[PATCH for-next v2 08/12] io_uring: never run tw and fallback in parallel

[Pavel Begunkov <asml.silence@xxxxxxxxx>]

Once we fallback a tw we want all requests to that task to be given to
the fallback wq so we dont run it in parallel with the last, i.e. post
PF_EXITING, tw run of the task.

Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
 io_uring/io_uring.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 3a422a7b7132..0e424d8721ab 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -149,6 +149,7 @@ static void io_clean_op(struct io_kiocb *req);
 static void io_queue_sqe(struct io_kiocb *req);
 static void io_move_task_work_from_local(struct io_ring_ctx *ctx);
 static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
+static __cold void io_fallback_tw(struct io_uring_task *tctx);
 
 static struct kmem_cache *req_cachep;
 
@@ -1160,10 +1161,17 @@ void tctx_task_work(struct callback_head *cb)
 	struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
 						  task_work);
 	struct llist_node fake = {};
-	struct llist_node *node = io_llist_xchg(&tctx->task_list, &fake);
+	struct llist_node *node;
 	unsigned int loops = 1;
-	unsigned int count = handle_tw_list(node, &ctx, &uring_locked, NULL);
+	unsigned int count;
+
+	if (unlikely(current->flags & PF_EXITING)) {
+		io_fallback_tw(tctx);
+		return;
+	}
 
+	node = io_llist_xchg(&tctx->task_list, &fake);
+	count = handle_tw_list(node, &ctx, &uring_locked, NULL);
 	node = io_llist_cmpxchg(&tctx->task_list, &fake, NULL);
 	while (node != &fake) {
 		loops++;
-- 
2.38.1