io_uring: optimise locking for local tw with submit_wait

Running local task_work requires taking uring_lock, for submit + wait we
can try to run them right after submit while we still hold the lock and
save one lock/unlokc pair. The optimisation was implemented in the first
local tw patches but got dropped for simplicity.

Suggested-by: Dylan Yudaken <dylany@fb.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/281fc79d98b5d91fe4778c5137a17a2ab4693e5c.1665088876.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -3227,8 +3227,16 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			mutex_unlock(&ctx->uring_lock);
 			goto out;
 		}
-		if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll)
-			goto iopoll_locked;
+		if (flags & IORING_ENTER_GETEVENTS) {
+			if (ctx->syscall_iopoll)
+				goto iopoll_locked;
+			/*
+			 * Ignore errors, we'll soon call io_cqring_wait() and
+			 * it should handle ownership problems if any.
+			 */
+			if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+				(void)io_run_local_work_locked(ctx);
+		}
 		mutex_unlock(&ctx->uring_lock);
 	}
 

io_uring/io_uring.h

@@ -275,6 +275,13 @@ static inline int io_run_task_work_ctx(struct io_ring_ctx *ctx)
 	return ret;
 }
 
+static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
+{
+	if (llist_empty(&ctx->work_llist))
+		return 0;
+	return __io_run_local_work(ctx, true);
+}
+
 static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
 {
 	if (!*locked) {