[PATCH 3/3] io_uring: wait for cancelations on final ring put

[Jens Axboe <axboe@kernel.dk>]

We still offload the cancelation to a workqueue, as not to introduce
dependencies between the exiting task waiting on cleanup, and that
task needing to run task_work to complete the process.

This means that once the final ring put is done, any request that was
inflight and needed cancelation will be done as well. Notably requests
that hold references to files - once the ring fd close is done, we will
have dropped any of those references too.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  2 ++
 io_uring/io_uring.c            | 16 ++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index c30c267689bb..df6ee78b70aa 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -374,6 +374,8 @@ struct io_ring_ctx {
 	unsigned			sq_thread_idle;
 	/* protected by ->completion_lock */
 	unsigned			evfd_last_cq_tail;
+
+	struct completion		*exit_comp;
 };
 
 struct io_tw_state {
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 68344fbfc055..c65575fb4643 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3068,6 +3068,9 @@ static __cold void io_ring_exit_work(struct work_struct *work)
 		 */
 	} while (!wait_for_completion_interruptible_timeout(&ctx->ref_comp, interval));
 
+	if (ctx->exit_comp)
+		complete(ctx->exit_comp);
+
 	init_completion(&exit.completion);
 	init_task_work(&exit.task_work, io_tctx_exit_cb);
 	exit.ctx = ctx;
@@ -3116,6 +3119,8 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 
 	mutex_lock(&ctx->uring_lock);
 	io_ring_ref_kill(ctx);
+	if (current->io_uring)
+		io_fallback_tw(current->io_uring, false);
 	xa_for_each(&ctx->personalities, index, creds)
 		io_unregister_personality(ctx, index);
 	if (ctx->rings)
@@ -3144,9 +3149,20 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 static int io_uring_release(struct inode *inode, struct file *file)
 {
 	struct io_ring_ctx *ctx = file->private_data;
+	DECLARE_COMPLETION_ONSTACK(exit_comp);
 
 	file->private_data = NULL;
+	WRITE_ONCE(ctx->exit_comp, &exit_comp);
 	io_ring_ctx_wait_and_kill(ctx);
+
+	/*
+	 * Wait for cancel to run before exiting task
+	 */
+	do {
+		if (current->io_uring)
+			io_fallback_tw(current->io_uring, false);
+	} while (wait_for_completion_interruptible(&exit_comp));
+
 	return 0;
 }
 
-- 
2.40.1