Eric Dumazet
2021-Apr-20 20:01 UTC
[PATCH net-next] virtio-net: restrict build_skb() use to some arches
From: Eric Dumazet <edumazet at google.com>
build_skb() is supposed to be followed by
skb_reserve(skb, NET_IP_ALIGN), so that IP headers are word-aligned.
(Best practice is to reserve NET_IP_ALIGN+NET_SKB_PAD, but the NET_SKB_PAD
part is only a performance optimization if tunnel encaps are added.)
Unfortunately virtio_net has not provisioned this reserve.
We can only use build_skb() for arches where NET_IP_ALIGN == 0
We might refine this later, with enough testing.
Fixes: fb32856b16ad ("virtio-net: page_to_skb() use build_skb when
there's sufficient tailroom")
Signed-off-by: Eric Dumazet <edumazet at google.com>
Reported-by: Guenter Roeck <linux at roeck-us.net>
Cc: Xuan Zhuo <xuanzhuo at linux.alibaba.com>
Cc: Jason Wang <jasowang at redhat.com>
Cc: "Michael S. Tsirkin" <mst at redhat.com>
Cc: virtualization at lists.linux-foundation.org
---
drivers/net/virtio_net.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index
2e28c04aa6351d2b4016f7d277ce104c4970069d..74d2d49264f3f3b7039be70331d4a44c53b8cc28
100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -416,7 +416,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- if (len > GOOD_COPY_LEN && tailroom >= shinfo_size) {
+ if (!NET_IP_ALIGN && len > GOOD_COPY_LEN && tailroom >=
shinfo_size) {
skb = build_skb(p, truesize);
if (unlikely(!skb))
return NULL;
--
2.31.1.368.gbe11c130af-goog
Jason Wang
2021-Apr-21 02:18 UTC
[PATCH net-next] virtio-net: restrict build_skb() use to some arches
? 2021/4/21 ??4:01, Eric Dumazet ??:> From: Eric Dumazet <edumazet at google.com> > > build_skb() is supposed to be followed by > skb_reserve(skb, NET_IP_ALIGN), so that IP headers are word-aligned. > (Best practice is to reserve NET_IP_ALIGN+NET_SKB_PAD, but the NET_SKB_PAD > part is only a performance optimization if tunnel encaps are added.) > > Unfortunately virtio_net has not provisioned this reserve. > We can only use build_skb() for arches where NET_IP_ALIGN == 0 > > We might refine this later, with enough testing. > > Fixes: fb32856b16ad ("virtio-net: page_to_skb() use build_skb when there's sufficient tailroom") > Signed-off-by: Eric Dumazet <edumazet at google.com> > Reported-by: Guenter Roeck <linux at roeck-us.net> > Cc: Xuan Zhuo <xuanzhuo at linux.alibaba.com> > Cc: Jason Wang <jasowang at redhat.com> > Cc: "Michael S. Tsirkin" <mst at redhat.com> > Cc: virtualization at lists.linux-foundation.orgAcked-by: Jason Wang <jasowang at redhat.com>> --- > drivers/net/virtio_net.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index 2e28c04aa6351d2b4016f7d277ce104c4970069d..74d2d49264f3f3b7039be70331d4a44c53b8cc28 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -416,7 +416,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, > > shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); > > - if (len > GOOD_COPY_LEN && tailroom >= shinfo_size) { > + if (!NET_IP_ALIGN && len > GOOD_COPY_LEN && tailroom >= shinfo_size) { > skb = build_skb(p, truesize); > if (unlikely(!skb)) > return NULL;