io_uring: optimise io_req_local_work_add

Chains of memory accesses are never good for performance.
The req->task->io_uring->in_cancel in io_req_local_work_add() is there
so that when a task is exiting via io_uring_try_cancel_requests() and
starts waiting for completions, it gets woken up by every new task_work
item queued.

Do a little trick by announcing waiting in io_uring_try_cancel_requests(),
making io_req_local_work_add() wake us up. We also need to check for
deferred tw items after prepare_to_wait(TASK_INTERRUPTIBLE);
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/fb11597e9bbcb365901824f8c5c2cf0d6ee100d0.1680782017.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -1335,10 +1335,6 @@ static void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 			      &req->io_task_work.node));
 
 	if (!first) {
-		if (unlikely(atomic_read(&req->task->io_uring->in_cancel))) {
-			io_move_task_work_from_local(ctx);
-			return;
-		}
 		if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 			atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 		if (ctx->has_evfd)
@@ -3205,6 +3201,12 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 	enum io_wq_cancel cret;
 	bool ret = false;
 
+	/* set it so io_req_local_work_add() would wake us up */
+	if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
+		atomic_set(&ctx->cq_wait_nr, 1);
+		smp_mb();
+	}
+
 	/* failed during ring init, it couldn't have issued any requests */
 	if (!ctx->rings)
 		return false;
@@ -3259,6 +3261,8 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 {
 	struct io_uring_task *tctx = current->io_uring;
 	struct io_ring_ctx *ctx;
+	struct io_tctx_node *node;
+	unsigned long index;
 	s64 inflight;
 	DEFINE_WAIT(wait);
 
@@ -3280,9 +3284,6 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 			break;
 
 		if (!sqd) {
-			struct io_tctx_node *node;
-			unsigned long index;
-
 			xa_for_each(&tctx->xa, index, node) {
 				/* sqpoll task will cancel all its requests */
 				if (node->ctx->sq_data)
@@ -3305,7 +3306,13 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 		prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
 		io_run_task_work();
 		io_uring_drop_tctx_refs(current);
-
+		xa_for_each(&tctx->xa, index, node) {
+			if (!llist_empty(&node->ctx->work_llist)) {
+				WARN_ON_ONCE(node->ctx->submitter_task &&
+					     node->ctx->submitter_task != current);
+				goto end_wait;
+			}
+		}
 		/*
 		 * If we've seen completions, retry without waiting. This
 		 * avoids a race where a completion comes in before we did
@@ -3313,6 +3320,7 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 		 */
 		if (inflight == tctx_inflight(tctx, !cancel_all))
 			schedule();
+end_wait:
 		finish_wait(&tctx->wait, &wait);
 	} while (1);