io_uring: fix ctx-exit io_rsrc_put_work() deadlock

__io_rsrc_put_work() might need ->uring_lock, so nobody should wait for
rsrc nodes holding the mutex. However, that's exactly what
io_ring_ctx_free() does with io_wait_rsrc_data().

Split it into rsrc wait + dealloc, and move the first one out of the
lock.

Cc: stable@vger.kernel.org
Fixes: b60c8dce33 ("io_uring: preparation for rsrc tagging")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/0130c5c2693468173ec1afab714e0885d2c9c363.1628559783.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -8652,13 +8652,10 @@ static void io_req_caches_free(struct io_ring_ctx *ctx)
 	mutex_unlock(&ctx->uring_lock);
 }
 
-static bool io_wait_rsrc_data(struct io_rsrc_data *data)
+static void io_wait_rsrc_data(struct io_rsrc_data *data)
 {
-	if (!data)
-		return false;
-	if (!atomic_dec_and_test(&data->refs))
+	if (data && !atomic_dec_and_test(&data->refs))
 		wait_for_completion(&data->done);
-	return true;
 }
 
 static void io_ring_ctx_free(struct io_ring_ctx *ctx)
@@ -8670,10 +8667,14 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		ctx->mm_account = NULL;
 	}
 
+	/* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */
+	io_wait_rsrc_data(ctx->buf_data);
+	io_wait_rsrc_data(ctx->file_data);
+
 	mutex_lock(&ctx->uring_lock);
-	if (io_wait_rsrc_data(ctx->buf_data))
+	if (ctx->buf_data)
 		__io_sqe_buffers_unregister(ctx);
-	if (io_wait_rsrc_data(ctx->file_data))
+	if (ctx->file_data)
 		__io_sqe_files_unregister(ctx);
 	if (ctx->rings)
 		__io_cqring_overflow_flush(ctx, true);