[PATCH v2 2/4] io_uring: fix io_rsrc_ref_quiesce races

[Pavel Begunkov <asml.silence@xxxxxxxxx>]

There are different types of races in io_rsrc_ref_quiesce()  between
->release() of percpu_refs and reinit_completion(), fix them by always
resurrecting between iterations. BTW, clean the function up, because
DRY.

Fixes: a4f2225d1cb2 ("io_uring: don't hold uring_lock when calling io_run_task_work*")
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
 fs/io_uring.c | 57 +++++++++++++++++++++------------------------------
 1 file changed, 23 insertions(+), 34 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 50d4dba08f82..292fba2b8e36 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -236,6 +236,7 @@ struct fixed_rsrc_data {
 	struct fixed_rsrc_ref_node	*node;
 	struct percpu_ref		refs;
 	struct completion		done;
+	bool				quiesce;
 };
 
 struct io_buffer {
@@ -7316,19 +7317,6 @@ static void io_sqe_rsrc_set_node(struct io_ring_ctx *ctx,
 	percpu_ref_get(&rsrc_data->refs);
 }
 
-static int io_sqe_rsrc_add_node(struct io_ring_ctx *ctx, struct fixed_rsrc_data *data)
-{
-	struct fixed_rsrc_ref_node *backup_node;
-
-	backup_node = alloc_fixed_rsrc_ref_node(ctx);
-	if (!backup_node)
-		return -ENOMEM;
-	init_fixed_file_ref_node(ctx, backup_node);
-	io_sqe_rsrc_set_node(ctx, data, backup_node);
-
-	return 0;
-}
-
 static void io_sqe_rsrc_kill_node(struct io_ring_ctx *ctx, struct fixed_rsrc_data *data)
 {
 	struct fixed_rsrc_ref_node *ref_node = NULL;
@@ -7347,39 +7335,40 @@ static int io_rsrc_ref_quiesce(struct fixed_rsrc_data *data,
 {
 	int ret;
 
-	io_sqe_rsrc_kill_node(ctx, data);
-	percpu_ref_kill(&data->refs);
+	if (data->quiesce)
+		return -ENXIO;
 
-	/* wait for all refs nodes to complete */
-	flush_delayed_work(&ctx->rsrc_put_work);
+	data->quiesce = true;
 	do {
+		io_sqe_rsrc_kill_node(ctx, data);
+		percpu_ref_kill(&data->refs);
+		flush_delayed_work(&ctx->rsrc_put_work);
+
 		ret = wait_for_completion_interruptible(&data->done);
 		if (!ret)
 			break;
 
-		ret = io_sqe_rsrc_add_node(ctx, data);
-		if (ret < 0)
-			break;
-		/*
-		 * There is small possibility that data->done is already completed
-		 * So reinit it here
-		 */
+		percpu_ref_resurrect(&data->refs);
+		io_sqe_rsrc_set_node(ctx, data, backup_node);
+		backup_node = NULL;
 		reinit_completion(&data->done);
 		mutex_unlock(&ctx->uring_lock);
 		ret = io_run_task_work_sig();
 		mutex_lock(&ctx->uring_lock);
-		io_sqe_rsrc_kill_node(ctx, data);
-	} while (ret >= 0);
 
-	if (ret < 0) {
-		percpu_ref_resurrect(&data->refs);
-		reinit_completion(&data->done);
-		io_sqe_rsrc_set_node(ctx, data, backup_node);
-		return ret;
-	}
+		if (ret < 0)
+			break;
+		backup_node = alloc_fixed_rsrc_ref_node(ctx);
+		ret = -ENOMEM;
+		if (!backup_node)
+			break;
+		init_fixed_file_ref_node(ctx, backup_node);
+	} while (1);
+	data->quiesce = false;
 
-	destroy_fixed_rsrc_ref_node(backup_node);
-	return 0;
+	if (backup_node)
+		destroy_fixed_rsrc_ref_node(backup_node);
+	return ret;
 }
 
 static struct fixed_rsrc_data *alloc_fixed_rsrc_data(struct io_ring_ctx *ctx)
-- 
2.24.0