Commit 6bd8614f authored by Frederik Deweerdt's avatar Frederik Deweerdt Committed by Jakub Kicinski
Browse files

splice: do not checksum AF_UNIX sockets 



When `skb_splice_from_iter` was introduced, it inadvertently added
checksumming for AF_UNIX sockets. This resulted in significant
slowdowns, for example when using sendfile over unix sockets.

Using the test code in [1] in my test setup (2G single core qemu),
the client receives a 1000M file in:
- without the patch: 1482ms (+/- 36ms)
- with the patch: 652.5ms (+/- 22.9ms)

This commit addresses the issue by marking checksumming as unnecessary in
`unix_stream_sendmsg`

Cc: stable@vger.kernel.org
Signed-off-by: default avatarFrederik Deweerdt <deweerdt.lkml@gmail.com>
Fixes: 2e910b95 ("net: Add a function to splice pages into an skbuff for MSG_SPLICE_PAGES")
Reviewed-by: default avatarKuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarJoe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/Z1fMaHkRf8cfubuE@xiberoa


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 3b58b53a

net/unix/af_unix.c

+1 −0
Original line number Diff line number Diff line
@@ -2313,6 +2313,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, 
		fds_sent = true;



		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {

			skb->ip_summed = CHECKSUM_UNNECESSARY;

			err = skb_splice_from_iter(skb, &msg->msg_iter, size,

						   sk->sk_allocation);

			if (err < 0) {