similar to: [PATCH] virtio-net: free bufs correctly on invalid packet length

When a packet with invalid length arrives, ensure that the packet is freed correctly if mergeable packet buffers and big packets (GUEST_TSO4) are both enabled. Signed-off-by: Michael Dalton <mwdalton at google.com> --- drivers/net/virtio_net.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 916241d..6a4665c

When a packet with invalid length arrives, ensure that the packet is freed correctly if mergeable packet buffers and big packets (GUEST_TSO4) are both enabled. Signed-off-by: Michael Dalton <mwdalton at google.com> --- drivers/net/virtio_net.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 916241d..6a4665c

Hello. On 12/05/2013 11:16 PM, Michael Dalton wrote: > When a packet with invalid length arrives, ensure that the packet > is freed correctly if mergeable packet buffers and big packets > (GUEST_TSO4) are both enabled. Looks like a similar patch have been posted by Andrey Vagin today. You also forgot to sign off the patch, so it can't be applied anyway. > --- >

On 12/05/2013 10:36 PM, Andrey Vagin wrote: > free_unused_bufs must check vi->mergeable_rx_bufs before > vi->big_packets, because we use this sequence in other places. > Otherwise we allocate buffer of one type, then free it as another > type. > > general protection fault: 0000 [#1] SMP > Dumping ftrace buffer: > (ftrace buffer empty) > Modules linked in:

On 12/05/2013 10:36 PM, Andrey Vagin wrote: > free_unused_bufs must check vi->mergeable_rx_bufs before > vi->big_packets, because we use this sequence in other places. > Otherwise we allocate buffer of one type, then free it as another > type. > > general protection fault: 0000 [#1] SMP > Dumping ftrace buffer: > (ftrace buffer empty) > Modules linked in:

They can be easy to reproduce, if you try to unload virtio-net Andrey Vagin (2): virtio-net: determine type of bufs correctly virtio: delete napi objects from netdev before releasing memory drivers/net/virtio_net.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst at redhat.com>

They can be easy to reproduce, if you try to unload virtio-net Andrey Vagin (2): virtio-net: determine type of bufs correctly virtio: delete napi objects from netdev before releasing memory drivers/net/virtio_net.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst at redhat.com>

On Thu, Dec 05, 2013 at 06:36:20PM +0400, Andrey Vagin wrote: > free_unused_bufs must check vi->mergeable_rx_bufs before > vi->big_packets, because we use this sequence in other places. > Otherwise we allocate buffer of one type, then free it as another > type. > > general protection fault: 0000 [#1] SMP > Dumping ftrace buffer: > (ftrace buffer empty) >

free_unused_bufs must check vi->mergeable_rx_bufs before vi->big_packets, because we use this sequence in other places. Otherwise we allocate buffer of one type, then free it as another type. general protection fault: 0000 [#1] SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: ip6table_filter ip6_tables iptable_filter ip_tables pcspkr virtio_balloon virtio_net(-)

virtnet_rq_free_unused_buf() helper function to free the buffer already exists. Avoid code duplication by reusing existing function. Signed-off-by: Parav Pandit <parav at nvidia.com> --- drivers/net/virtio_net.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d45e140b6852..c1faaf11fbcd 100644 ---

The virtio_net driver's mergeable receive buffer allocator uses 4KB packet buffers. For MTU-sized traffic, SKB truesize is > 4KB but only ~1500 bytes of the buffer is used to store packet data, reducing the effective TCP window size substantially. This patch addresses the performance concerns with mergeable receive buffers by allocating MTU-sized packet buffers using page frag allocators.

The virtio_net driver's mergeable receive buffer allocator uses 4KB packet buffers. For MTU-sized traffic, SKB truesize is > 4KB but only ~1500 bytes of the buffer is used to store packet data, reducing the effective TCP window size substantially. This patch addresses the performance concerns with mergeable receive buffers by allocating MTU-sized packet buffers using page frag allocators.

receive mergeable now handles errors internally. Do same for big and small packet paths, otherwise the logic is too hard to follow. Cc: Jason Wang <jasowang at redhat.com> Cc: David S. Miller <davem at davemloft.net> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> (cherry picked from commit f121159d72091f25afb22007c833e60a6845e912) --- drivers/net/virtio_net.c | 56

receive mergeable now handles errors internally. Do same for big and small packet paths, otherwise the logic is too hard to follow. Cc: Jason Wang <jasowang at redhat.com> Cc: David S. Miller <davem at davemloft.net> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> (cherry picked from commit f121159d72091f25afb22007c833e60a6845e912) --- drivers/net/virtio_net.c | 56

receive mergeable now handles errors internally. Do same for big and small packet paths, otherwise the logic is too hard to follow. Cc: Jason Wang <jasowang at redhat.com> Cc: David S. Miller <davem at davemloft.net> Acked-by: Michael Dalton <mwdalton at google.com> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> (cherry picked from commit

receive mergeable now handles errors internally. Do same for big and small packet paths, otherwise the logic is too hard to follow. Cc: Jason Wang <jasowang at redhat.com> Cc: David S. Miller <davem at davemloft.net> Acked-by: Michael Dalton <mwdalton at google.com> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> (cherry picked from commit

Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag allocators") changed the mergeable receive buffer size from PAGE_SIZE to MTU-size, introducing a single-stream regression for benchmarks with large average packet size. There is no single optimal buffer size for all workloads. For workloads with packet size <= MTU bytes, MTU + virtio-net header-sized buffers

On Mon, Oct 28, 2013 at 10:44 PM, Michael Dalton <mwdalton at google.com> wrote: > The virtio_net driver's mergeable receive buffer allocator > uses 4KB packet buffers. For MTU-sized traffic, SKB truesize > is > 4KB but only ~1500 bytes of the buffer is used to store > packet data, reducing the effective TCP window size > substantially. This patch addresses the

Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag allocators") changed the mergeable receive buffer size from PAGE_SIZE to MTU-size, introducing a single-stream regression for benchmarks with large average packet size. There is no single optimal buffer size for all workloads. For workloads with packet size <= MTU bytes, MTU + virtio-net header-sized buffers

skb_page_frag_refill currently permits only order-0 page allocs unless GFP_WAIT is used. Change skb_page_frag_refill to attempt higher-order page allocations whether or not GFP_WAIT is used. If memory cannot be allocated, the allocator will fall back to successively smaller page allocs (down to order-0 page allocs). This change brings skb_page_frag_refill in line with the existing page allocation