[ upstream commit 539bcb57da2f58886d7d5c17134236b0ec9cd15d ]
We may never try to process a poll wake and its mask if there was multiple wake ups racing for queueing up a tw. Force io_poll_check_events() to update the mask by vfs_poll().
Cc: stable@vger.kernel.org Fixes: aa43477b04025 ("io_uring: poll rework") Signed-off-by: Pavel Begunkov asml.silence@gmail.com Link: https://lore.kernel.org/r/00344d60f8b18907171178d7cf598de71d127b0b.166871022... Signed-off-by: Jens Axboe axboe@kernel.dk --- fs/io_uring.c | 7 +++++++ 1 file changed, 7 insertions(+)
diff --git a/fs/io_uring.c b/fs/io_uring.c index 2ba42e6e0881..62e0d352c78e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5440,6 +5440,13 @@ static int io_poll_check_events(struct io_kiocb *req) return 0; if (v & IO_POLL_CANCEL_FLAG) return -ECANCELED; + /* + * cqe.res contains only events of the first wake up + * and all others are be lost. Redo vfs_poll() to get + * up to date state. + */ + if ((v & IO_POLL_REF_MASK) != 1) + req->result = 0;
if (!req->result) { struct poll_table_struct pt = { ._key = poll->events };