summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
authorArjun Roy <arjunroy@google.com>2020-02-15 02:30:50 +0300
committerDavid S. Miller <davem@davemloft.net>2020-02-17 06:25:02 +0300
commit33946518d493cdf10aedb4a483f1aa41948a3dab (patch)
treeac31781461616de8689ed71d153a29ae8b8523ee /net/ipv4/tcp.c
parentc8856c051454909e5059df4e81c77b9c366c5515 (diff)
downloadlinux-33946518d493cdf10aedb4a483f1aa41948a3dab.tar.xz
tcp-zerocopy: Return sk_err (if set) along with tcp receive zerocopy.
This patchset is intended to reduce the number of extra system calls imposed by TCP receive zerocopy. For ping-pong RPC style workloads, this patchset has demonstrated a system call reduction of about 30% when coupled with userspace changes. For applications using epoll, returning sk_err along with the result of tcp receive zerocopy could remove the need to call recvmsg()=-EAGAIN after a spurious wakeup. Consider a multi-threaded application using epoll. A thread may awaken with EPOLLIN but another thread may already be reading. The spuriously-awoken thread does not necessarily know that another thread 'won'; rather, it may be possible that it was woken up due to the presence of an error if there is no data. A zerocopy read receiving 0 bytes thus would need to be followed up by recvmsg to be sure. Instead, we return sk_err directly with zerocopy, so the application can avoid this extra system call. Signed-off-by: Arjun Roy <arjunroy@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c8
1 files changed, 7 insertions, 1 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a697f1455f8d..1b685485a5b5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3676,14 +3676,20 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
lock_sock(sk);
err = tcp_zerocopy_receive(sk, &zc);
release_sock(sk);
+ if (len == sizeof(zc))
+ goto zerocopy_rcv_sk_err;
switch (len) {
- case sizeof(zc):
+ case offsetofend(struct tcp_zerocopy_receive, err):
+ goto zerocopy_rcv_sk_err;
case offsetofend(struct tcp_zerocopy_receive, inq):
goto zerocopy_rcv_inq;
case offsetofend(struct tcp_zerocopy_receive, length):
default:
goto zerocopy_rcv_out;
}
+zerocopy_rcv_sk_err:
+ if (!err)
+ zc.err = sock_error(sk);
zerocopy_rcv_inq:
zc.inq = tcp_inq_hint(sk);
zerocopy_rcv_out: