Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 1ea406c0 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband 

Pull infiniband/rdma updates from Roland Dreier:
 - Re-enable flow steering verbs with new improved userspace ABI
 - Fixes for slow connection due to GID lookup scalability
 - IPoIB fixes
 - Many fixes to HW drivers including mlx4, mlx5, ocrdma and qib
 - Further improvements to SRP error handling
 - Add new transport type for Cisco usNIC

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (66 commits)
  IB/core: Re-enable create_flow/destroy_flow uverbs
  IB/core: extended command: an improved infrastructure for uverbs commands
  IB/core: Remove ib_uverbs_flow_spec structure from userspace
  IB/core: Use a common header for uverbs flow_specs
  IB/core: Make uverbs flow structure use names like verbs ones
  IB/core: Rename 'flow' structs to match other uverbs structs
  IB/core: clarify overflow/underflow checks on ib_create/destroy_flow
  IB/ucma: Convert use of typedef ctl_table to struct ctl_table
  IB/cm: Convert to using idr_alloc_cyclic()
  IB/mlx5: Fix page shift in create CQ for userspace
  IB/mlx4: Fix device max capabilities check
  IB/mlx5: Fix list_del of empty list
  IB/mlx5: Remove dead code
  IB/core: Encorce MR access rights rules on kernel consumers
  IB/mlx4: Fix endless loop in resize CQ
  RDMA/cma: Remove unused argument and minor dead code
  RDMA/ucma: Discard events for IDs not yet claimed by user space
  IB/core: Add Cisco usNIC rdma node and transport types
  RDMA/nes: Remove self-assignment from nes_query_qp()
  IB/srp: Report receive errors correctly
  ...
parents a709bd58 b4fdf52b

Documentation/ABI/stable/sysfs-driver-ib_srp

+13 −0
Original line number Diff line number Diff line
@@ -61,6 +61,12 @@ Description: Interface for making ib_srp connect to a new target. 
		  interrupt is handled by a different CPU then the comp_vector

		  parameter can be used to spread the SRP completion workload

		  over multiple CPU's.

		* tl_retry_count, a number in the range 2..7 specifying the

		  IB RC retry count.

		* queue_size, the maximum number of commands that the

		  initiator is allowed to queue per SCSI host. The default

		  value for this parameter is 62. The lowest supported value

		  is 2.



What:		/sys/class/infiniband_srp/srp-<hca>-<port_number>/ibdev

Date:		January 2, 2006
@@ -153,6 +159,13 @@ Contact: linux-rdma@vger.kernel.org 
Description:	InfiniBand service ID used for establishing communication with

		the SRP	target.



What:		/sys/class/scsi_host/host<n>/sgid

Date:		February 1, 2014

KernelVersion:	3.13

Contact:	linux-rdma@vger.kernel.org

Description:	InfiniBand GID of the source port used for communication with

		the SRP target.



What:		/sys/class/scsi_host/host<n>/zero_req_lim

Date:		September 20, 2006

KernelVersion:	2.6.18

Documentation/ABI/stable/sysfs-transport-srp

+39 −0
Original line number Diff line number Diff line
@@ -5,6 +5,24 @@ Contact: linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org 
Description:	Instructs an SRP initiator to disconnect from a target and to

		remove all LUNs imported from that target.



What:		/sys/class/srp_remote_ports/port-<h>:<n>/dev_loss_tmo

Date:		February 1, 2014

KernelVersion:	3.13

Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org

Description:	Number of seconds the SCSI layer will wait after a transport

		layer error has been observed before removing a target port.

		Zero means immediate removal. Setting this attribute to "off"

		will disable the dev_loss timer.



What:		/sys/class/srp_remote_ports/port-<h>:<n>/fast_io_fail_tmo

Date:		February 1, 2014

KernelVersion:	3.13

Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org

Description:	Number of seconds the SCSI layer will wait after a transport

		layer error has been observed before failing I/O. Zero means

		failing I/O immediately. Setting this attribute to "off" will

		disable the fast_io_fail timer.



What:		/sys/class/srp_remote_ports/port-<h>:<n>/port_id

Date:		June 27, 2007

KernelVersion:	2.6.24
@@ -12,8 +30,29 @@ Contact: linux-scsi@vger.kernel.org 
Description:	16-byte local SRP port identifier in hexadecimal format. An

		example: 4c:49:4e:55:58:20:56:49:4f:00:00:00:00:00:00:00.



What:		/sys/class/srp_remote_ports/port-<h>:<n>/reconnect_delay

Date:		February 1, 2014

KernelVersion:	3.13

Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org

Description:	Number of seconds the SCSI layer will wait after a reconnect

		attempt failed before retrying. Setting this attribute to

		"off" will disable time-based reconnecting.



What:		/sys/class/srp_remote_ports/port-<h>:<n>/roles

Date:		June 27, 2007

KernelVersion:	2.6.24

Contact:	linux-scsi@vger.kernel.org

Description:	Role of the remote port. Either "SRP Initiator" or "SRP Target".



What:		/sys/class/srp_remote_ports/port-<h>:<n>/state

Date:		February 1, 2014

KernelVersion:	3.13

Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org

Description:	State of the transport layer used for communication with the

		remote port. "running" if the transport layer is operational;

		"blocked" if a transport layer error has been encountered but

		the fast_io_fail_tmo timer has not yet fired; "fail-fast"

		after the fast_io_fail_tmo timer has fired and before the

		"dev_loss_tmo" timer has fired; "lost" after the

		"dev_loss_tmo" timer has fired and before the port is finally

		removed.

drivers/infiniband/Kconfig

+0 −11
Original line number Diff line number Diff line
@@ -31,17 +31,6 @@ config INFINIBAND_USER_ACCESS 
	  libibverbs, libibcm and a hardware driver library from

	  <http://www.openfabrics.org/git/>.



config INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING

       bool "Experimental and unstable ABI for userspace access to flow steering verbs"

       depends on INFINIBAND_USER_ACCESS

       depends on STAGING

	---help---

	  The final ABI for userspace access to flow steering verbs

	  has not been defined.  To use the current ABI, *WHICH WILL

	  CHANGE IN THE FUTURE*, say Y here.



	  If unsure, say N.



config INFINIBAND_USER_MEM

	bool

	depends on INFINIBAND_USER_ACCESS != n

drivers/infiniband/core/cm.c

+1 −4
Original line number Diff line number Diff line
@@ -383,14 +383,11 @@ static int cm_alloc_id(struct cm_id_private *cm_id_priv) 
{

	unsigned long flags;

	int id;

	static int next_id;



	idr_preload(GFP_KERNEL);

	spin_lock_irqsave(&cm.lock, flags);



	id = idr_alloc(&cm.local_id_table, cm_id_priv, next_id, 0, GFP_NOWAIT);

	if (id >= 0)

		next_id = max(id + 1, 0);

	id = idr_alloc_cyclic(&cm.local_id_table, cm_id_priv, 0, 0, GFP_NOWAIT);



	spin_unlock_irqrestore(&cm.lock, flags);

	idr_preload_end();

drivers/infiniband/core/cma.c

+33 −35
Original line number Diff line number Diff line
@@ -328,28 +328,6 @@ static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) 
	return ret;

}



static int find_gid_port(struct ib_device *device, union ib_gid *gid, u8 port_num)

{

	int i;

	int err;

	struct ib_port_attr props;

	union ib_gid tmp;



	err = ib_query_port(device, port_num, &props);

	if (err)

		return err;



	for (i = 0; i < props.gid_tbl_len; ++i) {

		err = ib_query_gid(device, port_num, i, &tmp);

		if (err)

			return err;

		if (!memcmp(&tmp, gid, sizeof tmp))

			return 0;

	}



	return -EADDRNOTAVAIL;

}



static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr)

{

	dev_addr->dev_type = ARPHRD_INFINIBAND;
@@ -371,13 +349,14 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a 
	return ret;

}



static int cma_acquire_dev(struct rdma_id_private *id_priv)

static int cma_acquire_dev(struct rdma_id_private *id_priv,

			   struct rdma_id_private *listen_id_priv)

{

	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;

	struct cma_device *cma_dev;

	union ib_gid gid, iboe_gid;

	int ret = -ENODEV;

	u8 port;

	u8 port, found_port;

	enum rdma_link_layer dev_ll = dev_addr->dev_type == ARPHRD_INFINIBAND ?

		IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
@@ -389,17 +368,39 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv) 
	iboe_addr_get_sgid(dev_addr, &iboe_gid);

	memcpy(&gid, dev_addr->src_dev_addr +

	       rdma_addr_gid_offset(dev_addr), sizeof gid);

	if (listen_id_priv &&

	    rdma_port_get_link_layer(listen_id_priv->id.device,

				     listen_id_priv->id.port_num) == dev_ll) {

		cma_dev = listen_id_priv->cma_dev;

		port = listen_id_priv->id.port_num;

		if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB &&

		    rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET)

			ret = ib_find_cached_gid(cma_dev->device, &iboe_gid,

						 &found_port, NULL);

		else

			ret = ib_find_cached_gid(cma_dev->device, &gid,

						 &found_port, NULL);



		if (!ret && (port  == found_port)) {

			id_priv->id.port_num = found_port;

			goto out;

		}

	}

	list_for_each_entry(cma_dev, &dev_list, list) {

		for (port = 1; port <= cma_dev->device->phys_port_cnt; ++port) {

			if (listen_id_priv &&

			    listen_id_priv->cma_dev == cma_dev &&

			    listen_id_priv->id.port_num == port)

				continue;

			if (rdma_port_get_link_layer(cma_dev->device, port) == dev_ll) {

				if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB &&

				    rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET)

					ret = find_gid_port(cma_dev->device, &iboe_gid, port);

					ret = ib_find_cached_gid(cma_dev->device, &iboe_gid, &found_port, NULL);

				else

					ret = find_gid_port(cma_dev->device, &gid, port);

					ret = ib_find_cached_gid(cma_dev->device, &gid, &found_port, NULL);



				if (!ret) {

					id_priv->id.port_num = port;

				if (!ret && (port == found_port)) {

					id_priv->id.port_num = found_port;

					goto out;

				}

			}
@@ -1292,7 +1293,7 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) 
	}



	mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);

	ret = cma_acquire_dev(conn_id);

	ret = cma_acquire_dev(conn_id, listen_id);

	if (ret)

		goto err2;
@@ -1451,7 +1452,6 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, 
{

	struct rdma_cm_id *new_cm_id;

	struct rdma_id_private *listen_id, *conn_id;

	struct net_device *dev = NULL;

	struct rdma_cm_event event;

	int ret;

	struct ib_device_attr attr;
@@ -1481,7 +1481,7 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, 
		goto out;

	}



	ret = cma_acquire_dev(conn_id);

	ret = cma_acquire_dev(conn_id, listen_id);

	if (ret) {

		mutex_unlock(&conn_id->handler_mutex);

		rdma_destroy_id(new_cm_id);
@@ -1529,8 +1529,6 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, 
	cma_deref_id(conn_id);



out:

	if (dev)

		dev_put(dev);

	mutex_unlock(&listen_id->handler_mutex);

	return ret;

}
@@ -2066,7 +2064,7 @@ static void addr_handler(int status, struct sockaddr *src_addr, 
		goto out;



	if (!status && !id_priv->cma_dev)

		status = cma_acquire_dev(id_priv);

		status = cma_acquire_dev(id_priv, NULL);



	if (status) {

		if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED,
@@ -2563,7 +2561,7 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) 
		if (ret)

			goto err1;



		ret = cma_acquire_dev(id_priv);

		ret = cma_acquire_dev(id_priv, NULL);

		if (ret)

			goto err1;

	}