virtio-net: drop the rest of buffers when we can't allocate skb
Subsystems (4)
PATCH 1/3 virtio-net: drop the rest of buffers when we can't allocate skb
When mergeable buffer were used, we only put the first page buf leave the rest of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this packet.
The bug was introduced by commit 9ab86bbcf8be755256f0a5e994e0b38af6b4d399 (virtio_net: Defer skb allocation in receive path).
---
This patch was needed for stable
--- drivers/net/virtio_net.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)
drivers/net/virtio_net.c +17 -1
@@ -222,6 +222,17 @@ static void skb_xmit_done(struct virtqueue *vq)netif_wake_subqueue (vi->dev,vq2txq (vq)); } +static void drop_mergeable_buffer (struct receive_queue *rq,int num_buf) +{ +char *buf; +int len; + +while (--num_buf && (buf =virtqueue_get_buf (rq->vq, &len)) !=NULL ) { + --rq->num; +put_page (virt_to_head_page (buf)); + } +} +/* Called from bottom half context */ static struct sk_buff *page_to_skb(struct receive_queue *rq, struct page *page, unsigned int offset,
@@ -237,8 +248,13 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,/* copy small packet so we can reuse these pages for small data */ skb =netdev_alloc_skb_ip_align (vi->dev,GOOD_COPY_LEN ); -if (unlikely (!skb)) +if (unlikely (!skb)) { +if (vi->mergeable_rx_bufs) { + hdr = (struct skb_vnet_hdr *)p; +drop_mergeable_buffer (rq, hdr->mhdr.num_buffers); + }return NULL ; + } hdr =skb_vnet_hdr (skb);
Signature · 1 line
1.8.3.2
PATCH 2/3 virtio-net: fix num calculation on frag skb allocation failure
We need decrease the rq->num after we can get a buf through virtqueue_get_buf() even if we could not allocate frag skb. Otherwise, the refill routine won't be triggered under heavy memory stress since the driver may still think there's enough room.
This bug was introduced by commit 2613af0ed18a11d5c566a81f9a6510b73180660a (virtio_net: migrate mergeable rx buffers to page frag allocators).
---
The patch was needed for 3.12 stable.
--- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/virtio_net.c +1 -1
@@ -333,6 +333,7 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) head_skb->dev->stats.rx_length_errors++;return -EINVAL ; } + --rq->num;if (unlikely (len >MERGE_BUFFER_LEN )) {pr_debug ("%s: rx error: merge buffer too long\n" , head_skb->dev->name);
@@ -367,7 +368,6 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)skb_add_rx_frag (curr_skb, num_skb_frags, page, offset, len,MERGE_BUFFER_LEN ); } - --rq->num; }return 0 ; }
Signature · 1 line
1.8.3.2
Michael S. Tsirkin
maintainerRe: [PATCH net 2/3] virtio-net: fix num calculation on frag skb allocation failure
Quoted 5 lines · Jason Wang
We need decrease the
rq->numafter we can get a buf throughvirtqueue_get_buf()even if we could not allocate frag skb. Otherwise, the refill routine won't be triggered under heavy memory stress since the driver may still think there's enough room.
Quoted 8 lines
This bug was introduced by commit
2613af0ed18a11d5c566a81f9a6510b73180660a(virtio_net: migrate mergeable rx buffers to page frag allocators).Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Signed-off-by Jason Wang <[email protected]>
So let's wrap virtqueue_get_buf to make sure we get it right?
Quoted 28 lines
---
The patch was needed for 3.12 stable.--- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)drivers/net/virtio_net.c +1
-1@@ -333,6 +333,7 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) head_skb->dev->stats.rx_length_errors++;return -EINVAL ; } + --rq->num;if (unlikely (len >MERGE_BUFFER_LEN )) {pr_debug ("%s: rx error: merge buffer too long\n" , head_skb->dev->name);@@ -367,7 +368,6 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)skb_add_rx_frag (curr_skb, num_skb_frags, page, offset, len,MERGE_BUFFER_LEN ); } - --rq->num; }return 0 ; }Signature · 1 line
1.8.3.2
Re: [PATCH net 2/3] virtio-net: fix num calculation on frag skb allocation failure
----- 原始邮件 -----
Quoted 10 lines · Jason Wang
Quoted 9 lines
We need decrease the
rq->numafter we can get a buf throughvirtqueue_get_buf()even if we could not allocate frag skb. Otherwise, the refill routine won't be triggered under heavy memory stress since the driver may
still think there's enough room.This bug was introduced by commit
2613af0ed18a11d5c566a81f9a6510b73180660a(virtio_net: migrate mergeable rx buffers to page frag allocators).
Quoted 8 lines
Quoted 5 lines
Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Signed-off-by Jason Wang <[email protected]>So let's wrap
virtqueue_get_bufto make sure we get it right?
Ok. good idea.
Quoted 22 lines
Quoted 22 lines
---
The patch was needed for 3.12 stable.--- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)drivers/net/virtio_net.c +1
-0@@ -333,6 +333,7 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) head_skb->dev->stats.rx_length_errors++;return -EINVAL ; } + --rq->num;if (unlikely (len >MERGE_BUFFER_LEN )) { pr_debug("%s: rx error: merge buffer too long\n",drivers/net/virtio_net.c +0
-0head_skb->dev->name);@@ -367,7 +368,6 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) skb_add_rx_frag(curr_skb, num_skb_frags, page,
Quoted 9 lines
Quoted 8 lines
drivers/net/virtio_net.c +0
-1offset, len, MERGE_BUFFER_LEN); } - --rq->num; }return 0 ;}
--
1.8.3.2
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Michael S. Tsirkin
maintainerRe: [PATCH net 2/3] virtio-net: fix num calculation on frag skb allocation failure
Quoted 19 lines · Jason Wang
----- 原始邮件 -----
Quoted 16 lines · Jason Wang
Quoted 14 lines
We need decrease the
rq->numafter we can get a buf throughvirtqueue_get_buf()even if we could not allocate frag skb. Otherwise, the refill routine won't be triggered under heavy memory stress since the driver may
still think there's enough room.This bug was introduced by commit
2613af0ed18a11d5c566a81f9a6510b73180660a(virtio_net: migrate mergeable rx buffers to page frag allocators).Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Signed-off-by Jason Wang <[email protected]>
Quoted 4 lines
Quoted 2 lines
So let's wrap
virtqueue_get_bufto make sure we get it right?Ok. good idea.
So I did this (below) but the compiler is not smart enough to avoid two branches on data path.
So I'm not sure anymore: with my patch it's pretty clear how the code works.
but I don't think we need to apply this.
drivers/net/virtio_net.c +11 -6
@@ -296,6 +296,14 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,return skb; } +static void *rq_get_buf (struct receive_queue *rq,unsigned int *len) +{ +void *buf =virtqueue_get_buf (rq->vq, len); +if (buf) + rq->num--; +return buf; +} + static struct sk_buff *receive_mergeable(struct net_device *dev, struct receive_queue *rq, void *buf,
@@ -315,7 +323,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,while (--num_buf) {int num_skb_frags; - buf =virtqueue_get_buf (rq->vq, &len); + buf =rq_get_buf (rq, &len);if (unlikely (!buf)) {pr_debug ("%s: rx error: %d buffers out of %d missing\n" , dev->name, num_buf, hdr->mhdr.num_buffers);
@@ -329,7 +337,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } page =virt_to_head_page (buf); - --rq->num; num_skb_frags =skb_shinfo (curr_skb)->nr_frags;if (unlikely (num_skb_frags ==MAX_SKB_FRAGS )) {
@@ -370,7 +377,7 @@ err_buf: dev->stats.rx_dropped++;dev_kfree_skb (head_skb);while (--num_buf) { - buf =virtqueue_get_buf (rq->vq, &len); + buf =rq_get_buf (rq, &len);if (unlikely (!buf)) {pr_debug ("%s: rx error: %d buffers missing\n" , dev->name, num_buf);
@@ -379,7 +386,6 @@ err_buf: } page =virt_to_head_page (buf);put_page (page); - --rq->num; }return NULL ; }
@@ -675,9 +681,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget) again:while (received < budget && - (buf =virtqueue_get_buf (rq->vq, &len)) !=NULL ) { + (buf =rq_get_buf (rq, &len)) !=NULL ) {receive_buf (rq, buf, len); - --rq->num; received++; }
Re: [PATCH net 2/3] virtio-net: fix num calculation on frag skb allocation failure
----- 原始邮件 -----
Quoted 27 lines · Jason Wang
Quoted 21 lines
----- 原始邮件 -----
Quoted 18 lines · Jason Wang
Quoted 16 lines
We need decrease the
rq->numafter we can get a buf throughvirtqueue_get_buf()even if we could not allocate frag skb. Otherwise, the
refill routine won't be triggered under heavy memory stress since the driver may
still think there's enough room.This bug was introduced by commit
2613af0ed18a11d5c566a81f9a6510b73180660a
(virtio_net: migrate mergeable rx buffers to page frag allocators).Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Signed-off-by Jason Wang <[email protected]>Quoted 4 lines
Quoted 2 lines
So let's wrap
virtqueue_get_bufto make sure we get it right?Ok. good idea.
Quoted 9 lines
So I did this (below) but the compiler is not smart enough to avoid two branches on data path.
So I'm not sure anymore: with my patch it's pretty clear how the code works.Signed-off-by Michael S. Tsirkin <[email protected]>but I don't think we need to apply this.
True, another point is we'd better to handle both increasing and decreasing in the same way. We do not increase it in a helper.
Quoted 69 lines
drivers/net/virtio_net.c +8
-0@@ -296,6 +296,14 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq, return skb; } +static void *rq_get_buf (struct receive_queue *rq,unsigned int *len) +{ +void *buf =virtqueue_get_buf (rq->vq, len); +if (buf) + rq->num--; +return buf; +} + static struct sk_buff *receive_mergeable(struct net_device *dev, struct receive_queue *rq,drivers/net/virtio_net.c +1
-1void *buf,@@ -315,7 +323,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, while (--num_buf) {int num_skb_frags; - buf =virtqueue_get_buf (rq->vq, &len); + buf =rq_get_buf (rq, &len);if (unlikely (!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n",drivers/net/virtio_net.c +0
-1dev->name, num_buf, hdr->mhdr.num_buffers);@@ -329,7 +337,6 @@ static struct sk_buff *receive_mergeable(structnet_device *dev, } page =virt_to_head_page (buf); - --rq->num; num_skb_frags =skb_shinfo (curr_skb)->nr_frags;drivers/net/virtio_net.c +2
-5if (unlikely (num_skb_frags ==MAX_SKB_FRAGS )) {@@ -370,7 +377,7 @@ err_buf: dev->stats.rx_dropped++;dev_kfree_skb (head_skb);while (--num_buf) { - buf =virtqueue_get_buf (rq->vq, &len); + buf =rq_get_buf (rq, &len);if (unlikely (!buf)) {pr_debug ("%s: rx error: %d buffers missing\n" , dev->name, num_buf);@@ -379,7 +386,6 @@ err_buf: } page =virt_to_head_page (buf);put_page (page); - --rq->num; }return NULL ; }@@ -675,9 +681,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget) again:while (received < budget && - (buf =virtqueue_get_buf (rq->vq, &len)) !=NULL ) { + (buf =rq_get_buf (rq, &len)) !=NULL ) {receive_buf (rq, buf, len); - --rq->num; received++; } --
Quoted 4 lines
To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 3/3 virtio-net: fix resources leaking when fail to allocate frag skb
In reply to Jason WangWhen we fail to allocate a frag skb, we need put the refcnt of the page and drop the rest of the buffers. Otherwise the page was leaked and driver won't get a correct head buffer after this failure.
This bug was introduced by commit 2613af0ed18a11d5c566a81f9a6510b73180660a (virtio_net: migrate mergeable rx buffers to page frag allocators).
---
The patch was needed for 3.12 stable.
--- drivers/net/virtio_net.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/virtio_net.c +3 -1
@@ -339,9 +339,12 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) head_skb->dev->name); len =MERGE_BUFFER_LEN ; } + page =virt_to_head_page (buf);if (unlikely (num_skb_frags ==MAX_SKB_FRAGS )) {struct sk_buff *nskb =alloc_skb (0 ,GFP_ATOMIC );if (unlikely (!nskb)) { +put_page (page); +drop_mergeable_buffer (rq, num_buf); head_skb->dev->stats.rx_dropped++;return -ENOMEM ; }
@@ -358,7 +361,6 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) head_skb->len += len; head_skb->truesize +=MERGE_BUFFER_LEN ; } - page =virt_to_head_page (buf); offset = buf - (char *)page_address (page);if (skb_can_coalesce (curr_skb, num_skb_frags, page, offset)) {put_page (page);
Signature · 1 line
1.8.3.2
Michael S. Tsirkin
maintainerQuoted 29 lines · Jason Wang
When mergeable buffer were used, we only put the first page buf leave the rest of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this packet.
The bug was introduced by commit
9ab86bbcf8be755256f0a5e994e0b38af6b4d399(virtio_net: Defer skb allocation in receive path).Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Cc Shirley Ma <[email protected]>Signed-off-by Jason Wang <[email protected]>---
This patch was needed for stable--- drivers/net/virtio_net.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)drivers/net/virtio_net.c +1
-0@@ -222,6 +222,17 @@ static void skb_xmit_done(struct virtqueue *vq)netif_wake_subqueue (vi->dev,vq2txq (vq)); } +static void drop_mergeable_buffer (struct receive_queue *rq,int num_buf)
drivers/net/virtio_net.c static void skb_xmit_done(struct virtqueue *vq) · line 235
Quoted 10 lines
drivers/net/virtio_net.c +10
-0+{ +char *buf; +int len; + +while (--num_buf && (buf =virtqueue_get_buf (rq->vq, &len)) !=NULL ) { + --rq->num; +put_page (virt_to_head_page (buf)); + } +} +
This is the same code we have in receive_mergeable anyway. So let's reuse that.
Quoted 20 lines
drivers/net/virtio_net.c +6
-1/* Called from bottom half context */ static struct sk_buff *page_to_skb(struct receive_queue *rq, struct page *page, unsigned int offset,@@ -237,8 +248,13 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,/* copy small packet so we can reuse these pages for small data */ skb =netdev_alloc_skb_ip_align (vi->dev,GOOD_COPY_LEN ); -if (unlikely (!skb)) +if (unlikely (!skb)) { +if (vi->mergeable_rx_bufs) { + hdr = (struct skb_vnet_hdr *)p; +drop_mergeable_buffer (rq, hdr->mhdr.num_buffers); + }return NULL ; + } hdr =skb_vnet_hdr (skb);Signature · 1 line
1.8.3.2
----- 原始邮件 -----
Quoted 31 lines · Jason Wang
Quoted 30 lines
When mergeable buffer were used, we only put the first page buf leave the rest
of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this
packet.The bug was introduced by commit
9ab86bbcf8be755256f0a5e994e0b38af6b4d399(virtio_net: Defer skb allocation in receive path).Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Cc Shirley Ma <[email protected]>Signed-off-by Jason Wang <[email protected]>---
This patch was needed for stable--- drivers/net/virtio_net.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)drivers/net/virtio_net.c +0
-0@@ -222,6 +222,17 @@ static void skb_xmit_done(struct virtqueue *vq)netif_wake_subqueue (vi->dev,vq2txq (vq)); }
Quoted 16 lines
drivers/net/virtio_net.c static void skb_xmit_done(struct virtqueue *vq) · line 235
Quoted 11 lines
drivers/net/virtio_net.c +11
-0+static void drop_mergeable_buffer (struct receive_queue *rq,int num_buf) +{ +char *buf; +int len; + +while (--num_buf && (buf =virtqueue_get_buf (rq->vq, &len)) !=NULL ) { + --rq->num; +put_page (virt_to_head_page (buf)); + } +} +This is the same code we have in
receive_mergeableanyway. So let's reuse that.
receive_mergeable() was called after page_to_skb() was called and there's lots of conditions check there. I'm not sure how could we reuse them.
Quoted 19 lines
Quoted 19 lines
drivers/net/virtio_net.c +6
-1/* Called from bottom half context */ static struct sk_buff *page_to_skb(struct receive_queue *rq, struct page *page, unsigned int offset,@@ -237,8 +248,13 @@ static struct sk_buff *page_to_skb(structreceive_queue *rq,/* copy small packet so we can reuse these pages for small data */ skb =netdev_alloc_skb_ip_align (vi->dev,GOOD_COPY_LEN ); -if (unlikely (!skb)) +if (unlikely (!skb)) { +if (vi->mergeable_rx_bufs) { + hdr = (struct skb_vnet_hdr *)p; +drop_mergeable_buffer (rq, hdr->mhdr.num_buffers); + }return NULL ; + } hdr =skb_vnet_hdr (skb);
Quoted 8 lines
Quoted 2 lines
--
1.8.3.2--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Michael S. Tsirkin
maintainerQuoted 51 lines · Jason Wang
----- 原始邮件 -----
Quoted 31 lines · Jason Wang
Quoted 30 lines
When mergeable buffer were used, we only put the first page buf leave the rest
of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this
packet.The bug was introduced by commit
9ab86bbcf8be755256f0a5e994e0b38af6b4d399(virtio_net: Defer skb allocation in receive path).Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Cc Shirley Ma <[email protected]>Signed-off-by Jason Wang <[email protected]>---
This patch was needed for stable--- drivers/net/virtio_net.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)drivers/net/virtio_net.c +0
-0@@ -222,6 +222,17 @@ static void skb_xmit_done(struct virtqueue *vq)netif_wake_subqueue (vi->dev,vq2txq (vq)); }Quoted 16 lines
drivers/net/virtio_net.c static void skb_xmit_done(struct virtqueue *vq) · line 235
Quoted 11 lines
drivers/net/virtio_net.c +11
-0+static void drop_mergeable_buffer (struct receive_queue *rq,int num_buf) +{ +char *buf; +int len; + +while (--num_buf && (buf =virtqueue_get_buf (rq->vq, &len)) !=NULL ) { + --rq->num; +put_page (virt_to_head_page (buf)); + } +} +This is the same code we have in
receive_mergeableanyway. So let's reuse that.
Quoted 3 lines
receive_mergeable()was called afterpage_to_skb()was called and there's lots of conditions check there. I'm not sure how could we reuse them.
I posted a patch showing how :)
Quoted 27 lines
Quoted 27 lines
Quoted 20 lines
drivers/net/virtio_net.c +6
-2/* Called from bottom half context */ static struct sk_buff *page_to_skb(struct receive_queue *rq, struct page *page, unsigned int offset,@@ -237,8 +248,13 @@ static struct sk_buff *page_to_skb(structreceive_queue *rq,/* copy small packet so we can reuse these pages for small data */ skb =netdev_alloc_skb_ip_align (vi->dev,GOOD_COPY_LEN ); -if (unlikely (!skb)) +if (unlikely (!skb)) { +if (vi->mergeable_rx_bufs) { + hdr = (struct skb_vnet_hdr *)p; +drop_mergeable_buffer (rq, hdr->mhdr.num_buffers); + }return NULL ; + } hdr =skb_vnet_hdr (skb); --Quoted 1 line
1.8.3.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Michael S. Tsirkin
maintainerRFC PATCH 1/1 virtio_net: fix error handling for mergeable buffers
In reply to Jason WangQuoted 8 lines · Jason Wang
When mergeable buffer were used, we only put the first page buf leave the rest of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this packet.
The bug was introduced by commit
9ab86bbcf8be755256f0a5e994e0b38af6b4d399(virtio_net: Defer skb allocation in receive path).
Quoted 6 lines
Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Cc Shirley Ma <[email protected]>Signed-off-by Jason Wang <[email protected]>
Just to clarify my previous comment: it was not about the idea of adding drop_mergeable_buffer - rather, I think that adding knowledge about mergeable buffers into page_to_skb creates an ugly internal API.
Let's move the call to page_to_skb within receive_mergeable instead:
it's also nice that int offset = buf - page_address(page) logic is not spread around like it was.
Also, it's not nice that we ignore length errors when we drop packets because of OOM.
So I came up with the following - it seems to work but I didn't stress test yet.
commit ebffb3fe4335ffe07124e4518e76d6e05844fa18
Author: Michael S. Tsirkin <[email protected]> Date: Wed Nov 20 14:41:29 2013 +0200
virtio_net: fix error handling for mergeable buffers
Eric Dumazet noticed that if we encounter an error when processing a mergeable buffer, we don't dequeue all of the buffers from this packet, the result is almost sure to be loss of networking.
Jason Wang noticed that we also leak a page and that we don't decrement the rq buf count, so we won't repost buffers (a resource leak).
drivers/net/virtio_net.c +53 -33
@@ -296,41 +296,53 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,return skb; } -static int receive_mergeable (struct receive_queue *rq,struct sk_buff *head_skb) +static struct sk_buff *receive_mergeable (struct net_device *dev, +struct receive_queue *rq, +void *buf, +unsigned int len) { -struct skb_vnet_hdr *hdr =skb_vnet_hdr (head_skb); +struct skb_vnet_hdr *hdr = buf; +int num_buf = hdr->mhdr.num_buffers; +struct page *page =virt_to_head_page (buf); +int offset = buf -page_address (page); +struct sk_buff *head_skb =page_to_skb (rq, page, offset, len, +MAX_PACKET_LEN );struct sk_buff *curr_skb = head_skb; -char *buf; -struct page *page; -int num_buf, len, offset; - num_buf = hdr->mhdr.num_buffers; -while (--num_buf) { -int num_skb_frags =skb_shinfo (curr_skb)->nr_frags; +if (unlikely (!curr_skb)) + goto err_skb; + +while (--num_buf) { +int num_skb_frags; + buf =virtqueue_get_buf (rq->vq, &len);if (unlikely (!buf)) { -pr_debug ("%s: rx error: %d buffers missing\n" , - head_skb->dev->name, hdr->mhdr.num_buffers); - head_skb->dev->stats.rx_length_errors++; -return -EINVAL ; +pr_debug ("%s: rx error: %d buffers out of %d missing\n" , + dev->name, num_buf, hdr->mhdr.num_buffers); + dev->stats.rx_length_errors++; + goto err_buf; }if (unlikely (len >MAX_PACKET_LEN )) {pr_debug ("%s: rx error: merge buffer too long\n" , - head_skb->dev->name); + dev->name); len =MAX_PACKET_LEN ; } + + page =virt_to_head_page (buf); + --rq->num; + + num_skb_frags =skb_shinfo (curr_skb)->nr_frags;if (unlikely (num_skb_frags ==MAX_SKB_FRAGS )) {struct sk_buff *nskb =alloc_skb (0 ,GFP_ATOMIC ); -if (unlikely (!nskb)) { - head_skb->dev->stats.rx_dropped++; -return -ENOMEM ; - } + +if (unlikely (!nskb)) + goto err_skb;if (curr_skb == head_skb)skb_shinfo (curr_skb)->frag_list = nskb;else curr_skb->next = nskb; - curr_skb = nskb; head_skb->truesize += nskb->truesize; + curr_skb = nskb; num_skb_frags =0 ; }if (curr_skb != head_skb) {
@@ -338,8 +350,7 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) head_skb->len += len; head_skb->truesize +=MAX_PACKET_LEN ; } - page =virt_to_head_page (buf); - offset = buf - (char *)page_address (page); + offset = buf -page_address (page);if (skb_can_coalesce (curr_skb, num_skb_frags, page, offset)) {put_page (page); skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
@@ -349,9 +360,28 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) offset, len, MAX_PACKET_LEN); } + } + +return head_skb; + +err_skb: +put_page (page); +err_buf: + dev->stats.rx_dropped++; +dev_kfree_skb (head_skb); +while (--num_buf) { + buf =virtqueue_get_buf (rq->vq, &len); +if (unlikely (!buf)) { +pr_debug ("%s: rx error: %d buffers missing\n" , + dev->name, num_buf); + dev->stats.rx_length_errors++; +break ; + } + page =virt_to_head_page (buf); +put_page (page); --rq->num; } -return 0 ; +return NULL ; }static void receive_buf (struct receive_queue *rq,void *buf,unsigned int len)
@@ -380,19 +410,9 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) len -=sizeof (struct virtio_net_hdr );skb_trim (skb, len); }else if (vi->mergeable_rx_bufs) { -struct page *page =virt_to_head_page (buf); - skb =page_to_skb (rq, page, - (char *)buf - (char *)page_address (page), - len,MAX_PACKET_LEN ); -if (unlikely (!skb)) { - dev->stats.rx_dropped++; -put_page (page); + skb =receive_mergeable (dev, rq, buf, len); +if (unlikely (!skb))return ; - } -if (receive_mergeable (rq, skb)) { -dev_kfree_skb (skb); -return ; - } }else { page = buf; skb =page_to_skb (rq, page,0 , len,PAGE_SIZE );
Re: [PATCH RFC] virtio_net: fix error handling for mergeable buffers
----- 原始邮件 -----
Quoted 27 lines · Jason Wang
Quoted 10 lines
When mergeable buffer were used, we only put the first page buf leave the rest
of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this
packet.The bug was introduced by commit
9ab86bbcf8be755256f0a5e994e0b38af6b4d399(virtio_net: Defer skb allocation in receive path).Quoted 6 lines
Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Cc Shirley Ma <[email protected]>Signed-off-by Jason Wang <[email protected]>Just to clarify my previous comment: it was not about the idea of adding
drop_mergeable_buffer- rather, I think that adding knowledge about mergeable buffers intopage_to_skbcreates an ugly internal API.Let's move the call to
page_to_skbwithinreceive_mergeableinstead:
it's also nice that int offset = buf -page_address(page)logic is not spread around like it was.
Quoted 5 lines
Also, it's not nice that we ignore length errors when we drop packets because of OOM.
So I came up with the following - it seems to work but I didn't stress test yet.
I've no objection on this. But I've rather like my small and direct patch to be applied to -net first. It has lower risk and was much more easier to be backported to stable trees. Then we can do the re-factor like this in net-next.
Quoted 164 lines
commit
ebffb3fe4335ffe07124e4518e76d6e05844fa18Author: Michael S. Tsirkin <[email protected]> Date: Wed Nov 20 14:41:29 2013 +0200
virtio_net: fix error handling for mergeable buffersEric Dumazet noticed that if we encounter an error when processing a mergeable buffer, we don't dequeue all of the buffers from this packet, the result is almost sure to be loss of networking.
Jason Wang noticed that we also leak a page and that we don't decrement the rq buf count, so we won't repost buffers (a resource leak).
Cc Rusty Russell <[email protected]>Cc Michael Dalton <[email protected]>Reported-by Eric Dumazet <[email protected]>Reported-by Jason Wang <[email protected]>Signed-off-by Michael S. Tsirkin <[email protected]>drivers/net/virtio_net.c +30
-18@@ -296,41 +296,53 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq, return skb; } -static int receive_mergeable (struct receive_queue *rq,struct sk_buff *head_skb) +static struct sk_buff *receive_mergeable (struct net_device *dev, +struct receive_queue *rq, +void *buf, +unsigned int len) { -struct skb_vnet_hdr *hdr =skb_vnet_hdr (head_skb); +struct skb_vnet_hdr *hdr = buf; +int num_buf = hdr->mhdr.num_buffers; +struct page *page =virt_to_head_page (buf); +int offset = buf -page_address (page); +struct sk_buff *head_skb =page_to_skb (rq, page, offset, len, +MAX_PACKET_LEN );struct sk_buff *curr_skb = head_skb; -char *buf; -struct page *page; -int num_buf, len, offset; - num_buf = hdr->mhdr.num_buffers; -while (--num_buf) { -int num_skb_frags =skb_shinfo (curr_skb)->nr_frags; +if (unlikely (!curr_skb)) + goto err_skb; + +while (--num_buf) { +int num_skb_frags; + buf =virtqueue_get_buf (rq->vq, &len);if (unlikely (!buf)) { -pr_debug ("%s: rx error: %d buffers missing\n" , - head_skb->dev->name, hdr->mhdr.num_buffers); - head_skb->dev->stats.rx_length_errors++; -return -EINVAL ; +pr_debug ("%s: rx error: %d buffers out of %d missing\n" , + dev->name, num_buf, hdr->mhdr.num_buffers); + dev->stats.rx_length_errors++; + goto err_buf; }if (unlikely (len >MAX_PACKET_LEN )) {pr_debug ("%s: rx error: merge buffer too long\n" , - head_skb->dev->name); + dev->name); len =MAX_PACKET_LEN ; } + + page =virt_to_head_page (buf); + --rq->num; + + num_skb_frags =skb_shinfo (curr_skb)->nr_frags;if (unlikely (num_skb_frags ==MAX_SKB_FRAGS )) {struct sk_buff *nskb =alloc_skb (0 ,GFP_ATOMIC ); -if (unlikely (!nskb)) { - head_skb->dev->stats.rx_dropped++; -return -ENOMEM ; - } + +if (unlikely (!nskb)) + goto err_skb;if (curr_skb == head_skb)skb_shinfo (curr_skb)->frag_list = nskb;else curr_skb->next = nskb; - curr_skb = nskb; head_skb->truesize += nskb->truesize; + curr_skb = nskb; num_skb_frags =0 ;drivers/net/virtio_net.c +1
-2}if (curr_skb != head_skb) {@@ -338,8 +350,7 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) head_skb->len += len; head_skb->truesize +=MAX_PACKET_LEN ; } - page =virt_to_head_page (buf); - offset = buf - (char *)page_address (page); + offset = buf -page_address (page);if (skb_can_coalesce (curr_skb, num_skb_frags, page, offset)) {put_page (page);drivers/net/virtio_net.c +20
-1skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,@@ -349,9 +360,28 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb) offset, len, MAX_PACKET_LEN); } + } + +return head_skb; + +err_skb: +put_page (page); +err_buf: + dev->stats.rx_dropped++; +dev_kfree_skb (head_skb); +while (--num_buf) { + buf =virtqueue_get_buf (rq->vq, &len); +if (unlikely (!buf)) { +pr_debug ("%s: rx error: %d buffers missing\n" , + dev->name, num_buf); + dev->stats.rx_length_errors++; +break ; + } + page =virt_to_head_page (buf); +put_page (page); --rq->num; } -return 0 ; +return NULL ; }static void
receive_buf(struct receive_queue *rq, void *buf, unsigned int len)drivers/net/virtio_net.c +2
-12@@ -380,19 +410,9 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) len -= sizeof(struct virtio_net_hdr);skb_trim (skb, len); }else if (vi->mergeable_rx_bufs) { -struct page *page =virt_to_head_page (buf); - skb =page_to_skb (rq, page, - (char *)buf - (char *)page_address (page), - len,MAX_PACKET_LEN ); -if (unlikely (!skb)) { - dev->stats.rx_dropped++; -put_page (page); + skb =receive_mergeable (dev, rq, buf, len); +if (unlikely (!skb))return ; - } -if (receive_mergeable (rq, skb)) { -dev_kfree_skb (skb); -return ; - } }else { page = buf;
Quoted 6 lines
skb =
page_to_skb(rq, page, 0, len, PAGE_SIZE);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Michael S. Tsirkin
maintainerRe: [PATCH RFC] virtio_net: fix error handling for mergeable buffers
Quoted 33 lines · Jason Wang
----- 原始邮件 -----
Quoted 30 lines · Jason Wang
Quoted 10 lines
When mergeable buffer were used, we only put the first page buf leave the rest
of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this
packet.The bug was introduced by commit
9ab86bbcf8be755256f0a5e994e0b38af6b4d399(virtio_net: Defer skb allocation in receive path).Quoted 6 lines
Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Cc Shirley Ma <[email protected]>Signed-off-by Jason Wang <[email protected]>Just to clarify my previous comment: it was not about the idea of adding
drop_mergeable_buffer- rather, I think that adding knowledge about mergeable buffers intopage_to_skbcreates an ugly internal API.Let's move the call to
page_to_skbwithinreceive_mergeableinstead:
it's also nice that int offset = buf -page_address(page)logic is not spread around like it was.Also, it's not nice that we ignore length errors when we drop packets because of OOM.
Quoted 7 lines
Quoted 2 lines
So I came up with the following - it seems to work but I didn't stress test yet.
I've no objection on this. But I've rather like my small and direct patch to be applied to -net first. It has lower risk and was much more easier to be backported to stable trees. Then we can do the re-factor like this in net-next.
It makes the interfaces too messy. We are not in code freeze in -net - only feature freeze, so no reason to make code like spagetty, and it's only 25 lines changed as compared to 40.
It's not a huge refactoring.
It's just as easy to backport my patch too. You just drop the goto in the new code path we added.
Let me show you (untested) - your patch is not smaller.
commit 9b442fe970d5c71311d4314edef26ee2eb16e7fb
Author: Michael S. Tsirkin <[email protected]> Date: Wed Nov 20 12:44:14 2013 +0200
virtio_net: fix resource leak on alloc failure
virtio net got confused, started dropping packets.
drivers/net/virtio_net.c +47 -19
@@ -297,13 +297,22 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,return skb; } -static int receive_mergeable (struct receive_queue *rq,struct sk_buff *skb) +static struct sk_buff *receive_mergeable (struct net_device *dev, +struct receive_queue *rq, +struct page *page, +unsigned int len) { -struct skb_vnet_hdr *hdr =skb_vnet_hdr (skb); -struct page *page; -int num_buf, i, len; +struct skb_vnet_hdr *hdr =page_address (buf); +int num_buf = hdr->mhdr.num_buffers; +struct sk_buff *skb =page_to_skb (rq, page, len); +int i; + + skb =page_to_skb (rq, page, len); + +if (unlikely (!skb)) + goto err_skb; + - num_buf = hdr->mhdr.num_buffers;while (--num_buf) { i =skb_shinfo (skb)->nr_frags;if (i >=MAX_SKB_FRAGS ) {
@@ -313,10 +322,10 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb) } page =virtqueue_get_buf (rq->vq, &len);if (!page) { -pr_debug ("%s: rx error: %d buffers missing\n" , - skb->dev->name, hdr->mhdr.num_buffers); - skb->dev->stats.rx_length_errors++; -return -EINVAL ; +pr_debug ("%s: rx error: %d buffers %d missing\n" , + dev->name, hdr->mhdr.num_buffers, num_buf); + dev->stats.rx_length_errors++; + goto err_buf; }if (len >PAGE_SIZE )
@@ -326,7 +335,25 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb) --rq->num; } -return 0 ; +return skb; +err_skb: +put_page (page); +err_buf: + dev->stats.rx_dropped++; +dev_kfree_skb (head_skb); +while (--num_buf) { + buf =virtqueue_get_buf (rq->vq, &len); +if (unlikely (!buf)) { +pr_debug ("%s: rx error: %d buffers missing\n" , + dev->name, num_buf); + dev->stats.rx_length_errors++; +break ; + } + page = buf; +give_pages (rq, page); + --rq->num; + } +return NULL ; }static void receive_buf (struct receive_queue *rq,void *buf,unsigned int len)
@@ -354,17 +381,18 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)skb_trim (skb, len); }else { page = buf; - skb =page_to_skb (rq, page, len); -if (unlikely (!skb)) { - dev->stats.rx_dropped++; -give_pages (rq, page); -return ; - } -if (vi->mergeable_rx_bufs) -if (receive_mergeable (rq, skb)) { -dev_kfree_skb (skb); +if (vi->mergeable_rx_bufs) { + skb =receive_mergeable (dev, rq, page, len); +if (unlikely (!skb)) +return ; + }else { + skb =page_to_skb (rq, page, len); +if (unlikely (!skb)) { + dev->stats.rx_dropped++; +give_pages (rq, page);return ; } + } } hdr =skb_vnet_hdr (skb);
Re: [PATCH RFC] virtio_net: fix error handling for mergeable buffers
Quoted 32 lines · Michael S. Tsirkin
Quoted 31 lines · Jason Wang
----- 原始邮件 -----
Quoted 29 lines · Jason Wang
Quoted 10 lines
When mergeable buffer were used, we only put the first page buf leave the rest
of buffers in the virt queue. This will cause the driver could not get the correct head buffer any more. Fix this by dropping the rest of buffers for this
packet.The bug was introduced by commit
9ab86bbcf8be755256f0a5e994e0b38af6b4d399(virtio_net: Defer skb allocation in receive path).Quoted 6 lines
Cc Rusty Russell <[email protected]>Cc Michael S. Tsirkin <[email protected]>Cc Michael Dalton <[email protected]>Cc Eric Dumazet <[email protected]>Cc Shirley Ma <[email protected]>Signed-off-by Jason Wang <[email protected]>Just to clarify my previous comment: it was not about the idea of adding
drop_mergeable_buffer- rather, I think that adding knowledge about mergeable buffers intopage_to_skbcreates an ugly internal API.Let's move the call to
page_to_skbwithinreceive_mergeableinstead:
it's also nice that int offset = buf -page_address(page)logic is not spread around like it was.Also, it's not nice that we ignore length errors when we drop packets because of OOM.
Quoted 7 lines
Quoted 6 lines
Quoted 2 lines
So I came up with the following - it seems to work but I didn't stress test yet.
I've no objection on this. But I've rather like my small and direct patch to be applied to -net first. It has lower risk and was much more easier to be backported to stable trees. Then we can do the re-factor like this in net-next.
It makes the interfaces too messy.
Do you mean receive_mergeable() should call page_to_skb()? It has been there several years. And even with your changes, for big and small packets, page_to_skb() were still called directly receive_buf() and the error handling were done there.
Quoted 4 lines
We are not in code freeze in -net -
only feature freeze, so no reason to make code like spagetty, and it's only 25 lines changed as compared to 40. It's not a huge refactoring.
The problem is your patch mixes several bugs fixing with re-factoring, only one of the bug fixing was really needed for stable. At least we should make incremental patches on this.
Quoted 3 lines
It's just as easy to backport my patch too. You just drop the goto in the new code path we added.
It may not be so easy for the people who are not familiar with virtio-net and the s/skb->dev/dev/g changes looks irrelevant here.
Quoted 108 lines
Let me show you (untested) - your patch is not smaller.
Signed-off-by Michael S. Tsirkin <[email protected]>commit
9b442fe970d5c71311d4314edef26ee2eb16e7fbAuthor: Michael S. Tsirkin <[email protected]> Date: Wed Nov 20 12:44:14 2013 +0200
virtio_net: fix resource leak on alloc failurevirtio net got confused, started dropping packets.
Signed-off-by Michael S. Tsirkin <[email protected]>drivers/net/virtio_net.c +42
-19@@ -297,13 +297,22 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,return skb; } -static int receive_mergeable (struct receive_queue *rq,struct sk_buff *skb) +static struct sk_buff *receive_mergeable (struct net_device *dev, +struct receive_queue *rq, +struct page *page, +unsigned int len) { -struct skb_vnet_hdr *hdr =skb_vnet_hdr (skb); -struct page *page; -int num_buf, i, len; +struct skb_vnet_hdr *hdr =page_address (buf); +int num_buf = hdr->mhdr.num_buffers; +struct sk_buff *skb =page_to_skb (rq, page, len); +int i; + + skb =page_to_skb (rq, page, len); + +if (unlikely (!skb)) + goto err_skb; + - num_buf = hdr->mhdr.num_buffers;while (--num_buf) { i =skb_shinfo (skb)->nr_frags;if (i >=MAX_SKB_FRAGS ) {@@ -313,10 +322,10 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb) } page =virtqueue_get_buf (rq->vq, &len);if (!page) { -pr_debug ("%s: rx error: %d buffers missing\n" , - skb->dev->name, hdr->mhdr.num_buffers); - skb->dev->stats.rx_length_errors++; -return -EINVAL ; +pr_debug ("%s: rx error: %d buffers %d missing\n" , + dev->name, hdr->mhdr.num_buffers, num_buf); + dev->stats.rx_length_errors++; + goto err_buf; }if (len >PAGE_SIZE )@@ -326,7 +335,25 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb) --rq->num; } -return 0 ; +return skb; +err_skb: +put_page (page); +err_buf: + dev->stats.rx_dropped++; +dev_kfree_skb (head_skb); +while (--num_buf) { + buf =virtqueue_get_buf (rq->vq, &len); +if (unlikely (!buf)) { +pr_debug ("%s: rx error: %d buffers missing\n" , + dev->name, num_buf); + dev->stats.rx_length_errors++; +break ; + } + page = buf; +give_pages (rq, page); + --rq->num; + } +return NULL ; }static void receive_buf (struct receive_queue *rq,void *buf,unsigned int len)@@ -354,17 +381,18 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)skb_trim (skb, len); }else { page = buf; - skb =page_to_skb (rq, page, len); -if (unlikely (!skb)) { - dev->stats.rx_dropped++; -give_pages (rq, page); -return ; - } -if (vi->mergeable_rx_bufs) -if (receive_mergeable (rq, skb)) { -dev_kfree_skb (skb); +if (vi->mergeable_rx_bufs) { + skb =receive_mergeable (dev, rq, page, len); +if (unlikely (!skb)) +return ; + }else {
drivers/net/virtio_net.c static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) · line 398
Quoted 10 lines
drivers/net/virtio_net.c +5
-0+ skb =page_to_skb (rq, page, len); +if (unlikely (!skb)) { + dev->stats.rx_dropped++; +give_pages (rq, page);return ; } + } } hdr =skb_vnet_hdr (skb);
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization