virtio_net: Do not pull payload in skb->head
Xuan Zhuo reported that commit 3226b158e67c ("net: avoid 32 x truesize
under-estimation for tiny skbs") brought a ~10% performance drop.
The reason for the performance drop was that GRO was forced
to chain sk_buff (using skb_shinfo(skb)->frag_list), which
uses more memory but also cause packet consumers to go over
a lot of overhead handling all the tiny skbs.
It turns out that virtio_net page_to_skb() has a wrong strategy :
It allocates skbs with GOOD_COPY_LEN (128) bytes in skb->head, then
copies 128 bytes from the page, before feeding the packet to GRO stack.
This was suboptimal before commit 3226b158e67c ("net: avoid 32 x truesize
under-estimation for tiny skbs") because GRO was using 2 frags per MSS,
meaning we were not packing MSS with 100% efficiency.
Fix is to pull only the ethernet header in page_to_skb()
Then, we change virtio_net_hdr_to_skb() to pull the missing
headers, instead of assuming they were already pulled by callers.
This fixes the performance regression, but could also allow virtio_net
to accept packets with more than 128bytes of headers.
Many thanks to Xuan Zhuo for his report, and his tests/help.
RELEASE_NOTE=avoid 32 x truesize under-estimation for tiny skbs
Fixes: 3226b158e67c ("net: avoid 32 x truesize under-estimation for tiny skbs")
Reported-by: Xuan Zhuo <email@example.com>
Co-Developed-by: Xuan Zhuo <firstname.lastname@example.org>
Signed-off-by: Xuan Zhuo <email@example.com>
Signed-off-by: Eric Dumazet <firstname.lastname@example.org>
Cc: "Michael S. Tsirkin" <email@example.com>
Cc: Jason Wang <firstname.lastname@example.org>
Acked-by: Jason Wang <email@example.com>
Signed-off-by: David S. Miller <firstname.lastname@example.org>
Tested-by: Cusky Presubmit Bot <email@example.com>
Main-Branch-Verified: Cusky Presubmit Bot <firstname.lastname@example.org>
Reviewed-by: Roy Yang <email@example.com>
(cherry picked from commit 9d617b9c34f5ddea288d4eb9ddf3706b04a00713)
2 files changed