io_uring: ensure local task_work is run on wait timeout

A previous commit added an earlier break condition here, which is fine if
we're using non-local task_work as it'll be run on return to userspace.
However, if DEFER_TASKRUN is used, then we could be leaving local
task_work that is ready to process in the ctx list until next time that
we enter the kernel to wait for events.

Move the break condition to _after_ we have run task_work.

Cc: stable@vger.kernel.org
Fixes: 846072f16eed ("io_uring: mimimise io_cqring_wait_schedule")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index a9a519fa9926ed2c665085290ef76bcf756106bb..4afb911fc042bda0a6c7a7e3827da9e902122aa3 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2615,8 +2615,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
                __set_current_state(TASK_RUNNING);
                atomic_set(&ctx->cq_wait_nr, 0);
 
-               if (ret < 0)
-                       break;
                /*
                 * Run task_work after scheduling and before io_should_wake().
                 * If we got woken because of task_work being processed, run it
@@ -2626,6 +2624,18 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
                if (!llist_empty(&ctx->work_llist))
                        io_run_local_work(ctx);
 
+               /*
+                * Non-local task_work will be run on exit to userspace, but
+                * if we're using DEFER_TASKRUN, then we could have waited
+                * with a timeout for a number of requests. If the timeout
+                * hits, we could have some requests ready to process. Ensure
+                * this break is _after_ we have run task_work, to avoid
+                * deferring running potentially pending requests until the
+                * next time we wait for events.
+                */
+               if (ret < 0)
+                       break;
+
                check_cq = READ_ONCE(ctx->check_cq);
                if (unlikely(check_cq)) {
                        /* let the caller flush overflows, retry */