
	Device: 00:27           Inode: 2           Links: 125
	Access: (3777/drwxrwxrwx)  Uid:     0   Gid:  4041
	Access: 2016-11-24 09:02:12.219699527+0000
	Modify: 2016-11-17 10:44:36.225653653+0000
	Change: 2016-11-17 10:44:36.225653653+0000

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/Locking             |   3 +-
 Documentation/filesystems/vfs.txt             |   3 +-
 arch/x86/entry/syscalls/syscall_32.tbl        |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl        |   1 +
 drivers/base/devtmpfs.c                       |   3 +-
 drivers/block/loop.c                          |   3 +-
 drivers/mtd/ubi/build.c                       |   2 +-
 drivers/mtd/ubi/kapi.c                        |   2 +-
 drivers/staging/lustre/lustre/llite/file.c    |   9 +-
 .../lustre/lustre/llite/llite_internal.h      |   3 +-
 fs/9p/vfs_inode.c                             |  10 +-
 fs/9p/vfs_inode_dotl.c                        |   5 +-
 fs/afs/inode.c                                |   8 +-
 fs/afs/internal.h                             |   2 +-
 fs/bad_inode.c                                |   4 +-
 fs/btrfs/inode.c                              |   6 +-
 fs/ceph/inode.c                               |   6 +-
 fs/ceph/super.h                               |   4 +-
 fs/cifs/cifsfs.h                              |   2 +-
 fs/cifs/inode.c                               |   5 +-
 fs/coda/coda_linux.h                          |   2 +-
 fs/coda/inode.c                               |   7 +-
 fs/ecryptfs/inode.c                           |  13 +-
 fs/exportfs/expfs.c                           |   3 +-
 fs/ext4/ext4.h                                |   3 +-
 fs/ext4/inode.c                               |   6 +-
 fs/f2fs/f2fs.h                                |   4 +-
 fs/f2fs/file.c                                |   6 +-
 fs/fat/fat.h                                  |   4 +-
 fs/fat/file.c                                 |   5 +-
 fs/fuse/dir.c                                 |   6 +-
 fs/gfs2/inode.c                               |  11 +-
 fs/kernfs/inode.c                             |   8 +-
 fs/kernfs/kernfs-internal.h                   |   4 +-
 fs/libfs.c                                    |  12 +-
 fs/minix/inode.c                              |  11 +-
 fs/minix/minix.h                              |   2 +-
 fs/nfs/inode.c                                |  13 +-
 fs/nfs/namespace.c                            |   9 +-
 fs/nfsd/nfs4xdr.c                             |   4 +-
 fs/nfsd/vfs.h                                 |   3 +-
 fs/ocfs2/file.c                               |  11 +-
 fs/ocfs2/file.h                               |   4 +-
 fs/orangefs/inode.c                           |  13 +-
 fs/orangefs/orangefs-kernel.h                 |   5 +-
 fs/overlayfs/copy_up.c                        |   6 +-
 fs/overlayfs/dir.c                            |  10 +-
 fs/overlayfs/inode.c                          |   7 +-
 fs/proc/base.c                                |  12 +-
 fs/proc/generic.c                             |   6 +-
 fs/proc/internal.h                            |   2 +-
 fs/proc/proc_net.c                            |   6 +-
 fs/proc/proc_sysctl.c                         |   5 +-
 fs/proc/root.c                                |   6 +-
 fs/stat.c                                     | 214 ++++++++++++---
 fs/sysv/itree.c                               |   7 +-
 fs/sysv/sysv.h                                |   2 +-
 fs/ubifs/dir.c                                |   6 +-
 fs/ubifs/ubifs.h                              |   4 +-
 fs/udf/symlink.c                              |   5 +-
 fs/xfs/xfs_iops.c                             |   9 +-
 include/linux/fs.h                            |  35 ++-
 include/linux/nfs_fs.h                        |   2 +-
 include/linux/stat.h                          |  24 +-
 include/linux/syscalls.h                      |   3 +
 include/uapi/linux/fcntl.h                    |   5 +
 include/uapi/linux/stat.h                     | 131 +++++++++
 mm/shmem.c                                    |   6 +-
 samples/Kconfig                               |   6 +
 samples/Makefile                              |   2 +-
 samples/statx/Makefile                        |  10 +
 samples/statx/test-statx.c                    | 254 ++++++++++++++++++
 72 files changed, 822 insertions(+), 214 deletions(-)
 create mode 100644 samples/statx/Makefile
 create mode 100644 samples/statx/test-statx.c

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index ace63cd7af8c..fdcfdd79682a 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -58,7 +58,8 @@ prototypes:
 	int (*permission) (struct inode *, int, unsigned int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
-	int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
+	int (*getattr) (const struct path *, struct dentry *, struct kstat *,
+			u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 	void (*update_time)(struct inode *, struct timespec *, int);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index b968084eeac1..569211703721 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -382,7 +382,8 @@ struct inode_operations {
 	int (*permission) (struct inode *, int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
-	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
+	int (*getattr) (const struct path *, struct dentry *, struct kstat *,
+			u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 2b3618542544..9ba050fe47f3 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -389,3 +389,4 @@
 380	i386	pkey_mprotect		sys_pkey_mprotect
 381	i386	pkey_alloc		sys_pkey_alloc
 382	i386	pkey_free		sys_pkey_free
+383	i386	statx			sys_statx
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index e93ef0b38db8..5aef183e2f85 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -338,6 +338,7 @@
 329	common	pkey_mprotect		sys_pkey_mprotect
 330	common	pkey_alloc		sys_pkey_alloc
 331	common	pkey_free		sys_pkey_free
+332	common	statx			sys_statx
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 44a74cf1372c..d2fb9c8ed205 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -309,7 +309,8 @@ static int handle_remove(const char *nodename, struct device *dev)
 	if (d_really_is_positive(dentry)) {
 		struct kstat stat;
 		struct path p = {.mnt = parent.mnt, .dentry = dentry};
-		err = vfs_getattr(&p, &stat);
+		err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
+				  AT_STATX_SYNC_AS_STAT);
 		if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
 			struct iattr newattrs;
 			/*
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index eeb1db73f44e..8f4051999741 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1175,7 +1175,8 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
 
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
-	error = vfs_getattr(&file->f_path, &stat);
+	error = vfs_getattr(&file->f_path, &stat,
+			    STATX_INO, AT_STATX_SYNC_AS_STAT);
 	if (error)
 		return error;
 	memset(info, 0, sizeof(*info));
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 85d54f37e28f..77513195f50e 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -1159,7 +1159,7 @@ static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev)
 	if (err)
 		return ERR_PTR(err);
 
-	err = vfs_getattr(&path, &stat);
+	err = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT);
 	path_put(&path);
 	if (err)
 		return ERR_PTR(err);
diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c
index 88b1897aeb40..d4b2e8744498 100644
--- a/drivers/mtd/ubi/kapi.c
+++ b/drivers/mtd/ubi/kapi.c
@@ -314,7 +314,7 @@ struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode)
 	if (error)
 		return ERR_PTR(error);
 
-	error = vfs_getattr(&path, &stat);
+	error = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT);
 	path_put(&path);
 	if (error)
 		return ERR_PTR(error);
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 10adfcdd7035..481c0d01d4c6 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -2952,15 +2952,16 @@ static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
 	return rc;
 }
 
-int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
+int ll_getattr(const struct path *path, struct kstat *stat,
+	       u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(de);
+	struct inode *inode = d_inode(path->dentry);
 	struct ll_sb_info *sbi = ll_i2sbi(inode);
 	struct ll_inode_info *lli = ll_i2info(inode);
 	int res;
 
-	res = ll_inode_revalidate(de, MDS_INODELOCK_UPDATE |
-				      MDS_INODELOCK_LOOKUP);
+	res = ll_inode_revalidate(path->dentry,
+				  MDS_INODELOCK_UPDATE | MDS_INODELOCK_LOOKUP);
 	ll_stats_ops_tally(sbi, LPROC_LL_GETATTR, 1);
 
 	if (res)
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index ecdfd0c29b7f..55f68acd85d1 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -750,7 +750,8 @@ int ll_file_open(struct inode *inode, struct file *file);
 int ll_file_release(struct inode *inode, struct file *file);
 int ll_release_openhandle(struct inode *, struct lookup_intent *);
 int ll_md_real_close(struct inode *inode, fmode_t fmode);
-int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat);
+int ll_getattr(const struct path *path, struct kstat *stat,
+	       u32 request_mask, unsigned int flags);
 struct posix_acl *ll_get_acl(struct inode *inode, int type);
 int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
 	       const char *name, int namelen);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index f4f4450119e4..f1d96233670c 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1047,16 +1047,18 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 /**
  * v9fs_vfs_getattr - retrieve file metadata
- * @mnt: mount information
- * @dentry: file to get attributes on
+ * @path: Object to query
  * @stat: metadata structure to populate
+ * @request_mask: Mask of STATX_xxx flags indicating the caller's interests
+ * @flags: AT_STATX_xxx setting
  *
  */
 
 static int
-v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+v9fs_vfs_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid;
 	struct p9_wstat *st;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 5999bd050678..570e63ee5b71 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -468,9 +468,10 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 }
 
 static int
-v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid;
 	struct p9_stat_dotl *st;
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 86cc7264c21c..1e4897a048d2 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -375,12 +375,10 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 /*
  * read the attributes of an inode
  */
-int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		      struct kstat *stat)
+int afs_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode;
-
-	inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 
 	_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 8acf3670e756..5dfa56903a2d 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -533,7 +533,7 @@ extern struct inode *afs_iget(struct super_block *, struct key *,
 			      struct afs_callback *);
 extern void afs_zap_data(struct afs_vnode *);
 extern int afs_validate(struct afs_vnode *, struct key *);
-extern int afs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int afs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int afs_setattr(struct dentry *, struct iattr *);
 extern void afs_evict_inode(struct inode *);
 extern int afs_drop_inode(struct inode *);
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 5f685c819298..bb53728c7a31 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -89,8 +89,8 @@ static int bad_inode_permission(struct inode *inode, int mask)
 	return -EIO;
 }
 
-static int bad_inode_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat)
+static int bad_inode_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
 	return -EIO;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ee6978d80491..c40060cc481f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9413,11 +9413,11 @@ int btrfs_init_cachep(void)
 	return -ENOMEM;
 }
 
-static int btrfs_getattr(struct vfsmount *mnt,
-			 struct dentry *dentry, struct kstat *stat)
+static int btrfs_getattr(const struct path *path, struct kstat *stat,
+			 u32 request_mask, unsigned int flags)
 {
 	u64 delalloc_bytes;
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	u32 blocksize = inode->i_sb->s_blocksize;
 
 	generic_fillattr(inode, stat);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index fd8f771f99b7..d449e1c03cbd 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2187,10 +2187,10 @@ int ceph_permission(struct inode *inode, int mask)
  * Get all attributes.  Hopefully somedata we'll have a statlite()
  * and can limit the fields we require to be accurate.
  */
-int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+int ceph_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int err;
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index e9410bcf4113..fe6b9cfc4013 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -784,8 +784,8 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
 extern int ceph_permission(struct inode *inode, int mask);
 extern int __ceph_setattr(struct inode *inode, struct iattr *attr);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
-extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat);
+extern int ceph_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags);
 
 /* xattr.c */
 int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index c9c00a862036..da717fee3026 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -83,7 +83,7 @@ extern int cifs_revalidate_dentry(struct dentry *);
 extern int cifs_invalidate_mapping(struct inode *inode);
 extern int cifs_revalidate_mapping(struct inode *inode);
 extern int cifs_zap_mapping(struct inode *inode);
-extern int cifs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int cifs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int cifs_setattr(struct dentry *, struct iattr *);
 
 extern const struct inode_operations cifs_file_inode_ops;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7ab5be7944aa..1363fff460b9 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1990,9 +1990,10 @@ int cifs_revalidate_dentry(struct dentry *dentry)
 	return cifs_revalidate_mapping(inode);
 }
 
-int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+int cifs_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct inode *inode = d_inode(dentry);
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index 5104d84c4f64..d3c361883c28 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -47,7 +47,7 @@ int coda_open(struct inode *i, struct file *f);
 int coda_release(struct inode *i, struct file *f);
 int coda_permission(struct inode *inode, int mask);
 int coda_revalidate_inode(struct inode *);
-int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+int coda_getattr(const struct path *, struct kstat *, u32, unsigned int);
 int coda_setattr(struct dentry *, struct iattr *);
 
 /* this file:  heloers */
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 71dbe7e287ce..2dea594da199 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -255,11 +255,12 @@ static void coda_evict_inode(struct inode *inode)
 	coda_cache_clear_inode(inode);
 }
 
-int coda_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int coda_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
-	int err = coda_revalidate_inode(d_inode(dentry));
+	int err = coda_revalidate_inode(d_inode(path->dentry));
 	if (!err)
-		generic_fillattr(d_inode(dentry), stat);
+		generic_fillattr(d_inode(path->dentry), stat);
 	return err;
 }
 
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e7413f82d27b..efc2db42d175 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -959,9 +959,10 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 	return rc;
 }
 
-static int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
-				 struct kstat *stat)
+static int ecryptfs_getattr_link(const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	int rc = 0;
 
@@ -983,13 +984,15 @@ static int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
 	return rc;
 }
 
-static int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			    struct kstat *stat)
+static int ecryptfs_getattr(const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct kstat lower_stat;
 	int rc;
 
-	rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat);
+	rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat,
+			 request_mask, flags);
 	if (!rc) {
 		fsstack_copy_attr_all(d_inode(dentry),
 				      ecryptfs_inode_to_lower(d_inode(dentry)));
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index a4b531be9168..f2d24bb8d745 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -299,7 +299,8 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
 	 * filesystem supports 64-bit inode numbers.  So we need to
 	 * actually call ->getattr, not just read i_ino:
 	 */
-	error = vfs_getattr_nosec(&child_path, &stat);
+	error = vfs_getattr_nosec(&child_path, &stat,
+				  STATX_INO, AT_STATX_SYNC_AS_STAT);
 	if (error)
 		return error;
 	buffer.ino = stat.ino;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2fd17e8e4984..025d2e85f454 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2462,8 +2462,7 @@ extern struct inode *ext4_iget(struct super_block *, unsigned long);
 extern struct inode *ext4_iget_normal(struct super_block *, unsigned long);
 extern int  ext4_write_inode(struct inode *, struct writeback_control *);
 extern int  ext4_setattr(struct dentry *, struct iattr *);
-extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
-				struct kstat *stat);
+extern int  ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern void ext4_evict_inode(struct inode *);
 extern void ext4_clear_inode(struct inode *);
 extern int  ext4_sync_inode(handle_t *, struct inode *);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 971f66342080..7385e6a6b6cb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5387,13 +5387,13 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	return error;
 }
 
-int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+int ext4_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode;
 	unsigned long long delalloc_blocks;
 
-	inode = d_inode(dentry);
+	inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 
 	/*
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d1483136fed6..e849f83d6114 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2040,8 +2040,8 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
 void truncate_data_blocks(struct dnode_of_data *dn);
 int truncate_blocks(struct inode *inode, u64 from, bool lock);
 int f2fs_truncate(struct inode *inode);
-int f2fs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat);
+int f2fs_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags);
 int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
 int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
 int truncate_data_blocks_range(struct dnode_of_data *dn, int count);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 78e65288f2b2..5f7317875a67 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -633,10 +633,10 @@ int f2fs_truncate(struct inode *inode)
 	return 0;
 }
 
-int f2fs_getattr(struct vfsmount *mnt,
-			 struct dentry *dentry, struct kstat *stat)
+int f2fs_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 	stat->blocks <<= 3;
 	return 0;
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index e6b764a17a9c..051dac1ce3be 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -364,8 +364,8 @@ extern const struct file_operations fat_file_operations;
 extern const struct inode_operations fat_file_inode_operations;
 extern int fat_setattr(struct dentry *dentry, struct iattr *attr);
 extern void fat_truncate_blocks(struct inode *inode, loff_t offset);
-extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		       struct kstat *stat);
+extern int fat_getattr(const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int flags);
 extern int fat_file_fsync(struct file *file, loff_t start, loff_t end,
 			  int datasync);
 
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 3d04b124bce0..4724cc9ad650 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -365,9 +365,10 @@ void fat_truncate_blocks(struct inode *inode, loff_t offset)
 	fat_flush_inodes(inode->i_sb, inode, NULL);
 }
 
-int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int fat_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 	stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size;
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 811fd8929a18..beb3d64f16e2 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1777,10 +1777,10 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr)
 	return ret;
 }
 
-static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
-			struct kstat *stat)
+static int fuse_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(entry);
+	struct inode *inode = d_inode(path->dentry);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 
 	if (!fuse_allow_current_process(fc))
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index eb7724b8578a..288c15f385bd 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1959,9 +1959,10 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
 
 /**
  * gfs2_getattr - Read out an inode's attributes
- * @mnt: The vfsmount the inode is being accessed from
- * @dentry: The dentry to stat
+ * @path: Object to query
  * @stat: The inode's stats
+ * @request_mask: Mask of STATX_xxx flags indicating the caller's interests
+ * @flags: AT_STATX_xxx setting
  *
  * This may be called from the VFS directly, or from within GFS2 with the
  * inode locked, so we look to see if the glock is already locked and only
@@ -1972,10 +1973,10 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
  * Returns: errno
  */
 
-static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat)
+static int gfs2_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int error;
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index ac9e108ce1ea..fb4b4a79a0d6 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -200,11 +200,11 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
 		set_nlink(inode, kn->dir.subdirs + 2);
 }
 
-int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		   struct kstat *stat)
+int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int query_flags)
 {
-	struct kernfs_node *kn = dentry->d_fsdata;
-	struct inode *inode = d_inode(dentry);
+	struct kernfs_node *kn = path->dentry->d_fsdata;
+	struct inode *inode = d_inode(path->dentry);
 
 	mutex_lock(&kernfs_mutex);
 	kernfs_refresh_inode(kn, inode);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 3100987cf8ba..2d5144ab4251 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -80,8 +80,8 @@ extern const struct xattr_handler *kernfs_xattr_handlers[];
 void kernfs_evict_inode(struct inode *inode);
 int kernfs_iop_permission(struct inode *inode, int mask);
 int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr);
-int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		       struct kstat *stat);
+int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int query_flags);
 ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
 
 /*
diff --git a/fs/libfs.c b/fs/libfs.c
index 28d6f35feed6..1dfaf8f606c0 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -20,10 +20,10 @@
 
 #include "internal.h"
 
-int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		   struct kstat *stat)
+int simple_getattr(const struct path *path, struct kstat *stat,
+		   u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 	stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9);
 	return 0;
@@ -1143,10 +1143,10 @@ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry,
 	return ERR_PTR(-ENOENT);
 }
 
-static int empty_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
-				 struct kstat *stat)
+static int empty_dir_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 	return 0;
 }
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index e7d9bf86d975..6ac76b0434e9 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -622,11 +622,14 @@ static int minix_write_inode(struct inode *inode, struct writeback_control *wbc)
 	return err;
 }
 
-int minix_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int minix_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags)
 {
-	struct super_block *sb = dentry->d_sb;
-	generic_fillattr(d_inode(dentry), stat);
-	if (INODE_VERSION(d_inode(dentry)) == MINIX_V1)
+	struct super_block *sb = path->dentry->d_sb;
+	struct inode *inode = d_inode(path->dentry);
+
+	generic_fillattr(inode, stat);
+	if (INODE_VERSION(inode) == MINIX_V1)
 		stat->blocks = (BLOCK_SIZE / 512) * V1_minix_blocks(stat->size, sb);
 	else
 		stat->blocks = (sb->s_blocksize / 512) * V2_minix_blocks(stat->size, sb);
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index 01ad81dcacc5..663d66138d06 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -51,7 +51,7 @@ extern unsigned long minix_count_free_inodes(struct super_block *sb);
 extern int minix_new_block(struct inode * inode);
 extern void minix_free_block(struct inode *inode, unsigned long block);
 extern unsigned long minix_count_free_blocks(struct super_block *sb);
-extern int minix_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int minix_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len);
 
 extern void V1_minix_truncate(struct inode *);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5ca4d96b1942..b5425315adcc 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -703,9 +703,10 @@ static bool nfs_need_revalidate_inode(struct inode *inode)
 	return false;
 }
 
-int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int nfs_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
 	int err = 0;
 
@@ -726,17 +727,17 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	 *  - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
 	 *    no point in checking those.
 	 */
- 	if ((mnt->mnt_flags & MNT_NOATIME) ||
- 	    ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
+	if ((path->mnt->mnt_flags & MNT_NOATIME) ||
+	    ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
 		need_atime = 0;
 
 	if (need_atime || nfs_need_revalidate_inode(inode)) {
 		struct nfs_server *server = NFS_SERVER(inode);
 
-		nfs_readdirplus_parent_cache_miss(dentry);
+		nfs_readdirplus_parent_cache_miss(path->dentry);
 		err = __nfs_revalidate_inode(server, inode);
 	} else
-		nfs_readdirplus_parent_cache_hit(dentry);
+		nfs_readdirplus_parent_cache_hit(path->dentry);
 	if (!err) {
 		generic_fillattr(inode, stat);
 		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index e49d831c4e85..786f17580582 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -178,11 +178,12 @@ struct vfsmount *nfs_d_automount(struct path *path)
 }
 
 static int
-nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+nfs_namespace_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int query_flags)
 {
-	if (NFS_FH(d_inode(dentry))->size != 0)
-		return nfs_getattr(mnt, dentry, stat);
-	generic_fillattr(d_inode(dentry), stat);
+	if (NFS_FH(d_inode(path->dentry))->size != 0)
+		return nfs_getattr(path, stat, request_mask, query_flags);
+	generic_fillattr(d_inode(path->dentry), stat);
 	return 0;
 }
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 382c1fd05b4c..33017d652b1d 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2301,7 +2301,7 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
 		if (path.dentry != path.mnt->mnt_root)
 			break;
 	}
-	err = vfs_getattr(&path, stat);
+	err = vfs_getattr(&path, stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
 	path_put(&path);
 	return err;
 }
@@ -2385,7 +2385,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 			goto out;
 	}
 
-	err = vfs_getattr(&path, &stat);
+	err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_nfserr;
 	if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index db98c48c735a..1bbdccecbf3d 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -135,7 +135,8 @@ static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
 {
 	struct path p = {.mnt = fh->fh_export->ex_path.mnt,
 			 .dentry = fh->fh_dentry};
-	return nfserrno(vfs_getattr(&p, stat));
+	return nfserrno(vfs_getattr(&p, stat, STATX_BASIC_STATS,
+				    AT_STATX_SYNC_AS_STAT));
 }
 
 static inline int nfsd_create_is_exclusive(int createmode)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 8836305eb378..bfeb647459d9 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1306,16 +1306,15 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	return status;
 }
 
-int ocfs2_getattr(struct vfsmount *mnt,
-		  struct dentry *dentry,
-		  struct kstat *stat)
+int ocfs2_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
-	struct super_block *sb = dentry->d_sb;
+	struct inode *inode = d_inode(path->dentry);
+	struct super_block *sb = path->dentry->d_sb;
 	struct ocfs2_super *osb = sb->s_fs_info;
 	int err;
 
-	err = ocfs2_inode_revalidate(dentry);
+	err = ocfs2_inode_revalidate(path->dentry);
 	if (err) {
 		if (err != -ENOENT)
 			mlog_errno(err);
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 897fd9a2e51d..1fdc9839cd93 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -68,8 +68,8 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
 		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
-int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat);
+int ocfs2_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags);
 int ocfs2_permission(struct inode *inode, int mask);
 
 int ocfs2_should_update_atime(struct inode *inode,
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 5cd617980fbf..a304bf34b212 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -245,25 +245,24 @@ int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
 /*
  * Obtain attributes of an object given a dentry
  */
-int orangefs_getattr(struct vfsmount *mnt,
-		  struct dentry *dentry,
-		  struct kstat *kstat)
+int orangefs_getattr(const struct path *path, struct kstat *stat,
+		     u32 request_mask, unsigned int flags)
 {
 	int ret = -ENOENT;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = path->dentry->d_inode;
 	struct orangefs_inode_s *orangefs_inode = NULL;
 
 	gossip_debug(GOSSIP_INODE_DEBUG,
 		     "orangefs_getattr: called on %pd\n",
-		     dentry);
+		     path->dentry);
 
 	ret = orangefs_inode_getattr(inode, 0, 0);
 	if (ret == 0) {
-		generic_fillattr(inode, kstat);
+		generic_fillattr(inode, stat);
 
 		/* override block size reported to stat */
 		orangefs_inode = ORANGEFS_I(inode);
-		kstat->blksize = orangefs_inode->blksize;
+		stat->blksize = orangefs_inode->blksize;
 	}
 	return ret;
 }
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 70355a9a2596..0c4f03c22ce0 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -439,9 +439,8 @@ struct inode *orangefs_new_inode(struct super_block *sb,
 
 int orangefs_setattr(struct dentry *dentry, struct iattr *iattr);
 
-int orangefs_getattr(struct vfsmount *mnt,
-		  struct dentry *dentry,
-		  struct kstat *kstat);
+int orangefs_getattr(const struct path *path, struct kstat *stat,
+		     u32 request_mask, unsigned int flags);
 
 int orangefs_permission(struct inode *inode, int mask);
 
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index f57043dace62..a6f9ca621e0b 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -346,7 +346,8 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	ovl_path_upper(parent, &parentpath);
 	upperdir = parentpath.dentry;
 
-	err = vfs_getattr(&parentpath, &pstat);
+	err = vfs_getattr(&parentpath, &pstat,
+			  STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT);
 	if (err)
 		return err;
 
@@ -409,7 +410,8 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
 		}
 
 		ovl_path_lower(next, &lowerpath);
-		err = vfs_getattr(&lowerpath, &stat);
+		err = vfs_getattr(&lowerpath, &stat,
+				  STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
 		/* maybe truncate regular file. this has no effect on dirs */
 		if (flags & O_TRUNC)
 			stat.size = 0;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 16e06dd89457..6515796460df 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -138,9 +138,10 @@ static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
 	return err;
 }
 
-static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			 struct kstat *stat)
+static int ovl_dir_getattr(const struct path *path, struct kstat *stat,
+			   u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	int err;
 	enum ovl_path_type type;
 	struct path realpath;
@@ -148,7 +149,7 @@ static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
 
 	type = ovl_path_real(dentry, &realpath);
 	old_cred = ovl_override_creds(dentry->d_sb);
-	err = vfs_getattr(&realpath, stat);
+	err = vfs_getattr(&realpath, stat, request_mask, flags);
 	revert_creds(old_cred);
 	if (err)
 		return err;
@@ -264,7 +265,8 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 		goto out;
 
 	ovl_path_upper(dentry, &upperpath);
-	err = vfs_getattr(&upperpath, &stat);
+	err = vfs_getattr(&upperpath, &stat,
+			  STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_unlock;
 
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 08643ac44a02..d4bb54f7b6b4 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -56,16 +56,17 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	return err;
 }
 
-static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			 struct kstat *stat)
+static int ovl_getattr(const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct path realpath;
 	const struct cred *old_cred;
 	int err;
 
 	ovl_path_real(dentry, &realpath);
 	old_cred = ovl_override_creds(dentry->d_sb);
-	err = vfs_getattr(&realpath, stat);
+	err = vfs_getattr(&realpath, stat, request_mask, flags);
 	revert_creds(old_cred);
 	return err;
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1e1e182d571b..3b5e6aa2a326 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1724,11 +1724,12 @@ struct inode *proc_pid_make_inode(struct super_block * sb,
 	return NULL;
 }
 
-int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int pid_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct task_struct *task;
-	struct pid_namespace *pid = dentry->d_sb->s_fs_info;
+	struct pid_namespace *pid = path->dentry->d_sb->s_fs_info;
 
 	generic_fillattr(inode, stat);
 
@@ -3511,9 +3512,10 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 	return 0;
 }
 
-static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+static int proc_task_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct task_struct *p = get_proc_task(inode);
 	generic_fillattr(inode, stat);
 
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 06c73904d497..ee27feb34cf4 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -118,10 +118,10 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
 	return 0;
 }
 
-static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat)
+static int proc_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct proc_dir_entry *de = PDE(inode);
 	if (de && de->nlink)
 		set_nlink(inode, de->nlink);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5d6960f5f1c0..e93cdc6ddb31 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -149,7 +149,7 @@ extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
  * base.c
  */
 extern const struct dentry_operations pid_dentry_operations;
-extern int pid_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int proc_setattr(struct dentry *, struct iattr *);
 extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
 extern int pid_revalidate(struct dentry *, unsigned int);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index ffd72a6c6e04..9db1df2537fc 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -140,10 +140,10 @@ static struct dentry *proc_tgid_net_lookup(struct inode *dir,
 	return de;
 }
 
-static int proc_tgid_net_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		struct kstat *stat)
+static int proc_tgid_net_getattr(const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct net *net;
 
 	net = get_proc_task_net(inode);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 3e64c6502dc8..3d8726445ad1 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -801,9 +801,10 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
 	return 0;
 }
 
-static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+static int proc_sys_getattr(const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index b90da888b81a..fb1955c82274 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -149,10 +149,10 @@ void __init proc_root_init(void)
 	proc_sys_init();
 }
 
-static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
-)
+static int proc_root_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
-	generic_fillattr(d_inode(dentry), stat);
+	generic_fillattr(d_inode(path->dentry), stat);
 	stat->nlink = proc_root.nlink + nr_processes();
 	return 0;
 }
diff --git a/fs/stat.c b/fs/stat.c
index 3f14d1ef0868..a3804feadade 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -18,6 +18,15 @@
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 
+/**
+ * generic_fillattr - Fill in the basic attributes from the inode struct
+ * @inode: Inode to use as the source
+ * @stat: Where to fill in the attributes
+ *
+ * Fill in the basic attributes in the kstat structure from data that's to be
+ * found on the VFS inode structure.  This is the default if no getattr inode
+ * operation is supplied.
+ */
 void generic_fillattr(struct inode *inode, struct kstat *stat)
 {
 	stat->dev = inode->i_sb->s_dev;
@@ -33,81 +42,147 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 	stat->ctime = inode->i_ctime;
 	stat->blksize = i_blocksize(inode);
 	stat->blocks = inode->i_blocks;
-}
 
+	if (IS_NOATIME(inode))
+		stat->result_mask &= ~STATX_ATIME;
+	if (IS_AUTOMOUNT(inode))
+		stat->attributes |= STATX_ATTR_AUTOMOUNT;
+}
 EXPORT_SYMBOL(generic_fillattr);
 
 /**
  * vfs_getattr_nosec - getattr without security checks
  * @path: file to get attributes from
  * @stat: structure to return attributes in
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
  *
  * Get attributes without calling security_inode_getattr.
  *
  * Currently the only caller other than vfs_getattr is internal to the
- * filehandle lookup code, which uses only the inode number and returns
- * no attributes to any user.  Any other code probably wants
- * vfs_getattr.
+ * filehandle lookup code, which uses only the inode number and returns no
+ * attributes to any user.  Any other code probably wants vfs_getattr.
  */
-int vfs_getattr_nosec(struct path *path, struct kstat *stat)
+int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_backing_inode(path->dentry);
 
+	memset(stat, 0, sizeof(*stat));
+	stat->result_mask |= STATX_BASIC_STATS;
+	request_mask &= STATX_ALL;
+	query_flags &= KSTAT_QUERY_FLAGS;
 	if (inode->i_op->getattr)
-		return inode->i_op->getattr(path->mnt, path->dentry, stat);
+		return inode->i_op->getattr(path, stat, request_mask,
+					    query_flags);
 
 	generic_fillattr(inode, stat);
 	return 0;
 }
-
 EXPORT_SYMBOL(vfs_getattr_nosec);
 
-int vfs_getattr(struct path *path, struct kstat *stat)
+/*
+ * vfs_getattr - Get the enhanced basic attributes of a file
+ * @path: The file of interest
+ * @stat: Where to return the statistics
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ *
+ * Ask the filesystem for a file's attributes.  The caller must indicate in
+ * request_mask and query_flags to indicate what they want.
+ *
+ * If the file is remote, the filesystem can be forced to update the attributes
+ * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can
+ * suppress the update by passing AT_STATX_DONT_SYNC.
+ *
+ * Bits must have been set in request_mask to indicate which attributes the
+ * caller wants retrieving.  Any such attribute not requested may be returned
+ * anyway, but the value may be approximate, and, if remote, may not have been
+ * synchronised with the server.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
 	int retval;
 
 	retval = security_inode_getattr(path);
 	if (retval)
 		return retval;
-	return vfs_getattr_nosec(path, stat);
+	return vfs_getattr_nosec(path, stat, request_mask, query_flags);
 }
-
 EXPORT_SYMBOL(vfs_getattr);
 
-int vfs_fstat(unsigned int fd, struct kstat *stat)
+/**
+ * vfs_statx_fd - Get the enhanced basic attributes by file descriptor
+ * @fd: The file descriptor referring to the file of interest
+ * @stat: The result structure to fill in.
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ *
+ * This function is a wrapper around vfs_getattr().  The main difference is
+ * that it uses a file descriptor to determine the file location.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_statx_fd(unsigned int fd, struct kstat *stat,
+		 u32 request_mask, unsigned int query_flags)
 {
 	struct fd f = fdget_raw(fd);
 	int error = -EBADF;
 
 	if (f.file) {
-		error = vfs_getattr(&f.file->f_path, stat);
+		error = vfs_getattr(&f.file->f_path, stat,
+				    request_mask, query_flags);
 		fdput(f);
 	}
 	return error;
 }
-EXPORT_SYMBOL(vfs_fstat);
+EXPORT_SYMBOL(vfs_statx_fd);
 
-int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
-		int flag)
+/**
+ * vfs_statx - Get basic and extra attributes by filename
+ * @dfd: A file descriptor representing the base dir for a relative filename
+ * @filename: The name of the file of interest
+ * @flags: Flags to control the query
+ * @stat: The result structure to fill in.
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ *
+ * This function is a wrapper around vfs_getattr().  The main difference is
+ * that it uses a filename and base directory to determine the file location.
+ * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
+ * at the given name from being referenced.
+ *
+ * The caller must have preset stat->request_mask as for vfs_getattr().  The
+ * flags are also used to load up stat->query_flags.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_statx(int dfd, const char __user *filename, int flags,
+	      struct kstat *stat, u32 request_mask)
 {
 	struct path path;
 	int error = -EINVAL;
-	unsigned int lookup_flags = 0;
+	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
 
-	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
-		      AT_EMPTY_PATH)) != 0)
-		goto out;
+	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+		       AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
+		return -EINVAL;
 
-	if (!(flag & AT_SYMLINK_NOFOLLOW))
-		lookup_flags |= LOOKUP_FOLLOW;
-	if (flag & AT_EMPTY_PATH)
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
+
 retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
-	error = vfs_getattr(&path, stat);
+	error = vfs_getattr(&path, stat, request_mask, flags);
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -116,19 +191,7 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 out:
 	return error;
 }
-EXPORT_SYMBOL(vfs_fstatat);
-
-int vfs_stat(const char __user *name, struct kstat *stat)
-{
-	return vfs_fstatat(AT_FDCWD, name, stat, 0);
-}
-EXPORT_SYMBOL(vfs_stat);
-
-int vfs_lstat(const char __user *name, struct kstat *stat)
-{
-	return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
-}
-EXPORT_SYMBOL(vfs_lstat);
+EXPORT_SYMBOL(vfs_statx);
 
 
 #ifdef __ARCH_WANT_OLD_STAT
@@ -141,7 +204,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 {
 	static int warncount = 5;
 	struct __old_kernel_stat tmp;
-	
+
 	if (warncount > 0) {
 		warncount--;
 		printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n",
@@ -166,7 +229,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 #if BITS_PER_LONG == 32
 	if (stat->size > MAX_NON_LFS)
 		return -EOVERFLOW;
-#endif	
+#endif
 	tmp.st_size = stat->size;
 	tmp.st_atime = stat->atime.tv_sec;
 	tmp.st_mtime = stat->mtime.tv_sec;
@@ -445,6 +508,81 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
 
+static inline int __put_timestamp(struct timespec *kts,
+				  struct statx_timestamp __user *uts)
+{
+	return (__put_user(kts->tv_sec,		&uts->tv_sec		) ||
+		__put_user(kts->tv_nsec,	&uts->tv_nsec		) ||
+		__put_user(0,			&uts->__reserved	));
+}
+
+/*
+ * Set the statx results.
+ */
+static long statx_set_result(struct kstat *stat, struct statx __user *buffer)
+{
+	uid_t uid = from_kuid_munged(current_user_ns(), stat->uid);
+	gid_t gid = from_kgid_munged(current_user_ns(), stat->gid);
+
+	if (__put_user(stat->result_mask,	&buffer->stx_mask	) ||
+	    __put_user(stat->mode,		&buffer->stx_mode	) ||
+	    __clear_user(&buffer->__spare0, sizeof(buffer->__spare0))	  ||
+	    __put_user(stat->nlink,		&buffer->stx_nlink	) ||
+	    __put_user(uid,			&buffer->stx_uid	) ||
+	    __put_user(gid,			&buffer->stx_gid	) ||
+	    __put_user(stat->attributes,	&buffer->stx_attributes	) ||
+	    __put_user(stat->blksize,		&buffer->stx_blksize	) ||
+	    __put_user(MAJOR(stat->rdev),	&buffer->stx_rdev_major	) ||
+	    __put_user(MINOR(stat->rdev),	&buffer->stx_rdev_minor	) ||
+	    __put_user(MAJOR(stat->dev),	&buffer->stx_dev_major	) ||
+	    __put_user(MINOR(stat->dev),	&buffer->stx_dev_minor	) ||
+	    __put_timestamp(&stat->atime,	&buffer->stx_atime	) ||
+	    __put_timestamp(&stat->btime,	&buffer->stx_btime	) ||
+	    __put_timestamp(&stat->ctime,	&buffer->stx_ctime	) ||
+	    __put_timestamp(&stat->mtime,	&buffer->stx_mtime	) ||
+	    __put_user(stat->ino,		&buffer->stx_ino	) ||
+	    __put_user(stat->size,		&buffer->stx_size	) ||
+	    __put_user(stat->blocks,		&buffer->stx_blocks	) ||
+	    __clear_user(&buffer->__spare1, sizeof(buffer->__spare1))	  ||
+	    __clear_user(&buffer->__spare2, sizeof(buffer->__spare2)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/**
+ * sys_statx - System call to get enhanced stats
+ * @dfd: Base directory to pathwalk from *or* fd to stat.
+ * @filename: File to stat *or* NULL.
+ * @flags: AT_* flags to control pathwalk.
+ * @mask: Parts of statx struct actually required.
+ * @buffer: Result buffer.
+ *
+ * Note that if filename is NULL, then it does the equivalent of fstat() using
+ * dfd to indicate the file of interest.
+ */
+SYSCALL_DEFINE5(statx,
+		int, dfd, const char __user *, filename, unsigned, flags,
+		unsigned int, mask,
+		struct statx __user *, buffer)
+{
+	struct kstat stat;
+	int error;
+
+	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
+		return -EINVAL;
+	if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer)))
+		return -EFAULT;
+
+	if (filename)
+		error = vfs_statx(dfd, filename, flags, &stat, mask);
+	else
+		error = vfs_statx_fd(dfd, &stat, mask, flags);
+	if (error)
+		return error;
+	return statx_set_result(&stat, buffer);
+}
+
 /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
 void __inode_add_bytes(struct inode *inode, loff_t bytes)
 {
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 08d3e630b49c..83809f5b5eca 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -440,10 +440,11 @@ static unsigned sysv_nblocks(struct super_block *s, loff_t size)
 	return blocks;
 }
 
-int sysv_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int sysv_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
-	struct super_block *s = dentry->d_sb;
-	generic_fillattr(d_inode(dentry), stat);
+	struct super_block *s = path->dentry->d_sb;
+	generic_fillattr(d_inode(path->dentry), stat);
 	stat->blocks = (s->s_blocksize / 512) * sysv_nblocks(s, stat->size);
 	stat->blksize = s->s_blocksize;
 	return 0;
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index 6c212288adcb..1e7e27c729af 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -142,7 +142,7 @@ extern struct inode *sysv_iget(struct super_block *, unsigned int);
 extern int sysv_write_inode(struct inode *, struct writeback_control *wbc);
 extern int sysv_sync_inode(struct inode *);
 extern void sysv_set_inode(struct inode *, dev_t);
-extern int sysv_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int sysv_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int sysv_init_icache(void);
 extern void sysv_destroy_icache(void);
 
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 528369f3e472..30825d882aa9 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -1622,11 +1622,11 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
-int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat)
+int ubifs_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags)
 {
 	loff_t size;
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct ubifs_inode *ui = ubifs_inode(inode);
 
 	mutex_lock(&ui->ui_mutex);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index f0c86f076535..4d57e488038e 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1749,8 +1749,8 @@ int ubifs_update_time(struct inode *inode, struct timespec *time, int flags);
 /* dir.c */
 struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir,
 			      umode_t mode);
-int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat);
+int ubifs_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags);
 int ubifs_check_dir_empty(struct inode *dir);
 
 /* xattr.c */
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index f7dfef53f739..6023c97c6da2 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -152,9 +152,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	return err;
 }
 
-static int udf_symlink_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			       struct kstat *stat)
+static int udf_symlink_getattr(const struct path *path, struct kstat *stat,
+				u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct inode *inode = d_backing_inode(dentry);
 	struct page *page;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 22c16155f1b4..229cc6a6d8ef 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -489,11 +489,12 @@ xfs_vn_get_link_inline(
 
 STATIC int
 xfs_vn_getattr(
-	struct vfsmount		*mnt,
-	struct dentry		*dentry,
-	struct kstat		*stat)
+	const struct path	*path,
+	struct kstat		*stat,
+	u32			request_mask,
+	unsigned int		query_flags)
 {
-	struct inode		*inode = d_inode(dentry);
+	struct inode		*inode = d_inode(path->dentry);
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 52350947c670..aad3fd0ff5f8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1709,7 +1709,7 @@ struct inode_operations {
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
-	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
+	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
@@ -2902,8 +2902,8 @@ extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
 extern void generic_fillattr(struct inode *, struct kstat *);
-int vfs_getattr_nosec(struct path *path, struct kstat *stat);
-extern int vfs_getattr(struct path *, struct kstat *);
+extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
+extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 void __inode_add_bytes(struct inode *inode, loff_t bytes);
 void inode_add_bytes(struct inode *inode, loff_t bytes);
 void __inode_sub_bytes(struct inode *inode, loff_t bytes);
@@ -2916,10 +2916,29 @@ extern const struct inode_operations simple_symlink_inode_operations;
 
 extern int iterate_dir(struct file *, struct dir_context *);
 
-extern int vfs_stat(const char __user *, struct kstat *);
-extern int vfs_lstat(const char __user *, struct kstat *);
-extern int vfs_fstat(unsigned int, struct kstat *);
-extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
+extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
+extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int);
+
+static inline int vfs_stat(const char __user *filename, struct kstat *stat)
+{
+	return vfs_statx(AT_FDCWD, filename, 0, stat, STATX_BASIC_STATS);
+}
+static inline int vfs_lstat(const char __user *name, struct kstat *stat)
+{
+	return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW,
+			 stat, STATX_BASIC_STATS);
+}
+static inline int vfs_fstatat(int dfd, const char __user *filename,
+			      struct kstat *stat, int flags)
+{
+	return vfs_statx(dfd, filename, flags, stat, STATX_BASIC_STATS);
+}
+static inline int vfs_fstat(int fd, struct kstat *stat)
+{
+	return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0);
+}
+
+
 extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
 extern int vfs_readlink(struct dentry *, char __user *, int);
 
@@ -2949,7 +2968,7 @@ extern int dcache_dir_close(struct inode *, struct file *);
 extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
 extern int dcache_readdir(struct file *, struct dir_context *);
 extern int simple_setattr(struct dentry *, struct iattr *);
-extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int simple_statfs(struct dentry *, struct kstatfs *);
 extern int simple_open(struct inode *inode, struct file *file);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index f1da8c8dd473..287f34161086 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -335,7 +335,7 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *);
 extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr);
-extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
 extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
 extern int nfs_permission(struct inode *, int);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 075cb0c7eb2a..c76e524fb34b 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -18,20 +18,32 @@
 #include <linux/time.h>
 #include <linux/uidgid.h>
 
+#define KSTAT_QUERY_FLAGS (AT_STATX_SYNC_TYPE)
+
 struct kstat {
-	u64		ino;
-	dev_t		dev;
+	u32		result_mask;	/* What fields the user got */
 	umode_t		mode;
 	unsigned int	nlink;
+	uint32_t	blksize;	/* Preferred I/O size */
+	u64		attributes;
+#define KSTAT_ATTR_FS_IOC_FLAGS				\
+	(STATX_ATTR_COMPRESSED |			\
+	 STATX_ATTR_IMMUTABLE |				\
+	 STATX_ATTR_APPEND |				\
+	 STATX_ATTR_NODUMP |				\
+	 STATX_ATTR_ENCRYPTED				\
+	 )/* Attrs corresponding to FS_*_FL flags */
+	u64		ino;
+	dev_t		dev;
+	dev_t		rdev;
 	kuid_t		uid;
 	kgid_t		gid;
-	dev_t		rdev;
 	loff_t		size;
-	struct timespec  atime;
+	struct timespec	atime;
 	struct timespec	mtime;
 	struct timespec	ctime;
-	unsigned long	blksize;
-	unsigned long long	blocks;
+	struct timespec	btime;			/* File creation time */
+	u64		blocks;
 };
 
 #endif
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 91a740f6b884..980c3c9b06f8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -48,6 +48,7 @@ struct stat;
 struct stat64;
 struct statfs;
 struct statfs64;
+struct statx;
 struct __sysctl_args;
 struct sysinfo;
 struct timespec;
@@ -902,5 +903,7 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len,
 				  unsigned long prot, int pkey);
 asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
 asmlinkage long sys_pkey_free(int pkey);
+asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
+			  unsigned mask, struct statx __user *buffer);
 
 #endif
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index beed138bd359..813afd6eee71 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -63,5 +63,10 @@
 #define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
 #define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
 
+#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
+
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7fec7e36d921..51a6b86e3700 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -1,6 +1,7 @@
 #ifndef _UAPI_LINUX_STAT_H
 #define _UAPI_LINUX_STAT_H
 
+#include <linux/types.h>
 
 #if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
 
@@ -41,5 +42,135 @@
 
 #endif
 
+/*
+ * Timestamp structure for the timestamps in struct statx.
+ *
+ * tv_sec holds the number of seconds before (negative) or after (positive)
+ * 00:00:00 1st January 1970 UTC.
+ *
+ * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
+ * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
+ *
+ * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
+ * either be both positive or both negative.
+ *
+ * __reserved is held in case we need a yet finer resolution.
+ */
+struct statx_timestamp {
+	__s64	tv_sec;
+	__s32	tv_nsec;
+	__s32	__reserved;
+};
+
+/*
+ * Structures for the extended file attribute retrieval system call
+ * (statx()).
+ *
+ * The caller passes a mask of what they're specifically interested in as a
+ * parameter to statx().  What statx() actually got will be indicated in
+ * st_mask upon return.
+ *
+ * For each bit in the mask argument:
+ *
+ * - if the datum is not supported:
+ *
+ *   - the bit will be cleared, and
+ *
+ *   - the datum will be set to an appropriate fabricated value if one is
+ *     available (eg. CIFS can take a default uid and gid), otherwise
+ *
+ *   - the field will be cleared;
+ *
+ * - otherwise, if explicitly requested:
+ *
+ *   - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
+ *     set or if the datum is considered out of date, and
+ *
+ *   - the field will be filled in and the bit will be set;
+ *
+ * - otherwise, if not requested, but available in approximate form without any
+ *   effort, it will be filled in anyway, and the bit will be set upon return
+ *   (it might not be up to date, however, and no attempt will be made to
+ *   synchronise the internal state first);
+ *
+ * - otherwise the field and the bit will be cleared before returning.
+ *
+ * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
+ * will have values installed for compatibility purposes so that stat() and
+ * co. can be emulated in userspace.
+ */
+struct statx {
+	/* 0x00 */
+	__u32	stx_mask;	/* What results were written [uncond] */
+	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
+	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
+	/* 0x10 */
+	__u32	stx_nlink;	/* Number of hard links */
+	__u32	stx_uid;	/* User ID of owner */
+	__u32	stx_gid;	/* Group ID of owner */
+	__u16	stx_mode;	/* File mode */
+	__u16	__spare0[1];
+	/* 0x20 */
+	__u64	stx_ino;	/* Inode number */
+	__u64	stx_size;	/* File size */
+	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
+	__u64	__spare1[1];
+	/* 0x40 */
+	struct statx_timestamp	stx_atime;	/* Last access time */
+	struct statx_timestamp	stx_btime;	/* File creation time */
+	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
+	struct statx_timestamp	stx_mtime;	/* Last data modification time */
+	/* 0x80 */
+	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
+	__u32	stx_rdev_minor;
+	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
+	__u32	stx_dev_minor;
+	/* 0x90 */
+	__u64	__spare2[14];	/* Spare space for future expansion */
+	/* 0x100 */
+};
+
+/*
+ * Flags to be stx_mask
+ *
+ * Query request/result mask for statx() and struct statx::stx_mask.
+ *
+ * These bits should be set in the mask argument of statx() to request
+ * particular items when calling statx().
+ */
+#define STATX_TYPE		0x00000001U	/* Want/got stx_mode & S_IFMT */
+#define STATX_MODE		0x00000002U	/* Want/got stx_mode & ~S_IFMT */
+#define STATX_NLINK		0x00000004U	/* Want/got stx_nlink */
+#define STATX_UID		0x00000008U	/* Want/got stx_uid */
+#define STATX_GID		0x00000010U	/* Want/got stx_gid */
+#define STATX_ATIME		0x00000020U	/* Want/got stx_atime */
+#define STATX_MTIME		0x00000040U	/* Want/got stx_mtime */
+#define STATX_CTIME		0x00000080U	/* Want/got stx_ctime */
+#define STATX_INO		0x00000100U	/* Want/got stx_ino */
+#define STATX_SIZE		0x00000200U	/* Want/got stx_size */
+#define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
+#define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
+#define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
+#define STATX_ALL		0x00000fffU	/* All currently supported flags */
+
+/*
+ * Attributes to be found in stx_attributes
+ *
+ * These give information about the features or the state of a file that might
+ * be of use to ordinary userspace programs such as GUIs or ls rather than
+ * specialised tools.
+ *
+ * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * semantically.  Where possible, the numerical value is picked to correspond
+ * also.
+ */
+#define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
+#define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
+#define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
+#define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
+#define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
+
+#define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+
 
 #endif /* _UAPI_LINUX_STAT_H */
diff --git a/mm/shmem.c b/mm/shmem.c
index a26649a6633f..e07728f716b2 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -958,10 +958,10 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 }
 EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
-static int shmem_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			 struct kstat *stat)
+static int shmem_getattr(const struct path *path, struct kstat *stat,
+			 u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = path->dentry->d_inode;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 
 	if (info->alloced - info->swapped != inode->i_mapping->nrpages) {
diff --git a/samples/Kconfig b/samples/Kconfig
index b124f62ed6cb..9cb63188d3ef 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -112,4 +112,10 @@ config SAMPLE_VFIO_MDEV_MTTY
 	  Build a virtual tty sample driver for use as a VFIO
 	  mediated device
 
+config SAMPLE_STATX
+	bool "Build example extended-stat using code"
+	depends on BROKEN
+	help
+	  Build example userspace program to use the new extended-stat syscall.
+
 endif # SAMPLES
diff --git a/samples/Makefile b/samples/Makefile
index 86a137e451d9..db54e766ddb1 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -3,4 +3,4 @@
 obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ trace_events/ livepatch/ \
 			   hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
 			   configfs/ connector/ v4l/ trace_printk/ blackfin/ \
-			   vfio-mdev/
+			   vfio-mdev/ statx/
diff --git a/samples/statx/Makefile b/samples/statx/Makefile
new file mode 100644
index 000000000000..1f80a3d8cf45
--- /dev/null
+++ b/samples/statx/Makefile
@@ -0,0 +1,10 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-$(CONFIG_SAMPLE_STATX) := test-statx
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS_test-statx.o += -I$(objtree)/usr/include
diff --git a/samples/statx/test-statx.c b/samples/statx/test-statx.c
new file mode 100644
index 000000000000..8571d766331d
--- /dev/null
+++ b/samples/statx/test-statx.c
@@ -0,0 +1,254 @@
+/* Test the statx() system call.
+ *
+ * Note that the output of this program is intended to look like the output of
+ * /bin/stat where possible.
+ *
+ * Copyright (C) 2015 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define _GNU_SOURCE
+#define _ATFILE_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <linux/stat.h>
+#include <linux/fcntl.h>
+#include <sys/stat.h>
+
+#define AT_STATX_SYNC_TYPE	0x6000
+#define AT_STATX_SYNC_AS_STAT	0x0000
+#define AT_STATX_FORCE_SYNC	0x2000
+#define AT_STATX_DONT_SYNC	0x4000
+
+static __attribute__((unused))
+ssize_t statx(int dfd, const char *filename, unsigned flags,
+	      unsigned int mask, struct statx *buffer)
+{
+	return syscall(__NR_statx, dfd, filename, flags, mask, buffer);
+}
+
+static void print_time(const char *field, struct statx_timestamp *ts)
+{
+	struct tm tm;
+	time_t tim;
+	char buffer[100];
+	int len;
+
+	tim = ts->tv_sec;
+	if (!localtime_r(&tim, &tm)) {
+		perror("localtime_r");
+		exit(1);
+	}
+	len = strftime(buffer, 100, "%F %T", &tm);
+	if (len == 0) {
+		perror("strftime");
+		exit(1);
+	}
+	printf("%s", field);
+	fwrite(buffer, 1, len, stdout);
+	printf(".%09u", ts->tv_nsec);
+	len = strftime(buffer, 100, "%z", &tm);
+	if (len == 0) {
+		perror("strftime2");
+		exit(1);
+	}
+	fwrite(buffer, 1, len, stdout);
+	printf("\n");
+}
+
+static void dump_statx(struct statx *stx)
+{
+	char buffer[256], ft = '?';
+
+	printf("results=%x\n", stx->stx_mask);
+
+	printf(" ");
+	if (stx->stx_mask & STATX_SIZE)
+		printf(" Size: %-15llu", (unsigned long long)stx->stx_size);
+	if (stx->stx_mask & STATX_BLOCKS)
+		printf(" Blocks: %-10llu", (unsigned long long)stx->stx_blocks);
+	printf(" IO Block: %-6llu", (unsigned long long)stx->stx_blksize);
+	if (stx->stx_mask & STATX_TYPE) {
+		switch (stx->stx_mode & S_IFMT) {
+		case S_IFIFO:	printf("  FIFO\n");			ft = 'p'; break;
+		case S_IFCHR:	printf("  character special file\n");	ft = 'c'; break;
+		case S_IFDIR:	printf("  directory\n");		ft = 'd'; break;
+		case S_IFBLK:	printf("  block special file\n");	ft = 'b'; break;
+		case S_IFREG:	printf("  regular file\n");		ft = '-'; break;
+		case S_IFLNK:	printf("  symbolic link\n");		ft = 'l'; break;
+		case S_IFSOCK:	printf("  socket\n");			ft = 's'; break;
+		default:
+			printf(" unknown type (%o)\n", stx->stx_mode & S_IFMT);
+			break;
+		}
+	} else {
+		printf(" no type\n");
+	}
+
+	sprintf(buffer, "%02x:%02x", stx->stx_dev_major, stx->stx_dev_minor);
+	printf("Device: %-15s", buffer);
+	if (stx->stx_mask & STATX_INO)
+		printf(" Inode: %-11llu", (unsigned long long) stx->stx_ino);
+	if (stx->stx_mask & STATX_NLINK)
+		printf(" Links: %-5u", stx->stx_nlink);
+	if (stx->stx_mask & STATX_TYPE) {
+		switch (stx->stx_mode & S_IFMT) {
+		case S_IFBLK:
+		case S_IFCHR:
+			printf(" Device type: %u,%u",
+			       stx->stx_rdev_major, stx->stx_rdev_minor);
+			break;
+		}
+	}
+	printf("\n");
+
+	if (stx->stx_mask & STATX_MODE)
+		printf("Access: (%04o/%c%c%c%c%c%c%c%c%c%c)  ",
+		       stx->stx_mode & 07777,
+		       ft,
+		       stx->stx_mode & S_IRUSR ? 'r' : '-',
+		       stx->stx_mode & S_IWUSR ? 'w' : '-',
+		       stx->stx_mode & S_IXUSR ? 'x' : '-',
+		       stx->stx_mode & S_IRGRP ? 'r' : '-',
+		       stx->stx_mode & S_IWGRP ? 'w' : '-',
+		       stx->stx_mode & S_IXGRP ? 'x' : '-',
+		       stx->stx_mode & S_IROTH ? 'r' : '-',
+		       stx->stx_mode & S_IWOTH ? 'w' : '-',
+		       stx->stx_mode & S_IXOTH ? 'x' : '-');
+	if (stx->stx_mask & STATX_UID)
+		printf("Uid: %5d   ", stx->stx_uid);
+	if (stx->stx_mask & STATX_GID)
+		printf("Gid: %5d\n", stx->stx_gid);
+
+	if (stx->stx_mask & STATX_ATIME)
+		print_time("Access: ", &stx->stx_atime);
+	if (stx->stx_mask & STATX_MTIME)
+		print_time("Modify: ", &stx->stx_mtime);
+	if (stx->stx_mask & STATX_CTIME)
+		print_time("Change: ", &stx->stx_ctime);
+	if (stx->stx_mask & STATX_BTIME)
+		print_time(" Birth: ", &stx->stx_btime);
+
+	if (stx->stx_attributes) {
+		unsigned char bits;
+		int loop, byte;
+
+		static char attr_representation[64 + 1] =
+			/* STATX_ATTR_ flags: */
+			"????????"	/* 63-56 */
+			"????????"	/* 55-48 */
+			"????????"	/* 47-40 */
+			"????????"	/* 39-32 */
+			"????????"	/* 31-24	0x00000000-ff000000 */
+			"????????"	/* 23-16	0x00000000-00ff0000 */
+			"???me???"	/* 15- 8	0x00000000-0000ff00 */
+			"?dai?c??"	/*  7- 0	0x00000000-000000ff */
+			;
+
+		printf("Attributes: %016llx (", stx->stx_attributes);
+		for (byte = 64 - 8; byte >= 0; byte -= 8) {
+			bits = stx->stx_attributes >> byte;
+			for (loop = 7; loop >= 0; loop--) {
+				int bit = byte + loop;
+
+				if (bits & 0x80)
+					putchar(attr_representation[63 - bit]);
+				else
+					putchar('-');
+				bits <<= 1;
+			}
+			if (byte)
+				putchar(' ');
+		}
+		printf(")\n");
+	}
+}
+
+static void dump_hex(unsigned long long *data, int from, int to)
+{
+	unsigned offset, print_offset = 1, col = 0;
+
+	from /= 8;
+	to = (to + 7) / 8;
+
+	for (offset = from; offset < to; offset++) {
+		if (print_offset) {
+			printf("%04x: ", offset * 8);
+			print_offset = 0;
+		}
+		printf("%016llx", data[offset]);
+		col++;
+		if ((col & 3) == 0) {
+			printf("\n");
+			print_offset = 1;
+		} else {
+			printf(" ");
+		}
+	}
+
+	if (!print_offset)
+		printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct statx stx;
+	int ret, raw = 0, atflag = AT_SYMLINK_NOFOLLOW;
+
+	unsigned int mask = STATX_ALL;
+
+	for (argv++; *argv; argv++) {
+		if (strcmp(*argv, "-F") == 0) {
+			atflag &= ~AT_STATX_SYNC_TYPE;
+			atflag |= AT_STATX_FORCE_SYNC;
+			continue;
+		}
+		if (strcmp(*argv, "-D") == 0) {
+			atflag &= ~AT_STATX_SYNC_TYPE;
+			atflag |= AT_STATX_DONT_SYNC;
+			continue;
+		}
+		if (strcmp(*argv, "-L") == 0) {
+			atflag &= ~AT_SYMLINK_NOFOLLOW;
+			continue;
+		}
+		if (strcmp(*argv, "-O") == 0) {
+			mask &= ~STATX_BASIC_STATS;
+			continue;
+		}
+		if (strcmp(*argv, "-A") == 0) {
+			atflag |= AT_NO_AUTOMOUNT;
+			continue;
+		}
+		if (strcmp(*argv, "-R") == 0) {
+			raw = 1;
+			continue;
+		}
+
+		memset(&stx, 0xbf, sizeof(stx));
+		ret = statx(AT_FDCWD, *argv, atflag, mask, &stx);
+		printf("statx(%s) = %d\n", *argv, ret);
+		if (ret < 0) {
+			perror(*argv);
+			exit(1);
+		}
+
+		if (raw)
+			dump_hex((unsigned long long *)&stx, 0, sizeof(stx));
+
+		dump_statx(&stx);
+	}
+	return 0;
+}
-- 
GitLab


From c74042f3b3ca982652af99cad85252a2655c6064 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 3 Feb 2017 09:19:40 -0800
Subject: [PATCH 670/898] ixgbe: Limit use of 2K buffers on architectures with
 256B or larger cache lines

On architectures that have a cache line size larger than 64 Bytes we start
running into issues where the amount of headroom for the frame starts
shrinking.

The size of skb_shared_info on a system with a 64B L1 cache line size is
320.  This increases to 384 with a 128B cache line, and 512 with a 256B
cache line.

In addition the NET_SKB_PAD value increases as well consistent with the
cache line size.  As a result when we get to a 256B cache line as seen on
the s390 we end up 768 bytes used by padding and shared info leaving us
with only 1280 bytes to use for data storage.  On architectures such as
this we should default to using 3K Rx buffers out of a 8K page instead of
trying to do 1.5K buffers out of a 4K page.

To take all of this into account I have added one small check so that we
compare the max_frame to the amount of actual data we can store.  This was
already occurring for igb, but I had overlooked it for ixgbe as it doesn't
have strict limits for 82599 once we enable jumbo frames.  By adding this
check we will automatically enable 3K Rx buffers as soon as the maximum
frame size we can handle drops below the standard Ethernet MTU.

I also went through and fixed one small typo that I found where I had left
an IGB in a variable name due to a copy/paste error.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h      | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 7a951b116821..b1ecc2627a5a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -96,7 +96,7 @@
 #define IXGBE_MAX_FRAME_BUILD_SKB \
 	(SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K) - IXGBE_SKB_PAD)
 #else
-#define IGB_MAX_FRAME_BUILD_SKB IXGBE_RXBUFFER_2K
+#define IXGBE_MAX_FRAME_BUILD_SKB IXGBE_RXBUFFER_2K
 #endif
 
 /*
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 67ab13fd163c..a7a430a7be2c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3972,7 +3972,8 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
 		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 
-		if (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))
+		if ((max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)) ||
+		    (max_frame > IXGBE_MAX_FRAME_BUILD_SKB))
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 #endif
 	}
-- 
GitLab


From 284316dd42a2027afe37df34c5199eb4eabed8fd Mon Sep 17 00:00:00 2001
From: Steve French <smfrench@gmail.com>
Date: Thu, 2 Mar 2017 15:42:48 -0600
Subject: [PATCH 671/898] CIFS: Fix sparse warnings

Fix two minor sparse compile check warnings

Signed-off-by: Steve French <steve.french@primarydata.com>
Acked-by: Pavel Shilovsky <pshilov@microsoft.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/cifs_unicode.h | 6 +++---
 fs/cifs/cifssmb.c      | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index 479bc0a941f3..3d7298cc0aeb 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -130,10 +130,10 @@ wchar_t cifs_toupper(wchar_t in);
  * Returns:
  *     Address of the first string
  */
-static inline wchar_t *
-UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
+static inline __le16 *
+UniStrcat(__le16 *ucs1, const __le16 *ucs2)
 {
-	wchar_t *anchor = ucs1;	/* save a pointer to start of ucs1 */
+	__le16 *anchor = ucs1;	/* save a pointer to start of ucs1 */
 
 	while (*ucs1++) ;	/* To end of first string */
 	ucs1--;			/* Return to the null */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 5005c7995b6a..066950671929 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -4886,7 +4886,7 @@ CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses,
 				 le16_to_cpu(pSMBr->t2.DataCount),
 				 num_of_nodes, target_nodes, nls_codepage,
 				 remap, search_name,
-				 pSMBr->hdr.Flags2 & SMBFLG2_UNICODE);
+				 (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) != 0);
 
 GetDFSRefExit:
 	cifs_buf_release(pSMB);
-- 
GitLab


From ef65aaede23f75977af56a8c330bb9be8c6e125c Mon Sep 17 00:00:00 2001
From: Sachin Prabhu <sprabhu@redhat.com>
Date: Wed, 18 Jan 2017 15:35:57 +0530
Subject: [PATCH 672/898] smb2: Enforce sec= mount option

If the security type specified using a mount option is not supported,
the SMB2 session setup code changes the security type to RawNTLMSSP. We
should instead fail the mount and return an error.

The patch changes the code for SMB2 to make it similar to the code used
for SMB1. Like in SMB1, we now use the global security flags to select
the security method to be used when no security method is specified and
to return an error when the requested auth method is not available.

For SMB2, we also use ntlmv2 as a synonym for nltmssp.

Signed-off-by: Sachin Prabhu <sprabhu@redhat.com>
Acked-by: Pavel Shilovsky <pshilov@microsoft.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <smfrench@gmail.com>
---
 fs/cifs/cifsglob.h  |  3 +++
 fs/cifs/cifsproto.h |  2 ++
 fs/cifs/connect.c   |  3 ++-
 fs/cifs/sess.c      |  4 ++--
 fs/cifs/smb1ops.c   |  1 +
 fs/cifs/smb2ops.c   |  4 ++++
 fs/cifs/smb2pdu.c   | 37 +++++++++++++++++++++++++++++++++----
 fs/cifs/smb2proto.h |  2 ++
 8 files changed, 49 insertions(+), 7 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index af224cda8697..d42dd3288647 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -443,6 +443,9 @@ struct smb_version_operations {
 	int (*is_transform_hdr)(void *buf);
 	int (*receive_transform)(struct TCP_Server_Info *,
 				 struct mid_q_entry **);
+	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
+			    enum securityEnum);
+
 };
 
 struct smb_version_values {
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 9ee46c1c3ebd..97e5d236d265 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -533,4 +533,6 @@ int cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 int __cifs_calc_signature(struct smb_rqst *rqst,
 			struct TCP_Server_Info *server, char *signature,
 			struct shash_desc *shash);
+enum securityEnum cifs_select_sectype(struct TCP_Server_Info *,
+					enum securityEnum);
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 777ad9f4fc3c..de4c56e8fb37 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2073,7 +2073,8 @@ match_security(struct TCP_Server_Info *server, struct smb_vol *vol)
 	 * that was specified, or "Unspecified" if that sectype was not
 	 * compatible with the given NEGOTIATE request.
 	 */
-	if (select_sectype(server, vol->sectype) == Unspecified)
+	if (server->ops->select_sectype(server, vol->sectype)
+	     == Unspecified)
 		return false;
 
 	/*
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index dcbcc927399a..8b0502cd39af 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -498,7 +498,7 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 }
 
 enum securityEnum
-select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
+cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 {
 	switch (server->negflavor) {
 	case CIFS_NEGFLAVOR_EXTENDED:
@@ -1391,7 +1391,7 @@ static int select_sec(struct cifs_ses *ses, struct sess_data *sess_data)
 {
 	int type;
 
-	type = select_sectype(ses->server, ses->sectype);
+	type = cifs_select_sectype(ses->server, ses->sectype);
 	cifs_dbg(FYI, "sess setup type %d\n", type);
 	if (type == Unspecified) {
 		cifs_dbg(VFS,
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 67a987e4d026..cc93ba4da9b5 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -1087,6 +1087,7 @@ struct smb_version_operations smb1_operations = {
 	.is_read_op = cifs_is_read_op,
 	.wp_retry_size = cifs_wp_retry_size,
 	.dir_needs_close = cifs_dir_needs_close,
+	.select_sectype = cifs_select_sectype,
 #ifdef CONFIG_CIFS_XATTR
 	.query_all_EAs = CIFSSMBQAllEAs,
 	.set_EA = CIFSSMBSetEA,
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index b360c381b00e..0231108d9387 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2381,6 +2381,7 @@ struct smb_version_operations smb20_operations = {
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
 };
 
 struct smb_version_operations smb21_operations = {
@@ -2463,6 +2464,7 @@ struct smb_version_operations smb21_operations = {
 	.dir_needs_close = smb2_dir_needs_close,
 	.enum_snapshots = smb3_enum_snapshots,
 	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
 };
 
 struct smb_version_operations smb30_operations = {
@@ -2555,6 +2557,7 @@ struct smb_version_operations smb30_operations = {
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
 	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
 };
 
 #ifdef CONFIG_CIFS_SMB311
@@ -2648,6 +2651,7 @@ struct smb_version_operations smb311_operations = {
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
 	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
 };
 #endif /* CIFS_SMB311 */
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2069431b32e3..7446496850a3 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -657,6 +657,28 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 	return -EIO;
 }
 
+enum securityEnum
+smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
+{
+	switch (requested) {
+	case Kerberos:
+	case RawNTLMSSP:
+		return requested;
+	case NTLMv2:
+		return RawNTLMSSP;
+	case Unspecified:
+		if (server->sec_ntlmssp &&
+			(global_secflags & CIFSSEC_MAY_NTLMSSP))
+			return RawNTLMSSP;
+		if ((server->sec_kerberos || server->sec_mskerberos) &&
+			(global_secflags & CIFSSEC_MAY_KRB5))
+			return Kerberos;
+		/* Fallthrough */
+	default:
+		return Unspecified;
+	}
+}
+
 struct SMB2_sess_data {
 	unsigned int xid;
 	struct cifs_ses *ses;
@@ -1009,10 +1031,17 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
 static int
 SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data)
 {
-	if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
-		ses->sectype = RawNTLMSSP;
+	int type;
+
+	type = smb2_select_sectype(ses->server, ses->sectype);
+	cifs_dbg(FYI, "sess setup type %d\n", type);
+	if (type == Unspecified) {
+		cifs_dbg(VFS,
+			"Unable to select appropriate authentication method!");
+		return -EINVAL;
+	}
 
-	switch (ses->sectype) {
+	switch (type) {
 	case Kerberos:
 		sess_data->func = SMB2_auth_kerberos;
 		break;
@@ -1020,7 +1049,7 @@ SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data)
 		sess_data->func = SMB2_sess_auth_rawntlmssp_negotiate;
 		break;
 	default:
-		cifs_dbg(VFS, "secType %d not supported!\n", ses->sectype);
+		cifs_dbg(VFS, "secType %d not supported!\n", type);
 		return -EOPNOTSUPP;
 	}
 
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 11d9f3013db8..69e35873b1de 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -181,4 +181,6 @@ extern int SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 			    __u8 *lease_key, const __le32 lease_state);
 extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
+extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
+					enum securityEnum);
 #endif			/* _SMB2PROTO_H */
-- 
GitLab


From 0265634eb9e04a16ae99941c320718c38eb865e0 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Sat, 25 Feb 2017 08:28:16 -0300
Subject: [PATCH 673/898] [media] serial_ir: ensure we're ready to receive
 interrupts

When the interrupt requested with devm_request_irq(), serial_ir.rcdev
is still null so will cause null deference if the irq handler is called
early on.

Also ensure that timeout_timer is setup.

Link: http://lkml.kernel.org/r/CA+55aFxsh2uF8gi5sN_guY3Z+tiLv7LpJYKBw+y8vqLzp+TsnQ@mail.gmail.com

[mchehab@s-opensource.com: moved serial_ir_probe() back to its original place]

Cc: <stable@vger.kernel.org> # 4.10
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
---
 drivers/media/rc/serial_ir.c | 123 ++++++++++++++++++-----------------
 1 file changed, 62 insertions(+), 61 deletions(-)

diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c
index 923fb2299553..41b54e40176c 100644
--- a/drivers/media/rc/serial_ir.c
+++ b/drivers/media/rc/serial_ir.c
@@ -487,10 +487,69 @@ static void serial_ir_timeout(unsigned long arg)
 	ir_raw_event_handle(serial_ir.rcdev);
 }
 
+/* Needed by serial_ir_probe() */
+static int serial_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
+			unsigned int count);
+static int serial_ir_tx_duty_cycle(struct rc_dev *dev, u32 cycle);
+static int serial_ir_tx_carrier(struct rc_dev *dev, u32 carrier);
+static int serial_ir_open(struct rc_dev *rcdev);
+static void serial_ir_close(struct rc_dev *rcdev);
+
 static int serial_ir_probe(struct platform_device *dev)
 {
+	struct rc_dev *rcdev;
 	int i, nlow, nhigh, result;
 
+	rcdev = devm_rc_allocate_device(&dev->dev, RC_DRIVER_IR_RAW);
+	if (!rcdev)
+		return -ENOMEM;
+
+	if (hardware[type].send_pulse && hardware[type].send_space)
+		rcdev->tx_ir = serial_ir_tx;
+	if (hardware[type].set_send_carrier)
+		rcdev->s_tx_carrier = serial_ir_tx_carrier;
+	if (hardware[type].set_duty_cycle)
+		rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle;
+
+	switch (type) {
+	case IR_HOMEBREW:
+		rcdev->input_name = "Serial IR type home-brew";
+		break;
+	case IR_IRDEO:
+		rcdev->input_name = "Serial IR type IRdeo";
+		break;
+	case IR_IRDEO_REMOTE:
+		rcdev->input_name = "Serial IR type IRdeo remote";
+		break;
+	case IR_ANIMAX:
+		rcdev->input_name = "Serial IR type AnimaX";
+		break;
+	case IR_IGOR:
+		rcdev->input_name = "Serial IR type IgorPlug";
+		break;
+	}
+
+	rcdev->input_phys = KBUILD_MODNAME "/input0";
+	rcdev->input_id.bustype = BUS_HOST;
+	rcdev->input_id.vendor = 0x0001;
+	rcdev->input_id.product = 0x0001;
+	rcdev->input_id.version = 0x0100;
+	rcdev->open = serial_ir_open;
+	rcdev->close = serial_ir_close;
+	rcdev->dev.parent = &serial_ir.pdev->dev;
+	rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER;
+	rcdev->driver_name = KBUILD_MODNAME;
+	rcdev->map_name = RC_MAP_RC6_MCE;
+	rcdev->min_timeout = 1;
+	rcdev->timeout = IR_DEFAULT_TIMEOUT;
+	rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
+	rcdev->rx_resolution = 250000;
+
+	serial_ir.rcdev = rcdev;
+
+	setup_timer(&serial_ir.timeout_timer, serial_ir_timeout,
+		    (unsigned long)&serial_ir);
+
 	result = devm_request_irq(&dev->dev, irq, serial_ir_irq_handler,
 				  share_irq ? IRQF_SHARED : 0,
 				  KBUILD_MODNAME, &hardware);
@@ -516,9 +575,6 @@ static int serial_ir_probe(struct platform_device *dev)
 		return -EBUSY;
 	}
 
-	setup_timer(&serial_ir.timeout_timer, serial_ir_timeout,
-		    (unsigned long)&serial_ir);
-
 	result = hardware_init_port();
 	if (result < 0)
 		return result;
@@ -552,7 +608,8 @@ static int serial_ir_probe(struct platform_device *dev)
 			 sense ? "low" : "high");
 
 	dev_dbg(&dev->dev, "Interrupt %d, port %04x obtained\n", irq, io);
-	return 0;
+
+	return devm_rc_register_device(&dev->dev, rcdev);
 }
 
 static int serial_ir_open(struct rc_dev *rcdev)
@@ -723,7 +780,6 @@ static void serial_ir_exit(void)
 
 static int __init serial_ir_init_module(void)
 {
-	struct rc_dev *rcdev;
 	int result;
 
 	switch (type) {
@@ -754,63 +810,9 @@ static int __init serial_ir_init_module(void)
 		sense = !!sense;
 
 	result = serial_ir_init();
-	if (result)
-		return result;
-
-	rcdev = devm_rc_allocate_device(&serial_ir.pdev->dev, RC_DRIVER_IR_RAW);
-	if (!rcdev) {
-		result = -ENOMEM;
-		goto serial_cleanup;
-	}
-
-	if (hardware[type].send_pulse && hardware[type].send_space)
-		rcdev->tx_ir = serial_ir_tx;
-	if (hardware[type].set_send_carrier)
-		rcdev->s_tx_carrier = serial_ir_tx_carrier;
-	if (hardware[type].set_duty_cycle)
-		rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle;
-
-	switch (type) {
-	case IR_HOMEBREW:
-		rcdev->input_name = "Serial IR type home-brew";
-		break;
-	case IR_IRDEO:
-		rcdev->input_name = "Serial IR type IRdeo";
-		break;
-	case IR_IRDEO_REMOTE:
-		rcdev->input_name = "Serial IR type IRdeo remote";
-		break;
-	case IR_ANIMAX:
-		rcdev->input_name = "Serial IR type AnimaX";
-		break;
-	case IR_IGOR:
-		rcdev->input_name = "Serial IR type IgorPlug";
-		break;
-	}
-
-	rcdev->input_phys = KBUILD_MODNAME "/input0";
-	rcdev->input_id.bustype = BUS_HOST;
-	rcdev->input_id.vendor = 0x0001;
-	rcdev->input_id.product = 0x0001;
-	rcdev->input_id.version = 0x0100;
-	rcdev->open = serial_ir_open;
-	rcdev->close = serial_ir_close;
-	rcdev->dev.parent = &serial_ir.pdev->dev;
-	rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER;
-	rcdev->driver_name = KBUILD_MODNAME;
-	rcdev->map_name = RC_MAP_RC6_MCE;
-	rcdev->min_timeout = 1;
-	rcdev->timeout = IR_DEFAULT_TIMEOUT;
-	rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
-	rcdev->rx_resolution = 250000;
-
-	serial_ir.rcdev = rcdev;
-
-	result = rc_register_device(rcdev);
-
 	if (!result)
 		return 0;
-serial_cleanup:
+
 	serial_ir_exit();
 	return result;
 }
@@ -818,7 +820,6 @@ static int __init serial_ir_init_module(void)
 static void __exit serial_ir_exit_module(void)
 {
 	del_timer_sync(&serial_ir.timeout_timer);
-	rc_unregister_device(serial_ir.rcdev);
 	serial_ir_exit();
 }
 
-- 
GitLab


From 2e1e4949f9dfb053122785cd73540bb1e61f768b Mon Sep 17 00:00:00 2001
From: Qi Hou <qi.hou@windriver.com>
Date: Fri, 3 Mar 2017 15:57:11 +0800
Subject: [PATCH 674/898] i2c: add missing of_node_put in i2c_mux_del_adapters

Refcount of of_node is increased with of_node_get() in i2c_mux_add_adapter().
It must be decreased with of_node_put() in i2c_mux_del_adapters().

Cc: stable@vger.kernel.org
Signed-off-by: Qi Hou <qi.hou@windriver.com>
Reviewed-by: Zhang Xiao <xiao.zhang@windriver.com>
Signed-off-by: Peter Rosin <peda@axentia.se>
---
 drivers/i2c/i2c-mux.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 83768e85a919..2178266bca79 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -429,6 +429,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 	while (muxc->num_adapters) {
 		struct i2c_adapter *adap = muxc->adapter[--muxc->num_adapters];
 		struct i2c_mux_priv *priv = adap->algo_data;
+		struct device_node *np = adap->dev.of_node;
 
 		muxc->adapter[muxc->num_adapters] = NULL;
 
@@ -438,6 +439,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 
 		sysfs_remove_link(&priv->adap.dev.kobj, "mux_device");
 		i2c_del_adapter(adap);
+		of_node_put(np);
 		kfree(priv);
 	}
 }
-- 
GitLab


From db5b15b74ed9a5c04bb808d18ffa2c773f5c18c0 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Mon, 13 Feb 2017 10:35:44 -0200
Subject: [PATCH 675/898] [media] lirc: fix dead lock between open and
 wakeup_filter

The locking in lirc needs improvement, but for now just fix this potential
deadlock.

======================================================
[ INFO: possible circular locking dependency detected ]
4.10.0-rc1+ #1 Not tainted
-------------------------------------------------------
bash/2502 is trying to acquire lock:
 (ir_raw_handler_lock){+.+.+.}, at: [<ffffffffc06f6a5e>] ir_raw_encode_scancode+0x3e/0xb0 [rc_core]

               but task is already holding lock:
 (&dev->lock){+.+.+.}, at: [<ffffffffc06f511f>] store_filter+0x9f/0x240 [rc_core]

               which lock already depends on the new lock.

               the existing dependency chain (in reverse order) is:

               -> #2 (&dev->lock){+.+.+.}:

[<ffffffffa110adad>] lock_acquire+0xfd/0x200
[<ffffffffa1921327>] mutex_lock_nested+0x77/0x6d0
[<ffffffffc06f436a>] rc_open+0x2a/0x80 [rc_core]
[<ffffffffc07114ca>] lirc_dev_fop_open+0xda/0x1e0 [lirc_dev]
[<ffffffffa12975e0>] chrdev_open+0xb0/0x210
[<ffffffffa128eb5a>] do_dentry_open+0x20a/0x2f0
[<ffffffffa128ffcc>] vfs_open+0x4c/0x80
[<ffffffffa12a35ec>] path_openat+0x5bc/0xc00
[<ffffffffa12a5271>] do_filp_open+0x91/0x100
[<ffffffffa12903f0>] do_sys_open+0x130/0x220
[<ffffffffa12904fe>] SyS_open+0x1e/0x20
[<ffffffffa19278c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
               -> #1 (lirc_dev_lock){+.+.+.}:
[<ffffffffa110adad>] lock_acquire+0xfd/0x200
[<ffffffffa1921327>] mutex_lock_nested+0x77/0x6d0
[<ffffffffc0711f47>] lirc_register_driver+0x67/0x59b [lirc_dev]
[<ffffffffc06db7f4>] ir_lirc_register+0x1f4/0x260 [ir_lirc_codec]
[<ffffffffc06f6cac>] ir_raw_handler_register+0x7c/0xb0 [rc_core]
[<ffffffffc0398010>] 0xffffffffc0398010
[<ffffffffa1002192>] do_one_initcall+0x52/0x1b0
[<ffffffffa11ef5c8>] do_init_module+0x5f/0x1fa
[<ffffffffa11566b5>] load_module+0x2675/0x2b00
[<ffffffffa1156dcf>] SYSC_finit_module+0xdf/0x110
[<ffffffffa1156e1e>] SyS_finit_module+0xe/0x10
[<ffffffffa1003f5c>] do_syscall_64+0x6c/0x1f0
[<ffffffffa1927989>] return_from_SYSCALL_64+0x0/0x7a
               -> #0 (ir_raw_handler_lock){+.+.+.}:
[<ffffffffa110a7b7>] __lock_acquire+0x10f7/0x1290
[<ffffffffa110adad>] lock_acquire+0xfd/0x200
[<ffffffffa1921327>] mutex_lock_nested+0x77/0x6d0
[<ffffffffc06f6a5e>] ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
[<ffffffffc0b0f492>] loop_set_wakeup_filter+0x62/0xbd [rc_loopback]
[<ffffffffc06f522a>] store_filter+0x1aa/0x240 [rc_core]
[<ffffffffa15e46f8>] dev_attr_store+0x18/0x30
[<ffffffffa13318e5>] sysfs_kf_write+0x45/0x60
[<ffffffffa1330b55>] kernfs_fop_write+0x155/0x1e0
[<ffffffffa1290797>] __vfs_write+0x37/0x160
[<ffffffffa12921f8>] vfs_write+0xc8/0x1e0
[<ffffffffa12936e8>] SyS_write+0x58/0xc0
[<ffffffffa19278c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2

               other info that might help us debug this:

Chain exists of:
                 ir_raw_handler_lock --> lirc_dev_lock --> &dev->lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&dev->lock);
                               lock(lirc_dev_lock);
                               lock(&dev->lock);
  lock(ir_raw_handler_lock);

                *** DEADLOCK ***

4 locks held by bash/2502:
 #0:  (sb_writers#4){.+.+.+}, at: [<ffffffffa12922c5>] vfs_write+0x195/0x1e0
 #1:  (&of->mutex){+.+.+.}, at: [<ffffffffa1330b1f>] kernfs_fop_write+0x11f/0x1e0
 #2:  (s_active#215){.+.+.+}, at: [<ffffffffa1330b28>] kernfs_fop_write+0x128/0x1e0
 #3:  (&dev->lock){+.+.+.}, at: [<ffffffffc06f511f>] store_filter+0x9f/0x240 [rc_core]

               stack backtrace:
CPU: 3 PID: 2502 Comm: bash Not tainted 4.10.0-rc1+ #1
Hardware name:                  /DG45ID, BIOS IDG4510H.86A.0135.2011.0225.1100 02/25/2011
Call Trace:
 dump_stack+0x86/0xc3
 print_circular_bug+0x1be/0x210
 __lock_acquire+0x10f7/0x1290
 lock_acquire+0xfd/0x200
 ? ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 ? ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 mutex_lock_nested+0x77/0x6d0
 ? ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 ? loop_set_wakeup_filter+0x44/0xbd [rc_loopback]
 ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 loop_set_wakeup_filter+0x62/0xbd [rc_loopback]
 ? loop_set_tx_duty_cycle+0x70/0x70 [rc_loopback]
 store_filter+0x1aa/0x240 [rc_core]
 dev_attr_store+0x18/0x30
 sysfs_kf_write+0x45/0x60
 kernfs_fop_write+0x155/0x1e0
 __vfs_write+0x37/0x160
 ? rcu_read_lock_sched_held+0x4a/0x80
 ? rcu_sync_lockdep_assert+0x2f/0x60
 ? __sb_start_write+0x10c/0x220
 ? vfs_write+0x195/0x1e0
 ? security_file_permission+0x3b/0xc0
 vfs_write+0xc8/0x1e0
 SyS_write+0x58/0xc0
 entry_SYSCALL_64_fastpath+0x1f/0xc2

Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
---
 drivers/media/rc/lirc_dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index a54ca531d8ef..4630f3e67538 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -436,6 +436,8 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
 		return -ERESTARTSYS;
 
 	ir = irctls[iminor(inode)];
+	mutex_unlock(&lirc_dev_lock);
+
 	if (!ir) {
 		retval = -ENODEV;
 		goto error;
@@ -476,8 +478,6 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
 	}
 
 error:
-	mutex_unlock(&lirc_dev_lock);
-
 	nonseekable_open(inode, file);
 
 	return retval;
-- 
GitLab


From c1305a40722f3e02f3d971acc22f5991aff239a6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 12 Feb 2017 15:01:22 -0200
Subject: [PATCH 676/898] [media] rc: nuvoton: fix deadlock in
 nvt_write_wakeup_codes

nvt_write_wakeup_codes acquires the same lock as the ISR but doesn't
disable interrupts on the local CPU. This caused the following
deadlock. Fix this by using spin_lock_irqsave.

[  432.362008] ================================
[  432.362074] WARNING: inconsistent lock state
[  432.362144] 4.10.0-rc7-next-20170210 #1 Not tainted
[  432.362219] --------------------------------
[  432.362286] inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
[  432.362379] swapper/0/0 [HC1[1]:SC0[0]:HE0:SE1] takes:
[  432.362457]  (&(&nvt->lock)->rlock){?.+...}, at: [<ffffffffa016b17d>] nvt_cir_isr+0x2d/0x520 [nuvoton_cir]
[  432.362611] {HARDIRQ-ON-W} state was registered at:
[  432.362686]
[  432.362698] [<ffffffff810adb7c>] __lock_acquire+0x5dc/0x1260
[  432.362812]
[  432.362817] [<ffffffff810aec29>] lock_acquire+0xe9/0x1d0
[  432.362927]
[  432.362934] [<ffffffff81609f63>] _raw_spin_lock+0x33/0x50
[  432.363045]
[  432.363051] [<ffffffffa016b822>] nvt_write_wakeup_codes.isra.12+0x22/0xe0 [nuvoton_cir]
[  432.363193]
[  432.363199] [<ffffffffa016b9bf>] wakeup_data_store+0xdf/0xf0 [nuvoton_cir]
[  432.363327]
[  432.363333] [<ffffffff81484223>] dev_attr_store+0x13/0x20
[  432.363441]
[  432.363449] [<ffffffff81232450>] sysfs_kf_write+0x40/0x50
[  432.363558]
[  432.363564] [<ffffffff81231640>] kernfs_fop_write+0x150/0x1e0
[  432.363676]
[  432.363685] [<ffffffff811b36a3>] __vfs_write+0x23/0x120
[  432.363791]
[  432.363798] [<ffffffff811b4d53>] vfs_write+0xc3/0x1e0
[  432.363902]
[  432.363909] [<ffffffff811b6124>] SyS_write+0x44/0xa0
[  432.364012]
[  432.364021] [<ffffffff81002c47>] do_syscall_64+0x57/0x140
[  432.364129]
[  432.364135] [<ffffffff8160a9e4>] return_from_SYSCALL_64+0x0/0x7a
[  432.364252] irq event stamp: 415118
[  432.364313] hardirqs last  enabled at (415115): [<ffffffff814fd2eb>] cpuidle_enter_state+0x11b/0x370
[  432.364445] hardirqs last disabled at (415116): [<ffffffff8160b2cb>] common_interrupt+0x8b/0x90
[  432.364573] softirqs last  enabled at (415118): [<ffffffff8106157c>] _local_bh_enable+0x1c/0x50
[  432.364699] softirqs last disabled at (415117): [<ffffffff810629a3>] irq_enter+0x43/0x60
[  432.364814]
               other info that might help us debug this:
[  432.364909]  Possible unsafe locking scenario:

[  432.367821]        CPU0
[  432.370645]        ----
[  432.373432]   lock(&(&nvt->lock)->rlock);
[  432.376228]   <Interrupt>
[  432.378982]     lock(&(&nvt->lock)->rlock);
[  432.381757]
                *** DEADLOCK ***

[  432.389888] no locks held by swapper/0/0.
[  432.392574]
               stack backtrace:
[  432.397774] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.10.0-rc7-next-20170210 #1
[  432.400375] Hardware name: ZOTAC ZBOX-CI321NANO/ZBOX-CI321NANO, BIOS B246P105 06/01/2015
[  432.403023] Call Trace:
[  432.405636]  <IRQ>
[  432.408208]  dump_stack+0x68/0x93
[  432.410775]  print_usage_bug+0x1dd/0x1f0
[  432.413334]  mark_lock+0x559/0x5c0
[  432.415871]  ? print_shortest_lock_dependencies+0x1a0/0x1a0
[  432.418431]  __lock_acquire+0x6b1/0x1260
[  432.420941]  lock_acquire+0xe9/0x1d0
[  432.423396]  ? nvt_cir_isr+0x2d/0x520 [nuvoton_cir]
[  432.425844]  _raw_spin_lock+0x33/0x50
[  432.428252]  ? nvt_cir_isr+0x2d/0x520 [nuvoton_cir]
[  432.430670]  nvt_cir_isr+0x2d/0x520 [nuvoton_cir]
[  432.433085]  __handle_irq_event_percpu+0x43/0x330
[  432.435493]  handle_irq_event_percpu+0x1e/0x50
[  432.437884]  handle_irq_event+0x34/0x60
[  432.440236]  handle_edge_irq+0x6a/0x150
[  432.442561]  handle_irq+0x15/0x20
[  432.444854]  do_IRQ+0x57/0x110
[  432.447115]  common_interrupt+0x90/0x90
[  432.449380] RIP: 0010:cpuidle_enter_state+0x120/0x370
[  432.451653] RSP: 0018:ffffffff81c03dd8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffffcc
[  432.453994] RAX: ffffffff81c14500 RBX: 0000000000000008 RCX: 00000064aac6f2d2
[  432.456349] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffffff81c14500
[  432.458704] RBP: ffffffff81c03e18 R08: cccccccccccccccd R09: 0000000000000018
[  432.461072] R10: 0000000000000000 R11: 0000000000000000 R12: ffff880100a21260
[  432.463450] R13: ffffffff81c7e6f8 R14: 0000000000000008 R15: ffffffff81c7e6e0
[  432.465819]  </IRQ>
[  432.468104]  ? cpuidle_enter_state+0x11b/0x370
[  432.470413]  cpuidle_enter+0x12/0x20
[  432.472698]  call_cpuidle+0x1e/0x40
[  432.474967]  do_idle+0xe3/0x1c0
[  432.477172]  cpu_startup_entry+0x18/0x20
[  432.479376]  rest_init+0x130/0x140
[  432.481565]  start_kernel+0x3cc/0x3d9
[  432.483750]  x86_64_start_reservations+0x2a/0x2c
[  432.485980]  x86_64_start_kernel+0x178/0x18b
[  432.488222]  start_cpu+0x14/0x14
[  432.490453]  ? start_cpu+0x14/0x14

Fixes: 97c129747af5 "[media] rc: nuvoton-cir: Add support wakeup via sysfs filter callback"

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
---
 drivers/media/rc/nuvoton-cir.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index b109f8246b96..ec4b25bd2ec2 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -176,12 +176,13 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev,
 {
 	u8 tolerance, config;
 	struct nvt_dev *nvt = dev->priv;
+	unsigned long flags;
 	int i;
 
 	/* hardcode the tolerance to 10% */
 	tolerance = DIV_ROUND_UP(count, 10);
 
-	spin_lock(&nvt->lock);
+	spin_lock_irqsave(&nvt->lock, flags);
 
 	nvt_clear_cir_wake_fifo(nvt);
 	nvt_cir_wake_reg_write(nvt, count, CIR_WAKE_FIFO_CMP_DEEP);
@@ -203,7 +204,7 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev,
 
 	nvt_cir_wake_reg_write(nvt, config, CIR_WAKE_IRCON);
 
-	spin_unlock(&nvt->lock);
+	spin_unlock_irqrestore(&nvt->lock, flags);
 }
 
 static ssize_t wakeup_data_show(struct device *dev,
-- 
GitLab


From 413808685dd7c9b54bbc5af79da2eaddd0fc3cb2 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Wed, 22 Feb 2017 18:48:01 -0300
Subject: [PATCH 677/898] [media] rc: raw decoder for keymap protocol is not
 loaded on register

When the protocol is set via the sysfs protocols attribute, the
decoder is loaded. However, when it is not when a device is first
plugged in or registered.

Fixes: acc1c3c ("[media] media: rc: load decoder modules on-demand")

Signed-off-by: Sean Young <sean@mess.org>
Cc: <stable@vger.kernel.org> # v4.5+
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
---
 drivers/media/rc/rc-main.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 2424946740e6..a158b321b40a 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1663,6 +1663,7 @@ static int rc_setup_rx_device(struct rc_dev *dev)
 {
 	int rc;
 	struct rc_map *rc_map;
+	u64 rc_type;
 
 	if (!dev->map_name)
 		return -EINVAL;
@@ -1677,15 +1678,18 @@ static int rc_setup_rx_device(struct rc_dev *dev)
 	if (rc)
 		return rc;
 
-	if (dev->change_protocol) {
-		u64 rc_type = (1ll << rc_map->rc_type);
+	rc_type = BIT_ULL(rc_map->rc_type);
 
+	if (dev->change_protocol) {
 		rc = dev->change_protocol(dev, &rc_type);
 		if (rc < 0)
 			goto out_table;
 		dev->enabled_protocols = rc_type;
 	}
 
+	if (dev->driver_type == RC_DRIVER_IR_RAW)
+		ir_raw_load_modules(&rc_type);
+
 	set_bit(EV_KEY, dev->input_dev->evbit);
 	set_bit(EV_REP, dev->input_dev->evbit);
 	set_bit(EV_MSC, dev->input_dev->evbit);
-- 
GitLab


From 5df62771c556e4ec9d7ecea1f070ff6da4bce151 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Thu, 23 Feb 2017 06:11:21 -0300
Subject: [PATCH 678/898] [media] rc: protocol is not set on register for raw
 IR devices

ir_raw_event_register() sets up change_protocol(), and without that set,
rc_setup_rx_device() does not set the protocol for the device on register.

The standard udev rules run ir-keytable, which writes to the protocols
file again, which hides this problem.

Fixes: 7ff2c2b ("[media] rc-main: split setup and unregister functions")

Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
---
 drivers/media/rc/rc-main.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index a158b321b40a..d84533699668 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1781,12 +1781,6 @@ int rc_register_device(struct rc_dev *dev)
 		dev->input_name ?: "Unspecified device", path ?: "N/A");
 	kfree(path);
 
-	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
-		rc = rc_setup_rx_device(dev);
-		if (rc)
-			goto out_dev;
-	}
-
 	if (dev->driver_type == RC_DRIVER_IR_RAW ||
 	    dev->driver_type == RC_DRIVER_IR_RAW_TX) {
 		if (!raw_init) {
@@ -1795,7 +1789,13 @@ int rc_register_device(struct rc_dev *dev)
 		}
 		rc = ir_raw_event_register(dev);
 		if (rc < 0)
-			goto out_rx;
+			goto out_dev;
+	}
+
+	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
+		rc = rc_setup_rx_device(dev);
+		if (rc)
+			goto out_raw;
 	}
 
 	/* Allow the RC sysfs nodes to be accessible */
@@ -1807,8 +1807,8 @@ int rc_register_device(struct rc_dev *dev)
 
 	return 0;
 
-out_rx:
-	rc_free_rx_device(dev);
+out_raw:
+	ir_raw_event_unregister(dev);
 out_dev:
 	device_del(&dev->dev);
 out_unlock:
-- 
GitLab


From c919a3069c775c1c876bec55e00b2305d5125caa Mon Sep 17 00:00:00 2001
From: Ethan Zonca <e@ethanzonca.com>
Date: Fri, 24 Feb 2017 11:27:36 -0500
Subject: [PATCH 679/898] can: gs_usb: Don't use stack memory for USB transfers

Fixes: 05ca5270005c can: gs_usb: add ethtool set_phys_id callback to locate physical device

The gs_usb driver is performing USB transfers using buffers allocated on
the stack. This causes the driver to not function with vmapped stacks.
Instead, allocate memory for the transfer buffers.

Signed-off-by: Ethan Zonca <e@ethanzonca.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v4.8
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 40 ++++++++++++++++++++++++++----------
 1 file changed, 29 insertions(+), 11 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 77e3cc06a30c..a0dabd4038ba 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -908,10 +908,14 @@ static int gs_usb_probe(struct usb_interface *intf,
 	struct gs_usb *dev;
 	int rc = -ENOMEM;
 	unsigned int icount, i;
-	struct gs_host_config hconf = {
-		.byte_order = 0x0000beef,
-	};
-	struct gs_device_config dconf;
+	struct gs_host_config *hconf;
+	struct gs_device_config *dconf;
+
+	hconf = kmalloc(sizeof(*hconf), GFP_KERNEL);
+	if (!hconf)
+		return -ENOMEM;
+
+	hconf->byte_order = 0x0000beef;
 
 	/* send host config */
 	rc = usb_control_msg(interface_to_usbdev(intf),
@@ -920,16 +924,22 @@ static int gs_usb_probe(struct usb_interface *intf,
 			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
-			     &hconf,
-			     sizeof(hconf),
+			     hconf,
+			     sizeof(*hconf),
 			     1000);
 
+	kfree(hconf);
+
 	if (rc < 0) {
 		dev_err(&intf->dev, "Couldn't send data format (err=%d)\n",
 			rc);
 		return rc;
 	}
 
+	dconf = kmalloc(sizeof(*dconf), GFP_KERNEL);
+	if (!dconf)
+		return -ENOMEM;
+
 	/* read device config */
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_rcvctrlpipe(interface_to_usbdev(intf), 0),
@@ -937,28 +947,33 @@ static int gs_usb_probe(struct usb_interface *intf,
 			     USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
-			     &dconf,
-			     sizeof(dconf),
+			     dconf,
+			     sizeof(*dconf),
 			     1000);
 	if (rc < 0) {
 		dev_err(&intf->dev, "Couldn't get device config: (err=%d)\n",
 			rc);
+		kfree(dconf);
 		return rc;
 	}
 
-	icount = dconf.icount + 1;
+	icount = dconf->icount + 1;
 	dev_info(&intf->dev, "Configuring for %d interfaces\n", icount);
 
 	if (icount > GS_MAX_INTF) {
 		dev_err(&intf->dev,
 			"Driver cannot handle more that %d CAN interfaces\n",
 			GS_MAX_INTF);
+		kfree(dconf);
 		return -EINVAL;
 	}
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
+	if (!dev) {
+		kfree(dconf);
 		return -ENOMEM;
+	}
+
 	init_usb_anchor(&dev->rx_submitted);
 
 	atomic_set(&dev->active_channels, 0);
@@ -967,7 +982,7 @@ static int gs_usb_probe(struct usb_interface *intf,
 	dev->udev = interface_to_usbdev(intf);
 
 	for (i = 0; i < icount; i++) {
-		dev->canch[i] = gs_make_candev(i, intf, &dconf);
+		dev->canch[i] = gs_make_candev(i, intf, dconf);
 		if (IS_ERR_OR_NULL(dev->canch[i])) {
 			/* save error code to return later */
 			rc = PTR_ERR(dev->canch[i]);
@@ -978,12 +993,15 @@ static int gs_usb_probe(struct usb_interface *intf,
 				gs_destroy_candev(dev->canch[i]);
 
 			usb_kill_anchored_urbs(&dev->rx_submitted);
+			kfree(dconf);
 			kfree(dev);
 			return rc;
 		}
 		dev->canch[i]->parent = dev;
 	}
 
+	kfree(dconf);
+
 	return 0;
 }
 
-- 
GitLab


From 540a27aef355e3fd8c598600d4a3c8f92127ee05 Mon Sep 17 00:00:00 2001
From: Ethan Zonca <e@ethanzonca.com>
Date: Fri, 24 Feb 2017 11:00:34 -0500
Subject: [PATCH 680/898] can: gs_usb: fix coding style

This patch fixes five minor style issues, spaces are between bitwise OR
operators.

Signed-off-by: Ethan Zonca <e@ethanzonca.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index a0dabd4038ba..300349fe8dc0 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -258,7 +258,7 @@ static int gs_cmd_reset(struct gs_usb *gsusb, struct gs_can *gsdev)
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_sndctrlpipe(interface_to_usbdev(intf), 0),
 			     GS_USB_BREQ_MODE,
-			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
 			     gsdev->channel,
 			     0,
 			     dm,
@@ -432,7 +432,7 @@ static int gs_usb_set_bittiming(struct net_device *netdev)
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_sndctrlpipe(interface_to_usbdev(intf), 0),
 			     GS_USB_BREQ_BITTIMING,
-			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
 			     dev->channel,
 			     0,
 			     dbt,
@@ -546,7 +546,6 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
 				  hf,
 				  urb->transfer_dma);
 
-
 		if (rc == -ENODEV) {
 			netif_device_detach(netdev);
 		} else {
@@ -804,7 +803,7 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_rcvctrlpipe(interface_to_usbdev(intf), 0),
 			     GS_USB_BREQ_BT_CONST,
-			     USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
 			     channel,
 			     0,
 			     bt_const,
@@ -921,7 +920,7 @@ static int gs_usb_probe(struct usb_interface *intf,
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_sndctrlpipe(interface_to_usbdev(intf), 0),
 			     GS_USB_BREQ_HOST_FORMAT,
-			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
 			     hconf,
@@ -944,7 +943,7 @@ static int gs_usb_probe(struct usb_interface *intf,
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_rcvctrlpipe(interface_to_usbdev(intf), 0),
 			     GS_USB_BREQ_DEVICE_CONFIG,
-			     USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
 			     dconf,
-- 
GitLab


From 7c42631376306fb3f34d51fda546b50a9b6dd6ec Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 2 Mar 2017 12:03:40 +0100
Subject: [PATCH 681/898] can: usb_8dev: Fix memory leak of
 priv->cmd_msg_buffer

The priv->cmd_msg_buffer is allocated in the probe function, but never
kfree()ed. This patch converts the kzalloc() to resource-managed
kzalloc.

Cc: linux-stable <stable@vger.kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/usb_8dev.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index 108a30e15097..d000cb62d6ae 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -951,8 +951,8 @@ static int usb_8dev_probe(struct usb_interface *intf,
 	for (i = 0; i < MAX_TX_URBS; i++)
 		priv->tx_contexts[i].echo_index = MAX_TX_URBS;
 
-	priv->cmd_msg_buffer = kzalloc(sizeof(struct usb_8dev_cmd_msg),
-				      GFP_KERNEL);
+	priv->cmd_msg_buffer = devm_kzalloc(&intf->dev, sizeof(struct usb_8dev_cmd_msg),
+					    GFP_KERNEL);
 	if (!priv->cmd_msg_buffer)
 		goto cleanup_candev;
 
@@ -966,7 +966,7 @@ static int usb_8dev_probe(struct usb_interface *intf,
 	if (err) {
 		netdev_err(netdev,
 			"couldn't register CAN device: %d\n", err);
-		goto cleanup_cmd_msg_buffer;
+		goto cleanup_candev;
 	}
 
 	err = usb_8dev_cmd_version(priv, &version);
@@ -987,9 +987,6 @@ static int usb_8dev_probe(struct usb_interface *intf,
 cleanup_unregister_candev:
 	unregister_netdev(priv->netdev);
 
-cleanup_cmd_msg_buffer:
-	kfree(priv->cmd_msg_buffer);
-
 cleanup_candev:
 	free_candev(netdev);
 
-- 
GitLab


From 66ddb82129df66a94219844c509074adb4330a28 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 2 Mar 2017 15:42:49 +0100
Subject: [PATCH 682/898] can: flexcan: fix typo in comment

This patch fixes the typo "Disble" -> "Disable".

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index ea57fed375c6..13f0f219d8aa 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -196,7 +196,7 @@
 #define FLEXCAN_QUIRK_BROKEN_ERR_STATE	BIT(1) /* [TR]WRN_INT not connected */
 #define FLEXCAN_QUIRK_DISABLE_RXFG	BIT(2) /* Disable RX FIFO Global mask */
 #define FLEXCAN_QUIRK_ENABLE_EACEN_RRS	BIT(3) /* Enable EACEN and RRS bit in ctrl2 */
-#define FLEXCAN_QUIRK_DISABLE_MECR	BIT(4) /* Disble Memory error detection */
+#define FLEXCAN_QUIRK_DISABLE_MECR	BIT(4) /* Disable Memory error detection */
 #define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP	BIT(5) /* Use timestamp based offloading */
 
 /* Structure of the message buffer */
-- 
GitLab


From da2f27e9e615d1c799c9582b15262458da61fddc Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Wed, 1 Mar 2017 15:33:26 +0100
Subject: [PATCH 683/898] netfilter: nf_conntrack_sip: fix wrong memory
 initialisation

In commit 82de0be6862cd ("netfilter: Add helper array
register/unregister functions"),
struct nf_conntrack_helper sip[MAX_PORTS][4] was changed to
sip[MAX_PORTS * 4], so the memory init should have been changed to
memset(&sip[4 * i], 0, 4 * sizeof(sip[i]));

But as the sip[] table is allocated in the BSS, it is already set to 0

Fixes: 82de0be6862cd ("netfilter: Add helper array register/unregister functions")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_sip.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 24174c520239..0d17894798b5 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1628,8 +1628,6 @@ static int __init nf_conntrack_sip_init(void)
 		ports[ports_c++] = SIP_PORT;
 
 	for (i = 0; i < ports_c; i++) {
-		memset(&sip[i], 0, sizeof(sip[i]));
-
 		nf_ct_helper_init(&sip[4 * i], AF_INET, IPPROTO_UDP, "sip",
 				  SIP_PORT, ports[i], i, sip_exp_policy,
 				  SIP_EXPECT_MAX,
-- 
GitLab


From f9121355eb6f9babadb97bf5b34ab0cce7764406 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 1 Mar 2017 18:15:11 +0100
Subject: [PATCH 684/898] netfilter: nft_set_rbtree: incorrect assumption on
 lower interval lookups

In case of adjacent ranges, we may indeed see either the high part of
the range in first place or the low part of it. Remove this incorrect
assumption, let's make sure we annotate the low part of the interval in
case of we have adjacent interva intervals so we hit a matching in
lookups.

Reported-by: Simon Hanisch <hanisch@wh2.tu-dresden.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_rbtree.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 71e8fb886a73..78dfbf9588b3 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -60,11 +60,10 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 		d = memcmp(this, key, set->klen);
 		if (d < 0) {
 			parent = parent->rb_left;
-			/* In case of adjacent ranges, we always see the high
-			 * part of the range in first place, before the low one.
-			 * So don't update interval if the keys are equal.
-			 */
-			if (interval && nft_rbtree_equal(set, this, interval))
+			if (interval &&
+			    nft_rbtree_equal(set, this, interval) &&
+			    nft_rbtree_interval_end(this) &&
+			    !nft_rbtree_interval_end(interval))
 				continue;
 			interval = rbe;
 		} else if (d > 0)
-- 
GitLab


From 25e94a997b324b5f167f56d56d7106d38b78c9de Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 1 Mar 2017 12:52:31 +0100
Subject: [PATCH 685/898] netfilter: nf_tables: don't call nfnetlink_set_err()
 if nfnetlink_send() fails

The underlying nlmsg_multicast() already sets sk->sk_err for us to
notify socket overruns, so we should not do anything with this return
value. So we just call nfnetlink_set_err() if:

1) We fail to allocate the netlink message.

or

2) We don't have enough space in the netlink message to place attributes,
   which means that we likely need to allocate a larger message.

Before this patch, the internal ESRCH netlink error code was propagated
to userspace, which is quite misleading. Netlink semantics mandate that
listeners just hit ENOBUFS if the socket buffer overruns.

Reported-by: Alexander Alemayhu <alexander@alemayhu.com>
Tested-by: Alexander Alemayhu <alexander@alemayhu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |   6 +-
 net/netfilter/nf_tables_api.c     | 133 ++++++++++++------------------
 2 files changed, 58 insertions(+), 81 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index ac84686aaafb..2aa8a9d80fbe 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -988,9 +988,9 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
 					const struct nlattr *nla, u32 objtype,
 					u8 genmask);
 
-int nft_obj_notify(struct net *net, struct nft_table *table,
-		   struct nft_object *obj, u32 portid, u32 seq,
-		   int event, int family, int report, gfp_t gfp);
+void nft_obj_notify(struct net *net, struct nft_table *table,
+		    struct nft_object *obj, u32 portid, u32 seq,
+		    int event, int family, int report, gfp_t gfp);
 
 /**
  *	struct nft_object_type - stateful object type
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ff7304ae58ac..5e0ccfd5bb37 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -461,16 +461,15 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 	return -1;
 }
 
-static int nf_tables_table_notify(const struct nft_ctx *ctx, int event)
+static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
 	int err;
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
-		return 0;
+		return;
 
-	err = -ENOBUFS;
 	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb == NULL)
 		goto err;
@@ -482,14 +481,11 @@ static int nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-			     ctx->report, GFP_KERNEL);
+	nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+		       ctx->report, GFP_KERNEL);
+	return;
 err:
-	if (err < 0) {
-		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-				  err);
-	}
-	return err;
+	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 
 static int nf_tables_dump_tables(struct sk_buff *skb,
@@ -1050,16 +1046,15 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 	return -1;
 }
 
-static int nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
+static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
 	int err;
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
-		return 0;
+		return;
 
-	err = -ENOBUFS;
 	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb == NULL)
 		goto err;
@@ -1072,14 +1067,11 @@ static int nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-			     ctx->report, GFP_KERNEL);
+	nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+		       ctx->report, GFP_KERNEL);
+	return;
 err:
-	if (err < 0) {
-		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-				  err);
-	}
-	return err;
+	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 
 static int nf_tables_dump_chains(struct sk_buff *skb,
@@ -1934,18 +1926,16 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 	return -1;
 }
 
-static int nf_tables_rule_notify(const struct nft_ctx *ctx,
-				 const struct nft_rule *rule,
-				 int event)
+static void nf_tables_rule_notify(const struct nft_ctx *ctx,
+				  const struct nft_rule *rule, int event)
 {
 	struct sk_buff *skb;
 	int err;
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
-		return 0;
+		return;
 
-	err = -ENOBUFS;
 	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb == NULL)
 		goto err;
@@ -1958,14 +1948,11 @@ static int nf_tables_rule_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-			     ctx->report, GFP_KERNEL);
+	nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+		       ctx->report, GFP_KERNEL);
+	return;
 err:
-	if (err < 0) {
-		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-				  err);
-	}
-	return err;
+	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 
 struct nft_rule_dump_ctx {
@@ -2696,9 +2683,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	return -1;
 }
 
-static int nf_tables_set_notify(const struct nft_ctx *ctx,
-				const struct nft_set *set,
-				int event, gfp_t gfp_flags)
+static void nf_tables_set_notify(const struct nft_ctx *ctx,
+				 const struct nft_set *set, int event,
+			         gfp_t gfp_flags)
 {
 	struct sk_buff *skb;
 	u32 portid = ctx->portid;
@@ -2706,9 +2693,8 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx,
 
 	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
-		return 0;
+		return;
 
-	err = -ENOBUFS;
 	skb = nlmsg_new(NLMSG_GOODSIZE, gfp_flags);
 	if (skb == NULL)
 		goto err;
@@ -2719,12 +2705,11 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES,
-			     ctx->report, gfp_flags);
+	nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, ctx->report,
+		       gfp_flags);
+	return;
 err:
-	if (err < 0)
-		nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, err);
-	return err;
+	nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 
 static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
@@ -3504,10 +3489,10 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 	return -1;
 }
 
-static int nf_tables_setelem_notify(const struct nft_ctx *ctx,
-				    const struct nft_set *set,
-				    const struct nft_set_elem *elem,
-				    int event, u16 flags)
+static void nf_tables_setelem_notify(const struct nft_ctx *ctx,
+				     const struct nft_set *set,
+				     const struct nft_set_elem *elem,
+				     int event, u16 flags)
 {
 	struct net *net = ctx->net;
 	u32 portid = ctx->portid;
@@ -3515,9 +3500,8 @@ static int nf_tables_setelem_notify(const struct nft_ctx *ctx,
 	int err;
 
 	if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
-		return 0;
+		return;
 
-	err = -ENOBUFS;
 	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb == NULL)
 		goto err;
@@ -3529,12 +3513,11 @@ static int nf_tables_setelem_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report,
-			     GFP_KERNEL);
+	nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report,
+		       GFP_KERNEL);
+	return;
 err:
-	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
-	return err;
+	nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 
 static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx,
@@ -4476,18 +4459,17 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk,
 	return nft_delobj(&ctx, obj);
 }
 
-int nft_obj_notify(struct net *net, struct nft_table *table,
-		   struct nft_object *obj, u32 portid, u32 seq, int event,
-		   int family, int report, gfp_t gfp)
+void nft_obj_notify(struct net *net, struct nft_table *table,
+		    struct nft_object *obj, u32 portid, u32 seq, int event,
+		    int family, int report, gfp_t gfp)
 {
 	struct sk_buff *skb;
 	int err;
 
 	if (!report &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
-		return 0;
+		return;
 
-	err = -ENOBUFS;
 	skb = nlmsg_new(NLMSG_GOODSIZE, gfp);
 	if (skb == NULL)
 		goto err;
@@ -4499,21 +4481,18 @@ int nft_obj_notify(struct net *net, struct nft_table *table,
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, gfp);
+	nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, gfp);
+	return;
 err:
-	if (err < 0) {
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
-	}
-	return err;
+	nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 EXPORT_SYMBOL_GPL(nft_obj_notify);
 
-static int nf_tables_obj_notify(const struct nft_ctx *ctx,
-				struct nft_object *obj, int event)
+static void nf_tables_obj_notify(const struct nft_ctx *ctx,
+				 struct nft_object *obj, int event)
 {
-	return nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid,
-			      ctx->seq, event, ctx->afi->family, ctx->report,
-			      GFP_KERNEL);
+	nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event,
+		       ctx->afi->family, ctx->report, GFP_KERNEL);
 }
 
 static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
@@ -4543,7 +4522,8 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
 	return -EMSGSIZE;
 }
 
-static int nf_tables_gen_notify(struct net *net, struct sk_buff *skb, int event)
+static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb,
+				 int event)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
 	struct sk_buff *skb2;
@@ -4551,9 +4531,8 @@ static int nf_tables_gen_notify(struct net *net, struct sk_buff *skb, int event)
 
 	if (nlmsg_report(nlh) &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
-		return 0;
+		return;
 
-	err = -ENOBUFS;
 	skb2 = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb2 == NULL)
 		goto err;
@@ -4565,14 +4544,12 @@ static int nf_tables_gen_notify(struct net *net, struct sk_buff *skb, int event)
 		goto err;
 	}
 
-	err = nfnetlink_send(skb2, net, NETLINK_CB(skb).portid,
-			     NFNLGRP_NFTABLES, nlmsg_report(nlh), GFP_KERNEL);
+	nfnetlink_send(skb2, net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES,
+		       nlmsg_report(nlh), GFP_KERNEL);
+	return;
 err:
-	if (err < 0) {
-		nfnetlink_set_err(net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES,
-				  err);
-	}
-	return err;
+	nfnetlink_set_err(net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES,
+			  -ENOBUFS);
 }
 
 static int nf_tables_getgen(struct net *net, struct sock *nlsk,
-- 
GitLab


From 92ad18ec26611e8a47639e600bd9dc42fbe2edcf Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 2 Mar 2017 12:53:26 -0500
Subject: [PATCH 686/898] ftrace/graph: Do not modify the EMPTY_HASH for the
 function_graph filter

On boot up, if the kernel command line sets a graph funtion with the kernel
command line options "ftrace_graph_filter" or "ftrace_graph_notrace" then it
updates the corresponding function graph hash, ftrace_graph_hash or
ftrace_graph_notrace_hash respectively. Unfortunately, at boot up, these
variables are pointers to the "EMPTY_HASH" which is a constant used as a
placeholder when a hash has no entities. The problem was that the comand
line version to set the hashes updated the actual EMPTY_HASH instead of
creating a new hash for the function graph. This broke the EMPTY_HASH
because not only did it modify a constant (not sure how that was allowed to
happen, except maybe because it was done at early boot, const variables were
still mutable), but it made the filters have functions listed in them when
they were actually empty.

The kernel command line function needs to allocate a new hash for the
function graph filters and assign the necessary variables to that new hash
instead.

Link: http://lkml.kernel.org/r/1488420091.7212.17.camel@linux.intel.com

Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: b9b0c831bed2 ("ftrace: Convert graph filter to use hash tables")
Reported-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Tested-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fd84f2e30b6d..44122e7a6418 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4421,10 +4421,9 @@ static void __init set_ftrace_early_graph(char *buf, int enable)
 	char *func;
 	struct ftrace_hash *hash;
 
-	if (enable)
-		hash = ftrace_graph_hash;
-	else
-		hash = ftrace_graph_notrace_hash;
+	hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+	if (WARN_ON(!hash))
+		return;
 
 	while (buf) {
 		func = strsep(&buf, ",");
@@ -4434,6 +4433,11 @@ static void __init set_ftrace_early_graph(char *buf, int enable)
 			printk(KERN_DEBUG "ftrace: function %s not "
 					  "traceable\n", func);
 	}
+
+	if (enable)
+		ftrace_graph_hash = hash;
+	else
+		ftrace_graph_notrace_hash = hash;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-- 
GitLab


From ab42632156becd35d3884ee5c14da2bedbf3149a Mon Sep 17 00:00:00 2001
From: David Daney <david.daney@cavium.com>
Date: Wed, 1 Mar 2017 14:04:53 -0800
Subject: [PATCH 687/898] module: set __jump_table alignment to 8

For powerpc the __jump_table section in modules is not aligned, this
causes a WARN_ON() splat when loading a module containing a __jump_table.

Strict alignment became necessary with commit 3821fd35b58d
("jump_label: Reduce the size of struct static_key"), currently in
linux-next, which uses the two least significant bits of pointers to
__jump_table elements.

Fix by forcing __jump_table to 8, which is the same alignment used for
this section in the kernel proper.

Link: http://lkml.kernel.org/r/20170301220453.4756-1-david.daney@cavium.com

Reviewed-by: Jason Baron <jbaron@akamai.com>
Acked-by: Jessica Yu <jeyu@redhat.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 scripts/module-common.lds | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/module-common.lds b/scripts/module-common.lds
index 73a2c7da0e55..53234e85192a 100644
--- a/scripts/module-common.lds
+++ b/scripts/module-common.lds
@@ -19,4 +19,6 @@ SECTIONS {
 
 	. = ALIGN(8);
 	.init_array		0 : { *(SORT(.init_array.*)) *(.init_array) }
+
+	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
 }
-- 
GitLab


From cd8d860dcce906cd477be7d0648ba6f56a52eaa6 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Tue, 28 Feb 2017 11:32:22 -0500
Subject: [PATCH 688/898] jump_label: Fix anonymous union initialization

Pre-4.6 gcc do not allow direct static initialization of members of
anonymous structs/unions. After commit 3821fd35b58d ("jump_label:
Reduce the size of struct static_key") STATIC_KEY_INIT_{TRUE|FALSE}
definitions cannot be compiled with those older compilers.

Placing initializers inside curved brackets works around this problem.

Link: http://lkml.kernel.org/r/1488299542-30765-1-git-send-email-boris.ostrovsky@oracle.com

Fixes: 3821fd35b58d ("jump_label: Reduce the size of struct static_key")
Reviewed-by: Jason Baron <jbaron@akamai.com>
Compiled-by: Chris Mason <clm@fb.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/jump_label.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 680c98b2f41c..a7f90117cf7d 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -166,10 +166,10 @@ extern void static_key_disable(struct static_key *key);
  */
 #define STATIC_KEY_INIT_TRUE					\
 	{ .enabled = { 1 },					\
-	  .entries = (void *)JUMP_TYPE_TRUE }
+	  { .entries = (void *)JUMP_TYPE_TRUE } }
 #define STATIC_KEY_INIT_FALSE					\
 	{ .enabled = { 0 },					\
-	  .entries = (void *)JUMP_TYPE_FALSE }
+	  { .entries = (void *)JUMP_TYPE_FALSE } }
 
 #else  /* !HAVE_JUMP_LABEL */
 
-- 
GitLab


From b17ef2ed624aa7c1f68ed11acd16ecbf80fe01d7 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 2 Mar 2017 17:28:45 -0500
Subject: [PATCH 689/898] jump_label: Add comment about initialization order
 for anonymous unions

Commit 3821fd35b58d ("jump_label: Reduce the size of struct static_key")
broke old compilers that could not handle static initialization of anonymous
unions. Boris fixed it with a patch that added brackets around the static
initializer. But this creates a dependency between those initializers and
the structure's order of its fields. Document this dependency in case new
fields are added to struct static_key in the future.

Noted-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Suggested-by: Chris Mason <clm@fb.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/jump_label.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index a7f90117cf7d..28e04a33535a 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -90,6 +90,13 @@ extern bool static_key_initialized;
 struct static_key {
 	atomic_t enabled;
 /*
+ * Note:
+ *   To make anonymous unions work with old compilers, the static
+ *   initialization of them requires brackets. This creates a dependency
+ *   on the order of the struct with the initializers. If any fields
+ *   are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need
+ *   to be modified.
+ *
  * bit 0 => 1 if key is initially true
  *	    0 if initially false
  * bit 1 => 1 if points to struct static_key_mod
-- 
GitLab


From bf7165cfa23695c51998231c4efa080fe1d3548d Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Wed, 28 Sep 2016 22:55:54 -0400
Subject: [PATCH 690/898] tracing: Add #undef to fix compile error

There are several trace include files that define TRACE_INCLUDE_FILE.

Include several of them in the same .c file (as I currently have in
some code I am working on), and the compile will blow up with a
"warning: "TRACE_INCLUDE_FILE" redefined #define TRACE_INCLUDE_FILE syscalls"

Every other include file in include/trace/events/ avoids that issue
by having a #undef TRACE_INCLUDE_FILE before the #define; syscalls.h
should have one, too.

Link: http://lkml.kernel.org/r/20160928225554.13bd7ac6@annuminas.surriel.com

Cc: stable@vger.kernel.org
Fixes: b8007ef74222 ("tracing: Separate raw syscall from syscall tracer")
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/trace/events/syscalls.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 14e49c798135..b35533b94277 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -1,5 +1,6 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM raw_syscalls
+#undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE syscalls
 
 #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
-- 
GitLab


From 65a50c656276b0846bea09dd011c0a3d35b77f3e Mon Sep 17 00:00:00 2001
From: Todd Brandt <todd.e.brandt@linux.intel.com>
Date: Thu, 2 Mar 2017 16:12:15 -0800
Subject: [PATCH 691/898] ftrace/graph: Add ftrace_graph_max_depth kernel
 parameter

Early trace callgraphs can be extremely large on systems with
several seconds of boot time. The max_depth parameter limits how
deep the graph trace goes and reduces the output size. This
parameter is the same as the max_graph_depth file in tracefs.

Link: http://lkml.kernel.org/r/1488499935-23216-1-git-send-email-todd.e.brandt@linux.intel.com

Signed-off-by: Todd Brandt <todd.e.brandt@linux.intel.com>
[ changed comments about debugfs to tracefs ]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/admin-guide/kernel-parameters.txt | 6 ++++++
 kernel/trace/ftrace.c                           | 9 +++++++++
 2 files changed, 15 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 21e2d8863705..1c9016b27ee9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1173,6 +1173,12 @@
 			functions that can be changed at run time by the
 			set_graph_notrace file in the debugfs tracing directory.
 
+	ftrace_graph_max_depth=<uint>
+			[FTRACE] Used with the function graph tracer. This is
+			the max depth it will trace into a function. This value
+			can be changed at run time by the max_graph_depth file
+			in the tracefs tracing directory. default: 0 (no limit)
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 44122e7a6418..d129ae51329a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4415,6 +4415,15 @@ static int __init set_graph_notrace_function(char *str)
 }
 __setup("ftrace_graph_notrace=", set_graph_notrace_function);
 
+static int __init set_graph_max_depth_function(char *str)
+{
+	if (!str)
+		return 0;
+	fgraph_max_depth = simple_strtoul(str, NULL, 0);
+	return 1;
+}
+__setup("ftrace_graph_max_depth=", set_graph_max_depth_function);
+
 static void __init set_ftrace_early_graph(char *buf, int enable)
 {
 	int ret;
-- 
GitLab


From d67ce7da3b1eda838db7bdca86d7ec28ef37068e Mon Sep 17 00:00:00 2001
From: Paul Durrant <Paul.Durrant@citrix.com>
Date: Thu, 2 Mar 2017 12:54:25 +0000
Subject: [PATCH 692/898] xen-netback: keep a local pointer for vif in
 backend_disconnect()

This patch replaces use of 'be->vif' with 'vif' and hence generally
makes the function look tidier. No semantic change.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index bb854f92f5a5..d82ddc913b4c 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -492,24 +492,28 @@ static int backend_create_xenvif(struct backend_info *be)
 
 static void backend_disconnect(struct backend_info *be)
 {
-	if (be->vif) {
+	struct xenvif *vif = be->vif;
+
+	if (vif) {
 		unsigned int queue_index;
 
-		xen_unregister_watchers(be->vif);
+		xen_unregister_watchers(vif);
 #ifdef CONFIG_DEBUG_FS
-		xenvif_debugfs_delif(be->vif);
+		xenvif_debugfs_delif(vif);
 #endif /* CONFIG_DEBUG_FS */
-		xenvif_disconnect_data(be->vif);
-		for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
-			xenvif_deinit_queue(&be->vif->queues[queue_index]);
-
-		spin_lock(&be->vif->lock);
-		vfree(be->vif->queues);
-		be->vif->num_queues = 0;
-		be->vif->queues = NULL;
-		spin_unlock(&be->vif->lock);
-
-		xenvif_disconnect_ctrl(be->vif);
+		xenvif_disconnect_data(vif);
+		for (queue_index = 0;
+		     queue_index < vif->num_queues;
+		     ++queue_index)
+			xenvif_deinit_queue(&vif->queues[queue_index]);
+
+		spin_lock(&vif->lock);
+		vfree(vif->queues);
+		vif->num_queues = 0;
+		vif->queues = NULL;
+		spin_unlock(&vif->lock);
+
+		xenvif_disconnect_ctrl(vif);
 	}
 }
 
-- 
GitLab


From a254d8f9a8a928772ef4608342125ccb35b79d5d Mon Sep 17 00:00:00 2001
From: Paul Durrant <Paul.Durrant@citrix.com>
Date: Thu, 2 Mar 2017 12:54:26 +0000
Subject: [PATCH 693/898] xen-netback: don't vfree() queues under spinlock

This leads to a BUG of the following form:

[  174.512861] switch: port 2(vif3.0) entered disabled state
[  174.522735] BUG: sleeping function called from invalid context at
/home/build/linux-linus/mm/vmalloc.c:1441
[  174.523451] in_atomic(): 1, irqs_disabled(): 0, pid: 28, name: xenwatch
[  174.524131] CPU: 1 PID: 28 Comm: xenwatch Tainted: G        W
4.10.0upstream-11073-g4977ab6-dirty #1
[  174.524819] Hardware name: MSI MS-7680/H61M-P23 (MS-7680), BIOS V17.0
03/14/2011
[  174.525517] Call Trace:
[  174.526217]  show_stack+0x23/0x60
[  174.526899]  dump_stack+0x5b/0x88
[  174.527562]  ___might_sleep+0xde/0x130
[  174.528208]  __might_sleep+0x35/0xa0
[  174.528840]  ? _raw_spin_unlock_irqrestore+0x13/0x20
[  174.529463]  ? __wake_up+0x40/0x50
[  174.530089]  remove_vm_area+0x20/0x90
[  174.530724]  __vunmap+0x1d/0xc0
[  174.531346]  ? delete_object_full+0x13/0x20
[  174.531973]  vfree+0x40/0x80
[  174.532594]  set_backend_state+0x18a/0xa90
[  174.533221]  ? dwc_scan_descriptors+0x24d/0x430
[  174.533850]  ? kfree+0x5b/0xc0
[  174.534476]  ? xenbus_read+0x3d/0x50
[  174.535101]  ? xenbus_read+0x3d/0x50
[  174.535718]  ? xenbus_gather+0x31/0x90
[  174.536332]  ? ___might_sleep+0xf6/0x130
[  174.536945]  frontend_changed+0x6b/0xd0
[  174.537565]  xenbus_otherend_changed+0x7d/0x80
[  174.538185]  frontend_changed+0x12/0x20
[  174.538803]  xenwatch_thread+0x74/0x110
[  174.539417]  ? woken_wake_function+0x20/0x20
[  174.540049]  kthread+0xe5/0x120
[  174.540663]  ? xenbus_printf+0x50/0x50
[  174.541278]  ? __kthread_init_worker+0x40/0x40
[  174.541898]  ret_from_fork+0x21/0x2c
[  174.548635] switch: port 2(vif3.0) entered disabled state

This patch defers the vfree() until after the spinlock is released.

Reported-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index d82ddc913b4c..d2d7cd9145b1 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -496,6 +496,7 @@ static void backend_disconnect(struct backend_info *be)
 
 	if (vif) {
 		unsigned int queue_index;
+		struct xenvif_queue *queues;
 
 		xen_unregister_watchers(vif);
 #ifdef CONFIG_DEBUG_FS
@@ -508,11 +509,13 @@ static void backend_disconnect(struct backend_info *be)
 			xenvif_deinit_queue(&vif->queues[queue_index]);
 
 		spin_lock(&vif->lock);
-		vfree(vif->queues);
+		queues = vif->queues;
 		vif->num_queues = 0;
 		vif->queues = NULL;
 		spin_unlock(&vif->lock);
 
+		vfree(queues);
+
 		xenvif_disconnect_ctrl(vif);
 	}
 }
-- 
GitLab


From 16206524f6ea57d6dcd56fe46f9f4a06d4a1b113 Mon Sep 17 00:00:00 2001
From: Jon Mason <jon.mason@broadcom.com>
Date: Thu, 2 Mar 2017 17:59:56 -0500
Subject: [PATCH 694/898] net: ethernet: bgmac: init sequence bug

Fix a bug in the 'bgmac' driver init sequence that blind writes for init
sequence where it should preserve most bits other than the ones it is
deliberately manipulating.

The code now checks to see if the adapter needs to be brought out of
reset (where as before it was doing an IDM write to bring it out of
reset regardless of whether it was in reset or not).  Also, removed
unnecessary usleeps (as there is already a read present to flush the
IDM writes).

Signed-off-by: Zac Schroff <zschroff@broadcom.com>
Signed-off-by: Jon Mason <jon.mason@broadcom.com>
Fixes: f6a95a24957 ("net: ethernet: bgmac: Add platform device support")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bgmac-platform.c    | 27 ++++++++++++-------
 drivers/net/ethernet/broadcom/bgmac.h         | 16 +++++++++++
 2 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 7b1af950f312..da1b8b225eb9 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -51,8 +51,7 @@ static void platform_bgmac_idm_write(struct bgmac *bgmac, u16 offset, u32 value)
 
 static bool platform_bgmac_clk_enabled(struct bgmac *bgmac)
 {
-	if ((bgmac_idm_read(bgmac, BCMA_IOCTL) &
-	     (BCMA_IOCTL_CLK | BCMA_IOCTL_FGC)) != BCMA_IOCTL_CLK)
+	if ((bgmac_idm_read(bgmac, BCMA_IOCTL) & BGMAC_CLK_EN) != BGMAC_CLK_EN)
 		return false;
 	if (bgmac_idm_read(bgmac, BCMA_RESET_CTL) & BCMA_RESET_CTL_RESET)
 		return false;
@@ -61,15 +60,25 @@ static bool platform_bgmac_clk_enabled(struct bgmac *bgmac)
 
 static void platform_bgmac_clk_enable(struct bgmac *bgmac, u32 flags)
 {
-	bgmac_idm_write(bgmac, BCMA_IOCTL,
-			(BCMA_IOCTL_CLK | BCMA_IOCTL_FGC | flags));
-	bgmac_idm_read(bgmac, BCMA_IOCTL);
+	u32 val;
 
-	bgmac_idm_write(bgmac, BCMA_RESET_CTL, 0);
-	bgmac_idm_read(bgmac, BCMA_RESET_CTL);
-	udelay(1);
+	/* The Reset Control register only contains a single bit to show if the
+	 * controller is currently in reset.  Do a sanity check here, just in
+	 * case the bootloader happened to leave the device in reset.
+	 */
+	val = bgmac_idm_read(bgmac, BCMA_RESET_CTL);
+	if (val) {
+		bgmac_idm_write(bgmac, BCMA_RESET_CTL, 0);
+		bgmac_idm_read(bgmac, BCMA_RESET_CTL);
+		udelay(1);
+	}
 
-	bgmac_idm_write(bgmac, BCMA_IOCTL, (BCMA_IOCTL_CLK | flags));
+	val = bgmac_idm_read(bgmac, BCMA_IOCTL);
+	/* Some bits of BCMA_IOCTL set by HW/ATF and should not change */
+	val |= flags & ~(BGMAC_AWCACHE | BGMAC_ARCACHE | BGMAC_AWUSER |
+			 BGMAC_ARUSER);
+	val |= BGMAC_CLK_EN;
+	bgmac_idm_write(bgmac, BCMA_IOCTL, val);
 	bgmac_idm_read(bgmac, BCMA_IOCTL);
 	udelay(1);
 }
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 248727dc62f2..6d1c6ff1ed96 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -213,6 +213,22 @@
 /* BCMA GMAC core specific IO Control (BCMA_IOCTL) flags */
 #define BGMAC_BCMA_IOCTL_SW_CLKEN		0x00000004	/* PHY Clock Enable */
 #define BGMAC_BCMA_IOCTL_SW_RESET		0x00000008	/* PHY Reset */
+/* The IOCTL values appear to be different in NS, NSP, and NS2, and do not match
+ * the values directly above
+ */
+#define BGMAC_CLK_EN				BIT(0)
+#define BGMAC_RESERVED_0			BIT(1)
+#define BGMAC_SOURCE_SYNC_MODE_EN		BIT(2)
+#define BGMAC_DEST_SYNC_MODE_EN			BIT(3)
+#define BGMAC_TX_CLK_OUT_INVERT_EN		BIT(4)
+#define BGMAC_DIRECT_GMII_MODE			BIT(5)
+#define BGMAC_CLK_250_SEL			BIT(6)
+#define BGMAC_AWCACHE				(0xf << 7)
+#define BGMAC_RESERVED_1			(0x1f << 11)
+#define BGMAC_ARCACHE				(0xf << 16)
+#define BGMAC_AWUSER				(0x3f << 20)
+#define BGMAC_ARUSER				(0x3f << 26)
+#define BGMAC_RESERVED				BIT(31)
 
 /* BCMA GMAC core specific IO status (BCMA_IOST) flags */
 #define BGMAC_BCMA_IOST_ATTACHED		0x00000800
-- 
GitLab


From fa42245dff4a5f2f8f208da542acbd80c22f7c65 Mon Sep 17 00:00:00 2001
From: Hari Vyas <hariv@broadcom.com>
Date: Thu, 2 Mar 2017 17:59:57 -0500
Subject: [PATCH 695/898] net: ethernet: bgmac: mac address change bug

ndo_set_mac_address() passes struct sockaddr * as 2nd parameter to
bgmac_set_mac_address() but code assumed u8 *.  This caused two bytes
chopping and the wrong mac address was configured.

Signed-off-by: Hari Vyas <hariv@broadcom.com>
Signed-off-by: Jon Mason <jon.mason@broadcom.com>
Fixes: 4e209001b86 ("bgmac: write mac address to hardware in ndo_set_mac_address")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bgmac.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 415046750bb4..fd66fca00e01 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1223,12 +1223,16 @@ static netdev_tx_t bgmac_start_xmit(struct sk_buff *skb,
 static int bgmac_set_mac_address(struct net_device *net_dev, void *addr)
 {
 	struct bgmac *bgmac = netdev_priv(net_dev);
+	struct sockaddr *sa = addr;
 	int ret;
 
 	ret = eth_prepare_mac_addr_change(net_dev, addr);
 	if (ret < 0)
 		return ret;
-	bgmac_write_mac_address(bgmac, (u8 *)addr);
+
+	ether_addr_copy(net_dev->dev_addr, sa->sa_data);
+	bgmac_write_mac_address(bgmac, net_dev->dev_addr);
+
 	eth_commit_mac_addr_change(net_dev, addr);
 	return 0;
 }
-- 
GitLab


From 9383b33771e566fa547daa2d09c6e0f1aaa298c3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 2 Mar 2017 15:26:20 -0800
Subject: [PATCH 696/898] nfp: don't tell FW about the reserved buffer space

Since commit c0f031bc8866 ("nfp_net: use alloc_frag() and build_skb()")
we are allocating buffers which have to hold both the data and skb to
be created in place by build_skb().

FW should only be told about the buffer space it can DMA to, that
is without the build_skb() headroom and tailroom.  Note: firmware
applications should validate the buffers against both MTU and
free list buffer size so oversized packets would not pass through
the NIC anyway.

Fixes: c0f031bc8866 ("nfp: use alloc_frag() and build_skb()")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 074259cc8e06..00a83218857a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2198,7 +2198,8 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 	nfp_net_write_mac_addr(nn);
 
 	nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu);
-	nn_writel(nn, NFP_NET_CFG_FLBUFSZ, nn->fl_bufsz);
+	nn_writel(nn, NFP_NET_CFG_FLBUFSZ,
+		  nn->fl_bufsz - NFP_NET_RX_BUF_NON_DATA);
 
 	/* Enable device */
 	new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
-- 
GitLab


From d58cebb79b62ff84b537a35423b8d6b7f0746985 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 2 Mar 2017 15:26:21 -0800
Subject: [PATCH 697/898] nfp: correct DMA direction in XDP DMA sync

dma_sync_single_for_*() takes the direction in which the buffer
was mapped, not the direction of the sync.  We should sync XDP
buffers bidirectionally.

Fixes: ecd63a0217d5 ("nfp: add XDP support in the driver")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 00a83218857a..9179a99563af 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1498,7 +1498,7 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 	txbuf->real_len = pkt_len;
 
 	dma_sync_single_for_device(&nn->pdev->dev, rxbuf->dma_addr + pkt_off,
-				   pkt_len, DMA_TO_DEVICE);
+				   pkt_len, DMA_BIDIRECTIONAL);
 
 	/* Build TX descriptor */
 	txd = &tx_ring->txds[wr_idx];
@@ -1611,7 +1611,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 			dma_sync_single_for_cpu(&nn->pdev->dev,
 						rxbuf->dma_addr + pkt_off,
-						pkt_len, DMA_FROM_DEVICE);
+						pkt_len, DMA_BIDIRECTIONAL);
 			act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off,
 					      pkt_len);
 			switch (act) {
-- 
GitLab


From 37411cad633f5e41f8a13007654909d21b19363a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 2 Mar 2017 23:48:52 +0000
Subject: [PATCH 698/898] rxrpc: Fix potential NULL-pointer exception

Fix a potential NULL-pointer exception in rxrpc_do_sendmsg().  The call
state check that I added should have gone into the else-body of the
if-statement where we actually have a call to check.

Found by CoverityScan CID#1414316 ("Dereference after null check").

Fixes: 540b1c48c37a ("rxrpc: Fix deadlock between call creation and sendmsg/recvmsg")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/sendmsg.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 31c1538c1a8d..27685d8cba1a 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -517,13 +517,6 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		ret = -EBADSLT;
 		if (cmd != RXRPC_CMD_SEND_DATA)
 			goto error_release_sock;
-		ret = -EBUSY;
-		if (call->state == RXRPC_CALL_UNINITIALISED ||
-		    call->state == RXRPC_CALL_CLIENT_AWAIT_CONN ||
-		    call->state == RXRPC_CALL_SERVER_PREALLOC ||
-		    call->state == RXRPC_CALL_SERVER_SECURING ||
-		    call->state == RXRPC_CALL_SERVER_ACCEPTING)
-			goto error_release_sock;
 		call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID,
 							 exclusive);
 		/* The socket is now unlocked... */
@@ -531,6 +524,14 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
 	} else {
+		ret = -EBUSY;
+		if (call->state == RXRPC_CALL_UNINITIALISED ||
+		    call->state == RXRPC_CALL_CLIENT_AWAIT_CONN ||
+		    call->state == RXRPC_CALL_SERVER_PREALLOC ||
+		    call->state == RXRPC_CALL_SERVER_SECURING ||
+		    call->state == RXRPC_CALL_SERVER_ACCEPTING)
+			goto error_release_sock;
+
 		ret = mutex_lock_interruptible(&call->user_mutex);
 		release_sock(&rx->sk);
 		if (ret < 0) {
-- 
GitLab


From a8d63a53b3eac8626f62336dcc327c18f1bbca78 Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@oracle.com>
Date: Fri, 3 Mar 2017 00:44:26 -0500
Subject: [PATCH 699/898] rds: remove unnecessary returned value check

The function rds_trans_register always returns 0. As such, it is not
necessary to check the returned value.

Cc: Joe Jin <joe.jin@oracle.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib.c        | 6 +-----
 net/rds/rds.h       | 2 +-
 net/rds/tcp.c       | 6 +-----
 net/rds/transport.c | 4 +---
 4 files changed, 4 insertions(+), 14 deletions(-)

diff --git a/net/rds/ib.c b/net/rds/ib.c
index 0f557b243311..7a64c8db81ab 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -438,16 +438,12 @@ int rds_ib_init(void)
 	if (ret)
 		goto out_sysctl;
 
-	ret = rds_trans_register(&rds_ib_transport);
-	if (ret)
-		goto out_recv;
+	rds_trans_register(&rds_ib_transport);
 
 	rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
 
 	goto out;
 
-out_recv:
-	rds_ib_recv_exit();
 out_sysctl:
 	rds_ib_sysctl_exit();
 out_ibreg:
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 07fff73dd4f3..6f523ddfe1fb 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -910,7 +910,7 @@ void rds_connect_path_complete(struct rds_conn_path *conn, int curr);
 void rds_connect_complete(struct rds_connection *conn);
 
 /* transport.c */
-int rds_trans_register(struct rds_transport *trans);
+void rds_trans_register(struct rds_transport *trans);
 void rds_trans_unregister(struct rds_transport *trans);
 struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr);
 void rds_trans_put(struct rds_transport *trans);
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 5438f6725092..a973d3b4dff0 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -652,16 +652,12 @@ static int rds_tcp_init(void)
 	if (ret)
 		goto out_pernet;
 
-	ret = rds_trans_register(&rds_tcp_transport);
-	if (ret)
-		goto out_recv;
+	rds_trans_register(&rds_tcp_transport);
 
 	rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
 
 	goto out;
 
-out_recv:
-	rds_tcp_recv_exit();
 out_pernet:
 	unregister_pernet_subsys(&rds_tcp_net_ops);
 out_notifier:
diff --git a/net/rds/transport.c b/net/rds/transport.c
index 2ffd3e30c643..0b188dd0a344 100644
--- a/net/rds/transport.c
+++ b/net/rds/transport.c
@@ -40,7 +40,7 @@
 static struct rds_transport *transports[RDS_TRANS_COUNT];
 static DECLARE_RWSEM(rds_trans_sem);
 
-int rds_trans_register(struct rds_transport *trans)
+void rds_trans_register(struct rds_transport *trans)
 {
 	BUG_ON(strlen(trans->t_name) + 1 > TRANSNAMSIZ);
 
@@ -55,8 +55,6 @@ int rds_trans_register(struct rds_transport *trans)
 	}
 
 	up_write(&rds_trans_sem);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(rds_trans_register);
 
-- 
GitLab


From d0346b033899b9affa4da8c32bfb574dfb89859e Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 3 Mar 2017 15:22:09 +0000
Subject: [PATCH 700/898] sfc: avoid max() in array size

It confuses sparse, which thinks the size isn't constant.  Let's achieve
 the same thing with a BUILD_BUG_ON, since we know which one should be
 bigger and don't expect them ever to change.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 92e1c6d8b293..4d88e8532d3e 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -828,9 +828,7 @@ static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
 static int efx_ef10_link_piobufs(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-	_MCDI_DECLARE_BUF(inbuf,
-			  max(MC_CMD_LINK_PIOBUF_IN_LEN,
-			      MC_CMD_UNLINK_PIOBUF_IN_LEN));
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_LINK_PIOBUF_IN_LEN);
 	struct efx_channel *channel;
 	struct efx_tx_queue *tx_queue;
 	unsigned int offset, index;
@@ -839,8 +837,6 @@ static int efx_ef10_link_piobufs(struct efx_nic *efx)
 	BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_OUT_LEN != 0);
 	BUILD_BUG_ON(MC_CMD_UNLINK_PIOBUF_OUT_LEN != 0);
 
-	memset(inbuf, 0, sizeof(inbuf));
-
 	/* Link a buffer to each VI in the write-combining mapping */
 	for (index = 0; index < nic_data->n_piobufs; ++index) {
 		MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_PIOBUF_HANDLE,
@@ -920,6 +916,10 @@ static int efx_ef10_link_piobufs(struct efx_nic *efx)
 	return 0;
 
 fail:
+	/* inbuf was defined for MC_CMD_LINK_PIOBUF.  We can use the same
+	 * buffer for MC_CMD_UNLINK_PIOBUF because it's shorter.
+	 */
+	BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_IN_LEN < MC_CMD_UNLINK_PIOBUF_IN_LEN);
 	while (index--) {
 		MCDI_SET_DWORD(inbuf, UNLINK_PIOBUF_IN_TXQ_INSTANCE,
 			       nic_data->pio_write_vi_base + index);
-- 
GitLab


From 6d43131c158f42e2138d83495d19c70ed5cc0ffe Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 3 Mar 2017 15:22:27 +0000
Subject: [PATCH 701/898] sfc: fix IPID endianness in TSOv2

The value we read from the header is in network byte order, whereas
 EFX_POPULATE_QWORD_* takes values in host byte order (which it then
 converts to little-endian, as MCDI is little-endian).

Fixes: e9117e5099ea ("sfc: Firmware-Assisted TSO version 2")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 4d88e8532d3e..c60c2d4c646a 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2183,7 +2183,7 @@ static int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue,
 		/* Modify IPv4 header if needed. */
 		ip->tot_len = 0;
 		ip->check = 0;
-		ipv4_id = ip->id;
+		ipv4_id = ntohs(ip->id);
 	} else {
 		/* Modify IPv6 header if needed. */
 		struct ipv6hdr *ipv6 = ipv6_hdr(skb);
-- 
GitLab


From d3c1a297b6fe60fe7be637cb067b27fca46be504 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Fri, 24 Feb 2017 10:42:14 +0200
Subject: [PATCH 702/898] Documentation: Update path to sysrq.txt

Commit 9d85025b0418 ("docs-rst: create an user's manual book") moved the
sysrq.txt leaving old paths in the kernel docs.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/media/v4l-drivers/bttv.rst          | 2 +-
 Documentation/s390/Debugging390.txt               | 2 +-
 Documentation/sysctl/kernel.txt                   | 2 +-
 Documentation/virtual/uml/UserModeLinux-HOWTO.txt | 6 +++---
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/Documentation/media/v4l-drivers/bttv.rst b/Documentation/media/v4l-drivers/bttv.rst
index bc63b12efafd..195ccaac2816 100644
--- a/Documentation/media/v4l-drivers/bttv.rst
+++ b/Documentation/media/v4l-drivers/bttv.rst
@@ -312,7 +312,7 @@ information out of a register+stack dump printed by the kernel on
 protection faults (so-called "kernel oops").
 
 If you run into some kind of deadlock, you can try to dump a call trace
-for each process using sysrq-t (see Documentation/sysrq.txt).
+for each process using sysrq-t (see Documentation/admin-guide/sysrq.rst).
 This way it is possible to figure where *exactly* some process in "D"
 state is stuck.
 
diff --git a/Documentation/s390/Debugging390.txt b/Documentation/s390/Debugging390.txt
index 3df8babcdc41..5ae7f868a007 100644
--- a/Documentation/s390/Debugging390.txt
+++ b/Documentation/s390/Debugging390.txt
@@ -2116,7 +2116,7 @@ The sysrq key reading is very picky ( I have to type the keys in an
 This is particularly useful for syncing disks unmounting & rebooting
 if the machine gets partially hung.
 
-Read Documentation/sysrq.txt for more info
+Read Documentation/admin-guide/sysrq.rst for more info
 
 References:
 ===========
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index a32b4b748644..bac23c198360 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -85,7 +85,7 @@ show up in /proc/sys/kernel:
 - softlockup_all_cpu_backtrace
 - soft_watchdog
 - stop-a                      [ SPARC only ]
-- sysrq                       ==> Documentation/sysrq.txt
+- sysrq                       ==> Documentation/admin-guide/sysrq.rst
 - sysctl_writes_strict
 - tainted
 - threads-max
diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
index f4099ca6b483..87b80f589e1c 100644
--- a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
@@ -2401,9 +2401,9 @@
 
   This takes one argument, which is a single letter.  It calls the
   generic kernel's SysRq driver, which does whatever is called for by
-  that argument.  See the SysRq documentation in Documentation/sysrq.txt
-  in your favorite kernel tree to see what letters are valid and what
-  they do.
+  that argument.  See the SysRq documentation in
+  Documentation/admin-guide/sysrq.rst in your favorite kernel tree to
+  see what letters are valid and what they do.
 
 
 
-- 
GitLab


From 2eb6a4b26d13c51bdb8d5aefdfc846c0624b8ce4 Mon Sep 17 00:00:00 2001
From: Cao jin <caoj.fnst@cn.fujitsu.com>
Date: Wed, 1 Mar 2017 17:05:28 +0800
Subject: [PATCH 703/898] pcieaer doc: update the link

The original link is empty, replace it.

Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/PCI/pcieaer-howto.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/PCI/pcieaer-howto.txt b/Documentation/PCI/pcieaer-howto.txt
index ea8cafba255c..acd0dddd6bb8 100644
--- a/Documentation/PCI/pcieaer-howto.txt
+++ b/Documentation/PCI/pcieaer-howto.txt
@@ -256,7 +256,7 @@ After reboot with new kernel or insert the module, a device file named
 
 Then, you need a user space tool named aer-inject, which can be gotten
 from:
-    http://www.kernel.org/pub/linux/utils/pci/aer-inject/
+    https://git.kernel.org/cgit/linux/kernel/git/gong.chen/aer-inject.git/
 
 More information about aer-inject can be found in the document comes
 with its source code.
-- 
GitLab


From 9857b1ad4740ec2429e8ec0a39946d45a8d2cff9 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj38.park@gmail.com>
Date: Fri, 3 Mar 2017 15:44:02 +0900
Subject: [PATCH 704/898] doc/ko_KR/memory-barriers: Update
 control-dependencies section

This commit applies upstream change, commit c8241f8553e8 ("doc: Update
control-dependencies section of memory-barriers.txt"), to Korean
translation.

Signed-off-by: SeongJae Park <sj38.park@gmail.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 .../translations/ko_KR/memory-barriers.txt    | 68 ++++++++++---------
 1 file changed, 37 insertions(+), 31 deletions(-)

diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index a3228a676cc1..ce0b48d69eaa 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -662,6 +662,10 @@ include/linux/rcupdate.h 의 rcu_assign_pointer() 와 rcu_dereference() 를
 컨트롤 의존성
 -------------
 
+현재의 컴파일러들은 컨트롤 의존성을 이해하고 있지 않기 때문에 컨트롤 의존성은
+약간 다루기 어려울 수 있습니다.  이 섹션의 목적은 여러분이 컴파일러의 무시로
+인해 여러분의 코드가 망가지는 걸 막을 수 있도록 돕는겁니다.
+
 로드-로드 컨트롤 의존성은 데이터 의존성 배리어만으로는 정확히 동작할 수가
 없어서 읽기 메모리 배리어를 필요로 합니다.  아래의 코드를 봅시다:
 
@@ -689,20 +693,21 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 
 	q = READ_ONCE(a);
 	if (q) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 	}
 
 컨트롤 의존성은 보통 다른 타입의 배리어들과 짝을 맞춰 사용됩니다.  그렇다곤
-하나, READ_ONCE() 는 반드시 사용해야 함을 부디 명심하세요!  READ_ONCE() 가
-없다면, 컴파일러가 'a' 로부터의 로드를 'a' 로부터의 또다른 로드와, 'b' 로의
-스토어를 'b' 로의 또다른 스토어와 조합해 버려 매우 비직관적인 결과를 초래할 수
-있습니다.
+하나, READ_ONCE() 도 WRITE_ONCE() 도 선택사항이 아니라 필수사항임을 부디
+명심하세요!  READ_ONCE() 가 없다면, 컴파일러는 'a' 로부터의 로드를 'a' 로부터의
+또다른 로드와 조합할 수 있습니다.  WRITE_ONCE() 가 없다면, 컴파일러는 'b' 로의
+스토어를 'b' 로의 또라느 스토어들과 조합할 수 있습니다.  두 경우 모두 순서에
+있어 상당히 비직관적인 결과를 초래할 수 있습니다.
 
 이걸로 끝이 아닌게, 컴파일러가 변수 'a' 의 값이 항상 0이 아니라고 증명할 수
 있다면, 앞의 예에서 "if" 문을 없애서 다음과 같이 최적화 할 수도 있습니다:
 
 	q = a;
-	b = p;  /* BUG: Compiler and CPU can both reorder!!! */
+	b = 1;  /* BUG: Compiler and CPU can both reorder!!! */
 
 그러니 READ_ONCE() 를 반드시 사용하세요.
 
@@ -712,11 +717,11 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 	q = READ_ONCE(a);
 	if (q) {
 		barrier();
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
 		barrier();
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something_else();
 	}
 
@@ -725,12 +730,12 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 
 	q = READ_ONCE(a);
 	barrier();
-	WRITE_ONCE(b, p);  /* BUG: No ordering vs. load from a!!! */
+	WRITE_ONCE(b, 1);  /* BUG: No ordering vs. load from a!!! */
 	if (q) {
-		/* WRITE_ONCE(b, p); -- moved up, BUG!!! */
+		/* WRITE_ONCE(b, 1); -- moved up, BUG!!! */
 		do_something();
 	} else {
-		/* WRITE_ONCE(b, p); -- moved up, BUG!!! */
+		/* WRITE_ONCE(b, 1); -- moved up, BUG!!! */
 		do_something_else();
 	}
 
@@ -742,10 +747,10 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 
 	q = READ_ONCE(a);
 	if (q) {
-		smp_store_release(&b, p);
+		smp_store_release(&b, 1);
 		do_something();
 	} else {
-		smp_store_release(&b, p);
+		smp_store_release(&b, 1);
 		do_something_else();
 	}
 
@@ -754,10 +759,10 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 
 	q = READ_ONCE(a);
 	if (q) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 		do_something_else();
 	}
 
@@ -770,10 +775,10 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 
 	q = READ_ONCE(a);
 	if (q % MAX) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 		do_something_else();
 	}
 
@@ -781,7 +786,7 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 위의 코드를 아래와 같이 바꿔버릴 수 있습니다:
 
 	q = READ_ONCE(a);
-	WRITE_ONCE(b, p);
+	WRITE_ONCE(b, 1);
 	do_something_else();
 
 이렇게 되면, CPU 는 변수 'a' 로부터의 로드와 변수 'b' 로의 스토어 사이의 순서를
@@ -793,10 +798,10 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 	q = READ_ONCE(a);
 	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
 	if (q % MAX) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 		do_something_else();
 	}
 
@@ -828,35 +833,33 @@ CPU 는 b 로부터의 로드 오퍼레이션이 a 로부터의 로드 오퍼레
 
 	q = READ_ONCE(a);
 	if (q) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 	}
-	WRITE_ONCE(c, 1);  /* BUG: No ordering against the read from "a". */
+	WRITE_ONCE(c, 1);  /* BUG: No ordering against the read from 'a'. */
 
-컴파일러는 volatile 타입에 대한 액세스를 재배치 할 수 없고 이 조건 하의 "b"
+컴파일러는 volatile 타입에 대한 액세스를 재배치 할 수 없고 이 조건 하의 'b'
 로의 쓰기를 재배치 할 수 없기 때문에 여기에 순서 규칙이 존재한다고 주장하고
 싶을 겁니다.  불행히도 이 경우에, 컴파일러는 다음의 가상의 pseudo-assembly 언어
-코드처럼 "b" 로의 두개의 쓰기 오퍼레이션을 conditional-move 인스트럭션으로
+코드처럼 'b' 로의 두개의 쓰기 오퍼레이션을 conditional-move 인스트럭션으로
 번역할 수 있습니다:
 
 	ld r1,a
-	ld r2,p
-	ld r3,r
 	cmp r1,$0
-	cmov,ne r4,r2
-	cmov,eq r4,r3
+	cmov,ne r4,$1
+	cmov,eq r4,$2
 	st r4,b
 	st $1,c
 
-완화된 순서 규칙의 CPU 는 "a" 로부터의 로드와 "c" 로의 스토어 사이에 어떤
+완화된 순서 규칙의 CPU 는 'a' 로부터의 로드와 'c' 로의 스토어 사이에 어떤
 종류의 의존성도 갖지 않을 겁니다.  이 컨트롤 의존성은 두개의 cmov 인스트럭션과
 거기에 의존하는 스토어 에게만 적용될 겁니다.  짧게 말하자면, 컨트롤 의존성은
 주어진 if 문의 then 절과 else 절에게만 (그리고 이 두 절 내에서 호출되는
 함수들에게까지) 적용되지, 이 if 문을 뒤따르는 코드에는 적용되지 않습니다.
 
 마지막으로, 컨트롤 의존성은 이행성 (transitivity) 을 제공하지 -않습니다-.  이건
-x 와 y 가 둘 다 0 이라는 초기값을 가졌다는 가정 하의 두개의 예제로
+'x' 와 'y' 가 둘 다 0 이라는 초기값을 가졌다는 가정 하의 두개의 예제로
 보이겠습니다:
 
 	CPU 0                     CPU 1
@@ -924,6 +927,9 @@ http://www.cl.cam.ac.uk/users/pes20/ppc-supplemental/test6.pdf 와
   (*) 컨트롤 의존성은 이행성을 제공하지 -않습니다-.  이행성이 필요하다면,
       smp_mb() 를 사용하세요.
 
+  (*) 컴파일러는 컨트롤 의존성을 이해하고 있지 않습니다.  따라서 컴파일러가
+      여러분의 코드를 망가뜨리지 않도록 하는건 여러분이 해야 하는 일입니다.
+
 
 SMP 배리어 짝맞추기
 --------------------
-- 
GitLab


From f3fc83e55533b9fddac1d4eda79956768df569ea Mon Sep 17 00:00:00 2001
From: Martyn Welch <martyn.welch@collabora.co.uk>
Date: Fri, 3 Mar 2017 22:43:30 +0000
Subject: [PATCH 705/898] docs: Fix htmldocs build failure

Build of HTML docs failing due to conversion of deviceiobook.tmpl in
8a8a602f and regulator.tmpl in 028f2533 to RST without removing from
DOCBOOKS in Makefile, resulting (in the case of deviceiobook) the
following error:

make[1]: *** No rule to make target 'Documentation/DocBook/deviceiobook.xml', needed by 'Documentation/DocBook/deviceiobook.aux.xml'.  Stop.
Makefile:1452: recipe for target 'htmldocs' failed
make: *** [htmldocs] Error 2

Update DOCBOOKS to reflect available books.

Signed-off-by: Martyn Welch <martyn.welch@collabora.co.uk>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/DocBook/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 7b8831fb4e37..c339cf59ad69 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -7,12 +7,12 @@
 # list of DOCBOOKS.
 
 DOCBOOKS := z8530book.xml  \
-	    kernel-hacking.xml kernel-locking.xml deviceiobook.xml \
+	    kernel-hacking.xml kernel-locking.xml \
 	    writing_usb_driver.xml networking.xml \
 	    kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-	    sh.xml regulator.xml w1.xml \
+	    sh.xml w1.xml \
 	    writing_musb_glue_layer.xml
 
 ifeq ($(DOCBOOKS),)
-- 
GitLab


From fd5d666932d51b2552ecc0280047d6b35d9b6cd1 Mon Sep 17 00:00:00 2001
From: John Keeping <john@metanate.com>
Date: Fri, 3 Mar 2017 12:24:05 +0000
Subject: [PATCH 706/898] Documentation/sphinx: fix primary_domain
 configuration

With Sphinx 1.5.3 I get the warning:

	WARNING: primary_domain 'C' not found, ignored.

It seems that domain names in Sphinx are case-sensitive and for the C
domain the name must be lower case.

Signed-off-by: John Keeping <john@metanate.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/conf.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/conf.py b/Documentation/conf.py
index f6823cf01275..7fadb3b83293 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -135,7 +135,7 @@ pygments_style = 'sphinx'
 # If true, `todo` and `todoList` produce output, else they produce nothing.
 todo_include_todos = False
 
-primary_domain = 'C'
+primary_domain = 'c'
 highlight_language = 'none'
 
 # -- Options for HTML output ----------------------------------------------
-- 
GitLab


From 2bc756e7dde20972300bb8e2e46dd430d6d2d5db Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 2 Mar 2017 23:22:29 +0100
Subject: [PATCH 707/898] cpufreq: intel_pstate: Do not use performance_limits
 in passive mode

Using performance_limits in the passive mode doesn't make
sense, because in that mode the global limits are applied to the
frequency selected by the scaling governor.

The maximum and minimum P-state limits in performance_limits are both
set to 100 percent which will put all CPUs into the turbo range
regardless of what governor is used and what frequencies are
selected by it (that is particularly undesirable on CPUs with the
generic powersave governor attached).

For this reason, make intel_pstate_register_driver() always point
limits to powersave_limits in the passive mode.

Fixes: 001c76f05b01 (cpufreq: intel_pstate: Generic governors support)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9ee13f195c37..7fc1f8a0ef44 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2442,8 +2442,11 @@ static int intel_pstate_register_driver(void)
 
 	intel_pstate_init_limits(&powersave_limits);
 	intel_pstate_set_performance_limits(&performance_limits);
-	limits = IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) ?
-			&performance_limits : &powersave_limits;
+	if (IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) &&
+	    intel_pstate_driver == &intel_pstate)
+		limits = &performance_limits;
+	else
+		limits = &powersave_limits;
 
 	ret = cpufreq_register_driver(intel_pstate_driver);
 	if (ret) {
-- 
GitLab


From 7f17326fc0b69afbda7aed6c4ce8e2328b74203b Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 2 Mar 2017 23:24:36 +0100
Subject: [PATCH 708/898] cpufreq: intel_pstate: Fix
 intel_cpufreq_verify_policy()

The intel_pstate_update_perf_limits() called from
intel_cpufreq_verify_policy() may cause global P-state limits
to change which is generally confusing and unnecessary.

In the passive mode the global limits are only applied to the
frequency selected by the scaling governor (they are not taken
into account by governors when making decisions anyway), so making
them follow the per-policy limits serves no purpose and may go
against user expectations (as it generally causes the global
attributes in sysfs to change even though they have not been
written to in some cases).

Fix that by dropping the intel_pstate_update_perf_limits()
invocation from intel_cpufreq_verify_policy() (which also
reduces the code size by a few lines).

This change does not affect the per-CPU limits case, because those
limits allow any P-state to be set by default in the passive mode
and it removes the only piece of code updating them in that mode,
so the per-policy settings will be the only ones taken into account
in that case as expected.

Fixes: 001c76f05b01 (cpufreq: intel_pstate: Generic governors support)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 7fc1f8a0ef44..04b2aa162276 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2306,7 +2306,6 @@ static struct cpufreq_driver intel_pstate = {
 static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
-	struct perf_limits *perf_limits = limits;
 
 	update_turbo_state();
 	policy->cpuinfo.max_freq = limits->turbo_disabled ?
@@ -2314,15 +2313,6 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
 
 	cpufreq_verify_within_cpu_limits(policy);
 
-	if (per_cpu_limits)
-		perf_limits = cpu->perf_limits;
-
-	mutex_lock(&intel_pstate_limits_lock);
-
-	intel_pstate_update_perf_limits(policy, perf_limits);
-
-	mutex_unlock(&intel_pstate_limits_lock);
-
 	return 0;
 }
 
-- 
GitLab


From 6407829901f074cf6beef566d6af9a0b0e238f0d Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 3 Mar 2017 23:51:31 +0100
Subject: [PATCH 709/898] cpufreq: intel_pstate: Avoid triggering cpu_frequency
 tracepoint unnecessarily

In the passive mode the cpu_frequency trace event is already
triggered by the cpufreq core or by scaling governors, so
intel_pstate should not trigger it once again for the same
P-state updates.

In addition to that, the frequency returned by
intel_cpufreq_fast_switch() and passed via freqs.new from
intel_cpufreq_target() to cpufreq_freq_transition_end() should
reflect the P-state actually set, so make that happen.

Fixes: 001c76f05b01 (cpufreq: intel_pstate: Generic governors support)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 04b2aa162276..5e066b332598 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1879,13 +1879,11 @@ static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
 
 	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 	pstate = clamp_t(int, pstate, min_perf, max_perf);
-	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 	return pstate;
 }
 
 static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
 {
-	pstate = intel_pstate_prepare_request(cpu, pstate);
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
@@ -1905,6 +1903,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 
 	update_turbo_state();
 
+	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+	trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu);
 	intel_pstate_update_pstate(cpu, target_pstate);
 
 	sample = &cpu->sample;
@@ -2365,6 +2365,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 		wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
 			      pstate_funcs.get_val(cpu, target_pstate));
 	}
+	freqs.new = target_pstate * cpu->pstate.scaling;
 	cpufreq_freq_transition_end(policy, &freqs, false);
 
 	return 0;
@@ -2378,8 +2379,9 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 
 	target_freq = intel_cpufreq_turbo_update(cpu, policy, target_freq);
 	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
+	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
 	intel_pstate_update_pstate(cpu, target_pstate);
-	return target_freq;
+	return target_pstate * cpu->pstate.scaling;
 }
 
 static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
-- 
GitLab


From f78ef7cd9a0686b979679d0de061c6dbfd8d649e Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Fri, 3 Mar 2017 12:21:14 -0800
Subject: [PATCH 710/898] strparser: destroy workqueue on module exit

Fixes: 43a0c6751a32 ("strparser: Stream parser for messages")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 41adf362936d..b5c279b22680 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -504,6 +504,7 @@ static int __init strp_mod_init(void)
 
 static void __exit strp_mod_exit(void)
 {
+	destroy_workqueue(strp_wq);
 }
 module_init(strp_mod_init);
 module_exit(strp_mod_exit);
-- 
GitLab


From 2a9c4f40ab2c281f95d41577ff0f7f78668feb73 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Thu, 2 Mar 2017 17:41:24 +1100
Subject: [PATCH 711/898] powerpc/powernv: Fix opal tracepoints with
 JUMP_LABEL=n

The recent commit to allow calling OPAL calls in real mode, commit
ab9bad0ead9a ("powerpc/powernv: Remove separate entry for OPAL real mode
calls"), introduced a bug when CONFIG_JUMP_LABEL=n.

The commit moved the "mfmsr r12" prior to the call to OPAL_BRANCH, but
we missed that OPAL_BRANCH clobbers r12 when jump labels are disabled.
This leads to us using the tracepoint refcount as the MSR value,
typically zero, and saving that into PACASAVEDMSR. When we return from
OPAL we use that value as the MSR value for rfid, meaning we switch to
32-bit BE real mode - hilarity ensues.

Fix it by using r11 in OPAL_BRANCH, which is not live at the time the
macro is used in OPAL_CALL.

Fixes: ab9bad0ead9a ("powerpc/powernv: Remove separate entry for OPAL real mode calls")
Suggested-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/powernv/opal-wrappers.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6693f75e93d1..da8a0f7a035c 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -39,8 +39,8 @@ opal_tracepoint_refcount:
 BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
-	ld	r12,opal_tracepoint_refcount@toc(r2);		\
-	cmpdi	r12,0;						\
+	ld	r11,opal_tracepoint_refcount@toc(r2);		\
+	cmpdi	r11,0;						\
 	bne-	LABEL;						\
 1:
 
-- 
GitLab


From 6ad966d7303b70165228dba1ee8da1a05c10eefe Mon Sep 17 00:00:00 2001
From: Shile Zhang <shile.zhang@nokia.com>
Date: Sat, 4 Feb 2017 17:03:40 +0800
Subject: [PATCH 712/898] powerpc/64: Fix checksum folding in csum_add()

Paul's patch to fix checksum folding, commit b492f7e4e07a ("powerpc/64:
Fix checksum folding in csum_tcpudp_nofold and ip_fast_csum_nofold")
missed a case in csum_add(). Fix it.

Signed-off-by: Shile Zhang <shile.zhang@nokia.com>
Acked-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/checksum.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 4e63787dc3be..842124b199b5 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
 
 #ifdef __powerpc64__
 	res += (__force u64)addend;
-	return (__force __wsum)((u32)res + (res >> 32));
+	return (__force __wsum) from64to32(res);
 #else
 	asm("addc %0,%0,%1;"
 	    "addze %0,%0;"
-- 
GitLab


From c1ae3cfa0e89fa1a7ecc4c99031f5e9ae99d9201 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 5 Mar 2017 12:59:56 -0800
Subject: [PATCH 713/898] Linux 4.11-rc1

---
 Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 4cb6b0a1152b..165cf9783a5d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
-PATCHLEVEL = 10
+PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
-- 
GitLab


From 6c4f0fa643cb9e775dcc976e3db00d649468ff1d Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 2 Mar 2017 14:03:20 +0530
Subject: [PATCH 714/898] cpufreq: schedutil: move cached_raw_freq to struct
 sugov_policy

cached_raw_freq applies to the entire cpufreq policy and not individual
CPUs. Apart from wasting per-cpu memory, it is actually wrong to keep it
in struct sugov_cpu as we may end up comparing next_freq with a stale
cached_raw_freq of a random CPU.

Move cached_raw_freq to struct sugov_policy.

Fixes: 5cbea46984d6 (cpufreq: schedutil: map raw required frequency to driver frequency)
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/sched/cpufreq_schedutil.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 8f8de3d4d6b7..3ab2aeaec6ec 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -36,6 +36,7 @@ struct sugov_policy {
 	u64 last_freq_update_time;
 	s64 freq_update_delay_ns;
 	unsigned int next_freq;
+	unsigned int cached_raw_freq;
 
 	/* The next fields are only needed if fast switch cannot be used. */
 	struct irq_work irq_work;
@@ -52,7 +53,6 @@ struct sugov_cpu {
 	struct update_util_data update_util;
 	struct sugov_policy *sg_policy;
 
-	unsigned int cached_raw_freq;
 	unsigned long iowait_boost;
 	unsigned long iowait_boost_max;
 	u64 last_update;
@@ -146,9 +146,9 @@ static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
 
 	freq = (freq + (freq >> 2)) * util / max;
 
-	if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+	if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
 		return sg_policy->next_freq;
-	sg_cpu->cached_raw_freq = freq;
+	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
@@ -580,6 +580,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->next_freq = UINT_MAX;
 	sg_policy->work_in_progress = false;
 	sg_policy->need_freq_update = false;
+	sg_policy->cached_raw_freq = 0;
 
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
@@ -590,7 +591,6 @@ static int sugov_start(struct cpufreq_policy *policy)
 			sg_cpu->max = 0;
 			sg_cpu->flags = SCHED_CPUFREQ_RT;
 			sg_cpu->last_update = 0;
-			sg_cpu->cached_raw_freq = 0;
 			sg_cpu->iowait_boost = 0;
 			sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
 			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-- 
GitLab


From 655cb1ebff4b7918fc560502c3297af2d3c7d114 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 2 Mar 2017 14:03:21 +0530
Subject: [PATCH 715/898] cpufreq: schedutil: Pass sg_policy to get_next_freq()

get_next_freq() uses sg_cpu only to get sg_policy, which the callers of
get_next_freq() already have. Pass sg_policy instead of sg_cpu to
get_next_freq(), to make it more efficient.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/sched/cpufreq_schedutil.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3ab2aeaec6ec..cd7cd489f739 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -116,7 +116,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
 
 /**
  * get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @sg_cpu: schedutil cpu object to compute the new frequency for.
+ * @sg_policy: schedutil policy object to compute the new frequency for.
  * @util: Current CPU utilization.
  * @max: CPU capacity.
  *
@@ -136,10 +136,9 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
  * next_freq (as calculated above) is returned, subject to policy min/max and
  * cpufreq driver limitations.
  */
-static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
-				  unsigned long max)
+static unsigned int get_next_freq(struct sugov_policy *sg_policy,
+				  unsigned long util, unsigned long max)
 {
-	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
 	unsigned int freq = arch_scale_freq_invariant() ?
 				policy->cpuinfo.max_freq : policy->cur;
@@ -213,7 +212,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	} else {
 		sugov_get_util(&util, &max);
 		sugov_iowait_boost(sg_cpu, &util, &max);
-		next_f = get_next_freq(sg_cpu, util, max);
+		next_f = get_next_freq(sg_policy, util, max);
 	}
 	sugov_update_commit(sg_policy, time, next_f);
 }
@@ -267,7 +266,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 		sugov_iowait_boost(j_sg_cpu, &util, &max);
 	}
 
-	return get_next_freq(sg_cpu, util, max);
+	return get_next_freq(sg_policy, util, max);
 }
 
 static void sugov_update_shared(struct update_util_data *hook, u64 time,
-- 
GitLab


From d82f26925599cae83c38d17d07ae982356e81318 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 28 Feb 2017 16:44:16 -0500
Subject: [PATCH 716/898] cpufreq: Add the "cpufreq.off=1" cmdline option

Add the "cpufreq.off=1" cmdline option.

At boot-time, this allows a user to request CONFIG_CPU_FREQ=n
behavior from a kernel built with CONFIG_CPU_FREQ=y.

This is analogous to the existing "cpuidle.off=1" option
and CONFIG_CPU_IDLE=y

This capability is valuable when we need to debug end-user
issues in the BIOS or in Linux.  It is also convenient
for enabling comparisons, which may otherwise require a new kernel,
or help from BIOS SETUP, which may be buggy or unavailable.

Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/admin-guide/kernel-parameters.txt | 3 +++
 drivers/cpufreq/cpufreq.c                       | 1 +
 2 files changed, 4 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index be7c0d9506b1..3988d2311f97 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -662,6 +662,9 @@
 	cpuidle.off=1	[CPU_IDLE]
 			disable the cpuidle sub-system
 
+	cpufreq.off=1	[CPU_FREQ]
+			disable the cpufreq sub-system
+
 	cpu_init_udelay=N
 			[X86] Delay for N microsec between assert and de-assert
 			of APIC INIT to start processors.  This delay occurs
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 80a785ad17e8..7790db2645d7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2532,4 +2532,5 @@ static int __init cpufreq_core_init(void)
 
 	return 0;
 }
+module_param(off, int, 0444);
 core_initcall(cpufreq_core_init);
-- 
GitLab


From cd59b4bed9d11a2aefc4bb44eed9de0e6c1eea06 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 1 Mar 2017 00:07:36 +0100
Subject: [PATCH 717/898] cpufreq: intel_pstate: Fix global settings in active
 mode

Commit 111b8b3fe4fa (cpufreq: intel_pstate: Always keep all
limits settings in sync) changed intel_pstate to invoke
cpufreq_update_policy() for every registered CPU on global sysfs
attributes updates, but that led to undesirable effects in the
active mode if the "performance" P-state selection algorithm is
configufred for one CPU and the "powersave" one is chosen for
all of the other CPUs.

Namely, in that case, the following is possible:

 # cd /sys/devices/system/cpu/
 # cat intel_pstate/max_perf_pct
 100
 # cat intel_pstate/min_perf_pct
 26
 # echo performance > cpufreq/policy0/scaling_governor
 # cat intel_pstate/max_perf_pct
 100
 # cat intel_pstate/min_perf_pct
 100
 # echo 94 > intel_pstate/min_perf_pct
 # cat intel_pstate/min_perf_pct
 26

The reason why this happens is because intel_pstate attempts to
maintain two sets of global limits in the active mode, one for
the "performance" P-state selection algorithm and one for the
"powersave"  P-state selection algorithm, but the P-state selection
algorithms are set per policy, so the global limits cannot reflect
all of them at the same time if they are different for different
policies.

In the particular situation above, the attempt to change
min_perf_pct to 94 caused cpufreq_update_policy() to be run
for a CPU with the "powersave"  P-state selection algorithm
and intel_pstate_set_policy() called by it silently switched the
global limits to the "powersave" set which finally was reflected
by the sysfs interface.

To prevent that from happening, modify intel_pstate_update_policies()
to always switch back to the set of limits that was used right before
it has been invoked.

Fixes: 111b8b3fe4fa (cpufreq: intel_pstate: Always keep all limits settings in sync)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 5e066b332598..436a4c5ba70d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -973,11 +973,20 @@ static int intel_pstate_resume(struct cpufreq_policy *policy)
 }
 
 static void intel_pstate_update_policies(void)
+	__releases(&intel_pstate_limits_lock)
+	__acquires(&intel_pstate_limits_lock)
 {
+	struct perf_limits *saved_limits = limits;
 	int cpu;
 
+	mutex_unlock(&intel_pstate_limits_lock);
+
 	for_each_possible_cpu(cpu)
 		cpufreq_update_policy(cpu);
+
+	mutex_lock(&intel_pstate_limits_lock);
+
+	limits = saved_limits;
 }
 
 /************************** debugfs begin ************************/
@@ -1185,10 +1194,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
 	limits->no_turbo = clamp_t(int, input, 0, 1);
 
-	mutex_unlock(&intel_pstate_limits_lock);
-
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_limits_lock);
+
 	mutex_unlock(&intel_pstate_driver_lock);
 
 	return count;
@@ -1222,10 +1231,10 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 				   limits->max_perf_pct);
 	limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
 
-	mutex_unlock(&intel_pstate_limits_lock);
-
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_limits_lock);
+
 	mutex_unlock(&intel_pstate_driver_lock);
 
 	return count;
@@ -1259,10 +1268,10 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 				   limits->min_perf_pct);
 	limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
 
-	mutex_unlock(&intel_pstate_limits_lock);
-
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_limits_lock);
+
 	mutex_unlock(&intel_pstate_driver_lock);
 
 	return count;
-- 
GitLab


From d74b19929130c9b5395a497030dcf161353cd526 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 1 Mar 2017 00:11:05 +0100
Subject: [PATCH 718/898] cpufreq: intel_pstate: Fix
 intel_pstate_verify_policy()

The code added to intel_pstate_verify_policy() by commit 1443ebbacfd7
(cpufreq: intel_pstate: Fix sysfs limits enforcement for performance
policy) should use perf_limits instead of limits, because otherwise
setting global limits via sysfs may affect policies inconsistently.

For example, in the sequence of shell commands below, the
scaling_min_freq attribute for policy1 and policy2 should be
affected in the same way, because scaling_governor is set in
the same way for both of them:

 # cat cpufreq/policy1/scaling_governor
 powersave
 # cat cpufreq/policy2/scaling_governor
 powersave
 # echo performance > cpufreq/policy0/scaling_governor
 # echo 94 > intel_pstate/min_perf_pct
 # cat cpufreq/policy0/scaling_min_freq
 2914000
 # cat cpufreq/policy1/scaling_min_freq
 2914000
 # cat cpufreq/policy2/scaling_min_freq
 800000

The are affected differently, because intel_pstate_verify_policy()
is invoked with limits set to &performance_limits (left behind by
policy0) for policy1 and with limits set to &powersave_limits (left
behind by policy1) for policy2.  Since perf_limits is set to the
set of limits matching the policy being updated, using it instead
of limits fixes the inconsistency.

Fixes: 1443ebbacfd7 (cpufreq: intel_pstate: Fix sysfs limits enforcement for performance policy)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 436a4c5ba70d..3dc546601c88 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2212,9 +2212,9 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
 		unsigned int max_freq, min_freq;
 
 		max_freq = policy->cpuinfo.max_freq *
-						limits->max_sysfs_pct / 100;
+					perf_limits->max_sysfs_pct / 100;
 		min_freq = policy->cpuinfo.max_freq *
-						limits->min_sysfs_pct / 100;
+					perf_limits->min_sysfs_pct / 100;
 		cpufreq_verify_within_limits(policy, min_freq, max_freq);
 	}
 
-- 
GitLab


From a240c4aa5d0f9c8bb0db380ab9c1ec1f68b923ad Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 2 Mar 2017 23:29:12 +0100
Subject: [PATCH 719/898] cpufreq: intel_pstate: Do not reinit performance
 limits in ->setpolicy

If the current P-state selection algorithm is set to "performance"
in intel_pstate_set_policy(), the limits may be initialized from
scratch, but only if no_turbo is not set and the maximum frequency
allowed for the given CPU (i.e. the policy object representing it)
is at least equal to the max frequency supported by the CPU.  In all
of the other cases, the limits will not be updated.

For example, the following can happen:

 # cat intel_pstate/status
 active
 # echo performance > cpufreq/policy0/scaling_governor
 # cat intel_pstate/min_perf_pct
 100
 # echo 94 > intel_pstate/min_perf_pct
 # cat intel_pstate/min_perf_pct
 100
 # cat cpufreq/policy0/scaling_max_freq
 3100000
 echo 3000000 > cpufreq/policy0/scaling_max_freq
 # cat intel_pstate/min_perf_pct
 94
 # echo 95 > intel_pstate/min_perf_pct
 # cat intel_pstate/min_perf_pct
 95

That is confusing for two reasons.  First, the initial attempt to
change min_perf_pct to 94 seems to have no effect, even though
setting the global limits should always work.  Second, after
changing scaling_max_freq for policy0 the global min_perf_pct
attribute shows 94, even though it should have not been affected
by that operation in principle.

Moreover, the final attempt to change min_perf_pct to 95 worked
as expected, because scaling_max_freq for the only policy with
scaling_governor equal to "performance" was different from the
maximum at that time.

To make all that confusion go away, modify intel_pstate_set_policy()
so that it doesn't reinitialize the limits at all.

At the same time, change intel_pstate_set_performance_limits() to
set min_sysfs_pct to 100 in the "performance" limits set so that
switching the P-state selection algorithm to "performance" causes
intel_pstate/min_perf_pct in sysfs to go to 100 (or whatever value
min_sysfs_pct in the "performance" limits is set to later).

That requires per-CPU limits to be initialized explicitly rather
than by copying the global limits to avoid setting min_sysfs_pct
in the per-CPU limits to 100.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3dc546601c88..f1f8fbe0b4c4 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -382,6 +382,7 @@ static void intel_pstate_set_performance_limits(struct perf_limits *limits)
 	intel_pstate_init_limits(limits);
 	limits->min_perf_pct = 100;
 	limits->min_perf = int_ext_tofp(1);
+	limits->min_sysfs_pct = 100;
 }
 
 static DEFINE_MUTEX(intel_pstate_driver_lock);
@@ -2146,16 +2147,11 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	mutex_lock(&intel_pstate_limits_lock);
 
 	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		pr_debug("set performance\n");
 		if (!perf_limits) {
 			limits = &performance_limits;
 			perf_limits = limits;
 		}
-		if (policy->max >= policy->cpuinfo.max_freq &&
-		    !limits->no_turbo) {
-			pr_debug("set performance\n");
-			intel_pstate_set_performance_limits(perf_limits);
-			goto out;
-		}
 	} else {
 		pr_debug("set powersave\n");
 		if (!perf_limits) {
@@ -2166,7 +2162,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	}
 
 	intel_pstate_update_perf_limits(policy, perf_limits);
- out:
+
 	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		/*
 		 * NOHZ_FULL CPUs need this as the governor callback may not
@@ -2257,13 +2253,8 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	/*
-	 * We need sane value in the cpu->perf_limits, so inherit from global
-	 * perf_limits limits, which are seeded with values based on the
-	 * CONFIG_CPU_FREQ_DEFAULT_GOV_*, during boot up.
-	 */
 	if (per_cpu_limits)
-		memcpy(cpu->perf_limits, limits, sizeof(struct perf_limits));
+		intel_pstate_init_limits(cpu->perf_limits);
 
 	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
-- 
GitLab


From 36fc579761b50784b63dafd0f2e796b659e0f5ee Mon Sep 17 00:00:00 2001
From: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Date: Mon, 20 Feb 2017 16:25:45 +0100
Subject: [PATCH 720/898] drm/edid: Add EDID_QUIRK_FORCE_8BPC quirk for Rotel
 RSX-1058
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rotel RSX-1058 is a receiver with 4 HDMI inputs and a HDMI output, all
1.1.

When a sink that supports deep color is connected to the output, the
receiver will send EDIDs that advertise this capability, even if it
isn't possible with HDMI versions earlier than 1.3.

Currently the kernel is assuming that deep color is possible and the
sink displays an error.

This quirk will make sure that deep color isn't used with this
particular receiver.

Fixes: 7a0baa623446 ("Revert "drm/i915: Disable 12bpc hdmi for now"")
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170220152545.13153-1-tomeu.vizoso@collabora.com
Cc: stable@vger.kernel.org
Cc: Matt Horan <matt@matthoran.com>
Tested-by: Matt Horan <matt@matthoran.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=99869
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/drm_edid.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index c8baab9bee0d..ba58f1b11d1e 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -148,6 +148,9 @@ static const struct edid_quirk {
 
 	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
 	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
+
+	/* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/
+	{ "ETR", 13896, EDID_QUIRK_FORCE_8BPC },
 };
 
 /*
-- 
GitLab


From 7369090a9fb57c3fc705ce355d2e4523a5a24716 Mon Sep 17 00:00:00 2001
From: Felipe Balbi <felipe.balbi@linux.intel.com>
Date: Tue, 31 Jan 2017 13:24:54 +0200
Subject: [PATCH 721/898] usb: dwc3: gadget: make Set Endpoint Configuration
 macros safe

Some gadget drivers are bad, bad boys. We notice
that ADB was passing bad Burst Size which caused top
bits of param0 to be overwritten which confused DWC3
when running this command.

In order to avoid future issues, we're going to make
sure values passed by macros are always safe for the
controller. Note that ADB still needs a fix to *not*
pass bad values.

Cc: <stable@vger.kernel.org> # v3.2+
Reported-by: Mohamed Abbas <mohamed.abbas@intel.com>
Sugested-by: Adam Andruszak <adam.andruszak@intel.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/dwc3/gadget.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 3129bcf74d7d..265e223ab645 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -28,23 +28,23 @@ struct dwc3;
 #define gadget_to_dwc(g)	(container_of(g, struct dwc3, gadget))
 
 /* DEPCFG parameter 1 */
-#define DWC3_DEPCFG_INT_NUM(n)		((n) << 0)
+#define DWC3_DEPCFG_INT_NUM(n)		(((n) & 0x1f) << 0)
 #define DWC3_DEPCFG_XFER_COMPLETE_EN	(1 << 8)
 #define DWC3_DEPCFG_XFER_IN_PROGRESS_EN	(1 << 9)
 #define DWC3_DEPCFG_XFER_NOT_READY_EN	(1 << 10)
 #define DWC3_DEPCFG_FIFO_ERROR_EN	(1 << 11)
 #define DWC3_DEPCFG_STREAM_EVENT_EN	(1 << 13)
-#define DWC3_DEPCFG_BINTERVAL_M1(n)	((n) << 16)
+#define DWC3_DEPCFG_BINTERVAL_M1(n)	(((n) & 0xff) << 16)
 #define DWC3_DEPCFG_STREAM_CAPABLE	(1 << 24)
-#define DWC3_DEPCFG_EP_NUMBER(n)	((n) << 25)
+#define DWC3_DEPCFG_EP_NUMBER(n)	(((n) & 0x1f) << 25)
 #define DWC3_DEPCFG_BULK_BASED		(1 << 30)
 #define DWC3_DEPCFG_FIFO_BASED		(1 << 31)
 
 /* DEPCFG parameter 0 */
-#define DWC3_DEPCFG_EP_TYPE(n)		((n) << 1)
-#define DWC3_DEPCFG_MAX_PACKET_SIZE(n)	((n) << 3)
-#define DWC3_DEPCFG_FIFO_NUMBER(n)	((n) << 17)
-#define DWC3_DEPCFG_BURST_SIZE(n)	((n) << 22)
+#define DWC3_DEPCFG_EP_TYPE(n)		(((n) & 0x3) << 1)
+#define DWC3_DEPCFG_MAX_PACKET_SIZE(n)	(((n) & 0x7ff) << 3)
+#define DWC3_DEPCFG_FIFO_NUMBER(n)	(((n) & 0x1f) << 17)
+#define DWC3_DEPCFG_BURST_SIZE(n)	(((n) & 0xf) << 22)
 #define DWC3_DEPCFG_DATA_SEQ_NUM(n)	((n) << 26)
 /* This applies for core versions earlier than 1.94a */
 #define DWC3_DEPCFG_IGN_SEQ_NUM		(1 << 31)
-- 
GitLab


From 2bfa0719ac2a9b2f3c91345873d3cdebd0296ba9 Mon Sep 17 00:00:00 2001
From: Felipe Balbi <felipe.balbi@linux.intel.com>
Date: Tue, 31 Jan 2017 14:54:45 +0200
Subject: [PATCH 722/898] usb: gadget: function: f_fs: pass companion
 descriptor along

If we're dealing with SuperSpeed endpoints, we need
to make sure to pass along the companion descriptor
and initialize fields needed by the Gadget
API. Eventually, f_fs.c should be converted to use
config_ep_by_speed() like all other functions,
though.

Cc: <stable@vger.kernel.org>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/function/f_fs.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index a5b7cd615698..7e976f00cb02 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1834,11 +1834,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
 	spin_lock_irqsave(&func->ffs->eps_lock, flags);
 	while(count--) {
 		struct usb_endpoint_descriptor *ds;
+		struct usb_ss_ep_comp_descriptor *comp_desc = NULL;
+		int needs_comp_desc = false;
 		int desc_idx;
 
-		if (ffs->gadget->speed == USB_SPEED_SUPER)
+		if (ffs->gadget->speed == USB_SPEED_SUPER) {
 			desc_idx = 2;
-		else if (ffs->gadget->speed == USB_SPEED_HIGH)
+			needs_comp_desc = true;
+		} else if (ffs->gadget->speed == USB_SPEED_HIGH)
 			desc_idx = 1;
 		else
 			desc_idx = 0;
@@ -1855,6 +1858,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
 
 		ep->ep->driver_data = ep;
 		ep->ep->desc = ds;
+
+		comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds +
+				USB_DT_ENDPOINT_SIZE);
+		ep->ep->maxburst = comp_desc->bMaxBurst + 1;
+
+		if (needs_comp_desc)
+			ep->ep->comp_desc = comp_desc;
+
 		ret = usb_ep_enable(ep->ep);
 		if (likely(!ret)) {
 			epfile->ep = ep;
-- 
GitLab


From cf3113d893d4427b166ec8695460efa7aa660923 Mon Sep 17 00:00:00 2001
From: Felipe Balbi <felipe.balbi@linux.intel.com>
Date: Fri, 17 Feb 2017 11:12:44 +0200
Subject: [PATCH 723/898] usb: dwc3: gadget: properly increment dequeue pointer
 on ep_dequeue

If request was already started, this means we had to
stop the transfer. With that we also need to ignore
all TRBs used by the request, however TRBs can only
be modified after completion of END_TRANSFER
command. So what we have to do here is wait for
END_TRANSFER completion and only after that jump
over TRBs by clearing HWO and incrementing dequeue
pointer.

Note that we have 2 possible types of transfers
here:

i) Linear buffer request
ii) SG-list based request

SG-list based requests will have r->num_pending_sgs
set to a valid number (> 0). Linear requests,
normally use a single TRB.

For each of these two cases, if r->unaligned flag is
set, one extra TRB has been used to align transfer
size to wMaxPacketSize.

All of these cases need to be taken into
consideration so we don't mess up our TRB ring
pointers.

Tested-by: Janusz Dziedzic <januszx.dziedzic@intel.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/dwc3/gadget.c | 63 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4db97ecae885..f875b3f4b0ec 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1342,6 +1342,68 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 		if (r == req) {
 			/* wait until it is processed */
 			dwc3_stop_active_transfer(dwc, dep->number, true);
+
+			/*
+			 * If request was already started, this means we had to
+			 * stop the transfer. With that we also need to ignore
+			 * all TRBs used by the request, however TRBs can only
+			 * be modified after completion of END_TRANSFER
+			 * command. So what we do here is that we wait for
+			 * END_TRANSFER completion and only after that, we jump
+			 * over TRBs by clearing HWO and incrementing dequeue
+			 * pointer.
+			 *
+			 * Note that we have 2 possible types of transfers here:
+			 *
+			 * i) Linear buffer request
+			 * ii) SG-list based request
+			 *
+			 * SG-list based requests will have r->num_pending_sgs
+			 * set to a valid number (> 0). Linear requests,
+			 * normally use a single TRB.
+			 *
+			 * For each of these two cases, if r->unaligned flag is
+			 * set, one extra TRB has been used to align transfer
+			 * size to wMaxPacketSize.
+			 *
+			 * All of these cases need to be taken into
+			 * consideration so we don't mess up our TRB ring
+			 * pointers.
+			 */
+			wait_event_lock_irq(dep->wait_end_transfer,
+					!(dep->flags & DWC3_EP_END_TRANSFER_PENDING),
+					dwc->lock);
+
+			if (!r->trb)
+				goto out1;
+
+			if (r->num_pending_sgs) {
+				struct dwc3_trb *trb;
+				int i = 0;
+
+				for (i = 0; i < r->num_pending_sgs; i++) {
+					trb = r->trb + i;
+					trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+					dwc3_ep_inc_deq(dep);
+				}
+
+				if (r->unaligned) {
+					trb = r->trb + r->num_pending_sgs + 1;
+					trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+					dwc3_ep_inc_deq(dep);
+				}
+			} else {
+				struct dwc3_trb *trb = r->trb;
+
+				trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+				dwc3_ep_inc_deq(dep);
+
+				if (r->unaligned) {
+					trb = r->trb + 1;
+					trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+					dwc3_ep_inc_deq(dep);
+				}
+			}
 			goto out1;
 		}
 		dev_err(dwc->dev, "request %p was not queued to %s\n",
@@ -1352,6 +1414,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 
 out1:
 	/* giveback the request */
+	dep->queued_requests--;
 	dwc3_gadget_giveback(dep, req, -ECONNRESET);
 
 out0:
-- 
GitLab


From 2e46565cf622dd0534a9d8bffe152a577b48d7aa Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 24 Feb 2017 19:11:28 +0100
Subject: [PATCH 724/898] USB: serial: digi_acceleport: fix OOB-event
 processing

A recent change claimed to fix an off-by-one error in the OOB-port
completion handler, but instead introduced such an error. This could
specifically led to modem-status changes going unnoticed, effectively
breaking TIOCMGET.

Note that the offending commit fixes a loop-condition underflow and is
marked for stable, but should not be backported without this fix.

Reported-by: Ben Hutchings <ben@decadent.org.uk>
Fixes: 2d380889215f ("USB: serial: digi_acceleport: fix OOB data sanity
check")
Cc: stable <stable@vger.kernel.org>	# v2.6.30: 2d380889215f
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/digi_acceleport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index ab78111e0968..6537d3ca2797 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -1500,7 +1500,7 @@ static int digi_read_oob_callback(struct urb *urb)
 		return -1;
 
 	/* handle each oob command */
-	for (i = 0; i < urb->actual_length - 4; i += 4) {
+	for (i = 0; i < urb->actual_length - 3; i += 4) {
 		opcode = buf[i];
 		line = buf[i + 1];
 		status = buf[i + 2];
-- 
GitLab


From 8f1117abb408808af9cc4c948925c726bec4755a Mon Sep 17 00:00:00 2001
From: Chuanxiao Dong <chuanxiao.dong@intel.com>
Date: Mon, 6 Mar 2017 13:05:24 +0800
Subject: [PATCH 725/898] drm/i915/gvt: handle workload lifecycle properly

Currently i915 has a request replay mechanism which can make sure
the request can be replayed after a GPU reset. With this mechanism,
gvt should wait until the GVT request seqno passed before complete
the current workload. So that there should be a context switch interrupt
come before gvt free the workload. In this way, workload lifecylce
matches with the i915 request lifecycle. The workload can only be freed
after the request is completed.

v2: use gvt_dbg_sched instead of gvt_err to print when wait again

Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/scheduler.c | 49 +++++++++++++++++++---------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index e355a82ccabd..d3a56c949025 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -151,6 +151,15 @@ static int shadow_context_status_change(struct notifier_block *nb,
 	case INTEL_CONTEXT_SCHEDULE_OUT:
 		intel_gvt_restore_render_mmio(workload->vgpu,
 					      workload->ring_id);
+		/* If the status is -EINPROGRESS means this workload
+		 * doesn't meet any issue during dispatching so when
+		 * get the SCHEDULE_OUT set the status to be zero for
+		 * good. If the status is NOT -EINPROGRESS means there
+		 * is something wrong happened during dispatching and
+		 * the status should not be set to zero
+		 */
+		if (workload->status == -EINPROGRESS)
+			workload->status = 0;
 		atomic_set(&workload->shadow_ctx_active, 0);
 		break;
 	default:
@@ -362,15 +371,23 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	workload = scheduler->current_workload[ring_id];
 	vgpu = workload->vgpu;
 
-	if (!workload->status && !vgpu->resetting) {
+	/* For the workload w/ request, needs to wait for the context
+	 * switch to make sure request is completed.
+	 * For the workload w/o request, directly complete the workload.
+	 */
+	if (workload->req) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
-		update_guest_context(workload);
+		i915_gem_request_put(fetch_and_zero(&workload->req));
 
-		for_each_set_bit(event, workload->pending_events,
-				 INTEL_GVT_EVENT_MAX)
-			intel_vgpu_trigger_virtual_event(vgpu, event);
+		if (!workload->status && !vgpu->resetting) {
+			update_guest_context(workload);
+
+			for_each_set_bit(event, workload->pending_events,
+					 INTEL_GVT_EVENT_MAX)
+				intel_vgpu_trigger_virtual_event(vgpu, event);
+		}
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -400,7 +417,6 @@ static int workload_thread(void *priv)
 	int ring_id = p->ring_id;
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct intel_vgpu_workload *workload = NULL;
-	long lret;
 	int ret;
 	bool need_force_wake = IS_SKYLAKE(gvt->dev_priv);
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -449,23 +465,24 @@ static int workload_thread(void *priv)
 
 		gvt_dbg_sched("ring id %d wait workload %p\n",
 				workload->ring_id, workload);
-
-		lret = i915_wait_request(workload->req,
+retry:
+		i915_wait_request(workload->req,
 					 0, MAX_SCHEDULE_TIMEOUT);
-		if (lret < 0) {
-			workload->status = lret;
-			gvt_err("fail to wait workload, skip\n");
-		} else {
-			workload->status = 0;
+		/* I915 has replay mechanism and a request will be replayed
+		 * if there is i915 reset. So the seqno will be updated anyway.
+		 * If the seqno is not updated yet after waiting, which means
+		 * the replay may still be in progress and we can wait again.
+		 */
+		if (!i915_gem_request_completed(workload->req)) {
+			gvt_dbg_sched("workload %p not completed, wait again\n",
+					workload);
+			goto retry;
 		}
 
 complete:
 		gvt_dbg_sched("will complete workload %p, status: %d\n",
 				workload, workload->status);
 
-		if (workload->req)
-			i915_gem_request_put(fetch_and_zero(&workload->req));
-
 		complete_current_workload(gvt, ring_id);
 
 		if (need_force_wake)
-- 
GitLab


From c2e04fdab33181b53b5a2f9662b7b607b720f79f Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Mon, 6 Mar 2017 17:08:30 +0800
Subject: [PATCH 726/898] drm/i915/gvt: protect RO and Rsvd bits of virtual
 vgpu configuration space

Per PCI specification, Configuration Register has different types (RO,
RW, RW1C, Rsvd). For RO Register bits are read-only and cannot be
altered by software. For RW1C Register bits indicate status when read.
A Set bit indicates a status event which is Cleared by writing a 1b.
Writing a 0b to RW1C bits has no effect. Reserved Register is for future
implementations, and they are read-only and must return zero when read.

Current vGPU configuration write emulation just copy the value as it is.
So we haven't emulated RO, RW1C and Rsvd Registers correctly. This patch
is following the Spec to correct emulation logic. We add a function
vgpu_cfg_mem_write to wrap the access to vGPU configuration memory.
The write function uses a RW Register bitmap to avoid RO bits be
overwritten, and emulate RW1C behavior for the particular status Register.

v2:
  new = src[i] --> new = src[i] & mask (zhenyu)

Signed-off-by: Changbin Du <changbin.du@intel.com>
Cc: Xiaoguang Chen <xiaoguang.chen@intel.com>
Cc: Zhiyuan Lv <zhiyuan.lv@intel.com>
Cc: Min He <min.he@intel.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/cfg_space.c | 54 ++++++++++++++++++++++++++--
 1 file changed, 51 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index a77e050b85a3..b7d7721e72fa 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -41,6 +41,54 @@ enum {
 	INTEL_GVT_PCI_BAR_MAX,
 };
 
+/* bitmap for writable bits (RW or RW1C bits, but cannot co-exist in one
+ * byte) byte by byte in standard pci configuration space. (not the full
+ * 256 bytes.)
+ */
+static const u8 pci_cfg_space_rw_bmp[PCI_INTERRUPT_LINE + 4] = {
+	[PCI_COMMAND]		= 0xff, 0x07,
+	[PCI_STATUS]		= 0x00, 0xf9, /* the only one RW1C byte */
+	[PCI_CACHE_LINE_SIZE]	= 0xff,
+	[PCI_BASE_ADDRESS_0 ... PCI_CARDBUS_CIS - 1] = 0xff,
+	[PCI_ROM_ADDRESS]	= 0x01, 0xf8, 0xff, 0xff,
+	[PCI_INTERRUPT_LINE]	= 0xff,
+};
+
+/**
+ * vgpu_pci_cfg_mem_write - write virtual cfg space memory
+ *
+ * Use this function to write virtual cfg space memory.
+ * For standard cfg space, only RW bits can be changed,
+ * and we emulates the RW1C behavior of PCI_STATUS register.
+ */
+static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off,
+				   u8 *src, unsigned int bytes)
+{
+	u8 *cfg_base = vgpu_cfg_space(vgpu);
+	u8 mask, new, old;
+	int i = 0;
+
+	for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) {
+		mask = pci_cfg_space_rw_bmp[off + i];
+		old = cfg_base[off + i];
+		new = src[i] & mask;
+
+		/**
+		 * The PCI_STATUS high byte has RW1C bits, here
+		 * emulates clear by writing 1 for these bits.
+		 * Writing a 0b to RW1C bits has no effect.
+		 */
+		if (off + i == PCI_STATUS + 1)
+			new = (~new & old) & mask;
+
+		cfg_base[off + i] = (old & ~mask) | new;
+	}
+
+	/* For other configuration space directly copy as it is. */
+	if (i < bytes)
+		memcpy(cfg_base + off + i, src + i, bytes - i);
+}
+
 /**
  * intel_vgpu_emulate_cfg_read - emulate vGPU configuration space read
  *
@@ -123,7 +171,7 @@ static int emulate_pci_command_write(struct intel_vgpu *vgpu,
 	u8 changed = old ^ new;
 	int ret;
 
-	memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+	vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
 	if (!(changed & PCI_COMMAND_MEMORY))
 		return 0;
 
@@ -277,10 +325,10 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset,
 		if (ret)
 			return ret;
 
-		memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+		vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
 		break;
 	default:
-		memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+		vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
 		break;
 	}
 	return 0;
-- 
GitLab


From 68925176296a8b995e503349200e256674bfe5ac Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Fri, 17 Feb 2017 14:32:18 +0000
Subject: [PATCH 727/898] arm64: KVM: VHE: Clear HCR_TGE when invalidating
 guest TLBs

When invalidating guest TLBs, special care must be taken to
actually shoot the guest TLBs and not the host ones if we're
running on a VHE system.  This is controlled by the HCR_EL2.TGE
bit, which we forget to clear before invalidating TLBs.

Address the issue by introducing two wrappers (__tlb_switch_to_guest
and __tlb_switch_to_host) that take care of both the VTTBR_EL2
and HCR_EL2.TGE switching.

Reported-by: Tomasz Nowicki <tnowicki@caviumnetworks.com>
Tested-by: Tomasz Nowicki <tnowicki@caviumnetworks.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Cc: stable@vger.kernel.org
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/kvm/hyp/tlb.c | 64 ++++++++++++++++++++++++++++++++++------
 1 file changed, 55 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index e8e7ba2bc11f..9e1d2b75eecd 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -18,14 +18,62 @@
 #include <asm/kvm_hyp.h>
 #include <asm/tlbflush.h>
 
+static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
+{
+	u64 val;
+
+	/*
+	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+	 * most TLB operations target EL2/EL0. In order to affect the
+	 * guest TLBs (EL1/EL0), we need to change one of these two
+	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+	 * let's flip TGE before executing the TLB operation.
+	 */
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	val = read_sysreg(hcr_el2);
+	val &= ~HCR_TGE;
+	write_sysreg(val, hcr_el2);
+	isb();
+}
+
+static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
+{
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	isb();
+}
+
+static hyp_alternate_select(__tlb_switch_to_guest,
+			    __tlb_switch_to_guest_nvhe,
+			    __tlb_switch_to_guest_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm)
+{
+	/*
+	 * We're done with the TLB operation, let's restore the host's
+	 * view of HCR_EL2.
+	 */
+	write_sysreg(0, vttbr_el2);
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+}
+
+static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+static hyp_alternate_select(__tlb_switch_to_host,
+			    __tlb_switch_to_host_nvhe,
+			    __tlb_switch_to_host_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	dsb(ishst);
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -46,7 +94,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -55,14 +103,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -70,14 +117,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 
 	/* Switch to requested VMID */
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_flush_vm_context(void)
-- 
GitLab


From 4dfc050571523ac2bc02cbf948dd47621f7dd83f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 21 Feb 2017 11:32:47 +0000
Subject: [PATCH 728/898] KVM: arm/arm64: vgic-v3: Don't pretend to support
 IRQ/FIQ bypass

Our GICv3 emulation always presents ICC_SRE_EL1 with DIB/DFB set to
zero, which implies that there is a way to bypass the GIC and
inject raw IRQ/FIQ by driving the CPU pins.

Of course, we don't allow that when the GIC is configured, but
we fail to indicate that to the guest. The obvious fix is to
set these bits (and never let them being changed again).

Reported-by: Peter Maydell <peter.maydell@linaro.org>
Acked-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/linux/irqchip/arm-gic-v3.h | 2 ++
 virt/kvm/arm/vgic/vgic-v3.c        | 5 ++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 672cfef72fc8..97cbca19430d 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -373,6 +373,8 @@
 #define ICC_IGRPEN0_EL1_MASK		(1 << ICC_IGRPEN0_EL1_SHIFT)
 #define ICC_IGRPEN1_EL1_SHIFT		0
 #define ICC_IGRPEN1_EL1_MASK		(1 << ICC_IGRPEN1_EL1_SHIFT)
+#define ICC_SRE_EL1_DIB			(1U << 2)
+#define ICC_SRE_EL1_DFB			(1U << 1)
 #define ICC_SRE_EL1_SRE			(1U << 0)
 
 /*
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index edc6ee2dc852..be0f4c3e0142 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -229,10 +229,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 	/*
 	 * If we are emulating a GICv3, we do it in an non-GICv2-compatible
 	 * way, so we force SRE to 1 to demonstrate this to the guest.
+	 * Also, we don't support any form of IRQ/FIQ bypass.
 	 * This goes with the spec allowing the value to be RAO/WI.
 	 */
 	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
-		vgic_v3->vgic_sre = ICC_SRE_EL1_SRE;
+		vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB |
+				     ICC_SRE_EL1_DFB |
+				     ICC_SRE_EL1_SRE);
 		vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE;
 	} else {
 		vgic_v3->vgic_sre = 0;
-- 
GitLab


From a69e2fb70350a66f91175cd2625f1e8215c5b6e9 Mon Sep 17 00:00:00 2001
From: Balbir Singh <bsingharora@gmail.com>
Date: Fri, 3 Mar 2017 11:58:44 +1100
Subject: [PATCH 729/898] powerpc/xics: Work around limitations of OPAL XICS
 priority handling

The CPPR (Current Processor Priority Register) of a XICS interrupt
presentation controller contains a value N, such that only interrupts
with a priority "more favoured" than N will be received by the CPU,
where "more favoured" means "less than". So if the CPPR has the value 5
then only interrupts with a priority of 0-4 inclusive will be received.

In theory the CPPR can support a value of 0 to 255 inclusive.
In practice Linux only uses values of 0, 4, 5 and 0xff. Setting the CPPR
to 0 rejects all interrupts, setting it to 0xff allows all interrupts.
The values 4 and 5 are used to differentiate IPIs from external
interrupts. Setting the CPPR to 5 allows IPIs to be received but not
external interrupts.

The CPPR emulation in the OPAL XICS implementation only directly
supports priorities 0 and 0xff. All other priorities are considered
equivalent, and mapped to a single priority value internally. This means
when using icp-opal we can not allow IPIs but not externals.

This breaks Linux's use of priority values when a CPU is hot unplugged.
After migrating IRQs away from the CPU that is being offlined, we set
the priority to 5, meaning we still want the offline CPU to receive
IPIs. But the effect of the OPAL XICS emulation's use of a single
priority value is that all interrupts are rejected by the CPU. With the
CPU offline, and not receiving IPIs, we may not be able to wake it up to
bring it back online.

The first part of the fix is in icp_opal_set_cpu_priority(). CPPR values
of 0 to 4 inclusive will correctly cause all interrupts to be rejected,
so we pass those CPPR values through to OPAL. However if we are called
with a CPPR of 5 or greater, the caller is expecting to be able to allow
IPIs but not external interrupts. We know this doesn't work, so instead
of rejecting all interrupts we choose the opposite which is to allow all
interrupts. This is still not correct behaviour, but we know for the
only existing caller (xics_migrate_irqs_away()), that it is the better
option.

The other part of the fix is in xics_migrate_irqs_away(). Instead of
setting priority (CPPR) to 0, and then back to 5 before migrating IRQs,
we migrate the IRQs before setting the priority back to 5. This should
have no effect on an ICP backend with a working set_priority(), and on
icp-opal it means we will keep all interrupts blocked until after we've
finished doing the IRQ migration. Additionally we wait for 5ms after
doing the migration to make sure there are no IRQs in flight.

Fixes: d74361881f0d ("powerpc/xics: Add ICP OPAL backend")
Cc: stable@vger.kernel.org # v4.8+
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Reported-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Tested-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[mpe: Rewrote comments and change log, change delay to 5ms]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/sysdev/xics/icp-opal.c    | 10 ++++++++++
 arch/powerpc/sysdev/xics/xics-common.c | 17 ++++++++++++++---
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index f9670eabfcfa..b53f80f0b4d8 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -91,6 +91,16 @@ static unsigned int icp_opal_get_irq(void)
 
 static void icp_opal_set_cpu_priority(unsigned char cppr)
 {
+	/*
+	 * Here be dragons. The caller has asked to allow only IPI's and not
+	 * external interrupts. But OPAL XIVE doesn't support that. So instead
+	 * of allowing no interrupts allow all. That's still not right, but
+	 * currently the only caller who does this is xics_migrate_irqs_away()
+	 * and it works in that case.
+	 */
+	if (cppr >= DEFAULT_PRIORITY)
+		cppr = LOWEST_PRIORITY;
+
 	xics_set_base_cppr(cppr);
 	opal_int_set_cppr(cppr);
 	iosync();
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 69d858e51ac7..23efe4e42172 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/delay.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -198,9 +199,6 @@ void xics_migrate_irqs_away(void)
 	/* Remove ourselves from the global interrupt queue */
 	xics_set_cpu_giq(xics_default_distrib_server, 0);
 
-	/* Allow IPIs again... */
-	icp_ops->set_priority(DEFAULT_PRIORITY);
-
 	for_each_irq_desc(virq, desc) {
 		struct irq_chip *chip;
 		long server;
@@ -255,6 +253,19 @@ void xics_migrate_irqs_away(void)
 unlock:
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
+
+	/* Allow "sufficient" time to drop any inflight IRQ's */
+	mdelay(5);
+
+	/*
+	 * Allow IPIs again. This is done at the very end, after migrating all
+	 * interrupts, the expectation is that we'll only get woken up by an IPI
+	 * interrupt beyond this point, but leave externals masked just to be
+	 * safe. If we're using icp-opal this may actually allow all
+	 * interrupts anyway, but that should be OK.
+	 */
+	icp_ops->set_priority(DEFAULT_PRIORITY);
+
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-- 
GitLab


From 12cc9fd6b2d8ee307a735b3b9faed0d17b719463 Mon Sep 17 00:00:00 2001
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Date: Tue, 28 Feb 2017 17:03:47 +1100
Subject: [PATCH 730/898] powerpc: Parse the command line before calling CAS

On POWER9 the hypervisor requires the guest to decide whether it would
like to use a hash or radix mmu model at the time it calls
ibm,client-architecture-support (CAS) based on what the hypervisor has
said it's allowed to do. It is possible to disable radix by passing
"disable_radix" on the command line. The next patch will add support for
the new CAS format, thus we need to parse the command line before calling
CAS so we can correctly select which mmu we would like to use.

Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Reviewed-by: Paul Mackerras <paulus@ozlabs.org>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/prom_init.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a3944540fe0d..bf3966d12565 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2993,6 +2993,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	prom_check_initrd(r3, r4);
 
+	/*
+	 * Do early parsing of command line
+	 */
+	early_cmdline_parse();
+
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 	/*
 	 * On pSeries, inform the firmware about our capabilities
@@ -3008,11 +3013,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	if (of_platform != PLATFORM_POWERMAC)
 		copy_and_flush(0, kbase, 0x100, 0);
 
-	/*
-	 * Do early parsing of command line
-	 */
-	early_cmdline_parse();
-
 	/*
 	 * Initialize memory management within prom_init
 	 */
-- 
GitLab


From 014d02cbf16b3106dc8e93281d2a9c189751ed5e Mon Sep 17 00:00:00 2001
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Date: Tue, 28 Feb 2017 17:03:48 +1100
Subject: [PATCH 731/898] powerpc: Update to new option-vector-5 format for CAS

On POWER9 the ibm,client-architecture-support (CAS) negotiation process
has been updated to change how the host to guest negotiation is done for
the new hash/radix mmu as well as the nest mmu, process tables and guest
translation shootdown (GTSE).

This is documented in the unreleased PAPR ACR "CAS option vector
additions for P9".

The host tells the guest which options it supports in
ibm,arch-vec-5-platform-support. The guest then chooses a subset of these
to request in the CAS call and these are agreed to in the
ibm,architecture-vec-5 property of the chosen node.

Thus we read ibm,arch-vec-5-platform-support and make our selection before
calling CAS. We then parse the ibm,architecture-vec-5 property of the
chosen node to check whether we should run as hash or radix.

ibm,arch-vec-5-platform-support format:

index value pairs: <index, val> ... <index, val>

index: Option vector 5 byte number
val:   Some representation of supported values

Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Acked-by: Paul Mackerras <paulus@ozlabs.org>
[mpe: Don't print about unknown options, be consistent with OV5_FEAT]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/prom.h |  18 ++++--
 arch/powerpc/kernel/prom_init.c | 110 +++++++++++++++++++++++++++++++-
 arch/powerpc/mm/init_64.c       |  36 +++++++++--
 3 files changed, 150 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 4a90634e8322..35c00d7a0cf8 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -160,12 +160,18 @@ struct of_drconf_cell {
 #define OV5_PFO_HW_ENCR		0x1120	/* PFO Encryption Accelerator */
 #define OV5_SUB_PROCESSORS	0x1501	/* 1,2,or 4 Sub-Processors supported */
 #define OV5_XIVE_EXPLOIT	0x1701	/* XIVE exploitation supported */
-#define OV5_MMU_RADIX_300	0x1880	/* ISA v3.00 radix MMU supported */
-#define OV5_MMU_HASH_300	0x1840	/* ISA v3.00 hash MMU supported */
-#define OV5_MMU_SEGM_RADIX	0x1820	/* radix mode (no segmentation) */
-#define OV5_MMU_PROC_TBL	0x1810	/* hcall selects SLB or proc table */
-#define OV5_MMU_SLB		0x1800	/* always use SLB */
-#define OV5_MMU_GTSE		0x1808	/* Guest translation shootdown */
+/* MMU Base Architecture */
+#define OV5_MMU_SUPPORT		0x18C0	/* MMU Mode Support Mask */
+#define OV5_MMU_HASH		0x1800	/* Hash MMU Only */
+#define OV5_MMU_RADIX		0x1840	/* Radix MMU Only */
+#define OV5_MMU_EITHER		0x1880	/* Hash or Radix Supported */
+#define OV5_MMU_DYNAMIC		0x18C0	/* Hash or Radix Can Switch Later */
+#define OV5_NMMU		0x1820	/* Nest MMU Available */
+/* Hash Table Extensions */
+#define OV5_HASH_SEG_TBL	0x1980	/* In Memory Segment Tables Available */
+#define OV5_HASH_GTSE		0x1940	/* Guest Translation Shoot Down Avail */
+/* Radix Table Extensions */
+#define OV5_RADIX_GTSE		0x1A40	/* Guest Translation Shoot Down Avail */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX		0x02	/* Linux is our OS */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index bf3966d12565..1c1b44ec7642 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start;
 static unsigned long __initdata prom_tce_alloc_end;
 #endif
 
+static bool __initdata prom_radix_disable;
+
+struct platform_support {
+	bool hash_mmu;
+	bool radix_mmu;
+	bool radix_gtse;
+};
+
 /* Platforms codes are now obsolete in the kernel. Now only used within this
  * file and ultimately gone too. Feel free to change them if you need, they
  * are not shared with anything outside of this file anymore
@@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void)
 		prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
 #endif
 	}
+
+	opt = strstr(prom_cmd_line, "disable_radix");
+	if (opt) {
+		prom_debug("Radix disabled from cmdline\n");
+		prom_radix_disable = true;
+	}
 }
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
@@ -695,6 +709,8 @@ struct option_vector5 {
 	u8 byte22;
 	u8 intarch;
 	u8 mmu;
+	u8 hash_ext;
+	u8 radix_ext;
 } __packed;
 
 struct option_vector6 {
@@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
 		.reserved3 = 0,
 		.subprocessors = 1,
 		.intarch = 0,
-		.mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) |
-			OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE),
+		.mmu = 0,
+		.hash_ext = 0,
+		.radix_ext = 0,
 	},
 
 	/* option vector 6: IBM PAPR hints */
@@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void)
 
 }
 
+static void __init prom_parse_mmu_model(u8 val,
+					struct platform_support *support)
+{
+	switch (val) {
+	case OV5_FEAT(OV5_MMU_DYNAMIC):
+	case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+		prom_debug("MMU - either supported\n");
+		support->radix_mmu = !prom_radix_disable;
+		support->hash_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+		prom_debug("MMU - radix only\n");
+		if (prom_radix_disable) {
+			/*
+			 * If we __have__ to do radix, we're better off ignoring
+			 * the command line rather than not booting.
+			 */
+			prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		support->radix_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_HASH):
+		prom_debug("MMU - hash only\n");
+		support->hash_mmu = true;
+		break;
+	default:
+		prom_debug("Unknown mmu support option: 0x%x\n", val);
+		break;
+	}
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+					       struct platform_support *support)
+{
+	switch (index) {
+	case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+		prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+		break;
+	case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+		if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
+			prom_debug("Radix - GTSE supported\n");
+			support->radix_gtse = true;
+		}
+		break;
+	}
+}
+
+static void __init prom_check_platform_support(void)
+{
+	struct platform_support supported = {
+		.hash_mmu = false,
+		.radix_mmu = false,
+		.radix_gtse = false
+	};
+	int prop_len = prom_getproplen(prom.chosen,
+				       "ibm,arch-vec-5-platform-support");
+	if (prop_len > 1) {
+		int i;
+		u8 vec[prop_len];
+		prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+			   prop_len);
+		prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
+			     &vec, sizeof(vec));
+		for (i = 0; i < prop_len; i += 2) {
+			prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
+								  , vec[i]
+								  , vec[i + 1]);
+			prom_parse_platform_support(vec[i], vec[i + 1],
+						    &supported);
+		}
+	}
+
+	if (supported.radix_mmu && supported.radix_gtse) {
+		/* Radix preferred - but we require GTSE for now */
+		prom_debug("Asking for radix with GTSE\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+		ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+	} else if (supported.hash_mmu) {
+		/* Default to hash mmu (if we can) */
+		prom_debug("Asking for hash\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+	} else {
+		/* We're probably on a legacy hypervisor */
+		prom_debug("Assuming legacy hash support\n");
+	}
+}
 
 static void __init prom_send_capabilities(void)
 {
@@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void)
 	prom_arg_t ret;
 	u32 cores;
 
+	/* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+	prom_check_platform_support();
+
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
 		/* We need to tell the FW about the number of cores we support.
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6aa3b76aa0d6..9be992083d2a 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -356,18 +356,42 @@ static void early_check_vec5(void)
 	unsigned long root, chosen;
 	int size;
 	const u8 *vec5;
+	u8 mmu_supported;
 
 	root = of_get_flat_dt_root();
 	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
-	if (chosen == -FDT_ERR_NOTFOUND)
+	if (chosen == -FDT_ERR_NOTFOUND) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 		return;
+	}
 	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
-	if (!vec5)
+	if (!vec5) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 		return;
-	if (size <= OV5_INDX(OV5_MMU_RADIX_300) ||
-	    !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300)))
-		/* Hypervisor doesn't support radix */
+	}
+	if (size <= OV5_INDX(OV5_MMU_SUPPORT)) {
 		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+		return;
+	}
+
+	/* Check for supported configuration */
+	mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] &
+			OV5_FEAT(OV5_MMU_SUPPORT);
+	if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) {
+		/* Hypervisor only supports radix - check enabled && GTSE */
+		if (!early_radix_enabled()) {
+			pr_warn("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
+						OV5_FEAT(OV5_RADIX_GTSE))) {
+			pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
+		}
+		/* Do radix anyway - the hypervisor said we had to */
+		cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+	} else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
+		/* Hypervisor only supports hash - disable radix */
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+	}
 }
 
 void __init mmu_early_init_devtree(void)
@@ -383,7 +407,7 @@ void __init mmu_early_init_devtree(void)
 	 * even though the ibm,architecture-vec-5 property created by
 	 * skiboot doesn't have the necessary bits set.
 	 */
-	if (early_radix_enabled() && !(mfmsr() & MSR_HV))
+	if (!(mfmsr() & MSR_HV))
 		early_check_vec5();
 
 	if (early_radix_enabled())
-- 
GitLab


From 6ba422c75facb1b1e0e206c464ee121b8073f7e0 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 5 Mar 2017 10:54:34 +1100
Subject: [PATCH 732/898] powerpc/64: Avoid panic during boot due to divide by
 zero in init_cache_info()

I see a panic in early boot when building with a recent gcc toolchain.
The issue is a divide by zero, which is undefined. Older toolchains
let us get away with it:

int foo(int a) { return a / 0; }

foo:
	li 9,0
	divw 3,3,9
	extsw 3,3
	blr

But newer ones catch it:

foo:
	trap

Add a check to avoid the divide by zero.

Fixes: e2827fe5c156 ("powerpc/64: Clean up ppc64_caches using a struct per cache")
Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup_64.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index adf2084f214b..9cfaa8b69b5f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -408,7 +408,10 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
 	info->line_size = lsize;
 	info->block_size = bsize;
 	info->log_block_size = __ilog2(bsize);
-	info->blocks_per_page = PAGE_SIZE / bsize;
+	if (bsize)
+		info->blocks_per_page = PAGE_SIZE / bsize;
+	else
+		info->blocks_per_page = 0;
 
 	if (sets == 0)
 		info->assoc = 0xffff;
-- 
GitLab


From 3b3e78552d3077ec70d2640e629e07e3ab416a6a Mon Sep 17 00:00:00 2001
From: Matjaz Hegedic <matjaz.hegedic@gmail.com>
Date: Sun, 5 Mar 2017 19:16:44 +0100
Subject: [PATCH 733/898] x86/reboot/quirks: Add ASUS EeeBook X205TA/W reboot
 quirk

Without the parameter reboot=a, ASUS EeeBook X205TA/W will hang
when it should reboot. This adds the appropriate quirk, thus
fixing the problem.

Signed-off-by: Matjaz Hegedic <matjaz.hegedic@gmail.com>
Link: http://lkml.kernel.org/r/1488737804-20681-1-git-send-email-matjaz.hegedic@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/reboot.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 01c9cda3e1b7..4194d6f9bb29 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -231,6 +231,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
 		},
 	},
+	{	/* Handle problems with rebooting on ASUS EeeBook X205TAW */
+		.callback = set_acpi_reboot,
+		.ident = "ASUS EeeBook X205TAW",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+		},
+	},
 
 	/* Certec */
 	{       /* Handle problems with rebooting on Certec BPC600 */
-- 
GitLab


From f2853308b6409b97799b0beceacd9da43a82fe43 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 6 Mar 2017 10:57:48 +0200
Subject: [PATCH 734/898] x86/build/x86_64_defconfig: Enable CONFIG_R8169

Very common PCIe ethernet card. Already enabled in i386_defconfig.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Link: http://lkml.kernel.org/r/20170306085748.85957-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/configs/x86_64_defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 7ef4a099defc..6205d3b81e6d 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -176,6 +176,7 @@ CONFIG_E1000E=y
 CONFIG_SKY2=y
 CONFIG_FORCEDETH=y
 CONFIG_8139TOO=y
+CONFIG_R8169=y
 CONFIG_FDDI=y
 CONFIG_INPUT_POLLDEV=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-- 
GitLab


From 9c7a00868c3a77c86ab07a2c51f3bb4897bd8550 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 6 Mar 2017 21:51:32 +1100
Subject: [PATCH 735/898] powerpc/64: Fix L1D cache shape vector reporting L1I
 values

It seems we didn't pay quite enough attention when testing the new cache
shape vectors, which means we didn't notice the bug where the vector for
the L1D was using the L1I values. Fix it, resulting in eg:

  L1I  cache size:     0x8000      32768B         32K
  L1I  line size:        0x80       8-way associative
  L1D  cache size:    0x10000      65536B         64K
  L1D  line size:        0x80       8-way associative

Fixes: 98a5f361b862 ("powerpc: Add new cache geometry aux vectors")
Cut-and-paste-bug-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Badly-reviewed-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/elf.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 93b9b84568e8..09bde6e34f5d 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -144,8 +144,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define ARCH_DLINFO_CACHE_GEOMETRY					\
 	NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size);		\
 	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i));	\
-	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size);		\
-	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i));	\
+	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size);		\
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d));	\
 	NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size);		\
 	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2));	\
 	NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size);		\
-- 
GitLab


From a7d2475af7aedcb9b5c6343989a8bfadbf84429b Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 6 Mar 2017 22:53:59 +1100
Subject: [PATCH 736/898] powerpc: Sort the selects under CONFIG_PPC

We have a big list of selects under CONFIG_PPC, and currently they're
completely unsorted. This means people tend to add new selects at the
bottom of the list, and so two commits which both add a new select will
often conflict.

Instead sort it alphabetically. This is nicer in and of itself, but also
means two commits that add a new select will have a greater chance of
not conflicting.

Add a note at the top and bottom asking people to keep it sorted.

And while we're here pad out the 'if' expressions to make them stand
out.

Suggested-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/Kconfig | 138 ++++++++++++++++++++++---------------------
 1 file changed, 72 insertions(+), 66 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 494091762bd7..97a8bc8a095c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -80,93 +80,99 @@ config ARCH_HAS_DMA_SET_COHERENT_MASK
 config PPC
 	bool
 	default y
-	select BUILDTIME_EXTABLE_SORT
+	#
+	# Please keep this list sorted alphabetically.
+	#
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
+	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select BINFMT_ELF
-	select ARCH_HAS_ELF_RANDOMIZE
-	select OF
-	select OF_EARLY_FLATTREE
-	select OF_RESERVED_MEM
-	select HAVE_FTRACE_MCOUNT_RECORD
+	select BUILDTIME_EXTABLE_SORT
+	select CLONE_BACKWARDS
+	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
+	select EDAC_ATOMIC_SCRUB
+	select EDAC_SUPPORT
+	select GENERIC_ATOMIC64			if PPC32
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
+	select GENERIC_CMOS_UPDATE
+	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_SHOW_LEVEL
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select GENERIC_TIME_VSYSCALL_OLD
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HARDENED_USERCOPY
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_CBPF_JIT			if !PPC64
+	select HAVE_CONTEXT_TRACKING		if PPC64
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_DMA_API_DEBUG
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
-	select HAVE_FUNCTION_TRACER
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if MPROFILE_KERNEL
+	select HAVE_EBPF_JIT			if PPC64
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS	if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
-	select SYSCTL_EXCEPTION_TRACE
-	select VIRT_TO_BUS if !PPC64
+	select HAVE_GENERIC_RCU_GUP
+	select HAVE_HW_BREAKPOINT		if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
 	select HAVE_IDE
 	select HAVE_IOREMAP_PROT
-	select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK
+	select HAVE_KERNEL_GZIP
 	select HAVE_KPROBES
-	select HAVE_OPTPROBES if PPC64
-	select HAVE_ARCH_KGDB
 	select HAVE_KRETPROBES
-	select HAVE_ARCH_TRACEHOOK
+	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
-	select HAVE_DMA_API_DEBUG
+	select HAVE_MOD_ARCH_SPECIFIC
+	select HAVE_NMI				if PERF_EVENTS
 	select HAVE_OPROFILE
-	select HAVE_DEBUG_KMEMLEAK
-	select ARCH_HAS_SG_CHAIN
-	select GENERIC_ATOMIC64 if PPC32
+	select HAVE_OPTPROBES			if PPC64
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_RCU_TABLE_FREE		if SMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
-	select ARCH_WANT_IPC_PARSE_VERSION
-	select SPARSE_IRQ
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_VIRT_CPU_ACCOUNTING
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_SHOW
-	select GENERIC_IRQ_SHOW_LEVEL
 	select IRQ_FORCED_THREADING
-	select HAVE_RCU_TABLE_FREE if SMP
-	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_CBPF_JIT if !PPC64
-	select HAVE_EBPF_JIT if PPC64
-	select HAVE_ARCH_JUMP_LABEL
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select ARCH_HAS_GCOV_PROFILE_ALL
-	select GENERIC_SMP_IDLE_THREAD
-	select GENERIC_CMOS_UPDATE
-	select GENERIC_TIME_VSYSCALL_OLD
-	select GENERIC_CLOCKEVENTS
-	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
-	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
-	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select CLONE_BACKWARDS
-	select ARCH_USE_BUILTIN_BSWAP
-	select OLD_SIGSUSPEND
-	select OLD_SIGACTION if PPC32
-	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_IRQ_EXIT_ON_IRQ_STACK
-	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
-	select HAVE_ARCH_AUDITSYSCALL
-	select ARCH_SUPPORTS_ATOMIC_RMW
-	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
 	select NO_BOOTMEM
-	select HAVE_GENERIC_RCU_GUP
-	select HAVE_PERF_EVENTS_NMI if PPC64
-	select HAVE_NMI if PERF_EVENTS
-	select EDAC_SUPPORT
-	select EDAC_ATOMIC_SCRUB
-	select ARCH_HAS_DMA_SET_COHERENT_MASK
-	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select HAVE_ARCH_SECCOMP_FILTER
-	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
-	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select GENERIC_CPU_AUTOPROBE
-	select HAVE_VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
-	select HAVE_ARCH_HARDENED_USERCOPY
-	select HAVE_KERNEL_GZIP
-	select HAVE_CONTEXT_TRACKING if PPC64
+	select OF
+	select OF_EARLY_FLATTREE
+	select OF_RESERVED_MEM
+	select OLD_SIGACTION			if PPC32
+	select OLD_SIGSUSPEND
+	select SPARSE_IRQ
+	select SYSCTL_EXCEPTION_TRACE
+	select VIRT_TO_BUS			if !PPC64
+	#
+	# Please keep this list sorted alphabetically.
+	#
 
 config GENERIC_CSUM
 	def_bool n
-- 
GitLab


From 606142af57dad981b78707234cfbd15f9f7b7125 Mon Sep 17 00:00:00 2001
From: Jonathan McDowell <noodles@earth.li>
Date: Wed, 15 Feb 2017 18:29:15 -0200
Subject: [PATCH 737/898] [media] dw2102: don't do DMA on stack

On Kernel 4.9, WARNINGs about doing DMA on stack are hit at
the dw2102 driver: one in su3000_power_ctrl() and the other in tt_s2_4600_frontend_attach().

Both were due to the use of buffers on the stack as parameters to
dvb_usb_generic_rw() and the resulting attempt to do DMA with them.

The device was non-functional as a result.

So, switch this driver over to use a buffer within the device state
structure, as has been done with other DVB-USB drivers.

Tested with TechnoTrend TT-connect S2-4600.

[mchehab@osg.samsung.com: fixed a warning at su3000_i2c_transfer() that
 state var were dereferenced before check 'd']
Signed-off-by: Jonathan McDowell <noodles@earth.li>
Cc: <stable@vger.kernel.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
---
 drivers/media/usb/dvb-usb/dw2102.c | 244 +++++++++++++++++------------
 1 file changed, 145 insertions(+), 99 deletions(-)

diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 6ca502d834b4..4f42d57f81d9 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -68,6 +68,7 @@
 struct dw2102_state {
 	u8 initialized;
 	u8 last_lock;
+	u8 data[MAX_XFER_SIZE + 4];
 	struct i2c_client *i2c_client_demod;
 	struct i2c_client *i2c_client_tuner;
 
@@ -661,62 +662,72 @@ static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 								int num)
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
-	u8 obuf[0x40], ibuf[0x40];
+	struct dw2102_state *state;
 
 	if (!d)
 		return -ENODEV;
+
+	state = d->priv;
+
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
+	if (mutex_lock_interruptible(&d->data_mutex) < 0) {
+		mutex_unlock(&d->i2c_mutex);
+		return -EAGAIN;
+	}
 
 	switch (num) {
 	case 1:
 		switch (msg[0].addr) {
 		case SU3000_STREAM_CTRL:
-			obuf[0] = msg[0].buf[0] + 0x36;
-			obuf[1] = 3;
-			obuf[2] = 0;
-			if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 0, 0) < 0)
+			state->data[0] = msg[0].buf[0] + 0x36;
+			state->data[1] = 3;
+			state->data[2] = 0;
+			if (dvb_usb_generic_rw(d, state->data, 3,
+					state->data, 0, 0) < 0)
 				err("i2c transfer failed.");
 			break;
 		case DW2102_RC_QUERY:
-			obuf[0] = 0x10;
-			if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 2, 0) < 0)
+			state->data[0] = 0x10;
+			if (dvb_usb_generic_rw(d, state->data, 1,
+					state->data, 2, 0) < 0)
 				err("i2c transfer failed.");
-			msg[0].buf[1] = ibuf[0];
-			msg[0].buf[0] = ibuf[1];
+			msg[0].buf[1] = state->data[0];
+			msg[0].buf[0] = state->data[1];
 			break;
 		default:
 			/* always i2c write*/
-			obuf[0] = 0x08;
-			obuf[1] = msg[0].addr;
-			obuf[2] = msg[0].len;
+			state->data[0] = 0x08;
+			state->data[1] = msg[0].addr;
+			state->data[2] = msg[0].len;
 
-			memcpy(&obuf[3], msg[0].buf, msg[0].len);
+			memcpy(&state->data[3], msg[0].buf, msg[0].len);
 
-			if (dvb_usb_generic_rw(d, obuf, msg[0].len + 3,
-						ibuf, 1, 0) < 0)
+			if (dvb_usb_generic_rw(d, state->data, msg[0].len + 3,
+						state->data, 1, 0) < 0)
 				err("i2c transfer failed.");
 
 		}
 		break;
 	case 2:
 		/* always i2c read */
-		obuf[0] = 0x09;
-		obuf[1] = msg[0].len;
-		obuf[2] = msg[1].len;
-		obuf[3] = msg[0].addr;
-		memcpy(&obuf[4], msg[0].buf, msg[0].len);
-
-		if (dvb_usb_generic_rw(d, obuf, msg[0].len + 4,
-					ibuf, msg[1].len + 1, 0) < 0)
+		state->data[0] = 0x09;
+		state->data[1] = msg[0].len;
+		state->data[2] = msg[1].len;
+		state->data[3] = msg[0].addr;
+		memcpy(&state->data[4], msg[0].buf, msg[0].len);
+
+		if (dvb_usb_generic_rw(d, state->data, msg[0].len + 4,
+					state->data, msg[1].len + 1, 0) < 0)
 			err("i2c transfer failed.");
 
-		memcpy(msg[1].buf, &ibuf[1], msg[1].len);
+		memcpy(msg[1].buf, &state->data[1], msg[1].len);
 		break;
 	default:
 		warn("more than 2 i2c messages at a time is not handled yet.");
 		break;
 	}
+	mutex_unlock(&d->data_mutex);
 	mutex_unlock(&d->i2c_mutex);
 	return num;
 }
@@ -844,17 +855,23 @@ static int su3000_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 static int su3000_power_ctrl(struct dvb_usb_device *d, int i)
 {
 	struct dw2102_state *state = (struct dw2102_state *)d->priv;
-	u8 obuf[] = {0xde, 0};
+	int ret = 0;
 
 	info("%s: %d, initialized %d", __func__, i, state->initialized);
 
 	if (i && !state->initialized) {
+		mutex_lock(&d->data_mutex);
+
+		state->data[0] = 0xde;
+		state->data[1] = 0;
+
 		state->initialized = 1;
 		/* reset board */
-		return dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0);
+		ret = dvb_usb_generic_rw(d, state->data, 2, NULL, 0, 0);
+		mutex_unlock(&d->data_mutex);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6])
@@ -1309,49 +1326,57 @@ static int prof_7500_frontend_attach(struct dvb_usb_adapter *d)
 	return 0;
 }
 
-static int su3000_frontend_attach(struct dvb_usb_adapter *d)
+static int su3000_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	u8 obuf[3] = { 0xe, 0x80, 0 };
-	u8 ibuf[] = { 0 };
+	struct dvb_usb_device *d = adap->dev;
+	struct dw2102_state *state = d->priv;
+
+	mutex_lock(&d->data_mutex);
+
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x02;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x02;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 	msleep(300);
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 0;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0x51;
+	state->data[0] = 0x51;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
-	d->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config,
-					&d->dev->i2c_adap);
-	if (d->fe_adap[0].fe == NULL)
+	mutex_unlock(&d->data_mutex);
+
+	adap->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config,
+					&d->i2c_adap);
+	if (adap->fe_adap[0].fe == NULL)
 		return -EIO;
 
-	if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
+	if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe,
 				&dw2104_ts2020_config,
-				&d->dev->i2c_adap)) {
+				&d->i2c_adap)) {
 		info("Attached DS3000/TS2020!");
 		return 0;
 	}
@@ -1360,47 +1385,55 @@ static int su3000_frontend_attach(struct dvb_usb_adapter *d)
 	return -EIO;
 }
 
-static int t220_frontend_attach(struct dvb_usb_adapter *d)
+static int t220_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	u8 obuf[3] = { 0xe, 0x87, 0 };
-	u8 ibuf[] = { 0 };
+	struct dvb_usb_device *d = adap->dev;
+	struct dw2102_state *state = d->priv;
+
+	mutex_lock(&d->data_mutex);
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	state->data[0] = 0xe;
+	state->data[1] = 0x87;
+	state->data[2] = 0x0;
+
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x86;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x86;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x80;
-	obuf[2] = 0;
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
 	msleep(50);
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x80;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0x51;
+	state->data[0] = 0x51;
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
-	d->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config,
-					&d->dev->i2c_adap, NULL);
-	if (d->fe_adap[0].fe != NULL) {
-		if (dvb_attach(tda18271_attach, d->fe_adap[0].fe, 0x60,
-					&d->dev->i2c_adap, &tda18271_config)) {
+	mutex_unlock(&d->data_mutex);
+
+	adap->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config,
+					&d->i2c_adap, NULL);
+	if (adap->fe_adap[0].fe != NULL) {
+		if (dvb_attach(tda18271_attach, adap->fe_adap[0].fe, 0x60,
+					&d->i2c_adap, &tda18271_config)) {
 			info("Attached TDA18271HD/CXD2820R!");
 			return 0;
 		}
@@ -1410,23 +1443,30 @@ static int t220_frontend_attach(struct dvb_usb_adapter *d)
 	return -EIO;
 }
 
-static int m88rs2000_frontend_attach(struct dvb_usb_adapter *d)
+static int m88rs2000_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	u8 obuf[] = { 0x51 };
-	u8 ibuf[] = { 0 };
+	struct dvb_usb_device *d = adap->dev;
+	struct dw2102_state *state = d->priv;
+
+	mutex_lock(&d->data_mutex);
 
-	if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+	state->data[0] = 0x51;
+
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
-	d->fe_adap[0].fe = dvb_attach(m88rs2000_attach, &s421_m88rs2000_config,
-					&d->dev->i2c_adap);
+	mutex_unlock(&d->data_mutex);
 
-	if (d->fe_adap[0].fe == NULL)
+	adap->fe_adap[0].fe = dvb_attach(m88rs2000_attach,
+					&s421_m88rs2000_config,
+					&d->i2c_adap);
+
+	if (adap->fe_adap[0].fe == NULL)
 		return -EIO;
 
-	if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
+	if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe,
 				&dw2104_ts2020_config,
-				&d->dev->i2c_adap)) {
+				&d->i2c_adap)) {
 		info("Attached RS2000/TS2020!");
 		return 0;
 	}
@@ -1439,44 +1479,50 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap)
 {
 	struct dvb_usb_device *d = adap->dev;
 	struct dw2102_state *state = d->priv;
-	u8 obuf[3] = { 0xe, 0x80, 0 };
-	u8 ibuf[] = { 0 };
 	struct i2c_adapter *i2c_adapter;
 	struct i2c_client *client;
 	struct i2c_board_info board_info;
 	struct m88ds3103_platform_data m88ds3103_pdata = {};
 	struct ts2020_config ts2020_config = {};
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	mutex_lock(&d->data_mutex);
+
+	state->data[0] = 0xe;
+	state->data[1] = 0x80;
+	state->data[2] = 0x0;
+
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x02;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x02;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 	msleep(300);
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 0;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 0;
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0xe;
-	obuf[1] = 0x83;
-	obuf[2] = 1;
+	state->data[0] = 0xe;
+	state->data[1] = 0x83;
+	state->data[2] = 1;
 
-	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
 		err("command 0x0e transfer failed.");
 
-	obuf[0] = 0x51;
+	state->data[0] = 0x51;
 
-	if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 1, 0) < 0)
+	if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
+	mutex_unlock(&d->data_mutex);
+
 	/* attach demod */
 	m88ds3103_pdata.clk = 27000000;
 	m88ds3103_pdata.i2c_wr_max = 33;
-- 
GitLab


From 8e51533780ba223a3562ff4382c6b6f350c7e9a4 Mon Sep 17 00:00:00 2001
From: Timur Tabi <timur@codeaurora.org>
Date: Fri, 10 Feb 2017 17:21:00 -0600
Subject: [PATCH 738/898] pinctrl: qcom: add get_direction function

The get_direction callback function allows gpiolib to know the current
direction (input vs output) for a given GPIO.

This is particularly useful on ACPI systems, where the GPIOs are
configured only by firmware (typically UEFI), so the only way to
know the initial values to query the hardware directly.  Without
this function, gpiolib thinks that all GPIOs are configured for
input.

Signed-off-by: Timur Tabi <timur@codeaurora.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-msm.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index f8e9e1c2b2f6..c978be5eb9eb 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -422,6 +422,20 @@ static int msm_gpio_direction_output(struct gpio_chip *chip, unsigned offset, in
 	return 0;
 }
 
+static int msm_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+	struct msm_pinctrl *pctrl = gpiochip_get_data(chip);
+	const struct msm_pingroup *g;
+	u32 val;
+
+	g = &pctrl->soc->groups[offset];
+
+	val = readl(pctrl->regs + g->ctl_reg);
+
+	/* 0 = output, 1 = input */
+	return val & BIT(g->oe_bit) ? 0 : 1;
+}
+
 static int msm_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	const struct msm_pingroup *g;
@@ -510,6 +524,7 @@ static void msm_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 static struct gpio_chip msm_gpio_template = {
 	.direction_input  = msm_gpio_direction_input,
 	.direction_output = msm_gpio_direction_output,
+	.get_direction    = msm_gpio_get_direction,
 	.get              = msm_gpio_get,
 	.set              = msm_gpio_set,
 	.request          = gpiochip_generic_request,
-- 
GitLab


From 96e1ce8fcd66d850196758c038bd9d6f7857c518 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Mon, 20 Feb 2017 21:00:42 +0900
Subject: [PATCH 739/898] pinctrl: uniphier: change pin names of aio/xirq for
 LD11

This patch changes pin names of AIO and XIRQ according to updated
specification.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
index 77a0236ee781..83f8864fa76a 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
@@ -390,22 +390,22 @@ static const struct pinctrl_pin_desc uniphier_ld11_pins[] = {
 	UNIPHIER_PINCTRL_PIN(140, "AO1D0", 140,
 			     140, UNIPHIER_PIN_DRV_1BIT,
 			     140, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(141, "TCON0", 141,
+	UNIPHIER_PINCTRL_PIN(141, "AO1D1", 141,
 			     141, UNIPHIER_PIN_DRV_1BIT,
 			     141, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(142, "TCON1", 142,
+	UNIPHIER_PINCTRL_PIN(142, "AO1D2", 142,
 			     142, UNIPHIER_PIN_DRV_1BIT,
 			     142, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(143, "TCON2", 143,
+	UNIPHIER_PINCTRL_PIN(143, "XIRQ9", 143,
 			     143, UNIPHIER_PIN_DRV_1BIT,
 			     143, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(144, "TCON3", 144,
+	UNIPHIER_PINCTRL_PIN(144, "XIRQ10", 144,
 			     144, UNIPHIER_PIN_DRV_1BIT,
 			     144, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(145, "TCON4", 145,
+	UNIPHIER_PINCTRL_PIN(145, "XIRQ11", 145,
 			     145, UNIPHIER_PIN_DRV_1BIT,
 			     145, UNIPHIER_PIN_PULL_DOWN),
-	UNIPHIER_PINCTRL_PIN(146, "TCON5", 146,
+	UNIPHIER_PINCTRL_PIN(146, "XIRQ13", 146,
 			     146, UNIPHIER_PIN_DRV_1BIT,
 			     146, UNIPHIER_PIN_PULL_DOWN),
 	UNIPHIER_PINCTRL_PIN(147, "PWMA", 147,
-- 
GitLab


From b3bd0f2849f4480fc4f40bb954d27e58f4f0786b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 1 Mar 2017 23:50:19 +0100
Subject: [PATCH 740/898] staging/vc04_services: add CONFIG_OF dependency

After several hours of debugging this obviously bogus but elaborate
gcc-7.0.1 warning,

drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c: In function 'vchiq_complete_bulk':
drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c:603:4: error: argument 2 null where non-null expected [-Werror=nonnull]
    memcpy((char *)page_address(pages[0]) +
    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     pagelist->offset,
     ~~~~~~~~~~~~~~~~~
     fragments,
     ~~~~~~~~~~
     head_bytes);
     ~~~~~~~~~~~
In file included from include/linux/string.h:18:0,
                 from include/linux/bitmap.h:8,
                 from include/linux/cpumask.h:11,
                 from include/linux/interrupt.h:9,
                 from drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c:37:
arch/arm/include/asm/string.h:16:15: note: in a call to function 'memcpy' declared here
 extern void * memcpy(void *, const void *, __kernel_size_t) __nocapture(2);
               ^~~~~~

I have concluded that gcc was technically right in the first place:

vchiq_complete_bulk is an externally visible function that calls
free_pagelist(), which in turn derives a pointer from the global
g_fragments_base variable.

g_fragments_base is initialized in vchiq_platform_init(), but
we only get there if of_property_read_u32() successfully reads the
cache line size. When CONFIG_OF is disabled, this always fails, and
g_fragments_base is guaranteed to be NULL when vchiq_complete_bulk()
gets called.

This adds a CONFIG_OF Kconfig dependency, which is also technically correct
but nonobvious, and thus seems like a good fit for the warning.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vc04_services/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/staging/vc04_services/Kconfig b/drivers/staging/vc04_services/Kconfig
index e61e4ca064a8..74094fff4367 100644
--- a/drivers/staging/vc04_services/Kconfig
+++ b/drivers/staging/vc04_services/Kconfig
@@ -1,6 +1,7 @@
 config BCM2835_VCHIQ
 	tristate "Videocore VCHIQ"
 	depends on HAS_DMA
+	depends on OF
 	depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE)
 	default y
 	help
-- 
GitLab


From eb38d913c27f32f4df173791051fecf6aca34173 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Thu, 2 Mar 2017 10:44:58 +0200
Subject: [PATCH 741/898] Revert "usb: gadget: uvc: Add missing call for
 additional setup data"

This reverts commit 4fbac5206afd01b717d4bdc58793d471f3391b4b.

This commit breaks g_webcam when used with uvc-gadget [1].

The user space application (e.g. uvc-gadget) is responsible for
sending response to UVC class specific requests on control endpoint
in uvc_send_response() in uvc_v4l2.c.

The bad commit was causing a duplicate response to be sent with
incorrect response data thus causing UVC probe to fail at the host
and broken control transfer endpoint at the gadget.

[1] - git://git.ideasonboard.org/uvc-gadget.git

Cc: <stable@vger.kernel.org> # v4.9+
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/function/f_uvc.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 27ed51b5082f..29b41b5dee04 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -258,13 +258,6 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
 	memcpy(&uvc_event->req, ctrl, sizeof(uvc_event->req));
 	v4l2_event_queue(&uvc->vdev, &v4l2_event);
 
-	/* Pass additional setup data to userspace */
-	if (uvc->event_setup_out && uvc->event_length) {
-		uvc->control_req->length = uvc->event_length;
-		return usb_ep_queue(uvc->func.config->cdev->gadget->ep0,
-			uvc->control_req, GFP_ATOMIC);
-	}
-
 	return 0;
 }
 
-- 
GitLab


From 5bbc852676ae08e818241cf66a3ffe4be44225c4 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@nxp.com>
Date: Tue, 28 Feb 2017 14:25:45 +0800
Subject: [PATCH 742/898] usb: gadget: dummy_hcd: clear usb_gadget region
 before registration

When the user does device unbind and rebind test, the kernel will
show below dump due to usb_gadget memory region is dirty after unbind.
Clear usb_gadget region for every new probe.

root@imx6qdlsolo:/sys/bus/platform/drivers/dummy_udc# echo dummy_udc.0 > bind
[  102.523312] kobject (eddd78b0): tried to init an initialized object, something is seriously wrong.
[  102.532447] CPU: 0 PID: 734 Comm: sh Not tainted 4.10.0-rc7-00872-g1b2b8e9 #1298
[  102.539866] Hardware name: Freescale i.MX6 SoloX (Device Tree)
[  102.545717] Backtrace:
[  102.548225] [<c010d090>] (dump_backtrace) from [<c010d338>] (show_stack+0x18/0x1c)
[  102.555822]  r7:ede34000 r6:60010013 r5:00000000 r4:c0f29418
[  102.561512] [<c010d320>] (show_stack) from [<c040c2a4>] (dump_stack+0xb4/0xe8)
[  102.568764] [<c040c1f0>] (dump_stack) from [<c040e6d4>] (kobject_init+0x80/0x9c)
[  102.576187]  r10:0000001f r9:eddd7000 r8:eeaf8c10 r7:eddd78a8 r6:c177891c r5:c0f3b060
[  102.584036]  r4:eddd78b0 r3:00000000
[  102.587641] [<c040e654>] (kobject_init) from [<c05359a4>] (device_initialize+0x28/0xf8)
[  102.595665]  r5:eebc4800 r4:eddd78a8
[  102.599268] [<c053597c>] (device_initialize) from [<c05382ac>] (device_register+0x14/0x20)
[  102.607556]  r7:eddd78a8 r6:00000000 r5:eebc4800 r4:eddd78a8
[  102.613256] [<c0538298>] (device_register) from [<c0668ef4>] (usb_add_gadget_udc_release+0x8c/0x1ec)
[  102.622410]  r5:eebc4800 r4:eddd7860
[  102.626015] [<c0668e68>] (usb_add_gadget_udc_release) from [<c0669068>] (usb_add_gadget_udc+0x14/0x18)
[  102.635351]  r10:0000001f r9:eddd7000 r8:eddd788c r7:bf003770 r6:eddd77f8 r5:eddd7818
[  102.643198]  r4:eddd785c r3:eddd7b24
[  102.646834] [<c0669054>] (usb_add_gadget_udc) from [<bf003428>] (dummy_udc_probe+0x170/0x1c4 [dummy_hcd])
[  102.656458] [<bf0032b8>] (dummy_udc_probe [dummy_hcd]) from [<c053d114>] (platform_drv_probe+0x54/0xb8)
[  102.665881]  r10:00000008 r9:c1778960 r8:bf004128 r7:fffffdfb r6:bf004128 r5:eeaf8c10
[  102.673727]  r4:eeaf8c10
[  102.676293] [<c053d0c0>] (platform_drv_probe) from [<c053b160>] (driver_probe_device+0x264/0x474)
[  102.685186]  r7:00000000 r6:00000000 r5:c1778960 r4:eeaf8c10
[  102.690876] [<c053aefc>] (driver_probe_device) from [<c05397c4>] (bind_store+0xb8/0x14c)
[  102.698994]  r10:eeb3bb4c r9:ede34000 r8:0000000c r7:eeaf8c44 r6:bf004128 r5:c0f3b668
[  102.706840]  r4:eeaf8c10
[  102.709402] [<c053970c>] (bind_store) from [<c0538ca8>] (drv_attr_store+0x28/0x34)
[  102.716998]  r9:ede34000 r8:00000000 r7:ee3863c0 r6:ee3863c0 r5:c0538c80 r4:c053970c
[  102.724776] [<c0538c80>] (drv_attr_store) from [<c029c930>] (sysfs_kf_write+0x50/0x54)
[  102.732711]  r5:c0538c80 r4:0000000c
[  102.736313] [<c029c8e0>] (sysfs_kf_write) from [<c029be84>] (kernfs_fop_write+0x100/0x214)
[  102.744599]  r7:ee3863c0 r6:eeb3bb40 r5:00000000 r4:00000000
[  102.750287] [<c029bd84>] (kernfs_fop_write) from [<c0222dd8>] (__vfs_write+0x34/0x120)
[  102.758231]  r10:00000000 r9:ede34000 r8:c0108bc4 r7:0000000c r6:ede35f80 r5:c029bd84
[  102.766077]  r4:ee223780
[  102.768638] [<c0222da4>] (__vfs_write) from [<c0224678>] (vfs_write+0xa8/0x170)
[  102.775974]  r9:ede34000 r8:c0108bc4 r7:ede35f80 r6:01861cb0 r5:ee223780 r4:0000000c
[  102.783743] [<c02245d0>] (vfs_write) from [<c0225498>] (SyS_write+0x4c/0xa8)
[  102.790818]  r9:ede34000 r8:c0108bc4 r7:0000000c r6:01861cb0 r5:ee223780 r4:ee223780
[  102.798595] [<c022544c>] (SyS_write) from [<c0108a20>] (ret_fast_syscall+0x0/0x1c)
[  102.806188]  r7:00000004 r6:b6e83d58 r5:01861cb0 r4:0000000c

Fixes: 90fccb529d24 ("usb: gadget: Gadget directory cleanup - group UDC drivers")
Cc: stable <stable@vger.kernel.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Peter Chen <peter.chen@nxp.com>
Tested-by: Xiaolong Ye <xiaolong.ye@intel.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/udc/dummy_hcd.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index c60abe3a68f9..8cabc5944d5f 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1031,6 +1031,8 @@ static int dummy_udc_probe(struct platform_device *pdev)
 	int		rc;
 
 	dum = *((void **)dev_get_platdata(&pdev->dev));
+	/* Clear usb_gadget region for new registration to udc-core */
+	memzero_explicit(&dum->gadget, sizeof(struct usb_gadget));
 	dum->gadget.name = gadget_name;
 	dum->gadget.ops = &dummy_ops;
 	dum->gadget.max_speed = USB_SPEED_SUPER;
-- 
GitLab


From 077dbaee9df53c597df532a08d721d03f4570f3d Mon Sep 17 00:00:00 2001
From: Franck Demathieu <fdemathieu@gmail.com>
Date: Thu, 23 Feb 2017 10:48:55 +0100
Subject: [PATCH 743/898] irqchip/crossbar: Fix incorrect type of local
 variables

The max and entry variables are unsigned according to the dt-bindings.
Fix following 3 sparse issues (-Wtypesign):

  drivers/irqchip/irq-crossbar.c:222:52: warning: incorrect type in argument 3 (different signedness)
  drivers/irqchip/irq-crossbar.c:222:52:    expected unsigned int [usertype] *out_value
  drivers/irqchip/irq-crossbar.c:222:52:    got int *<noident>

  drivers/irqchip/irq-crossbar.c:245:56: warning: incorrect type in argument 4 (different signedness)
  drivers/irqchip/irq-crossbar.c:245:56:    expected unsigned int [usertype] *out_value
  drivers/irqchip/irq-crossbar.c:245:56:    got int *<noident>

  drivers/irqchip/irq-crossbar.c:263:56: warning: incorrect type in argument 4 (different signedness)
  drivers/irqchip/irq-crossbar.c:263:56:    expected unsigned int [usertype] *out_value
  drivers/irqchip/irq-crossbar.c:263:56:    got int *<noident>

Signed-off-by: Franck Demathieu <fdemathieu@gmail.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-crossbar.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 1eef56a89b1f..05bbf171df37 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -198,7 +198,8 @@ static const struct irq_domain_ops crossbar_domain_ops = {
 
 static int __init crossbar_of_init(struct device_node *node)
 {
-	int i, size, max = 0, reserved = 0, entry;
+	int i, size, reserved = 0;
+	u32 max = 0, entry;
 	const __be32 *irqsr;
 	int ret = -ENOMEM;
 
-- 
GitLab


From b3e228473e6cec7cf83b4025b4570c8066ab2dd8 Mon Sep 17 00:00:00 2001
From: Mian Yousaf Kaukab <yousaf.kaukab@suse.com>
Date: Thu, 2 Mar 2017 16:11:47 +0100
Subject: [PATCH 744/898] irqdomain: Add empty irq_domain_check_msi_remap

Fix following build error for s390:
drivers/vfio/vfio_iommu_type1.c: In function 'vfio_iommu_type1_attach_group':
drivers/vfio/vfio_iommu_type1.c:1290:25: error: implicit declaration of function 'irq_domain_check_msi_remap'

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Mian Yousaf Kaukab <yousaf.kaukab@suse.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/linux/irqdomain.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 188eced6813e..9f3616085423 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -524,6 +524,10 @@ static inline struct irq_domain *irq_find_matching_fwnode(
 {
 	return NULL;
 }
+static inline bool irq_domain_check_msi_remap(void)
+{
+	return false;
+}
 #endif /* !CONFIG_IRQ_DOMAIN */
 
 #endif /* _LINUX_IRQDOMAIN_H */
-- 
GitLab


From 38355b2a44776c25b0f2ad466e8c51bb805b3032 Mon Sep 17 00:00:00 2001
From: John Keeping <john@metanate.com>
Date: Tue, 28 Feb 2017 10:55:30 +0000
Subject: [PATCH 745/898] usb: gadget: configs: plug memory leak

When binding a gadget to a device, "name" is stored in gi->udc_name, but
this does not happen when unregistering and the string is leaked.

Signed-off-by: John Keeping <john@metanate.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/configfs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 78c44979dde3..cbff3b02840d 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -269,6 +269,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item,
 		ret = unregister_gadget(gi);
 		if (ret)
 			goto err;
+		kfree(name);
 	} else {
 		if (gi->composite.gadget_driver.udc_name) {
 			ret = -EBUSY;
-- 
GitLab


From 73561128eb72ca04c3be6e240f162a861bf68a86 Mon Sep 17 00:00:00 2001
From: Franck Demathieu <fdemathieu@gmail.com>
Date: Mon, 27 Feb 2017 11:52:46 +0100
Subject: [PATCH 746/898] usb: dwc3: Fix incorrect type for utmi mode

The utmi mode is unsigned according the dt-bindings.
Fix sparse issue (-Wtypesign):

  drivers/usb/dwc3/dwc3-omap.c:391:50: warning: incorrect type in argument 3 (different signedness)
  drivers/usb/dwc3/dwc3-omap.c:391:50:    expected unsigned int [usertype] *out_value
  drivers/usb/dwc3/dwc3-omap.c:391:50:    got int *<noident>

Signed-off-by: Franck Demathieu <fdemathieu@gmail.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/dwc3/dwc3-omap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 2092e46b1380..4a595777969e 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -392,7 +392,7 @@ static void dwc3_omap_set_utmi_mode(struct dwc3_omap *omap)
 {
 	u32			reg;
 	struct device_node	*node = omap->dev->of_node;
-	int			utmi_mode = 0;
+	u32			utmi_mode = 0;
 
 	reg = dwc3_omap_read_utmi_ctrl(omap);
 
-- 
GitLab


From 4242820277b5378c9e4064e79306f326d731472f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 22 Feb 2017 11:33:27 +0100
Subject: [PATCH 747/898] usb: gadget: udc: atmel: fix debug output

The debug output now contains the wrong variable, as seen from the compiler
warning:

drivers/usb/gadget/udc/atmel_usba_udc.c: In function 'usba_ep_enable':
drivers/usb/gadget/udc/atmel_usba_udc.c:632:550: error: 'ept_cfg' may be used uninitialized in this function [-Werror=maybe-uninitialized]
  DBG(DBG_ERR, "%s: EPT_CFG = 0x%lx (maxpacket = %lu)\n",

This changes the debug output the same way as the other code.

Fixes: 741d2558bf0a ("usb: gadget: udc: atmel: Update endpoint allocation scheme")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/udc/atmel_usba_udc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 11bbce28bc23..2035906b8ced 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -610,7 +610,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc)
 {
 	struct usba_ep *ep = to_usba_ep(_ep);
 	struct usba_udc *udc = ep->udc;
-	unsigned long flags, ept_cfg, maxpacket;
+	unsigned long flags, maxpacket;
 	unsigned int nr_trans;
 
 	DBG(DBG_GADGET, "%s: ep_enable: desc=%p\n", ep->ep.name, desc);
@@ -630,7 +630,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc)
 	ep->is_in = 0;
 
 	DBG(DBG_ERR, "%s: EPT_CFG = 0x%lx (maxpacket = %lu)\n",
-			ep->ep.name, ept_cfg, maxpacket);
+			ep->ep.name, ep->ept_cfg, maxpacket);
 
 	if (usb_endpoint_dir_in(desc)) {
 		ep->is_in = 1;
-- 
GitLab


From b6e7aeeaf235901c42ec35de4633c7c69501d303 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 21 Feb 2017 22:33:11 +0100
Subject: [PATCH 748/898] USB: gadgetfs: Fix a potential memory leak in
 'dev_config()'

'kbuf' is allocated just a few lines above using 'memdup_user()'.
If the 'if (dev->buf)' test fails, this memory is never released.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/legacy/inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index a2615d64d07c..0513dfa008e6 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -1782,8 +1782,10 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 
 	spin_lock_irq (&dev->lock);
 	value = -EINVAL;
-	if (dev->buf)
+	if (dev->buf) {
+		kfree(kbuf);
 		goto fail;
+	}
 	dev->buf = kbuf;
 
 	/* full or low speed config */
-- 
GitLab


From 3ba534df815f233535b5a3dd3de41055666bbd21 Mon Sep 17 00:00:00 2001
From: Janusz Dziedzic <januszx.dziedzic@linux.intel.com>
Date: Thu, 16 Feb 2017 14:54:12 +0100
Subject: [PATCH 749/898] Revert "usb: gadget: f_fs: Fix ExtCompat descriptor
 validation"

This reverts commit ac670a3a650b899fc020b81f63e810d06015b865.

This introduce bug we already fixed in
commit 53642399aa71 ("usb: gadget: f_fs: Fix wrong check on reserved1 wof OS_DESC_EXT_COMPAT")

Next FFS (adb) SS enumeration fail with Windows OS.

Signed-off-by: Janusz Dziedzic <januszx.dziedzic@linux.intel.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/function/f_fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 7e976f00cb02..a0085571824d 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2264,7 +2264,7 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
 
 		if (len < sizeof(*d) ||
 		    d->bFirstInterfaceNumber >= ffs->interfaces_count ||
-		    d->Reserved1)
+		    !d->Reserved1)
 			return -EINVAL;
 		for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i)
 			if (d->Reserved2[i])
-- 
GitLab


From 1551e35ea4189c1f7199fe278395fc94196715f2 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Wed, 15 Feb 2017 14:16:26 +0200
Subject: [PATCH 750/898] usb: dwc3: gadget: Fix system suspend/resume on TI
 platforms

On TI platforms (dra7, am437x), the DWC3_DSTS_DEVCTRLHLT bit is not set
after the device controller is stopped via DWC3_DCTL_RUN_STOP.

If we don't disconnect and stop the gadget, it stops working after a
system resume with the trace below.

There is no point in preventing gadget disconnect and gadget stop during
system suspend/resume as we're going to suspend in any case, whether
DEVCTRLHLT timed out or not.

[  141.727480] ------------[ cut here ]------------
[  141.732349] WARNING: CPU: 1 PID: 2135 at drivers/usb/dwc3/gadget.c:2384 dwc3_stop_active_transfer.constprop.4+0xc4/0xe4 [dwc3]
[  141.744299] Modules linked in: usb_f_ss_lb g_zero libcomposite xhci_plat_hcd xhci_hcd usbcore dwc3 evdev udc_core m25p80 usb_common spi_nor snd_soc_davinci_mcasp snd_soc_simple_card snd_soc_edma snd_soc_tlv3e
[  141.792163] CPU: 1 PID: 2135 Comm: irq/456-dwc3 Not tainted 4.10.0-rc8 #1138
[  141.799547] Hardware name: Generic DRA74X (Flattened Device Tree)
[  141.805940] [<c01101b4>] (unwind_backtrace) from [<c010c31c>] (show_stack+0x10/0x14)
[  141.814066] [<c010c31c>] (show_stack) from [<c04a0918>] (dump_stack+0xac/0xe0)
[  141.821648] [<c04a0918>] (dump_stack) from [<c013708c>] (__warn+0xd8/0x104)
[  141.828955] [<c013708c>] (__warn) from [<c0137164>] (warn_slowpath_null+0x20/0x28)
[  141.836902] [<c0137164>] (warn_slowpath_null) from [<bf27784c>] (dwc3_stop_active_transfer.constprop.4+0xc4/0xe4 [dwc3])
[  141.848329] [<bf27784c>] (dwc3_stop_active_transfer.constprop.4 [dwc3]) from [<bf27ab14>] (__dwc3_gadget_ep_disable+0x64/0x528 [dwc3])
[  141.861034] [<bf27ab14>] (__dwc3_gadget_ep_disable [dwc3]) from [<bf27c27c>] (dwc3_gadget_ep_disable+0x3c/0xc8 [dwc3])
[  141.872280] [<bf27c27c>] (dwc3_gadget_ep_disable [dwc3]) from [<bf23b428>] (usb_ep_disable+0x11c/0x18c [udc_core])
[  141.883160] [<bf23b428>] (usb_ep_disable [udc_core]) from [<bf342774>] (disable_ep+0x18/0x54 [usb_f_ss_lb])
[  141.893408] [<bf342774>] (disable_ep [usb_f_ss_lb]) from [<bf3437b0>] (disable_endpoints+0x18/0x50 [usb_f_ss_lb])
[  141.904168] [<bf3437b0>] (disable_endpoints [usb_f_ss_lb]) from [<bf343814>] (disable_source_sink+0x2c/0x34 [usb_f_ss_lb])
[  141.915771] [<bf343814>] (disable_source_sink [usb_f_ss_lb]) from [<bf329a9c>] (reset_config+0x48/0x7c [libcomposite])
[  141.927012] [<bf329a9c>] (reset_config [libcomposite]) from [<bf329afc>] (composite_disconnect+0x2c/0x54 [libcomposite])
[  141.938444] [<bf329afc>] (composite_disconnect [libcomposite]) from [<bf23d7dc>] (usb_gadget_udc_reset+0x10/0x34 [udc_core])
[  141.950237] [<bf23d7dc>] (usb_gadget_udc_reset [udc_core]) from [<bf276d70>] (dwc3_gadget_reset_interrupt+0x64/0x698 [dwc3])
[  141.962022] [<bf276d70>] (dwc3_gadget_reset_interrupt [dwc3]) from [<bf27952c>] (dwc3_thread_interrupt+0x618/0x1a3c [dwc3])
[  141.973723] [<bf27952c>] (dwc3_thread_interrupt [dwc3]) from [<c01a7ce8>] (irq_thread_fn+0x1c/0x54)
[  141.983215] [<c01a7ce8>] (irq_thread_fn) from [<c01a7fbc>] (irq_thread+0x120/0x1f0)
[  141.991247] [<c01a7fbc>] (irq_thread) from [<c015ba14>] (kthread+0xf8/0x138)
[  141.998641] [<c015ba14>] (kthread) from [<c01078f0>] (ret_from_fork+0x14/0x24)
[  142.006213] ---[ end trace b4ecfe9f175b9a9c ]---

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/dwc3/gadget.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index f875b3f4b0ec..3db5eeae2bfb 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3291,15 +3291,10 @@ void dwc3_gadget_exit(struct dwc3 *dwc)
 
 int dwc3_gadget_suspend(struct dwc3 *dwc)
 {
-	int ret;
-
 	if (!dwc->gadget_driver)
 		return 0;
 
-	ret = dwc3_gadget_run_stop(dwc, false, false);
-	if (ret < 0)
-		return ret;
-
+	dwc3_gadget_run_stop(dwc, false, false);
 	dwc3_disconnect_gadget(dwc);
 	__dwc3_gadget_stop(dwc);
 
-- 
GitLab


From 0913750f9fb6f26bcd00c8f9dd9a8d1b8d031246 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Wed, 15 Feb 2017 13:38:22 +0200
Subject: [PATCH 751/898] usb: dwc3-omap: Fix missing break in
 dwc3_omap_set_mailbox()

We need to break from all cases if we want to treat
each one of them separately.

Reported-by: Gustavo A. R. Silva <garsilva@embeddedor.com>
Fixes: d2728fb3e01f ("usb: dwc3: omap: Pass VBUS and ID events transparently")
Cc: <stable@vger.kernel.org> #v4.8+
Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/dwc3/dwc3-omap.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 4a595777969e..f8d0747810e7 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -250,6 +250,7 @@ static void dwc3_omap_set_mailbox(struct dwc3_omap *omap,
 		val = dwc3_omap_read_utmi_ctrl(omap);
 		val |= USBOTGSS_UTMI_OTG_CTRL_IDDIG;
 		dwc3_omap_write_utmi_ctrl(omap, val);
+		break;
 
 	case OMAP_DWC3_VBUS_OFF:
 		val = dwc3_omap_read_utmi_ctrl(omap);
-- 
GitLab


From df7545719a14fa7b481896fb8689e23d0a00f682 Mon Sep 17 00:00:00 2001
From: Petr Cvek <petr.cvek@tul.cz>
Date: Fri, 24 Feb 2017 02:54:56 +0100
Subject: [PATCH 752/898] usb: gadget: pxa27x: Test for a valid argument
 pointer

A call usb_put_phy(udc->transceiver) must be tested for a valid pointer.
Use an already existing test for usb_unregister_notifier call.

Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Reported-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Petr Cvek <petr.cvek@tul.cz>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/udc/pxa27x_udc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c
index e1335ad5bce9..832c4fdbe985 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.c
+++ b/drivers/usb/gadget/udc/pxa27x_udc.c
@@ -2534,9 +2534,10 @@ static int pxa_udc_remove(struct platform_device *_dev)
 	usb_del_gadget_udc(&udc->gadget);
 	pxa_cleanup_debugfs(udc);
 
-	if (!IS_ERR_OR_NULL(udc->transceiver))
+	if (!IS_ERR_OR_NULL(udc->transceiver)) {
 		usb_unregister_notifier(udc->transceiver, &pxa27x_udc_phy);
-	usb_put_phy(udc->transceiver);
+		usb_put_phy(udc->transceiver);
+	}
 
 	udc->transceiver = NULL;
 	the_controller = NULL;
-- 
GitLab


From ef5e2fa9f65befa12f1113c734602d2c1964d2a5 Mon Sep 17 00:00:00 2001
From: Raz Manor <Raz.Manor@valens.com>
Date: Thu, 9 Feb 2017 09:41:08 +0200
Subject: [PATCH 753/898] usb: gadget: udc: net2280: Fix tmp reusage in net2280
 driver

In the function scan_dma_completions() there is a reusage of tmp
variable. That coused a wrong value being used in some case when
reading a short packet terminated transaction from an endpoint,
in 2 concecutive reads.

This was my logic for the patch:

The req->td->dmadesc equals to 0 iff:
-- There was a transaction ending with a short packet, and
-- The read() to read it was shorter than the transaction length, and
-- The read() to complete it is longer than the residue.
I believe this is true from the printouts of various cases,
but I can't be positive it is correct.

Entering this if, there should be no more data in the endpoint
(a short packet terminated the transaction).
If there is, the transaction wasn't really done and we should exit and
wait for it to finish entirely. That is the inner if.
That inner if should never happen, but it is there to be on the safe
side. That is why it is marked with the comment /* paranoia */.
The size of the data available in the endpoint is ep->dma->dmacount
and it is read to tmp.
This entire clause is based on my own educated guesses.

If we passed that inner if without breaking in the original code,
than tmp & DMA_BYTE_MASK_COUNT== 0.
That means we will always pass dma bytes count of 0 to dma_done(),
meaning all the requested bytes were read.

dma_done() reports back to the upper layer that the request (read())
was done and how many bytes were read.
In the original code that would always be the request size,
regardless of the actual size of the data.
That did not make sense to me at all.

However, the original value of tmp is req->td->dmacount,
which is the dmacount value when the request's dma transaction was
finished. And that is a much more reasonable value to report back to
the caller.

To recreate the problem:
Read from a bulk out endpoint in a loop, 1024 * n bytes in each
iteration.
Connect the PLX to a host you can control.
Send to that endpoint 1024 * n + x bytes,
such that 0 < x < 1024 * n and (x % 1024) != 0
You would expect the first read() to return 1024 * n
and the second read() to return x.
But you will get the first read to return 1024 * n
and the second one to return 1024 * n.
That is true for every positive integer n.

Cc: Felipe Balbi <balbi@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Raz Manor <Raz.Manor@valens.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/gadget/udc/net2280.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index 85504419ab31..3828c2ec8623 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -1146,15 +1146,15 @@ static int scan_dma_completions(struct net2280_ep *ep)
 	 */
 	while (!list_empty(&ep->queue)) {
 		struct net2280_request	*req;
-		u32			tmp;
+		u32 req_dma_count;
 
 		req = list_entry(ep->queue.next,
 				struct net2280_request, queue);
 		if (!req->valid)
 			break;
 		rmb();
-		tmp = le32_to_cpup(&req->td->dmacount);
-		if ((tmp & BIT(VALID_BIT)) != 0)
+		req_dma_count = le32_to_cpup(&req->td->dmacount);
+		if ((req_dma_count & BIT(VALID_BIT)) != 0)
 			break;
 
 		/* SHORT_PACKET_TRANSFERRED_INTERRUPT handles "usb-short"
@@ -1163,40 +1163,41 @@ static int scan_dma_completions(struct net2280_ep *ep)
 		 */
 		if (unlikely(req->td->dmadesc == 0)) {
 			/* paranoia */
-			tmp = readl(&ep->dma->dmacount);
-			if (tmp & DMA_BYTE_COUNT_MASK)
+			u32 const ep_dmacount = readl(&ep->dma->dmacount);
+
+			if (ep_dmacount & DMA_BYTE_COUNT_MASK)
 				break;
 			/* single transfer mode */
-			dma_done(ep, req, tmp, 0);
+			dma_done(ep, req, req_dma_count, 0);
 			num_completed++;
 			break;
 		} else if (!ep->is_in &&
 			   (req->req.length % ep->ep.maxpacket) &&
 			   !(ep->dev->quirks & PLX_PCIE)) {
 
-			tmp = readl(&ep->regs->ep_stat);
+			u32 const ep_stat = readl(&ep->regs->ep_stat);
 			/* AVOID TROUBLE HERE by not issuing short reads from
 			 * your gadget driver.  That helps avoids errata 0121,
 			 * 0122, and 0124; not all cases trigger the warning.
 			 */
-			if ((tmp & BIT(NAK_OUT_PACKETS)) == 0) {
+			if ((ep_stat & BIT(NAK_OUT_PACKETS)) == 0) {
 				ep_warn(ep->dev, "%s lost packet sync!\n",
 						ep->ep.name);
 				req->req.status = -EOVERFLOW;
 			} else {
-				tmp = readl(&ep->regs->ep_avail);
-				if (tmp) {
+				u32 const ep_avail = readl(&ep->regs->ep_avail);
+				if (ep_avail) {
 					/* fifo gets flushed later */
 					ep->out_overflow = 1;
 					ep_dbg(ep->dev,
 						"%s dma, discard %d len %d\n",
-						ep->ep.name, tmp,
+						ep->ep.name, ep_avail,
 						req->req.length);
 					req->req.status = -EOVERFLOW;
 				}
 			}
 		}
-		dma_done(ep, req, tmp, 0);
+		dma_done(ep, req, req_dma_count, 0);
 		num_completed++;
 	}
 
-- 
GitLab


From 587d7e72aedca91cee80c0a56811649c3efab765 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Thu, 2 Mar 2017 12:41:48 -0800
Subject: [PATCH 754/898] kvm: nVMX: VMCLEAR should not cause the vCPU to shut
 down
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

VMCLEAR should silently ignore a failure to clear the launch state of
the VMCS referenced by the operand.

Signed-off-by: Jim Mattson <jmattson@google.com>
[Changed "kvm_write_guest(vcpu->kvm" to "kvm_vcpu_write_guest(vcpu".]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 22 ++++------------------
 1 file changed, 4 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 283aa8601833..3b626d6dc3ac 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7258,9 +7258,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 zero = 0;
 	gpa_t vmptr;
-	struct vmcs12 *vmcs12;
-	struct page *page;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
@@ -7271,22 +7270,9 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (vmptr == vmx->nested.current_vmptr)
 		nested_release_vmcs12(vmx);
 
-	page = nested_get_page(vcpu, vmptr);
-	if (page == NULL) {
-		/*
-		 * For accurate processor emulation, VMCLEAR beyond available
-		 * physical memory should do nothing at all. However, it is
-		 * possible that a nested vmx bug, not a guest hypervisor bug,
-		 * resulted in this case, so let's shut down before doing any
-		 * more damage:
-		 */
-		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		return 1;
-	}
-	vmcs12 = kmap(page);
-	vmcs12->launch_state = 0;
-	kunmap(page);
-	nested_release_page(page);
+	kvm_vcpu_write_guest(vcpu,
+			vmptr + offsetof(struct vmcs12, launch_state),
+			&zero, sizeof(zero));
 
 	nested_free_vmcs02(vmx, vmptr);
 
-- 
GitLab


From c771c14baa3319c85512e575671bf0bb18824c11 Mon Sep 17 00:00:00 2001
From: Eryu Guan <eguan@redhat.com>
Date: Thu, 2 Mar 2017 15:02:06 -0800
Subject: [PATCH 755/898] iomap: invalidate page caches should be after
 iomap_dio_complete() in direct write

After XFS switching to iomap based DIO (commit acdda3aae146 ("xfs:
use iomap_dio_rw")), I started to notice dio29/dio30 tests failures
from LTP run on ppc64 hosts, and they can be reproduced on x86_64
hosts with 512B/1k block size XFS too.

dio29	diotest3 -b 65536 -n 100 -i 1000 -o 1024000
dio30	diotest6 -b 65536 -n 100 -i 1000 -o 1024000

The failure message is like:
bufcmp: offset 0: Expected: 0x62, got 0x0
diotest03    1  TPASS  :  Read with Direct IO, Write without
diotest03    2  TFAIL  :  diotest3.c:142: comparsion failed; child=98 offset=1425408
diotest03    3  TFAIL  :  diotest3.c:194: Write Direct-child 98 failed

Direct write wrote 0x62 but buffer read got zero. This is because,
when doing direct write to a hole or preallocated file, we
invalidate the page caches before converting the extent from
unwritten state to normal state, which is done by
iomap_dio_complete(), thus leave a window for other buffer reader to
cache the unwritten state extent.

Consider this case, with sub-page blocksize XFS, two processes are
direct writing to different blocksize-aligned regions (say 512B) of
the same preallocated file, and reading the region back via buffered
I/O to compare contents.

process A, region [0,512]		process B, region [512,1024]
xfs_file_write_iter
 xfs_file_aio_dio_write
  iomap_dio_rw
   iomap_apply
   invalidate_inode_pages2_range
   					xfs_file_write_iter
				 	xfs_file_aio_dio_write
					  iomap_dio_rw
					   iomap_apply
					   invalidate_inode_pages2_range
					   iomap_dio_complete
					xfs_file_read_iter
					 xfs_file_buffered_aio_read
					  generic_file_read_iter
					   do_generic_file_read
					    <readahead fills pagecache with 0>
   iomap_dio_complete
xfs_file_read_iter
 <read gets 0 from pagecache>

Process A first invalidates page caches, at this point the
underlying extent is still in unwritten state (iomap_dio_complete
not called yet), and process B finishs direct write and populates
page caches via readahead, which caches zeros in page for region A,
then process A reads zeros from page cache, instead of the actual
data.

Fix it by invalidating page caches after converting unwritten extent
to make sure we read content from disk after extent state changed,
as what we did before switching to iomap based dio.

Also introduce a new 'start' variable to save the original write
offset (iomap_dio_complete() updates iocb->ki_pos), and a 'err'
variable for invalidating caches result, cause we can't reuse 'ret'
anymore.

Signed-off-by: Eryu Guan <eguan@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 3ca1a8e44135..141c3cd55a8b 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -846,7 +846,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	size_t count = iov_iter_count(iter);
-	loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0;
+	loff_t pos = iocb->ki_pos, start = pos;
+	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
 	struct blk_plug plug;
 	struct iomap_dio *dio;
@@ -887,12 +888,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	if (mapping->nrpages) {
-		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+		ret = filemap_write_and_wait_range(mapping, start, end);
 		if (ret)
 			goto out_free_dio;
 
 		ret = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
@@ -941,6 +942,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
+	ret = iomap_dio_complete(dio);
+
 	/*
 	 * Try again to invalidate clean pages which might have been cached by
 	 * non-direct readahead, or faulted in by get_user_pages() if the source
@@ -949,12 +952,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	 * this invalidation fails, tough, the write still worked...
 	 */
 	if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
+		int err = invalidate_inode_pages2_range(mapping,
+				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+		WARN_ON_ONCE(err);
 	}
 
-	return iomap_dio_complete(dio);
+	return ret;
 
 out_free_dio:
 	kfree(dio);
-- 
GitLab


From 040757f738e13caaa9c5078bca79aa97e11dde88 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 5 Mar 2017 15:03:22 -0600
Subject: [PATCH 756/898] ucount: Remove the atomicity from ucount->count

Always increment/decrement ucount->count under the ucounts_lock.  The
increments are there already and moving the decrements there means the
locking logic of the code is simpler.  This simplification in the
locking logic fixes a race between put_ucounts and get_ucounts that
could result in a use-after-free because the count could go zero then
be found by get_ucounts and then be freed by put_ucounts.

A bug presumably this one was found by a combination of syzkaller and
KASAN.  JongWhan Kim reported the syzkaller failure and Dmitry Vyukov
spotted the race in the code.

Cc: stable@vger.kernel.org
Fixes: f6b2db1a3e8d ("userns: Make the count of user namespaces per user")
Reported-by: JongHwan Kim <zzoru007@gmail.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/user_namespace.h |  2 +-
 kernel/ucount.c                | 18 +++++++++++-------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index be765234c0a2..32354b4b4b2b 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -72,7 +72,7 @@ struct ucounts {
 	struct hlist_node node;
 	struct user_namespace *ns;
 	kuid_t uid;
-	atomic_t count;
+	int count;
 	atomic_t ucount[UCOUNT_COUNTS];
 };
 
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 62630a40ab3a..b4eeee03934f 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 
 		new->ns = ns;
 		new->uid = uid;
-		atomic_set(&new->count, 0);
+		new->count = 0;
 
 		spin_lock_irq(&ucounts_lock);
 		ucounts = find_ucounts(ns, uid, hashent);
@@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 			ucounts = new;
 		}
 	}
-	if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
+	if (ucounts->count == INT_MAX)
 		ucounts = NULL;
+	else
+		ucounts->count += 1;
 	spin_unlock_irq(&ucounts_lock);
 	return ucounts;
 }
@@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts)
 {
 	unsigned long flags;
 
-	if (atomic_dec_and_test(&ucounts->count)) {
-		spin_lock_irqsave(&ucounts_lock, flags);
+	spin_lock_irqsave(&ucounts_lock, flags);
+	ucounts->count -= 1;
+	if (!ucounts->count)
 		hlist_del_init(&ucounts->node);
-		spin_unlock_irqrestore(&ucounts_lock, flags);
+	else
+		ucounts = NULL;
+	spin_unlock_irqrestore(&ucounts_lock, flags);
 
-		kfree(ucounts);
-	}
+	kfree(ucounts);
 }
 
 static inline bool atomic_inc_below(atomic_t *v, int u)
-- 
GitLab


From 1fbdbcea80056acfc8c8506594744f5ec52208c1 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 5 Mar 2017 17:05:57 -0800
Subject: [PATCH 757/898] avr32: Fix build error caused by include file
 reshuffling

Various avr32 builds fail:

  arch/avr32/oprofile/backtrace.c:58: error: dereferencing pointer to incomplete type
  arch/avr32/oprofile/backtrace.c:60: error: implicit declaration of function 'user_mode'

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Hans-Christian Noren Egtvedt <egtvedt@samfundet.no>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: oprofile-list@lists.sf.net
Fixes: f780d89a0e82 ("sched/headers: Remove <asm/ptrace.h> from ...")
Link: http://lkml.kernel.org/r/1488762357-4500-1-git-send-email-linux@roeck-us.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/avr32/oprofile/backtrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/avr32/oprofile/backtrace.c b/arch/avr32/oprofile/backtrace.c
index 75d9ad6f99cf..29cf2f191bfd 100644
--- a/arch/avr32/oprofile/backtrace.c
+++ b/arch/avr32/oprofile/backtrace.c
@@ -14,7 +14,7 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/sched.h>
+#include <linux/ptrace.h>
 #include <linux/uaccess.h>
 
 /* The first two words of each frame on the stack look like this if we have
-- 
GitLab


From 80aa1a54f054a1c71cc88e0cad6cfa0d20a10f23 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 5 Mar 2017 10:27:14 -0800
Subject: [PATCH 758/898] h8300: Fix build breakage caused by header file
 changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following h8300 build failures:

  arch/h8300/kernel/ptrace_h.c: In function ‘trace_trap’:
  arch/h8300/kernel/ptrace_h.c:253:3: error: implicit declaration of function ‘force_sig’

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: uclinux-h8-devel@lists.sourceforge.jp
Fixes: c3edc4010e9d ("sched/headers: Move task_struct::signal and ...")
Link: http://lkml.kernel.org/r/1488738434-3504-1-git-send-email-linux@roeck-us.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/h8300/kernel/ptrace_h.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/h8300/kernel/ptrace_h.c b/arch/h8300/kernel/ptrace_h.c
index fe3b5673baba..f5ff3b794c85 100644
--- a/arch/h8300/kernel/ptrace_h.c
+++ b/arch/h8300/kernel/ptrace_h.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <asm/ptrace.h>
 
 #define BREAKINST 0x5730 /* trapa #3 */
-- 
GitLab


From bb35e4515411396219431fa235bf21bf9c2794e9 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 5 Mar 2017 17:13:31 -0800
Subject: [PATCH 759/898] drivers/char/nwbutton: Fix build breakage caused by
 include file reshuffling

Fix:

  drivers/char/nwbutton.c: In function 'button_sequence_finished':
  drivers/char/nwbutton.c:134:3: error: implicit declaration of function 'kill_cad_pid'

The declaration has been moved from one include file to another.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: c3edc4010e9d102 ("sched/headers: Move task_struct::signal and ...")
Link: http://lkml.kernel.org/r/1488762811-9022-1-git-send-email-linux@roeck-us.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/char/nwbutton.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c
index a5b1eb276c0b..e6d0d271c58c 100644
--- a/drivers/char/nwbutton.c
+++ b/drivers/char/nwbutton.c
@@ -6,7 +6,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/timer.h>
-- 
GitLab


From 5c51f4ae84df0f9df33ac08aa5be50061a8b4242 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Thu, 2 Mar 2017 16:57:23 -0600
Subject: [PATCH 760/898] objtool: Fix another GCC jump table detection issue

Arnd Bergmann reported a (false positive) objtool warning:

  drivers/infiniband/sw/rxe/rxe_resp.o: warning: objtool: rxe_responder()+0xfe: sibling call from callable instruction with changed frame pointer

The issue is in find_switch_table().  It tries to find a switch
statement's jump table by walking backwards from an indirect jump
instruction, looking for a relocation to the .rodata section.  In this
case it stopped walking prematurely: the first .rodata relocation it
encountered was for a variable (resp_state_name) instead of a jump
table, so it just assumed there wasn't a jump table.

The fix is to ignore any .rodata relocation which refers to an ELF
object symbol.  This works because the jump tables are anonymous and
have no symbols associated with them.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 3732710ff6f2 ("objtool: Improve rare switch jump table pattern detection")
Link: http://lkml.kernel.org/r/20170302225723.3ndbsnl4hkqbne7a@treble
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/objtool/builtin-check.c | 15 ++++++++++++---
 tools/objtool/elf.c           | 12 ++++++++++++
 tools/objtool/elf.h           |  1 +
 3 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 4cfdbb5b6967..066086dd59a8 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -805,11 +805,20 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		     insn->jump_dest->offset > orig_insn->offset))
 		    break;
 
+		/* look for a relocation which references .rodata */
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
 						    insn->len);
-		if (text_rela && text_rela->sym == file->rodata->sym)
-			return find_rela_by_dest(file->rodata,
-						 text_rela->addend);
+		if (!text_rela || text_rela->sym != file->rodata->sym)
+			continue;
+
+		/*
+		 * Make sure the .rodata address isn't associated with a
+		 * symbol.  gcc jump tables are anonymous data.
+		 */
+		if (find_symbol_containing(file->rodata, text_rela->addend))
+			continue;
+
+		return find_rela_by_dest(file->rodata, text_rela->addend);
 	}
 
 	return NULL;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 0d7983ac63ef..d897702ce742 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
 	return NULL;
 }
 
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
+{
+	struct symbol *sym;
+
+	list_for_each_entry(sym, &sec->symbol_list, list)
+		if (sym->type != STT_SECTION &&
+		    offset >= sym->offset && offset < sym->offset + sym->len)
+			return sym;
+
+	return NULL;
+}
+
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
 				     unsigned int len)
 {
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index aa1ff6596684..731973e1a3f5 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -79,6 +79,7 @@ struct elf {
 struct elf *elf_open(const char *name);
 struct section *find_section_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
 				     unsigned int len);
-- 
GitLab


From fa3aa7a54fe6d3abf128f13cd4bbd40eaa48fed2 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Tue, 7 Mar 2017 10:55:34 +0100
Subject: [PATCH 761/898] jiffies: Revert bogus conversion of NSEC_PER_SEC to
 TICK_NSEC

commit 93825f2ec736 converted NSEC_PER_SEC to TICK_NSEC because the author
confused NSEC_PER_JIFFY with NSEC_PER_SEC.

As a result, the calculation of refined jiffies got broken, triggering
lockups.

Fixes: 93825f2ec736 ("jiffies: Reuse TICK_NSEC instead of NSEC_PER_JIFFY")
Reported-and-tested-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1488880534-3777-1-git-send-email-fweisbec@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 kernel/time/jiffies.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7906b3f0c41a..497719127bf9 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second)
 	shift_hz += cycles_per_tick/2;
 	do_div(shift_hz, cycles_per_tick);
 	/* Calculate nsec_per_tick using shift_hz */
-	nsec_per_tick = (u64)TICK_NSEC << 8;
+	nsec_per_tick = (u64)NSEC_PER_SEC << 8;
 	nsec_per_tick += (u32)shift_hz/2;
 	do_div(nsec_per_tick, (u32)shift_hz);
 
-- 
GitLab


From 9afd30dbc82a9dbea4101aba57beb2a2a7e1b8d5 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Tue, 28 Feb 2017 18:53:53 +0100
Subject: [PATCH 762/898] libceph: fix crush_decode() for older maps

Older (shorter) CRUSH maps too need to be finalized.

Fixes: 66a0e2d579db ("crush: remove mutable part of CRUSH map")
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/osdmap.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 6824c0ec8373..cc22dd282a3e 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	dout("crush decode tunable chooseleaf_stable = %d\n",
 	     c->chooseleaf_stable);
 
-	crush_finalize(c);
-
 done:
+	crush_finalize(c);
 	dout("crush_decode success\n");
 	return c;
 
-- 
GitLab


From b581a5854eee4b7851dedb0f8c2ceb54fb902c06 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 1 Mar 2017 17:33:27 +0100
Subject: [PATCH 763/898] libceph: don't set weight to IN when OSD is destroyed

Since ceph.git commit 4e28f9e63644 ("osd/OSDMap: clear osd_info,
osd_xinfo on osd deletion"), weight is set to IN when OSD is deleted.
This changes the result of applying an incremental for clients, not
just OSDs.  Because CRUSH computations are obviously affected,
pre-4e28f9e63644 servers disagree with post-4e28f9e63644 clients on
object placement, resulting in misdirected requests.

Mirrors ceph.git commit a6009d1039a55e2c77f431662b3d6cc5a8e8e63f.

Fixes: 930c53286977 ("libceph: apply new_state before new_up_client on incrementals")
Link: http://tracker.ceph.com/issues/19122
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
---
 net/ceph/osdmap.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index cc22dd282a3e..ffe9e904d4d1 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1379,7 +1379,6 @@ static int decode_new_up_state_weight(void **p, void *end,
 		if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
 		    (xorstate & CEPH_OSD_EXISTS)) {
 			pr_info("osd%d does not exist\n", osd);
-			map->osd_weight[osd] = CEPH_OSD_IN;
 			ret = set_primary_affinity(map, osd,
 						   CEPH_OSD_DEFAULT_PRIMARY_AFFINITY);
 			if (ret)
-- 
GitLab


From 8767b293a4ab6632f9288f34bcf2ab9ba20dca3a Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 2 Mar 2017 19:56:57 +0100
Subject: [PATCH 764/898] rbd: supported_features bus attribute

... so that userspace can generate meaningful error messages and spell
out unsupported features that need to be disabled.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
---
 drivers/block/rbd.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4d6807723798..517838b65964 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -120,10 +120,11 @@ static int atomic_dec_return_safe(atomic_t *v)
 
 /* Feature bits */
 
-#define RBD_FEATURE_LAYERING	(1<<0)
-#define RBD_FEATURE_STRIPINGV2	(1<<1)
-#define RBD_FEATURE_EXCLUSIVE_LOCK (1<<2)
-#define RBD_FEATURE_DATA_POOL (1<<7)
+#define RBD_FEATURE_LAYERING		(1ULL<<0)
+#define RBD_FEATURE_STRIPINGV2		(1ULL<<1)
+#define RBD_FEATURE_EXCLUSIVE_LOCK	(1ULL<<2)
+#define RBD_FEATURE_DATA_POOL		(1ULL<<7)
+
 #define RBD_FEATURES_ALL	(RBD_FEATURE_LAYERING |		\
 				 RBD_FEATURE_STRIPINGV2 |	\
 				 RBD_FEATURE_EXCLUSIVE_LOCK |	\
@@ -499,16 +500,23 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
 	return is_lock_owner;
 }
 
+static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf)
+{
+	return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED);
+}
+
 static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
 static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
 static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major);
 static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major);
+static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL);
 
 static struct attribute *rbd_bus_attrs[] = {
 	&bus_attr_add.attr,
 	&bus_attr_remove.attr,
 	&bus_attr_add_single_major.attr,
 	&bus_attr_remove_single_major.attr,
+	&bus_attr_supported_features.attr,
 	NULL,
 };
 
-- 
GitLab


From 7cc5e38f2f0b0b58a22a4c18a56348dd99a71270 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sun, 12 Feb 2017 17:11:07 +0100
Subject: [PATCH 765/898] libceph: osd_request_timeout option

osd_request_timeout specifies how many seconds to wait for a response
from OSDs before returning -ETIMEDOUT from an OSD request.  0 (default)
means no limit.

osd_request_timeout is osdkeepalive-precise -- in-flight requests are
swept through every osdkeepalive seconds.  With ack vs commit behaviour
gone, abort_request() is really simple.

This is based on a patch from Artur Molchanov <artur.molchanov@synesis.ru>.

Tested-by: Artur Molchanov <artur.molchanov@synesis.ru>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
---
 include/linux/ceph/libceph.h    |  2 ++
 include/linux/ceph/osd_client.h |  1 +
 net/ceph/ceph_common.c          | 15 ++++++++++++++
 net/ceph/osd_client.c           | 36 ++++++++++++++++++++++++++++++++-
 4 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 1816c5e26581..88cd5dc8e238 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -48,6 +48,7 @@ struct ceph_options {
 	unsigned long mount_timeout;		/* jiffies */
 	unsigned long osd_idle_ttl;		/* jiffies */
 	unsigned long osd_keepalive_timeout;	/* jiffies */
+	unsigned long osd_request_timeout;	/* jiffies */
 
 	/*
 	 * any type that can't be simply compared or doesn't need need
@@ -68,6 +69,7 @@ struct ceph_options {
 #define CEPH_MOUNT_TIMEOUT_DEFAULT	msecs_to_jiffies(60 * 1000)
 #define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
 #define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
+#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0  /* no timeout */
 
 #define CEPH_MONC_HUNT_INTERVAL		msecs_to_jiffies(3 * 1000)
 #define CEPH_MONC_PING_INTERVAL		msecs_to_jiffies(10 * 1000)
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 2ea0c282f3dc..c125b5d9e13c 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -189,6 +189,7 @@ struct ceph_osd_request {
 
 	/* internal */
 	unsigned long r_stamp;                /* jiffies, send or check time */
+	unsigned long r_start_stamp;          /* jiffies */
 	int r_attempts;
 	struct ceph_eversion r_replay_version; /* aka reassert_version */
 	u32 r_last_force_resend;
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 464e88599b9d..108533859a53 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -230,6 +230,7 @@ enum {
 	Opt_osdkeepalivetimeout,
 	Opt_mount_timeout,
 	Opt_osd_idle_ttl,
+	Opt_osd_request_timeout,
 	Opt_last_int,
 	/* int args above */
 	Opt_fsid,
@@ -256,6 +257,7 @@ static match_table_t opt_tokens = {
 	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
 	{Opt_mount_timeout, "mount_timeout=%d"},
 	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+	{Opt_osd_request_timeout, "osd_request_timeout=%d"},
 	/* int args above */
 	{Opt_fsid, "fsid=%s"},
 	{Opt_name, "name=%s"},
@@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name,
 	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
 	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
+	opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
 
 	/* get mon ip(s) */
 	/* ip1[:port1][,ip2[:port2]...] */
@@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name,
 			}
 			opt->mount_timeout = msecs_to_jiffies(intval * 1000);
 			break;
+		case Opt_osd_request_timeout:
+			/* 0 is "wait forever" (i.e. infinite timeout) */
+			if (intval < 0 || intval > INT_MAX / 1000) {
+				pr_err("osd_request_timeout out of range\n");
+				err = -EINVAL;
+				goto out;
+			}
+			opt->osd_request_timeout = msecs_to_jiffies(intval * 1000);
+			break;
 
 		case Opt_share:
 			opt->flags &= ~CEPH_OPT_NOSHARE;
@@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client)
 	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
 		seq_printf(m, "osdkeepalivetimeout=%d,",
 		    jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000);
+	if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT)
+		seq_printf(m, "osd_request_timeout=%d,",
+			   jiffies_to_msecs(opt->osd_request_timeout) / 1000);
 
 	/* drop redundant comma */
 	if (m->count != pos)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b65bbf9f45eb..e15ea9e4c495 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req)
 
 	req->r_flags |= CEPH_OSD_FLAG_ONDISK;
 	atomic_inc(&req->r_osdc->num_requests);
+
+	req->r_start_stamp = jiffies;
 }
 
 static void submit_request(struct ceph_osd_request *req, bool wrlocked)
@@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req)
 	ceph_osdc_put_request(req);
 }
 
+static void abort_request(struct ceph_osd_request *req, int err)
+{
+	dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);
+
+	cancel_map_check(req);
+	complete_request(req, err);
+}
+
 static void check_pool_dne(struct ceph_osd_request *req)
 {
 	struct ceph_osd_client *osdc = req->r_osdc;
@@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work)
 		container_of(work, struct ceph_osd_client, timeout_work.work);
 	struct ceph_options *opts = osdc->client->options;
 	unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
+	unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout;
 	LIST_HEAD(slow_osds);
 	struct rb_node *n, *p;
 
@@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work)
 		struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
 		bool found = false;
 
-		for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
+		for (p = rb_first(&osd->o_requests); p; ) {
 			struct ceph_osd_request *req =
 			    rb_entry(p, struct ceph_osd_request, r_node);
 
+			p = rb_next(p); /* abort_request() */
+
 			if (time_before(req->r_stamp, cutoff)) {
 				dout(" req %p tid %llu on osd%d is laggy\n",
 				     req, req->r_tid, osd->o_osd);
 				found = true;
 			}
+			if (opts->osd_request_timeout &&
+			    time_before(req->r_start_stamp, expiry_cutoff)) {
+				pr_err_ratelimited("tid %llu on osd%d timeout\n",
+				       req->r_tid, osd->o_osd);
+				abort_request(req, -ETIMEDOUT);
+			}
 		}
 		for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) {
 			struct ceph_osd_linger_request *lreq =
@@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work)
 			list_move_tail(&osd->o_keepalive_item, &slow_osds);
 	}
 
+	if (opts->osd_request_timeout) {
+		for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) {
+			struct ceph_osd_request *req =
+			    rb_entry(p, struct ceph_osd_request, r_node);
+
+			p = rb_next(p); /* abort_request() */
+
+			if (time_before(req->r_start_stamp, expiry_cutoff)) {
+				pr_err_ratelimited("tid %llu on osd%d timeout\n",
+				       req->r_tid, osdc->homeless_osd.o_osd);
+				abort_request(req, -ETIMEDOUT);
+			}
+		}
+	}
+
 	if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
 		maybe_request_map(osdc);
 
-- 
GitLab


From 90922a2d03d84de36bf8a9979d62580102f31a92 Mon Sep 17 00:00:00 2001
From: Shanker Donthineni <shankerd@codeaurora.org>
Date: Tue, 7 Mar 2017 08:20:38 -0600
Subject: [PATCH 766/898] irqchip/gicv3-its: Add workaround for QDF2400 ITS
 erratum 0065

On Qualcomm Datacenter Technologies QDF2400 SoCs, the ITS hardware
implementation uses 16Bytes for Interrupt Translation Entry (ITE),
but reports an incorrect value of 8Bytes in GITS_TYPER.ITTE_size.

It might cause kernel memory corruption depending on the number
of MSI(x) that are configured and the amount of memory that has
been allocated for ITEs in its_create_device().

This patch fixes the potential memory corruption by setting the
correct ITE size to 16Bytes.

Cc: stable@vger.kernel.org
Signed-off-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 Documentation/arm64/silicon-errata.txt |  1 +
 arch/arm64/Kconfig                     | 10 ++++++++++
 drivers/irqchip/irq-gic-v3-its.c       | 16 ++++++++++++++++
 3 files changed, 27 insertions(+)

diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index a71b8095dbd8..2f66683500b8 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -68,3 +68,4 @@ stable kernels.
 |                |                 |                 |                             |
 | Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
+| Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a39029b5414e..8c7c244247b6 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -508,6 +508,16 @@ config QCOM_FALKOR_ERRATUM_1009
 
 	  If unsure, say Y.
 
+config QCOM_QDF2400_ERRATUM_0065
+	bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size"
+	default y
+	help
+	  On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports
+	  ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have
+	  been indicated as 16Bytes (0xf), not 8Bytes (0x7).
+
+	  If unsure, say Y.
+
 endmenu
 
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 23201004fd7a..f77f840d2b5f 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1601,6 +1601,14 @@ static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
 }
 
+static void __maybe_unused its_enable_quirk_qdf2400_e0065(void *data)
+{
+	struct its_node *its = data;
+
+	/* On QDF2400, the size of the ITE is 16Bytes */
+	its->ite_size = 16;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1617,6 +1625,14 @@ static const struct gic_quirk its_quirks[] = {
 		.mask	= 0xffff0fff,
 		.init	= its_enable_quirk_cavium_23144,
 	},
+#endif
+#ifdef CONFIG_QCOM_QDF2400_ERRATUM_0065
+	{
+		.desc	= "ITS: QDF2400 erratum 0065",
+		.iidr	= 0x00001070, /* QDF2400 ITS rev 1.x */
+		.mask	= 0xffffffff,
+		.init	= its_enable_quirk_qdf2400_e0065,
+	},
 #endif
 	{
 	}
-- 
GitLab


From 4b9de5da7e120c7f02395da729f0ec77ce7a6044 Mon Sep 17 00:00:00 2001
From: Franck Demathieu <fdemathieu@gmail.com>
Date: Mon, 6 Mar 2017 14:41:06 +0100
Subject: [PATCH 767/898] irqchip/crossbar: Fix incorrect type of register size

The 'size' variable is unsigned according to the dt-bindings.
As this variable is used as integer in other places, create a new variable
that allows to fix the following sparse issue (-Wtypesign):

  drivers/irqchip/irq-crossbar.c:279:52: warning: incorrect type in argument 3 (different signedness)
  drivers/irqchip/irq-crossbar.c:279:52:    expected unsigned int [usertype] *out_value
  drivers/irqchip/irq-crossbar.c:279:52:    got int *<noident>

Signed-off-by: Franck Demathieu <fdemathieu@gmail.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-crossbar.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 05bbf171df37..1070b7b959f2 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -199,7 +199,7 @@ static const struct irq_domain_ops crossbar_domain_ops = {
 static int __init crossbar_of_init(struct device_node *node)
 {
 	int i, size, reserved = 0;
-	u32 max = 0, entry;
+	u32 max = 0, entry, reg_size;
 	const __be32 *irqsr;
 	int ret = -ENOMEM;
 
@@ -276,9 +276,9 @@ static int __init crossbar_of_init(struct device_node *node)
 	if (!cb->register_offsets)
 		goto err_irq_map;
 
-	of_property_read_u32(node, "ti,reg-size", &size);
+	of_property_read_u32(node, "ti,reg-size", &reg_size);
 
-	switch (size) {
+	switch (reg_size) {
 	case 1:
 		cb->write = crossbar_writeb;
 		break;
@@ -304,7 +304,7 @@ static int __init crossbar_of_init(struct device_node *node)
 			continue;
 
 		cb->register_offsets[i] = reserved;
-		reserved += size;
+		reserved += reg_size;
 	}
 
 	of_property_read_u32(node, "ti,irqs-safe-map", &cb->safe_map);
-- 
GitLab


From 2f707d97982286b307ef2a9b034e19aabc1abb56 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpeng.li@hotmail.com>
Date: Mon, 6 Mar 2017 04:03:28 -0800
Subject: [PATCH 768/898] KVM: nVMX: reset nested_run_pending if the vCPU is
 going to be reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reported by syzkaller:

    WARNING: CPU: 1 PID: 27742 at arch/x86/kvm/vmx.c:11029
    nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
    CPU: 1 PID: 27742 Comm: a.out Not tainted 4.10.0+ #229
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
    Call Trace:
     __dump_stack lib/dump_stack.c:15 [inline]
     dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
     panic+0x1fb/0x412 kernel/panic.c:179
     __warn+0x1c4/0x1e0 kernel/panic.c:540
     warn_slowpath_null+0x2c/0x40 kernel/panic.c:583
     nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
     vmx_leave_nested arch/x86/kvm/vmx.c:11136 [inline]
     vmx_set_msr+0x1565/0x1910 arch/x86/kvm/vmx.c:3324
     kvm_set_msr+0xd4/0x170 arch/x86/kvm/x86.c:1099
     do_set_msr+0x11e/0x190 arch/x86/kvm/x86.c:1128
     __msr_io arch/x86/kvm/x86.c:2577 [inline]
     msr_io+0x24b/0x450 arch/x86/kvm/x86.c:2614
     kvm_arch_vcpu_ioctl+0x35b/0x46a0 arch/x86/kvm/x86.c:3497
     kvm_vcpu_ioctl+0x232/0x1120 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2721
     vfs_ioctl fs/ioctl.c:43 [inline]
     do_vfs_ioctl+0x1bf/0x1790 fs/ioctl.c:683
     SYSC_ioctl fs/ioctl.c:698 [inline]
     SyS_ioctl+0x8f/0xc0 fs/ioctl.c:689
     entry_SYSCALL_64_fastpath+0x1f/0xc2

The syzkaller folks reported a nested_run_pending warning during userspace
clear VMX capability which is exposed to L1 before.

The warning gets thrown while doing

(*(uint32_t*)0x20aecfe8 = (uint32_t)0x1);
(*(uint32_t*)0x20aecfec = (uint32_t)0x0);
(*(uint32_t*)0x20aecff0 = (uint32_t)0x3a);
(*(uint32_t*)0x20aecff4 = (uint32_t)0x0);
(*(uint64_t*)0x20aecff8 = (uint64_t)0x0);
r[29] = syscall(__NR_ioctl, r[4], 0x4008ae89ul,
		0x20aecfe8ul, 0, 0, 0, 0, 0, 0);

i.e. KVM_SET_MSR ioctl with

struct kvm_msrs {
	.nmsrs = 1,
		.pad = 0,
		.entries = {
			{.index = MSR_IA32_FEATURE_CONTROL,
			 .reserved = 0,
			 .data = 0}
		}
}

The VMLANCH/VMRESUME emulation should be stopped since the CPU is going to
reset here. This patch resets the nested_run_pending since the CPU is going
to be reset hence there should be nothing pending.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Suggested-by: Radim Krčmář <rkrcmar@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3b626d6dc3ac..ab338581b3ec 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11107,8 +11107,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
  */
 static void vmx_leave_nested(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu))
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.nested_run_pending = 0;
 		nested_vmx_vmexit(vcpu, -1, 0, 0);
+	}
 	free_nested(to_vmx(vcpu));
 }
 
-- 
GitLab


From 370a0ec1819990f8e2a93df7cc9c0146980ed45f Mon Sep 17 00:00:00 2001
From: Jintack Lim <jintack@cs.columbia.edu>
Date: Mon, 6 Mar 2017 05:42:37 -0800
Subject: [PATCH 769/898] KVM: arm/arm64: Let vcpu thread modify its own active
 state

Currently, if a vcpu thread tries to change the active state of an
interrupt which is already on the same vcpu's AP list, it will loop
forever. Since the VGIC mmio handler is called after a vcpu has
already synced back the LR state to the struct vgic_irq, we can just
let it proceed safely.

Cc: stable@vger.kernel.org
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Jintack Lim <jintack@cs.columbia.edu>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 virt/kvm/arm/vgic/vgic-mmio.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 3654b4c835ef..2a5db1352722 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -180,21 +180,37 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 				    bool new_active_state)
 {
+	struct kvm_vcpu *requester_vcpu;
 	spin_lock(&irq->irq_lock);
+
+	/*
+	 * The vcpu parameter here can mean multiple things depending on how
+	 * this function is called; when handling a trap from the kernel it
+	 * depends on the GIC version, and these functions are also called as
+	 * part of save/restore from userspace.
+	 *
+	 * Therefore, we have to figure out the requester in a reliable way.
+	 *
+	 * When accessing VGIC state from user space, the requester_vcpu is
+	 * NULL, which is fine, because we guarantee that no VCPUs are running
+	 * when accessing VGIC state from user space so irq->vcpu->cpu is
+	 * always -1.
+	 */
+	requester_vcpu = kvm_arm_get_running_vcpu();
+
 	/*
 	 * If this virtual IRQ was written into a list register, we
 	 * have to make sure the CPU that runs the VCPU thread has
-	 * synced back LR state to the struct vgic_irq.  We can only
-	 * know this for sure, when either this irq is not assigned to
-	 * anyone's AP list anymore, or the VCPU thread is not
-	 * running on any CPUs.
+	 * synced back the LR state to the struct vgic_irq.
 	 *
-	 * In the opposite case, we know the VCPU thread may be on its
-	 * way back from the guest and still has to sync back this
-	 * IRQ, so we release and re-acquire the spin_lock to let the
-	 * other thread sync back the IRQ.
+	 * As long as the conditions below are true, we know the VCPU thread
+	 * may be on its way back from the guest (we kicked the VCPU thread in
+	 * vgic_change_active_prepare)  and still has to sync back this IRQ,
+	 * so we release and re-acquire the spin_lock to let the other thread
+	 * sync back the IRQ.
 	 */
 	while (irq->vcpu && /* IRQ may have state in an LR somewhere */
+	       irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */
 	       irq->vcpu->cpu != -1) /* VCPU thread is running */
 		cond_resched_lock(&irq->irq_lock);
 
-- 
GitLab


From f050fe7a9164945dd1c28be05bf00e8cfb082ccf Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 20 Feb 2017 12:30:11 +0000
Subject: [PATCH 770/898] arm: KVM: Survive unknown traps from guests

Currently we BUG() if we see a HSR.EC value we don't recognise. As
configurable disables/enables are added to the architecture (controlled
by RES1/RES0 bits respectively), with associated synchronous exceptions,
it may be possible for a guest to trigger exceptions with classes that
we don't recognise.

While we can't service these exceptions in a manner useful to the guest,
we can avoid bringing down the host. Per ARM DDI 0406C.c, all currently
unallocated HSR EC encodings are reserved, and per ARM DDI
0487A.k_iss10775, page G6-4395, EC values within the range 0x00 - 0x2c
are reserved for future use with synchronous exceptions, and EC values
within the range 0x2d - 0x3f may be used for either synchronous or
asynchronous exceptions.

The patch makes KVM handle any unknown EC by injecting an UNDEFINED
exception into the guest, with a corresponding (ratelimited) warning in
the host dmesg. We could later improve on this with with a new (opt-in)
exit to the host userspace.

Cc: Dave Martin <dave.martin@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_arm.h |  1 +
 arch/arm/kvm/handle_exit.c     | 19 ++++++++++++-------
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index e22089fb44dc..a3f0b3d50089 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -209,6 +209,7 @@
 #define HSR_EC_IABT_HYP	(0x21)
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
+#define HSR_EC_MAX	(0x3f)
 
 #define HSR_WFI_IS_WFE		(_AC(1, UL) << 0)
 
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 4e40d1955e35..96af65a30d78 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -79,7 +79,19 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n",
+		      hsr);
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... HSR_EC_MAX]	= kvm_handle_unknown_ec,
 	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -98,13 +110,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
 	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x\n",
-			(unsigned int)kvm_vcpu_get_hsr(vcpu));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 
-- 
GitLab


From ba4dd156eabdca93501d92a980ba27fa5f4bbd27 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 20 Feb 2017 12:30:12 +0000
Subject: [PATCH 771/898] arm64: KVM: Survive unknown traps from guests

Currently we BUG() if we see an ESR_EL2.EC value we don't recognise. As
configurable disables/enables are added to the architecture (controlled
by RES1/RES0 bits respectively), with associated synchronous exceptions,
it may be possible for a guest to trigger exceptions with classes that
we don't recognise.

While we can't service these exceptions in a manner useful to the guest,
we can avoid bringing down the host. Per ARM DDI 0487A.k_iss10775, page
D7-1937, EC values within the range 0x00 - 0x2c are reserved for future
use with synchronous exceptions, and EC values within the range 0x2d -
0x3f may be used for either synchronous or asynchronous exceptions.

The patch makes KVM handle any unknown EC by injecting an UNDEFINED
exception into the guest, with a corresponding (ratelimited) warning in
the host dmesg. We could later improve on this with with a new (opt-in)
exit to the host userspace.

Cc: Dave Martin <dave.martin@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/kvm/handle_exit.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 1bfe30dfbfe7..fa1b18e364fc 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -135,7 +135,19 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return ret;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
+		      hsr, esr_get_class_string(hsr));
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
 	[ESR_ELx_EC_CP15_32]	= kvm_handle_cp15_32,
 	[ESR_ELx_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -162,13 +174,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	u8 hsr_ec = ESR_ELx_EC(hsr);
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x -- %s\n",
-			hsr, esr_get_class_string(hsr));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 
-- 
GitLab


From a5e1e6ca94a8cec51571fd62e3eaec269717969c Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Thu, 16 Feb 2017 10:41:20 +0000
Subject: [PATCH 772/898] KVM: arm/arm64: VGIC: Fix command handling while ITS
 being disabled

The ITS spec says that ITS commands are only processed when the ITS
is enabled (section 8.19.4, Enabled, bit[0]). Our emulation was not taking
this into account.
Fix this by checking the enabled state before handling CWRITER writes.

On the other hand that means that CWRITER could advance while the ITS
is disabled, and enabling it would need those commands to be processed.
Fix this case as well by refactoring actual command processing and
calling this from both the GITS_CWRITER and GITS_CTLR handlers.

Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 virt/kvm/arm/vgic/vgic-its.c | 109 +++++++++++++++++++++--------------
 1 file changed, 65 insertions(+), 44 deletions(-)

diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 571b64a01c50..8d1da1af4b09 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -360,29 +360,6 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
-					     struct vgic_its *its,
-					     gpa_t addr, unsigned int len)
-{
-	u32 reg = 0;
-
-	mutex_lock(&its->cmd_lock);
-	if (its->creadr == its->cwriter)
-		reg |= GITS_CTLR_QUIESCENT;
-	if (its->enabled)
-		reg |= GITS_CTLR_ENABLE;
-	mutex_unlock(&its->cmd_lock);
-
-	return reg;
-}
-
-static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
-				     gpa_t addr, unsigned int len,
-				     unsigned long val)
-{
-	its->enabled = !!(val & GITS_CTLR_ENABLE);
-}
-
 static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
 					      struct vgic_its *its,
 					      gpa_t addr, unsigned int len)
@@ -1161,33 +1138,16 @@ static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its,
 #define ITS_CMD_SIZE			32
 #define ITS_CMD_OFFSET(reg)		((reg) & GENMASK(19, 5))
 
-/*
- * By writing to CWRITER the guest announces new commands to be processed.
- * To avoid any races in the first place, we take the its_cmd lock, which
- * protects our ring buffer variables, so that there is only one user
- * per ITS handling commands at a given time.
- */
-static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
-					gpa_t addr, unsigned int len,
-					unsigned long val)
+/* Must be called with the cmd_lock held. */
+static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
 {
 	gpa_t cbaser;
 	u64 cmd_buf[4];
-	u32 reg;
 
-	if (!its)
-		return;
-
-	mutex_lock(&its->cmd_lock);
-
-	reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
-	reg = ITS_CMD_OFFSET(reg);
-	if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
-		mutex_unlock(&its->cmd_lock);
+	/* Commands are only processed when the ITS is enabled. */
+	if (!its->enabled)
 		return;
-	}
 
-	its->cwriter = reg;
 	cbaser = CBASER_ADDRESS(its->cbaser);
 
 	while (its->cwriter != its->creadr) {
@@ -1207,6 +1167,34 @@ static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
 		if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser))
 			its->creadr = 0;
 	}
+}
+
+/*
+ * By writing to CWRITER the guest announces new commands to be processed.
+ * To avoid any races in the first place, we take the its_cmd lock, which
+ * protects our ring buffer variables, so that there is only one user
+ * per ITS handling commands at a given time.
+ */
+static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
+					gpa_t addr, unsigned int len,
+					unsigned long val)
+{
+	u64 reg;
+
+	if (!its)
+		return;
+
+	mutex_lock(&its->cmd_lock);
+
+	reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
+	reg = ITS_CMD_OFFSET(reg);
+	if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
+		mutex_unlock(&its->cmd_lock);
+		return;
+	}
+	its->cwriter = reg;
+
+	vgic_its_process_commands(kvm, its);
 
 	mutex_unlock(&its->cmd_lock);
 }
@@ -1287,6 +1275,39 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
 	*regptr = reg;
 }
 
+static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
+					     struct vgic_its *its,
+					     gpa_t addr, unsigned int len)
+{
+	u32 reg = 0;
+
+	mutex_lock(&its->cmd_lock);
+	if (its->creadr == its->cwriter)
+		reg |= GITS_CTLR_QUIESCENT;
+	if (its->enabled)
+		reg |= GITS_CTLR_ENABLE;
+	mutex_unlock(&its->cmd_lock);
+
+	return reg;
+}
+
+static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	mutex_lock(&its->cmd_lock);
+
+	its->enabled = !!(val & GITS_CTLR_ENABLE);
+
+	/*
+	 * Try to process any pending commands. This function bails out early
+	 * if the ITS is disabled or no commands have been queued.
+	 */
+	vgic_its_process_commands(kvm, its);
+
+	mutex_unlock(&its->cmd_lock);
+}
+
 #define REGISTER_ITS_DESC(off, rd, wr, length, acc)		\
 {								\
 	.reg_offset = off,					\
-- 
GitLab


From 8c71fff434e5ecf5ff27bd61db1bc9ac4c2b2a1b Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Mar 2017 06:31:48 -0300
Subject: [PATCH 773/898] [media] v4l: vsp1: Adapt vsp1_du_setup_lif()
 interface to use a structure

The interface to configure the LIF in the VSP1 requires adapting the
function prototype for any changes. This makes extending the interface
difficult.

Change the function prototype to pass a structure which can be easily
extended.

This changes the means of disabling the pipeline, by now passing a NULL
configuration rather than passing either a 0 width or height.

[Fixed kerneldoc, made vsp1_du_setup_lif() cfg argument const]

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
---
 drivers/gpu/drm/rcar-du/rcar_du_vsp.c  |  8 +++++--
 drivers/media/platform/vsp1/vsp1_drm.c | 33 +++++++++++++-------------
 include/media/vsp1.h                   | 13 ++++++++--
 3 files changed, 33 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index 83ebd162f3ef..22da2d671297 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -32,6 +32,10 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
 {
 	const struct drm_display_mode *mode = &crtc->crtc.state->adjusted_mode;
 	struct rcar_du_device *rcdu = crtc->group->dev;
+	struct vsp1_du_lif_config cfg = {
+		.width = mode->hdisplay,
+		.height = mode->vdisplay,
+	};
 	struct rcar_du_plane_state state = {
 		.state = {
 			.crtc = &crtc->crtc,
@@ -66,12 +70,12 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
 	 */
 	crtc->group->need_restart = true;
 
-	vsp1_du_setup_lif(crtc->vsp->vsp, mode->hdisplay, mode->vdisplay);
+	vsp1_du_setup_lif(crtc->vsp->vsp, &cfg);
 }
 
 void rcar_du_vsp_disable(struct rcar_du_crtc *crtc)
 {
-	vsp1_du_setup_lif(crtc->vsp->vsp, 0, 0);
+	vsp1_du_setup_lif(crtc->vsp->vsp, NULL);
 }
 
 void rcar_du_vsp_atomic_begin(struct rcar_du_crtc *crtc)
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index b4b583f7137a..b4c0f10fc3b0 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -54,12 +54,11 @@ EXPORT_SYMBOL_GPL(vsp1_du_init);
 /**
  * vsp1_du_setup_lif - Setup the output part of the VSP pipeline
  * @dev: the VSP device
- * @width: output frame width in pixels
- * @height: output frame height in pixels
+ * @cfg: the LIF configuration
  *
- * Configure the output part of VSP DRM pipeline for the given frame @width and
- * @height. This sets up formats on the BRU source pad, the WPF0 sink and source
- * pads, and the LIF sink pad.
+ * Configure the output part of VSP DRM pipeline for the given frame @cfg.width
+ * and @cfg.height. This sets up formats on the BRU source pad, the WPF0 sink
+ * and source pads, and the LIF sink pad.
  *
  * As the media bus code on the BRU source pad is conditioned by the
  * configuration of the BRU sink 0 pad, we also set up the formats on all BRU
@@ -69,8 +68,7 @@ EXPORT_SYMBOL_GPL(vsp1_du_init);
  *
  * Return 0 on success or a negative error code on failure.
  */
-int vsp1_du_setup_lif(struct device *dev, unsigned int width,
-		      unsigned int height)
+int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg)
 {
 	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
 	struct vsp1_pipeline *pipe = &vsp1->drm->pipe;
@@ -79,11 +77,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	unsigned int i;
 	int ret;
 
-	dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n",
-		__func__, width, height);
-
-	if (width == 0 || height == 0) {
-		/* Zero width or height means the CRTC is being disabled, stop
+	if (!cfg) {
+		/* NULL configuration means the CRTC is being disabled, stop
 		 * the pipeline and turn the light off.
 		 */
 		ret = vsp1_pipeline_stop(pipe);
@@ -108,6 +103,9 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 		return 0;
 	}
 
+	dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n",
+		__func__, cfg->width, cfg->height);
+
 	/* Configure the format at the BRU sinks and propagate it through the
 	 * pipeline.
 	 */
@@ -117,8 +115,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	for (i = 0; i < bru->entity.source_pad; ++i) {
 		format.pad = i;
 
-		format.format.width = width;
-		format.format.height = height;
+		format.format.width = cfg->width;
+		format.format.height = cfg->height;
 		format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
 		format.format.field = V4L2_FIELD_NONE;
 
@@ -133,8 +131,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	}
 
 	format.pad = bru->entity.source_pad;
-	format.format.width = width;
-	format.format.height = height;
+	format.format.width = cfg->width;
+	format.format.height = cfg->height;
 	format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
 	format.format.field = V4L2_FIELD_NONE;
 
@@ -180,7 +178,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
 	/* Verify that the format at the output of the pipeline matches the
 	 * requested frame size and media bus code.
 	 */
-	if (format.format.width != width || format.format.height != height ||
+	if (format.format.width != cfg->width ||
+	    format.format.height != cfg->height ||
 	    format.format.code != MEDIA_BUS_FMT_ARGB8888_1X32) {
 		dev_dbg(vsp1->dev, "%s: format mismatch\n", __func__);
 		return -EPIPE;
diff --git a/include/media/vsp1.h b/include/media/vsp1.h
index 458b400373d4..38aac554dbba 100644
--- a/include/media/vsp1.h
+++ b/include/media/vsp1.h
@@ -20,8 +20,17 @@ struct device;
 
 int vsp1_du_init(struct device *dev);
 
-int vsp1_du_setup_lif(struct device *dev, unsigned int width,
-		      unsigned int height);
+/**
+ * struct vsp1_du_lif_config - VSP LIF configuration
+ * @width: output frame width
+ * @height: output frame height
+ */
+struct vsp1_du_lif_config {
+	unsigned int width;
+	unsigned int height;
+};
+
+int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg);
 
 struct vsp1_du_atomic_config {
 	u32 pixelformat;
-- 
GitLab


From 82f2341c94d270421f383641b7cd670e474db56b Mon Sep 17 00:00:00 2001
From: Alexander Popov <alex.popov@linux.com>
Date: Tue, 28 Feb 2017 19:54:40 +0300
Subject: [PATCH 774/898] tty: n_hdlc: get rid of racy n_hdlc.tbuf

Currently N_HDLC line discipline uses a self-made singly linked list for
data buffers and has n_hdlc.tbuf pointer for buffer retransmitting after
an error.

The commit be10eb7589337e5defbe214dae038a53dd21add8
("tty: n_hdlc add buffer flushing") introduced racy access to n_hdlc.tbuf.
After tx error concurrent flush_tx_queue() and n_hdlc_send_frames() can put
one data buffer to tx_free_buf_list twice. That causes double free in
n_hdlc_release().

Let's use standard kernel linked list and get rid of n_hdlc.tbuf:
in case of tx error put current data buffer after the head of tx_buf_list.

Signed-off-by: Alexander Popov <alex.popov@linux.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_hdlc.c | 132 ++++++++++++++++++++++---------------------
 1 file changed, 69 insertions(+), 63 deletions(-)

diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index 1bacbc3b19a0..e94aea8c0d05 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -114,7 +114,7 @@
 #define DEFAULT_TX_BUF_COUNT 3
 
 struct n_hdlc_buf {
-	struct n_hdlc_buf *link;
+	struct list_head  list_item;
 	int		  count;
 	char		  buf[1];
 };
@@ -122,8 +122,7 @@ struct n_hdlc_buf {
 #define	N_HDLC_BUF_SIZE	(sizeof(struct n_hdlc_buf) + maxframe)
 
 struct n_hdlc_buf_list {
-	struct n_hdlc_buf *head;
-	struct n_hdlc_buf *tail;
+	struct list_head  list;
 	int		  count;
 	spinlock_t	  spinlock;
 };
@@ -136,7 +135,6 @@ struct n_hdlc_buf_list {
  * @backup_tty - TTY to use if tty gets closed
  * @tbusy - reentrancy flag for tx wakeup code
  * @woke_up - FIXME: describe this field
- * @tbuf - currently transmitting tx buffer
  * @tx_buf_list - list of pending transmit frame buffers
  * @rx_buf_list - list of received frame buffers
  * @tx_free_buf_list - list unused transmit frame buffers
@@ -149,7 +147,6 @@ struct n_hdlc {
 	struct tty_struct	*backup_tty;
 	int			tbusy;
 	int			woke_up;
-	struct n_hdlc_buf	*tbuf;
 	struct n_hdlc_buf_list	tx_buf_list;
 	struct n_hdlc_buf_list	rx_buf_list;
 	struct n_hdlc_buf_list	tx_free_buf_list;
@@ -159,6 +156,8 @@ struct n_hdlc {
 /*
  * HDLC buffer list manipulation functions
  */
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+						struct n_hdlc_buf *buf);
 static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
 			   struct n_hdlc_buf *buf);
 static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list);
@@ -208,16 +207,9 @@ static void flush_tx_queue(struct tty_struct *tty)
 {
 	struct n_hdlc *n_hdlc = tty2n_hdlc(tty);
 	struct n_hdlc_buf *buf;
-	unsigned long flags;
 
 	while ((buf = n_hdlc_buf_get(&n_hdlc->tx_buf_list)))
 		n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, buf);
- 	spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock, flags);
-	if (n_hdlc->tbuf) {
-		n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, n_hdlc->tbuf);
-		n_hdlc->tbuf = NULL;
-	}
-	spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
 }
 
 static struct tty_ldisc_ops n_hdlc_ldisc = {
@@ -283,7 +275,6 @@ static void n_hdlc_release(struct n_hdlc *n_hdlc)
 		} else
 			break;
 	}
-	kfree(n_hdlc->tbuf);
 	kfree(n_hdlc);
 	
 }	/* end of n_hdlc_release() */
@@ -402,13 +393,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 	n_hdlc->woke_up = 0;
 	spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
 
-	/* get current transmit buffer or get new transmit */
-	/* buffer from list of pending transmit buffers */
-		
-	tbuf = n_hdlc->tbuf;
-	if (!tbuf)
-		tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
-		
+	tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
 	while (tbuf) {
 		if (debuglevel >= DEBUG_LEVEL_INFO)	
 			printk("%s(%d)sending frame %p, count=%d\n",
@@ -420,7 +405,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 
 		/* rollback was possible and has been done */
 		if (actual == -ERESTARTSYS) {
-			n_hdlc->tbuf = tbuf;
+			n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
 			break;
 		}
 		/* if transmit error, throw frame away by */
@@ -435,10 +420,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 					
 			/* free current transmit buffer */
 			n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, tbuf);
-			
-			/* this tx buffer is done */
-			n_hdlc->tbuf = NULL;
-			
+
 			/* wait up sleeping writers */
 			wake_up_interruptible(&tty->write_wait);
 	
@@ -448,10 +430,12 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 			if (debuglevel >= DEBUG_LEVEL_INFO)	
 				printk("%s(%d)frame %p pending\n",
 					__FILE__,__LINE__,tbuf);
-					
-			/* buffer not accepted by driver */
-			/* set this buffer as pending buffer */
-			n_hdlc->tbuf = tbuf;
+
+			/*
+			 * the buffer was not accepted by driver,
+			 * return it back into tx queue
+			 */
+			n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
 			break;
 		}
 	}
@@ -749,7 +733,8 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 	int error = 0;
 	int count;
 	unsigned long flags;
-	
+	struct n_hdlc_buf *buf = NULL;
+
 	if (debuglevel >= DEBUG_LEVEL_INFO)	
 		printk("%s(%d)n_hdlc_tty_ioctl() called %d\n",
 			__FILE__,__LINE__,cmd);
@@ -763,8 +748,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 		/* report count of read data available */
 		/* in next available frame (if any) */
 		spin_lock_irqsave(&n_hdlc->rx_buf_list.spinlock,flags);
-		if (n_hdlc->rx_buf_list.head)
-			count = n_hdlc->rx_buf_list.head->count;
+		buf = list_first_entry_or_null(&n_hdlc->rx_buf_list.list,
+						struct n_hdlc_buf, list_item);
+		if (buf)
+			count = buf->count;
 		else
 			count = 0;
 		spin_unlock_irqrestore(&n_hdlc->rx_buf_list.spinlock,flags);
@@ -776,8 +763,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 		count = tty_chars_in_buffer(tty);
 		/* add size of next output frame in queue */
 		spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock,flags);
-		if (n_hdlc->tx_buf_list.head)
-			count += n_hdlc->tx_buf_list.head->count;
+		buf = list_first_entry_or_null(&n_hdlc->tx_buf_list.list,
+						struct n_hdlc_buf, list_item);
+		if (buf)
+			count += buf->count;
 		spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock,flags);
 		error = put_user(count, (int __user *)arg);
 		break;
@@ -825,14 +814,14 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp,
 		poll_wait(filp, &tty->write_wait, wait);
 
 		/* set bits for operations that won't block */
-		if (n_hdlc->rx_buf_list.head)
+		if (!list_empty(&n_hdlc->rx_buf_list.list))
 			mask |= POLLIN | POLLRDNORM;	/* readable */
 		if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
 			mask |= POLLHUP;
 		if (tty_hung_up_p(filp))
 			mask |= POLLHUP;
 		if (!tty_is_writelocked(tty) &&
-				n_hdlc->tx_free_buf_list.head)
+				!list_empty(&n_hdlc->tx_free_buf_list.list))
 			mask |= POLLOUT | POLLWRNORM;	/* writable */
 	}
 	return mask;
@@ -856,7 +845,12 @@ static struct n_hdlc *n_hdlc_alloc(void)
 	spin_lock_init(&n_hdlc->tx_free_buf_list.spinlock);
 	spin_lock_init(&n_hdlc->rx_buf_list.spinlock);
 	spin_lock_init(&n_hdlc->tx_buf_list.spinlock);
-	
+
+	INIT_LIST_HEAD(&n_hdlc->rx_free_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->tx_free_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->rx_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->tx_buf_list.list);
+
 	/* allocate free rx buffer list */
 	for(i=0;i<DEFAULT_RX_BUF_COUNT;i++) {
 		buf = kmalloc(N_HDLC_BUF_SIZE, GFP_KERNEL);
@@ -883,54 +877,66 @@ static struct n_hdlc *n_hdlc_alloc(void)
 	
 }	/* end of n_hdlc_alloc() */
 
+/**
+ * n_hdlc_buf_return - put the HDLC buffer after the head of the specified list
+ * @buf_list - pointer to the buffer list
+ * @buf - pointer to the buffer
+ */
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+						struct n_hdlc_buf *buf)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	list_add(&buf->list_item, &buf_list->list);
+	buf_list->count++;
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
+}
+
 /**
  * n_hdlc_buf_put - add specified HDLC buffer to tail of specified list
- * @list - pointer to buffer list
+ * @buf_list - pointer to buffer list
  * @buf	- pointer to buffer
  */
-static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
+static void n_hdlc_buf_put(struct n_hdlc_buf_list *buf_list,
 			   struct n_hdlc_buf *buf)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&list->spinlock,flags);
-	
-	buf->link=NULL;
-	if (list->tail)
-		list->tail->link = buf;
-	else
-		list->head = buf;
-	list->tail = buf;
-	(list->count)++;
-	
-	spin_unlock_irqrestore(&list->spinlock,flags);
-	
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	list_add_tail(&buf->list_item, &buf_list->list);
+	buf_list->count++;
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
 }	/* end of n_hdlc_buf_put() */
 
 /**
  * n_hdlc_buf_get - remove and return an HDLC buffer from list
- * @list - pointer to HDLC buffer list
+ * @buf_list - pointer to HDLC buffer list
  * 
  * Remove and return an HDLC buffer from the head of the specified HDLC buffer
  * list.
  * Returns a pointer to HDLC buffer if available, otherwise %NULL.
  */
-static struct n_hdlc_buf* n_hdlc_buf_get(struct n_hdlc_buf_list *list)
+static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *buf_list)
 {
 	unsigned long flags;
 	struct n_hdlc_buf *buf;
-	spin_lock_irqsave(&list->spinlock,flags);
-	
-	buf = list->head;
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	buf = list_first_entry_or_null(&buf_list->list,
+						struct n_hdlc_buf, list_item);
 	if (buf) {
-		list->head = buf->link;
-		(list->count)--;
+		list_del(&buf->list_item);
+		buf_list->count--;
 	}
-	if (!list->head)
-		list->tail = NULL;
-	
-	spin_unlock_irqrestore(&list->spinlock,flags);
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
 	return buf;
-	
 }	/* end of n_hdlc_buf_get() */
 
 static char hdlc_banner[] __initdata =
-- 
GitLab


From 2eacc79c27eb683c4a3ded80c2629387ee0d4e04 Mon Sep 17 00:00:00 2001
From: Rehas Sachdeva <aquannie@gmail.com>
Date: Sat, 18 Feb 2017 07:31:00 -0500
Subject: [PATCH 775/898] radix tree test suite: Add test for idr_get_next()

Assert that idr_get_next() returns the next populated entry in the tree with
an ID greater than or equal to the value pointed to by @nextid argument.

Signed-off-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/idr-test.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index a26098c6123d..f20690ac3a97 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -153,6 +153,30 @@ void idr_nowait_test(void)
 	idr_destroy(&idr);
 }
 
+void idr_get_next_test(void)
+{
+	unsigned long i;
+	int nextid;
+	DEFINE_IDR(idr);
+
+	int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0};
+
+	for(i = 0; indices[i]; i++) {
+		struct item *item = item_create(indices[i], 0);
+		assert(idr_alloc(&idr, item, indices[i], indices[i+1],
+				 GFP_KERNEL) == indices[i]);
+	}
+
+	for(i = 0, nextid = 0; indices[i]; i++) {
+		idr_get_next(&idr, &nextid);
+		assert(nextid == indices[i]);
+		nextid++;
+	}
+
+	idr_for_each(&idr, item_idr_free, &idr);
+	idr_destroy(&idr);
+}
+
 void idr_checks(void)
 {
 	unsigned long i;
@@ -202,6 +226,7 @@ void idr_checks(void)
 	idr_alloc_test();
 	idr_null_test();
 	idr_nowait_test();
+	idr_get_next_test();
 }
 
 /*
-- 
GitLab


From 166bb1f532fd9fe1b81c6b411ad5d5c9dd21a685 Mon Sep 17 00:00:00 2001
From: Rehas Sachdeva <aquannie@gmail.com>
Date: Mon, 20 Feb 2017 06:40:00 -0500
Subject: [PATCH 776/898] radix tree test suite: Add tests for ida_simple_get()
 and ida_simple_remove()

Assert that ida_simple_get() allocates an id in the passed range or returns
error on failure, and ida_simple_remove() releases an allocated id.

Signed-off-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/idr-test.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index f20690ac3a97..86de901fa5c6 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -387,6 +387,24 @@ void ida_check_random(void)
 		goto repeat;
 }
 
+void ida_simple_get_remove_test(void)
+{
+	DEFINE_IDA(ida);
+	unsigned long i;
+
+	for (i = 0; i < 10000; i++) {
+		assert(ida_simple_get(&ida, 0, 20000, GFP_KERNEL) == i);
+	}
+	assert(ida_simple_get(&ida, 5, 30, GFP_KERNEL) < 0);
+
+	for (i = 0; i < 10000; i++) {
+		ida_simple_remove(&ida, i);
+	}
+	assert(ida_is_empty(&ida));
+
+	ida_destroy(&ida);
+}
+
 void ida_checks(void)
 {
 	DEFINE_IDA(ida);
@@ -453,6 +471,7 @@ void ida_checks(void)
 	ida_check_max();
 	ida_check_conv();
 	ida_check_random();
+	ida_simple_get_remove_test();
 
 	radix_tree_cpu_dead(1);
 }
-- 
GitLab


From c629a344accd15022dd6d87fa28c8e22f978fbda Mon Sep 17 00:00:00 2001
From: Rehas Sachdeva <aquannie@gmail.com>
Date: Sun, 26 Feb 2017 06:33:00 -0500
Subject: [PATCH 777/898] radix tree test suite: Add test for
 radix_tree_clear_tags()

Assert that radix_tree_clear_tags() clears the tags on the passed node and
slot. Assert that the case where the radix tree has only one entry at index
zero and the node is NULL, is also handled.

Signed-off-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/tag_check.c | 29 ++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index d4ff00989245..36dcf7d6945d 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -330,6 +330,34 @@ static void single_check(void)
 	item_kill_tree(&tree);
 }
 
+void radix_tree_clear_tags_test(void)
+{
+	unsigned long index;
+	struct radix_tree_node *node;
+	struct radix_tree_iter iter;
+	void **slot;
+
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert(&tree, 0);
+	item_tag_set(&tree, 0, 0);
+	__radix_tree_lookup(&tree, 0, &node, &slot);
+	radix_tree_clear_tags(&tree, node, slot);
+	assert(item_tag_get(&tree, 0, 0) == 0);
+
+	for (index = 0; index < 1000; index++) {
+		item_insert(&tree, index);
+		item_tag_set(&tree, index, 0);
+	}
+
+	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
+		radix_tree_clear_tags(&tree, iter.node, slot);
+		assert(item_tag_get(&tree, iter.index, 0) == 0);
+	}
+
+	item_kill_tree(&tree);
+}
+
 void tag_check(void)
 {
 	single_check();
@@ -347,4 +375,5 @@ void tag_check(void)
 	thrash_tags();
 	rcu_barrier();
 	printv(2, "after thrash_tags: %d allocated\n", nr_allocated);
+	radix_tree_clear_tags_test();
 }
-- 
GitLab


From 0d4a41c1a0335dc515c6e7fabd447263b57f6457 Mon Sep 17 00:00:00 2001
From: Rehas Sachdeva <aquannie@gmail.com>
Date: Sun, 26 Feb 2017 16:17:00 -0500
Subject: [PATCH 778/898] radix tree test suite: Add performance benchmarks

Add performance benchmarks for radix tree insertion, tagging and deletion.

Signed-off-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/benchmark.c | 82 +++++++++++++++++++++++++---
 1 file changed, 75 insertions(+), 7 deletions(-)

diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 9b09ddfe462f..35741b9c2a4a 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,6 +17,9 @@
 #include <time.h>
 #include "test.h"
 
+#define for_each_index(i, base, order) \
+	        for (i = base; i < base + (1 << order); i++)
+
 #define NSEC_PER_SEC	1000000000L
 
 static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -57,22 +60,87 @@ static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
 	return nsec;
 }
 
+static void benchmark_insert(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		item_insert_order(root, index, order);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
+		size, step, order, nsec);
+}
+
+static void benchmark_tagging(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		radix_tree_tag_set(root, index, 0);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
+		size, step, order, nsec);
+}
+
+static void benchmark_delete(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index, i;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		for_each_index(i, index, order)
+			item_delete(root, i);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
+		size, step, order, nsec);
+}
+
 static void benchmark_size(unsigned long size, unsigned long step, int order)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
 	long long normal, tagged;
-	unsigned long index;
 
-	for (index = 0 ; index < size ; index += step) {
-		item_insert_order(&tree, index, order);
-		radix_tree_tag_set(&tree, index, 0);
-	}
+	benchmark_insert(&tree, size, step, order);
+	benchmark_tagging(&tree, size, step, order);
 
 	tagged = benchmark_iter(&tree, true);
 	normal = benchmark_iter(&tree, false);
 
-	printv(2, "Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n",
-		size, step, order, tagged, normal);
+	printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
+		size, step, order, tagged);
+	printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
+		size, step, order, normal);
+
+	benchmark_delete(&tree, size, step, order);
 
 	item_kill_tree(&tree);
 	rcu_barrier();
-- 
GitLab


From 6478581c85cd3091a6188a2433a8093f335f8f2a Mon Sep 17 00:00:00 2001
From: Rehas Sachdeva <aquannie@gmail.com>
Date: Mon, 27 Feb 2017 07:53:00 -0500
Subject: [PATCH 779/898] radix tree test suite: Add performance test for
 radix_tree_split()

Signed-off-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/benchmark.c | 44 ++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 35741b9c2a4a..b03c3f30c740 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -146,6 +146,46 @@ static void benchmark_size(unsigned long size, unsigned long step, int order)
 	rcu_barrier();
 }
 
+static long long  __benchmark_split(unsigned long index,
+				    int old_order, int new_order)
+{
+	struct timespec start, finish;
+	long long nsec;
+	RADIX_TREE(tree, GFP_ATOMIC);
+
+	item_insert_order(&tree, index, old_order);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	radix_tree_split(&tree, index, new_order);
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	item_kill_tree(&tree);
+
+	return nsec;
+
+}
+
+static void benchmark_split(unsigned long size, unsigned long step)
+{
+	int i, j, idx;
+	long long nsec = 0;
+
+
+	for (idx = 0; idx < size; idx += step) {
+		for (i = 3; i < 11; i++) {
+			for (j = 0; j < i; j++) {
+				nsec += __benchmark_split(idx, i, j);
+			}
+		}
+	}
+
+	printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
+			size, step, nsec);
+
+}
+
 void benchmark(void)
 {
 	unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -163,4 +203,8 @@ void benchmark(void)
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
 			benchmark_size(size[c], step[s] << 9, 9);
+
+	for (c = 0; size[c]; c++)
+		for (s = 0; step[s]; s++)
+			benchmark_split(size[c], step[s]);
 }
-- 
GitLab


From 54f4d3341c8fe31e20915e2c1fb322ff8a069832 Mon Sep 17 00:00:00 2001
From: Rehas Sachdeva <aquannie@gmail.com>
Date: Mon, 27 Feb 2017 08:11:00 -0500
Subject: [PATCH 780/898] radix tree test suite: Add performance test for
 radix_tree_join()

Signed-off-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/benchmark.c | 47 ++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index b03c3f30c740..99c40f3ed133 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -186,6 +186,50 @@ static void benchmark_split(unsigned long size, unsigned long step)
 
 }
 
+static long long  __benchmark_join(unsigned long index,
+			     unsigned order1, unsigned order2)
+{
+	unsigned long loc;
+	struct timespec start, finish;
+	long long nsec;
+	void *item, *item2 = item_create(index + 1, order1);
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert_order(&tree, index, order2);
+	item = radix_tree_lookup(&tree, index);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	radix_tree_join(&tree, index + 1, order1, item2);
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+		(finish.tv_nsec - start.tv_nsec);
+
+	loc = find_item(&tree, item);
+	if (loc == -1)
+		free(item);
+
+	item_kill_tree(&tree);
+
+	return nsec;
+}
+
+static void benchmark_join(unsigned long step)
+{
+	int i, j, idx;
+	long long nsec = 0;
+
+	for (idx = 0; idx < 1 << 10; idx += step) {
+		for (i = 1; i < 15; i++) {
+			for (j = 0; j < i; j++) {
+				nsec += __benchmark_join(idx, i, j);
+			}
+		}
+	}
+
+	printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
+			1 << 10, step, nsec);
+}
+
 void benchmark(void)
 {
 	unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -207,4 +251,7 @@ void benchmark(void)
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
 			benchmark_split(size[c], step[s]);
+
+	for (s = 0; step[s]; s++)
+		benchmark_join(step[s]);
 }
-- 
GitLab


From c4634b08d9eb9c13be2296230bf33c79390dbf9c Mon Sep 17 00:00:00 2001
From: Rehas Sachdeva <aquannie@gmail.com>
Date: Mon, 27 Feb 2017 08:49:00 -0500
Subject: [PATCH 781/898] radix tree test suite: Build 32 bit binaries

Add option 'make BUILD=32' for building 32-bit binaries.

Signed-off-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index f11315bedefc..b59c2a9ef778 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -10,6 +10,10 @@ ifndef SHIFT
 	SHIFT=3
 endif
 
+ifeq ($(BUILD), 32)
+	CFLAGS += -m32
+endif
+
 targets: mapshift $(TARGETS)
 
 main:	$(OFILES)
-- 
GitLab


From 284d96a494d705b9c5330c900e976fceda885b9f Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 2 Mar 2017 04:29:00 -0500
Subject: [PATCH 782/898] radix tree test suite: Fix build with --as-needed

Currently the radix tree test suite doesn't build with toolchains that
use --as-needed by default, for example Ubuntu's:

  cc -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address -lpthread -lurcu main.o ... -o main
  /usr/bin/ld: regression1.o: undefined reference to symbol 'pthread_join@@GLIBC_2.17'
  /lib/powerpc64le-linux-gnu/libpthread.so.0: error adding symbols: DSO missing from command line
  collect2: error: ld returned 1 exit status

This is caused by the custom makefile rules placing LDFLAGS before the
.o files that need the libraries.

We could fix it by using --no-as-needed, or rewriting the custom rules.
But we can also just drop the custom rules and move the libraries to
LDLIBS, and then the default rules work correctly - with the one caveat
that we need to add -fsanitize=address to LDFLAGS because that must be
passed to the linker as well as the compiler.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/Makefile | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index b59c2a9ef778..022488f50fc6 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -1,6 +1,7 @@
 
 CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address
-LDFLAGS += -lpthread -lurcu
+LDFLAGS += -fsanitize=address
+LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder
 CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
@@ -17,13 +18,10 @@ endif
 targets: mapshift $(TARGETS)
 
 main:	$(OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o main
 
 idr-test: idr-test.o $(CORE_OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o idr-test
 
 multiorder: multiorder.o $(CORE_OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o multiorder
 
 clean:
 	$(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h
-- 
GitLab


From 3f1b6f9d49ba5a209d745fa2448657d8b66ed0c0 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <mawilcox@microsoft.com>
Date: Thu, 2 Mar 2017 12:24:28 -0500
Subject: [PATCH 783/898] radix tree test suite: Depend on Makefile and quieten
 grep

Changing the CFLAGS in the Makefile didn't always lead to a
recompilation because the OFILES didn't depend on the Makefile.
Also, after doing make clean, grep would still complain about
a missing map-shift.h; we need -s as well as -q.

Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 022488f50fc6..4c6289c5d415 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -28,7 +28,7 @@ clean:
 
 vpath %.c ../../lib
 
-$(OFILES): *.h */*.h generated/map-shift.h \
+$(OFILES): Makefile *.h */*.h generated/map-shift.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
 	../../../include/linux/radix-tree.h \
@@ -43,7 +43,7 @@ idr.c: ../../../lib/idr.c
 .PHONY: mapshift
 
 mapshift:
-	@if ! grep -qw $(SHIFT) generated/map-shift.h; then		\
+	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
 		echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
 	fi
-- 
GitLab


From 4ecd9542dbc3e07f3bd3870aac12839f72b47db4 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <mawilcox@microsoft.com>
Date: Fri, 3 Mar 2017 12:16:10 -0500
Subject: [PATCH 784/898] ida: Free correct IDA bitmap

There's a relatively rare race where we look at the per-cpu preallocated
IDA bitmap, see it's NULL, allocate a new one, and atomically update it.
If the kmalloc() happened to sleep and we were rescheduled to a different
CPU, or an interrupt came in at the exact right time, another task
might have successfully allocated a bitmap and already deposited it.
I forgot what the semantics of cmpxchg() were and ended up freeing the
wrong bitmap leading to KASAN reporting a use-after-free.

Dmitry found the bug with syzkaller & wrote the patch.  I wrote the test
case that will reproduce the bug without his patch being applied.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 lib/radix-tree.c                    |  4 ++--
 tools/testing/radix-tree/idr-test.c | 34 ++++++++++++++++++++++++++---
 tools/testing/radix-tree/main.c     |  1 +
 tools/testing/radix-tree/test.h     |  1 +
 4 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 5ed506d648c4..691a9ad48497 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -2129,8 +2129,8 @@ int ida_pre_get(struct ida *ida, gfp_t gfp)
 		struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp);
 		if (!bitmap)
 			return 0;
-		bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap);
-		kfree(bitmap);
+		if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap))
+			kfree(bitmap);
 	}
 
 	return 1;
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 86de901fa5c6..30cd0b296f1a 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -363,7 +363,7 @@ void ida_check_random(void)
 {
 	DEFINE_IDA(ida);
 	DECLARE_BITMAP(bitmap, 2048);
-	int id;
+	int id, err;
 	unsigned int i;
 	time_t s = time(NULL);
 
@@ -377,8 +377,11 @@ void ida_check_random(void)
 			ida_remove(&ida, bit);
 		} else {
 			__set_bit(bit, bitmap);
-			ida_pre_get(&ida, GFP_KERNEL);
-			assert(!ida_get_new_above(&ida, bit, &id));
+			do {
+				ida_pre_get(&ida, GFP_KERNEL);
+				err = ida_get_new_above(&ida, bit, &id);
+			} while (err == -ENOMEM);
+			assert(!err);
 			assert(id == bit);
 		}
 	}
@@ -476,11 +479,36 @@ void ida_checks(void)
 	radix_tree_cpu_dead(1);
 }
 
+static void *ida_random_fn(void *arg)
+{
+	rcu_register_thread();
+	ida_check_random();
+	rcu_unregister_thread();
+	return NULL;
+}
+
+void ida_thread_tests(void)
+{
+	pthread_t threads[10];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++)
+		if (pthread_create(&threads[i], NULL, ida_random_fn, NULL)) {
+			perror("creating ida thread");
+			exit(1);
+		}
+
+	while (i--)
+		pthread_join(threads[i], NULL);
+}
+
 int __weak main(void)
 {
 	radix_tree_init();
 	idr_checks();
 	ida_checks();
+	ida_thread_tests();
+	radix_tree_cpu_dead(1);
 	rcu_barrier();
 	if (nr_allocated)
 		printf("nr_allocated = %d\n", nr_allocated);
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index b829127d5670..bc9a78449572 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -368,6 +368,7 @@ int main(int argc, char **argv)
 	iteration_test(0, 10 + 90 * long_run);
 	iteration_test(7, 10 + 90 * long_run);
 	single_thread_tests(long_run);
+	ida_thread_tests();
 
 	/* Free any remaining preallocated nodes */
 	radix_tree_cpu_dead(0);
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index b30e11d9d271..0f8220cc6166 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -36,6 +36,7 @@ void iteration_test(unsigned order, unsigned duration);
 void benchmark(void);
 void idr_checks(void);
 void ida_checks(void);
+void ida_thread_tests(void);
 
 struct item *
 item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);
-- 
GitLab


From f0f3f2d0a3e0f7c48163fd8b45f5909d46e7f371 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <mawilcox@microsoft.com>
Date: Fri, 3 Mar 2017 12:28:37 -0500
Subject: [PATCH 785/898] radix tree test suite: Specify -m32 in LDFLAGS too

Michael's patch to use the default make rule for linking and the patch
from Rehas to use -m32 if building a 32-bit test-suite on a 64-bit
platform don't work well together.

Reported-by: Rehas Sachdeva <aquannie@gmail.com>
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
---
 tools/testing/radix-tree/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 4c6289c5d415..6a9480c03cbd 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -13,6 +13,7 @@ endif
 
 ifeq ($(BUILD), 32)
 	CFLAGS += -m32
+	LDFLAGS += -m32
 endif
 
 targets: mapshift $(TARGETS)
-- 
GitLab


From 544714d8e17c33822319d5a1a00e5ddc4db502b6 Mon Sep 17 00:00:00 2001
From: Jaehoon Chung <jh80.chung@samsung.com>
Date: Tue, 7 Mar 2017 19:54:05 +0900
Subject: [PATCH 786/898] PCI: exynos: Initialize elbi_base even when using PHY
 framework

Even when using the PHY framework, we need the elbi_base.  Before this
patch, we didn't initialize elbi_base, which caused NULL pointer
dereferences later.

Fixes: e7cd7ef58e1f ("PCI: exynos: Support the PHY generic framework")
Signed-off-by: Jaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/dwc/pci-exynos.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/dwc/pci-exynos.c b/drivers/pci/dwc/pci-exynos.c
index 993b650ef275..44f774c12fb2 100644
--- a/drivers/pci/dwc/pci-exynos.c
+++ b/drivers/pci/dwc/pci-exynos.c
@@ -132,10 +132,6 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev,
 	struct device *dev = pci->dev;
 	struct resource *res;
 
-	/* If using the PHY framework, doesn't need to get other resource */
-	if (ep->using_phy)
-		return 0;
-
 	ep->mem_res = devm_kzalloc(dev, sizeof(*ep->mem_res), GFP_KERNEL);
 	if (!ep->mem_res)
 		return -ENOMEM;
@@ -145,6 +141,10 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev,
 	if (IS_ERR(ep->mem_res->elbi_base))
 		return PTR_ERR(ep->mem_res->elbi_base);
 
+	/* If using the PHY framework, doesn't need to get other resource */
+	if (ep->using_phy)
+		return 0;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	ep->mem_res->phy_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(ep->mem_res->phy_base))
-- 
GitLab


From f98c7bce570bdbe344b74ff5daa7dfeef3f22929 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Sat, 25 Feb 2017 18:36:44 +0200
Subject: [PATCH 787/898] serial: samsung: Continue to work if DMA request
 fails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If DMA is not available (even when configured in DeviceTree), the driver
will fail the startup procedure thus making serial console not
available.

For example this causes boot failure on QEMU ARMv7 (Exynos4210, SMDKC210):
    [    1.302575] OF: amba_device_add() failed (-19) for /amba/pdma@12680000
    ...
    [   11.435732] samsung-uart 13800000.serial: DMA request failed
    [   72.963893] samsung-uart 13800000.serial: DMA request failed
    [   73.143361] Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000000

DMA is not necessary for serial to work, so continue with UART startup
after emitting a warning.

Fixes: 62c37eedb74c ("serial: samsung: add dma reqest/release functions")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/samsung.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index b4f86c219db1..7a17aedbf902 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -1031,8 +1031,10 @@ static int s3c64xx_serial_startup(struct uart_port *port)
 	if (ourport->dma) {
 		ret = s3c24xx_serial_request_dma(ourport);
 		if (ret < 0) {
-			dev_warn(port->dev, "DMA request failed\n");
-			return ret;
+			dev_warn(port->dev,
+				 "DMA request failed, DMA will not be used\n");
+			devm_kfree(port->dev, ourport->dma);
+			ourport->dma = NULL;
 		}
 	}
 
-- 
GitLab


From 0d5370d1d85251e5893ab7c90a429464de2e140b Mon Sep 17 00:00:00 2001
From: Ethan Zhao <ethan.zhao@oracle.com>
Date: Mon, 27 Feb 2017 17:08:44 +0900
Subject: [PATCH 788/898] PCI: Prevent VPD access for QLogic ISP2722

QLogic ISP2722-based 16/32Gb Fibre Channel to PCIe Adapter has the VPD
access issue too, while read the common pci-sysfs access interface shown as

 /sys/devices/pci0000:00/0000:00:03.2/0000:0b:00.0/vpd

with simple 'cat' could cause system hang and panic:

  Kernel panic - not syncing: An NMI occurred. Depending on your system the reason for the NMI is logged in any one of the following resources:
  1. Integrated Management Log (IML)
  2. OA Syslog
  3. OA Forward Progress Log
  4. iLO Event Log
  CPU: 0 PID: 15070 Comm: udevadm Not tainted 4.1.12
  Hardware name: HP ProLiant DL380 Gen9/ProLiant DL380 Gen9, BIOS P89 12/27/2015
   0000000000000086 000000007f0cdf51 ffff880c4fa05d58 ffffffff817193de
   ffffffffa00b42d8 0000000000000075 ffff880c4fa05dd8 ffffffff81714072
   0000000000000008 ffff880c4fa05de8 ffff880c4fa05d88 000000007f0cdf51
  Call Trace:
   <NMI>  [<ffffffff817193de>] dump_stack+0x63/0x81
   [<ffffffff81714072>] panic+0xd0/0x20e
   [<ffffffffa00b390d>] hpwdt_pretimeout+0xdd/0xe0 [hpwdt]
   [<ffffffff81021fc9>] ? sched_clock+0x9/0x10
   [<ffffffff8101c101>] nmi_handle+0x91/0x170
   [<ffffffff8101c10c>] ? nmi_handle+0x9c/0x170
   [<ffffffff8101c5fe>] io_check_error+0x1e/0xa0
   [<ffffffff8101c719>] default_do_nmi+0x99/0x140
   [<ffffffff8101c8b4>] do_nmi+0xf4/0x170
   [<ffffffff817232c5>] end_repeat_nmi+0x1a/0x1e
   [<ffffffff815d724b>] ? pci_conf1_read+0xeb/0x120
   [<ffffffff815d724b>] ? pci_conf1_read+0xeb/0x120
   [<ffffffff815d724b>] ? pci_conf1_read+0xeb/0x120
   <<EOE>>  [<ffffffff815db4b3>] raw_pci_read+0x23/0x40
   [<ffffffff815db4fc>] pci_read+0x2c/0x30
   [<ffffffff8136f612>] pci_user_read_config_word+0x72/0x110
   [<ffffffff8136f746>] pci_vpd_pci22_wait+0x96/0x130
   [<ffffffff8136ff9b>] pci_vpd_pci22_read+0xdb/0x1a0
   [<ffffffff8136ea30>] pci_read_vpd+0x20/0x30
   [<ffffffff8137d590>] read_vpd_attr+0x30/0x40
   [<ffffffff8128e037>] sysfs_kf_bin_read+0x47/0x70
   [<ffffffff8128d24e>] kernfs_fop_read+0xae/0x180
   [<ffffffff8120dd97>] __vfs_read+0x37/0x100
   [<ffffffff812ba7e4>] ? security_file_permission+0x84/0xa0
   [<ffffffff8120e366>] ? rw_verify_area+0x56/0xe0
   [<ffffffff8120e476>] vfs_read+0x86/0x140
   [<ffffffff8120f3f5>] SyS_read+0x55/0xd0
   [<ffffffff81720f2e>] system_call_fastpath+0x12/0x71
  Shutting down cpus with NMI
  Kernel Offset: disabled
  drm_kms_helper: panic occurred, switching back to text console

So blacklist the access to its VPD.

Signed-off-by: Ethan Zhao <ethan.zhao@oracle.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: stable@vger.kernel.org	# v4.6+
---
 drivers/pci/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f754453fe754..673683660b5c 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2174,6 +2174,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005d, quirk_blacklist_vpd);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005f, quirk_blacklist_vpd);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, PCI_ANY_ID,
 		quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_QLOGIC, 0x2261, quirk_blacklist_vpd);
 
 /*
  * For Broadcom 5706, 5708, 5709 rev. A nics, any read beyond the
-- 
GitLab


From 3bd7db63a841e8c5297bb18ad801df67d5e38ad2 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Wed, 1 Mar 2017 00:25:40 -0800
Subject: [PATCH 789/898] PCI/ASPM: Always set link->downstream to avoid NULL
 dereference on remove

We call pcie_aspm_exit_link_state() when we remove a device.  If the device
is the last PCIe function to be removed below a bridge and the bridge has
an ASPM link_state struct, we disable ASPM on the link.  Disabling ASPM
requires link->downstream (used in pcie_config_aspm_link()).

We previously set link->downstream in pcie_aspm_cap_init(), but only if the
device was not blacklisted.  Removing the blacklisted device caused a NULL
pointer dereference in the pcie_aspm_exit_link_state() ->
pcie_config_aspm_link() path:

  # echo 1 > /sys/bus/pci/devices/0000\:0b\:00.0/remove
  ...
   BUG: unable to handle kernel NULL pointer dereference at 0000000000000080
   IP: pcie_config_aspm_link+0x5d/0x2b0
   Call Trace:
    pcie_aspm_exit_link_state+0x75/0x130
    pci_stop_bus_device+0xa4/0xb0
    pci_stop_and_remove_bus_device_locked+0x1a/0x30
    remove_store+0x50/0x70
    dev_attr_store+0x18/0x30
    sysfs_kf_write+0x44/0x60
    kernfs_fop_write+0x10e/0x190
    __vfs_write+0x28/0x110
    ? rcu_read_lock_sched_held+0x5d/0x80
    ? rcu_sync_lockdep_assert+0x2c/0x60
    ? __sb_start_write+0x173/0x1a0
    ? vfs_write+0xb3/0x180
    vfs_write+0xc4/0x180
    SyS_write+0x49/0xa0
    do_syscall_64+0xa6/0x1c0
    entry_SYSCALL64_slow_path+0x25/0x25
   ---[ end trace bd187ee0267df5d9 ]---

To avoid this, set link->downstream in alloc_pcie_link_state(), so every
pcie_link_state structure has a valid link->downstream pointer.

[bhelgaas: changelog]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rajat Jain <rajatja@google.com>
CC: stable@vger.kernel.org
---
 drivers/pci/pcie/aspm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 973472c23d89..1dfa10cc566b 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -478,7 +478,7 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 
 static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 {
-	struct pci_dev *child, *parent = link->pdev;
+	struct pci_dev *child = link->downstream, *parent = link->pdev;
 	struct pci_bus *linkbus = parent->subordinate;
 	struct aspm_register_info upreg, dwreg;
 
@@ -491,9 +491,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 	/* Get upstream/downstream components' register state */
 	pcie_get_aspm_reg(parent, &upreg);
-	child = pci_function_0(linkbus);
 	pcie_get_aspm_reg(child, &dwreg);
-	link->downstream = child;
 
 	/*
 	 * If ASPM not supported, don't mess with the clocks and link,
@@ -800,6 +798,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
 	INIT_LIST_HEAD(&link->children);
 	INIT_LIST_HEAD(&link->link);
 	link->pdev = pdev;
+	link->downstream = pci_function_0(pdev->subordinate);
 
 	/*
 	 * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe
-- 
GitLab


From 3802a345321a08093ba2ddb1849e736f84e8d450 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Mar 2017 16:45:58 -0800
Subject: [PATCH 790/898] xfs: only reclaim unwritten COW extents periodically

We only want to reclaim preallocations from our periodic work item.
Currently this is archived by looking for a dirty inode, but that check
is rather fragile.  Instead add a flag to xfs_reflink_cancel_cow_* so
that the caller can ask for just cancelling unwritten extents in the COW
fork.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
[darrick: fix typos in commit message]
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c    |  2 +-
 fs/xfs/xfs_icache.c  |  2 +-
 fs/xfs/xfs_inode.c   |  2 +-
 fs/xfs/xfs_reflink.c | 23 ++++++++++++++++-------
 fs/xfs/xfs_reflink.h |  4 ++--
 fs/xfs/xfs_super.c   |  2 +-
 6 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index bf65a9ea8642..aa8a6f0d09c3 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -293,7 +293,7 @@ xfs_end_io(
 			goto done;
 		if (ioend->io_bio->bi_error) {
 			error = xfs_reflink_cancel_cow_range(ip,
-					ioend->io_offset, ioend->io_size);
+					ioend->io_offset, ioend->io_size, true);
 			goto done;
 		}
 		error = xfs_reflink_end_cow(ip, ioend->io_offset,
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 7234b9748c36..3531f8f72fa5 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1608,7 +1608,7 @@ xfs_inode_free_cowblocks(
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 
-	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index edfa6a55b064..7eaf1ef74e3c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1615,7 +1615,7 @@ xfs_itruncate_extents(
 
 	/* Remove all pending CoW reservations. */
 	error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block,
-			last_block);
+			last_block, true);
 	if (error)
 		goto out;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index da6d08fb359c..4a84c5ea266d 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -548,14 +548,18 @@ xfs_reflink_trim_irec_to_next_cow(
 }
 
 /*
- * Cancel all pending CoW reservations for some block range of an inode.
+ * Cancel CoW reservations for some block range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_blocks(
 	struct xfs_inode		*ip,
 	struct xfs_trans		**tpp,
 	xfs_fileoff_t			offset_fsb,
-	xfs_fileoff_t			end_fsb)
+	xfs_fileoff_t			end_fsb,
+	bool				cancel_real)
 {
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
@@ -579,7 +583,7 @@ xfs_reflink_cancel_cow_blocks(
 					&idx, &got, &del);
 			if (error)
 				break;
-		} else {
+		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
 			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
@@ -621,13 +625,17 @@ xfs_reflink_cancel_cow_blocks(
 }
 
 /*
- * Cancel all pending CoW reservations for some byte range of an inode.
+ * Cancel CoW reservations for some byte range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_range(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		count)
+	xfs_off_t		count,
+	bool			cancel_real)
 {
 	struct xfs_trans	*tp;
 	xfs_fileoff_t		offset_fsb;
@@ -653,7 +661,8 @@ xfs_reflink_cancel_cow_range(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	/* Scrape out the old CoW reservations */
-	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb);
+	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
+			cancel_real);
 	if (error)
 		goto out_cancel;
 
@@ -1450,7 +1459,7 @@ xfs_reflink_clear_inode_flag(
 	 * We didn't find any shared blocks so turn off the reflink flag.
 	 * First, get rid of any leftover CoW mappings.
 	 */
-	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF);
+	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 33ac9b8db683..d29a7967f029 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -39,9 +39,9 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
-		xfs_fileoff_t end_fsb);
+		xfs_fileoff_t end_fsb, bool cancel_real);
 extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
-		xfs_off_t count);
+		xfs_off_t count, bool cancel_real);
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 890862f2447c..685c042a120f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -953,7 +953,7 @@ xfs_fs_destroy_inode(
 	XFS_STATS_INC(ip->i_mount, vn_remove);
 
 	if (xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
 		if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount))
 			xfs_warn(ip->i_mount,
 "Error %d while evicting CoW blocks for inode %llu.",
-- 
GitLab


From 627c845c0907894a1e5cd2d90ff4fc86c9e4458e Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Tue, 7 Mar 2017 04:08:34 -0500
Subject: [PATCH 791/898] drm/i915/gvt: change some gvt_err to gvt_dbg_cmd

gvt_err should be used for dumping error message. This patch changes
some gvt_err to gvt_dbg_cmd, as they are only debugging message, not
errors.

Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/cmd_parser.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 7bb11a555b76..f53cab604d49 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -669,7 +669,7 @@ static inline void print_opcode(u32 cmd, int ring_id)
 	if (d_info == NULL)
 		return;
 
-	gvt_err("opcode=0x%x %s sub_ops:",
+	gvt_dbg_cmd("opcode=0x%x %s sub_ops:",
 			cmd >> (32 - d_info->op_len), d_info->name);
 
 	for (i = 0; i < d_info->nr_sub_op; i++)
@@ -694,23 +694,23 @@ static void parser_exec_state_dump(struct parser_exec_state *s)
 	int cnt = 0;
 	int i;
 
-	gvt_err("  vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)"
+	gvt_dbg_cmd("  vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)"
 			" ring_head(%08lx) ring_tail(%08lx)\n", s->vgpu->id,
 			s->ring_id, s->ring_start, s->ring_start + s->ring_size,
 			s->ring_head, s->ring_tail);
 
-	gvt_err("  %s %s ip_gma(%08lx) ",
+	gvt_dbg_cmd("  %s %s ip_gma(%08lx) ",
 			s->buf_type == RING_BUFFER_INSTRUCTION ?
 			"RING_BUFFER" : "BATCH_BUFFER",
 			s->buf_addr_type == GTT_BUFFER ?
 			"GTT" : "PPGTT", s->ip_gma);
 
 	if (s->ip_va == NULL) {
-		gvt_err(" ip_va(NULL)");
+		gvt_dbg_cmd(" ip_va(NULL)");
 		return;
 	}
 
-	gvt_err("  ip_va=%p: %08x %08x %08x %08x\n",
+	gvt_dbg_cmd("  ip_va=%p: %08x %08x %08x %08x\n",
 			s->ip_va, cmd_val(s, 0), cmd_val(s, 1),
 			cmd_val(s, 2), cmd_val(s, 3));
 
-- 
GitLab


From 787eb485509f9d58962bd8b4dbc6a5ac6e2034fe Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 2 Mar 2017 15:02:51 -0800
Subject: [PATCH 792/898] xfs: fix and streamline error handling in xfs_end_io

There are two different cases of buffered I/O errors:

 - first we can have an already shutdown fs.  In that case we should skip
   any on-disk operations and just clean up the appen transaction if
   present and destroy the ioend
 - a real I/O error.  In that case we should cleanup any lingering COW
   blocks.  This gets skipped in the current code and is fixed by this
   patch.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 59 ++++++++++++++++++++++-------------------------
 1 file changed, 27 insertions(+), 32 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index aa8a6f0d09c3..61494295d92f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -274,54 +274,49 @@ xfs_end_io(
 	struct xfs_ioend	*ioend =
 		container_of(work, struct xfs_ioend, io_work);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	xfs_off_t		offset = ioend->io_offset;
+	size_t			size = ioend->io_size;
 	int			error = ioend->io_bio->bi_error;
 
 	/*
-	 * Set an error if the mount has shut down and proceed with end I/O
-	 * processing so it can perform whatever cleanups are necessary.
+	 * Just clean up the in-memory strutures if the fs has been shut down.
 	 */
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		error = -EIO;
+		goto done;
+	}
 
 	/*
-	 * For a CoW extent, we need to move the mapping from the CoW fork
-	 * to the data fork.  If instead an error happened, just dump the
-	 * new blocks.
+	 * Clean up any COW blocks on an I/O error.
 	 */
-	if (ioend->io_type == XFS_IO_COW) {
-		if (error)
-			goto done;
-		if (ioend->io_bio->bi_error) {
-			error = xfs_reflink_cancel_cow_range(ip,
-					ioend->io_offset, ioend->io_size, true);
-			goto done;
+	if (unlikely(error)) {
+		switch (ioend->io_type) {
+		case XFS_IO_COW:
+			xfs_reflink_cancel_cow_range(ip, offset, size, true);
+			break;
 		}
-		error = xfs_reflink_end_cow(ip, ioend->io_offset,
-				ioend->io_size);
-		if (error)
-			goto done;
+
+		goto done;
 	}
 
 	/*
-	 * For unwritten extents we need to issue transactions to convert a
-	 * range to normal written extens after the data I/O has finished.
-	 * Detecting and handling completion IO errors is done individually
-	 * for each case as different cleanup operations need to be performed
-	 * on error.
+	 * Success:  commit the COW or unwritten blocks if needed.
 	 */
-	if (ioend->io_type == XFS_IO_UNWRITTEN) {
-		if (error)
-			goto done;
-		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
-						  ioend->io_size);
-	} else if (ioend->io_append_trans) {
-		error = xfs_setfilesize_ioend(ioend, error);
-	} else {
-		ASSERT(!xfs_ioend_is_append(ioend) ||
-		       ioend->io_type == XFS_IO_COW);
+	switch (ioend->io_type) {
+	case XFS_IO_COW:
+		error = xfs_reflink_end_cow(ip, offset, size);
+		break;
+	case XFS_IO_UNWRITTEN:
+		error = xfs_iomap_write_unwritten(ip, offset, size);
+		break;
+	default:
+		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
+		break;
 	}
 
 done:
+	if (ioend->io_append_trans)
+		error = xfs_setfilesize_ioend(ioend, error);
 	xfs_destroy_ioend(ioend, error);
 }
 
-- 
GitLab


From d5825712ee98d68a2c17bc89dad2c30276894cba Mon Sep 17 00:00:00 2001
From: Chandan Rajendra <chandan@linux.vnet.ibm.com>
Date: Thu, 2 Mar 2017 15:06:33 -0800
Subject: [PATCH 793/898] xfs: Use xfs_icluster_size_fsb() to calculate inode
 alignment mask

When block size is larger than inode cluster size, the call to
XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size) returns 0. Also, mkfs.xfs
would have set xfs_sb->sb_inoalignmt to 0. Hence in
xfs_set_inoalignment(), xfs_mount->m_inoalign_mask gets initialized to
-1 instead of 0. However, xfs_mount->m_sinoalign would get correctly
intialized to 0 because for every positive value of xfs_mount->m_dalign,
the condition "!(mp->m_dalign & mp->m_inoalign_mask)" would evaluate to
false.

Also, xfs_imap() worked fine even with xfs_mount->m_inoalign_mask having
-1 as the value because blks_per_cluster variable would have the value 1
and hence we would never have a need to use xfs_mount->m_inoalign_mask
to compute the inode chunk's agbno and offset within the chunk.

Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_mount.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 450bde68bb75..688ebff1f663 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -513,8 +513,7 @@ STATIC void
 xfs_set_inoalignment(xfs_mount_t *mp)
 {
 	if (xfs_sb_version_hasalign(&mp->m_sb) &&
-	    mp->m_sb.sb_inoalignmt >=
-	    XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
+		mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp))
 		mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
 	else
 		mp->m_inoalign_mask = 0;
-- 
GitLab


From 08b005f1333154ae5b404ca28766e0ffb9f1c150 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Mon, 6 Mar 2017 11:58:20 -0800
Subject: [PATCH 794/898] xfs: remove kmem_zalloc_greedy

The sole remaining caller of kmem_zalloc_greedy is bulkstat, which uses
it to grab 1-4 pages for staging of inobt records.  The infinite loop in
the greedy allocation function is causing hangs[1] in generic/269, so
just get rid of the greedy allocator in favor of kmem_zalloc_large.
This makes bulkstat somewhat more likely to ENOMEM if there's really no
pages to spare, but eliminates a source of hangs.

[1] http://lkml.kernel.org/r/20170301044634.rgidgdqqiiwsmfpj%40XZHOUW.usersys.redhat.com

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
v2: remove single-page fallback
---
 fs/xfs/kmem.c       | 18 ------------------
 fs/xfs/kmem.h       |  2 --
 fs/xfs/xfs_itable.c |  6 ++----
 3 files changed, 2 insertions(+), 24 deletions(-)

diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 2dfdc62f795e..70a5b55e0870 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -25,24 +25,6 @@
 #include "kmem.h"
 #include "xfs_message.h"
 
-/*
- * Greedy allocation.  May fail and may return vmalloced memory.
- */
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
-{
-	void		*ptr;
-	size_t		kmsize = maxsize;
-
-	while (!(ptr = vzalloc(kmsize))) {
-		if ((kmsize >>= 1) <= minsize)
-			kmsize = minsize;
-	}
-	if (ptr)
-		*size = kmsize;
-	return ptr;
-}
-
 void *
 kmem_alloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 689f746224e7..f0fc84fcaac2 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -69,8 +69,6 @@ static inline void  kmem_free(const void *ptr)
 }
 
 
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
-
 static inline void *
 kmem_zalloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 66e881790c17..2a6d9b1558e0 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -361,7 +361,6 @@ xfs_bulkstat(
 	xfs_agino_t		agino;	/* inode # in allocation group */
 	xfs_agnumber_t		agno;	/* allocation group number */
 	xfs_btree_cur_t		*cur;	/* btree cursor for ialloc btree */
-	size_t			irbsize; /* size of irec buffer in bytes */
 	xfs_inobt_rec_incore_t	*irbuf;	/* start of irec buffer */
 	int			nirbuf;	/* size of irbuf */
 	int			ubcount; /* size of user's buffer */
@@ -388,11 +387,10 @@ xfs_bulkstat(
 	*ubcountp = 0;
 	*done = 0;
 
-	irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
+	irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP);
 	if (!irbuf)
 		return -ENOMEM;
-
-	nirbuf = irbsize / sizeof(*irbuf);
+	nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf);
 
 	/*
 	 * Loop over the allocation groups, starting from the last
-- 
GitLab


From 69eb1596b4df8ca834ba6f9a3df40f78943f6dca Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 17 Feb 2017 15:32:23 +0100
Subject: [PATCH 795/898] staging: octeon: remove unused variable

A cleanup patch left one local variable without a reference:

drivers/staging/octeon/ethernet-rx.c:339:28: warning: unused variable 'priv' [-Wunused-variable]

This removes the declaration too.

Fixes: 66812da3a689 ("staging: octeon: Use net_device_stats from struct net_device")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/octeon/ethernet-rx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c
index 7f8cf875157c..65a285631994 100644
--- a/drivers/staging/octeon/ethernet-rx.c
+++ b/drivers/staging/octeon/ethernet-rx.c
@@ -336,7 +336,6 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
 		if (likely((port < TOTAL_NUMBER_OF_PORTS) &&
 			   cvm_oct_device[port])) {
 			struct net_device *dev = cvm_oct_device[port];
-			struct octeon_ethernet *priv = netdev_priv(dev);
 
 			/*
 			 * Only accept packets for devices that are
-- 
GitLab


From fc69910f329d61821897871e0e957eda39beb3d8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 8 Mar 2017 08:29:31 +0100
Subject: [PATCH 796/898] MIPS: Add missing include files

After the split of linux/sched.h, several platforms in arch/mips stopped building.

Add the respective additional #include statements to fix the problem I first
tried adding these into asm/processor.h, but ran into circular header
dependencies with that which I could not figure out.

The commit I listed as causing the problem is the branch merge, as there is
likely a combination of multiple patches in that branch.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mips@linux-mips.org
Cc: ralf@linux-mips.org
Fixes: 1827adb11ad2 ("Merge branch 'WIP.sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip")
Link: http://lkml.kernel.org/r/20170308072931.3836696-1-arnd@arndb.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/cavium-octeon/cpu.c                  | 2 ++
 arch/mips/cavium-octeon/crypto/octeon-crypto.c | 1 +
 arch/mips/cavium-octeon/smp.c                  | 1 +
 arch/mips/include/asm/fpu.h                    | 1 +
 arch/mips/kernel/smp-bmips.c                   | 1 +
 arch/mips/kernel/smp-mt.c                      | 1 +
 arch/mips/loongson64/loongson-3/cop2-ex.c      | 1 +
 arch/mips/netlogic/common/smp.c                | 1 +
 arch/mips/netlogic/xlp/cop2-ex.c               | 3 +++
 arch/mips/sgi-ip22/ip28-berr.c                 | 1 +
 arch/mips/sgi-ip27/ip27-berr.c                 | 2 ++
 arch/mips/sgi-ip27/ip27-smp.c                  | 3 +++
 arch/mips/sgi-ip32/ip32-berr.c                 | 1 +
 arch/mips/sgi-ip32/ip32-reset.c                | 1 +
 14 files changed, 20 insertions(+)

diff --git a/arch/mips/cavium-octeon/cpu.c b/arch/mips/cavium-octeon/cpu.c
index a5b427909b5c..036d56cc4591 100644
--- a/arch/mips/cavium-octeon/cpu.c
+++ b/arch/mips/cavium-octeon/cpu.c
@@ -10,7 +10,9 @@
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>
diff --git a/arch/mips/cavium-octeon/crypto/octeon-crypto.c b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
index 4d22365844af..cfb4a146cf17 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-crypto.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
@@ -9,6 +9,7 @@
 #include <asm/cop2.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
+#include <linux/sched/task_stack.h>
 
 #include "octeon-crypto.h"
 
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 4b94b7fbafa3..3de786545ded 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -12,6 +12,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/init.h>
 #include <linux/export.h>
 
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 321752bcbab6..f94455f964ec 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/ptrace.h>
 #include <linux/thread_info.h>
 #include <linux/bitops.h>
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 3daa2cae50b0..1b070a76fcdd 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index e077ea3e11fb..e398cbc3d776 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/mips-gic.h>
 #include <linux/compiler.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 
 #include <linux/atomic.h>
diff --git a/arch/mips/loongson64/loongson-3/cop2-ex.c b/arch/mips/loongson64/loongson-3/cop2-ex.c
index ea13764d0a03..621d6af5f6eb 100644
--- a/arch/mips/loongson64/loongson-3/cop2-ex.c
+++ b/arch/mips/loongson64/loongson-3/cop2-ex.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
+#include <linux/ptrace.h>
 
 #include <asm/fpu.h>
 #include <asm/cop2.h>
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 10d86d54880a..bddf1ef553a4 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
 
diff --git a/arch/mips/netlogic/xlp/cop2-ex.c b/arch/mips/netlogic/xlp/cop2-ex.c
index 52bc5de42005..21e439b3db70 100644
--- a/arch/mips/netlogic/xlp/cop2-ex.c
+++ b/arch/mips/netlogic/xlp/cop2-ex.c
@@ -9,11 +9,14 @@
  * Copyright (C) 2009 Wind River Systems,
  *   written by Ralf Baechle <ralf@linux-mips.org>
  */
+#include <linux/capability.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 1f2a5bc4779e..75460e1e106b 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <linux/seq_file.h>
 
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index d12879eb2b1f..83efe03d5c60 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -12,7 +12,9 @@
 #include <linux/signal.h>	/* for SIGBUS */
 #include <linux/sched.h>	/* schow_regs(), force_sig() */
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 
+#include <asm/ptrace.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/sn0/hub.h>
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index f5ed45e8f442..4cd47d23d81a 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -8,10 +8,13 @@
  */
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/topology.h>
 #include <linux/nodemask.h>
+
 #include <asm/page.h>
 #include <asm/processor.h>
+#include <asm/ptrace.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/gda.h>
 #include <asm/sn/intr.h>
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index 57d8c7486fe6..c1f12a9cf305 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 8bd415c8729f..b3b442def423 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/notifier.h>
 #include <linux/delay.h>
 #include <linux/rtc/ds1685.h>
-- 
GitLab


From 35b2719e72d375f3e32c819858165668d948d5f2 Mon Sep 17 00:00:00 2001
From: Felipe Balbi <felipe.balbi@linux.intel.com>
Date: Wed, 8 Mar 2017 13:56:37 +0200
Subject: [PATCH 797/898] usb: dwc3: gadget: make to increment req->remaining
 in all cases

Sometimes, we might get a completion for a TRB which is left with HWO
bit. Even in these cases, we should increment req->remaining to
properly report total transferred size. I noticed this while debuggin
a separate problem seen with MSC tests from USBCV. Sometimes we would
erroneously report a completion for a 512-byte transfer when, in
reality, we transferred 0 bytes.

Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
---
 drivers/usb/dwc3/gadget.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 3db5eeae2bfb..0d75158e43fe 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2189,12 +2189,12 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
 		return 1;
 	}
 
-	if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
-		return 1;
-
 	count = trb->size & DWC3_TRB_SIZE_MASK;
 	req->remaining += count;
 
+	if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
+		return 1;
+
 	if (dep->direction) {
 		if (count) {
 			trb_status = DWC3_TRB_SIZE_TRBSTS(trb->size);
-- 
GitLab


From 0b1d250afb8eb9d65afb568bac9b9f9253a82b49 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 6 Mar 2017 17:36:37 +0100
Subject: [PATCH 798/898] USB: serial: io_ti: fix NULL-deref in interrupt
 callback

Fix a NULL-pointer dereference in the interrupt callback should a
malicious device send data containing a bad port number by adding the
missing sanity check.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/io_ti.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index ceaeebaa6f90..4561dd4cde8b 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -1674,6 +1674,12 @@ static void edge_interrupt_callback(struct urb *urb)
 	function    = TIUMP_GET_FUNC_FROM_CODE(data[0]);
 	dev_dbg(dev, "%s - port_number %d, function %d, info 0x%x\n", __func__,
 		port_number, function, data[1]);
+
+	if (port_number >= edge_serial->serial->num_ports) {
+		dev_err(dev, "bad port number %d\n", port_number);
+		goto exit;
+	}
+
 	port = edge_serial->serial->port[port_number];
 	edge_port = usb_get_serial_port_data(port);
 	if (!edge_port) {
-- 
GitLab


From 30572418b445d85fcfe6c8fe84c947d2606767d8 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 6 Mar 2017 17:36:38 +0100
Subject: [PATCH 799/898] USB: serial: omninet: fix reference leaks at open

This driver needlessly took another reference to the tty on open, a
reference which was then never released on close. This lead to not just
a leak of the tty, but also a driver reference leak that prevented the
driver from being unloaded after a port had once been opened.

Fixes: 4a90f09b20f4 ("tty: usb-serial krefs")
Cc: stable <stable@vger.kernel.org>	# 2.6.28
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/omninet.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c
index a180b17d2432..76564b3bebb9 100644
--- a/drivers/usb/serial/omninet.c
+++ b/drivers/usb/serial/omninet.c
@@ -142,12 +142,6 @@ static int omninet_port_remove(struct usb_serial_port *port)
 
 static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port)
 {
-	struct usb_serial	*serial = port->serial;
-	struct usb_serial_port	*wport;
-
-	wport = serial->port[1];
-	tty_port_tty_set(&wport->port, tty);
-
 	return usb_serial_generic_open(tty, port);
 }
 
-- 
GitLab


From 367ec1706745912702c187722065285cd4d2aee7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 6 Mar 2017 17:36:39 +0100
Subject: [PATCH 800/898] USB: serial: omninet: drop open callback

Remove the now redundant open callback and let core call the generic
handler for us instead.

Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/omninet.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c
index 76564b3bebb9..dd706953b466 100644
--- a/drivers/usb/serial/omninet.c
+++ b/drivers/usb/serial/omninet.c
@@ -31,7 +31,6 @@
 #define BT_IGNITIONPRO_ID	0x2000
 
 /* function prototypes */
-static int  omninet_open(struct tty_struct *tty, struct usb_serial_port *port);
 static void omninet_process_read_urb(struct urb *urb);
 static void omninet_write_bulk_callback(struct urb *urb);
 static int  omninet_write(struct tty_struct *tty, struct usb_serial_port *port,
@@ -60,7 +59,6 @@ static struct usb_serial_driver zyxel_omninet_device = {
 	.attach =		omninet_attach,
 	.port_probe =		omninet_port_probe,
 	.port_remove =		omninet_port_remove,
-	.open =			omninet_open,
 	.write =		omninet_write,
 	.write_room =		omninet_write_room,
 	.write_bulk_callback =	omninet_write_bulk_callback,
@@ -140,11 +138,6 @@ static int omninet_port_remove(struct usb_serial_port *port)
 	return 0;
 }
 
-static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port)
-{
-	return usb_serial_generic_open(tty, port);
-}
-
 #define OMNINET_HEADERLEN	4
 #define OMNINET_BULKOUTSIZE	64
 #define OMNINET_PAYLOADSIZE	(OMNINET_BULKOUTSIZE - OMNINET_HEADERLEN)
-- 
GitLab


From 654b404f2a222f918af9b0cd18ad469d0c941a8e Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 6 Mar 2017 17:36:40 +0100
Subject: [PATCH 801/898] USB: serial: io_ti: fix information leak in
 completion handler

Add missing sanity check to the bulk-in completion handler to avoid an
integer underflow that can be triggered by a malicious device.

This avoids leaking 128 kB of memory content from after the URB transfer
buffer to user space.

Fixes: 8c209e6782ca ("USB: make actual_length in struct urb field u32")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable <stable@vger.kernel.org>	# 2.6.30
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/io_ti.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index 4561dd4cde8b..a76b95d32157 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -1761,7 +1761,7 @@ static void edge_bulk_in_callback(struct urb *urb)
 
 	port_number = edge_port->port->port_number;
 
-	if (edge_port->lsr_event) {
+	if (urb->actual_length > 0 && edge_port->lsr_event) {
 		edge_port->lsr_event = 0;
 		dev_dbg(dev, "%s ===== Port %u LSR Status = %02x, Data = %02x ======\n",
 			__func__, port_number, edge_port->lsr_mask, *data);
-- 
GitLab


From 8c76d7cd520ebffc1ea9ea0850d87a224a50c7f2 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 6 Mar 2017 17:36:41 +0100
Subject: [PATCH 802/898] USB: serial: safe_serial: fix information leak in
 completion handler

Add missing sanity check to the bulk-in completion handler to avoid an
integer underflow that could be triggered by a malicious device.

This avoids leaking up to 56 bytes from after the URB transfer buffer to
user space.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/safe_serial.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c
index 93c6c9b08daa..8a069aa154ed 100644
--- a/drivers/usb/serial/safe_serial.c
+++ b/drivers/usb/serial/safe_serial.c
@@ -200,6 +200,11 @@ static void safe_process_read_urb(struct urb *urb)
 	if (!safe)
 		goto out;
 
+	if (length < 2) {
+		dev_err(&port->dev, "malformed packet\n");
+		return;
+	}
+
 	fcs = fcs_compute10(data, length, CRC10_INITFCS);
 	if (fcs) {
 		dev_err(&port->dev, "%s - bad CRC %x\n", __func__, fcs);
-- 
GitLab


From 99c014a87979c9244806685f3c3fc7767f79f645 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Wed, 8 Mar 2017 10:16:17 -0500
Subject: [PATCH 803/898] ktest: Fix while loop in wait_for_input

The run_command function was changed to use the wait_for_input function to
allow having a timeout if the command to run takes too much time. There was
a bug in the wait_for_input where it could end up going into an infinite
loop. There's two issues here. One is that the return value of the sysread
wasn't used for the write (to write a proper size), and that it should
continue processing the passed in file descriptor too even if there was
input. There was no check for error, if for some reason STDIN returned an
error, the function would go into an infinite loop and never exit.

Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: 6e98d1b4415f ("ktest: Add timeout to ssh command")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/testing/ktest/ktest.pl | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 29470b554711..0c006a2f165d 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1904,11 +1904,12 @@ sub wait_for_input
 
 	# copy data from stdin to the console
 	if (vec($rout, fileno(\*STDIN), 1) == 1) {
-	    sysread(\*STDIN, $buf, 1000);
-	    syswrite($fp, $buf, 1000);
-	    next;
+	    $nr = sysread(\*STDIN, $buf, 1000);
+	    syswrite($fp, $buf, $nr) if ($nr > 0);
 	}
 
+	next if (vec($rout, fileno($fp), 1) != 1);
+
 	$line = "";
 
 	# try to read one char at a time
-- 
GitLab


From f7c6401ff84ab8ffffc281a29aa0a787f7eb346e Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Wed, 8 Mar 2017 10:36:59 -0500
Subject: [PATCH 804/898] ktest: Make sure wait_for_input does honor the
 timeout

The function wait_for_input takes in a timeout, and even has a default
timeout. But if for some reason the STDIN descriptor keeps sending in data,
the function will never time out. The timout is to wait for the data from
the passed in file descriptor, not for STDIN. Adding a test in the case
where there's no data from the passed in file descriptor that checks to see
if the timeout passed, will ensure that it will timeout properly even if
there's input in STDIN.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/testing/ktest/ktest.pl | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 0c006a2f165d..49f7c8b9d9c4 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1880,6 +1880,7 @@ sub get_grub_index {
 sub wait_for_input
 {
     my ($fp, $time) = @_;
+    my $start_time;
     my $rin;
     my $rout;
     my $nr;
@@ -1895,12 +1896,12 @@ sub wait_for_input
     vec($rin, fileno($fp), 1) = 1;
     vec($rin, fileno(\*STDIN), 1) = 1;
 
+    $start_time = time;
+
     while (1) {
 	$nr = select($rout=$rin, undef, undef, $time);
 
-	if ($nr <= 0) {
-	    return undef;
-	}
+	last if ($nr <= 0);
 
 	# copy data from stdin to the console
 	if (vec($rout, fileno(\*STDIN), 1) == 1) {
@@ -1908,7 +1909,11 @@ sub wait_for_input
 	    syswrite($fp, $buf, $nr) if ($nr > 0);
 	}
 
-	next if (vec($rout, fileno($fp), 1) != 1);
+	# The timeout is based on time waiting for the fp data
+	if (vec($rout, fileno($fp), 1) != 1) {
+	    last if (defined($time) && (time - $start_time > $time));
+	    next;
+	}
 
 	$line = "";
 
@@ -1918,12 +1923,11 @@ sub wait_for_input
 	    last if ($ch eq "\n");
 	}
 
-	if (!length($line)) {
-	    return undef;
-	}
+	last if (!length($line));
 
 	return $line;
     }
+    return undef;
 }
 
 sub reboot_to {
-- 
GitLab


From 2501c1bb054290679baad0ff7f4f07c714251f4c Mon Sep 17 00:00:00 2001
From: Chris Brandt <chris.brandt@renesas.com>
Date: Mon, 6 Mar 2017 15:20:51 -0500
Subject: [PATCH 805/898] i2c: riic: fix restart condition

While modifying the driver to use the STOP interrupt, the completion of the
intermediate transfers need to wake the driver back up in order to initiate
the next transfer (restart condition). Otherwise you get never ending
interrupts and only the first transfer sent.

Fixes: 71ccea095ea1 ("i2c: riic: correctly finish transfers")
Reported-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Chris Brandt <chris.brandt@renesas.com>
Tested-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-riic.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c
index 8f11d347b3ec..c811af4c8d81 100644
--- a/drivers/i2c/busses/i2c-riic.c
+++ b/drivers/i2c/busses/i2c-riic.c
@@ -218,8 +218,12 @@ static irqreturn_t riic_tend_isr(int irq, void *data)
 	}
 
 	if (riic->is_last || riic->err) {
-		riic_clear_set_bit(riic, 0, ICIER_SPIE, RIIC_ICIER);
+		riic_clear_set_bit(riic, ICIER_TEIE, ICIER_SPIE, RIIC_ICIER);
 		writeb(ICCR2_SP, riic->base + RIIC_ICCR2);
+	} else {
+		/* Transfer is complete, but do not send STOP */
+		riic_clear_set_bit(riic, ICIER_TEIE, 0, RIIC_ICIER);
+		complete(&riic->msg_done);
 	}
 
 	return IRQ_HANDLED;
-- 
GitLab


From 737f98cfe7de8df7433a4d846850aa8efa44bd48 Mon Sep 17 00:00:00 2001
From: Ming Lei <tom.leiming@gmail.com>
Date: Wed, 22 Feb 2017 18:13:59 +0800
Subject: [PATCH 806/898] blk-mq: initialize mq kobjects in
 blk_mq_init_allocated_queue()

Both q->mq_kobj and sw queues' kobjects should have been initialized
once, instead of doing that each add_disk context.

Also this patch removes clearing of ctx in blk_mq_init_cpu_queues()
because percpu allocator fills zero to allocated variable.

This patch fixes one issue[1] reported from Omar.

[1] kernel wearning when doing unbind/bind on one scsi-mq device

[   19.347924] kobject (ffff8800791ea0b8): tried to init an initialized object, something is seriously wrong.
[   19.349781] CPU: 1 PID: 84 Comm: kworker/u8:1 Not tainted 4.10.0-rc7-00210-g53f39eeaa263 #34
[   19.350686] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-20161122_114906-anatol 04/01/2014
[   19.350920] Workqueue: events_unbound async_run_entry_fn
[   19.350920] Call Trace:
[   19.350920]  dump_stack+0x63/0x83
[   19.350920]  kobject_init+0x77/0x90
[   19.350920]  blk_mq_register_dev+0x40/0x130
[   19.350920]  blk_register_queue+0xb6/0x190
[   19.350920]  device_add_disk+0x1ec/0x4b0
[   19.350920]  sd_probe_async+0x10d/0x1c0 [sd_mod]
[   19.350920]  async_run_entry_fn+0x48/0x150
[   19.350920]  process_one_work+0x1d0/0x480
[   19.350920]  worker_thread+0x48/0x4e0
[   19.350920]  kthread+0x101/0x140
[   19.350920]  ? process_one_work+0x480/0x480
[   19.350920]  ? kthread_create_on_node+0x60/0x60
[   19.350920]  ret_from_fork+0x2c/0x40

Cc: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Tested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq-sysfs.c | 4 +---
 block/blk-mq.c       | 4 +++-
 block/blk-mq.h       | 1 +
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 295e69670c39..124305407c80 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -277,7 +277,7 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
 	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
 }
 
-static void blk_mq_sysfs_init(struct request_queue *q)
+void blk_mq_sysfs_init(struct request_queue *q)
 {
 	struct blk_mq_ctx *ctx;
 	int cpu;
@@ -297,8 +297,6 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
 
 	blk_mq_disable_hotplug();
 
-	blk_mq_sysfs_init(q);
-
 	ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
 	if (ret < 0)
 		goto out;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b2fd175e84d7..ed4b55176cdd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2045,7 +2045,6 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
 		struct blk_mq_hw_ctx *hctx;
 
-		memset(__ctx, 0, sizeof(*__ctx));
 		__ctx->cpu = i;
 		spin_lock_init(&__ctx->lock);
 		INIT_LIST_HEAD(&__ctx->rq_list);
@@ -2352,6 +2351,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	if (!q->queue_ctx)
 		goto err_exit;
 
+	/* init q->mq_kobj and sw queues' kobjects */
+	blk_mq_sysfs_init(q);
+
 	q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)),
 						GFP_KERNEL, set->numa_node);
 	if (!q->queue_hw_ctx)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 088ced003c13..ad8bfd7473ef 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -77,6 +77,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 /*
  * sysfs helpers
  */
+extern void blk_mq_sysfs_init(struct request_queue *q);
 extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
-- 
GitLab


From 7ea5fe31c12dd8bcf4a9c5a4a7e8e23826a9a3b8 Mon Sep 17 00:00:00 2001
From: Ming Lei <tom.leiming@gmail.com>
Date: Wed, 22 Feb 2017 18:14:00 +0800
Subject: [PATCH 807/898] blk-mq: make lifetime consitent between q/ctx and its
 kobject

Currently from kobject view, both q->mq_kobj and ctx->kobj can
be released during one cycle of blk_mq_register_dev() and
blk_mq_unregister_dev(). Actually, sw queue's lifetime is
same with its request queue's, which is covered by request_queue->kobj.

So we don't need to call kobject_put() for the two kinds of
kobject in __blk_mq_unregister_dev(), instead we do that
in release handler of request queue.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Tested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq-sysfs.c | 20 +++++++++++++-------
 block/blk-mq.c       |  7 ++++++-
 block/blk-mq.h       |  1 +
 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 124305407c80..77fb238af2be 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -242,15 +242,11 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-	int i, j;
+	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		blk_mq_unregister_hctx(hctx);
 
-		hctx_for_each_ctx(hctx, ctx, j)
-			kobject_put(&ctx->kobj);
-
 		kobject_put(&hctx->kobj);
 	}
 
@@ -258,8 +254,6 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
-	kobject_put(&q->mq_kobj);
-
 	kobject_put(&dev->kobj);
 
 	q->mq_sysfs_init_done = false;
@@ -277,6 +271,18 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
 	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
 }
 
+void blk_mq_sysfs_deinit(struct request_queue *q)
+{
+	struct blk_mq_ctx *ctx;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		ctx = per_cpu_ptr(q->queue_ctx, cpu);
+		kobject_put(&ctx->kobj);
+	}
+	kobject_put(&q->mq_kobj);
+}
+
 void blk_mq_sysfs_init(struct request_queue *q)
 {
 	struct blk_mq_ctx *ctx;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ed4b55176cdd..b985c236f50f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2264,7 +2264,12 @@ void blk_mq_release(struct request_queue *q)
 
 	kfree(q->queue_hw_ctx);
 
-	/* ctx kobj stays in queue_ctx */
+	/*
+	 * release .mq_kobj and sw queue's kobject now because
+	 * both share lifetime with request queue.
+	 */
+	blk_mq_sysfs_deinit(q);
+
 	free_percpu(q->queue_ctx);
 }
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index ad8bfd7473ef..b79f9a7d8cf6 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -78,6 +78,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
  * sysfs helpers
  */
 extern void blk_mq_sysfs_init(struct request_queue *q);
+extern void blk_mq_sysfs_deinit(struct request_queue *q);
 extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
-- 
GitLab


From 6c8b232efea1ad3d263ff8b9c16b7e8767a77488 Mon Sep 17 00:00:00 2001
From: Ming Lei <tom.leiming@gmail.com>
Date: Wed, 22 Feb 2017 18:14:01 +0800
Subject: [PATCH 808/898] blk-mq: make lifetime consistent between hctx and its
 kobject

This patch removes kobject_put() over hctx in __blk_mq_unregister_dev(),
and trys to keep lifetime consistent between hctx and hctx's kobject.

Now blk_mq_sysfs_register() and blk_mq_sysfs_unregister() become
totally symmetrical, and kobject's refcounter drops to zero just
when the hctx is freed.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Tested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq-sysfs.c | 15 ++++++++++-----
 block/blk-mq.c       |  5 +----
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 77fb238af2be..cb19ec16a7fc 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -17,6 +17,14 @@ static void blk_mq_sysfs_release(struct kobject *kobj)
 {
 }
 
+static void blk_mq_hw_sysfs_release(struct kobject *kobj)
+{
+	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
+						  kobj);
+	kfree(hctx->ctxs);
+	kfree(hctx);
+}
+
 struct blk_mq_ctx_sysfs_entry {
 	struct attribute attr;
 	ssize_t (*show)(struct blk_mq_ctx *, char *);
@@ -200,7 +208,7 @@ static struct kobj_type blk_mq_ctx_ktype = {
 static struct kobj_type blk_mq_hw_ktype = {
 	.sysfs_ops	= &blk_mq_hw_sysfs_ops,
 	.default_attrs	= default_hw_ctx_attrs,
-	.release	= blk_mq_sysfs_release,
+	.release	= blk_mq_hw_sysfs_release,
 };
 
 static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
@@ -244,12 +252,9 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	queue_for_each_hw_ctx(q, hctx, i) {
+	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 
-		kobject_put(&hctx->kobj);
-	}
-
 	blk_mq_debugfs_unregister_hctxs(q);
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b985c236f50f..f70595e5fb86 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2256,8 +2256,7 @@ void blk_mq_release(struct request_queue *q)
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx)
 			continue;
-		kfree(hctx->ctxs);
-		kfree(hctx);
+		kobject_put(&hctx->kobj);
 	}
 
 	q->mq_map = NULL;
@@ -2336,8 +2335,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 			blk_mq_exit_hctx(q, set, hctx, j);
 			free_cpumask_var(hctx->cpumask);
 			kobject_put(&hctx->kobj);
-			kfree(hctx->ctxs);
-			kfree(hctx);
 			hctxs[j] = NULL;
 
 		}
-- 
GitLab


From 01388df37627d2e89f0b835377c0eb39d81f671c Mon Sep 17 00:00:00 2001
From: Ming Lei <tom.leiming@gmail.com>
Date: Wed, 22 Feb 2017 18:14:02 +0800
Subject: [PATCH 809/898] blk-mq: free hctx->cpumask in release handler of
 hctx's kobject

It is obviously that hctx->cpumask is per hctx, and both
share same lifetime, so this patch moves freeing of hctx->cpumask
into release handler of hctx's kobject.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Tested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq-sysfs.c |  1 +
 block/blk-mq.c       | 12 ------------
 2 files changed, 1 insertion(+), 12 deletions(-)

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index cb19ec16a7fc..d745ab81033a 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -21,6 +21,7 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 {
 	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
 						  kobj);
+	free_cpumask_var(hctx->cpumask);
 	kfree(hctx->ctxs);
 	kfree(hctx);
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f70595e5fb86..159187a28d66 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1955,16 +1955,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	}
 }
 
-static void blk_mq_free_hw_queues(struct request_queue *q,
-		struct blk_mq_tag_set *set)
-{
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
-
-	queue_for_each_hw_ctx(q, hctx, i)
-		free_cpumask_var(hctx->cpumask);
-}
-
 static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
@@ -2333,7 +2323,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 			if (hctx->tags)
 				blk_mq_free_map_and_requests(set, j);
 			blk_mq_exit_hctx(q, set, hctx, j);
-			free_cpumask_var(hctx->cpumask);
 			kobject_put(&hctx->kobj);
 			hctxs[j] = NULL;
 
@@ -2446,7 +2435,6 @@ void blk_mq_free_queue(struct request_queue *q)
 	blk_mq_del_queue_tag_set(q);
 
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
-	blk_mq_free_hw_queues(q, set);
 }
 
 /* Basically redo blk_mq_init_queue with queue frozen */
-- 
GitLab


From 0bc315381fe9ed9fb91db8b0e82171b645ac008f Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Mon, 6 Mar 2017 11:23:35 +0100
Subject: [PATCH 810/898] zram: set physical queue limits to avoid array out of
 bounds accesses

zram can handle at most SECTORS_PER_PAGE sectors in a bio's bvec. When using
the NVMe over Fabrics loopback target which potentially sends a huge bulk of
pages attached to the bio's bvec this results in a kernel panic because of
array out of bounds accesses in zram_decompress_page().

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/zram/zram_drv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e27d89a36c34..dceb5edd1e54 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1189,6 +1189,8 @@ static int zram_add(void)
 	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
 	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
 	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
+	zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE;
+	zram->disk->queue->limits.chunk_sectors = 0;
 	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
 	/*
 	 * zram_bio_discard() will clear all logical blocks if logical block
-- 
GitLab


From b0bfdfc2bf7fa85317824c6a389fc373dfcef5bc Mon Sep 17 00:00:00 2001
From: Jon Derrick <jonathan.derrick@intel.com>
Date: Mon, 6 Mar 2017 08:41:04 -0700
Subject: [PATCH 811/898] block/sed: Fix opal user range check and unused
 variables

Fixes check that the opal user is within the range, and cleans up unused
method variables.

Signed-off-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Scott Bauer <scott.bauer@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/sed-opal.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/block/sed-opal.c b/block/sed-opal.c
index 1e18dca360fc..14035f826b5e 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -1023,7 +1023,6 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
 
 static int gen_key(struct opal_dev *dev, void *data)
 {
-	const u8 *method;
 	u8 uid[OPAL_UID_LENGTH];
 	int err = 0;
 
@@ -1031,7 +1030,6 @@ static int gen_key(struct opal_dev *dev, void *data)
 	set_comid(dev, dev->comid);
 
 	memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len));
-	method = opalmethod[OPAL_GENKEY];
 	kfree(dev->prev_data);
 	dev->prev_data = NULL;
 
@@ -1669,7 +1667,6 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 {
 	u8 lr_buffer[OPAL_UID_LENGTH];
-	const u8 *method;
 	struct opal_lock_unlock *lkul = data;
 	u8 read_locked = 1, write_locked = 1;
 	int err = 0;
@@ -1677,7 +1674,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	clear_opal_cmd(dev);
 	set_comid(dev, dev->comid);
 
-	method = opalmethod[OPAL_SET];
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
 		return -ERANGE;
@@ -1733,14 +1729,12 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
 {
 	u8 lr_buffer[OPAL_UID_LENGTH];
 	u8 read_locked = 1, write_locked = 1;
-	const u8 *method;
 	struct opal_lock_unlock *lkul = data;
 	int ret;
 
 	clear_opal_cmd(dev);
 	set_comid(dev, dev->comid);
 
-	method = opalmethod[OPAL_SET];
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
 		return -ERANGE;
@@ -2133,7 +2127,7 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
 		pr_err("Locking state was not RO or RW\n");
 		return -EINVAL;
 	}
-	if (lk_unlk->session.who < OPAL_USER1 &&
+	if (lk_unlk->session.who < OPAL_USER1 ||
 	    lk_unlk->session.who > OPAL_USER9) {
 		pr_err("Authority was not within the range of users: %d\n",
 		       lk_unlk->session.who);
@@ -2316,7 +2310,7 @@ static int opal_activate_user(struct opal_dev *dev,
 	int ret;
 
 	/* We can't activate Admin1 it's active as manufactured */
-	if (opal_session->who < OPAL_USER1 &&
+	if (opal_session->who < OPAL_USER1 ||
 	    opal_session->who > OPAL_USER9) {
 		pr_err("Who was not a valid user: %d\n", opal_session->who);
 		return -EINVAL;
-- 
GitLab


From 02dbfa5e5583523035f05636c614a0eca77f1aab Mon Sep 17 00:00:00 2001
From: Qi Hou <qi.hou@windriver.com>
Date: Fri, 3 Mar 2017 15:57:11 +0800
Subject: [PATCH 812/898] i2c: add missing of_node_put in i2c_mux_del_adapters

Refcount of of_node is increased with of_node_get() in i2c_mux_add_adapter().
It must be decreased with of_node_put() in i2c_mux_del_adapters().

Signe-off-by: Qi Hou <qi.hou@windriver.com>
Reviewed-by: Zhang Xiao <xiao.zhang@windriver.com>
Acked-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-mux.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 83768e85a919..2178266bca79 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -429,6 +429,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 	while (muxc->num_adapters) {
 		struct i2c_adapter *adap = muxc->adapter[--muxc->num_adapters];
 		struct i2c_mux_priv *priv = adap->algo_data;
+		struct device_node *np = adap->dev.of_node;
 
 		muxc->adapter[muxc->num_adapters] = NULL;
 
@@ -438,6 +439,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 
 		sysfs_remove_link(&priv->adap.dev.kobj, "mux_device");
 		i2c_del_adapter(adap);
+		of_node_put(np);
 		kfree(priv);
 	}
 }
-- 
GitLab


From 2de3ec4f1d4ba6ee380478055104eb918bd50cce Mon Sep 17 00:00:00 2001
From: Jaedon Shin <jaedon.shin@gmail.com>
Date: Fri, 3 Mar 2017 10:55:03 +0900
Subject: [PATCH 813/898] i2c: brcmstb: Fix START and STOP conditions

The BSC data buffers to send and receive data are each of size 32 bytes
or 8 bytes 'xfersz' depending on SoC. The problem observed for all the
combined message transfer was if length of data transfer was a multiple
of 'xfersz' a repeated START was being transmitted by BSC driver. Fixed
this by appropriately setting START/STOP conditions for such transfers.

Fixes: dd1aa2524bc5 ("i2c: brcmstb: Add Broadcom settop SoC i2c controller driver")
Signed-off-by: Jaedon Shin <jaedon.shin@gmail.com>
Acked-by: Kamal Dasu <kdasu.kdev@gmail.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-brcmstb.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c
index 0652281662a8..78792b4d6437 100644
--- a/drivers/i2c/busses/i2c-brcmstb.c
+++ b/drivers/i2c/busses/i2c-brcmstb.c
@@ -465,6 +465,7 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 	u8 *tmp_buf;
 	int len = 0;
 	int xfersz = brcmstb_i2c_get_xfersz(dev);
+	u32 cond, cond_per_msg;
 
 	if (dev->is_suspended)
 		return -EBUSY;
@@ -481,10 +482,11 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 			pmsg->buf ? pmsg->buf[0] : '0', pmsg->len);
 
 		if (i < (num - 1) && (msgs[i + 1].flags & I2C_M_NOSTART))
-			brcmstb_set_i2c_start_stop(dev, ~(COND_START_STOP));
+			cond = ~COND_START_STOP;
 		else
-			brcmstb_set_i2c_start_stop(dev,
-						   COND_RESTART | COND_NOSTOP);
+			cond = COND_RESTART | COND_NOSTOP;
+
+		brcmstb_set_i2c_start_stop(dev, cond);
 
 		/* Send slave address */
 		if (!(pmsg->flags & I2C_M_NOSTART)) {
@@ -497,13 +499,24 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 			}
 		}
 
+		cond_per_msg = cond;
+
 		/* Perform data transfer */
 		while (len) {
 			bytes_to_xfer = min(len, xfersz);
 
-			if (len <= xfersz && i == (num - 1))
-				brcmstb_set_i2c_start_stop(dev,
-							   ~(COND_START_STOP));
+			if (len <= xfersz) {
+				if (i == (num - 1))
+					cond_per_msg = cond_per_msg &
+						~(COND_RESTART | COND_NOSTOP);
+				else
+					cond_per_msg = cond;
+			} else {
+				cond_per_msg = (cond_per_msg & ~COND_RESTART) |
+					COND_NOSTOP;
+			}
+
+			brcmstb_set_i2c_start_stop(dev, cond_per_msg);
 
 			rc = brcmstb_i2c_xfer_bsc_data(dev, tmp_buf,
 						       bytes_to_xfer, pmsg);
@@ -512,6 +525,8 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
 
 			len -=  bytes_to_xfer;
 			tmp_buf += bytes_to_xfer;
+
+			cond_per_msg = COND_NOSTART | COND_NOSTOP;
 		}
 	}
 
-- 
GitLab


From 1945250d979203ed326b5a44fd705b6b2c46eec5 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Mon, 27 Feb 2017 20:25:05 +0100
Subject: [PATCH 814/898] i2c: m65xx: drop superfluous quirk structure

All length fields in Linux I2C are u16, so a HW length limitation of 16
bit lengths is not a limitation. Remove the quirk structure.

Tested-by: Jun Gao <jun.gao@mediatek.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-mt65xx.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 4a7d9bc2142b..45d61714c81b 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -172,14 +172,6 @@ static const struct i2c_adapter_quirks mt6577_i2c_quirks = {
 	.max_comb_2nd_msg_len = 31,
 };
 
-static const struct i2c_adapter_quirks mt8173_i2c_quirks = {
-	.max_num_msgs = 65535,
-	.max_write_len = 65535,
-	.max_read_len = 65535,
-	.max_comb_1st_msg_len = 65535,
-	.max_comb_2nd_msg_len = 65535,
-};
-
 static const struct mtk_i2c_compatible mt6577_compat = {
 	.quirks = &mt6577_i2c_quirks,
 	.pmic_i2c = 0,
@@ -199,7 +191,6 @@ static const struct mtk_i2c_compatible mt6589_compat = {
 };
 
 static const struct mtk_i2c_compatible mt8173_compat = {
-	.quirks = &mt8173_i2c_quirks,
 	.pmic_i2c = 0,
 	.dcm = 1,
 	.auto_restart = 1,
-- 
GitLab


From b0c1e95ab44feaad8831f2c06a3473c974003b49 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 28 Feb 2017 11:10:51 -0800
Subject: [PATCH 815/898] i2c: copy device properties when using
 i2c_register_board_info()

This will allow marking device property lists as __initdata, the same as
board info structures themselves.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-boardinfo.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/i2c/i2c-boardinfo.c b/drivers/i2c/i2c-boardinfo.c
index 6e5fac6a5262..5b8f6c3a6950 100644
--- a/drivers/i2c/i2c-boardinfo.c
+++ b/drivers/i2c/i2c-boardinfo.c
@@ -15,6 +15,7 @@
 #include <linux/export.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
+#include <linux/property.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
 
@@ -55,6 +56,7 @@ EXPORT_SYMBOL_GPL(__i2c_first_dynamic_bus_num);
  *
  * The board info passed can safely be __initdata, but be careful of embedded
  * pointers (for platform_data, functions, etc) since that won't be copied.
+ * Device properties are deep-copied though.
  */
 int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned len)
 {
@@ -78,6 +80,14 @@ int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsig
 
 		devinfo->busnum = busnum;
 		devinfo->board_info = *info;
+
+		if (info->properties) {
+			devinfo->board_info.properties =
+					property_entries_dup(info->properties);
+			if (IS_ERR(devinfo->board_info.properties))
+				return PTR_ERR(devinfo->board_info.properties);
+		}
+
 		list_add_tail(&devinfo->list, &__i2c_board_list);
 	}
 
-- 
GitLab


From 3b0277f198ac928f323c42e180680d2f79aa980d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 7 Mar 2017 21:06:38 +0100
Subject: [PATCH 816/898] i2c: meson: fix wrong variable usage in
 meson_i2c_put_data

Most likely a copy & paste error.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Fixes: 30021e3707a7 ("i2c: add support for Amlogic Meson I2C controller")
---
 drivers/i2c/busses/i2c-meson.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c
index 2aa61bbbd307..73b97c71a484 100644
--- a/drivers/i2c/busses/i2c-meson.c
+++ b/drivers/i2c/busses/i2c-meson.c
@@ -175,7 +175,7 @@ static void meson_i2c_put_data(struct meson_i2c *i2c, char *buf, int len)
 		wdata1 |= *buf++ << ((i - 4) * 8);
 
 	writel(wdata0, i2c->regs + REG_TOK_WDATA0);
-	writel(wdata0, i2c->regs + REG_TOK_WDATA1);
+	writel(wdata1, i2c->regs + REG_TOK_WDATA1);
 
 	dev_dbg(i2c->dev, "%s: data %08x %08x len %d\n", __func__,
 		wdata0, wdata1, len);
-- 
GitLab


From ab809fd81fde3d416f8656d8f814a0777fb9b65e Mon Sep 17 00:00:00 2001
From: Zhangfei Gao <zhangfei.gao@linaro.org>
Date: Tue, 27 Dec 2016 22:22:40 +0800
Subject: [PATCH 817/898] i2c: designware: add reset interface

Some platforms like hi3660 need do reset first to allow accessing registers

Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Ramiro Oliveira <ramiro.oliveira@synopsys.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-designware-core.h    |  1 +
 drivers/i2c/busses/i2c-designware-platdrv.c | 28 ++++++++++++++++++---
 2 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h
index c1db3a5a340f..d9aaf1790e0e 100644
--- a/drivers/i2c/busses/i2c-designware-core.h
+++ b/drivers/i2c/busses/i2c-designware-core.h
@@ -88,6 +88,7 @@ struct dw_i2c_dev {
 	void __iomem		*base;
 	struct completion	cmd_complete;
 	struct clk		*clk;
+	struct reset_control	*rst;
 	u32			(*get_clk_rate_khz) (struct dw_i2c_dev *dev);
 	struct dw_pci_controller *controller;
 	int			cmd_err;
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 6ce431323125..79c4b4ea0539 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -38,6 +38,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
 #include <linux/io.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/platform_data/i2c-designware.h>
@@ -199,6 +200,14 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	dev->irq = irq;
 	platform_set_drvdata(pdev, dev);
 
+	dev->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(dev->rst)) {
+		if (PTR_ERR(dev->rst) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+	} else {
+		reset_control_deassert(dev->rst);
+	}
+
 	if (pdata) {
 		dev->clk_freq = pdata->i2c_scl_freq;
 	} else {
@@ -235,12 +244,13 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	    && dev->clk_freq != 1000000 && dev->clk_freq != 3400000) {
 		dev_err(&pdev->dev,
 			"Only 100kHz, 400kHz, 1MHz and 3.4MHz supported");
-		return -EINVAL;
+		r = -EINVAL;
+		goto exit_reset;
 	}
 
 	r = i2c_dw_eval_lock_support(dev);
 	if (r)
-		return r;
+		goto exit_reset;
 
 	dev->functionality = I2C_FUNC_10BIT_ADDR | DW_IC_DEFAULT_FUNCTIONALITY;
 
@@ -286,10 +296,18 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	}
 
 	r = i2c_dw_probe(dev);
-	if (r && !dev->pm_runtime_disabled)
-		pm_runtime_disable(&pdev->dev);
+	if (r)
+		goto exit_probe;
 
 	return r;
+
+exit_probe:
+	if (!dev->pm_runtime_disabled)
+		pm_runtime_disable(&pdev->dev);
+exit_reset:
+	if (!IS_ERR_OR_NULL(dev->rst))
+		reset_control_assert(dev->rst);
+	return r;
 }
 
 static int dw_i2c_plat_remove(struct platform_device *pdev)
@@ -306,6 +324,8 @@ static int dw_i2c_plat_remove(struct platform_device *pdev)
 	pm_runtime_put_sync(&pdev->dev);
 	if (!dev->pm_runtime_disabled)
 		pm_runtime_disable(&pdev->dev);
+	if (!IS_ERR_OR_NULL(dev->rst))
+		reset_control_assert(dev->rst);
 
 	return 0;
 }
-- 
GitLab


From b6f8fec4448aa52a8c36a392aa1ca2ea99acd460 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Mar 2017 17:48:31 +0100
Subject: [PATCH 818/898] block: Allow bdi re-registration

SCSI can call device_add_disk() several times for one request queue when
a device in unbound and bound, creating new gendisk each time. This will
lead to bdi being repeatedly registered and unregistered. This was not a
big problem until commit 165a5e22fafb "block: Move bdi_unregister() to
del_gendisk()" since bdi was only registered repeatedly (bdi_register()
handles repeated calls fine, only we ended up leaking reference to
gendisk due to overwriting bdi->owner) but unregistered only in
blk_cleanup_queue() which didn't get called repeatedly. After
165a5e22fafb we were doing correct bdi_register() - bdi_unregister()
cycles however bdi_unregister() is not prepared for it. So make sure
bdi_unregister() cleans up bdi in such a way that it is prepared for
a possible following bdi_register() call.

An easy way to provoke this behavior is to enable
CONFIG_DEBUG_TEST_DRIVER_REMOVE and use scsi_debug driver to create a
scsi disk which immediately hangs without this fix.

Fixes: 165a5e22fafb127ecb5914e12e8c32a1f0d3f820
Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 mm/backing-dev.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6d861d090e9f..6ac932210f56 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -710,6 +710,11 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
 	 */
 	atomic_dec(&bdi->usage_cnt);
 	wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt));
+	/*
+	 * Grab back our reference so that we hold it when @bdi gets
+	 * re-registered.
+	 */
+	atomic_inc(&bdi->usage_cnt);
 }
 
 /**
@@ -857,6 +862,8 @@ int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner)
 			MINOR(owner->devt));
 	if (rc)
 		return rc;
+	/* Leaking owner reference... */
+	WARN_ON(bdi->owner);
 	bdi->owner = owner;
 	get_device(owner);
 	return 0;
-- 
GitLab


From df23de55615fa7a190a85f49a950ccecdd9102f3 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Mar 2017 17:48:32 +0100
Subject: [PATCH 819/898] bdi: Fix use-after-free in wb_congested_put()

bdi_writeback_congested structures get created for each blkcg and bdi
regardless whether bdi is registered or not. When they are created in
unregistered bdi and the request queue (and thus bdi) is then destroyed
while blkg still holds reference to bdi_writeback_congested structure,
this structure will be referencing freed bdi and last wb_congested_put()
will try to remove the structure from already freed bdi.

With commit 165a5e22fafb "block: Move bdi_unregister() to
del_gendisk()", SCSI started to destroy bdis without calling
bdi_unregister() first (previously it was calling bdi_unregister() even
for unregistered bdis) and thus the code detaching
bdi_writeback_congested in cgwb_bdi_destroy() was not triggered and we
started hitting this use-after-free bug. It is enough to boot a KVM
instance with virtio-scsi device to trigger this behavior.

Fix the problem by detaching bdi_writeback_congested structures in
bdi_exit() instead of bdi_unregister(). This is also more logical as
they can get attached to bdi regardless whether it ever got registered
or not.

Fixes: 165a5e22fafb127ecb5914e12e8c32a1f0d3f820
Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 mm/backing-dev.c | 36 +++++++++++++++++++++---------------
 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6ac932210f56..c6f2a37028c2 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -683,30 +683,18 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
 {
 	struct radix_tree_iter iter;
-	struct rb_node *rbn;
 	void **slot;
 
 	WARN_ON(test_bit(WB_registered, &bdi->wb.state));
 
 	spin_lock_irq(&cgwb_lock);
-
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
-
-	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
-		struct bdi_writeback_congested *congested =
-			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
-
-		rb_erase(rbn, &bdi->cgwb_congested_tree);
-		congested->bdi = NULL;	/* mark @congested unlinked */
-	}
-
 	spin_unlock_irq(&cgwb_lock);
 
 	/*
-	 * All cgwb's and their congested states must be shutdown and
-	 * released before returning.  Drain the usage counter to wait for
-	 * all cgwb's and cgwb_congested's ever created on @bdi.
+	 * All cgwb's must be shutdown and released before returning.  Drain
+	 * the usage counter to wait for all cgwb's ever created on @bdi.
 	 */
 	atomic_dec(&bdi->usage_cnt);
 	wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt));
@@ -754,6 +742,21 @@ void wb_blkcg_offline(struct blkcg *blkcg)
 	spin_unlock_irq(&cgwb_lock);
 }
 
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
+{
+	struct rb_node *rbn;
+
+	spin_lock_irq(&cgwb_lock);
+	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
+		struct bdi_writeback_congested *congested =
+			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
+
+		rb_erase(rbn, &bdi->cgwb_congested_tree);
+		congested->bdi = NULL;	/* mark @congested unlinked */
+	}
+	spin_unlock_irq(&cgwb_lock);
+}
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static int cgwb_bdi_init(struct backing_dev_info *bdi)
@@ -774,7 +777,9 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	return 0;
 }
 
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
+
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
 {
 	wb_congested_put(bdi->wb_congested);
 }
@@ -905,6 +910,7 @@ static void bdi_exit(struct backing_dev_info *bdi)
 {
 	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
+	cgwb_bdi_exit(bdi);
 }
 
 static void release_bdi(struct kref *ref)
-- 
GitLab


From 90f16fddcc2802726142b8386c65ccb89f044613 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Mar 2017 17:48:33 +0100
Subject: [PATCH 820/898] block: Make del_gendisk() safer for disks without
 queues

Commit 165a5e22fafb "block: Move bdi_unregister() to del_gendisk()"
added disk->queue dereference to del_gendisk(). Although del_gendisk()
is not supposed to be called without disk->queue valid and
blk_unregister_queue() warns in that case, this change will make it oops
instead. Return to the old more robust behavior of just warning when
del_gendisk() gets called for gendisk with disk->queue being NULL.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/genhd.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index b26a5ea115d0..94f323842b52 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -681,12 +681,16 @@ void del_gendisk(struct gendisk *disk)
 	disk->flags &= ~GENHD_FL_UP;
 
 	sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
-	/*
-	 * Unregister bdi before releasing device numbers (as they can get
-	 * reused and we'd get clashes in sysfs).
-	 */
-	bdi_unregister(disk->queue->backing_dev_info);
-	blk_unregister_queue(disk);
+	if (disk->queue) {
+		/*
+		 * Unregister bdi before releasing device numbers (as they can
+		 * get reused and we'd get clashes in sysfs).
+		 */
+		bdi_unregister(disk->queue->backing_dev_info);
+		blk_unregister_queue(disk);
+	} else {
+		WARN_ON(1);
+	}
 	blk_unregister_region(disk_devt(disk), disk->minors);
 
 	part_stat_set_all(&disk->part0, 0);
-- 
GitLab


From c01228db4ba965986511a5b28c478bddd7e2726e Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Mar 2017 17:48:34 +0100
Subject: [PATCH 821/898] Revert "scsi, block: fix duplicate bdi name
 registration crashes"

This reverts commit 0dba1314d4f81115dce711292ec7981d17231064. It causes
leaking of device numbers for SCSI when SCSI registers multiple gendisks
for one request_queue in succession. It can be easily reproduced using
Omar's script [1] on kernel with CONFIG_DEBUG_TEST_DRIVER_REMOVE.
Furthermore the protection provided by this commit is not needed anymore
as the problem it was fixing got also fixed by commit 165a5e22fafb
"block: Move bdi_unregister() to del_gendisk()".

[1]: http://marc.info/?l=linux-block&m=148554717109098&w=2

Signed-off-by: Jan Kara <jack@suse.cz>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       |  2 --
 block/genhd.c          | 21 ---------------------
 drivers/scsi/sd.c      | 41 ++++++++---------------------------------
 include/linux/blkdev.h |  1 -
 include/linux/genhd.h  |  8 --------
 5 files changed, 8 insertions(+), 65 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 1086dac8724c..a76895c9776d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -578,8 +578,6 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
-	put_disk_devt(q->disk_devt);
-
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }
diff --git a/block/genhd.c b/block/genhd.c
index 94f323842b52..a9c516a8b37d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -572,20 +572,6 @@ static void register_disk(struct device *parent, struct gendisk *disk)
 	disk_part_iter_exit(&piter);
 }
 
-void put_disk_devt(struct disk_devt *disk_devt)
-{
-	if (disk_devt && atomic_dec_and_test(&disk_devt->count))
-		disk_devt->release(disk_devt);
-}
-EXPORT_SYMBOL(put_disk_devt);
-
-void get_disk_devt(struct disk_devt *disk_devt)
-{
-	if (disk_devt)
-		atomic_inc(&disk_devt->count);
-}
-EXPORT_SYMBOL(get_disk_devt);
-
 /**
  * device_add_disk - add partitioning information to kernel list
  * @parent: parent device for the disk
@@ -626,13 +612,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 
 	disk_alloc_events(disk);
 
-	/*
-	 * Take a reference on the devt and assign it to queue since it
-	 * must not be reallocated while the bdi is registered
-	 */
-	disk->queue->disk_devt = disk->disk_devt;
-	get_disk_devt(disk->disk_devt);
-
 	/* Register BDI before referencing it from bdev */
 	bdi = disk->queue->backing_dev_info;
 	bdi_register_owner(bdi, disk_to_dev(disk));
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c7839f6c35cc..d277e8620e3e 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3075,23 +3075,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 	put_device(&sdkp->dev);
 }
 
-struct sd_devt {
-	int idx;
-	struct disk_devt disk_devt;
-};
-
-static void sd_devt_release(struct disk_devt *disk_devt)
-{
-	struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt,
-			disk_devt);
-
-	spin_lock(&sd_index_lock);
-	ida_remove(&sd_index_ida, sd_devt->idx);
-	spin_unlock(&sd_index_lock);
-
-	kfree(sd_devt);
-}
-
 /**
  *	sd_probe - called during driver initialization and whenever a
  *	new scsi device is attached to the system. It is called once
@@ -3113,7 +3096,6 @@ static void sd_devt_release(struct disk_devt *disk_devt)
 static int sd_probe(struct device *dev)
 {
 	struct scsi_device *sdp = to_scsi_device(dev);
-	struct sd_devt *sd_devt;
 	struct scsi_disk *sdkp;
 	struct gendisk *gd;
 	int index;
@@ -3139,13 +3121,9 @@ static int sd_probe(struct device *dev)
 	if (!sdkp)
 		goto out;
 
-	sd_devt = kzalloc(sizeof(*sd_devt), GFP_KERNEL);
-	if (!sd_devt)
-		goto out_free;
-
 	gd = alloc_disk(SD_MINORS);
 	if (!gd)
-		goto out_free_devt;
+		goto out_free;
 
 	do {
 		if (!ida_pre_get(&sd_index_ida, GFP_KERNEL))
@@ -3161,11 +3139,6 @@ static int sd_probe(struct device *dev)
 		goto out_put;
 	}
 
-	atomic_set(&sd_devt->disk_devt.count, 1);
-	sd_devt->disk_devt.release = sd_devt_release;
-	sd_devt->idx = index;
-	gd->disk_devt = &sd_devt->disk_devt;
-
 	error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN);
 	if (error) {
 		sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n");
@@ -3205,12 +3178,11 @@ static int sd_probe(struct device *dev)
 	return 0;
 
  out_free_index:
-	put_disk_devt(&sd_devt->disk_devt);
-	sd_devt = NULL;
+	spin_lock(&sd_index_lock);
+	ida_remove(&sd_index_ida, index);
+	spin_unlock(&sd_index_lock);
  out_put:
 	put_disk(gd);
- out_free_devt:
-	kfree(sd_devt);
  out_free:
 	kfree(sdkp);
  out:
@@ -3271,7 +3243,10 @@ static void scsi_disk_release(struct device *dev)
 	struct scsi_disk *sdkp = to_scsi_disk(dev);
 	struct gendisk *disk = sdkp->disk;
 	
-	put_disk_devt(disk->disk_devt);
+	spin_lock(&sd_index_lock);
+	ida_remove(&sd_index_ida, sdkp->index);
+	spin_unlock(&sd_index_lock);
+
 	disk->private_data = NULL;
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 796016e63c1d..5a7da607ca04 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -435,7 +435,6 @@ struct request_queue {
 	struct delayed_work	delay_work;
 
 	struct backing_dev_info	*backing_dev_info;
-	struct disk_devt	*disk_devt;
 
 	/*
 	 * The queue owner gets to use this for whatever they like.
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index a999d281a2f1..76f39754e7b0 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -167,13 +167,6 @@ struct blk_integrity {
 };
 
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
-struct disk_devt {
-	atomic_t count;
-	void (*release)(struct disk_devt *disk_devt);
-};
-
-void put_disk_devt(struct disk_devt *disk_devt);
-void get_disk_devt(struct disk_devt *disk_devt);
 
 struct gendisk {
 	/* major, first_minor and minors are input parameters only,
@@ -183,7 +176,6 @@ struct gendisk {
 	int first_minor;
 	int minors;                     /* maximum number of minors, =1 for
                                          * disks that can't be partitioned. */
-	struct disk_devt *disk_devt;
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 	char *(*devnode)(struct gendisk *gd, umode_t *mode);
-- 
GitLab


From 79bd99596b7305ab08109a8bf44a6a4511dbf1cd Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Wed, 8 Mar 2017 07:38:05 +1100
Subject: [PATCH 822/898] blk: improve order of bio handling in
 generic_make_request()

To avoid recursion on the kernel stack when stacked block devices
are in use, generic_make_request() will, when called recursively,
queue new requests for later handling.  They will be handled when the
make_request_fn for the current bio completes.

If any bios are submitted by a make_request_fn, these will ultimately
be handled seqeuntially.  If the handling of one of those generates
further requests, they will be added to the end of the queue.

This strict first-in-first-out behaviour can lead to deadlocks in
various ways, normally because a request might need to wait for a
previous request to the same device to complete.  This can happen when
they share a mempool, and can happen due to interdependencies
particular to the device.  Both md and dm have examples where this happens.

These deadlocks can be erradicated by more selective ordering of bios.
Specifically by handling them in depth-first order.  That is: when the
handling of one bio generates one or more further bios, they are
handled immediately after the parent, before any siblings of the
parent.  That way, when generic_make_request() calls make_request_fn
for some particular device, we can be certain that all previously
submited requests for that device have been completely handled and are
not waiting for anything in the queue of requests maintained in
generic_make_request().

An easy way to achieve this would be to use a last-in-first-out stack
instead of a queue.  However this will change the order of consecutive
bios submitted by a make_request_fn, which could have unexpected consequences.
Instead we take a slightly more complex approach.
A fresh queue is created for each call to a make_request_fn.  After it completes,
any bios for a different device are placed on the front of the main queue, followed
by any bios for the same device, followed by all bios that were already on
the queue before the make_request_fn was called.
This provides the depth-first approach without reordering bios on the same level.

This, by itself, it not enough to remove all deadlocks.  It just makes
it possible for drivers to take the extra step required themselves.

To avoid deadlocks, drivers must never risk waiting for a request
after submitting one to generic_make_request.  This includes never
allocing from a mempool twice in the one call to a make_request_fn.

A common pattern in drivers is to call bio_split() in a loop, handling
the first part and then looping around to possibly split the next part.
Instead, a driver that finds it needs to split a bio should queue
(with generic_make_request) the second part, handle the first part,
and then return.  The new code in generic_make_request will ensure the
requests to underlying bios are processed first, then the second bio
that was split off.  If it splits again, the same process happens.  In
each case one bio will be completely handled before the next one is attempted.

With this is place, it should be possible to disable the
punt_bios_to_recover() recovery thread for many block devices, and
eventually it may be possible to remove it completely.

Ref: http://www.spinics.net/lists/raid/msg54680.html
Tested-by: Jinpu Wang <jinpu.wang@profitbricks.com>
Inspired-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index a76895c9776d..0eeb99ef654f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2015,17 +2015,34 @@ blk_qc_t generic_make_request(struct bio *bio)
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
 		if (likely(blk_queue_enter(q, false) == 0)) {
+			struct bio_list hold;
+			struct bio_list lower, same;
+
+			/* Create a fresh bio_list for all subordinate requests */
+			hold = bio_list_on_stack;
+			bio_list_init(&bio_list_on_stack);
 			ret = q->make_request_fn(q, bio);
 
 			blk_queue_exit(q);
 
-			bio = bio_list_pop(current->bio_list);
+			/* sort new bios into those for a lower level
+			 * and those for the same level
+			 */
+			bio_list_init(&lower);
+			bio_list_init(&same);
+			while ((bio = bio_list_pop(&bio_list_on_stack)) != NULL)
+				if (q == bdev_get_queue(bio->bi_bdev))
+					bio_list_add(&same, bio);
+				else
+					bio_list_add(&lower, bio);
+			/* now assemble so we handle the lowest level first */
+			bio_list_merge(&bio_list_on_stack, &lower);
+			bio_list_merge(&bio_list_on_stack, &same);
+			bio_list_merge(&bio_list_on_stack, &hold);
 		} else {
-			struct bio *bio_next = bio_list_pop(current->bio_list);
-
 			bio_io_error(bio);
-			bio = bio_next;
 		}
+		bio = bio_list_pop(current->bio_list);
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 
-- 
GitLab


From 672a2c87c83649fb0167202342ce85af9a3b4f1c Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Mar 2017 14:56:05 +0100
Subject: [PATCH 823/898] axonram: Fix gendisk handling

It is invalid to call del_gendisk() when disk->queue is NULL. Fix error
handling in axon_ram_probe() to avoid doing that.

Also del_gendisk() does not drop a reference to gendisk allocated by
alloc_disk(). That has to be done by put_disk(). Add that call where
needed.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 arch/powerpc/sysdev/axonram.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ada29eaed6e2..f523ac883150 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -274,7 +274,9 @@ static int axon_ram_probe(struct platform_device *device)
 			if (bank->disk->major > 0)
 				unregister_blkdev(bank->disk->major,
 						bank->disk->disk_name);
-			del_gendisk(bank->disk);
+			if (bank->disk->flags & GENHD_FL_UP)
+				del_gendisk(bank->disk);
+			put_disk(bank->disk);
 		}
 		device->dev.platform_data = NULL;
 		if (bank->io_addr != 0)
@@ -299,6 +301,7 @@ axon_ram_remove(struct platform_device *device)
 	device_remove_file(&device->dev, &dev_attr_ecc);
 	free_irq(bank->irq_id, device);
 	del_gendisk(bank->disk);
+	put_disk(bank->disk);
 	iounmap((void __iomem *) bank->io_addr);
 	kfree(bank);
 
-- 
GitLab


From f65e6fad293b3a5793b7fa2044800506490e7a2e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 8 Mar 2017 09:58:08 -0800
Subject: [PATCH 824/898] xfs: use iomap new flag for newly allocated delalloc
 blocks

Commit fa7f138 ("xfs: clear delalloc and cache on buffered write
failure") fixed one regression in the iomap error handling code and
exposed another. The fundamental problem is that if a buffered write
is a rewrite of preexisting delalloc blocks and the write fails, the
failure handling code can punch out preexisting blocks with valid
file data.

This was reproduced directly by sub-block writes in the LTP
kernel/syscalls/write/write03 test. A first 100 byte write allocates
a single block in a file. A subsequent 100 byte write fails and
punches out the block, including the data successfully written by
the previous write.

To address this problem, update the ->iomap_begin() handler to
distinguish newly allocated delalloc blocks from preexisting
delalloc blocks via the IOMAP_F_NEW flag. Use this flag in the
->iomap_end() handler to decide when a failed or short write should
punch out delalloc blocks.

This introduces the subtle requirement that ->iomap_begin() should
never combine newly allocated delalloc blocks with existing blocks
in the resulting iomap descriptor. This can occur when a new
delalloc reservation merges with a neighboring extent that is part
of the current write, for example. Therefore, drop the
post-allocation extent lookup from xfs_bmapi_reserve_delalloc() and
just return the record inserted into the fork. This ensures only new
blocks are returned and thus that preexisting delalloc blocks are
always handled as "found" blocks and not punched out on a failed
rewrite.

Reported-by: Xiong Zhou <xzhou@redhat.com>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 24 ++++++++++++++----------
 fs/xfs/xfs_iomap.c       | 25 ++++++++++++++++++-------
 2 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a9c66d47757a..bfa59a1a2d09 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4150,6 +4150,19 @@ xfs_bmapi_read(
 	return 0;
 }
 
+/*
+ * Add a delayed allocation extent to an inode. Blocks are reserved from the
+ * global pool and the extent inserted into the inode in-core extent tree.
+ *
+ * On entry, got refers to the first extent beyond the offset of the extent to
+ * allocate or eof is specified if no such extent exists. On return, got refers
+ * to the extent record that was inserted to the inode fork.
+ *
+ * Note that the allocated extent may have been merged with contiguous extents
+ * during insertion into the inode fork. Thus, got does not reflect the current
+ * state of the inode fork on return. If necessary, the caller can use lastx to
+ * look up the updated record in the inode fork.
+ */
 int
 xfs_bmapi_reserve_delalloc(
 	struct xfs_inode	*ip,
@@ -4236,13 +4249,8 @@ xfs_bmapi_reserve_delalloc(
 	got->br_startblock = nullstartblock(indlen);
 	got->br_blockcount = alen;
 	got->br_state = XFS_EXT_NORM;
-	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
-	/*
-	 * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
-	 * might have merged it into one of the neighbouring ones.
-	 */
-	xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
+	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
 	/*
 	 * Tag the inode if blocks were preallocated. Note that COW fork
@@ -4254,10 +4262,6 @@ xfs_bmapi_reserve_delalloc(
 	if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
 		xfs_inode_set_cowblocks_tag(ip);
 
-	ASSERT(got->br_startoff <= aoff);
-	ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen);
-	ASSERT(isnullstartblock(got->br_startblock));
-	ASSERT(got->br_state == XFS_EXT_NORM);
 	return 0;
 
 out_unreserve_blocks:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 41662fb14e87..288ee5b840d7 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -630,6 +630,11 @@ xfs_file_iomap_begin_delay(
 		goto out_unlock;
 	}
 
+	/*
+	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
+	 * them out if the write happens to fail.
+	 */
+	iomap->flags = IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -1071,16 +1076,22 @@ xfs_file_iomap_end_delalloc(
 	struct xfs_inode	*ip,
 	loff_t			offset,
 	loff_t			length,
-	ssize_t			written)
+	ssize_t			written,
+	struct iomap		*iomap)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_fsb;
 	xfs_fileoff_t		end_fsb;
 	int			error = 0;
 
-	/* behave as if the write failed if drop writes is enabled */
-	if (xfs_mp_drop_writes(mp))
+	/*
+	 * Behave as if the write failed if drop writes is enabled. Set the NEW
+	 * flag to force delalloc cleanup.
+	 */
+	if (xfs_mp_drop_writes(mp)) {
+		iomap->flags |= IOMAP_F_NEW;
 		written = 0;
+	}
 
 	/*
 	 * start_fsb refers to the first unused block after a short write. If
@@ -1094,14 +1105,14 @@ xfs_file_iomap_end_delalloc(
 	end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
 	/*
-	 * Trim back delalloc blocks if we didn't manage to write the whole
-	 * range reserved.
+	 * Trim delalloc blocks if they were allocated by this write and we
+	 * didn't manage to write the whole range.
 	 *
 	 * We don't need to care about racing delalloc as we hold i_mutex
 	 * across the reserve/allocate/unreserve calls. If there are delalloc
 	 * blocks in the range, they are ours.
 	 */
-	if (start_fsb < end_fsb) {
+	if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
 		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
 					 XFS_FSB_TO_B(mp, end_fsb) - 1);
 
@@ -1131,7 +1142,7 @@ xfs_file_iomap_end(
 {
 	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
 		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
-				length, written);
+				length, written, iomap);
 	return 0;
 }
 
-- 
GitLab


From bd0f9b356d00aa241ced36fb075a07041c28d3b8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 7 Mar 2017 15:33:14 -0800
Subject: [PATCH 825/898] sched/headers: fix up header file dependency on
 <linux/sched/signal.h>

The scheduler header file split and cleanups ended up exposing a few
nasty header file dependencies, and in particular it showed how we in
<linux/wait.h> ended up depending on "signal_pending()", which now comes
from <linux/sched/signal.h>.

That's a very subtle and annoying dependency, which already caused a
semantic merge conflict (see commit e58bc927835a "Pull overlayfs updates
from Miklos Szeredi", which added that fixup in the merge commit).

It turns out that we can avoid this dependency _and_ improve code
generation by moving the guts of the fairly nasty helper #define
__wait_event_interruptible_locked() to out-of-line code.  The code that
includes the signal_pending() check is all in the slow-path where we
actually go to sleep waiting for the event anyway, so using a helper
function is the right thing to do.

Using a helper function is also what we already did for the non-locked
versions, see the "__wait_event*()" macros and the "prepare_to_wait*()"
set of helper functions.

We might want to try to unify all these macro games, we have a _lot_ of
subtly different wait-event loops.  But this is the minimal patch to fix
the annoying header dependency.

Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/wait.h | 31 ++++++++++---------------------
 kernel/sched/wait.c  | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+), 21 deletions(-)

diff --git a/include/linux/wait.h b/include/linux/wait.h
index aacb1282d19a..db076ca7f11d 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -620,30 +620,19 @@ do {									\
 	__ret;								\
 })
 
+extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *);
+extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
 
-#define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \
+#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \
 ({									\
-	int __ret = 0;							\
+	int __ret;							\
 	DEFINE_WAIT(__wait);						\
 	if (exclusive)							\
 		__wait.flags |= WQ_FLAG_EXCLUSIVE;			\
 	do {								\
-		if (likely(list_empty(&__wait.task_list)))		\
-			__add_wait_queue_tail(&(wq), &__wait);		\
-		set_current_state(TASK_INTERRUPTIBLE);			\
-		if (signal_pending(current)) {				\
-			__ret = -ERESTARTSYS;				\
+		__ret = fn(&(wq), &__wait);				\
+		if (__ret)						\
 			break;						\
-		}							\
-		if (irq)						\
-			spin_unlock_irq(&(wq).lock);			\
-		else							\
-			spin_unlock(&(wq).lock);			\
-		schedule();						\
-		if (irq)						\
-			spin_lock_irq(&(wq).lock);			\
-		else							\
-			spin_lock(&(wq).lock);				\
 	} while (!(condition));						\
 	__remove_wait_queue(&(wq), &__wait);				\
 	__set_current_state(TASK_RUNNING);				\
@@ -676,7 +665,7 @@ do {									\
  */
 #define wait_event_interruptible_locked(wq, condition)			\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 0))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr))
 
 /**
  * wait_event_interruptible_locked_irq - sleep until a condition gets true
@@ -703,7 +692,7 @@ do {									\
  */
 #define wait_event_interruptible_locked_irq(wq, condition)		\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 1))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq))
 
 /**
  * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true
@@ -734,7 +723,7 @@ do {									\
  */
 #define wait_event_interruptible_exclusive_locked(wq, condition)	\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 0))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr))
 
 /**
  * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true
@@ -765,7 +754,7 @@ do {									\
  */
 #define wait_event_interruptible_exclusive_locked_irq(wq, condition)	\
 	((condition)							\
-	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1))
+	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq))
 
 
 #define __wait_event_killable(wq, condition)				\
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4d2ea6f25568..b8c84c6dee64 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_event);
 
+/*
+ * Note! These two wait functions are entered with the
+ * wait-queue lock held (and interrupts off in the _irq
+ * case), so there is no race with testing the wakeup
+ * condition in the caller before they add the wait
+ * entry to the wake queue.
+ */
+int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+	if (likely(list_empty(&wait->task_list)))
+		__add_wait_queue_tail(wq, wait);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (signal_pending(current))
+		return -ERESTARTSYS;
+
+	spin_unlock(&wq->lock);
+	schedule();
+	spin_lock(&wq->lock);
+	return 0;
+}
+EXPORT_SYMBOL(do_wait_intr);
+
+int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+	if (likely(list_empty(&wait->task_list)))
+		__add_wait_queue_tail(wq, wait);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (signal_pending(current))
+		return -ERESTARTSYS;
+
+	spin_unlock_irq(&wq->lock);
+	schedule();
+	spin_lock_irq(&wq->lock);
+	return 0;
+}
+EXPORT_SYMBOL(do_wait_intr_irq);
+
 /**
  * finish_wait - clean up after waiting in a queue
  * @q: waitqueue waited on
-- 
GitLab


From 2fcc319d2467a5f5b78f35f79fd6e22741a31b1e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Mar 2017 10:38:53 -0800
Subject: [PATCH 826/898] xfs: try any AG when allocating the first btree block
 when reflinking

When a reflink operation causes the bmap code to allocate a btree block
we're currently doing single-AG allocations due to having ->firstblock
set and then try any higher AG due a little reflink quirk we've put in
when adding the reflink code.  But given that we do not have a minleft
reservation of any kind in this AG we can still not have any space in
the same or higher AG even if the file system has enough free space.
To fix this use a XFS_ALLOCTYPE_FIRST_AG allocation in this fall back
path instead.

[And yes, we need to redo this properly instead of piling hacks over
 hacks.  I'm working on that, but it's not going to be a small series.
 In the meantime this fixes the customer reported issue]

Also add a warning for failing allocations to make it easier to debug.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       | 10 +++++++---
 fs/xfs/libxfs/xfs_bmap_btree.c |  6 +++---
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index bfa59a1a2d09..9bd104f32908 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree(
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
 	} else if (dfops->dop_low) {
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
 		args.fsbno = *firstblock;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -790,13 +790,17 @@ xfs_bmap_extents_to_btree(
 	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
 	    args.fsbno == NULLFSBLOCK &&
 	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		dfops->dop_low = true;
+		args.type = XFS_ALLOCTYPE_FIRST_AG;
 		goto try_another_ag;
 	}
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
+		xfs_iroot_realloc(ip, -1, whichfork);
+		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+		return -ENOSPC;
+	}
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
-	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(*firstblock == NULLFSBLOCK ||
 	       args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
 	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index f93072b58a58..fd55db479385 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -447,8 +447,8 @@ xfs_bmbt_alloc_block(
 
 	if (args.fsbno == NULLFSBLOCK) {
 		args.fsbno = be64_to_cpu(start->l);
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
 		/*
 		 * Make sure there is sufficient room left in the AG to
 		 * complete a full tree split for an extent insert.  If
@@ -488,8 +488,8 @@ xfs_bmbt_alloc_block(
 	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
 	    args.fsbno == NULLFSBLOCK &&
 	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		cur->bc_private.b.dfops->dop_low = true;
 		args.fsbno = cur->bc_private.b.firstblock;
+		args.type = XFS_ALLOCTYPE_FIRST_AG;
 		goto try_another_ag;
 	}
 
@@ -506,7 +506,7 @@ xfs_bmbt_alloc_block(
 			goto error0;
 		cur->bc_private.b.dfops->dop_low = true;
 	}
-	if (args.fsbno == NULLFSBLOCK) {
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 		*stat = 0;
 		return 0;
-- 
GitLab


From 04bb94b13c02e9dbc92d622cddf88937127bd7ed Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 8 Mar 2017 10:42:13 -0800
Subject: [PATCH 827/898] overlayfs: remove now unnecessary header file include

This removes the extra include header file that was added in commit
e58bc927835a "Pull overlayfs updates from Miklos Szeredi" now that it
is no longer needed.

There are probably other such includes that got added during the
scheduler header splitup series, but this is the one that annoyed me
personally and I know about.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/overlayfs/util.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 1953986ee6bc..6e610a205e15 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -12,7 +12,6 @@
 #include <linux/slab.h>
 #include <linux/cred.h>
 #include <linux/xattr.h>
-#include <linux/sched/signal.h>
 #include "overlayfs.h"
 #include "ovl_entry.h"
 
-- 
GitLab


From b4fb8f66f1ae2e167d06c12d018025a8d4d3ba7e Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 8 Mar 2017 09:35:39 -0800
Subject: [PATCH 828/898] mm, page_alloc: Add missing check for memory holes

Commit 13ad59df67f1 ("mm, page_alloc: avoid page_to_pfn() when merging
buddies") moved the check for memory holes out of page_is_buddy() and
had the callers do the check.

But this wasn't done correctly in one place which caused ia64 to crash
very early in boot.

Update to fix that and make ia64 boot again.

[ v2: Vlastimil pointed out we don't need to call page_to_pfn()
      since we already have the result of that in "buddy_pfn" ]

Fixes: 13ad59df67f1 ("avoid page_to_pfn() when merging buddies")
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eaa64d2ffdc5..6cbde310abed 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -873,7 +873,8 @@ static inline void __free_one_page(struct page *page,
 		higher_page = page + (combined_pfn - pfn);
 		buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
 		higher_buddy = higher_page + (buddy_pfn - combined_pfn);
-		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
+		if (pfn_valid_within(buddy_pfn) &&
+		    page_is_buddy(higher_page, higher_buddy, order + 1)) {
 			list_add_tail(&page->lru,
 				&zone->free_area[order].free_list[migratetype]);
 			goto out;
-- 
GitLab


From c085bd5119d5d0bdf3ef591a5563566be7dedced Mon Sep 17 00:00:00 2001
From: Jim Qu <Jim.Qu@amd.com>
Date: Wed, 1 Mar 2017 15:53:29 +0800
Subject: [PATCH 829/898] drm/amd/amdgpu: fix console deadlock if late init
 failed

Signed-off-by: Jim Qu <Jim.Qu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6abb238b25c9..4120b351a8e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2094,8 +2094,11 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	r = amdgpu_late_init(adev);
-	if (r)
+	if (r) {
+		if (fbcon)
+			console_unlock();
 		return r;
+	}
 
 	/* pin cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-- 
GitLab


From a677e7046ab5edb33d051bda60cb3be0d60a48cc Mon Sep 17 00:00:00 2001
From: Linu Cherian <linu.cherian@cavium.com>
Date: Wed, 8 Mar 2017 11:38:32 +0530
Subject: [PATCH 830/898] KVM: Add documentation for KVM_CAP_NR_MEMSLOTS

Add documentation for KVM_CAP_NR_MEMSLOTS capability.

Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Linu Cherian <linu.cherian@cavium.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 Documentation/virtual/kvm/api.txt | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 069450938b79..3c248f772ae6 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -951,6 +951,10 @@ This ioctl allows the user to create or modify a guest physical memory
 slot.  When changing an existing slot, it may be moved in the guest
 physical memory space, or its flags may be modified.  It may not be
 resized.  Slots may not overlap in guest physical address space.
+Bits 0-15 of "slot" specifies the slot id and this value should be
+less than the maximum number of user memory slots supported per VM.
+The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
+if this capability is supported by the architecture.
 
 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
 specifies the address space which is being modified.  They must be
-- 
GitLab


From 7af4df85796589e60a2dfc0f821eca0c4bbce4d2 Mon Sep 17 00:00:00 2001
From: Linu Cherian <linu.cherian@cavium.com>
Date: Wed, 8 Mar 2017 11:38:33 +0530
Subject: [PATCH 831/898] KVM: arm/arm64: Enable KVM_CAP_NR_MEMSLOTS on
 arm/arm64

Return KVM_USER_MEM_SLOTS for userspace capability query on
NR_MEMSLOTS.

Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Linu Cherian <linu.cherian@cavium.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/kvm/arm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index c9a2103faeb9..96dba7cd8be7 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -221,6 +221,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
 	case KVM_CAP_MSI_DEVID:
 		if (!kvm)
 			r = -EINVAL;
-- 
GitLab


From 3e92f94a3b8e925a6dd7ec88a5794b2084b5fb65 Mon Sep 17 00:00:00 2001
From: Linu Cherian <linu.cherian@cavium.com>
Date: Wed, 8 Mar 2017 11:38:34 +0530
Subject: [PATCH 832/898] KVM: arm/arm64: Remove KVM_PRIVATE_MEM_SLOTS
 definition that are unused

arm/arm64 architecture doesnt use private memslots, hence removing
KVM_PRIVATE_MEM_SLOTS macro definition.

Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Linu Cherian <linu.cherian@cavium.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/include/asm/kvm_host.h   | 1 -
 arch/arm64/include/asm/kvm_host.h | 1 -
 2 files changed, 2 deletions(-)

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index cc495d799c67..31ee468ce667 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -30,7 +30,6 @@
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
 #define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
 #define KVM_HALT_POLL_NS_DEFAULT 500000
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f21fd3894370..6ac17ee887c9 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -31,7 +31,6 @@
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
 #define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 
-- 
GitLab


From 955a3fc6d2a1c11d6d00bce4f3816100ce0530cf Mon Sep 17 00:00:00 2001
From: Linu Cherian <linu.cherian@cavium.com>
Date: Wed, 8 Mar 2017 11:38:35 +0530
Subject: [PATCH 833/898] KVM: arm64: Increase number of user memslots to 512

Having only 32 memslots is a real constraint for the maximum
number of PCI devices that can be assigned to a single guest.
Assuming each PCI device/virtual function having two memory BAR
regions, we could assign only 15 devices/virtual functions to a
guest.

Hence increase KVM_USER_MEM_SLOTS to 512 as done in other archs like
powerpc.

Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Linu Cherian <linu.cherian@cavium.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/include/asm/kvm_host.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 6ac17ee887c9..e7705e7bb07b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,7 +30,7 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#define KVM_USER_MEM_SLOTS 32
+#define KVM_USER_MEM_SLOTS 512
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 
-- 
GitLab


From 85550f9148a852ed363a386577ad31b97b95dfb8 Mon Sep 17 00:00:00 2001
From: Jelle Martijn Kok <jmkok@youcom.nl>
Date: Tue, 21 Feb 2017 12:48:18 +0100
Subject: [PATCH 834/898] usb: ohci-at91: Do not drop unhandled USB suspend
 control requests

In patch 2e2aa1bc7eff90ecm, USB suspend and wakeup control requests are
passed to SFR_OHCIICR register. If a processor does not have such a
register, this hub control request will be dropped.

If no such a SFR register is available, all USB suspend control requests
will now be processed using ohci_hub_control()
(like before patch 2e2aa1bc7eff90ecm.)

Tested on an Atmel AT91SAM9G20 with an on-board TI TUSB2046B hub chip
If the last USB device is unplugged from the USB hub, the hub goes into
sleep and will not wakeup when an USB devices is inserted.

Fixes: 2e2aa1bc7eff90ec ("usb: ohci-at91: Forcibly suspend ports while USB suspend")
Signed-off-by: Jelle Martijn Kok <jmkok@youcom.nl>
Tested-by: Wenyou Yang <wenyou.yang@atmel.com>
Cc: Wenyou Yang <wenyou.yang@atmel.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: stable <stable@vger.kernel.org>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/ohci-at91.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 414e3c376dbb..5302f988e7e6 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -350,7 +350,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 
 		case USB_PORT_FEAT_SUSPEND:
 			dev_dbg(hcd->self.controller, "SetPortFeat: SUSPEND\n");
-			if (valid_port(wIndex)) {
+			if (valid_port(wIndex) && ohci_at91->sfr_regmap) {
 				ohci_at91_port_suspend(ohci_at91->sfr_regmap,
 						       1);
 				return 0;
@@ -393,7 +393,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 
 		case USB_PORT_FEAT_SUSPEND:
 			dev_dbg(hcd->self.controller, "ClearPortFeature: SUSPEND\n");
-			if (valid_port(wIndex)) {
+			if (valid_port(wIndex) && ohci_at91->sfr_regmap) {
 				ohci_at91_port_suspend(ohci_at91->sfr_regmap,
 						       0);
 				return 0;
-- 
GitLab


From fd567653bdb908009b650f079bfd4b63169e2ac4 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier@osg.samsung.com>
Date: Wed, 22 Feb 2017 15:23:22 -0300
Subject: [PATCH 835/898] usb: phy: isp1301: Add OF device ID table

The driver doesn't have a struct of_device_id table but supported devices
are registered via Device Trees. This is working on the assumption that a
I2C device registered via OF will always match a legacy I2C device ID and
that the MODALIAS reported will always be of the form i2c:<device>.

But this could change in the future so the correct approach is to have an
OF device ID table if the devices are registered via OF.

Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/phy/phy-isp1301.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c
index db68156568e6..b3b33cf7ddf6 100644
--- a/drivers/usb/phy/phy-isp1301.c
+++ b/drivers/usb/phy/phy-isp1301.c
@@ -33,6 +33,12 @@ static const struct i2c_device_id isp1301_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, isp1301_id);
 
+static const struct of_device_id isp1301_of_match[] = {
+	{.compatible = "nxp,isp1301" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, isp1301_of_match);
+
 static struct i2c_client *isp1301_i2c_client;
 
 static int __isp1301_write(struct isp1301 *isp, u8 reg, u8 value, u8 clear)
@@ -130,6 +136,7 @@ static int isp1301_remove(struct i2c_client *client)
 static struct i2c_driver isp1301_driver = {
 	.driver = {
 		.name = DRV_NAME,
+		.of_match_table = of_match_ptr(isp1301_of_match),
 	},
 	.probe = isp1301_probe,
 	.remove = isp1301_remove,
-- 
GitLab


From b7321e81fc369abe353cf094d4f0dc2fe11ab95f Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 7 Mar 2017 16:11:03 +0100
Subject: [PATCH 836/898] USB: iowarrior: fix NULL-deref at probe

Make sure to check for the required interrupt-in endpoint to avoid
dereferencing a NULL-pointer should a malicious device lack such an
endpoint.

Note that a fairly recent change purported to fix this issue, but added
an insufficient test on the number of endpoints only, a test which can
now be removed.

Fixes: 4ec0ef3a8212 ("USB: iowarrior: fix oops with malicious USB descriptors")
Fixes: 946b960d13c1 ("USB: add driver for iowarrior devices.")
Cc: stable <stable@vger.kernel.org>	# 2.6.21
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 095778ff984d..3ad058cbe6ca 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -781,12 +781,6 @@ static int iowarrior_probe(struct usb_interface *interface,
 	iface_desc = interface->cur_altsetting;
 	dev->product_id = le16_to_cpu(udev->descriptor.idProduct);
 
-	if (iface_desc->desc.bNumEndpoints < 1) {
-		dev_err(&interface->dev, "Invalid number of endpoints\n");
-		retval = -EINVAL;
-		goto error;
-	}
-
 	/* set up the endpoint information */
 	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
 		endpoint = &iface_desc->endpoint[i].desc;
@@ -797,6 +791,13 @@ static int iowarrior_probe(struct usb_interface *interface,
 			/* this one will match for the IOWarrior56 only */
 			dev->int_out_endpoint = endpoint;
 	}
+
+	if (!dev->int_in_endpoint) {
+		dev_err(&interface->dev, "no interrupt-in endpoint found\n");
+		retval = -ENODEV;
+		goto error;
+	}
+
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
 	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
-- 
GitLab


From de46e56653de7b3b54baa625bd582635008b8d05 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 7 Mar 2017 16:11:04 +0100
Subject: [PATCH 837/898] USB: iowarrior: fix NULL-deref in write

Make sure to verify that we have the required interrupt-out endpoint for
IOWarrior56 devices to avoid dereferencing a NULL-pointer in write
should a malicious device lack such an endpoint.

Fixes: 946b960d13c1 ("USB: add driver for iowarrior devices.")
Cc: stable <stable@vger.kernel.org>     # 2.6.21
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 3ad058cbe6ca..37c63cb39714 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -798,6 +798,14 @@ static int iowarrior_probe(struct usb_interface *interface,
 		goto error;
 	}
 
+	if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+		if (!dev->int_out_endpoint) {
+			dev_err(&interface->dev, "no interrupt-out endpoint found\n");
+			retval = -ENODEV;
+			goto error;
+		}
+	}
+
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
 	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
-- 
GitLab


From d595259fbb7a7afed241b1afb2c4fe4b47de47fa Mon Sep 17 00:00:00 2001
From: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Date: Tue, 28 Feb 2017 00:46:58 +0100
Subject: [PATCH 838/898] usb-storage: Add ignore-residue quirk for Initio
 INIC-3619

This USB-SATA bridge chip is used in a StarTech enclosure for
optical drives.

Without the quirk MakeMKV fails during the key exchange with an
installed BluRay drive:
> Error 'Scsi error - ILLEGAL REQUEST:COPY PROTECTION KEY EXCHANGE FAILURE - KEY NOT ESTABLISHED'
> occurred while issuing SCSI command AD010..080002400 to device 'SG:dev_11:2'

Signed-off-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/storage/unusual_devs.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 16cc18369111..9129f6cb8230 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2071,6 +2071,20 @@ UNUSUAL_DEV(  0x1370, 0x6828, 0x0110, 0x0110,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE ),
 
+/*
+ * Reported by Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
+ * The INIC-3619 bridge is used in the StarTech SLSODDU33B
+ * SATA-USB enclosure for slimline optical drives.
+ *
+ * The quirk enables MakeMKV to properly exchange keys with
+ * an installed BD drive.
+ */
+UNUSUAL_DEV(  0x13fd, 0x3609, 0x0209, 0x0209,
+		"Initio Corporation",
+		"INIC-3619",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
 /* Reported by Qinglin Ye <yestyle@gmail.com> */
 UNUSUAL_DEV(  0x13fe, 0x3600, 0x0100, 0x0100,
 		"Kingston",
-- 
GitLab


From cfa47afe77b393e2c24a57e7e9611857a0b064f1 Mon Sep 17 00:00:00 2001
From: Richard Leitner <richard.leitner@skidata.com>
Date: Mon, 6 Mar 2017 09:24:20 +0100
Subject: [PATCH 839/898] usb: usb251xb: remove max_{power,current}_{sp,bp}
 properties

Remove the max_{power,current}_{sp,bp} properties of the usb251xb driver
from devicetree. This is done to simplify the dt bindings as requested
by Rob Herring in https://lkml.org/lkml/2017/2/15/1283. If those
properties are ever needed by somebody they can be enabled again easily.

Signed-off-by: Richard Leitner <richard.leitner@skidata.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/usb/usb251xb.txt      | 20 ----------------
 drivers/usb/misc/usb251xb.c                   | 24 ++++---------------
 2 files changed, 4 insertions(+), 40 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt
index 0c065f77658f..a5efd10ace9e 100644
--- a/Documentation/devicetree/bindings/usb/usb251xb.txt
+++ b/Documentation/devicetree/bindings/usb/usb251xb.txt
@@ -40,26 +40,6 @@ Optional properties :
 	device connected.
  - sp-disabled-ports : Specifies the ports which will be self-power disabled
  - bp-disabled-ports : Specifies the ports which will be bus-power disabled
- - max-sp-power : Specifies the maximum current the hub consumes from an
-	upstream port when operating as self-powered hub including the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 2).
- - max-bp-power : Specifies the maximum current the hub consumes from an
-	upstream port when operating as bus-powered hub including the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 100).
- - max-sp-current : Specifies the maximum current the hub consumes from an
-	upstream port when operating as self-powered hub EXCLUDING the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 2).
- - max-bp-current : Specifies the maximum current the hub consumes from an
-	upstream port when operating as bus-powered hub EXCLUDING the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 100).
  - power-on-time : Specifies the time it takes from the time the host initiates
 	the power-on sequence to a port until the port has adequate power. The
 	value is given in ms in a 0 - 510 range (default is 100ms).
diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c
index 4e18600dc9b4..3f9c3060c477 100644
--- a/drivers/usb/misc/usb251xb.c
+++ b/drivers/usb/misc/usb251xb.c
@@ -432,26 +432,6 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 		}
 	}
 
-	hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF;
-	if (!of_property_read_u32(np, "max-sp-power", property_u32))
-		hub->max_power_sp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					  250);
-
-	hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS;
-	if (!of_property_read_u32(np, "max-bp-power", property_u32))
-		hub->max_power_bp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					  250);
-
-	hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF;
-	if (!of_property_read_u32(np, "max-sp-current", property_u32))
-		hub->max_current_sp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					    250);
-
-	hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS;
-	if (!of_property_read_u32(np, "max-bp-current", property_u32))
-		hub->max_current_bp = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					    250);
-
 	hub->power_on_time = USB251XB_DEF_POWER_ON_TIME;
 	if (!of_property_read_u32(np, "power-on-time", property_u32))
 		hub->power_on_time = min_t(u8, be32_to_cpu(*property_u32) / 2,
@@ -492,6 +472,10 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 	/* The following parameters are currently not exposed to devicetree, but
 	 * may be as soon as needed.
 	 */
+	hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF;
+	hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS;
+	hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF;
+	hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS;
 	hub->bat_charge_en = USB251XB_DEF_BATTERY_CHARGING_ENABLE;
 	hub->boost_up = USB251XB_DEF_BOOST_UP;
 	hub->boost_x = USB251XB_DEF_BOOST_X;
-- 
GitLab


From 7f7d8ba3b2140d993887a7db7a83d85c1f8db0e8 Mon Sep 17 00:00:00 2001
From: Richard Leitner <richard.leitner@skidata.com>
Date: Mon, 6 Mar 2017 09:24:21 +0100
Subject: [PATCH 840/898] usb: usb251xb: dt: add unit suffix to oc-delay and
 power-on-time

Rename oc-delay-* to oc-delay-us and make it expect a time value.
Furthermore add -ms suffix to power-on-time. There changes were
suggested by Rob Herring in https://lkml.org/lkml/2017/2/15/1283.

Signed-off-by: Richard Leitner <richard.leitner@skidata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/usb/usb251xb.txt      | 10 +++---
 drivers/usb/misc/usb251xb.c                   | 35 +++++++++++--------
 2 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt
index a5efd10ace9e..91499ae028db 100644
--- a/Documentation/devicetree/bindings/usb/usb251xb.txt
+++ b/Documentation/devicetree/bindings/usb/usb251xb.txt
@@ -31,7 +31,9 @@ Optional properties :
 	(default is individual)
  - dynamic-power-switching : enable auto-switching from self- to bus-powered
 	operation if the local power source is removed or unavailable
- - oc-delay-{100us,4ms,8ms,16ms} : set over current timer delay (default is 8ms)
+ - oc-delay-us : Delay time (in microseconds) for filtering the over-current
+	sense inputs. Valid values are 100, 4000, 8000 (default) and 16000. If
+	an invalid value is given, the default is used instead.
  - compound-device : indicated the hub is part of a compound device
  - port-mapping-mode : enable port mapping mode
  - string-support : enable string descriptor support (required for manufacturer,
@@ -40,9 +42,9 @@ Optional properties :
 	device connected.
  - sp-disabled-ports : Specifies the ports which will be self-power disabled
  - bp-disabled-ports : Specifies the ports which will be bus-power disabled
- - power-on-time : Specifies the time it takes from the time the host initiates
-	the power-on sequence to a port until the port has adequate power. The
-	value is given in ms in a 0 - 510 range (default is 100ms).
+ - power-on-time-ms : Specifies the time it takes from the time the host
+	initiates the power-on sequence to a port until the port has adequate
+	power. The value is given in ms in a 0 - 510 range (default is 100ms).
 
 Examples:
 	usb2512b@2c {
diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c
index 3f9c3060c477..91f66d68bcb7 100644
--- a/drivers/usb/misc/usb251xb.c
+++ b/drivers/usb/misc/usb251xb.c
@@ -375,18 +375,24 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 	if (of_get_property(np, "dynamic-power-switching", NULL))
 		hub->conf_data2 |= BIT(7);
 
-	if (of_get_property(np, "oc-delay-100us", NULL)) {
-		hub->conf_data2 &= ~BIT(5);
-		hub->conf_data2 &= ~BIT(4);
-	} else if (of_get_property(np, "oc-delay-4ms", NULL)) {
-		hub->conf_data2 &= ~BIT(5);
-		hub->conf_data2 |= BIT(4);
-	} else if (of_get_property(np, "oc-delay-8ms", NULL)) {
-		hub->conf_data2 |= BIT(5);
-		hub->conf_data2 &= ~BIT(4);
-	} else if (of_get_property(np, "oc-delay-16ms", NULL)) {
-		hub->conf_data2 |= BIT(5);
-		hub->conf_data2 |= BIT(4);
+	if (!of_property_read_u32(np, "oc-delay-us", property_u32)) {
+		if (*property_u32 == 100) {
+			/* 100 us*/
+			hub->conf_data2 &= ~BIT(5);
+			hub->conf_data2 &= ~BIT(4);
+		} else if (*property_u32 == 4000) {
+			/* 4 ms */
+			hub->conf_data2 &= ~BIT(5);
+			hub->conf_data2 |= BIT(4);
+		} else if (*property_u32 == 16000) {
+			/* 16 ms */
+			hub->conf_data2 |= BIT(5);
+			hub->conf_data2 |= BIT(4);
+		} else {
+			/* 8 ms (DEFAULT) */
+			hub->conf_data2 |= BIT(5);
+			hub->conf_data2 &= ~BIT(4);
+		}
 	}
 
 	if (of_get_property(np, "compound-device", NULL))
@@ -433,9 +439,8 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 	}
 
 	hub->power_on_time = USB251XB_DEF_POWER_ON_TIME;
-	if (!of_property_read_u32(np, "power-on-time", property_u32))
-		hub->power_on_time = min_t(u8, be32_to_cpu(*property_u32) / 2,
-					   255);
+	if (!of_property_read_u32(np, "power-on-time-ms", property_u32))
+		hub->power_on_time = min_t(u8, *property_u32 / 2, 255);
 
 	if (of_property_read_u16_array(np, "language-id", &hub->lang_id, 1))
 		hub->lang_id = USB251XB_DEF_LANGUAGE_ID;
-- 
GitLab


From fa56fe4ca4a1e4d9715f144857c98074e41bc94f Mon Sep 17 00:00:00 2001
From: Richard Leitner <richard.leitner@skidata.com>
Date: Mon, 6 Mar 2017 09:24:22 +0100
Subject: [PATCH 841/898] doc: dt-bindings: usb251xb: mark reg as required

Mark the reg property as required and furthermore fix some typos and
spellings in the documentation.

Signed-off-by: Richard Leitner <richard.leitner@skidata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/usb/usb251xb.txt      | 23 ++++++++++---------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt
index 91499ae028db..3957d4edaa74 100644
--- a/Documentation/devicetree/bindings/usb/usb251xb.txt
+++ b/Documentation/devicetree/bindings/usb/usb251xb.txt
@@ -7,18 +7,18 @@ Required properties :
  - compatible : Should be "microchip,usb251xb" or one of the specific types:
 	"microchip,usb2512b", "microchip,usb2512bi", "microchip,usb2513b",
 	"microchip,usb2513bi", "microchip,usb2514b", "microchip,usb2514bi"
- - hub-reset-gpios : Should specify the gpio for hub reset
+ - reset-gpios : Should specify the gpio for hub reset
+ - reg : I2C address on the selected bus (default is <0x2C>)
 
 Optional properties :
- - reg : I2C address on the selected bus (default is <0x2C>)
  - skip-config : Skip Hub configuration, but only send the USB-Attach command
- - vendor-id : USB Vendor ID of the hub (16 bit, default is 0x0424)
- - product-id : USB Product ID of the hub (16 bit, default depends on type)
- - device-id : USB Device ID of the hub (16 bit, default is 0x0bb3)
- - language-id : USB Language ID (16 bit, default is 0x0000)
- - manufacturer : USB Manufacturer string (max 31 characters long)
- - product : USB Product string (max 31 characters long)
- - serial : USB Serial string (max 31 characters long)
+ - vendor-id : Set USB Vendor ID of the hub (16 bit, default is 0x0424)
+ - product-id : Set USB Product ID of the hub (16 bit, default depends on type)
+ - device-id : Set USB Device ID of the hub (16 bit, default is 0x0bb3)
+ - language-id : Set USB Language ID (16 bit, default is 0x0000)
+ - manufacturer : Set USB Manufacturer string (max 31 characters long)
+ - product : Set USB Product string (max 31 characters long)
+ - serial : Set USB Serial string (max 31 characters long)
  - {bus,self}-powered : selects between self- and bus-powered operation (default
 	is self-powered)
  - disable-hi-speed : disable USB Hi-Speed support
@@ -34,7 +34,7 @@ Optional properties :
  - oc-delay-us : Delay time (in microseconds) for filtering the over-current
 	sense inputs. Valid values are 100, 4000, 8000 (default) and 16000. If
 	an invalid value is given, the default is used instead.
- - compound-device : indicated the hub is part of a compound device
+ - compound-device : indicate the hub is part of a compound device
  - port-mapping-mode : enable port mapping mode
  - string-support : enable string descriptor support (required for manufacturer,
 	product and serial string configuration)
@@ -49,7 +49,8 @@ Optional properties :
 Examples:
 	usb2512b@2c {
 		compatible = "microchip,usb2512b";
-		hub-reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+		reg = <0x2c>;
+		reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	};
 
 	usb2514b@2c {
-- 
GitLab


From 829b84db0c0c120ae5855a69cc0c94ff75fafabb Mon Sep 17 00:00:00 2001
From: Richard Leitner <richard.leitner@skidata.com>
Date: Mon, 6 Mar 2017 09:24:23 +0100
Subject: [PATCH 842/898] MAINTAINERS: usb251xb: remove reference inexistent
 file

The platform_data header file was dropped in the merged version of the
USB251xB driver. Therefore remove its reference from the MAINTAINERS file.

Signed-off-by: Richard Leitner <richard.leitner@skidata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c265a5fe4848..c776906f67a9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8307,7 +8307,6 @@ M:	Richard Leitner <richard.leitner@skidata.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/misc/usb251xb.c
-F:	include/linux/platform_data/usb251xb.h
 F:	Documentation/devicetree/bindings/usb/usb251xb.txt
 
 MICROSOFT SURFACE PRO 3 BUTTON DRIVER
-- 
GitLab


From 2f6821462fe3ace62df3f1b5a9463153e8288298 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 24 Feb 2017 19:11:28 +0100
Subject: [PATCH 843/898] USB: serial: digi_acceleport: fix OOB-event
 processing

A recent change claimed to fix an off-by-one error in the OOB-port
completion handler, but instead introduced such an error. This could
specifically led to modem-status changes going unnoticed, effectively
breaking TIOCMGET.

Note that the offending commit fixes a loop-condition underflow and is
marked for stable, but should not be backported without this fix.

Reported-by: Ben Hutchings <ben@decadent.org.uk>
Fixes: 2d380889215f ("USB: serial: digi_acceleport: fix OOB data sanity check")
Cc: stable <stable@vger.kernel.org>	# v2.6.30
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/serial/digi_acceleport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index ab78111e0968..6537d3ca2797 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -1500,7 +1500,7 @@ static int digi_read_oob_callback(struct urb *urb)
 		return -1;
 
 	/* handle each oob command */
-	for (i = 0; i < urb->actual_length - 4; i += 4) {
+	for (i = 0; i < urb->actual_length - 3; i += 4) {
 		opcode = buf[i];
 		line = buf[i + 1];
 		status = buf[i + 2];
-- 
GitLab


From 05d8d34611139f8435af90ac54b65eb31e82e388 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@redhat.com>
Date: Tue, 7 Mar 2017 17:51:49 +0100
Subject: [PATCH 844/898] KVM: nVMX: do not warn when MSR bitmap address is not
 backed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before trying to do nested_get_page() in nested_vmx_merge_msr_bitmap(),
we have already checked that the MSR bitmap address is valid (4k aligned
and within physical limits).  SDM doesn't specify what happens if the
there is no memory mapped at the valid address, but Intel CPUs treat the
situation as if the bitmap was configured to trap all MSRs.

KVM already does that by returning false and a correct handling doesn't
need the guest-trigerrable warning that was reported by syzkaller:
(The warning was originally there to catch some possible bugs in nVMX.)

  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 7832 at arch/x86/kvm/vmx.c:9709
  nested_vmx_merge_msr_bitmap arch/x86/kvm/vmx.c:9709 [inline]
  WARNING: CPU: 0 PID: 7832 at arch/x86/kvm/vmx.c:9709
  nested_get_vmcs12_pages+0xfb6/0x15c0 arch/x86/kvm/vmx.c:9640
  Kernel panic - not syncing: panic_on_warn set ...
  CPU: 0 PID: 7832 Comm: syz-executor1 Not tainted 4.10.0+ #229
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  Call Trace:
   __dump_stack lib/dump_stack.c:15 [inline]
   dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
   panic+0x1fb/0x412 kernel/panic.c:179
   __warn+0x1c4/0x1e0 kernel/panic.c:540
   warn_slowpath_null+0x2c/0x40 kernel/panic.c:583
   nested_vmx_merge_msr_bitmap arch/x86/kvm/vmx.c:9709 [inline]
   nested_get_vmcs12_pages+0xfb6/0x15c0 arch/x86/kvm/vmx.c:9640
   enter_vmx_non_root_mode arch/x86/kvm/vmx.c:10471 [inline]
   nested_vmx_run+0x6186/0xaab0 arch/x86/kvm/vmx.c:10561
   handle_vmlaunch+0x1a/0x20 arch/x86/kvm/vmx.c:7312
   vmx_handle_exit+0xfc0/0x3f00 arch/x86/kvm/vmx.c:8526
   vcpu_enter_guest arch/x86/kvm/x86.c:6982 [inline]
   vcpu_run arch/x86/kvm/x86.c:7044 [inline]
   kvm_arch_vcpu_ioctl_run+0x1418/0x4840 arch/x86/kvm/x86.c:7205
   kvm_vcpu_ioctl+0x673/0x1120 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2570

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
[Jim Mattson explained the bare metal behavior: "I believe this behavior
 would be documented in the chipset data sheet rather than the SDM,
 since the chipset returns all 1s for an unclaimed read."]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
---
 arch/x86/kvm/vmx.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ab338581b3ec..98e82ee1e699 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9680,10 +9680,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		return false;
 
 	page = nested_get_page(vcpu, vmcs12->msr_bitmap);
-	if (!page) {
-		WARN_ON(1);
+	if (!page)
 		return false;
-	}
 	msr_bitmap_l1 = (unsigned long *)kmap(page);
 
 	memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
-- 
GitLab


From 9ad224744218a352964f31007a1420f2420a08a0 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier@osg.samsung.com>
Date: Thu, 9 Mar 2017 11:05:33 -0300
Subject: [PATCH 845/898] i2c: exynos5: Avoid transaction timeouts due
 TRANSFER_DONE_AUTO not set

After commit 7999eecb7e56 ("i2c: exynos5: fix arbitration lost handling"),
some I2C transactions are failing because the TRANSFER_DONE_AUTO field is
not set in the I2C_TRANS_STATUS register so the i2c->status value is left
to -EINVAL causing the i2c->msg_complete completion to never be signaled.

For example, when reading the time of an I2C rtc on an Exynos5800 machine:

$ cat /sys/class/rtc/rtc0/time
[   25.924594] exynos5-hsi2c 12e10000.i2c: rx timeout
[   65.028365] max77686-rtc max77802-rtc: Fail to read time reg(-22)
cat: /sys/class/rtc/rtc0/time: Invalid argument

The Exynos5422 manual states clearly that most I2C_TRANS_STATUS reg bits
(including TRANSFER_DONE_AUTO) are cleared after the register is read. So
reading has side effects and should only be done if HSI2C_INT_I2C was set.

Fixes: 7999eecb7e56 ("i2c: exynos5: fix arbitration lost handling")
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Reviewed-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-exynos5.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index cbd93ce0661f..736a82472101 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -457,7 +457,6 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id)
 
 	int_status = readl(i2c->regs + HSI2C_INT_STATUS);
 	writel(int_status, i2c->regs + HSI2C_INT_STATUS);
-	trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
 
 	/* handle interrupt related to the transfer status */
 	if (i2c->variant->hw == HSI2C_EXYNOS7) {
@@ -482,11 +481,13 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id)
 			goto stop;
 		}
 
+		trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
 		if ((trans_status & HSI2C_MASTER_ST_MASK) == HSI2C_MASTER_ST_LOSE) {
 			i2c->state = -EAGAIN;
 			goto stop;
 		}
 	} else if (int_status & HSI2C_INT_I2C) {
+		trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
 		if (trans_status & HSI2C_NO_DEV_ACK) {
 			dev_dbg(i2c->dev, "No ACK from device\n");
 			i2c->state = -ENXIO;
-- 
GitLab


From 8ce0928e6867fda4d208d7bddf251bce96ab8431 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Thu, 9 Mar 2017 16:32:17 +0100
Subject: [PATCH 846/898] Revert "i2c: add missing of_node_put in
 i2c_mux_del_adapters"

This reverts commit 02dbfa5e5583523035f05636c614a0eca77f1aab. I grabbed
the wrong version from the list and will pull the proper one from Peter
Rosin's mux tree.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-mux.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 2178266bca79..83768e85a919 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -429,7 +429,6 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 	while (muxc->num_adapters) {
 		struct i2c_adapter *adap = muxc->adapter[--muxc->num_adapters];
 		struct i2c_mux_priv *priv = adap->algo_data;
-		struct device_node *np = adap->dev.of_node;
 
 		muxc->adapter[muxc->num_adapters] = NULL;
 
@@ -439,7 +438,6 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
 
 		sysfs_remove_link(&priv->adap.dev.kobj, "mux_device");
 		i2c_del_adapter(adap);
-		of_node_put(np);
 		kfree(priv);
 	}
 }
-- 
GitLab


From 806dbb20efde821910b5f747befed794077a9109 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Thu, 9 Mar 2017 16:41:48 +0100
Subject: [PATCH 847/898] Revert "i2c: copy device properties when using
 i2c_register_board_info()"

This reverts commit b0c1e95ab44feaad8831f2c06a3473c974003b49. It
contains a flaw and the next version has more features added which makes
me want to move it to the next cycle.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-boardinfo.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/i2c/i2c-boardinfo.c b/drivers/i2c/i2c-boardinfo.c
index 5b8f6c3a6950..6e5fac6a5262 100644
--- a/drivers/i2c/i2c-boardinfo.c
+++ b/drivers/i2c/i2c-boardinfo.c
@@ -15,7 +15,6 @@
 #include <linux/export.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
-#include <linux/property.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
 
@@ -56,7 +55,6 @@ EXPORT_SYMBOL_GPL(__i2c_first_dynamic_bus_num);
  *
  * The board info passed can safely be __initdata, but be careful of embedded
  * pointers (for platform_data, functions, etc) since that won't be copied.
- * Device properties are deep-copied though.
  */
 int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned len)
 {
@@ -80,14 +78,6 @@ int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsig
 
 		devinfo->busnum = busnum;
 		devinfo->board_info = *info;
-
-		if (info->properties) {
-			devinfo->board_info.properties =
-					property_entries_dup(info->properties);
-			if (IS_ERR(devinfo->board_info.properties))
-				return PTR_ERR(devinfo->board_info.properties);
-		}
-
 		list_add_tail(&devinfo->list, &__i2c_board_list);
 	}
 
-- 
GitLab


From 94a631d91ad341b3b4bdac72d1104d9f090e0ca9 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Thu, 9 Mar 2017 15:39:34 +0200
Subject: [PATCH 848/898] usb: xhci-mtk: check hcc_params after adding primary
 hcd

hcc_params is set in xhci_gen_setup() called from usb_add_hcd(),
so checks the Maximum Primary Stream Array Size in the hcc_params
register after adding primary hcd.

Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mtk.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index 9066ec9e0c2e..6ac73a6b4da6 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -678,13 +678,13 @@ static int xhci_mtk_probe(struct platform_device *pdev)
 		goto power_off_phys;
 	}
 
-	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
-		xhci->shared_hcd->can_do_streams = 1;
-
 	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto put_usb3_hcd;
 
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
 	ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto dealloc_usb2_hcd;
-- 
GitLab


From 20e4e37e4a2f1bfd43bcc8c3e666e47665036cc3 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Thu, 9 Mar 2017 15:39:35 +0200
Subject: [PATCH 849/898] usb: xhci: remove dummy extra_priv_size for size of
 xhci_hcd struct

because hcd_priv_size is already size of xhci_hcd struct,
extra_priv_size is not needed anymore for MTK and tegra drivers.

Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Tested-by: Thierry Reding <treding@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mtk.c   | 1 -
 drivers/usb/host/xhci-tegra.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index 6ac73a6b4da6..67d5dc79b6b5 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -382,7 +382,6 @@ static int usb_wakeup_of_property_parse(struct xhci_hcd_mtk *mtk,
 
 static int xhci_mtk_setup(struct usb_hcd *hcd);
 static const struct xhci_driver_overrides xhci_mtk_overrides __initconst = {
-	.extra_priv_size = sizeof(struct xhci_hcd),
 	.reset = xhci_mtk_setup,
 };
 
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index a59fafb4b329..74436f8ca538 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1308,7 +1308,6 @@ static int tegra_xhci_setup(struct usb_hcd *hcd)
 }
 
 static const struct xhci_driver_overrides tegra_xhci_overrides __initconst = {
-	.extra_priv_size = sizeof(struct xhci_hcd),
 	.reset = tegra_xhci_setup,
 };
 
-- 
GitLab


From f95e60a7dbecd2de816bb3ad517b3d4fbc20b507 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@nxp.com>
Date: Thu, 9 Mar 2017 15:39:36 +0200
Subject: [PATCH 850/898] usb: host: xhci-dbg: HCIVERSION should be a binary
 number

According to xHCI spec, HCIVERSION containing a BCD encoding
of the xHCI specification revision number, 0100h corresponds
to xHCI version 1.0. Change "100" as "0x100".

Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: stable <stable@vger.kernel.org>
Fixes: 04abb6de2825 ("xhci: Read and parse new xhci
	1.1 capability register")
Signed-off-by: Peter Chen <peter.chen@nxp.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index 363d125300ea..2b4a00fa735d 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -109,7 +109,7 @@ static void xhci_print_cap_regs(struct xhci_hcd *xhci)
 	xhci_dbg(xhci, "RTSOFF 0x%x:\n", temp & RTSOFF_MASK);
 
 	/* xhci 1.1 controllers have the HCCPARAMS2 register */
-	if (hci_version > 100) {
+	if (hci_version > 0x100) {
 		temp = readl(&xhci->cap_regs->hcc_params2);
 		xhci_dbg(xhci, "HCC PARAMS2 0x%x:\n", (unsigned int) temp);
 		xhci_dbg(xhci, "  HC %s Force save context capability",
-- 
GitLab


From dcc7620cad5ad1326a78f4031a7bf4f0e5b42984 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 9 Mar 2017 15:39:37 +0200
Subject: [PATCH 851/898] usb: host: xhci-plat: Fix timeout on removal of hot
 pluggable xhci controllers

Upstream commit 98d74f9ceaef ("xhci: fix 10 second timeout on removal of
PCI hotpluggable xhci controllers") fixes a problem with hot pluggable PCI
xhci controllers which can result in excessive timeouts, to the point where
the system reports a deadlock.

The same problem is seen with hot pluggable xhci controllers using the
xhci-plat driver, such as the driver used for Type-C ports on rk3399.
Similar to hot-pluggable PCI controllers, the driver for this chip
removes the xhci controller from the system when the Type-C cable is
disconnected.

The solution for PCI devices works just as well for non-PCI devices
and avoids the problem.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-plat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 6d33b42ffcf5..bd02a6cd8e2c 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -286,6 +286,8 @@ static int xhci_plat_remove(struct platform_device *dev)
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	struct clk *clk = xhci->clk;
 
+	xhci->xhc_state |= XHCI_STATE_REMOVING;
+
 	usb_remove_hcd(xhci->shared_hcd);
 	usb_phy_shutdown(hcd->usb_phy);
 
-- 
GitLab


From 6fb895692a034393d58679cd8d00c9e229719a5f Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 17:24:02 +0300
Subject: [PATCH 852/898] x86/cpufeature: Add 5-level paging detection

Look for 'la57' in /proc/cpuinfo to see if your machine supports 5-level
paging.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/cpufeatures.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4e7772387c6e..b04bb6dfed7f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -289,7 +289,8 @@
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
 #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
+#define X86_FEATURE_LA57	(16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID	(16*32+22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
-- 
GitLab


From 505a60e225606fbd3d2eadc31ff793d939ba66f1 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 17:24:03 +0300
Subject: [PATCH 853/898] asm-generic: introduce 5level-fixup.h

We are going to switch core MM to 5-level paging abstraction.

This is preparation step which adds <asm-generic/5level-fixup.h>
As with 4level-fixup.h, the new header allows quickly make all
architectures compatible with 5-level paging in core MM.

In long run we would like to switch architectures to properly folded p4d
level by using <asm-generic/pgtable-nop4d.h>, but it requires more
changes to arch-specific code.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/4level-fixup.h |  3 ++-
 include/asm-generic/5level-fixup.h | 41 ++++++++++++++++++++++++++++++
 include/linux/mm.h                 |  3 +++
 3 files changed, 46 insertions(+), 1 deletion(-)
 create mode 100644 include/asm-generic/5level-fixup.h

diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 5bdab6bffd23..928fd66b1271 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -15,7 +15,6 @@
 	((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \
  		NULL: pmd_offset(pud, address))
 
-#define pud_alloc(mm, pgd, address)	(pgd)
 #define pud_offset(pgd, start)		(pgd)
 #define pud_none(pud)			0
 #define pud_bad(pud)			0
@@ -35,4 +34,6 @@
 #undef  pud_addr_end
 #define pud_addr_end(addr, end)		(end)
 
+#include <asm-generic/5level-fixup.h>
+
 #endif
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
new file mode 100644
index 000000000000..b5ca82dc4175
--- /dev/null
+++ b/include/asm-generic/5level-fixup.h
@@ -0,0 +1,41 @@
+#ifndef _5LEVEL_FIXUP_H
+#define _5LEVEL_FIXUP_H
+
+#define __ARCH_HAS_5LEVEL_HACK
+#define __PAGETABLE_P4D_FOLDED
+
+#define P4D_SHIFT			PGDIR_SHIFT
+#define P4D_SIZE			PGDIR_SIZE
+#define P4D_MASK			PGDIR_MASK
+#define PTRS_PER_P4D			1
+
+#define p4d_t				pgd_t
+
+#define pud_alloc(mm, p4d, address) \
+	((unlikely(pgd_none(*(p4d))) && __pud_alloc(mm, p4d, address)) ? \
+		NULL : pud_offset(p4d, address))
+
+#define p4d_alloc(mm, pgd, address)	(pgd)
+#define p4d_offset(pgd, start)		(pgd)
+#define p4d_none(p4d)			0
+#define p4d_bad(p4d)			0
+#define p4d_present(p4d)		1
+#define p4d_ERROR(p4d)			do { } while (0)
+#define p4d_clear(p4d)			pgd_clear(p4d)
+#define p4d_val(p4d)			pgd_val(p4d)
+#define p4d_populate(mm, p4d, pud)	pgd_populate(mm, p4d, pud)
+#define p4d_page(p4d)			pgd_page(p4d)
+#define p4d_page_vaddr(p4d)		pgd_page_vaddr(p4d)
+
+#define __p4d(x)			__pgd(x)
+#define set_p4d(p4dp, p4d)		set_pgd(p4dp, p4d)
+
+#undef p4d_free_tlb
+#define p4d_free_tlb(tlb, x, addr)	do { } while (0)
+#define p4d_free(mm, x)			do { } while (0)
+#define __p4d_free_tlb(tlb, x, addr)	do { } while (0)
+
+#undef  p4d_addr_end
+#define p4d_addr_end(addr, end)		(end)
+
+#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0d65dd72c0f4..be1fe264eb37 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1619,11 +1619,14 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
  * Remove it when 4level-fixup.h has been removed.
  */
 #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
+
+#ifndef __ARCH_HAS_5LEVEL_HACK
 static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 {
 	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
 		NULL: pud_offset(pgd, address);
 }
+#endif /* !__ARCH_HAS_5LEVEL_HACK */
 
 static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 {
-- 
GitLab


From 30ec842660bd0d056d4a7028ac5bd4a82b113d4f Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 17:24:04 +0300
Subject: [PATCH 854/898] asm-generic: introduce __ARCH_USE_5LEVEL_HACK

We are going to introduce <asm-generic/pgtable-nop4d.h> to provide
abstraction for properly (in opposite to 5level-fixup.h hack) folded
p4d level. The new header will be included from pgtable-nopud.h.

If an architecture uses <asm-generic/nop*d.h>, we cannot use
5level-fixup.h directly to quickly convert the architecture to 5-level
paging as it would conflict with pgtable-nop4d.h.

With this patch an architecture can define __ARCH_USE_5LEVEL_HACK before
inclusion <asm-genenric/nop*d.h> to use 5level-fixup.h.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/pgtable-nop4d-hack.h | 62 ++++++++++++++++++++++++
 include/asm-generic/pgtable-nopud.h      |  5 ++
 2 files changed, 67 insertions(+)
 create mode 100644 include/asm-generic/pgtable-nop4d-hack.h

diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h
new file mode 100644
index 000000000000..752fb7511750
--- /dev/null
+++ b/include/asm-generic/pgtable-nop4d-hack.h
@@ -0,0 +1,62 @@
+#ifndef _PGTABLE_NOP4D_HACK_H
+#define _PGTABLE_NOP4D_HACK_H
+
+#ifndef __ASSEMBLY__
+#include <asm-generic/5level-fixup.h>
+
+#define __PAGETABLE_PUD_FOLDED
+
+/*
+ * Having the pud type consist of a pgd gets the size right, and allows
+ * us to conceptually access the pgd entry that this pud is folded into
+ * without casting.
+ */
+typedef struct { pgd_t pgd; } pud_t;
+
+#define PUD_SHIFT	PGDIR_SHIFT
+#define PTRS_PER_PUD	1
+#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pud is never bad, and a pud always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd)		{ return 0; }
+static inline int pgd_bad(pgd_t pgd)		{ return 0; }
+static inline int pgd_present(pgd_t pgd)	{ return 1; }
+static inline void pgd_clear(pgd_t *pgd)	{ }
+#define pud_ERROR(pud)				(pgd_ERROR((pud).pgd))
+
+#define pgd_populate(mm, pgd, pud)		do { } while (0)
+/*
+ * (puds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pgd(pgdptr, pgdval)	set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
+
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+{
+	return (pud_t *)pgd;
+}
+
+#define pud_val(x)				(pgd_val((x).pgd))
+#define __pud(x)				((pud_t) { __pgd(x) })
+
+#define pgd_page(pgd)				(pud_page((pud_t){ pgd }))
+#define pgd_page_vaddr(pgd)			(pud_page_vaddr((pud_t){ pgd }))
+
+/*
+ * allocating and freeing a pud is trivial: the 1-entry pud is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+#define pud_alloc_one(mm, address)		NULL
+#define pud_free(mm, x)				do { } while (0)
+#define __pud_free_tlb(tlb, x, a)		do { } while (0)
+
+#undef  pud_addr_end
+#define pud_addr_end(addr, end)			(end)
+
+#endif /* __ASSEMBLY__ */
+#endif /* _PGTABLE_NOP4D_HACK_H */
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index 810431d8351b..5e49430a30a4 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -3,6 +3,10 @@
 
 #ifndef __ASSEMBLY__
 
+#ifdef __ARCH_USE_5LEVEL_HACK
+#include <asm-generic/pgtable-nop4d-hack.h>
+#else
+
 #define __PAGETABLE_PUD_FOLDED
 
 /*
@@ -58,4 +62,5 @@ static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
 #define pud_addr_end(addr, end)			(end)
 
 #endif /* __ASSEMBLY__ */
+#endif /* !__ARCH_USE_5LEVEL_HACK */
 #endif /* _PGTABLE_NOPUD_H */
-- 
GitLab


From 9849a5697d3defb2087cb6b9be5573a142697889 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 17:24:05 +0300
Subject: [PATCH 855/898] arch, mm: convert all architectures to use
 5level-fixup.h

If an architecture uses 4level-fixup.h we don't need to do anything as
it includes 5level-fixup.h.

If an architecture uses pgtable-nop*d.h, define __ARCH_USE_5LEVEL_HACK
before inclusion of the header. It makes asm-generic code to use
5level-fixup.h.

If an architecture has 4-level paging or folds levels on its own,
include 5level-fixup.h directly.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/include/asm/hugepage.h                  | 1 +
 arch/arc/include/asm/pgtable.h                   | 1 +
 arch/arm/include/asm/pgtable.h                   | 1 +
 arch/arm64/include/asm/pgtable-types.h           | 4 ++++
 arch/avr32/include/asm/pgtable-2level.h          | 1 +
 arch/cris/include/asm/pgtable.h                  | 1 +
 arch/frv/include/asm/pgtable.h                   | 1 +
 arch/h8300/include/asm/pgtable.h                 | 1 +
 arch/hexagon/include/asm/pgtable.h               | 1 +
 arch/ia64/include/asm/pgtable.h                  | 2 ++
 arch/metag/include/asm/pgtable.h                 | 1 +
 arch/microblaze/include/asm/page.h               | 3 ++-
 arch/mips/include/asm/pgtable-32.h               | 1 +
 arch/mips/include/asm/pgtable-64.h               | 1 +
 arch/mn10300/include/asm/page.h                  | 1 +
 arch/nios2/include/asm/pgtable.h                 | 1 +
 arch/openrisc/include/asm/pgtable.h              | 1 +
 arch/powerpc/include/asm/book3s/32/pgtable.h     | 1 +
 arch/powerpc/include/asm/book3s/64/pgtable.h     | 3 +++
 arch/powerpc/include/asm/nohash/32/pgtable.h     | 1 +
 arch/powerpc/include/asm/nohash/64/pgtable-4k.h  | 3 +++
 arch/powerpc/include/asm/nohash/64/pgtable-64k.h | 1 +
 arch/s390/include/asm/pgtable.h                  | 1 +
 arch/score/include/asm/pgtable.h                 | 1 +
 arch/sh/include/asm/pgtable-2level.h             | 1 +
 arch/sh/include/asm/pgtable-3level.h             | 1 +
 arch/sparc/include/asm/pgtable_64.h              | 1 +
 arch/tile/include/asm/pgtable_32.h               | 1 +
 arch/tile/include/asm/pgtable_64.h               | 1 +
 arch/um/include/asm/pgtable-2level.h             | 1 +
 arch/um/include/asm/pgtable-3level.h             | 1 +
 arch/unicore32/include/asm/pgtable.h             | 1 +
 arch/x86/include/asm/pgtable_types.h             | 4 ++++
 arch/xtensa/include/asm/pgtable.h                | 1 +
 34 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index 317ff773e1ca..b18fcb606908 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -11,6 +11,7 @@
 #define _ASM_ARC_HUGEPAGE_H
 
 #include <linux/types.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline pte_t pmd_pte(pmd_t pmd)
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index e94ca72b974e..ee22d40afef4 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -37,6 +37,7 @@
 
 #include <asm/page.h>
 #include <asm/mmu.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <linux/const.h>
 
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index a8d656d9aec7..1c462381c225 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -20,6 +20,7 @@
 
 #else
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h
index 69b2fd41503c..345a072b5856 100644
--- a/arch/arm64/include/asm/pgtable-types.h
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -55,9 +55,13 @@ typedef struct { pteval_t pgprot; } pgprot_t;
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
 #if CONFIG_PGTABLE_LEVELS == 2
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #elif CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
+#elif CONFIG_PGTABLE_LEVELS == 4
+#include <asm-generic/5level-fixup.h>
 #endif
 
 #endif	/* __ASM_PGTABLE_TYPES_H */
diff --git a/arch/avr32/include/asm/pgtable-2level.h b/arch/avr32/include/asm/pgtable-2level.h
index 425dd567b5b9..d5b1c63993ec 100644
--- a/arch/avr32/include/asm/pgtable-2level.h
+++ b/arch/avr32/include/asm/pgtable-2level.h
@@ -8,6 +8,7 @@
 #ifndef __ASM_AVR32_PGTABLE_2LEVEL_H
 #define __ASM_AVR32_PGTABLE_2LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /*
diff --git a/arch/cris/include/asm/pgtable.h b/arch/cris/include/asm/pgtable.h
index 2a3210ba4c72..fa3a73004cc5 100644
--- a/arch/cris/include/asm/pgtable.h
+++ b/arch/cris/include/asm/pgtable.h
@@ -6,6 +6,7 @@
 #define _CRIS_PGTABLE_H
 
 #include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h
index a0513d463a1f..ab6e7e961b54 100644
--- a/arch/frv/include/asm/pgtable.h
+++ b/arch/frv/include/asm/pgtable.h
@@ -16,6 +16,7 @@
 #ifndef _ASM_PGTABLE_H
 #define _ASM_PGTABLE_H
 
+#include <asm-generic/5level-fixup.h>
 #include <asm/mem-layout.h>
 #include <asm/setup.h>
 #include <asm/processor.h>
diff --git a/arch/h8300/include/asm/pgtable.h b/arch/h8300/include/asm/pgtable.h
index 8341db67821d..7d265d28ba5e 100644
--- a/arch/h8300/include/asm/pgtable.h
+++ b/arch/h8300/include/asm/pgtable.h
@@ -1,5 +1,6 @@
 #ifndef _H8300_PGTABLE_H
 #define _H8300_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm-generic/pgtable.h>
 #define pgtable_cache_init()   do { } while (0)
diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h
index 49eab8136ec3..24a9177fb897 100644
--- a/arch/hexagon/include/asm/pgtable.h
+++ b/arch/hexagon/include/asm/pgtable.h
@@ -26,6 +26,7 @@
  */
 #include <linux/swap.h>
 #include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* A handy thing to have if one has the RAM. Declared in head.S */
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 384794e665fc..6cc22c8d8923 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -587,8 +587,10 @@ extern struct page *zero_page_memmap_ptr;
 
 
 #if CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #endif
+#include <asm-generic/5level-fixup.h>
 #include <asm-generic/pgtable.h>
 
 #endif /* _ASM_IA64_PGTABLE_H */
diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h
index ffa3a3a2ecad..0c151e5af079 100644
--- a/arch/metag/include/asm/pgtable.h
+++ b/arch/metag/include/asm/pgtable.h
@@ -6,6 +6,7 @@
 #define _METAG_PGTABLE_H
 
 #include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */
diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h
index fd850879854d..d506bb0893f9 100644
--- a/arch/microblaze/include/asm/page.h
+++ b/arch/microblaze/include/asm/page.h
@@ -95,7 +95,8 @@ typedef struct { unsigned long pgd; } pgd_t;
 #   else /* CONFIG_MMU */
 typedef struct { unsigned long	ste[64]; }	pmd_t;
 typedef struct { pmd_t		pue[1]; }	pud_t;
-typedef struct { pud_t		pge[1]; }	pgd_t;
+typedef struct { pud_t		p4e[1]; }	p4d_t;
+typedef struct { p4d_t		pge[1]; }	pgd_t;
 #   endif /* CONFIG_MMU */
 
 # define pte_val(x)	((x).pte)
diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h
index d21f3da7bdb6..6f94bed571c4 100644
--- a/arch/mips/include/asm/pgtable-32.h
+++ b/arch/mips/include/asm/pgtable-32.h
@@ -16,6 +16,7 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 extern int temp_tlb_entry;
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 514cbc0a6a67..130a2a6c1531 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -17,6 +17,7 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
+#define __ARCH_USE_5LEVEL_HACK
 #if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48)
 #include <asm-generic/pgtable-nopmd.h>
 #else
diff --git a/arch/mn10300/include/asm/page.h b/arch/mn10300/include/asm/page.h
index 3810a6f740fd..dfe730a5ede0 100644
--- a/arch/mn10300/include/asm/page.h
+++ b/arch/mn10300/include/asm/page.h
@@ -57,6 +57,7 @@ typedef struct page *pgtable_t;
 #define __pgd(x)	((pgd_t) { (x) })
 #define __pgprot(x)	((pgprot_t) { (x) })
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h
index 298393c3cb42..db4f7d179220 100644
--- a/arch/nios2/include/asm/pgtable.h
+++ b/arch/nios2/include/asm/pgtable.h
@@ -22,6 +22,7 @@
 #include <asm/tlbflush.h>
 
 #include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #define FIRST_USER_ADDRESS	0UL
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index 3567aa7be555..ff97374ca069 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -25,6 +25,7 @@
 #ifndef __ASM_OPENRISC_PGTABLE_H
 #define __ASM_OPENRISC_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 012223638815..26ed228d4dc6 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
 #define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #include <asm/book3s/32/hash.h>
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 1eeeb72c7015..13c39b6d5d64 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1,9 +1,12 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 
+#include <asm-generic/5level-fixup.h>
+
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
 #endif
+
 /*
  * Common bits between hash and Radix page table
  */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index ba9921bf202e..5134ade2e850 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H
 #define _ASM_POWERPC_NOHASH_32_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
index d0db98793dd8..9f4de0a1035e 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
@@ -1,5 +1,8 @@
 #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
 #define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
+
+#include <asm-generic/5level-fixup.h>
+
 /*
  * Entries per page directory level.  The PTE level must use a 64b record
  * for each page table entry.  The PMD and PGD level use a 32b record for
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
index 55b28ef3409a..1facb584dd29 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
 #define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 7ed1972b1920..93e37b12e882 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -24,6 +24,7 @@
  * the S390 page table tree.
  */
 #ifndef __ASSEMBLY__
+#include <asm-generic/5level-fixup.h>
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
diff --git a/arch/score/include/asm/pgtable.h b/arch/score/include/asm/pgtable.h
index 0553e5cd5985..46ff8fd678a7 100644
--- a/arch/score/include/asm/pgtable.h
+++ b/arch/score/include/asm/pgtable.h
@@ -2,6 +2,7 @@
 #define _ASM_SCORE_PGTABLE_H
 
 #include <linux/const.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #include <asm/fixmap.h>
diff --git a/arch/sh/include/asm/pgtable-2level.h b/arch/sh/include/asm/pgtable-2level.h
index 19bd89db17e7..f75cf4387257 100644
--- a/arch/sh/include/asm/pgtable-2level.h
+++ b/arch/sh/include/asm/pgtable-2level.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_SH_PGTABLE_2LEVEL_H
 #define __ASM_SH_PGTABLE_2LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /*
diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h
index 249a985d9648..9b1e776eca31 100644
--- a/arch/sh/include/asm/pgtable-3level.h
+++ b/arch/sh/include/asm/pgtable-3level.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_SH_PGTABLE_3LEVEL_H
 #define __ASM_SH_PGTABLE_3LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 /*
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 56e49c8f770d..8a598528ec1f 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -12,6 +12,7 @@
  * the SpitFire page tables.
  */
 
+#include <asm-generic/5level-fixup.h>
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <asm/types.h>
diff --git a/arch/tile/include/asm/pgtable_32.h b/arch/tile/include/asm/pgtable_32.h
index d26a42279036..5f8c615cb5e9 100644
--- a/arch/tile/include/asm/pgtable_32.h
+++ b/arch/tile/include/asm/pgtable_32.h
@@ -74,6 +74,7 @@ extern unsigned long VMALLOC_RESERVE /* = CONFIG_VMALLOC_RESERVE */;
 #define MAXMEM		(_VMALLOC_START - PAGE_OFFSET)
 
 /* We have no pmd or pud since we are strictly a two-level page table */
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline int pud_huge_page(pud_t pud)	{ return 0; }
diff --git a/arch/tile/include/asm/pgtable_64.h b/arch/tile/include/asm/pgtable_64.h
index e96cec52f6d8..96fe58b45118 100644
--- a/arch/tile/include/asm/pgtable_64.h
+++ b/arch/tile/include/asm/pgtable_64.h
@@ -59,6 +59,7 @@
 #ifndef __ASSEMBLY__
 
 /* We have no pud since we are a three-level page table. */
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 /*
diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h
index cfbe59752469..179c0ea87a0c 100644
--- a/arch/um/include/asm/pgtable-2level.h
+++ b/arch/um/include/asm/pgtable-2level.h
@@ -8,6 +8,7 @@
 #ifndef __UM_PGTABLE_2LEVEL_H
 #define __UM_PGTABLE_2LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* PGDIR_SHIFT determines what a third-level page table entry can map */
diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h
index bae8523a162f..c4d876dfb9ac 100644
--- a/arch/um/include/asm/pgtable-3level.h
+++ b/arch/um/include/asm/pgtable-3level.h
@@ -7,6 +7,7 @@
 #ifndef __UM_PGTABLE_3LEVEL_H
 #define __UM_PGTABLE_3LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 /* PGDIR_SHIFT determines what a third-level page table entry can map */
diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h
index 818d0f5598e3..a4f2bef37e70 100644
--- a/arch/unicore32/include/asm/pgtable.h
+++ b/arch/unicore32/include/asm/pgtable.h
@@ -12,6 +12,7 @@
 #ifndef __UNICORE_PGTABLE_H__
 #define __UNICORE_PGTABLE_H__
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <asm/cpu-single.h>
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 8b4de22d6429..62484333673d 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -273,6 +273,8 @@ static inline pgdval_t pgd_flags(pgd_t pgd)
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
+#include <asm-generic/5level-fixup.h>
+
 typedef struct { pudval_t pud; } pud_t;
 
 static inline pud_t native_make_pud(pmdval_t val)
@@ -285,6 +287,7 @@ static inline pudval_t native_pud_val(pud_t pud)
 	return pud.pud;
 }
 #else
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 static inline pudval_t native_pud_val(pud_t pud)
@@ -306,6 +309,7 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 	return pmd.pmd;
 }
 #else
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline pmdval_t native_pmd_val(pmd_t pmd)
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 8aa0e0d9cbb2..30dd5b2e4ad5 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -11,6 +11,7 @@
 #ifndef _XTENSA_PGTABLE_H
 #define _XTENSA_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <asm/page.h>
 #include <asm/kmem_layout.h>
-- 
GitLab


From 048456dcf2c56ad6f6248e2899dda92fb6a613f6 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 17:24:06 +0300
Subject: [PATCH 856/898] asm-generic: introduce <asm-generic/pgtable-nop4d.h>

Like with pgtable-nopud.h for 4-level paging, this new header is base
for converting an architectures to properly folded p4d_t level.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/pgtable-nop4d.h | 56 +++++++++++++++++++++++++++++
 include/asm-generic/pgtable-nopud.h | 43 +++++++++++-----------
 include/asm-generic/tlb.h           | 14 ++++++--
 3 files changed, 89 insertions(+), 24 deletions(-)
 create mode 100644 include/asm-generic/pgtable-nop4d.h

diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
new file mode 100644
index 000000000000..de364ecb8df6
--- /dev/null
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -0,0 +1,56 @@
+#ifndef _PGTABLE_NOP4D_H
+#define _PGTABLE_NOP4D_H
+
+#ifndef __ASSEMBLY__
+
+#define __PAGETABLE_P4D_FOLDED
+
+typedef struct { pgd_t pgd; } p4d_t;
+
+#define P4D_SHIFT	PGDIR_SHIFT
+#define PTRS_PER_P4D	1
+#define P4D_SIZE	(1UL << P4D_SHIFT)
+#define P4D_MASK	(~(P4D_SIZE-1))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the p4d is never bad, and a p4d always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd)		{ return 0; }
+static inline int pgd_bad(pgd_t pgd)		{ return 0; }
+static inline int pgd_present(pgd_t pgd)	{ return 1; }
+static inline void pgd_clear(pgd_t *pgd)	{ }
+#define p4d_ERROR(p4d)				(pgd_ERROR((p4d).pgd))
+
+#define pgd_populate(mm, pgd, p4d)		do { } while (0)
+/*
+ * (p4ds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pgd(pgdptr, pgdval)	set_p4d((p4d_t *)(pgdptr), (p4d_t) { pgdval })
+
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	return (p4d_t *)pgd;
+}
+
+#define p4d_val(x)				(pgd_val((x).pgd))
+#define __p4d(x)				((p4d_t) { __pgd(x) })
+
+#define pgd_page(pgd)				(p4d_page((p4d_t){ pgd }))
+#define pgd_page_vaddr(pgd)			(p4d_page_vaddr((p4d_t){ pgd }))
+
+/*
+ * allocating and freeing a p4d is trivial: the 1-entry p4d is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+#define p4d_alloc_one(mm, address)		NULL
+#define p4d_free(mm, x)				do { } while (0)
+#define __p4d_free_tlb(tlb, x, a)		do { } while (0)
+
+#undef  p4d_addr_end
+#define p4d_addr_end(addr, end)			(end)
+
+#endif /* __ASSEMBLY__ */
+#endif /* _PGTABLE_NOP4D_H */
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index 5e49430a30a4..c2b9b96d6268 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -6,53 +6,54 @@
 #ifdef __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nop4d-hack.h>
 #else
+#include <asm-generic/pgtable-nop4d.h>
 
 #define __PAGETABLE_PUD_FOLDED
 
 /*
- * Having the pud type consist of a pgd gets the size right, and allows
- * us to conceptually access the pgd entry that this pud is folded into
+ * Having the pud type consist of a p4d gets the size right, and allows
+ * us to conceptually access the p4d entry that this pud is folded into
  * without casting.
  */
-typedef struct { pgd_t pgd; } pud_t;
+typedef struct { p4d_t p4d; } pud_t;
 
-#define PUD_SHIFT	PGDIR_SHIFT
+#define PUD_SHIFT	P4D_SHIFT
 #define PTRS_PER_PUD	1
 #define PUD_SIZE  	(1UL << PUD_SHIFT)
 #define PUD_MASK  	(~(PUD_SIZE-1))
 
 /*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * The "p4d_xxx()" functions here are trivial for a folded two-level
  * setup: the pud is never bad, and a pud always exists (as it's folded
- * into the pgd entry)
+ * into the p4d entry)
  */
-static inline int pgd_none(pgd_t pgd)		{ return 0; }
-static inline int pgd_bad(pgd_t pgd)		{ return 0; }
-static inline int pgd_present(pgd_t pgd)	{ return 1; }
-static inline void pgd_clear(pgd_t *pgd)	{ }
-#define pud_ERROR(pud)				(pgd_ERROR((pud).pgd))
+static inline int p4d_none(p4d_t p4d)		{ return 0; }
+static inline int p4d_bad(p4d_t p4d)		{ return 0; }
+static inline int p4d_present(p4d_t p4d)	{ return 1; }
+static inline void p4d_clear(p4d_t *p4d)	{ }
+#define pud_ERROR(pud)				(p4d_ERROR((pud).p4d))
 
-#define pgd_populate(mm, pgd, pud)		do { } while (0)
+#define p4d_populate(mm, p4d, pud)		do { } while (0)
 /*
- * (puds are folded into pgds so this doesn't get actually called,
+ * (puds are folded into p4ds so this doesn't get actually called,
  * but the define is needed for a generic inline function.)
  */
-#define set_pgd(pgdptr, pgdval)			set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
+#define set_p4d(p4dptr, p4dval)	set_pud((pud_t *)(p4dptr), (pud_t) { p4dval })
 
-static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 {
-	return (pud_t *)pgd;
+	return (pud_t *)p4d;
 }
 
-#define pud_val(x)				(pgd_val((x).pgd))
-#define __pud(x)				((pud_t) { __pgd(x) } )
+#define pud_val(x)				(p4d_val((x).p4d))
+#define __pud(x)				((pud_t) { __p4d(x) })
 
-#define pgd_page(pgd)				(pud_page((pud_t){ pgd }))
-#define pgd_page_vaddr(pgd)			(pud_page_vaddr((pud_t){ pgd }))
+#define p4d_page(p4d)				(pud_page((pud_t){ p4d }))
+#define p4d_page_vaddr(p4d)			(pud_page_vaddr((pud_t){ p4d }))
 
 /*
  * allocating and freeing a pud is trivial: the 1-entry pud is
- * inside the pgd, so has no extra memory associated with it.
+ * inside the p4d, so has no extra memory associated with it.
  */
 #define pud_alloc_one(mm, address)		NULL
 #define pud_free(mm, x)				do { } while (0)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 4329bc6ef04b..8afa4335e5b2 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -270,6 +270,12 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 
+#define pmd_free_tlb(tlb, pmdp, address)			\
+	do {							\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__pmd_free_tlb(tlb, pmdp, address);		\
+	} while (0)
+
 #ifndef __ARCH_HAS_4LEVEL_HACK
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
@@ -278,11 +284,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 	} while (0)
 #endif
 
-#define pmd_free_tlb(tlb, pmdp, address)			\
+#ifndef __ARCH_HAS_5LEVEL_HACK
+#define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		__pmd_free_tlb(tlb, pmdp, address);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
+#endif
 
 #define tlb_migrate_finish(mm) do {} while (0)
 
-- 
GitLab


From c2febafc67734a62196c1b9dfba926412d4077ba Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 17:24:07 +0300
Subject: [PATCH 857/898] mm: convert generic code to 5-level paging

Convert all non-architecture-specific code to 5-level paging.

It's mostly mechanical adding handling one more page table level in
places where we deal with pud_t.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/misc/sgi-gru/grufault.c |   9 +-
 fs/userfaultfd.c                |   6 +-
 include/asm-generic/pgtable.h   |  48 +++++++-
 include/linux/hugetlb.h         |   5 +-
 include/linux/kasan.h           |   1 +
 include/linux/mm.h              |  31 ++++-
 lib/ioremap.c                   |  39 +++++-
 mm/gup.c                        |  46 ++++++-
 mm/huge_memory.c                |   7 +-
 mm/hugetlb.c                    |  29 +++--
 mm/kasan/kasan_init.c           |  44 ++++++-
 mm/memory.c                     | 207 ++++++++++++++++++++++++++------
 mm/mlock.c                      |   1 +
 mm/mprotect.c                   |  26 +++-
 mm/mremap.c                     |  13 +-
 mm/page_vma_mapped.c            |   6 +-
 mm/pagewalk.c                   |  32 ++++-
 mm/pgtable-generic.c            |   6 +
 mm/rmap.c                       |   7 +-
 mm/sparse-vmemmap.c             |  22 +++-
 mm/swapfile.c                   |  26 +++-
 mm/userfaultfd.c                |  23 ++--
 mm/vmalloc.c                    |  81 +++++++++----
 23 files changed, 595 insertions(+), 120 deletions(-)

diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index 6fb773dbcd0c..93be82fc338a 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -219,15 +219,20 @@ static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr,
 	int write, unsigned long *paddr, int *pageshift)
 {
 	pgd_t *pgdp;
-	pmd_t *pmdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
+	pmd_t *pmdp;
 	pte_t pte;
 
 	pgdp = pgd_offset(vma->vm_mm, vaddr);
 	if (unlikely(pgd_none(*pgdp)))
 		goto err;
 
-	pudp = pud_offset(pgdp, vaddr);
+	p4dp = p4d_offset(pgdp, vaddr);
+	if (unlikely(p4d_none(*p4dp)))
+		goto err;
+
+	pudp = pud_offset(p4dp, vaddr);
 	if (unlikely(pud_none(*pudp)))
 		goto err;
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 973607df579d..02ce3944d0f5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -267,6 +267,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 {
 	struct mm_struct *mm = ctx->mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
@@ -277,7 +278,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
 		goto out;
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto out;
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto out;
 	pmd = pmd_offset(pud, address);
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f4ca23b158b3..1fad160f35de 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -10,9 +10,9 @@
 #include <linux/bug.h>
 #include <linux/errno.h>
 
-#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \
-	CONFIG_PGTABLE_LEVELS
-#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED
+#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
+	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
+#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
 #endif
 
 /*
@@ -424,6 +424,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+#ifndef p4d_addr_end
+#define p4d_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK;	\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+#endif
+
 #ifndef pud_addr_end
 #define pud_addr_end(addr, end)						\
 ({	unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK;	\
@@ -444,6 +451,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
  * Do the tests inline, but report and clear the bad entry in mm/memory.c.
  */
 void pgd_clear_bad(pgd_t *);
+void p4d_clear_bad(p4d_t *);
 void pud_clear_bad(pud_t *);
 void pmd_clear_bad(pmd_t *);
 
@@ -458,6 +466,17 @@ static inline int pgd_none_or_clear_bad(pgd_t *pgd)
 	return 0;
 }
 
+static inline int p4d_none_or_clear_bad(p4d_t *p4d)
+{
+	if (p4d_none(*p4d))
+		return 1;
+	if (unlikely(p4d_bad(*p4d))) {
+		p4d_clear_bad(p4d);
+		return 1;
+	}
+	return 0;
+}
+
 static inline int pud_none_or_clear_bad(pud_t *pud)
 {
 	if (pud_none(*pud))
@@ -844,11 +863,30 @@ static inline int pmd_protnone(pmd_t pmd)
 #endif /* CONFIG_MMU */
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+
+#ifndef __PAGETABLE_P4D_FOLDED
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
+int p4d_clear_huge(p4d_t *p4d);
+#else
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
+#endif /* !__PAGETABLE_P4D_FOLDED */
+
 int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
 static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
@@ -857,6 +895,10 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
 }
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
 static inline int pud_clear_huge(pud_t *pud)
 {
 	return 0;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 503099d8aada..b857fc8cc2ec 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -122,7 +122,7 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
 int pmd_huge(pmd_t pmd);
-int pud_huge(pud_t pmd);
+int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
@@ -197,6 +197,9 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 #ifndef pgd_huge
 #define pgd_huge(x)	0
 #endif
+#ifndef p4d_huge
+#define p4d_huge(x)	0
+#endif
 
 #ifndef pgd_write
 static inline int pgd_write(pgd_t pgd)
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index ceb3fe78a0d3..1c823bef4c15 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -18,6 +18,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE];
 extern pte_t kasan_zero_pte[PTRS_PER_PTE];
 extern pmd_t kasan_zero_pmd[PTRS_PER_PMD];
 extern pud_t kasan_zero_pud[PTRS_PER_PUD];
+extern p4d_t kasan_zero_p4d[PTRS_PER_P4D];
 
 void kasan_populate_zero_shadow(const void *shadow_start,
 				const void *shadow_end);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index be1fe264eb37..5f01c88f0800 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1560,14 +1560,24 @@ static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
 	return ptep;
 }
 
+#ifdef __PAGETABLE_P4D_FOLDED
+static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
+						unsigned long address)
+{
+	return 0;
+}
+#else
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+#endif
+
 #ifdef __PAGETABLE_PUD_FOLDED
-static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
+static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
 						unsigned long address)
 {
 	return 0;
 }
 #else
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
 #endif
 
 #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
@@ -1621,10 +1631,18 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
 #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
 
 #ifndef __ARCH_HAS_5LEVEL_HACK
-static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
+		unsigned long address)
+{
+	return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ?
+		NULL : p4d_offset(pgd, address);
+}
+
+static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d,
+		unsigned long address)
 {
-	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
-		NULL: pud_offset(pgd, address);
+	return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ?
+		NULL : pud_offset(p4d, address);
 }
 #endif /* !__ARCH_HAS_5LEVEL_HACK */
 
@@ -2388,7 +2406,8 @@ void sparse_mem_maps_populate_node(struct page **map_map,
 
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
-pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
+p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
+pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);
diff --git a/lib/ioremap.c b/lib/ioremap.c
index a3e14ce92a56..4bb30206b942 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -14,6 +14,7 @@
 #include <asm/pgtable.h>
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+static int __read_mostly ioremap_p4d_capable;
 static int __read_mostly ioremap_pud_capable;
 static int __read_mostly ioremap_pmd_capable;
 static int __read_mostly ioremap_huge_disabled;
@@ -35,6 +36,11 @@ void __init ioremap_huge_init(void)
 	}
 }
 
+static inline int ioremap_p4d_enabled(void)
+{
+	return ioremap_p4d_capable;
+}
+
 static inline int ioremap_pud_enabled(void)
 {
 	return ioremap_pud_capable;
@@ -46,6 +52,7 @@ static inline int ioremap_pmd_enabled(void)
 }
 
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int ioremap_p4d_enabled(void) { return 0; }
 static inline int ioremap_pud_enabled(void) { return 0; }
 static inline int ioremap_pmd_enabled(void) { return 0; }
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
@@ -94,14 +101,14 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 	return 0;
 }
 
-static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
+static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
 	pud_t *pud;
 	unsigned long next;
 
 	phys_addr -= addr;
-	pud = pud_alloc(&init_mm, pgd, addr);
+	pud = pud_alloc(&init_mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -120,6 +127,32 @@ static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
 	return 0;
 }
 
+static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
+		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	phys_addr -= addr;
+	p4d = p4d_alloc(&init_mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (ioremap_p4d_enabled() &&
+		    ((next - addr) == P4D_SIZE) &&
+		    IS_ALIGNED(phys_addr + addr, P4D_SIZE)) {
+			if (p4d_set_huge(p4d, phys_addr + addr, prot))
+				continue;
+		}
+
+		if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 int ioremap_page_range(unsigned long addr,
 		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
@@ -135,7 +168,7 @@ int ioremap_page_range(unsigned long addr,
 	pgd = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot);
+		err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
diff --git a/mm/gup.c b/mm/gup.c
index 9c047e951aa3..c74bad1bf6e8 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned int *page_mask)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	spinlock_t *ptl;
@@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	pgd = pgd_offset(mm, address);
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		return no_page_table(vma, flags);
-
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d))
+		return no_page_table(vma, flags);
+	BUILD_BUG_ON(p4d_huge(*p4d));
+	if (unlikely(p4d_bad(*p4d)))
+		return no_page_table(vma, flags);
+	pud = pud_offset(p4d, address);
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
@@ -325,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 		struct page **page)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -338,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 	else
 		pgd = pgd_offset_gate(mm, address);
 	BUG_ON(pgd_none(*pgd));
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	BUG_ON(p4d_none(*p4d));
+	pud = pud_offset(p4d, address);
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd))
@@ -1400,13 +1409,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(&pgd, addr);
+	pudp = pud_offset(&p4d, addr);
 	do {
 		pud_t pud = READ_ONCE(*pudp);
 
@@ -1428,6 +1437,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			 int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	p4d_t *p4dp;
+
+	p4dp = p4d_offset(&pgd, addr);
+	do {
+		p4d_t p4d = READ_ONCE(*p4dp);
+
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(p4d))
+			return 0;
+		BUILD_BUG_ON(p4d_huge(p4d));
+		if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
+			if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
+					 P4D_SHIFT, next, write, pages, nr))
+				return 0;
+		} else if (!gup_p4d_range(p4d, addr, next, write, pages, nr))
+			return 0;
+	} while (p4dp++, addr = next, addr != end);
+
+	return 1;
+}
+
 /*
  * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
  * the regular GUP. It will only return non-negative values.
@@ -1478,7 +1512,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
 					 PGDIR_SHIFT, next, write, pages, &nr))
 				break;
-		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		} else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d36b2af4d1bf..e4766de25709 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2048,6 +2048,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 		bool freeze, struct page *page)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -2055,7 +2056,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 	if (!pgd_present(*pgd))
 		return;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		return;
+
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		return;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a7aa811b7d14..3d0aab9ee80d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4555,7 +4555,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	pgd_t *pgd = pgd_offset(mm, *addr);
-	pud_t *pud = pud_offset(pgd, *addr);
+	p4d_t *p4d = p4d_offset(pgd, *addr);
+	pud_t *pud = pud_offset(p4d, *addr);
 
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
 	if (page_count(virt_to_page(ptep)) == 1)
@@ -4586,11 +4587,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (pud) {
 		if (sz == PUD_SIZE) {
 			pte = (pte_t *)pud;
@@ -4610,18 +4613,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd = NULL;
+	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud)) {
-			if (pud_huge(*pud))
-				return (pte_t *)pud;
-			pmd = pmd_offset(pud, addr);
-		}
-	}
+	if (!pgd_present(*pgd))
+		return NULL;
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return NULL;
+	if (pud_huge(*pud))
+		return (pte_t *)pud;
+	pmd = pmd_offset(pud, addr);
 	return (pte_t *) pmd;
 }
 
diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c
index 31238dad85fb..b96a5f773d88 100644
--- a/mm/kasan/kasan_init.c
+++ b/mm/kasan/kasan_init.c
@@ -30,6 +30,9 @@
  */
 unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
 
+#if CONFIG_PGTABLE_LEVELS > 4
+p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss;
+#endif
 #if CONFIG_PGTABLE_LEVELS > 3
 pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
 #endif
@@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr,
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
+static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr,
 				unsigned long end)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	unsigned long next;
 
 	do {
@@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
 	} while (pud++, addr = next, addr != end);
 }
 
+static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr,
+				unsigned long end)
+{
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (p4d_none(*p4d)) {
+			p4d_populate(&init_mm, p4d,
+				early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+		}
+		zero_pud_populate(p4d, addr, next);
+	} while (p4d++, addr = next, addr != end);
+}
+
 /**
  * kasan_populate_zero_shadow - populate shadow memory region with
  *                               kasan_zero_page
@@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
 		next = pgd_addr_end(addr, end);
 
 		if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) {
+			p4d_t *p4d;
 			pud_t *pud;
 			pmd_t *pmd;
 
@@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
 			 * 3,2 - level page tables where we don't have
 			 * puds,pmds, so pgd_populate(), pud_populate()
 			 * is noops.
+			 *
+			 * The ifndef is required to avoid build breakage.
+			 *
+			 * With 5level-fixup.h, pgd_populate() is not nop and
+			 * we reference kasan_zero_p4d. It's not defined
+			 * unless 5-level paging enabled.
+			 *
+			 * The ifndef can be dropped once all KASAN-enabled
+			 * architectures will switch to pgtable-nop4d.h.
 			 */
-			pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud));
-			pud = pud_offset(pgd, addr);
+#ifndef __ARCH_HAS_5LEVEL_HACK
+			pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d));
+#endif
+			p4d = p4d_offset(pgd, addr);
+			p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud));
+			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd));
 			pmd = pmd_offset(pud, addr);
 			pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte));
@@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
 			pgd_populate(&init_mm, pgd,
 				early_alloc(PAGE_SIZE, NUMA_NO_NODE));
 		}
-		zero_pud_populate(pgd, addr, next);
+		zero_p4d_populate(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
diff --git a/mm/memory.c b/mm/memory.c
index a97a4cec2e1f..7f1c2163b3ce 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	mm_dec_nr_pmds(tlb->mm);
 }
 
-static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				unsigned long floor, unsigned long ceiling)
 {
@@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	unsigned long start;
 
 	start = addr;
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
 	} while (pud++, addr = next, addr != end);
 
+	start &= P4D_MASK;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= P4D_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
+
+	pud = pud_offset(p4d, start);
+	p4d_clear(p4d);
+	pud_free_tlb(tlb, pud, start);
+}
+
+static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	unsigned long start;
+
+	start = addr;
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		free_pud_range(tlb, p4d, addr, next, floor, ceiling);
+	} while (p4d++, addr = next, addr != end);
+
 	start &= PGDIR_MASK;
 	if (start < floor)
 		return;
@@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	if (end - 1 > ceiling - 1)
 		return;
 
-	pud = pud_offset(pgd, start);
+	p4d = p4d_offset(pgd, start);
 	pgd_clear(pgd);
-	pud_free_tlb(tlb, pud, start);
+	p4d_free_tlb(tlb, p4d, start);
 }
 
 /*
@@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+		free_p4d_range(tlb, pgd, addr, next, floor, ceiling);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 			  pte_t pte, struct page *page)
 {
 	pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
-	pud_t *pud = pud_offset(pgd, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	pmd_t *pmd = pmd_offset(pud, addr);
 	struct address_space *mapping;
 	pgoff_t index;
@@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 }
 
 static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end)
 {
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
 
-	dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+	dst_pud = pud_alloc(dst_mm, dst_p4d, addr);
 	if (!dst_pud)
 		return -ENOMEM;
-	src_pud = pud_offset(src_pgd, addr);
+	src_pud = pud_offset(src_p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
@@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 	return 0;
 }
 
+static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		unsigned long addr, unsigned long end)
+{
+	p4d_t *src_p4d, *dst_p4d;
+	unsigned long next;
+
+	dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr);
+	if (!dst_p4d)
+		return -ENOMEM;
+	src_p4d = p4d_offset(src_pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(src_p4d))
+			continue;
+		if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
+						vma, addr, next))
+			return -ENOMEM;
+	} while (dst_p4d++, src_p4d++, addr = next, addr != end);
+	return 0;
+}
+
 int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		struct vm_area_struct *vma)
 {
@@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
-		if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+		if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
 					    vma, addr, next))) {
 			ret = -ENOMEM;
 			break;
@@ -1267,14 +1323,14 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 }
 
 static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
-				struct vm_area_struct *vma, pgd_t *pgd,
+				struct vm_area_struct *vma, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				struct zap_details *details)
 {
 	pud_t *pud;
 	unsigned long next;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
@@ -1295,6 +1351,25 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 	return addr;
 }
 
+static inline unsigned long zap_p4d_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				struct zap_details *details)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		next = zap_pud_range(tlb, vma, p4d, addr, next, details);
+	} while (p4d++, addr = next, addr != end);
+
+	return addr;
+}
+
 void unmap_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end,
@@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+		next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
 }
@@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
 pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 			spinlock_t **ptl)
 {
-	pgd_t *pgd = pgd_offset(mm, addr);
-	pud_t *pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		pmd_t *pmd = pmd_alloc(mm, pud, addr);
-		if (pmd) {
-			VM_BUG_ON(pmd_trans_huge(*pmd));
-			return pte_alloc_map_lock(mm, pmd, addr, ptl);
-		}
-	}
-	return NULL;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
+
+	VM_BUG_ON(pmd_trans_huge(*pmd));
+	return pte_alloc_map_lock(mm, pmd, addr, ptl);
 }
 
 /*
@@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	return 0;
 }
 
-static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 			unsigned long addr, unsigned long end,
 			unsigned long pfn, pgprot_t prot)
 {
@@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	unsigned long next;
 
 	pfn -= addr >> PAGE_SHIFT;
-	pud = pud_alloc(mm, pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	return 0;
 }
 
+static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+			unsigned long addr, unsigned long end,
+			unsigned long pfn, pgprot_t prot)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	pfn -= addr >> PAGE_SHIFT;
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		if (remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 /**
  * remap_pfn_range - remap kernel memory to userspace
  * @vma: user vma to map to
@@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	flush_cache_range(vma, addr, end);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = remap_pud_range(mm, pgd, addr, next,
+		err = remap_p4d_range(mm, pgd, addr, next,
 				pfn + (addr >> PAGE_SHIFT), prot);
 		if (err)
 			break;
@@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	return err;
 }
 
-static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
 {
@@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	unsigned long next;
 	int err;
 
-	pud = pud_alloc(mm, pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	return err;
 }
 
+static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+				     unsigned long addr, unsigned long end,
+				     pte_fn_t fn, void *data)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int err;
+
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
+		if (err)
+			break;
+	} while (p4d++, addr = next, addr != end);
+	return err;
+}
+
 /*
  * Scan a region of virtual memory, filling in page tables as necessary
  * and calling a provided function on each leaf page table.
@@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
@@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	};
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	int ret;
 
 	pgd = pgd_offset(mm, address);
+	p4d = p4d_alloc(mm, pgd, address);
+	if (!p4d)
+		return VM_FAULT_OOM;
 
-	vmf.pud = pud_alloc(mm, pgd, address);
+	vmf.pud = pud_alloc(mm, p4d, address);
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
 	if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
@@ -3784,7 +3911,7 @@ EXPORT_SYMBOL_GPL(handle_mm_fault);
  * Allocate page upper directory.
  * We've already handled the fast-path in-line.
  */
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
 {
 	pud_t *new = pud_alloc_one(mm, address);
 	if (!new)
@@ -3793,10 +3920,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 	smp_wmb(); /* See comment in __pte_alloc */
 
 	spin_lock(&mm->page_table_lock);
-	if (pgd_present(*pgd))		/* Another has populated it */
+#ifndef __ARCH_HAS_5LEVEL_HACK
+	if (p4d_present(*p4d))		/* Another has populated it */
+		pud_free(mm, new);
+	else
+		p4d_populate(mm, p4d, new);
+#else
+	if (pgd_present(*p4d))		/* Another has populated it */
 		pud_free(mm, new);
 	else
-		pgd_populate(mm, pgd, new);
+		pgd_populate(mm, p4d, new);
+#endif /* __ARCH_HAS_5LEVEL_HACK */
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
@@ -3839,6 +3973,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *ptep;
@@ -3847,7 +3982,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		goto out;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d)))
+		goto out;
+
+	pud = pud_offset(p4d, address);
 	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
 		goto out;
 
diff --git a/mm/mlock.c b/mm/mlock.c
index 1050511f8b2b..945edac46810 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -380,6 +380,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 	pte = get_locked_pte(vma->vm_mm, start,	&ptl);
 	/* Make sure we do not cross the page table boundary */
 	end = pgd_addr_end(start, end);
+	end = p4d_addr_end(start, end);
 	end = pud_addr_end(start, end);
 	end = pmd_addr_end(start, end);
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 848e946b08e5..8edd0d576254 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -193,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 }
 
 static inline unsigned long change_pud_range(struct vm_area_struct *vma,
-		pgd_t *pgd, unsigned long addr, unsigned long end,
+		p4d_t *p4d, unsigned long addr, unsigned long end,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
 {
 	pud_t *pud;
 	unsigned long next;
 	unsigned long pages = 0;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -212,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 	return pages;
 }
 
+static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
+		pgd_t *pgd, unsigned long addr, unsigned long end,
+		pgprot_t newprot, int dirty_accountable, int prot_numa)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	unsigned long pages = 0;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		pages += change_pud_range(vma, p4d, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+	} while (p4d++, addr = next, addr != end);
+
+	return pages;
+}
+
 static unsigned long change_protection_range(struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable, int prot_numa)
@@ -230,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		pages += change_pud_range(vma, pgd, addr, next, newprot,
+		pages += change_p4d_range(vma, pgd, addr, next, newprot,
 				 dirty_accountable, prot_numa);
 	} while (pgd++, addr = next, addr != end);
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 8233b0105c82..cd8a1b199ef9 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -32,6 +32,7 @@
 static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -39,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 	if (pgd_none_or_clear_bad(pgd))
 		return NULL;
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none_or_clear_bad(p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, addr);
 	if (pud_none_or_clear_bad(pud))
 		return NULL;
 
@@ -54,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 			    unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return NULL;
 
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index a23001a22c15..c4c9def8ffea 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -104,6 +104,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	struct mm_struct *mm = pvmw->vma->vm_mm;
 	struct page *page = pvmw->page;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 
 	/* The only possible pmd mapping has been handled on last iteration */
@@ -133,7 +134,10 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	pgd = pgd_offset(mm, pvmw->address);
 	if (!pgd_present(*pgd))
 		return false;
-	pud = pud_offset(pgd, pvmw->address);
+	p4d = p4d_offset(pgd, pvmw->address);
+	if (!p4d_present(*p4d))
+		return false;
+	pud = pud_offset(p4d, pvmw->address);
 	if (!pud_present(*pud))
 		return false;
 	pvmw->pmd = pmd_offset(pud, pvmw->address);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 03761577ae86..60f7856e508f 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -69,14 +69,14 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	return err;
 }
 
-static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
 	pud_t *pud;
 	unsigned long next;
 	int err = 0;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
  again:
 		next = pud_addr_end(addr, end);
@@ -113,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	return err;
 }
 
+static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int err = 0;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, next, walk);
+			if (err)
+				break;
+			continue;
+		}
+		if (walk->pmd_entry || walk->pte_entry)
+			err = walk_pud_range(p4d, addr, next, walk);
+		if (err)
+			break;
+	} while (p4d++, addr = next, addr != end);
+
+	return err;
+}
+
 static int walk_pgd_range(unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
@@ -131,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
 			continue;
 		}
 		if (walk->pmd_entry || walk->pte_entry)
-			err = walk_pud_range(pgd, addr, next, walk);
+			err = walk_p4d_range(pgd, addr, next, walk);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4ed5908c65b0..c99d9512a45b 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd)
 	pgd_clear(pgd);
 }
 
+void p4d_clear_bad(p4d_t *p4d)
+{
+	p4d_ERROR(*p4d);
+	p4d_clear(p4d);
+}
+
 void pud_clear_bad(pud_t *pud)
 {
 	pud_ERROR(*pud);
diff --git a/mm/rmap.c b/mm/rmap.c
index 2da487d6cea8..2984403a2424 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd = NULL;
 	pmd_t pmde;
@@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 	if (!pgd_present(*pgd))
 		goto out;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto out;
+
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto out;
 
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 574c67b663fe..a56c3989f773 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 	return pmd;
 }
 
-pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
+pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
 		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
@@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
 	return pud;
 }
 
+p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
+{
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d)) {
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		if (!p)
+			return NULL;
+		p4d_populate(&init_mm, p4d, p);
+	}
+	return p4d;
+}
+
 pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 {
 	pgd_t *pgd = pgd_offset_k(addr);
@@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
 {
 	unsigned long addr = start;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
 		pgd = vmemmap_pgd_populate(addr, node);
 		if (!pgd)
 			return -ENOMEM;
-		pud = vmemmap_pud_populate(pgd, addr, node);
+		p4d = vmemmap_p4d_populate(pgd, addr, node);
+		if (!p4d)
+			return -ENOMEM;
+		pud = vmemmap_pud_populate(p4d, addr, node);
 		if (!pud)
 			return -ENOMEM;
 		pmd = vmemmap_pmd_populate(pud, addr, node);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 521ef9b6064f..178130880b90 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1517,7 +1517,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	return 0;
 }
 
-static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				swp_entry_t entry, struct page *page)
 {
@@ -1525,7 +1525,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 	unsigned long next;
 	int ret;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -1537,6 +1537,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 	return 0;
 }
 
+static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				swp_entry_t entry, struct page *page)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int ret;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		ret = unuse_pud_range(vma, p4d, addr, next, entry, page);
+		if (ret)
+			return ret;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 static int unuse_vma(struct vm_area_struct *vma,
 				swp_entry_t entry, struct page *page)
 {
@@ -1560,7 +1580,7 @@ static int unuse_vma(struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		ret = unuse_pud_range(vma, pgd, addr, next, entry, page);
+		ret = unuse_p4d_range(vma, pgd, addr, next, entry, page);
 		if (ret)
 			return ret;
 	} while (pgd++, addr = next, addr != end);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 479e631d43c2..8bcb501bce60 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -128,19 +128,22 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm,
 static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd = NULL;
 
 	pgd = pgd_offset(mm, address);
-	pud = pud_alloc(mm, pgd, address);
-	if (pud)
-		/*
-		 * Note that we didn't run this because the pmd was
-		 * missing, the *pmd may be already established and in
-		 * turn it may also be a trans_huge_pmd.
-		 */
-		pmd = pmd_alloc(mm, pud, address);
-	return pmd;
+	p4d = p4d_alloc(mm, pgd, address);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, address);
+	if (!pud)
+		return NULL;
+	/*
+	 * Note that we didn't run this because the pmd was
+	 * missing, the *pmd may be already established and in
+	 * turn it may also be a trans_huge_pmd.
+	 */
+	return pmd_alloc(mm, pud, address);
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b4024d688f38..0dd80222b20b 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end)
 {
 	pud_t *pud;
 	unsigned long next;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_clear_huge(pud))
@@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
 	} while (pud++, addr = next, addr != end);
 }
 
+static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_clear_huge(p4d))
+			continue;
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		vunmap_pud_range(p4d, addr, next);
+	} while (p4d++, addr = next, addr != end);
+}
+
 static void vunmap_page_range(unsigned long addr, unsigned long end)
 {
 	pgd_t *pgd;
@@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		vunmap_pud_range(pgd, addr, next);
+		vunmap_p4d_range(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr,
 	return 0;
 }
 
-static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
 {
 	pud_t *pud;
 	unsigned long next;
 
-	pud = pud_alloc(&init_mm, pgd, addr);
+	pud = pud_alloc(&init_mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
 	return 0;
 }
 
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_alloc(&init_mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 /*
  * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
  * will have pfns corresponding to the "pages" array.
@@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end,
 	pgd = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = vmap_pud_range(pgd, addr, next, prot, pages, &nr);
+		err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
 		if (err)
 			return err;
 	} while (pgd++, addr = next, addr != end);
@@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	unsigned long addr = (unsigned long) vmalloc_addr;
 	struct page *page = NULL;
 	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *ptep, pte;
 
 	/*
 	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
@@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	 */
 	VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
 
-	if (!pgd_none(*pgd)) {
-		pud_t *pud = pud_offset(pgd, addr);
-		if (!pud_none(*pud)) {
-			pmd_t *pmd = pmd_offset(pud, addr);
-			if (!pmd_none(*pmd)) {
-				pte_t *ptep, pte;
-
-				ptep = pte_offset_map(pmd, addr);
-				pte = *ptep;
-				if (pte_present(pte))
-					page = pte_page(pte);
-				pte_unmap(ptep);
-			}
-		}
-	}
+	if (pgd_none(*pgd))
+		return NULL;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return NULL;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return NULL;
+
+	ptep = pte_offset_map(pmd, addr);
+	pte = *ptep;
+	if (pte_present(pte))
+		page = pte_page(pte);
+	pte_unmap(ptep);
 	return page;
 }
 EXPORT_SYMBOL(vmalloc_to_page);
-- 
GitLab


From 90eceff1a375f6ffa78caf8654e787c0a8a591ef Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 17:24:08 +0300
Subject: [PATCH 858/898] mm: introduce __p4d_alloc()

For full 5-level paging we need a helper to allocate p4d page table.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/mm/memory.c b/mm/memory.c
index 7f1c2163b3ce..235ba51b2fbf 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3906,6 +3906,29 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL_GPL(handle_mm_fault);
 
+#ifndef __PAGETABLE_P4D_FOLDED
+/*
+ * Allocate p4d page table.
+ * We've already handled the fast-path in-line.
+ */
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+	p4d_t *new = p4d_alloc_one(mm, address);
+	if (!new)
+		return -ENOMEM;
+
+	smp_wmb(); /* See comment in __pte_alloc */
+
+	spin_lock(&mm->page_table_lock);
+	if (pgd_present(*pgd))		/* Another has populated it */
+		p4d_free(mm, new);
+	else
+		pgd_populate(mm, pgd, new);
+	spin_unlock(&mm->page_table_lock);
+	return 0;
+}
+#endif /* __PAGETABLE_P4D_FOLDED */
+
 #ifndef __PAGETABLE_PUD_FOLDED
 /*
  * Allocate page upper directory.
-- 
GitLab


From 834e0f8ae4e104fa026ffe5cdee58491f3078403 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 8 Mar 2017 17:40:17 -0500
Subject: [PATCH 859/898] drm/amdgpu: validate paramaters in the gem ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reject it if there are any invalid flags or domains.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 51d759463384..106cf83c2e6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -202,6 +202,27 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	bool kernel = false;
 	int r;
 
+	/* reject invalid gem flags */
+	if (args->in.domain_flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+				      AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
+				      AMDGPU_GEM_CREATE_CPU_GTT_USWC |
+				      AMDGPU_GEM_CREATE_VRAM_CLEARED|
+				      AMDGPU_GEM_CREATE_SHADOW |
+				      AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
+		r = -EINVAL;
+		goto error_unlock;
+	}
+	/* reject invalid gem domains */
+	if (args->in.domains & ~(AMDGPU_GEM_DOMAIN_CPU |
+				 AMDGPU_GEM_DOMAIN_GTT |
+				 AMDGPU_GEM_DOMAIN_VRAM |
+				 AMDGPU_GEM_DOMAIN_GDS |
+				 AMDGPU_GEM_DOMAIN_GWS |
+				 AMDGPU_GEM_DOMAIN_OA)) {
+		r = -EINVAL;
+		goto error_unlock;
+	}
+
 	/* create a gem object to contain this object in */
 	if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
 	    AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
-- 
GitLab


From a5b11dac1f57c4b327c2d6eccb8fdd01499f9e17 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 8 Mar 2017 17:23:21 -0500
Subject: [PATCH 860/898] drm/amdgpu: bump driver version for some new features
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We added new gem ioctl flags and the new fences ioctl, but forgot
to bump the version.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 75fc376ba735..f7adbace428a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -59,9 +59,10 @@
  * - 3.7.0 - Add support for VCE clock list packet
  * - 3.8.0 - Add support raster config init in the kernel
  * - 3.9.0 - Add support for memory query info about VRAM and GTT.
+ * - 3.10.0 - Add support for new fences ioctl, new gem ioctl flags
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	9
+#define KMS_DRIVER_MINOR	10
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
-- 
GitLab


From 8bd49ac86677ca43d64f08c45864e438283d6a76 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 6 Mar 2017 09:57:17 +0100
Subject: [PATCH 861/898] s390: wire up statx system call

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/uapi/asm/unistd.h | 4 +++-
 arch/s390/kernel/compat_wrapper.c   | 1 +
 arch/s390/kernel/syscalls.S         | 2 ++
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 4384bc797a54..152de9b796e1 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -313,7 +313,9 @@
 #define __NR_copy_file_range	375
 #define __NR_preadv2		376
 #define __NR_pwritev2		377
-#define NR_syscalls 378
+/* Number 378 is reserved for guarded storage */
+#define __NR_statx		379
+#define NR_syscalls 380
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index ae2cda5eee5a..e89cc2e71db1 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -178,3 +178,4 @@ COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
 COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
 COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
 COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 9b59e6212d8f..2659b5cfeddb 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -386,3 +386,5 @@ SYSCALL(sys_mlock2,compat_sys_mlock2)
 SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */
 SYSCALL(sys_preadv2,compat_sys_preadv2)
 SYSCALL(sys_pwritev2,compat_sys_pwritev2)
+NI_SYSCALL
+SYSCALL(sys_statx,compat_sys_statx)
-- 
GitLab


From 6bbc4a4144b1a69743022ac68dfaf6e7d993abb9 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Thu, 9 Mar 2017 16:16:28 -0800
Subject: [PATCH 862/898] userfaultfd: shmem: __do_fault requires
 VM_FAULT_NOPAGE

__do_fault assumes vmf->page has been initialized and is valid if
VM_FAULT_NOPAGE is not returned by vma->vm_ops->fault(vma, vmf).

handle_userfault() in turn should return VM_FAULT_NOPAGE if it doesn't
return VM_FAULT_SIGBUS or VM_FAULT_RETRY (the other two possibilities).

This VM_FAULT_NOPAGE case is only invoked when signal are pending and it
didn't matter for anonymous memory before.  It only started to matter
since shmem was introduced.  hugetlbfs also takes a different path and
doesn't exercise __do_fault.

Link: http://lkml.kernel.org/r/20170228154201.GH5816@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/userfaultfd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 973607df579d..f62199b90fd0 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -490,7 +490,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 			 * in such case.
 			 */
 			down_read(&mm->mmap_sem);
-			ret = 0;
+			ret = VM_FAULT_NOPAGE;
 		}
 	}
 
-- 
GitLab


From 8a1115ff6b6d90cf1066ec3a0c4e51276553eebe Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 9 Mar 2017 16:16:31 -0800
Subject: [PATCH 863/898] scripts/spelling.txt: add "disble(d)" pattern and fix
 typo instances

Fix typos and add the following to the scripts/spelling.txt:

  disble||disable
  disbled||disabled

I kept the TSL2563_INT_DISBLED in /drivers/iio/light/tsl2563.c
untouched.  The macro is not referenced at all, but this commit is
touching only comment blocks just in case.

Link: http://lkml.kernel.org/r/1481573103-11329-20-git-send-email-yamada.masahiro@socionext.com
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/dev-tools/kcov.rst        | 2 +-
 arch/cris/arch-v32/drivers/cryptocop.c  | 2 +-
 arch/x86/kernel/ftrace.c                | 2 +-
 drivers/crypto/ux500/cryp/cryp.c        | 2 +-
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c  | 2 +-
 drivers/hv/channel.c                    | 2 +-
 drivers/isdn/hisax/st5481_b.c           | 2 +-
 drivers/mtd/spi-nor/spi-nor.c           | 2 +-
 drivers/net/ethernet/qlogic/qlge/qlge.h | 2 +-
 drivers/scsi/aic7xxx/aic79xx_core.c     | 2 +-
 drivers/usb/gadget/legacy/inode.c       | 3 +--
 drivers/usb/host/xhci.c                 | 4 ++--
 include/linux/regulator/machine.h       | 2 +-
 kernel/cgroup/cgroup.c                  | 2 +-
 kernel/events/core.c                    | 2 +-
 scripts/spelling.txt                    | 2 ++
 sound/soc/amd/acp-pcm-dma.c             | 2 +-
 17 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst
index 2c41b713841f..44886c91e112 100644
--- a/Documentation/dev-tools/kcov.rst
+++ b/Documentation/dev-tools/kcov.rst
@@ -10,7 +10,7 @@ Note that kcov does not aim to collect as much coverage as possible. It aims
 to collect more or less stable coverage that is function of syscall inputs.
 To achieve this goal it does not collect coverage in soft/hard interrupts
 and instrumentation of some inherently non-deterministic parts of kernel is
-disbled (e.g. scheduler, locking).
+disabled (e.g. scheduler, locking).
 
 Usage
 -----
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index ae6903d7fdbe..14970f11bbf2 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -2086,7 +2086,7 @@ static void cryptocop_job_queue_close(void)
 		dma_in_cfg.en = regk_dma_no;
 		REG_WR(dma, IN_DMA_INST, rw_cfg, dma_in_cfg);
 
-		/* Disble the cryptocop. */
+		/* Disable the cryptocop. */
 		rw_cfg = REG_RD(strcop, regi_strcop, rw_cfg);
 		rw_cfg.en = 0;
 		REG_WR(strcop, regi_strcop, rw_cfg, rw_cfg);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8639bb2ae058..8f3d9cf26ff9 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -535,7 +535,7 @@ static void run_sync(void)
 {
 	int enable_irqs = irqs_disabled();
 
-	/* We may be called with interrupts disbled (on bootup). */
+	/* We may be called with interrupts disabled (on bootup). */
 	if (enable_irqs)
 		local_irq_enable();
 	on_each_cpu(do_sync_core, NULL, 1);
diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c
index 43a0c8a26ab0..00a16ab601cb 100644
--- a/drivers/crypto/ux500/cryp/cryp.c
+++ b/drivers/crypto/ux500/cryp/cryp.c
@@ -82,7 +82,7 @@ void cryp_activity(struct cryp_device_data *device_data,
 void cryp_flush_inoutfifo(struct cryp_device_data *device_data)
 {
 	/*
-	 * We always need to disble the hardware before trying to flush the
+	 * We always need to disable the hardware before trying to flush the
 	 * FIFO. This is something that isn't written in the design
 	 * specification, but we have been informed by the hardware designers
 	 * that this must be done.
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 31375bdde6f1..011800f621c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -788,7 +788,7 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
 		}
 	}
 
-	/* disble sdma engine before programing it */
+	/* disable sdma engine before programing it */
 	sdma_v3_0_ctx_switch_enable(adev, false);
 	sdma_v3_0_enable(adev, false);
 
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 81a80c82f1bd..bd0d1988feb2 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -543,7 +543,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	/*
 	 * In case a device driver's probe() fails (e.g.,
 	 * util_probe() -> vmbus_open() returns -ENOMEM) and the device is
-	 * rescinded later (e.g., we dynamically disble an Integrated Service
+	 * rescinded later (e.g., we dynamically disable an Integrated Service
 	 * in Hyper-V Manager), the driver's remove() invokes vmbus_close():
 	 * here we should skip most of the below cleanup work.
 	 */
diff --git a/drivers/isdn/hisax/st5481_b.c b/drivers/isdn/hisax/st5481_b.c
index 409849165838..f64a36007800 100644
--- a/drivers/isdn/hisax/st5481_b.c
+++ b/drivers/isdn/hisax/st5481_b.c
@@ -239,7 +239,7 @@ static void st5481B_mode(struct st5481_bcs *bcs, int mode)
 			}
 		}
 	} else {
-		// Disble B channel interrupts
+		// Disable B channel interrupts
 		st5481_usb_device_ctrl_msg(adapter, FFMSK_B1+(bcs->channel * 2), 0, NULL, NULL);
 
 		// Disable B channel FIFOs
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 1ae872bfc3ba..747645c74134 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -186,7 +186,7 @@ static inline int write_enable(struct spi_nor *nor)
 }
 
 /*
- * Send write disble instruction to the chip.
+ * Send write disable instruction to the chip.
  */
 static inline int write_disable(struct spi_nor *nor)
 {
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 6d31f92ef2b6..90b3b46f85cc 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -1163,7 +1163,7 @@ struct ib_mac_iocb_rsp {
 	u8 opcode;		/* 0x20 */
 	u8 flags1;
 #define IB_MAC_IOCB_RSP_OI	0x01	/* Overide intr delay */
-#define IB_MAC_IOCB_RSP_I	0x02	/* Disble Intr Generation */
+#define IB_MAC_IOCB_RSP_I	0x02	/* Disable Intr Generation */
 #define IB_MAC_CSUM_ERR_MASK 0x1c	/* A mask to use for csum errs */
 #define IB_MAC_IOCB_RSP_TE	0x04	/* Checksum error */
 #define IB_MAC_IOCB_RSP_NU	0x08	/* No checksum rcvd */
diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c
index 109e2c99e6c1..95d8f25cbcca 100644
--- a/drivers/scsi/aic7xxx/aic79xx_core.c
+++ b/drivers/scsi/aic7xxx/aic79xx_core.c
@@ -6278,7 +6278,7 @@ ahd_reset(struct ahd_softc *ahd, int reinit)
 		 * does not disable its parity logic prior to
 		 * the start of the reset.  This may cause a
 		 * parity error to be detected and thus a
-		 * spurious SERR or PERR assertion.  Disble
+		 * spurious SERR or PERR assertion.  Disable
 		 * PERR and SERR responses during the CHIPRST.
 		 */
 		mod_cmd = cmd & ~(PCIM_CMD_PERRESPEN|PCIM_CMD_SERRESPEN);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index a2615d64d07c..79a2d8fba6b6 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -84,8 +84,7 @@ static int ep_open(struct inode *, struct file *);
 
 /* /dev/gadget/$CHIP represents ep0 and the whole device */
 enum ep0_state {
-	/* DISBLED is the initial state.
-	 */
+	/* DISABLED is the initial state. */
 	STATE_DEV_DISABLED = 0,
 
 	/* Only one open() of /dev/gadget/$CHIP; only one file tracks
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6d6c46000e56..50aee8b7718b 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -868,7 +868,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
 
 	spin_lock_irqsave(&xhci->lock, flags);
 
-	/* disble usb3 ports Wake bits*/
+	/* disable usb3 ports Wake bits */
 	port_index = xhci->num_usb3_ports;
 	port_array = xhci->usb3_ports;
 	while (port_index--) {
@@ -879,7 +879,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
 			writel(t2, port_array[port_index]);
 	}
 
-	/* disble usb2 ports Wake bits*/
+	/* disable usb2 ports Wake bits */
 	port_index = xhci->num_usb2_ports;
 	port_array = xhci->usb2_ports;
 	while (port_index--) {
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index ad3e5158e586..c9f795e9a2ee 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -65,7 +65,7 @@ struct regulator_state {
 	int uV;	/* suspend voltage */
 	unsigned int mode; /* suspend regulator operating mode */
 	int enabled; /* is regulator enabled in this suspend state */
-	int disabled; /* is the regulator disbled in this suspend state */
+	int disabled; /* is the regulator disabled in this suspend state */
 };
 
 /**
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 0125589c7428..48851327a15e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2669,7 +2669,7 @@ static bool css_visible(struct cgroup_subsys_state *css)
  *
  * Returns 0 on success, -errno on failure.  On failure, csses which have
  * been processed already aren't cleaned up.  The caller is responsible for
- * cleaning up with cgroup_apply_control_disble().
+ * cleaning up with cgroup_apply_control_disable().
  */
 static int cgroup_apply_control_enable(struct cgroup *cgrp)
 {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6f41548f2e32..a17ed56c8ce1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -998,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event,
  */
 #define PERF_CPU_HRTIMER (1000 / HZ)
 /*
- * function must be called with interrupts disbled
+ * function must be called with interrupts disabled
  */
 static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
 {
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 0458b037c8a1..6dae4df472f6 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -372,6 +372,8 @@ disassocation||disassociation
 disapear||disappear
 disapeared||disappeared
 disappared||disappeared
+disble||disable
+disbled||disabled
 disconnet||disconnect
 discontinous||discontinuous
 dispertion||dispersion
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index ec1067a679da..08b1399d1da2 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -89,7 +89,7 @@ static void acp_reg_write(u32 val, void __iomem *acp_mmio, u32 reg)
 	writel(val, acp_mmio + (reg * 4));
 }
 
-/* Configure a given dma channel parameters - enable/disble,
+/* Configure a given dma channel parameters - enable/disable,
  * number of descriptors, priority
  */
 static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num,
-- 
GitLab


From 505d3085d7120a9f4cd0d6ffaa876968854b3baa Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 9 Mar 2017 16:16:33 -0800
Subject: [PATCH 864/898] scripts/spelling.txt: add "overide" pattern and fix
 typo instances

Fix typos and add the following to the scripts/spelling.txt:

  overide||override

While we are here, fix the doubled "address" in the touched line
Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt.

Also, fix the comment block style in the touched hunks in
drivers/media/dvb-frontends/drx39xyj/drx_driver.h.

Link: http://lkml.kernel.org/r/1481573103-11329-21-git-send-email-yamada.masahiro@socionext.com
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .../devicetree/bindings/regulator/ti-abb-regulator.txt    | 2 +-
 drivers/block/paride/pcd.c                                | 2 +-
 drivers/block/paride/pd.c                                 | 2 +-
 drivers/block/paride/pf.c                                 | 2 +-
 drivers/block/paride/pg.c                                 | 2 +-
 drivers/block/paride/pt.c                                 | 2 +-
 drivers/media/dvb-frontends/drx39xyj/drx_driver.h         | 8 +++-----
 drivers/net/ethernet/qlogic/qlge/qlge.h                   | 2 +-
 include/dt-bindings/sound/cs42l42.h                       | 2 +-
 include/net/irda/timer.h                                  | 2 +-
 kernel/trace/trace_stack.c                                | 2 +-
 scripts/spelling.txt                                      | 1 +
 tools/lguest/lguest.c                                     | 2 +-
 tools/lib/bpf/Makefile                                    | 2 +-
 tools/lib/traceevent/Makefile                             | 2 +-
 tools/lib/traceevent/event-parse.h                        | 2 +-
 16 files changed, 18 insertions(+), 19 deletions(-)

diff --git a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
index c3f6546ebac7..6a23ad9ac53a 100644
--- a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
@@ -45,7 +45,7 @@ Required Properties:
 Optional Properties:
 - reg-names: In addition to the required properties, the following are optional
   - "efuse-address"	- Contains efuse base address used to pick up ABB info.
-  - "ldo-address"	- Contains address of ABB LDO overide register address.
+  - "ldo-address"	- Contains address of ABB LDO override register.
 	"efuse-address" is required for this.
 - ti,ldovbb-vset-mask	- Required if ldo-address is set, mask for LDO override
 	register to provide override vset value.
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 10aed84244f5..939641d6e262 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -50,7 +50,7 @@
                         the slower the port i/o.  In some cases, setting
                         this to zero will speed up the device. (default -1)
                         
-            major       You may use this parameter to overide the
+            major       You may use this parameter to override the
                         default major number (46) that this driver
                         will use.  Be sure to change the device
                         name as well.
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 644ba0888bd4..9cfd2e06a649 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -61,7 +61,7 @@
                         first drive found.
 			
 
-            major       You may use this parameter to overide the
+            major       You may use this parameter to override the
                         default major number (45) that this driver
                         will use.  Be sure to change the device
                         name as well.
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index ed93e8badf56..14c5d32f5d8b 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -59,7 +59,7 @@
                         the slower the port i/o.  In some cases, setting
                         this to zero will speed up the device. (default -1)
 
-	    major	You may use this parameter to overide the
+	    major	You may use this parameter to override the
 			default major number (47) that this driver
 			will use.  Be sure to change the device
 			name as well.
diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c
index 5db955fe3a94..3b5882bfb736 100644
--- a/drivers/block/paride/pg.c
+++ b/drivers/block/paride/pg.c
@@ -84,7 +84,7 @@
 			the slower the port i/o.  In some cases, setting
 			this to zero will speed up the device. (default -1)
 
-	    major	You may use this parameter to overide the
+	    major	You may use this parameter to override the
 			default major number (97) that this driver
 			will use.  Be sure to change the device
 			name as well.
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 61fc6824299a..e815312a00ad 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -61,7 +61,7 @@
                         the slower the port i/o.  In some cases, setting
                         this to zero will speed up the device. (default -1)
 
-	    major	You may use this parameter to overide the
+	    major	You may use this parameter to override the
 			default major number (96) that this driver
 			will use.  Be sure to change the device
 			name as well.
diff --git a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
index 7a681d8202c7..4442e478db72 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
+++ b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
@@ -256,8 +256,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
 *
 * The actual DAP implementation may be restricted to only one of the modes.
 * A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the mode defined below.
-*
+* overrides or cannot handle the mode defined below.
 */
 #ifndef DRXDAP_SINGLE_MASTER
 #define DRXDAP_SINGLE_MASTER 1
@@ -272,7 +271,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
 *
 * This maximum size may be restricted by the actual DAP implementation.
 * A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the chunksize defined below.
+* overrides or cannot handle the chunksize defined below.
 *
 * Beware that the DAP uses  DRXDAP_MAX_WCHUNKSIZE to create a temporary data
 * buffer. Do not undefine or choose too large, unless your system is able to
@@ -292,8 +291,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
 *
 * This maximum size may be restricted by the actual DAP implementation.
 * A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the chunksize defined below.
-*
+* overrides or cannot handle the chunksize defined below.
 */
 #ifndef DRXDAP_MAX_RCHUNKSIZE
 #define  DRXDAP_MAX_RCHUNKSIZE 60
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 90b3b46f85cc..84ac50f92c9c 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -1162,7 +1162,7 @@ struct ob_mac_tso_iocb_rsp {
 struct ib_mac_iocb_rsp {
 	u8 opcode;		/* 0x20 */
 	u8 flags1;
-#define IB_MAC_IOCB_RSP_OI	0x01	/* Overide intr delay */
+#define IB_MAC_IOCB_RSP_OI	0x01	/* Override intr delay */
 #define IB_MAC_IOCB_RSP_I	0x02	/* Disable Intr Generation */
 #define IB_MAC_CSUM_ERR_MASK 0x1c	/* A mask to use for csum errs */
 #define IB_MAC_IOCB_RSP_TE	0x04	/* Checksum error */
diff --git a/include/dt-bindings/sound/cs42l42.h b/include/dt-bindings/sound/cs42l42.h
index 399a123aed58..db69d84ed7d1 100644
--- a/include/dt-bindings/sound/cs42l42.h
+++ b/include/dt-bindings/sound/cs42l42.h
@@ -20,7 +20,7 @@
 #define CS42L42_HPOUT_LOAD_1NF		0
 #define CS42L42_HPOUT_LOAD_10NF		1
 
-/* HPOUT Clamp to GND Overide */
+/* HPOUT Clamp to GND Override */
 #define CS42L42_HPOUT_CLAMP_EN		0
 #define CS42L42_HPOUT_CLAMP_DIS		1
 
diff --git a/include/net/irda/timer.h b/include/net/irda/timer.h
index cb2615ccf761..d784f242cf7b 100644
--- a/include/net/irda/timer.h
+++ b/include/net/irda/timer.h
@@ -59,7 +59,7 @@ struct lap_cb;
  *  Slot timer must never exceed 85 ms, and must always be at least 25 ms, 
  *  suggested to  75-85 msec by IrDA lite. This doesn't work with a lot of
  *  devices, and other stackes uses a lot more, so it's best we do it as well
- *  (Note : this is the default value and sysctl overides it - Jean II)
+ *  (Note : this is the default value and sysctl overrides it - Jean II)
  */
 #define SLOT_TIMEOUT            (90*HZ/1000)
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 1d68b5b7ad41..5fb1f2c87e6b 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -65,7 +65,7 @@ void stack_trace_print(void)
 }
 
 /*
- * When arch-specific code overides this function, the following
+ * When arch-specific code overrides this function, the following
  * data should be filled up, assuming stack_trace_max_lock is held to
  * prevent concurrent updates.
  *     stack_trace_index[]
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 6dae4df472f6..0545f5a8cabe 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -734,6 +734,7 @@ oustanding||outstanding
 overaall||overall
 overhread||overhead
 overlaping||overlapping
+overide||override
 overrided||overridden
 overriden||overridden
 overun||overrun
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 11c8d9bc762e..5d19fdf80292 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
 		/* Allow writing to any other BAR, or expansion ROM */
 		iowrite(portoff, val, mask, &d->config_words[reg]);
 		return true;
-		/* We let them overide latency timer and cacheline size */
+		/* We let them override latency timer and cacheline size */
 	} else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
 		/* Only let them change the first two fields. */
 		if (mask == 0xFFFFFFFF)
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index e2efddf10231..1f5300e56b44 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -132,7 +132,7 @@ else
   Q = @
 endif
 
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
 MAKEOVERRIDES=
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 47076b15eebe..9b8555ea3459 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -135,7 +135,7 @@ else
   Q = @
 endif
 
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
 MAKEOVERRIDES=
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 66342804161c..0c03538df74c 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -140,7 +140,7 @@ struct pevent_plugin_option {
  *   struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
  *	{
  *		.name = "option-name",
- *		.plugin_alias = "overide-file-name", (optional)
+ *		.plugin_alias = "override-file-name", (optional)
  *		.description = "description of option to show users",
  *	},
  *	{
-- 
GitLab


From 52c50ca75c534c0772b71900a29b3a71439b32ef Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Thu, 9 Mar 2017 16:16:36 -0800
Subject: [PATCH 865/898] powerpc/mm: handle protnone ptes on fork

We need to mark pages of parent process read only on fork.  Numa fault
pte needs a protnone ptes variant with saved write flag set.  On fork we
need to make sure we remove the saved write bit.  Instead of adding the
protnone check in the caller update ptep_set_wrprotect variants to clear
savedwrite bit.

Without this we see random segfaults in application on fork.

Fixes: c137a2757b886 ("powerpc/mm/autonuma: switch ppc64 to its own implementation of saved write")
Link: http://lkml.kernel.org/r/1488203787-17849-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h | 73 +++++++++++---------
 1 file changed, 42 insertions(+), 31 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 1eeeb72c7015..f0b08acda5eb 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -347,23 +347,53 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 	__r;							\
 })
 
+static inline int pte_write(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+	/*
+	 * Saved write ptes are prot none ptes that doesn't have
+	 * privileged bit sit. We mark prot none as one which has
+	 * present and pviliged bit set and RWX cleared. To mark
+	 * protnone which used to have _PAGE_WRITE set we clear
+	 * the privileged bit.
+	 */
+	return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+}
+#else
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+	return false;
+}
+#endif
+
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+	if (pte_write(*ptep))
+		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+	else if (unlikely(pte_savedwrite(*ptep)))
+		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
 }
 
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+	/*
+	 * We should not find protnone for hugetlb, but this complete the
+	 * interface.
+	 */
+	if (pte_write(*ptep))
+		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+	else if (unlikely(pte_savedwrite(*ptep)))
+		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
 }
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@@ -397,11 +427,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 	pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
 
-static inline int pte_write(pte_t pte)
-{
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
-}
-
 static inline int pte_dirty(pte_t pte)
 {
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
@@ -466,19 +491,6 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
 	return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
 }
 
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
-{
-	/*
-	 * Saved write ptes are prot none ptes that doesn't have
-	 * privileged bit sit. We mark prot none as one which has
-	 * present and pviliged bit set and RWX cleared. To mark
-	 * protnone which used to have _PAGE_WRITE set we clear
-	 * the privileged bit.
-	 */
-	VM_BUG_ON(!pte_protnone(pte));
-	return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
-}
 #endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
@@ -982,11 +994,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
 {
-
-	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+	if (pmd_write((*pmdp)))
+		pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+	else if (unlikely(pmd_savedwrite(*pmdp)))
+		pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
 }
 
 static inline int pmd_trans_huge(pmd_t pmd)
-- 
GitLab


From d19469e8415813cceaa494b6f538e327b9a95f3b Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Thu, 9 Mar 2017 16:16:39 -0800
Subject: [PATCH 866/898] power/mm: update pte_write and pte_wrprotect to
 handle savedwrite

We use pte_write() to check whethwer the pte entry is writable.  This is
mostly used to later mark the pte read only if it is writable.  The other
use of pte_write() is to check whether the pte_entry is writable so that
hardware page table entry can be marked accordingly.  This is used in kvm
where we look at qemu page table entry and update hardware hash page table
for the guest with correct write enable bit.

With the above, for the first usage we should also check the savedwrite
bit so that we can correctly clear the savedwite bit.  For the later, we
add a new variant __pte_write().

With this we can revert write_protect_page part of 595cd8f256d2 ("mm/ksm:
handle protnone saved writes when making page write protect").  But I left
it as it is as an example code for savedwrite check.

Fixes: c137a2757b886 ("powerpc/mm/autonuma: switch ppc64 to its own implementation of saved write")
Link: http://lkml.kernel.org/r/1488203787-17849-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h | 24 ++++++++++++++++----
 arch/powerpc/kvm/book3s_64_mmu_hv.c          |  2 +-
 arch/powerpc/kvm/book3s_hv_rm_mmu.c          |  2 +-
 3 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index f0b08acda5eb..ec1e731e6a2d 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -347,7 +347,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 	__r;							\
 })
 
-static inline int pte_write(pte_t pte)
+static inline int __pte_write(pte_t pte)
 {
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
 }
@@ -373,11 +373,16 @@ static inline bool pte_savedwrite(pte_t pte)
 }
 #endif
 
+static inline int pte_write(pte_t pte)
+{
+	return __pte_write(pte) || pte_savedwrite(pte);
+}
+
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	if (pte_write(*ptep))
+	if (__pte_write(*ptep))
 		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
 	else if (unlikely(pte_savedwrite(*ptep)))
 		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
@@ -390,7 +395,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	 * We should not find protnone for hugetlb, but this complete the
 	 * interface.
 	 */
-	if (pte_write(*ptep))
+	if (__pte_write(*ptep))
 		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
 	else if (unlikely(pte_savedwrite(*ptep)))
 		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
@@ -490,7 +495,13 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
 	VM_BUG_ON(!pte_protnone(pte));
 	return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
 }
-
+#else
+#define pte_clear_savedwrite pte_clear_savedwrite
+static inline pte_t pte_clear_savedwrite(pte_t pte)
+{
+	VM_WARN_ON(1);
+	return __pte(pte_val(pte) & ~_PAGE_WRITE);
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
@@ -518,6 +529,8 @@ static inline unsigned long pte_pfn(pte_t pte)
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {
+	if (unlikely(pte_savedwrite(pte)))
+		return pte_clear_savedwrite(pte);
 	return __pte(pte_val(pte) & ~_PAGE_WRITE);
 }
 
@@ -938,6 +951,7 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+#define __pmd_write(pmd)	__pte_write(pmd_pte(pmd))
 #define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -994,7 +1008,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
 {
-	if (pmd_write((*pmdp)))
+	if (__pmd_write((*pmdp)))
 		pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
 	else if (unlikely(pmd_savedwrite(*pmdp)))
 		pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f3158fb16de3..8c68145ba1bd 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -601,7 +601,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 							 hva, NULL, NULL);
 			if (ptep) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
-				if (pte_write(pte))
+				if (__pte_write(pte))
 					write_ok = 1;
 			}
 			local_irq_restore(flags);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6fca970373ee..ce6f2121fffe 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -256,7 +256,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		}
 		pte = kvmppc_read_update_linux_pte(ptep, writing);
 		if (pte_present(pte) && !pte_protnone(pte)) {
-			if (writing && !pte_write(pte))
+			if (writing && !__pte_write(pte))
 				/* make the actual HPTE be read-only */
 				ptel = hpte_make_readonly(ptel);
 			is_ci = pte_ci(pte);
-- 
GitLab


From ef947b2529f918d9606533eb9c32b187ed6a5ede Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 9 Mar 2017 16:16:42 -0800
Subject: [PATCH 867/898] x86, mm: fix gup_pte_range() vs DAX mappings

gup_pte_range() fails to check pte_allows_gup() before translating a DAX
pte entry, pte_devmap(), to a page.  This allows writes to read-only
mappings, and bypasses the DAX cacheline dirty tracking due to missed
'mkwrite' faults.  The gup_huge_pmd() path and the gup_huge_pud() path
correctly check pte_allows_gup() before checking for _devmap() entries.

Fixes: 3565fce3a659 ("mm, x86: get_user_pages() for dax mappings")
Link: http://lkml.kernel.org/r/148804251312.36605.12665024794196605053.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: Dave Hansen <dave.hansen@linux.intel.com>
Reported-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Xiong Zhou <xzhou@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/gup.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 99c7805a9693..9d32ee608807 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -120,6 +120,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 
+		if (!pte_allows_gup(pte_val(pte), write)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if (pte_devmap(pte)) {
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
@@ -127,8 +132,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 				pte_unmap(ptep);
 				return 0;
 			}
-		} else if (!pte_allows_gup(pte_val(pte), write) ||
-			   pte_special(pte)) {
+		} else if (pte_special(pte)) {
 			pte_unmap(ptep);
 			return 0;
 		}
-- 
GitLab


From b2e593e271b0760ebc8999e5f9dd068ae2b9d30a Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 9 Mar 2017 16:16:45 -0800
Subject: [PATCH 868/898] x86, mm: unify exit paths in gup_pte_range()

All exit paths from gup_pte_range() require pte_unmap() of the original
pte page before returning.  Refactor the code to have a single exit
point to do the unmap.

This mirrors the flow of the generic gup_pte_range() in mm/gup.c.

Link: http://lkml.kernel.org/r/148804251828.36605.14910389618497006945.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/gup.c | 39 ++++++++++++++++++++-------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 9d32ee608807..1f3b6ef105cd 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -106,36 +106,35 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	struct dev_pagemap *pgmap = NULL;
-	int nr_start = *nr;
-	pte_t *ptep;
+	int nr_start = *nr, ret = 0;
+	pte_t *ptep, *ptem;
 
-	ptep = pte_offset_map(&pmd, addr);
+	/*
+	 * Keep the original mapped PTE value (ptem) around since we
+	 * might increment ptep off the end of the page when finishing
+	 * our loop iteration.
+	 */
+	ptem = ptep = pte_offset_map(&pmd, addr);
 	do {
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
 		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_protnone(pte)) {
-			pte_unmap(ptep);
-			return 0;
-		}
+		if (pte_protnone(pte))
+			break;
 
-		if (!pte_allows_gup(pte_val(pte), write)) {
-			pte_unmap(ptep);
-			return 0;
-		}
+		if (!pte_allows_gup(pte_val(pte), write))
+			break;
 
 		if (pte_devmap(pte)) {
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
 				undo_dev_pagemap(nr, nr_start, pages);
-				pte_unmap(ptep);
-				return 0;
+				break;
 			}
-		} else if (pte_special(pte)) {
-			pte_unmap(ptep);
-			return 0;
-		}
+		} else if (pte_special(pte))
+			break;
+
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 		get_page(page);
@@ -145,9 +144,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		(*nr)++;
 
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(ptep - 1);
+	if (addr == end)
+		ret = 1;
+	pte_unmap(ptem);
 
-	return 1;
+	return ret;
 }
 
 static inline void get_head_page_multiple(struct page *page, int nr)
-- 
GitLab


From dd0db88d8094a6d9d4d1fc5fcd56ab619f54ccf8 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Thu, 9 Mar 2017 16:16:49 -0800
Subject: [PATCH 869/898] userfaultfd: non-cooperative: rollback
 userfaultfd_exit

Patch series "userfaultfd non-cooperative further update for 4.11 merge
window".

Unfortunately I noticed one relevant bug in userfaultfd_exit while doing
more testing.  I've been doing testing before and this was also tested
by kbuild bot and exercised by the selftest, but this bug never
reproduced before.

I dropped userfaultfd_exit as result.  I dropped it because of
implementation difficulty in receiving signals in __mmput and because I
think -ENOSPC as result from the background UFFDIO_COPY should be enough
already.

Before I decided to remove userfaultfd_exit, I noticed userfaultfd_exit
wasn't exercised by the selftest and when I tried to exercise it, after
moving it to a more correct place in __mmput where it would make more
sense and where the vma list is stable, it resulted in the
event_wait_completion in D state.  So then I added the second patch to
be sure even if we call userfaultfd_event_wait_completion too late
during task exit(), we won't risk to generate tasks in D state.  The
same check exists in handle_userfault() for the same reason, except it
makes a difference there, while here is just a robustness check and it's
run under WARN_ON_ONCE.

While looking at the userfaultfd_event_wait_completion() function I
looked back at its callers too while at it and I think it's not ok to
stop executing dup_fctx on the fcs list because we relay on
userfaultfd_event_wait_completion to execute
userfaultfd_ctx_put(fctx->orig) which is paired against
userfaultfd_ctx_get(fctx->orig) in dup_userfault just before
list_add(fcs).  This change only takes care of fctx->orig but this area
also needs further review looking for similar problems in fctx->new.

The only patch that is urgent is the first because it's an use after
free during a SMP race condition that affects all processes if
CONFIG_USERFAULTFD=y.  Very hard to reproduce though and probably
impossible without SLUB poisoning enabled.

This patch (of 3):

I once reproduced this oops with the userfaultfd selftest, it's not
easily reproducible and it requires SLUB poisoning to reproduce.

    general protection fault: 0000 [#1] SMP
    Modules linked in:
    CPU: 2 PID: 18421 Comm: userfaultfd Tainted: G               ------------ T 3.10.0+ #15
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014
    task: ffff8801f83b9440 ti: ffff8801f833c000 task.ti: ffff8801f833c000
    RIP: 0010:[<ffffffff81451299>]  [<ffffffff81451299>] userfaultfd_exit+0x29/0xa0
    RSP: 0018:ffff8801f833fe80  EFLAGS: 00010202
    RAX: ffff8801f833ffd8 RBX: 6b6b6b6b6b6b6b6b RCX: ffff8801f83b9440
    RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8800baf18600
    RBP: ffff8801f833fee8 R08: 0000000000000000 R09: 0000000000000001
    R10: 0000000000000000 R11: ffffffff8127ceb3 R12: 0000000000000000
    R13: ffff8800baf186b0 R14: ffff8801f83b99f8 R15: 00007faed746c700
    FS:  0000000000000000(0000) GS:ffff88023fc80000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
    CR2: 00007faf0966f028 CR3: 0000000001bc6000 CR4: 00000000000006e0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
    Call Trace:
      do_exit+0x297/0xd10
      SyS_exit+0x17/0x20
      tracesys+0xdd/0xe2
    Code: 00 00 66 66 66 66 90 55 48 89 e5 41 54 53 48 83 ec 58 48 8b 1f 48 85 db 75 11 eb 73 66 0f 1f 44 00 00 48 8b 5b 10 48 85 db 74 64 <4c> 8b a3 b8 00 00 00 4d 85 e4 74 eb 41 f6 84 24 2c 01 00 00 80
    RIP  [<ffffffff81451299>] userfaultfd_exit+0x29/0xa0
     RSP <ffff8801f833fe80>
    ---[ end trace 9fecd6dcb442846a ]---

In the debugger I located the "mm" pointer in the stack and walking
mm->mmap->vm_next through the end shows the vma->vm_next list is fully
consistent and it is null terminated list as expected.  So this has to
be an SMP race condition where userfaultfd_exit was running while the
vma list was being modified by another CPU.

When userfaultfd_exit() run one of the ->vm_next pointers pointed to
SLAB_POISON (RBX is the vma pointer and is 0x6b6b..).

The reason is that it's not running in __mmput but while there are still
other threads running and it's not holding the mmap_sem (it can't as it
has to wait the even to be received by the manager).  So this is an use
after free that was happening for all processes.

One more implementation problem aside from the race condition:
userfaultfd_exit has really to check a flag in mm->flags before walking
the vma or it's going to slowdown the exit() path for regular tasks.

One more implementation problem: at that point signals can't be
delivered so it would also create a task in D state if the manager
doesn't read the event.

The major design issue: it overall looks superfluous as the manager can
check for -ENOSPC in the background transfer:

	if (mmget_not_zero(ctx->mm)) {
[..]
	} else {
		return -ENOSPC;
	}

It's safer to roll it back and re-introduce it later if at all.

[rppt@linux.vnet.ibm.com: documentation fixup after removal of UFFD_EVENT_EXIT]
  Link: http://lkml.kernel.org/r/1488345437-4364-1-git-send-email-rppt@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/20170224181957.19736-2-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/userfaultfd.txt |  4 ----
 fs/userfaultfd.c                 | 28 ----------------------------
 include/linux/userfaultfd_k.h    |  6 ------
 include/uapi/linux/userfaultfd.h |  5 +----
 kernel/exit.c                    |  1 -
 5 files changed, 1 insertion(+), 43 deletions(-)

diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/vm/userfaultfd.txt
index 0e5543a920e5..bb2f945f87ab 100644
--- a/Documentation/vm/userfaultfd.txt
+++ b/Documentation/vm/userfaultfd.txt
@@ -172,10 +172,6 @@ the same read(2) protocol as for the page fault notifications. The
 manager has to explicitly enable these events by setting appropriate
 bits in uffdio_api.features passed to UFFDIO_API ioctl:
 
-UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the
-non-cooperative process. When the monitored process exits, the uffd
-manager will get UFFD_EVENT_EXIT.
-
 UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
 this feature is enabled, the userfaultfd context of the parent process
 is duplicated into the newly created process. The manager receives
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f62199b90fd0..16d0cc600fa9 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -775,34 +775,6 @@ void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
 	}
 }
 
-void userfaultfd_exit(struct mm_struct *mm)
-{
-	struct vm_area_struct *vma = mm->mmap;
-
-	/*
-	 * We can do the vma walk without locking because the caller
-	 * (exit_mm) knows it now has exclusive access
-	 */
-	while (vma) {
-		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
-
-		if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) {
-			struct userfaultfd_wait_queue ewq;
-
-			userfaultfd_ctx_get(ctx);
-
-			msg_init(&ewq.msg);
-			ewq.msg.event = UFFD_EVENT_EXIT;
-
-			userfaultfd_event_wait_completion(ctx, &ewq);
-
-			ctx->features &= ~UFFD_FEATURE_EVENT_EXIT;
-		}
-
-		vma = vma->vm_next;
-	}
-}
-
 static int userfaultfd_release(struct inode *inode, struct file *file)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 0468548acebf..f2b79bf4c895 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -72,8 +72,6 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma,
 extern void userfaultfd_unmap_complete(struct mm_struct *mm,
 				       struct list_head *uf);
 
-extern void userfaultfd_exit(struct mm_struct *mm);
-
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
@@ -139,10 +137,6 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
 {
 }
 
-static inline void userfaultfd_exit(struct mm_struct *mm)
-{
-}
-
 #endif /* CONFIG_USERFAULTFD */
 
 #endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index c055947c5c98..3b059530dac9 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -18,8 +18,7 @@
  * means the userland is reading).
  */
 #define UFFD_API ((__u64)0xAA)
-#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_EXIT |		\
-			   UFFD_FEATURE_EVENT_FORK |		\
+#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |		\
 			   UFFD_FEATURE_EVENT_REMAP |		\
 			   UFFD_FEATURE_EVENT_REMOVE |	\
 			   UFFD_FEATURE_EVENT_UNMAP |		\
@@ -113,7 +112,6 @@ struct uffd_msg {
 #define UFFD_EVENT_REMAP	0x14
 #define UFFD_EVENT_REMOVE	0x15
 #define UFFD_EVENT_UNMAP	0x16
-#define UFFD_EVENT_EXIT		0x17
 
 /* flags for UFFD_EVENT_PAGEFAULT */
 #define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
@@ -163,7 +161,6 @@ struct uffdio_api {
 #define UFFD_FEATURE_MISSING_HUGETLBFS		(1<<4)
 #define UFFD_FEATURE_MISSING_SHMEM		(1<<5)
 #define UFFD_FEATURE_EVENT_UNMAP		(1<<6)
-#define UFFD_FEATURE_EVENT_EXIT			(1<<7)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/kernel/exit.c b/kernel/exit.c
index e126ebf2400c..516acdb0e0ec 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -554,7 +554,6 @@ static void exit_mm(void)
 	enter_lazy_tlb(mm, current);
 	task_unlock(current);
 	mm_update_next_owner(mm);
-	userfaultfd_exit(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
 		exit_oom_victim();
-- 
GitLab


From 9a69a829f9b656c2a220d65a94ecf7b5887c5da1 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Thu, 9 Mar 2017 16:16:52 -0800
Subject: [PATCH 870/898] userfaultfd: non-cooperative: robustness check

Similar to the handle_userfault() case, also make sure to never attempt
to send any event past the PF_EXITING point of no return.

This is purely a robustness check.

Link: http://lkml.kernel.org/r/20170224181957.19736-3-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/userfaultfd.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 16d0cc600fa9..668bbbd2e04d 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -530,8 +530,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 					     struct userfaultfd_wait_queue *ewq)
 {
-	int ret = 0;
+	int ret;
+
+	ret = -1;
+	if (WARN_ON_ONCE(current->flags & PF_EXITING))
+		goto out;
 
+	ret = 0;
 	ewq->ctx = ctx;
 	init_waitqueue_entry(&ewq->wq, current);
 
@@ -566,7 +571,7 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	 * ctx may go away after this if the userfault pseudo fd is
 	 * already released.
 	 */
-
+out:
 	userfaultfd_ctx_put(ctx);
 	return ret;
 }
-- 
GitLab


From 8c9e7bb7a41f2bbd54b2caefb274fb3de239819f Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Thu, 9 Mar 2017 16:16:54 -0800
Subject: [PATCH 871/898] userfaultfd: non-cooperative: release all ctx in
 dup_userfaultfd_complete

Don't stop running dup_fctx() even if userfaultfd_event_wait_completion
fails as it has to run userfaultfd_ctx_put on all ctx to pair against
the userfaultfd_ctx_get that was run on all fctx->orig in
dup_userfaultfd.

Link: http://lkml.kernel.org/r/20170224181957.19736-4-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/userfaultfd.c | 18 +++++-------------
 1 file changed, 5 insertions(+), 13 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 668bbbd2e04d..dd48052e086f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -527,16 +527,12 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	return ret;
 }
 
-static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
-					     struct userfaultfd_wait_queue *ewq)
+static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
+					      struct userfaultfd_wait_queue *ewq)
 {
-	int ret;
-
-	ret = -1;
 	if (WARN_ON_ONCE(current->flags & PF_EXITING))
 		goto out;
 
-	ret = 0;
 	ewq->ctx = ctx;
 	init_waitqueue_entry(&ewq->wq, current);
 
@@ -552,7 +548,6 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 			break;
 		if (ACCESS_ONCE(ctx->released) ||
 		    fatal_signal_pending(current)) {
-			ret = -1;
 			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
 			break;
 		}
@@ -573,7 +568,6 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	 */
 out:
 	userfaultfd_ctx_put(ctx);
-	return ret;
 }
 
 static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
@@ -631,7 +625,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 	return 0;
 }
 
-static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
+static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
 {
 	struct userfaultfd_ctx *ctx = fctx->orig;
 	struct userfaultfd_wait_queue ewq;
@@ -641,17 +635,15 @@ static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
 	ewq.msg.event = UFFD_EVENT_FORK;
 	ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
 
-	return userfaultfd_event_wait_completion(ctx, &ewq);
+	userfaultfd_event_wait_completion(ctx, &ewq);
 }
 
 void dup_userfaultfd_complete(struct list_head *fcs)
 {
-	int ret = 0;
 	struct userfaultfd_fork_ctx *fctx, *n;
 
 	list_for_each_entry_safe(fctx, n, fcs, list) {
-		if (!ret)
-			ret = dup_fctx(fctx);
+		dup_fctx(fctx);
 		list_del(&fctx->list);
 		kfree(fctx);
 	}
-- 
GitLab


From cbfd0c1001bedb4b051cf4a1f5df24f1500381bc Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 9 Mar 2017 16:16:57 -0800
Subject: [PATCH 872/898] include/linux/fs.h: fix unsigned enum warning with
 gcc-4.2

With arm-linux-gcc-4.2, almost every file we build in the kernel ends up
with this warning:

  include/linux/fs.h:2648: warning: comparison of unsigned expression < 0 is always false

Later versions don't have this problem, but it's easy enough to work
around.

Link: http://lkml.kernel.org/r/20161216105634.235457-12-arnd@arndb.de
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index aad3fd0ff5f8..7251f7bb45e8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2678,7 +2678,7 @@ static const char * const kernel_read_file_str[] = {
 
 static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 {
-	if (id < 0 || id >= READING_MAX_ID)
+	if ((unsigned)id >= READING_MAX_ID)
 		return kernel_read_file_str[READING_UNKNOWN];
 
 	return kernel_read_file_str[id];
-- 
GitLab


From ce9311cf95ad8baf044a014738d76973d93b739a Mon Sep 17 00:00:00 2001
From: Yisheng Xie <xieyisheng1@huawei.com>
Date: Thu, 9 Mar 2017 16:17:00 -0800
Subject: [PATCH 873/898] mm/vmstats: add thp_split_pud event for clarity

We added support for PUD-sized transparent hugepages, however we count
the event "thp split pud" into thp_split_pmd event.

To separate the event count of thp split pud from pmd, add a new event
named thp_split_pud.

Link: http://lkml.kernel.org/r/1488282380-5076-1-git-send-email-xieyisheng1@huawei.com
Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vm_event_item.h | 3 +++
 mm/huge_memory.c              | 2 +-
 mm/vmstat.c                   | 3 +++
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 6aa1b6cb5828..a80b7b59cf33 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -79,6 +79,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_SPLIT_PAGE_FAILED,
 		THP_DEFERRED_SPLIT_PAGE,
 		THP_SPLIT_PMD,
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+		THP_SPLIT_PUD,
+#endif
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d36b2af4d1bf..8f037e256c54 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1828,7 +1828,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
 	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
 
-	count_vm_event(THP_SPLIT_PMD);
+	count_vm_event(THP_SPLIT_PUD);
 
 	pudp_huge_clear_flush_notify(vma, haddr, pud);
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 69f9aff39a2e..b1947f0cbee2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = {
 	"thp_split_page_failed",
 	"thp_deferred_split_page",
 	"thp_split_pmd",
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	"thp_split_pud",
+#endif
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
-- 
GitLab


From f4b7ac68f438fa8521bbbf421f194ff10b0a7577 Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Thu, 9 Mar 2017 16:17:03 -0800
Subject: [PATCH 874/898] drivers/md/bcache/util.h: remove duplicate inclusion
 of blkdev.h

Link: http://lkml.kernel.org/r/20170226060230.11555-1-standby24x7@gmail.com
Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Acked-by: Coly Li <colyli@suse.de>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/md/bcache/util.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index a126919ed102..5d13930f0f22 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -4,7 +4,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/errno.h>
-#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/sched/clock.h>
 #include <linux/llist.h>
-- 
GitLab


From bfc7228b9a9647e1c353e50b40297a2929801759 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Date: Thu, 9 Mar 2017 16:17:06 -0800
Subject: [PATCH 875/898] mm/cgroup: avoid panic when init with low memory

The system may panic when initialisation is done when almost all the
memory is assigned to the huge pages using the kernel command line
parameter hugepage=xxxx.  Panic may occur like this:

  Unable to handle kernel paging request for data at address 0x00000000
  Faulting instruction address: 0xc000000000302b88
  Oops: Kernel access of bad area, sig: 11 [#1]
  SMP NR_CPUS=2048 [    0.082424] NUMA
  pSeries
  Modules linked in:
  CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.9.0-15-generic #16-Ubuntu
  task: c00000021ed01600 task.stack: c00000010d108000
  NIP: c000000000302b88 LR: c000000000270e04 CTR: c00000000016cfd0
  REGS: c00000010d10b2c0 TRAP: 0300   Not tainted (4.9.0-15-generic)
  MSR: 8000000002009033 <SF,VEC,EE,ME,IR,DR,RI,LE>[ 0.082770]   CR: 28424422  XER: 00000000
  CFAR: c0000000003d28b8 DAR: 0000000000000000 DSISR: 40000000 SOFTE: 1
  GPR00: c000000000270e04 c00000010d10b540 c00000000141a300 c00000010fff6300
  GPR04: 0000000000000000 00000000026012c0 c00000010d10b630 0000000487ab0000
  GPR08: 000000010ee90000 c000000001454fd8 0000000000000000 0000000000000000
  GPR12: 0000000000004400 c00000000fb80000 00000000026012c0 00000000026012c0
  GPR16: 00000000026012c0 0000000000000000 0000000000000000 0000000000000002
  GPR20: 000000000000000c 0000000000000000 0000000000000000 00000000024200c0
  GPR24: c0000000016eef48 0000000000000000 c00000010fff7d00 00000000026012c0
  GPR28: 0000000000000000 c00000010fff7d00 c00000010fff6300 c00000010d10b6d0
  NIP mem_cgroup_soft_limit_reclaim+0xf8/0x4f0
  LR do_try_to_free_pages+0x1b4/0x450
  Call Trace:
    do_try_to_free_pages+0x1b4/0x450
    try_to_free_pages+0xf8/0x270
    __alloc_pages_nodemask+0x7a8/0xff0
    new_slab+0x104/0x8e0
    ___slab_alloc+0x620/0x700
    __slab_alloc+0x34/0x60
    kmem_cache_alloc_node_trace+0xdc/0x310
    mem_cgroup_init+0x158/0x1c8
    do_one_initcall+0x68/0x1d0
    kernel_init_freeable+0x278/0x360
    kernel_init+0x24/0x170
    ret_from_kernel_thread+0x5c/0x74
  Instruction dump:
  eb81ffe0 eba1ffe8 ebc1fff0 ebe1fff8 4e800020 3d230001 e9499a42 3d220004
  3929acd8 794a1f24 7d295214 eac90100 <e9360000> 2fa90000 419eff74 3b200000
  ---[ end trace 342f5208b00d01b6 ]---

This is a chicken and egg issue where the kernel try to get free memory
when allocating per node data in mem_cgroup_init(), but in that path
mem_cgroup_soft_limit_reclaim() is called which assumes that these data
are allocated.

As mem_cgroup_soft_limit_reclaim() is best effort, it should return when
these data are not yet allocated.

This patch also fixes potential null pointer access in
mem_cgroup_remove_from_trees() and mem_cgroup_update_tree().

Link: http://lkml.kernel.org/r/1487856999-16581-2-git-send-email-ldufour@linux.vnet.ibm.com
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c52ec893e241..76f513cc1b0e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	struct mem_cgroup_tree_per_node *mctz;
 
 	mctz = soft_limit_tree_from_page(page);
+	if (!mctz)
+		return;
 	/*
 	 * Necessary to update all ancestors when hierarchy is used.
 	 * because their event counter is not touched.
@@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
 	for_each_node(nid) {
 		mz = mem_cgroup_nodeinfo(memcg, nid);
 		mctz = soft_limit_tree_node(nid);
-		mem_cgroup_remove_exceeded(mz, mctz);
+		if (mctz)
+			mem_cgroup_remove_exceeded(mz, mctz);
 	}
 }
 
@@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 	 * is empty. Do it lockless to prevent lock bouncing. Races
 	 * are acceptable as soft limit is best effort anyway.
 	 */
-	if (RB_EMPTY_ROOT(&mctz->rb_root))
+	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
 		return 0;
 
 	/*
-- 
GitLab


From 7eb76d457fd758d396bc2e65cb0ace5aae614149 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Thu, 9 Mar 2017 16:17:09 -0800
Subject: [PATCH 876/898] userfaultfd: non-cooperative: fix fork fctx->new
 memleak

We have a memleak in the ->new ctx if the uffd of the parent is closed
before the fork event is read, nothing frees the new context.

Link: http://lkml.kernel.org/r/20170302173738.18994-2-aarcange@redhat.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/userfaultfd.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index dd48052e086f..2407249998c3 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -549,6 +549,15 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 		if (ACCESS_ONCE(ctx->released) ||
 		    fatal_signal_pending(current)) {
 			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
+			if (ewq->msg.event == UFFD_EVENT_FORK) {
+				struct userfaultfd_ctx *new;
+
+				new = (struct userfaultfd_ctx *)
+					(unsigned long)
+					ewq->msg.arg.reserved.reserved1;
+
+				userfaultfd_ctx_put(new);
+			}
 			break;
 		}
 
-- 
GitLab


From 70ccb92fdd90b35bb6f9200093d4ffd6cb38156b Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Thu, 9 Mar 2017 16:17:11 -0800
Subject: [PATCH 877/898] userfaultfd: non-cooperative: userfaultfd_remove
 revalidate vma in MADV_DONTNEED

userfaultfd_remove() has to be execute before zapping the pagetables or
UFFDIO_COPY could keep filling pages after zap_page_range returned,
which would result in non zero data after a MADV_DONTNEED.

However userfaultfd_remove() may have to release the mmap_sem.  This was
handled correctly in MADV_REMOVE, but MADV_DONTNEED accessed a
potentially stale vma (the very vma passed to zap_page_range(vma, ...)).

The fix consists in revalidating the vma in case userfaultfd_remove()
had to release the mmap_sem.

This also optimizes away an unnecessary down_read/up_read in the
MADV_REMOVE case if UFFD_EVENT_FORK had to be delivered.

It all remains zero runtime cost in case CONFIG_USERFAULTFD=n as
userfaultfd_remove() will be defined as "true" at build time.

Link: http://lkml.kernel.org/r/20170302173738.18994-3-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/userfaultfd.c              |  9 +++----
 include/linux/userfaultfd_k.h |  7 +++---
 mm/madvise.c                  | 44 ++++++++++++++++++++++++++++++++---
 3 files changed, 47 insertions(+), 13 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 2407249998c3..9fd5e51ffb31 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -695,8 +695,7 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
 	userfaultfd_event_wait_completion(ctx, &ewq);
 }
 
-void userfaultfd_remove(struct vm_area_struct *vma,
-			struct vm_area_struct **prev,
+bool userfaultfd_remove(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
 	struct mm_struct *mm = vma->vm_mm;
@@ -705,13 +704,11 @@ void userfaultfd_remove(struct vm_area_struct *vma,
 
 	ctx = vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
-		return;
+		return true;
 
 	userfaultfd_ctx_get(ctx);
 	up_read(&mm->mmap_sem);
 
-	*prev = NULL; /* We wait for ACK w/o the mmap semaphore */
-
 	msg_init(&ewq.msg);
 
 	ewq.msg.event = UFFD_EVENT_REMOVE;
@@ -720,7 +717,7 @@ void userfaultfd_remove(struct vm_area_struct *vma,
 
 	userfaultfd_event_wait_completion(ctx, &ewq);
 
-	down_read(&mm->mmap_sem);
+	return false;
 }
 
 static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index f2b79bf4c895..48a3483dccb1 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -61,8 +61,7 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
 					unsigned long from, unsigned long to,
 					unsigned long len);
 
-extern void userfaultfd_remove(struct vm_area_struct *vma,
-			       struct vm_area_struct **prev,
+extern bool userfaultfd_remove(struct vm_area_struct *vma,
 			       unsigned long start,
 			       unsigned long end);
 
@@ -118,11 +117,11 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
 {
 }
 
-static inline void userfaultfd_remove(struct vm_area_struct *vma,
-				      struct vm_area_struct **prev,
+static inline bool userfaultfd_remove(struct vm_area_struct *vma,
 				      unsigned long start,
 				      unsigned long end)
 {
+	return true;
 }
 
 static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
diff --git a/mm/madvise.c b/mm/madvise.c
index dc5927c812d3..7a2abf0127ae 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma,
 	if (!can_madv_dontneed_vma(vma))
 		return -EINVAL;
 
-	userfaultfd_remove(vma, prev, start, end);
+	if (!userfaultfd_remove(vma, start, end)) {
+		*prev = NULL; /* mmap_sem has been dropped, prev is stale */
+
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma(current->mm, start);
+		if (!vma)
+			return -ENOMEM;
+		if (start < vma->vm_start) {
+			/*
+			 * This "vma" under revalidation is the one
+			 * with the lowest vma->vm_start where start
+			 * is also < vma->vm_end. If start <
+			 * vma->vm_start it means an hole materialized
+			 * in the user address space within the
+			 * virtual range passed to MADV_DONTNEED.
+			 */
+			return -ENOMEM;
+		}
+		if (!can_madv_dontneed_vma(vma))
+			return -EINVAL;
+		if (end > vma->vm_end) {
+			/*
+			 * Don't fail if end > vma->vm_end. If the old
+			 * vma was splitted while the mmap_sem was
+			 * released the effect of the concurrent
+			 * operation may not cause MADV_DONTNEED to
+			 * have an undefined result. There may be an
+			 * adjacent next vma that we'll walk
+			 * next. userfaultfd_remove() will generate an
+			 * UFFD_EVENT_REMOVE repetition on the
+			 * end-vma->vm_end range, but the manager can
+			 * handle a repetition fine.
+			 */
+			end = vma->vm_end;
+		}
+		VM_WARN_ON(start >= end);
+	}
 	zap_page_range(vma, start, end - start);
 	return 0;
 }
@@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma,
 	 * mmap_sem.
 	 */
 	get_file(f);
-	userfaultfd_remove(vma, prev, start, end);
-	up_read(&current->mm->mmap_sem);
+	if (userfaultfd_remove(vma, start, end)) {
+		/* mmap_sem was not released by userfaultfd_remove() */
+		up_read(&current->mm->mmap_sem);
+	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
-- 
GitLab


From 46aa6a302b53f543f8e8b8e1714dc5e449ad36a6 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Thu, 9 Mar 2017 16:17:14 -0800
Subject: [PATCH 878/898] userfaultfd: selftest: vm: allow to build in vm/
 directory

linux/tools/testing/selftests/vm $ make

  gcc -Wall -I ../../../../usr/include     compaction_test.c -lrt -o /compaction_test
  /usr/lib/gcc/x86_64-pc-linux-gnu/4.9.4/../../../../x86_64-pc-linux-gnu/bin/ld: cannot open output file /compaction_test: Permission denied
  collect2: error: ld returned 1 exit status
  make: *** [../lib.mk:54: /compaction_test] Error 1

Since commit a8ba798bc8ec ("selftests: enable O and KBUILD_OUTPUT")
selftests/vm build fails if run from the "selftests/vm" directory, but
it works in the selftests/ directory.  It's quicker to be able to do a
local vm-only build after a tree wipe and this patch allows for it
again.

Link: http://lkml.kernel.org/r/20170302173738.18994-4-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 4cff7e7ddcc4..41642ba5e318 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,5 +1,9 @@
 # Makefile for vm selftests
 
+ifndef OUTPUT
+  OUTPUT := $(shell pwd)
+endif
+
 CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 LDLIBS = -lrt
 TEST_GEN_FILES = compaction_test
-- 
GitLab


From c9a1b80daeb50e39f21fd7e62f7224f317ac85f0 Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Thu, 9 Mar 2017 16:17:17 -0800
Subject: [PATCH 879/898] mm/memblock.c: fix memblock_next_valid_pfn()

Obviously, we should not access memblock.memory.regions[right] if
'right' is outside of [0..memblock.memory.cnt>.

Fixes: b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns where possible")
Link: http://lkml.kernel.org/r/20170303023745.9104-1-takahiro.akashi@linaro.org
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Paul Burton <paul.burton@imgtec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memblock.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index b64b47803e52..696f06d17c4e 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
 		}
 	} while (left < right);
 
-	return min(PHYS_PFN(type->regions[right].base), max_pfn);
+	if (right == type->cnt)
+		return max_pfn;
+	else
+		return min(PHYS_PFN(type->regions[right].base), max_pfn);
 }
 
 /**
-- 
GitLab


From 8346242a7e32c4c93316684ad8f45473932586b9 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 16:17:20 -0800
Subject: [PATCH 880/898] rmap: fix NULL-pointer dereference on THP munlocking

The following test case triggers NULL-pointer derefernce in
try_to_unmap_one():

	#include <fcntl.h>
	#include <stdlib.h>
	#include <unistd.h>
	#include <sys/mman.h>

	int main(int argc, char *argv[])
	{
		int fd;

		system("mount -t tmpfs -o huge=always none /mnt");
		fd = open("/mnt/test", O_CREAT | O_RDWR);
		ftruncate(fd, 2UL << 20);
		mmap(NULL, 2UL << 20, PROT_READ | PROT_WRITE,
				MAP_SHARED | MAP_FIXED | MAP_LOCKED, fd, 0);
		mmap(NULL, 2UL << 20, PROT_READ | PROT_WRITE,
				MAP_SHARED | MAP_LOCKED, fd, 0);
		munlockall();
		return 0;
	}

Apparently, there's a case when we call try_to_unmap() on huge PMDs:
it's TTU_MUNLOCK.

Let's handle this case correctly.

Fixes: c7ab0d2fdc84 ("mm: convert try_to_unmap_one() to use page_vma_mapped_walk()")
Link: http://lkml.kernel.org/r/20170302151159.30592-1-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/rmap.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index 2da487d6cea8..250635dc47b7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1316,12 +1316,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	}
 
 	while (page_vma_mapped_walk(&pvmw)) {
-		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
-		address = pvmw.address;
-
-		/* Unexpected PMD-mapped THP? */
-		VM_BUG_ON_PAGE(!pvmw.pte, page);
-
 		/*
 		 * If the page is mlock()d, we cannot swap it out.
 		 * If it's recently referenced (perhaps page_referenced
@@ -1345,6 +1339,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				continue;
 		}
 
+		/* Unexpected PMD-mapped THP? */
+		VM_BUG_ON_PAGE(!pvmw.pte, page);
+
+		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+		address = pvmw.address;
+
+
 		if (!(flags & TTU_IGNORE_ACCESS)) {
 			if (ptep_clear_flush_young_notify(vma, address,
 						pvmw.pte)) {
-- 
GitLab


From 6ebb4a1b848fe75323135f93e72c78f8780fd268 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 9 Mar 2017 16:17:23 -0800
Subject: [PATCH 881/898] thp: fix another corner case of munlock() vs. THPs

The following test case triggers BUG() in munlock_vma_pages_range():

	int main(int argc, char *argv[])
	{
		int fd;

		system("mount -t tmpfs -o huge=always none /mnt");
		fd = open("/mnt/test", O_CREAT | O_RDWR);
		ftruncate(fd, 4UL << 20);
		mmap(NULL, 4UL << 20, PROT_READ | PROT_WRITE,
				MAP_SHARED | MAP_FIXED | MAP_LOCKED, fd, 0);
		mmap(NULL, 4096, PROT_READ | PROT_WRITE,
				MAP_SHARED | MAP_LOCKED, fd, 0);
		munlockall();
		return 0;
	}

The second mmap() create PTE-mapping of the first huge page in file.  It
makes kernel munlock the page as we never keep PTE-mapped page mlocked.

On munlockall() when we handle vma created by the first mmap(),
munlock_vma_page() returns page_mask == 0, as the page is not mlocked
anymore.  On next iteration follow_page_mask() return tail page, but
page_mask is HPAGE_NR_PAGES - 1.  It makes us skip to the first tail
page of the next huge page and step on
VM_BUG_ON_PAGE(PageMlocked(page)).

The fix is not use the page_mask from follow_page_mask() at all.  It has
no use for us.

Link: http://lkml.kernel.org/r/20170302150252.34120-1-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>    [4.5+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/mlock.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/mm/mlock.c b/mm/mlock.c
index 1050511f8b2b..02f138244bf5 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -442,7 +442,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 
 	while (start < end) {
 		struct page *page;
-		unsigned int page_mask;
+		unsigned int page_mask = 0;
 		unsigned long page_increm;
 		struct pagevec pvec;
 		struct zone *zone;
@@ -456,8 +456,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 		 * suits munlock very well (and if somehow an abnormal page
 		 * has sneaked into the range, we won't oops here: great).
 		 */
-		page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
-				&page_mask);
+		page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);
 
 		if (page && !IS_ERR(page)) {
 			if (PageTransTail(page)) {
@@ -468,8 +467,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				/*
 				 * Any THP page found by follow_page_mask() may
 				 * have gotten split before reaching
-				 * munlock_vma_page(), so we need to recompute
-				 * the page_mask here.
+				 * munlock_vma_page(), so we need to compute
+				 * the page_mask here instead.
 				 */
 				page_mask = munlock_vma_page(page);
 				unlock_page(page);
-- 
GitLab


From 40e952f9d687928b32db20226f085ae660a7237c Mon Sep 17 00:00:00 2001
From: Tahsin Erdogan <tahsin@google.com>
Date: Thu, 9 Mar 2017 16:17:26 -0800
Subject: [PATCH 882/898] mm: do not call mem_cgroup_free() from within
 mem_cgroup_alloc()

mem_cgroup_free() indirectly calls wb_domain_exit() which is not
prepared to deal with a struct wb_domain object that hasn't executed
wb_domain_init().  For instance, the following warning message is
printed by lockdep if alloc_percpu() fails in mem_cgroup_alloc():

  INFO: trying to register non-static key.
  the code is fine but needs lockdep annotation.
  turning off the locking correctness validator.
  CPU: 1 PID: 1950 Comm: mkdir Not tainted 4.10.0+ #151
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  Call Trace:
   dump_stack+0x67/0x99
   register_lock_class+0x36d/0x540
   __lock_acquire+0x7f/0x1a30
   lock_acquire+0xcc/0x200
   del_timer_sync+0x3c/0xc0
   wb_domain_exit+0x14/0x20
   mem_cgroup_free+0x14/0x40
   mem_cgroup_css_alloc+0x3f9/0x620
   cgroup_apply_control_enable+0x190/0x390
   cgroup_mkdir+0x290/0x3d0
   kernfs_iop_mkdir+0x58/0x80
   vfs_mkdir+0x10e/0x1a0
   SyS_mkdirat+0xa8/0xd0
   SyS_mkdir+0x14/0x20
   entry_SYSCALL_64_fastpath+0x18/0xad

Add __mem_cgroup_free() which skips wb_domain_exit().  This is used by
both mem_cgroup_free() and mem_cgroup_alloc() clean up.

Fixes: 0b8f73e104285 ("mm: memcontrol: clean up alloc, online, offline, free functions")
Link: http://lkml.kernel.org/r/20170306192122.24262-1-tahsin@google.com
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 76f513cc1b0e..2bd7541d7c11 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4138,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	kfree(memcg->nodeinfo[node]);
 }
 
-static void mem_cgroup_free(struct mem_cgroup *memcg)
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	memcg_wb_domain_exit(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->stat);
 	kfree(memcg);
 }
 
+static void mem_cgroup_free(struct mem_cgroup *memcg)
+{
+	memcg_wb_domain_exit(memcg);
+	__mem_cgroup_free(memcg);
+}
+
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
@@ -4199,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 fail:
 	if (memcg->id.id > 0)
 		idr_remove(&mem_cgroup_idr, memcg->id.id);
-	mem_cgroup_free(memcg);
+	__mem_cgroup_free(memcg);
 	return NULL;
 }
 
-- 
GitLab


From 68fd814a3391c7e017ae6ace8855788748edd981 Mon Sep 17 00:00:00 2001
From: Dmitry Vyukov <dvyukov@google.com>
Date: Thu, 9 Mar 2017 16:17:28 -0800
Subject: [PATCH 883/898] kasan: resched in quarantine_remove_cache()

We see reported stalls/lockups in quarantine_remove_cache() on machines
with large amounts of RAM.  quarantine_remove_cache() needs to scan
whole quarantine in order to take out all objects belonging to the
cache.  Quarantine is currently 1/32-th of RAM, e.g.  on a machine with
256GB of memory that will be 8GB.  Moreover quarantine scanning is a
walk over uncached linked list, which is slow.

Add cond_resched() after scanning of each non-empty batch of objects.
Batches are specifically kept of reasonable size for quarantine_put().
On a machine with 256GB of RAM we should have ~512 non-empty batches,
each with 16MB of objects.

Link: http://lkml.kernel.org/r/20170308154239.25440-1-dvyukov@google.com
Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/kasan/quarantine.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 6f1ed1630873..4ac39f20757a 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -283,8 +283,15 @@ void quarantine_remove_cache(struct kmem_cache *cache)
 	on_each_cpu(per_cpu_remove_cache, cache, 1);
 
 	spin_lock_irqsave(&quarantine_lock, flags);
-	for (i = 0; i < QUARANTINE_BATCHES; i++)
+	for (i = 0; i < QUARANTINE_BATCHES; i++) {
+		if (qlist_empty(&global_quarantine[i]))
+			continue;
 		qlist_move_cache(&global_quarantine[i], &to_free, cache);
+		/* Scanning whole quarantine can take a while. */
+		spin_unlock_irqrestore(&quarantine_lock, flags);
+		cond_resched();
+		spin_lock_irqsave(&quarantine_lock, flags);
+	}
 	spin_unlock_irqrestore(&quarantine_lock, flags);
 
 	qlist_free_all(&to_free, cache);
-- 
GitLab


From ce5bec54bb5debbbe51b40270d8f209a23cadae4 Mon Sep 17 00:00:00 2001
From: Dmitry Vyukov <dvyukov@google.com>
Date: Thu, 9 Mar 2017 16:17:32 -0800
Subject: [PATCH 884/898] kasan: fix races in quarantine_remove_cache()

quarantine_remove_cache() frees all pending objects that belong to the
cache, before we destroy the cache itself.  However there are currently
two possibilities how it can fail to do so.

First, another thread can hold some of the objects from the cache in
temp list in quarantine_put().  quarantine_put() has a windows of
enabled interrupts, and on_each_cpu() in quarantine_remove_cache() can
finish right in that window.  These objects will be later freed into the
destroyed cache.

Then, quarantine_reduce() has the same problem.  It grabs a batch of
objects from the global quarantine, then unlocks quarantine_lock and
then frees the batch.  quarantine_remove_cache() can finish while some
objects from the cache are still in the local to_free list in
quarantine_reduce().

Fix the race with quarantine_put() by disabling interrupts for the whole
duration of quarantine_put().  In combination with on_each_cpu() in
quarantine_remove_cache() it ensures that quarantine_remove_cache()
either sees the objects in the per-cpu list or in the global list.

Fix the race with quarantine_reduce() by protecting quarantine_reduce()
with srcu critical section and then doing synchronize_srcu() at the end
of quarantine_remove_cache().

I've done some assessment of how good synchronize_srcu() works in this
case.  And on a 4 CPU VM I see that it blocks waiting for pending read
critical sections in about 2-3% of cases.  Which looks good to me.

I suspect that these races are the root cause of some GPFs that I
episodically hit.  Previously I did not have any explanation for them.

  BUG: unable to handle kernel NULL pointer dereference at 00000000000000c8
  IP: qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155
  PGD 6aeea067
  PUD 60ed7067
  PMD 0
  Oops: 0000 [#1] SMP KASAN
  Dumping ftrace buffer:
     (ftrace buffer empty)
  Modules linked in:
  CPU: 0 PID: 13667 Comm: syz-executor2 Not tainted 4.10.0+ #60
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  task: ffff88005f948040 task.stack: ffff880069818000
  RIP: 0010:qlist_free_all+0x2e/0xc0 mm/kasan/quarantine.c:155
  RSP: 0018:ffff88006981f298 EFLAGS: 00010246
  RAX: ffffea0000ffff00 RBX: 0000000000000000 RCX: ffffea0000ffff1f
  RDX: 0000000000000000 RSI: ffff88003fffc3e0 RDI: 0000000000000000
  RBP: ffff88006981f2c0 R08: ffff88002fed7bd8 R09: 00000001001f000d
  R10: 00000000001f000d R11: ffff88006981f000 R12: ffff88003fffc3e0
  R13: ffff88006981f2d0 R14: ffffffff81877fae R15: 0000000080000000
  FS:  00007fb911a2d700(0000) GS:ffff88003ec00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00000000000000c8 CR3: 0000000060ed6000 CR4: 00000000000006f0
  Call Trace:
   quarantine_reduce+0x10e/0x120 mm/kasan/quarantine.c:239
   kasan_kmalloc+0xca/0xe0 mm/kasan/kasan.c:590
   kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544
   slab_post_alloc_hook mm/slab.h:456 [inline]
   slab_alloc_node mm/slub.c:2718 [inline]
   kmem_cache_alloc_node+0x1d3/0x280 mm/slub.c:2754
   __alloc_skb+0x10f/0x770 net/core/skbuff.c:219
   alloc_skb include/linux/skbuff.h:932 [inline]
   _sctp_make_chunk+0x3b/0x260 net/sctp/sm_make_chunk.c:1388
   sctp_make_data net/sctp/sm_make_chunk.c:1420 [inline]
   sctp_make_datafrag_empty+0x208/0x360 net/sctp/sm_make_chunk.c:746
   sctp_datamsg_from_user+0x7e8/0x11d0 net/sctp/chunk.c:266
   sctp_sendmsg+0x2611/0x3970 net/sctp/socket.c:1962
   inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761
   sock_sendmsg_nosec net/socket.c:633 [inline]
   sock_sendmsg+0xca/0x110 net/socket.c:643
   SYSC_sendto+0x660/0x810 net/socket.c:1685
   SyS_sendto+0x40/0x50 net/socket.c:1653

I am not sure about backporting.  The bug is quite hard to trigger, I've
seen it few times during our massive continuous testing (however, it
could be cause of some other episodic stray crashes as it leads to
memory corruption...).  If it is triggered, the consequences are very
bad -- almost definite bad memory corruption.  The fix is non trivial
and has chances of introducing new bugs.  I am also not sure how
actively people use KASAN on older releases.

[dvyukov@google.com: - sorted includes[
  Link: http://lkml.kernel.org/r/20170309094028.51088-1-dvyukov@google.com
Link: http://lkml.kernel.org/r/20170308151532.5070-1-dvyukov@google.com
Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/kasan/quarantine.c | 42 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 4ac39f20757a..3a8ddf8baf7d 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -25,6 +25,7 @@
 #include <linux/printk.h>
 #include <linux/shrinker.h>
 #include <linux/slab.h>
+#include <linux/srcu.h>
 #include <linux/string.h>
 #include <linux/types.h>
 
@@ -103,6 +104,7 @@ static int quarantine_tail;
 /* Total size of all objects in global_quarantine across all batches. */
 static unsigned long quarantine_size;
 static DEFINE_SPINLOCK(quarantine_lock);
+DEFINE_STATIC_SRCU(remove_cache_srcu);
 
 /* Maximum size of the global queue. */
 static unsigned long quarantine_max_size;
@@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 	struct qlist_head *q;
 	struct qlist_head temp = QLIST_INIT;
 
+	/*
+	 * Note: irq must be disabled until after we move the batch to the
+	 * global quarantine. Otherwise quarantine_remove_cache() can miss
+	 * some objects belonging to the cache if they are in our local temp
+	 * list. quarantine_remove_cache() executes on_each_cpu() at the
+	 * beginning which ensures that it either sees the objects in per-cpu
+	 * lists or in the global quarantine.
+	 */
 	local_irq_save(flags);
 
 	q = this_cpu_ptr(&cpu_quarantine);
 	qlist_put(q, &info->quarantine_link, cache->size);
-	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
+	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
 		qlist_move_all(q, &temp);
 
-	local_irq_restore(flags);
-
-	if (unlikely(!qlist_empty(&temp))) {
-		spin_lock_irqsave(&quarantine_lock, flags);
+		spin_lock(&quarantine_lock);
 		WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
 		qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
 		if (global_quarantine[quarantine_tail].bytes >=
@@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 			if (new_tail != quarantine_head)
 				quarantine_tail = new_tail;
 		}
-		spin_unlock_irqrestore(&quarantine_lock, flags);
+		spin_unlock(&quarantine_lock);
 	}
+
+	local_irq_restore(flags);
 }
 
 void quarantine_reduce(void)
 {
 	size_t total_size, new_quarantine_size, percpu_quarantines;
 	unsigned long flags;
+	int srcu_idx;
 	struct qlist_head to_free = QLIST_INIT;
 
 	if (likely(READ_ONCE(quarantine_size) <=
 		   READ_ONCE(quarantine_max_size)))
 		return;
 
+	/*
+	 * srcu critical section ensures that quarantine_remove_cache()
+	 * will not miss objects belonging to the cache while they are in our
+	 * local to_free list. srcu is chosen because (1) it gives us private
+	 * grace period domain that does not interfere with anything else,
+	 * and (2) it allows synchronize_srcu() to return without waiting
+	 * if there are no pending read critical sections (which is the
+	 * expected case).
+	 */
+	srcu_idx = srcu_read_lock(&remove_cache_srcu);
 	spin_lock_irqsave(&quarantine_lock, flags);
 
 	/*
@@ -237,6 +257,7 @@ void quarantine_reduce(void)
 	spin_unlock_irqrestore(&quarantine_lock, flags);
 
 	qlist_free_all(&to_free, NULL);
+	srcu_read_unlock(&remove_cache_srcu, srcu_idx);
 }
 
 static void qlist_move_cache(struct qlist_head *from,
@@ -280,6 +301,13 @@ void quarantine_remove_cache(struct kmem_cache *cache)
 	unsigned long flags, i;
 	struct qlist_head to_free = QLIST_INIT;
 
+	/*
+	 * Must be careful to not miss any objects that are being moved from
+	 * per-cpu list to the global quarantine in quarantine_put(),
+	 * nor objects being freed in quarantine_reduce(). on_each_cpu()
+	 * achieves the first goal, while synchronize_srcu() achieves the
+	 * second.
+	 */
 	on_each_cpu(per_cpu_remove_cache, cache, 1);
 
 	spin_lock_irqsave(&quarantine_lock, flags);
@@ -295,4 +323,6 @@ void quarantine_remove_cache(struct kmem_cache *cache)
 	spin_unlock_irqrestore(&quarantine_lock, flags);
 
 	qlist_free_all(&to_free, cache);
+
+	synchronize_srcu(&remove_cache_srcu);
 }
-- 
GitLab


From ca5b58ea3db88b5e69ba2a1f6bc3cf239cdcc64f Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Date: Thu, 9 Mar 2017 16:17:34 -0800
Subject: [PATCH 885/898] sh: cayman: IDE support fix

Remove incorrect CONFIG_IDE ifdef (CONFIG_IDE config option is for
internal drivers/ide/ use) and make IDE hardware interface always
initialized (not only when IDE subsystem is built-in).

This patch allows Cayman board to work with modular IDE subsystem
support and removes the requirement of having the whole core IDE
subsystem built-in when using libata PATA support.

Link: http://lkml.kernel.org/r/1990884.yFoE6lSB9G@amdc3058
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/sh/boards/mach-cayman/setup.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c
index 340fd40b381d..9c292c27e0d7 100644
--- a/arch/sh/boards/mach-cayman/setup.c
+++ b/arch/sh/boards/mach-cayman/setup.c
@@ -128,7 +128,6 @@ static int __init smsc_superio_setup(void)
 	SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_PRIMARY_INT_INDEX);
 	SMSC_SUPERIO_WRITE_INDEXED(12, SMSC_SECONDARY_INT_INDEX);
 
-#ifdef CONFIG_IDE
 	/*
 	 * Only IDE1 exists on the Cayman
 	 */
@@ -158,7 +157,6 @@ static int __init smsc_superio_setup(void)
 	SMSC_SUPERIO_WRITE_INDEXED(0x01, 0xc5); /* GP45 = IDE1_IRQ */
 	SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc6); /* GP46 = nIOROP */
 	SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc7); /* GP47 = nIOWOP */
-#endif
 
 	/* Exit the configuration state */
 	outb(SMSC_EXIT_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR);
-- 
GitLab


From c0d0e351285161a515396b7b1ee53ec9ffd97e3c Mon Sep 17 00:00:00 2001
From: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Date: Thu, 9 Mar 2017 16:17:37 -0800
Subject: [PATCH 886/898] fat: fix using uninitialized fields of
 fat_inode/fsinfo_inode

Recently fallocate patch was merged and it uses
MSDOS_I(inode)->mmu_private at fat_evict_inode().  However,
fat_inode/fsinfo_inode that was introduced in past didn't initialize
MSDOS_I(inode) properly.

With those combinations, it became the cause of accessing random entry
in FAT area.

Link: http://lkml.kernel.org/r/87pohrj4i8.fsf@mail.parknet.co.jp
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Reported-by: Moreno Bartalucci <moreno.bartalucci@tecnorama.it>
Tested-by: Moreno Bartalucci <moreno.bartalucci@tecnorama.it>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fat/inode.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 338d2f73eb29..a2c05f2ada6d 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1359,6 +1359,16 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	return 0;
 }
 
+static void fat_dummy_inode_init(struct inode *inode)
+{
+	/* Initialize this dummy inode to work as no-op. */
+	MSDOS_I(inode)->mmu_private = 0;
+	MSDOS_I(inode)->i_start = 0;
+	MSDOS_I(inode)->i_logstart = 0;
+	MSDOS_I(inode)->i_attrs = 0;
+	MSDOS_I(inode)->i_pos = 0;
+}
+
 static int fat_read_root(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	fat_inode = new_inode(sb);
 	if (!fat_inode)
 		goto out_fail;
-	MSDOS_I(fat_inode)->i_pos = 0;
+	fat_dummy_inode_init(fat_inode);
 	sbi->fat_inode = fat_inode;
 
 	fsinfo_inode = new_inode(sb);
 	if (!fsinfo_inode)
 		goto out_fail;
+	fat_dummy_inode_init(fsinfo_inode);
 	fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
 	sbi->fsinfo_inode = fsinfo_inode;
 	insert_inode_hash(fsinfo_inode);
-- 
GitLab


From 2378cd6181edd94748d699448823609977283b11 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 9 Mar 2017 16:17:40 -0800
Subject: [PATCH 887/898] userfaultfd: remove wrong comment from
 userfaultfd_ctx_get()

It's a void function, so there is no return value;

Link: http://lkml.kernel.org/r/20170309150817.7510-1-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/userfaultfd.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 9fd5e51ffb31..2bb1c72380f2 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -138,8 +138,6 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
  * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
  * context.
  * @ctx: [in] Pointer to the userfaultfd context.
- *
- * Returns: In case of success, returns not zero.
  */
 static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
 {
-- 
GitLab


From 10f2889ba35aeb251b9945ec4c461af8c124c41f Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Wed, 14 Dec 2016 17:28:41 -0800
Subject: [PATCH 888/898] drm: mxsfb: use bus_format to determine LCD bus width

The LCD bus width does not need to align with the pixel format. The
LCDIF controller automatically converts between pixel formats and
bus width by padding or dropping LSBs.

The DRM subsystem has the notion of bus_format which allows to
determine what bus_formats are supported by the display. Choose the
first available or fallback to 24 bit if none are available.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Acked-by: Marek Vasut <marex@denx.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/mxsfb/mxsfb_crtc.c | 34 ++++++++++++++++++++++++++++--
 drivers/gpu/drm/mxsfb/mxsfb_regs.h |  1 +
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
index e10a4eda4078..259f71b3a76a 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
@@ -65,13 +65,11 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb)
 	switch (format) {
 	case DRM_FORMAT_RGB565:
 		dev_dbg(drm->dev, "Setting up RGB565 mode\n");
-		ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT);
 		ctrl |= CTRL_SET_WORD_LENGTH(0);
 		ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0xf);
 		break;
 	case DRM_FORMAT_XRGB8888:
 		dev_dbg(drm->dev, "Setting up XRGB8888 mode\n");
-		ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT);
 		ctrl |= CTRL_SET_WORD_LENGTH(3);
 		/* Do not use packed pixels = one pixel per word instead. */
 		ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0x7);
@@ -87,6 +85,36 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb)
 	return 0;
 }
 
+static void mxsfb_set_bus_fmt(struct mxsfb_drm_private *mxsfb)
+{
+	struct drm_crtc *crtc = &mxsfb->pipe.crtc;
+	struct drm_device *drm = crtc->dev;
+	u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+	u32 reg;
+
+	reg = readl(mxsfb->base + LCDC_CTRL);
+
+	if (mxsfb->connector.display_info.num_bus_formats)
+		bus_format = mxsfb->connector.display_info.bus_formats[0];
+
+	reg &= ~CTRL_BUS_WIDTH_MASK;
+	switch (bus_format) {
+	case MEDIA_BUS_FMT_RGB565_1X16:
+		reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT);
+		break;
+	case MEDIA_BUS_FMT_RGB666_1X18:
+		reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_18BIT);
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X24:
+		reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT);
+		break;
+	default:
+		dev_err(drm->dev, "Unknown media bus format %d\n", bus_format);
+		break;
+	}
+	writel(reg, mxsfb->base + LCDC_CTRL);
+}
+
 static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb)
 {
 	u32 reg;
@@ -175,6 +203,8 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
 
 	writel(vdctrl0, mxsfb->base + LCDC_VDCTRL0);
 
+	mxsfb_set_bus_fmt(mxsfb);
+
 	/* Frame length in lines. */
 	writel(m->crtc_vtotal, mxsfb->base + LCDC_VDCTRL1);
 
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_regs.h b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
index 31d62cd0d3d7..66a6ba9ec533 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_regs.h
+++ b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
@@ -44,6 +44,7 @@
 #define CTRL_DATA_SELECT		(1 << 16)
 #define CTRL_SET_BUS_WIDTH(x)		(((x) & 0x3) << 10)
 #define CTRL_GET_BUS_WIDTH(x)		(((x) >> 10) & 0x3)
+#define CTRL_BUS_WIDTH_MASK		(0x3 << 10)
 #define CTRL_SET_WORD_LENGTH(x)		(((x) & 0x3) << 8)
 #define CTRL_GET_WORD_LENGTH(x)		(((x) >> 8) & 0x3)
 #define CTRL_MASTER			(1 << 5)
-- 
GitLab


From 53990e416bb7adaa59d045f325a47f31a11b75ee Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Wed, 14 Dec 2016 12:48:09 -0800
Subject: [PATCH 889/898] drm: mxsfb: fix pixel clock polarity

The DRM subsystem specifies the pixel clock polarity from a
controllers perspective: DRM_BUS_FLAG_PIXDATA_NEGEDGE means
the controller drives the data on pixel clocks falling edge.
That is the controllers DOTCLK_POL=0 (Default is data launched
at negative edge).

Also change the data enable logic to be high active by default
and only change if explicitly requested via bus_flags. With
that defaults are:
- Data enable: high active
- Pixel clock polarity: controller drives data on negative edge

Signed-off-by: Stefan Agner <stefan@agner.ch>
Acked-by: Marek Vasut <marex@denx.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/mxsfb/mxsfb_crtc.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
index 259f71b3a76a..165abd227436 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
@@ -196,9 +196,16 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
 		vdctrl0 |= VDCTRL0_HSYNC_ACT_HIGH;
 	if (m->flags & DRM_MODE_FLAG_PVSYNC)
 		vdctrl0 |= VDCTRL0_VSYNC_ACT_HIGH;
-	if (bus_flags & DRM_BUS_FLAG_DE_HIGH)
+	/* Make sure Data Enable is high active by default */
+	if (!(bus_flags & DRM_BUS_FLAG_DE_LOW))
 		vdctrl0 |= VDCTRL0_ENABLE_ACT_HIGH;
-	if (bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE)
+	/*
+	 * DRM_BUS_FLAG_PIXDATA_ defines are controller centric,
+	 * controllers VDCTRL0_DOTCLK is display centric.
+	 * Drive on positive edge       -> display samples on falling edge
+	 * DRM_BUS_FLAG_PIXDATA_POSEDGE -> VDCTRL0_DOTCLK_ACT_FALLING
+	 */
+	if (bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE)
 		vdctrl0 |= VDCTRL0_DOTCLK_ACT_FALLING;
 
 	writel(vdctrl0, mxsfb->base + LCDC_VDCTRL0);
-- 
GitLab


From 7ad7a5acfb96215216f46b9848bd2d341663358f Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Sat, 28 Jan 2017 18:01:57 +0100
Subject: [PATCH 890/898] drm: mxsfb: Fix crash when provided invalid DT
 bindings

The mxsfb driver will crash if the mxsfb DT node has a subnode,
but the content of the subnode is not of-graph binding with an
endpoint linking to panel. The crash was triggered by providing
old-style panel bindings to the mxsfb driver instead of the new
of-graph ones.

The problem happens in mxsfb_create_output(), which is invoked
from mxsfb_load(). The mxsfb_create_output() iterates over all
mxsfb DT subnode endpoints and tries to bind a panel on each
endpoint. If there is any problem binding the panel, that is,
mxsfb->panel == NULL, this function will return an error code,
otherwise success 0 is returned.

If the subnodes do not specify of-graph binding with an endpoint,
the iteration over endpoints in mxsfb_create_output() will have
zero cycles and the function will immediatelly return 0, but the
mxsfb->panel will remain NULL. This is propagated back into the
mxsfb_load(), which does not detect any problem and expects that
the mxsfb->panel is valid, thus calls mxsfb_panel_attach(). But
since mxsfb->panel == NULL, mxsfb_panel_attach() is called with
first argument NULL and this crashes the kernel.

This patch fixes the problem by explicitly checking for valid
mxsfb->panel at the end of the iteration in mxsfb_create_output().

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Stefan Agner <stefan@agner.ch>
Cc: Breno Matheus Lima <brenomatheus@gmail.com>
Tested-by: Breno Lima <breno.lima@nxp.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/mxsfb/mxsfb_out.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/mxsfb/mxsfb_out.c b/drivers/gpu/drm/mxsfb/mxsfb_out.c
index fa8d17399407..b8e81422d4e2 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_out.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_out.c
@@ -112,6 +112,7 @@ static int mxsfb_attach_endpoint(struct drm_device *drm,
 
 int mxsfb_create_output(struct drm_device *drm)
 {
+	struct mxsfb_drm_private *mxsfb = drm->dev_private;
 	struct device_node *ep_np = NULL;
 	struct of_endpoint ep;
 	int ret;
@@ -127,5 +128,8 @@ int mxsfb_create_output(struct drm_device *drm)
 		}
 	}
 
+	if (!mxsfb->panel)
+		return -EPROBE_DEFER;
+
 	return 0;
 }
-- 
GitLab


From d42986b6c600da4215973878f1c889cdabbdd122 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Thu, 2 Feb 2017 19:26:38 -0200
Subject: [PATCH 891/898] drm: mxsfb_crtc: Fix the framebuffer misplacement

Currently the framebuffer content is displayed with incorrect offsets
in both the vertical and horizontal directions.

The fbdev version of the driver does not show this problem. Breno Lima
dumped the eLCDIF controller registers on both the drm and fbdev drivers
and noticed that the VDCTRL3 register is configured incorrectly in the
drm driver.

The fbdev driver calculates the vertical and horizontal wait counts
of the VDCTRL3 register by doing: back porch + sync length.

Looking at the horizontal and vertical timing diagram from
include/drm/drm_modes.h this value corresponds to:

crtc_[hv]total - crtc_[hv]sync_start

So fix the VDCTRL3 register setting accordingly so that the eLCDIF
controller can properly show the framebuffer content in the correct
position.

Reported-by: Breno Lima <breno.lima@nxp.com>
Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Tested-by: Breno Lima <breno.lima@nxp.com>
Tested-by: Marek Vasut <marex@denx.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/mxsfb/mxsfb_crtc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
index 165abd227436..1144e0c9e894 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
@@ -221,8 +221,8 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
 	       VDCTRL2_SET_HSYNC_PERIOD(m->crtc_htotal),
 	       mxsfb->base + LCDC_VDCTRL2);
 
-	writel(SET_HOR_WAIT_CNT(m->crtc_hblank_end - m->crtc_hsync_end) |
-	       SET_VERT_WAIT_CNT(m->crtc_vblank_end - m->crtc_vsync_end),
+	writel(SET_HOR_WAIT_CNT(m->crtc_htotal - m->crtc_hsync_start) |
+	       SET_VERT_WAIT_CNT(m->crtc_vtotal - m->crtc_vsync_start),
 	       mxsfb->base + LCDC_VDCTRL3);
 
 	writel(SET_DOTCLK_H_VALID_DATA_CNT(m->hdisplay),
-- 
GitLab


From 3f81e1340706e9a7f854808e2f580c3106805d0c Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Wed, 1 Feb 2017 15:19:47 -0200
Subject: [PATCH 892/898] drm: mxsfb: Implement drm_panel handling

Currently when the 'power-supply' regulator is passed via device tree
it does not actually work since drm_panel_prepare()/drm_panel_enable()
are never called.

Quoting Thierry Reding: "It should really call drm_panel_prepare() and
drm_panel_enable() while switching on the display pipeline and
drm_panel_disable(), followed by drm_panel_unprepare() while switching
off the display pipeline."

So do as suggested, so that the 'power-supply' regulator can be functional.

Reported-by: Breno Lima <breno.lima@nxp.com>
Suggested-by: Thierry Reding <thierry.reding@gmail.com>
Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Tested-by: Marek Vasut <marex@denx.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/mxsfb/mxsfb_drv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index cdfbe0284635..ff6d6a6f842e 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -102,14 +102,18 @@ static void mxsfb_pipe_enable(struct drm_simple_display_pipe *pipe,
 {
 	struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
 
+	drm_panel_prepare(mxsfb->panel);
 	mxsfb_crtc_enable(mxsfb);
+	drm_panel_enable(mxsfb->panel);
 }
 
 static void mxsfb_pipe_disable(struct drm_simple_display_pipe *pipe)
 {
 	struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
 
+	drm_panel_disable(mxsfb->panel);
 	mxsfb_crtc_disable(mxsfb);
+	drm_panel_unprepare(mxsfb->panel);
 }
 
 static void mxsfb_pipe_update(struct drm_simple_display_pipe *pipe,
-- 
GitLab


From bba8376aea1dcbbe22bbda118c52abee317c7609 Mon Sep 17 00:00:00 2001
From: Matjaz Hegedic <matjaz.hegedic@gmail.com>
Date: Thu, 9 Mar 2017 14:00:17 +0100
Subject: [PATCH 893/898] x86/reboot/quirks: Fix typo in ASUS EeeBook X205TA
 reboot quirk

The reboot quirk for ASUS EeeBook X205TA contains a typo in
DMI_PRODUCT_NAME, improperly referring to X205TAW instead of
X205TA, which prevents the quirk from being triggered. The
model X205TAW already has a reboot quirk of its own.

This fix simply removes the inappropriate final letter W.

Fixes: 90b28ded88dd ("x86/reboot/quirks: Add ASUS EeeBook X205TA reboot quirk")
Signed-off-by: Matjaz Hegedic <matjaz.hegedic@gmail.com>
Link: http://lkml.kernel.org/r/1489064417-7445-1-git-send-email-matjaz.hegedic@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/reboot.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 4194d6f9bb29..067f9813fd2c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -228,7 +228,7 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		.ident = "ASUS EeeBook X205TA",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X205TA"),
 		},
 	},
 	{	/* Handle problems with rebooting on ASUS EeeBook X205TAW */
-- 
GitLab


From 40c50c1fecdf012a3bf055ec813f0ef2eda2749c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 10 Mar 2017 13:17:18 +0100
Subject: [PATCH 894/898] kexec, x86/purgatory: Unbreak it and clean it up

The purgatory code defines global variables which are referenced via a
symbol lookup in the kexec code (core and arch).

A recent commit addressing sparse warnings made these static and thereby
broke kexec_file.

Why did this happen? Simply because the whole machinery is undocumented and
lacks any form of forward declarations. The variable names are unspecific
and lack a prefix, so adding forward declarations creates shadow variables
in the core code. Aside of that the code relies on magic constants and
duplicate struct definitions with no way to ensure that these things stay
in sync. The section placement of the purgatory variables happened by
chance and not by design.

Unbreak kexec and cleanup the mess:

 - Add proper forward declarations and document the usage
 - Use common struct definition
 - Use the proper common defines instead of magic constants
 - Add a purgatory_ prefix to have a proper name space
 - Use ARRAY_SIZE() instead of a homebrewn reimplementation
 - Add proper sections to the purgatory variables [ From Mike ]

Fixes: 72042a8c7b01 ("x86/purgatory: Make functions and variables static")
Reported-by: Mike Galbraith <<efault@gmx.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: "Tobin C. Harding" <me@tobin.cc>
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1703101315140.3681@nanos
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/powerpc/purgatory/trampoline.S | 12 +++++-----
 arch/x86/include/asm/purgatory.h    | 20 +++++++++++++++++
 arch/x86/kernel/machine_kexec_64.c  |  9 +++++---
 arch/x86/purgatory/purgatory.c      | 35 ++++++++++++++---------------
 arch/x86/purgatory/purgatory.h      |  8 -------
 arch/x86/purgatory/setup-x86_64.S   |  2 +-
 arch/x86/purgatory/sha256.h         |  1 -
 include/linux/purgatory.h           | 23 +++++++++++++++++++
 kernel/kexec_file.c                 |  8 +++----
 kernel/kexec_internal.h             |  6 +----
 10 files changed, 78 insertions(+), 46 deletions(-)
 create mode 100644 arch/x86/include/asm/purgatory.h
 delete mode 100644 arch/x86/purgatory/purgatory.h
 create mode 100644 include/linux/purgatory.h

diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S
index f9760ccf4032..3696ea6c4826 100644
--- a/arch/powerpc/purgatory/trampoline.S
+++ b/arch/powerpc/purgatory/trampoline.S
@@ -116,13 +116,13 @@ dt_offset:
 
 	.data
 	.balign 8
-.globl sha256_digest
-sha256_digest:
+.globl purgatory_sha256_digest
+purgatory_sha256_digest:
 	.skip	32
-	.size sha256_digest, . - sha256_digest
+	.size purgatory_sha256_digest, . - purgatory_sha256_digest
 
 	.balign 8
-.globl sha_regions
-sha_regions:
+.globl purgatory_sha_regions
+purgatory_sha_regions:
 	.skip	8 * 2 * 16
-	.size sha_regions, . - sha_regions
+	.size purgatory_sha_regions, . - purgatory_sha_regions
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
new file mode 100644
index 000000000000..d7da2729903d
--- /dev/null
+++ b/arch/x86/include/asm/purgatory.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_PURGATORY_H
+#define _ASM_X86_PURGATORY_H
+
+#ifndef __ASSEMBLY__
+#include <linux/purgatory.h>
+
+extern void purgatory(void);
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ *    lookup in kexec works
+ */
+extern unsigned long purgatory_backup_dest;
+extern unsigned long purgatory_backup_src;
+extern unsigned long purgatory_backup_sz;
+#endif	/* __ASSEMBLY__ */
+
+#endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 307b1f4543de..857cdbd02867 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -194,19 +194,22 @@ static int arch_update_purgatory(struct kimage *image)
 
 	/* Setup copying of backup region */
 	if (image->type == KEXEC_TYPE_CRASH) {
-		ret = kexec_purgatory_get_set_symbol(image, "backup_dest",
+		ret = kexec_purgatory_get_set_symbol(image,
+				"purgatory_backup_dest",
 				&image->arch.backup_load_addr,
 				sizeof(image->arch.backup_load_addr), 0);
 		if (ret)
 			return ret;
 
-		ret = kexec_purgatory_get_set_symbol(image, "backup_src",
+		ret = kexec_purgatory_get_set_symbol(image,
+				"purgatory_backup_src",
 				&image->arch.backup_src_start,
 				sizeof(image->arch.backup_src_start), 0);
 		if (ret)
 			return ret;
 
-		ret = kexec_purgatory_get_set_symbol(image, "backup_sz",
+		ret = kexec_purgatory_get_set_symbol(image,
+				"purgatory_backup_sz",
 				&image->arch.backup_src_sz,
 				sizeof(image->arch.backup_src_sz), 0);
 		if (ret)
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index b6d5c8946e66..470edad96bb9 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -10,22 +10,19 @@
  * Version 2.  See the file COPYING for more details.
  */
 
+#include <linux/bug.h>
+#include <asm/purgatory.h>
+
 #include "sha256.h"
-#include "purgatory.h"
 #include "../boot/string.h"
 
-struct sha_region {
-	unsigned long start;
-	unsigned long len;
-};
-
-static unsigned long backup_dest;
-static unsigned long backup_src;
-static unsigned long backup_sz;
+unsigned long purgatory_backup_dest __section(.kexec-purgatory);
+unsigned long purgatory_backup_src __section(.kexec-purgatory);
+unsigned long purgatory_backup_sz __section(.kexec-purgatory);
 
-static u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory);
 
-struct sha_region sha_regions[16] = {};
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory);
 
 /*
  * On x86, second kernel requries first 640K of memory to boot. Copy
@@ -34,26 +31,28 @@ struct sha_region sha_regions[16] = {};
  */
 static int copy_backup_region(void)
 {
-	if (backup_dest)
-		memcpy((void *)backup_dest, (void *)backup_src, backup_sz);
-
+	if (purgatory_backup_dest) {
+		memcpy((void *)purgatory_backup_dest,
+		       (void *)purgatory_backup_src, purgatory_backup_sz);
+	}
 	return 0;
 }
 
 static int verify_sha256_digest(void)
 {
-	struct sha_region *ptr, *end;
+	struct kexec_sha_region *ptr, *end;
 	u8 digest[SHA256_DIGEST_SIZE];
 	struct sha256_state sctx;
 
 	sha256_init(&sctx);
-	end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])];
-	for (ptr = sha_regions; ptr < end; ptr++)
+	end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+
+	for (ptr = purgatory_sha_regions; ptr < end; ptr++)
 		sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
 
 	sha256_final(&sctx, digest);
 
-	if (memcmp(digest, sha256_digest, sizeof(digest)))
+	if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)))
 		return 1;
 
 	return 0;
diff --git a/arch/x86/purgatory/purgatory.h b/arch/x86/purgatory/purgatory.h
deleted file mode 100644
index e2e365a6c192..000000000000
--- a/arch/x86/purgatory/purgatory.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef PURGATORY_H
-#define PURGATORY_H
-
-#ifndef __ASSEMBLY__
-extern void purgatory(void);
-#endif	/* __ASSEMBLY__ */
-
-#endif /* PURGATORY_H */
diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S
index f90e9dfa90bb..dfae9b9e60b5 100644
--- a/arch/x86/purgatory/setup-x86_64.S
+++ b/arch/x86/purgatory/setup-x86_64.S
@@ -9,7 +9,7 @@
  * This source code is licensed under the GNU General Public License,
  * Version 2.  See the file COPYING for more details.
  */
-#include "purgatory.h"
+#include <asm/purgatory.h>
 
 	.text
 	.globl purgatory_start
diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h
index bd15a4127735..2867d9825a57 100644
--- a/arch/x86/purgatory/sha256.h
+++ b/arch/x86/purgatory/sha256.h
@@ -10,7 +10,6 @@
 #ifndef SHA256_H
 #define SHA256_H
 
-
 #include <linux/types.h>
 #include <crypto/sha.h>
 
diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h
new file mode 100644
index 000000000000..d60d4e278609
--- /dev/null
+++ b/include/linux/purgatory.h
@@ -0,0 +1,23 @@
+#ifndef _LINUX_PURGATORY_H
+#define _LINUX_PURGATORY_H
+
+#include <linux/types.h>
+#include <crypto/sha.h>
+#include <uapi/linux/kexec.h>
+
+struct kexec_sha_region {
+	unsigned long start;
+	unsigned long len;
+};
+
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ *    lookup in kexec works
+ */
+extern struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
+extern u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
+
+#endif
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b56a558e406d..b118735fea9d 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image)
 		ret = crypto_shash_final(desc, digest);
 		if (ret)
 			goto out_free_digest;
-		ret = kexec_purgatory_get_set_symbol(image, "sha_regions",
-						sha_regions, sha_region_sz, 0);
+		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
+						     sha_regions, sha_region_sz, 0);
 		if (ret)
 			goto out_free_digest;
 
-		ret = kexec_purgatory_get_set_symbol(image, "sha256_digest",
-						digest, SHA256_DIGEST_SIZE, 0);
+		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
+						     digest, SHA256_DIGEST_SIZE, 0);
 		if (ret)
 			goto out_free_digest;
 	}
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 4cef7e4706b0..799a8a452187 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image,
 extern struct mutex kexec_mutex;
 
 #ifdef CONFIG_KEXEC_FILE
-struct kexec_sha_region {
-	unsigned long start;
-	unsigned long len;
-};
-
+#include <linux/purgatory.h>
 void kimage_file_post_load_cleanup(struct kimage *image);
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
-- 
GitLab


From 0acf611997d9d05dbfb559c3c6e379c861eb5957 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 22 Feb 2017 11:07:57 -0800
Subject: [PATCH 895/898] score: Fix implicit includes now failing build after
 extable change

After changing from module.h to extable.h, score builds fail with:

  arch/score/kernel/traps.c: In function 'do_ri':
  arch/score/kernel/traps.c:248:4: error: implicit declaration of function 'user_disable_single_step'
  arch/score/mm/extable.c: In function 'fixup_exception':
  arch/score/mm/extable.c:32:38: error: dereferencing pointer to incomplete type
  arch/score/mm/extable.c:34:24: error: dereferencing pointer to incomplete type

because extable.h doesn't drag in the same amount of headers as the
module.h did.  Add in the headers which were implicitly expected.

Fixes: 90858794c960 ("module.h: remove extable.h include now users have migrated")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
[PG: tweak commit log; refresh for sched header refactoring.]
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 arch/score/kernel/traps.c | 1 +
 arch/score/mm/extable.c   | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index e359ec675869..12daf45369b4 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -24,6 +24,7 @@
  */
 
 #include <linux/extable.h>
+#include <linux/ptrace.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
diff --git a/arch/score/mm/extable.c b/arch/score/mm/extable.c
index ec871355fc2d..6736a3ad6286 100644
--- a/arch/score/mm/extable.c
+++ b/arch/score/mm/extable.c
@@ -24,6 +24,8 @@
  */
 
 #include <linux/extable.h>
+#include <linux/ptrace.h>
+#include <asm/extable.h>
 
 int fixup_exception(struct pt_regs *regs)
 {
-- 
GitLab


From 2c4ea6e28dbf15ab93632c5c189f3948366b8885 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 11 Mar 2017 01:31:19 +0100
Subject: [PATCH 896/898] x86/tlb: Fix tlb flushing when lguest clears PGE

Fengguang reported random corruptions from various locations on x86-32
after commits d2852a224050 ("arch: add ARCH_HAS_SET_MEMORY config") and
9d876e79df6a ("bpf: fix unlocking of jited image when module ronx not set")
that uses the former. While x86-32 doesn't have a JIT like x86_64, the
bpf_prog_lock_ro() and bpf_prog_unlock_ro() got enabled due to
ARCH_HAS_SET_MEMORY, whereas Fengguang's test kernel doesn't have module
support built in and therefore never had the DEBUG_SET_MODULE_RONX setting
enabled.

After investigating the crashes further, it turned out that using
set_memory_ro() and set_memory_rw() didn't have the desired effect, for
example, setting the pages as read-only on x86-32 would still let
probe_kernel_write() succeed without error. This behavior would manifest
itself in situations where the vmalloc'ed buffer was accessed prior to
set_memory_*() such as in case of bpf_prog_alloc(). In cases where it
wasn't, the page attribute changes seemed to have taken effect, leading to
the conclusion that a TLB invalidate didn't happen. Moreover, it turned out
that this issue reproduced with qemu in "-cpu kvm64" mode, but not for
"-cpu host". When the issue occurs, change_page_attr_set_clr() did trigger
a TLB flush as expected via __flush_tlb_all() through cpa_flush_range(),
though.

There are 3 variants for issuing a TLB flush: invpcid_flush_all() (depends
on CPU feature bits X86_FEATURE_INVPCID, X86_FEATURE_PGE), cr4 based flush
(depends on X86_FEATURE_PGE), and cr3 based flush.  For "-cpu host" case in
my setup, the flush used invpcid_flush_all() variant, whereas for "-cpu
kvm64", the flush was cr4 based. Switching the kvm64 case to cr3 manually
worked fine, and further investigating the cr4 one turned out that
X86_CR4_PGE bit was not set in cr4 register, meaning the
__native_flush_tlb_global_irq_disabled() wrote cr4 twice with the same
value instead of clearing X86_CR4_PGE in the first write to trigger the
flush.

It turned out that X86_CR4_PGE was cleared from cr4 during init from
lguest_arch_host_init() via adjust_pge(). The X86_FEATURE_PGE bit is also
cleared from there due to concerns of using PGE in guest kernel that can
lead to hard to trace bugs (see bff672e630a0 ("lguest: documentation V:
Host") in init()). The CPU feature bits are cleared in dynamic
boot_cpu_data, but they never propagated to __flush_tlb_all() as it uses
static_cpu_has() instead of boot_cpu_has() for testing which variant of TLB
flushing to use, meaning they still used the old setting of the host
kernel.

Clearing via setup_clear_cpu_cap(X86_FEATURE_PGE) so this would propagate
to static_cpu_has() checks is too late at this point as sections have been
patched already, so for now, it seems reasonable to switch back to
boot_cpu_has(X86_FEATURE_PGE) as it was prior to commit c109bf95992b
("x86/cpufeature: Remove cpu_has_pge"). This lets the TLB flush trigger via
cr3 as originally intended, properly makes the new page attributes visible
and thus fixes the crashes seen by Fengguang.

Fixes: c109bf95992b ("x86/cpufeature: Remove cpu_has_pge")
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: bp@suse.de
Cc: Kees Cook <keescook@chromium.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: lkp@01.org
Cc: Laura Abbott <labbott@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernrl.org/r/20170301125426.l4nf65rx4wahohyl@wfg-t540p.sh.intel.com
Link: http://lkml.kernel.org/r/25c41ad9eca164be4db9ad84f768965b7eb19d9e.1489191673.git.daniel@iogearbox.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/tlbflush.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6fa85944af83..fc5abff9b7fd 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -188,7 +188,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
 
 static inline void __flush_tlb_all(void)
 {
-	if (static_cpu_has(X86_FEATURE_PGE))
+	if (boot_cpu_has(X86_FEATURE_PGE))
 		__flush_tlb_global();
 	else
 		__flush_tlb();
-- 
GitLab


From 4495c08e84729385774601b5146d51d9e5849f81 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 12 Mar 2017 14:47:08 -0700
Subject: [PATCH 897/898] Linux 4.11-rc2

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 165cf9783a5d..b841fb36beb2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
-- 
GitLab


From 822f5845f710e57d7e2df1fd1ee00d6e19d334fe Mon Sep 17 00:00:00 2001
From: Daniel Drake <drake@endlessm.com>
Date: Tue, 7 Feb 2017 13:08:23 -0600
Subject: [PATCH 898/898] efi/esrt: Cleanup bad memory map log messages

The Intel Compute Stick STCK1A8LFC and Weibu F3C platforms both
log 2 error messages during boot:

   efi: requested map not found.
   esrt: ESRT header is not in the memory map.

Searching the web, this seems to affect many other platforms too.
Since these messages are logged as errors, they appear on-screen during
the boot process even when using the "quiet" boot parameter used by
distros.

Demote the ESRT error to a warning so that it does not appear on-screen,
and delete the error logging from efi_mem_desc_lookup; both callsites
of that function log more specific messages upon failure.

Out of curiosity I looked closer at the Weibu F3C. There is no entry in
the UEFI-provided memory map which corresponds to the ESRT pointer, but
hacking the code to map it anyway, the ESRT does appear to be valid with
2 entries.

Signed-off-by: Daniel Drake <drake@endlessm.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Acked-by: Peter Jones <pjones@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 drivers/firmware/efi/efi.c  | 1 -
 drivers/firmware/efi/esrt.c | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index e7d404059b73..b372aad3b449 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -389,7 +389,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 			return 0;
 		}
 	}
-	pr_err_once("requested map not found.\n");
 	return -ENOENT;
 }
 
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 08b026864d4e..8554d7aec31c 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -254,7 +254,7 @@ void __init efi_esrt_init(void)
 
 	rc = efi_mem_desc_lookup(efi.esrt, &md);
 	if (rc < 0) {
-		pr_err("ESRT header is not in the memory map.\n");
+		pr_warn("ESRT header is not in the memory map.\n");
 		return;
 	}
 
-- 
GitLab