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

Commit e3377f36 authored by Zoltan Kiss's avatar Zoltan Kiss Committed by David S. Miller
Browse files

xen-netback: Handle guests with too many frags 



Xen network protocol had implicit dependency on MAX_SKB_FRAGS. Netback has to
handle guests sending up to XEN_NETBK_LEGACY_SLOTS_MAX slots. To achieve that:
- create a new skb
- map the leftover slots to its frags (no linear buffer here!)
- chain it to the previous through skb_shinfo(skb)->frag_list
- map them
- copy and coalesce the frags into a brand new one and send it to the stack
- unmap the 2 old skb's pages

It's also introduces new stat counters, which help determine how often the guest
sends a packet with more than MAX_SKB_FRAGS frags.

NOTE: if bisect brought you here, you should apply the series up until
"xen-netback: Timeout packets in RX path", otherwise malicious guests can block
other guests by not releasing their sent packets.

Signed-off-by: default avatarZoltan Kiss <zoltan.kiss@citrix.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 1bb332af

drivers/net/xen-netback/common.h

+1 −0
Original line number Original line Diff line number Diff line
@@ -182,6 +182,7 @@ struct xenvif { 
	unsigned long tx_zerocopy_sent;

	unsigned long tx_zerocopy_sent;

	unsigned long tx_zerocopy_success;

	unsigned long tx_zerocopy_success;

	unsigned long tx_zerocopy_fail;

	unsigned long tx_zerocopy_fail;

	unsigned long tx_frag_overflow;





	/* Miscellaneous private stuff. */

	/* Miscellaneous private stuff. */

	struct net_device *dev;

	struct net_device *dev;

drivers/net/xen-netback/interface.c

+7 −0
Original line number Original line Diff line number Diff line
@@ -253,6 +253,13 @@ static const struct xenvif_stat { 
		"tx_zerocopy_fail",

		"tx_zerocopy_fail",

		offsetof(struct xenvif, tx_zerocopy_fail)

		offsetof(struct xenvif, tx_zerocopy_fail)

	},

	},

	/* Number of packets exceeding MAX_SKB_FRAG slots. You should use

	 * a guest with the same MAX_SKB_FRAG

	 */

	{

		"tx_frag_overflow",

		offsetof(struct xenvif, tx_frag_overflow)

	},

};

};





static int xenvif_get_sset_count(struct net_device *dev, int string_set)

static int xenvif_get_sset_count(struct net_device *dev, int string_set)

drivers/net/xen-netback/netback.c

+154 −10
Original line number Original line Diff line number Diff line
@@ -37,6 +37,7 @@ 
#include <linux/kthread.h>

#include <linux/kthread.h>

#include <linux/if_vlan.h>

#include <linux/if_vlan.h>

#include <linux/udp.h>

#include <linux/udp.h>

#include <linux/highmem.h>





#include <net/tcp.h>

#include <net/tcp.h>
@@ -801,6 +802,23 @@ static inline void xenvif_tx_create_gop(struct xenvif *vif, 
	       sizeof(*txp));

	       sizeof(*txp));

}

}





static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)

{

	struct sk_buff *skb =

		alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN,

			  GFP_ATOMIC | __GFP_NOWARN);

	if (unlikely(skb == NULL))

		return NULL;



	/* Packets passed to netif_rx() must have some headroom. */

	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);



	/* Initialize it here to avoid later surprises */

	skb_shinfo(skb)->destructor_arg = NULL;



	return skb;

}



static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,

static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,

							struct sk_buff *skb,

							struct sk_buff *skb,

							struct xen_netif_tx_request *txp,

							struct xen_netif_tx_request *txp,
@@ -811,11 +829,16 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, 
	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;

	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;

	int start;

	int start;

	pending_ring_idx_t index;

	pending_ring_idx_t index;

	unsigned int nr_slots;

	unsigned int nr_slots, frag_overflow = 0;





	/* At this point shinfo->nr_frags is in fact the number of

	/* At this point shinfo->nr_frags is in fact the number of

	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.

	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.

	 */

	 */

	if (shinfo->nr_frags > MAX_SKB_FRAGS) {

		frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS;

		BUG_ON(frag_overflow > MAX_SKB_FRAGS);

		shinfo->nr_frags = MAX_SKB_FRAGS;

	}

	nr_slots = shinfo->nr_frags;

	nr_slots = shinfo->nr_frags;





	/* Skip first skb fragment if it is on same page as header fragment. */

	/* Skip first skb fragment if it is on same page as header fragment. */
@@ -829,7 +852,29 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, 
		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);

		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);

	}

	}





	BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS);

	if (frag_overflow) {

		struct sk_buff *nskb = xenvif_alloc_skb(0);

		if (unlikely(nskb == NULL)) {

			if (net_ratelimit())

				netdev_err(vif->dev,

					   "Can't allocate the frag_list skb.\n");

			return NULL;

		}



		shinfo = skb_shinfo(nskb);

		frags = shinfo->frags;



		for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow;

		     shinfo->nr_frags++, txp++, gop++) {

			index = pending_index(vif->pending_cons++);

			pending_idx = vif->pending_ring[index];

			xenvif_tx_create_gop(vif, pending_idx, txp, gop);

			frag_set_pending_idx(&frags[shinfo->nr_frags],

					     pending_idx);

		}



		skb_shinfo(skb)->frag_list = nskb;

	}





	return gop;

	return gop;

}

}
@@ -871,6 +916,7 @@ static int xenvif_tx_check_gop(struct xenvif *vif, 
	struct pending_tx_info *tx_info;

	struct pending_tx_info *tx_info;

	int nr_frags = shinfo->nr_frags;

	int nr_frags = shinfo->nr_frags;

	int i, err, start;

	int i, err, start;

	struct sk_buff *first_skb = NULL;





	/* Check status of header. */

	/* Check status of header. */

	err = gop->status;

	err = gop->status;
@@ -882,6 +928,7 @@ static int xenvif_tx_check_gop(struct xenvif *vif, 
	/* Skip first skb fragment if it is on same page as header fragment. */

	/* Skip first skb fragment if it is on same page as header fragment. */

	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);

	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);





check_frags:

	for (i = start; i < nr_frags; i++) {

	for (i = start; i < nr_frags; i++) {

		int j, newerr;

		int j, newerr;
@@ -905,8 +952,10 @@ static int xenvif_tx_check_gop(struct xenvif *vif, 
		/* Not the first error? Preceding frags already invalidated. */

		/* Not the first error? Preceding frags already invalidated. */

		if (err)

		if (err)

			continue;

			continue;



		/* First error: invalidate header and preceding fragments. */

		/* First error: invalidate header and preceding fragments. */

		if (!first_skb)

			pending_idx = XENVIF_TX_CB(skb)->pending_idx;

		else

			pending_idx = XENVIF_TX_CB(skb)->pending_idx;

			pending_idx = XENVIF_TX_CB(skb)->pending_idx;

		xenvif_idx_unmap(vif, pending_idx);

		xenvif_idx_unmap(vif, pending_idx);

		for (j = start; j < i; j++) {

		for (j = start; j < i; j++) {
@@ -918,6 +967,30 @@ static int xenvif_tx_check_gop(struct xenvif *vif, 
		err = newerr;

		err = newerr;

	}

	}





	if (skb_has_frag_list(skb)) {

		first_skb = skb;

		skb = shinfo->frag_list;

		shinfo = skb_shinfo(skb);

		nr_frags = shinfo->nr_frags;

		start = 0;



		goto check_frags;

	}



	/* There was a mapping error in the frag_list skb. We have to unmap

	 * the first skb's frags

	 */

	if (first_skb && err) {

		int j;

		shinfo = skb_shinfo(first_skb);

		pending_idx = XENVIF_TX_CB(skb)->pending_idx;

		start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);

		for (j = start; j < shinfo->nr_frags; j++) {

			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);

			xenvif_idx_unmap(vif, pending_idx);

		}

	}



	*gopp = gop + 1;

	*gopp = gop + 1;

	return err;

	return err;

}

}
@@ -1169,8 +1242,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) 
			    ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?

			    ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?

			PKT_PROT_LEN : txreq.size;

			PKT_PROT_LEN : txreq.size;





		skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN,

		skb = xenvif_alloc_skb(data_len);

				GFP_ATOMIC | __GFP_NOWARN);

		if (unlikely(skb == NULL)) {

		if (unlikely(skb == NULL)) {

			netdev_dbg(vif->dev,

			netdev_dbg(vif->dev,

				   "Can't allocate a skb in start_xmit.\n");

				   "Can't allocate a skb in start_xmit.\n");
@@ -1178,9 +1250,6 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) 
			break;

			break;

		}

		}





		/* Packets passed to netif_rx() must have some headroom. */

		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);



		if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {

		if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {

			struct xen_netif_extra_info *gso;

			struct xen_netif_extra_info *gso;

			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];

			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
@@ -1231,6 +1300,71 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) 
	return gop - vif->tx_map_ops;

	return gop - vif->tx_map_ops;

}

}





/* Consolidate skb with a frag_list into a brand new one with local pages on

 * frags. Returns 0 or -ENOMEM if can't allocate new pages.

 */

static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)

{

	unsigned int offset = skb_headlen(skb);

	skb_frag_t frags[MAX_SKB_FRAGS];

	int i;

	struct ubuf_info *uarg;

	struct sk_buff *nskb = skb_shinfo(skb)->frag_list;



	vif->tx_zerocopy_sent += 2;

	vif->tx_frag_overflow++;



	xenvif_fill_frags(vif, nskb);

	/* Subtract frags size, we will correct it later */

	skb->truesize -= skb->data_len;

	skb->len += nskb->len;

	skb->data_len += nskb->len;



	/* create a brand new frags array and coalesce there */

	for (i = 0; offset < skb->len; i++) {

		struct page *page;

		unsigned int len;



		BUG_ON(i >= MAX_SKB_FRAGS);

		page = alloc_page(GFP_ATOMIC|__GFP_COLD);

		if (!page) {

			int j;

			skb->truesize += skb->data_len;

			for (j = 0; j < i; j++)

				put_page(frags[j].page.p);

			return -ENOMEM;

		}



		if (offset + PAGE_SIZE < skb->len)

			len = PAGE_SIZE;

		else

			len = skb->len - offset;

		if (skb_copy_bits(skb, offset, page_address(page), len))

			BUG();



		offset += len;

		frags[i].page.p = page;

		frags[i].page_offset = 0;

		skb_frag_size_set(&frags[i], len);

	}

	/* swap out with old one */

	memcpy(skb_shinfo(skb)->frags,

	       frags,

	       i * sizeof(skb_frag_t));

	skb_shinfo(skb)->nr_frags = i;

	skb->truesize += i * PAGE_SIZE;



	/* remove traces of mapped pages and frag_list */

	skb_frag_list_init(skb);

	uarg = skb_shinfo(skb)->destructor_arg;

	uarg->callback(uarg, true);

	skb_shinfo(skb)->destructor_arg = NULL;



	skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY;

	kfree_skb(nskb);



	return 0;

}





static int xenvif_tx_submit(struct xenvif *vif)

static int xenvif_tx_submit(struct xenvif *vif)

{

{
@@ -1267,7 +1401,6 @@ static int xenvif_tx_submit(struct xenvif *vif) 
				&vif->pending_tx_info[pending_idx].callback_struct;

				&vif->pending_tx_info[pending_idx].callback_struct;

		} else {

		} else {

			/* Schedule a response immediately. */

			/* Schedule a response immediately. */

			skb_shinfo(skb)->destructor_arg = NULL;

			xenvif_idx_unmap(vif, pending_idx);

			xenvif_idx_unmap(vif, pending_idx);

		}

		}
@@ -1278,6 +1411,17 @@ static int xenvif_tx_submit(struct xenvif *vif) 




		xenvif_fill_frags(vif, skb);

		xenvif_fill_frags(vif, skb);





		if (unlikely(skb_has_frag_list(skb))) {

			if (xenvif_handle_frag_list(vif, skb)) {

				if (net_ratelimit())

					netdev_err(vif->dev,

						   "Not enough memory to consolidate frag_list!\n");

				skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;

				kfree_skb(skb);

				continue;

			}

		}



		if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) {

		if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) {

			int target = min_t(int, skb->len, PKT_PROT_LEN);

			int target = min_t(int, skb->len, PKT_PROT_LEN);

			__pskb_pull_tail(skb, target - skb_headlen(skb));

			__pskb_pull_tail(skb, target - skb_headlen(skb));