9P: Fix race in p9_read_work()

Race scenario between p9_read_work() and p9_poll_mux()

Data arrive, Rworksched is set, p9_read_work() is called.

thread A                                thread B

                                        p9_read_work()
                                                .
                                        reads data
                                                .
                                        checks if new data ready. No.
                                                .
                                        gets preempted
                                                .
More data arrive, p9_poll_mux() is called.      .
                                                .
                                                .
p9_poll_mux()                                   .
                                                .
if (!test_and_set_bit(Rworksched,               .
                      &m->wsched)) {            .
  schedule_work(&m->rq);                        .
}                                               .
                                                .
-> does not schedule work because               .
   Rworksched is set                            .
                                                .
                                        clear_bit(Rworksched, &m->wsched);
                                        return;

No work has been scheduled, and yet data are waiting.

Currently p9_read_work() checks if there is data to read,
and if not, it clears Rworksched.

I think it should clear Rworksched first, and then check if there is data to read.

Signed-off-by: Simon Derr <simon.derr@bull.net>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>

diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 6449bae157023c182de306d862a6c0a11f0b04e9..de1bbad0c7ded496d51b0027bd6a105fb7599fad 100644 (file)
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -316,8 +316,7 @@ static void p9_read_work(struct work_struct *work)
                                                m->rsize - m->rpos);
        p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err);
        if (err == -EAGAIN) {
-               clear_bit(Rworksched, &m->wsched);
-               return;
+               goto end_clear;
        }
 
        if (err <= 0)
@@ -379,19 +378,20 @@ static void p9_read_work(struct work_struct *work)
                m->req = NULL;
        }
 
+end_clear:
+       clear_bit(Rworksched, &m->wsched);
+
        if (!list_empty(&m->req_list)) {
                if (test_and_clear_bit(Rpending, &m->wsched))
                        n = POLLIN;
                else
                        n = p9_fd_poll(m->client, NULL);
 
-               if (n & POLLIN) {
+               if ((n & POLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) {
                        p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m);
                        schedule_work(&m->rq);
-               } else
-                       clear_bit(Rworksched, &m->wsched);
-       } else
-               clear_bit(Rworksched, &m->wsched);
+               }
+       }
 
        return;
 error: