io_uring: prevent sq_thread from spinning when it should stop (7143b5ac) · Commits · 戴 / test

This patch drops 'cur_mm' before calling cond_resched(), to prevent the sq_thread from spinning even when the user process is finished. Before this patch, if the user process ended without closing the io_uring fd, the sq_thread continues to spin until the 'sq_thread_idle' timeout ends. In the worst case where the 'sq_thread_idle' parameter is bigger than INT_MAX, the sq_thread will spin forever. Fixes: ("io_uring: add submission polling") Signed-off-by:

Stefano Garzarella <sgarzare@redhat.com> Signed-off-by:

Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

+12 −12

Original line number	Diff line number	Diff line
		@@ -5142,6 +5142,18 @@ static int io_sq_thread(void *data)
		* to enter the kernel to reap and flush events.
		*/
		if (!to_submit \|\| ret == -EBUSY) {
		/*
		* Drop cur_mm before scheduling, we can't hold it for
		* long periods (or over schedule()). Do this before
		* adding ourselves to the waitqueue, as the unuse/drop
		* may sleep.
		*/
		if (cur_mm) {
		unuse_mm(cur_mm);
		mmput(cur_mm);
		cur_mm = NULL;
		}

		/*
		* We're polling. If we're within the defined idle
		* period, then let us spin without work before going
		@@ -5156,18 +5168,6 @@ static int io_sq_thread(void *data)
		continue;
		}

		/*
		* Drop cur_mm before scheduling, we can't hold it for
		* long periods (or over schedule()). Do this before
		* adding ourselves to the waitqueue, as the unuse/drop
		* may sleep.
		*/
		if (cur_mm) {
		unuse_mm(cur_mm);
		mmput(cur_mm);
		cur_mm = NULL;
		}

		prepare_to_wait(&ctx->sqo_wait, &wait,
		TASK_INTERRUPTIBLE);

Admin message