io_uring/poll: attempt request issue after racy poll wakeup

If we have multiple requests waiting on the same target poll waitqueue,
then it's quite possible to get a request triggered and get disappointed
in not being able to make any progress with it. If we race in doing so,
we'll potentially leave the poll request on the internal tables, but
removed from the waitqueue. That means that any subsequent trigger of
the poll waitqueue will not kick that request into action, causing an
application to potentially wait for completion of a request that will
never happen.

Fix this by adding a new poll return state, IOU_POLL_REISSUE. Rather
than have complicated logic for how to re-arm a given type of request,
just punt it for a reissue.

While in there, move the 'ret' variable to the only section where it
gets used. This avoids confusion the scope of it.

Cc: stable@vger.kernel.org
Fixes: eb0089d629 ("io_uring: single shot poll removal optimisation")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/poll.c

@@ -223,21 +223,22 @@ enum {
 	IOU_POLL_DONE = 0,
 	IOU_POLL_NO_ACTION = 1,
 	IOU_POLL_REMOVE_POLL_USE_RES = 2,
+	IOU_POLL_REISSUE = 3,
 };
 
 /*
  * All poll tw should go through this. Checks for poll events, manages
  * references, does rewait, etc.
  *
- * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action require,
+ * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action
- * which is either spurious wakeup or multishot CQE is served.
+ * require, which is either spurious wakeup or multishot CQE is served.
- * IOU_POLL_DONE when it's done with the request, then the mask is stored in req->cqe.res.
+ * IOU_POLL_DONE when it's done with the request, then the mask is stored in
- * IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot poll and that the result
+ * req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot
- * is stored in req->cqe.
+ * poll and that the result is stored in req->cqe.
  */
 static int io_poll_check_events(struct io_kiocb *req, bool *locked)
 {
-	int v, ret;
+	int v;
 
 	/* req->task == current here, checking PF_EXITING is safe */
 	if (unlikely(req->task->flags & PF_EXITING))
@@ -276,10 +277,15 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked)
 		if (!req->cqe.res) {
 			struct poll_table_struct pt = { ._key = req->apoll_events };
 			req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events;
+			/*
+			 * We got woken with a mask, but someone else got to
+			 * it first. The above vfs_poll() doesn't add us back
+			 * to the waitqueue, so if we get nothing back, we
+			 * should be safe and attempt a reissue.
+			 */
+			if (unlikely(!req->cqe.res))
+				return IOU_POLL_REISSUE;
 		}
-
-		if ((unlikely(!req->cqe.res)))
-			continue;
 		if (req->apoll_events & EPOLLONESHOT)
 			return IOU_POLL_DONE;
 
@@ -294,7 +300,7 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
 			}
 		} else {
-			ret = io_poll_issue(req, locked);
+			int ret = io_poll_issue(req, locked);
 			if (ret == IOU_STOP_MULTISHOT)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
 			if (ret < 0)
@@ -330,6 +336,9 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
 
 			poll = io_kiocb_to_cmd(req, struct io_poll);
 			req->cqe.res = mangle_poll(req->cqe.res & poll->events);
+		} else if (ret == IOU_POLL_REISSUE) {
+			io_req_task_submit(req, locked);
+			return;
 		} else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) {
 			req->cqe.res = ret;
 			req_set_fail(req);
@@ -342,7 +351,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
 
 		if (ret == IOU_POLL_REMOVE_POLL_USE_RES)
 			io_req_task_complete(req, locked);
-		else if (ret == IOU_POLL_DONE)
+		else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE)
 			io_req_task_submit(req, locked);
 		else
 			io_req_defer_failed(req, ret);