[PATCH v3 10/11] io_uring: add io_req_local_work_add wake fast path

[Pavel Begunkov <asml.silence@gmail.com>]

Don't wake the master task after queueing a deferred tw unless it's
currently waiting in io_cqring_wait.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 include/linux/io_uring_types.h | 1 +
 io_uring/io_uring.c            | 7 ++++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 7b5e90520278..cc0cf0705b8f 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -295,6 +295,7 @@ struct io_ring_ctx {
 		spinlock_t		completion_lock;
 
 		bool			poll_multi_queue;
+		bool			cq_waiting;
 
 		/*
 		 * ->iopoll_list is protected by the ctx->uring_lock for
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 62d879b14873..9c95ceb1a9f2 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1276,7 +1276,9 @@ static void io_req_local_work_add(struct io_kiocb *req)
 		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 	if (ctx->has_evfd)
 		io_eventfd_signal(ctx);
-	wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE);
+
+	if (READ_ONCE(ctx->cq_waiting))
+		wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE);
 	percpu_ref_put(&ctx->refs);
 }
 
@@ -2578,6 +2580,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		unsigned long check_cq;
 
 		if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
+			WRITE_ONCE(ctx->cq_waiting, 1);
 			set_current_state(TASK_INTERRUPTIBLE);
 		} else {
 			prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
@@ -2586,6 +2589,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 		ret = io_cqring_wait_schedule(ctx, &iowq);
 		__set_current_state(TASK_RUNNING);
+		WRITE_ONCE(ctx->cq_waiting, 0);
+
 		if (ret < 0)
 			break;
 		/*
-- 
2.38.1