2016-09-19 12:58:57

by David Vrabel

[permalink] [raw]
Subject: [PATCHv2] sunrpc: fix write space race causing stalls

Write space becoming available may race with putting the task to sleep
in xprt_wait_for_buffer_space(). The existing mechanism to avoid the
race does not work.

This (edited) partial trace illustrates the problem:

[1] rpc_task_run_action: task:43546@5 ... action=call_transmit
[2] xs_write_space <-xs_tcp_write_space
[3] xprt_write_space <-xs_write_space
[4] rpc_task_sleep: task:43546@5 ...
[5] xs_write_space <-xs_tcp_write_space

[1] Task 43546 runs but is out of write space.

[2] Space becomes available, xs_write_space() clears the
SOCKWQ_ASYNC_NOSPACE bit.

[3] xprt_write_space() attemts to wake xprt->snd_task (== 43546), but
this has not yet been queued and the wake up is lost.

[4] xs_nospace() is called which calls xprt_wait_for_buffer_space()
which queues task 43546.

[5] The call to sk->sk_write_space() at the end of xs_nospace() (which
is supposed to handle the above race) does not call
xprt_write_space() as the SOCKWQ_ASYNC_NOSPACE bit is clear and
thus the task is not woken.

Fix the race by resetting the SOCKWQ_ASYNC_NOSPACE bit in xs_nospace()
so the second call to sk->sk_write_space() calls xprt_write_space().

Suggested-by: Trond Myklebust <[email protected]>
Signed-off-by: David Vrabel <[email protected]>
---
net/sunrpc/xprtsock.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index bf16883..e72581d 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -473,7 +473,16 @@ static int xs_nospace(struct rpc_task *task)
spin_unlock_bh(&xprt->transport_lock);

/* Race breaker in case memory is freed before above code is called */
- sk->sk_write_space(sk);
+ if (ret == -EAGAIN) {
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags);
+ rcu_read_unlock();
+
+ sk->sk_write_space(sk);
+ }
return ret;
}

--
2.1.4