[PATCH 07/10] io_uring/sqpoll: don't wait for the thread to exit

[Jens Axboe <axboe@kernel.dk>]

From: Chris Mason <mason@kernel.org>

io_sq_thread_stop() wakes the SQPOLL thread and waits for it to exit.
The thread belongs to the thread group that created the ring, so a
SIGSTOP or the cgroup freezer holds it in get_signal(), and the wake up
doesn't change that. io_ring_exit_work() then sleeps in that wait until
someone continues or kills the process. iou_exit has 64 slots, so 64
closed SQPOLL rings of a stopped process keep every other ring from
being freed, for everyone.

Don't wait. Set the stop bit, wake the thread, and let it exit when it
gets to run again. The sqd can now outlive its last ring, so give it a
second refcount with one reference for the rings and one for the thread,
and free it with the last one. The thread can't reach a freed ring,
rings leave ctx_list before dropping their reference, and the io-wq hash
is refcounted.

Fixes: 16efa4fce3b7 ("io_uring: allow IO worker threads to be frozen")
Signed-off-by: Chris Mason <mason@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/sqpoll.c | 28 +++++++++++++++++++++++-----
 io_uring/sqpoll.h |  3 ++-
 2 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index ee97808a065a..49c52284ecdd 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -63,6 +63,24 @@ void io_sq_thread_park(struct io_sq_data *sqd)
 	}
 }
 
+/*
+ * The sqd has two holders: its rings, as one, and its thread. Neither waits
+ * for the other to let go. The one that lets go last frees the sqd.
+ */
+static void io_sq_data_release(struct io_sq_data *sqd)
+{
+	if (refcount_dec_and_test(&sqd->free_refs))
+		kfree(sqd);
+}
+
+/*
+ * Ask the thread to exit, and don't wait for it. A thread that is stopped or
+ * frozen exits only when a user lets it run again, and the exit work of the
+ * ring would keep its place in the workqueue until then. All rings have left
+ * ctx_list by now and have no request left, so the thread can reach none of
+ * them. What it still uses is its own or counted: the sqd by free_refs, the
+ * hash of its io-wq by hash->refs.
+ */
 void io_sq_thread_stop(struct io_sq_data *sqd)
 {
 	struct task_struct *tsk;
@@ -77,7 +95,6 @@ void io_sq_thread_stop(struct io_sq_data *sqd)
 		wake_up_process(tsk);
 	}
 	mutex_unlock(&sqd->lock);
-	wait_for_completion(&sqd->exited);
 }
 
 void io_put_sq_data(struct io_sq_data *sqd)
@@ -86,7 +103,7 @@ void io_put_sq_data(struct io_sq_data *sqd)
 		WARN_ON_ONCE(atomic_read(&sqd->park_pending));
 
 		io_sq_thread_stop(sqd);
-		kfree(sqd);
+		io_sq_data_release(sqd);
 	}
 }
 
@@ -160,10 +177,10 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
 
 	atomic_set(&sqd->park_pending, 0);
 	refcount_set(&sqd->refs, 1);
+	refcount_set(&sqd->free_refs, 2);
 	INIT_LIST_HEAD(&sqd->ctx_list);
 	mutex_init(&sqd->lock);
 	init_waitqueue_head(&sqd->wait);
-	init_completion(&sqd->exited);
 	return sqd;
 }
 
@@ -424,7 +441,7 @@ static int io_sq_thread(void *data)
 	io_run_task_work();
 	mutex_unlock(&sqd->lock);
 err_out:
-	complete(&sqd->exited);
+	io_sq_data_release(sqd);
 	do_exit(0);
 }
 
@@ -544,7 +561,8 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
 	}
 	return 0;
 err_sqpoll:
-	complete(&ctx->sq_data->exited);
+	/* no thread was made: let go of its share */
+	io_sq_data_release(ctx->sq_data);
 err:
 	io_sq_thread_finish(ctx);
 	return ret;
diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
index fd2f6f29b516..024a51dc3069 100644
--- a/io_uring/sqpoll.h
+++ b/io_uring/sqpoll.h
@@ -2,6 +2,8 @@
 
 struct io_sq_data {
 	refcount_t		refs;
+	/* one for all the rings, one for the thread: the last put frees */
+	refcount_t		free_refs;
 	atomic_t		park_pending;
 	struct mutex		lock;
 
@@ -18,7 +20,6 @@ struct io_sq_data {
 
 	u64			work_time;
 	unsigned long		state;
-	struct completion	exited;
 };
 
 int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p);
-- 
2.56.0