summaryrefslogtreecommitdiff
path: root/drivers/net/tun.c
diff options
context:
space:
mode:
authorAlexis Bauvin <abauvin@scaleway.com>2019-07-23 16:23:01 +0200
committerDavid S. Miller <davem@davemloft.net>2019-07-25 11:38:32 -0700
commit4b663366246be1d1d4b1b8b01245b2e88ad9e706 (patch)
tree181c9e87504e61761f8c58d759c9468e962303f7 /drivers/net/tun.c
parent16b2084a8afa1432d14ba72b7c97d7908e178178 (diff)
downloadlwn-4b663366246be1d1d4b1b8b01245b2e88ad9e706.tar.gz
lwn-4b663366246be1d1d4b1b8b01245b2e88ad9e706.zip
tun: mark small packets as owned by the tap sock
- v1 -> v2: Move skb_set_owner_w to __tun_build_skb to reduce patch size Small packets going out of a tap device go through an optimized code path that uses build_skb() rather than sock_alloc_send_pskb(). The latter calls skb_set_owner_w(), but the small packet code path does not. The net effect is that small packets are not owned by the userland application's socket (e.g. QEMU), while large packets are. This can be seen with a TCP session, where packets are not owned when the window size is small enough (around PAGE_SIZE), while they are once the window grows (note that this requires the host to support virtio tso for the guest to offload segmentation). All this leads to inconsistent behaviour in the kernel, especially on netfilter modules that uses sk->socket (e.g. xt_owner). Fixes: 66ccbc9c87c2 ("tap: use build_skb() for small packet") Signed-off-by: Alexis Bauvin <abauvin@scaleway.com> Acked-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/tun.c')
-rw-r--r--drivers/net/tun.c9
1 files changed, 6 insertions, 3 deletions
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 3d443597bd04..db16d7a13e00 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1599,7 +1599,8 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile,
return true;
}
-static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf,
+static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
+ struct page_frag *alloc_frag, char *buf,
int buflen, int len, int pad)
{
struct sk_buff *skb = build_skb(buf, buflen);
@@ -1609,6 +1610,7 @@ static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf,
skb_reserve(skb, pad);
skb_put(skb, len);
+ skb_set_owner_w(skb, tfile->socket.sk);
get_page(alloc_frag->page);
alloc_frag->offset += buflen;
@@ -1686,7 +1688,8 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
*/
if (hdr->gso_type || !xdp_prog) {
*skb_xdp = 1;
- return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
+ return __tun_build_skb(tfile, alloc_frag, buf, buflen, len,
+ pad);
}
*skb_xdp = 0;
@@ -1723,7 +1726,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
rcu_read_unlock();
local_bh_enable();
- return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
+ return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
err_xdp:
put_page(alloc_frag->page);