| Message ID | 2dac97e8f691231049cb259c4ae57e79e40b537c.1668710222.git.asml.silence@gmail.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | minor poll fixes | expand |
Pavel Begunkov <asml.silence@gmail.com> writes: > When io_poll_check_events() collides with someone attempting to queue a > task work, it'll spin for one more time. However, it'll continue to use > the mask from the first iteration instead of updating it. For example, > if the first wake up was a EPOLLIN and the second EPOLLOUT, the > userspace will not get EPOLLOUT in time. > > Clear the mask for all subsequent iterations to force vfs_poll(). Do we have a reproducer for it in liburing? Either way, I checked the code, it looks good to me. Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de> > > Cc: stable@vger.kernel.org > Fixes: aa43477b04025 ("io_uring: poll rework") > Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> > --- > io_uring/poll.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/io_uring/poll.c b/io_uring/poll.c > index f500506984ec..90920abf91ff 100644 > --- a/io_uring/poll.c > +++ b/io_uring/poll.c > @@ -258,6 +258,9 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) > return ret; > } > > + /* force the next iteration to vfs_poll() */ > + req->cqe.res = 0; > + > /* > * Release all references, retry if someone tried to restart > * task_work while we were executing it.
diff --git a/io_uring/poll.c b/io_uring/poll.c index f500506984ec..90920abf91ff 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -258,6 +258,9 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) return ret; } + /* force the next iteration to vfs_poll() */ + req->cqe.res = 0; + /* * Release all references, retry if someone tried to restart * task_work while we were executing it.
When io_poll_check_events() collides with someone attempting to queue a task work, it'll spin for one more time. However, it'll continue to use the mask from the first iteration instead of updating it. For example, if the first wake up was a EPOLLIN and the second EPOLLOUT, the userspace will not get EPOLLOUT in time. Clear the mask for all subsequent iterations to force vfs_poll(). Cc: stable@vger.kernel.org Fixes: aa43477b04025 ("io_uring: poll rework") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> --- io_uring/poll.c | 3 +++ 1 file changed, 3 insertions(+)