io_uring: add io_req_local_work_add wake fast path

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>
Link: https://lore.kernel.org/r/717702d772825a6647e6c315b4690277ba84c3fc.1673274244.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 7b5e90520278a08826734003f3205e11264a42d7..cc0cf0705b8f443ecd4c2c34f08cd5954864f200 100644 (file)
--- 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 be26829f7d20157c40faa0e3a8c5bef3cb6c1a8b..3f92028a7ee86765ad30a2a7f23532a10c879dcc 100644 (file)
--- 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);
 }
 
@@ -2576,6 +2578,7 @@ 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,
@@ -2584,6 +2587,8 @@ 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;
                /*