io_uring: force tw ctx locking

We can run normal task_work without locking the ctx, however we try to
lock anyway and most handlers prefer or require it locked. It might have
been interesting to multi-submitter ring with high contention completing
async read/write requests via task_work, however that will still need to
go through io_req_complete_post() and potentially take the lock for
rsrc node putting or some other case.

In other words, it's hard to care about it, so alawys force the locking.
The case described would also because of various io_uring caches.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/6ae858f2ef562e6ed9f13c60978c0d48926954ba.1710799188.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -1185,8 +1185,9 @@ struct llist_node *io_handle_tw_list(struct llist_node *node,
 		if (req->ctx != ctx) {
 			ctx_flush_and_put(ctx, &ts);
 			ctx = req->ctx;
-			/* if not contended, grab and improve batching */
-			ts.locked = mutex_trylock(&ctx->uring_lock);
+
+			ts.locked = true;
+			mutex_lock(&ctx->uring_lock);
 			percpu_ref_get(&ctx->refs);
 		}
 		INDIRECT_CALL_2(req->io_task_work.func,
@@ -1447,11 +1448,9 @@ static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts,
 
 	if (io_run_local_work_continue(ctx, ret, min_events))
 		goto again;
-	if (ts->locked) {
-		io_submit_flush_completions(ctx);
-		if (io_run_local_work_continue(ctx, ret, min_events))
-			goto again;
-	}
+	io_submit_flush_completions(ctx);
+	if (io_run_local_work_continue(ctx, ret, min_events))
+		goto again;
 
 	trace_io_uring_local_work_run(ctx, ret, loops);
 	return ret;
@@ -1475,14 +1474,12 @@ static inline int io_run_local_work_locked(struct io_ring_ctx *ctx,
 
 static int io_run_local_work(struct io_ring_ctx *ctx, int min_events)
 {
-	struct io_tw_state ts = {};
+	struct io_tw_state ts = { .locked = true };
 	int ret;
 
-	ts.locked = mutex_trylock(&ctx->uring_lock);
+	mutex_lock(&ctx->uring_lock);
 	ret = __io_run_local_work(ctx, &ts, min_events);
-	if (ts.locked)
-		mutex_unlock(&ctx->uring_lock);
-
+	mutex_unlock(&ctx->uring_lock);
 	return ret;
 }