| Message ID | 20210412083959.037627043@linuxfoundation.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | None | expand |
On Mon, Apr 12, 2021 at 10:40:34AM +0200, Greg Kroah-Hartman wrote: > From: Eric Dumazet <edumazet@google.com> > > [ Upstream commit 0f6925b3e8da0dbbb52447ca8a8b42b371aac7db ] > > 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. > > Fixes: 3226b158e67c ("net: avoid 32 x truesize under-estimation for tiny skbs") > Reported-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> > Link: https://www.spinics.net/lists/netdev/msg731397.html > Co-Developed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> > Signed-off-by: Eric Dumazet <edumazet@google.com> > Cc: "Michael S. Tsirkin" <mst@redhat.com> > Cc: Jason Wang <jasowang@redhat.com> > Cc: virtualization@lists.linux-foundation.org > Acked-by: Jason Wang <jasowang@redhat.com> > Signed-off-by: David S. Miller <davem@davemloft.net> > Signed-off-by: Sasha Levin <sashal@kernel.org> Note that an issue related to this patch was recently reported. It's quite possible that the root cause is a bug elsewhere in the kernel, but it probably makes sense to defer the backport until we know more ... > --- > drivers/net/virtio_net.c | 10 +++++++--- > include/linux/virtio_net.h | 14 +++++++++----- > 2 files changed, 16 insertions(+), 8 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index 0b1c6a8906b9..06ddf009f833 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -413,9 +413,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, > offset += hdr_padded_len; > p += hdr_padded_len; > > - copy = len; > - if (copy > skb_tailroom(skb)) > - copy = skb_tailroom(skb); > + /* Copy all frame if it fits skb->head, otherwise > + * we let virtio_net_hdr_to_skb() and GRO pull headers as needed. > + */ > + if (len <= skb_tailroom(skb)) > + copy = len; > + else > + copy = ETH_HLEN + metasize; > skb_put_data(skb, p, copy); > > if (metasize) { > diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h > index a1829139ff4a..8f48264f5dab 100644 > --- a/include/linux/virtio_net.h > +++ b/include/linux/virtio_net.h > @@ -65,14 +65,18 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, > skb_reset_mac_header(skb); > > if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { > - u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start); > - u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); > + u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); > + u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); > + u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); > + > + if (!pskb_may_pull(skb, needed)) > + return -EINVAL; > > if (!skb_partial_csum_set(skb, start, off)) > return -EINVAL; > > p_off = skb_transport_offset(skb) + thlen; > - if (p_off > skb_headlen(skb)) > + if (!pskb_may_pull(skb, p_off)) > return -EINVAL; > } else { > /* gso packets without NEEDS_CSUM do not set transport_offset. > @@ -102,14 +106,14 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, > } > > p_off = keys.control.thoff + thlen; > - if (p_off > skb_headlen(skb) || > + if (!pskb_may_pull(skb, p_off) || > keys.basic.ip_proto != ip_proto) > return -EINVAL; > > skb_set_transport_header(skb, keys.control.thoff); > } else if (gso_type) { > p_off = thlen; > - if (p_off > skb_headlen(skb)) > + if (!pskb_may_pull(skb, p_off)) > return -EINVAL; > } > } > -- > 2.30.2 > >
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0b1c6a8906b9..06ddf009f833 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -413,9 +413,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, offset += hdr_padded_len; p += hdr_padded_len; - copy = len; - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); + /* Copy all frame if it fits skb->head, otherwise + * we let virtio_net_hdr_to_skb() and GRO pull headers as needed. + */ + if (len <= skb_tailroom(skb)) + copy = len; + else + copy = ETH_HLEN + metasize; skb_put_data(skb, p, copy); if (metasize) { diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index a1829139ff4a..8f48264f5dab 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -65,14 +65,18 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, skb_reset_mac_header(skb); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { - u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start); - u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); + u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); + u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); + u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); + + if (!pskb_may_pull(skb, needed)) + return -EINVAL; if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; p_off = skb_transport_offset(skb) + thlen; - if (p_off > skb_headlen(skb)) + if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. @@ -102,14 +106,14 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, } p_off = keys.control.thoff + thlen; - if (p_off > skb_headlen(skb) || + if (!pskb_may_pull(skb, p_off) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { p_off = thlen; - if (p_off > skb_headlen(skb)) + if (!pskb_may_pull(skb, p_off)) return -EINVAL; } }