diff options
| author |   Ying Xue <ying.xue@windriver.com> | 2014-03-06 14:40:18 +0100 |
|---|---|---|
| committer |   David S. Miller <davem@davemloft.net> | 2014-03-06 14:46:23 -0500 |
| commit | fe8e4649397915cf3b2ab0b695929a27e543967e (patch) | |
| tree | 383c648ffdef61232e623f723f17247dcb860faf /net/tipc/socket.c | |
| parent | tipc: fix connection refcount leak (diff) | |
| download | linux-dev-fe8e4649397915cf3b2ab0b695929a27e543967e.tar.xz linux-dev-fe8e4649397915cf3b2ab0b695929a27e543967e.zip | |
tipc: avoid to unnecessary process switch under non-block mode
When messages are received via tipc socket under non-block mode,
schedule_timeout() is called in tipc_wait_for_rcvmsg(), that is,
the process of receiving messages will be scheduled once although
timeout value passed to schedule_timeout() is 0. The same issue
exists in accept()/wait_for_accept(). To avoid this unnecessary
process switch, we only call schedule_timeout() if the timeout
value is non-zero.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/tipc/socket.c')
| -rw-r--r-- | net/tipc/socket.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/net/tipc/socket.c b/net/tipc/socket.c index a4cf274455aa..0ed0eaa62f29 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -997,7 +997,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (skb_queue_empty(&sk->sk_receive_queue)) { + if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { if (sock->state == SS_DISCONNECTING) { err = -ENOTCONN; break; @@ -1623,7 +1623,7 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (skb_queue_empty(&sk->sk_receive_queue)) { + if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); |