io_uring: do not always force run task_work in io_uring_register

Running task work when not needed can unnecessarily delay
operations. Specifically IORING_SETUP_DEFER_TASKRUN tries to avoid running
task work until the user requests it. Therefore do not run it in
io_uring_register any more.

The one catch is that io_rsrc_ref_quiesce expects it to have run in order
to process all outstanding references, and so reorder it's loop to do this.

Signed-off-by: Dylan Yudaken <dylany@meta.com>
Link: https://lore.kernel.org/r/20221107123349.4106213-1-dylany@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -4056,8 +4056,6 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 
 	ctx = f.file->private_data;
 
-	io_run_task_work_ctx(ctx);
-
 	mutex_lock(&ctx->uring_lock);
 	ret = __io_uring_register(ctx, opcode, arg, nr_args);
 	mutex_unlock(&ctx->uring_lock);

io_uring/rsrc.c

@@ -321,6 +321,11 @@ __cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
 		if (atomic_dec_and_test(&data->refs))
 			break;
 		mutex_unlock(&ctx->uring_lock);
+
+		ret = io_run_task_work_sig(ctx);
+		if (ret < 0)
+			goto reinit;
+
 		flush_delayed_work(&ctx->rsrc_put_work);
 		ret = wait_for_completion_interruptible(&data->done);
 		if (!ret) {
@@ -336,12 +341,12 @@ __cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
 			}
 		}
 
+reinit:
 		atomic_inc(&data->refs);
 		/* wait for all works potentially completing data->done */
 		flush_delayed_work(&ctx->rsrc_put_work);
 		reinit_completion(&data->done);
 
-		ret = io_run_task_work_sig(ctx);
 		mutex_lock(&ctx->uring_lock);
 	} while (ret >= 0);
 	data->quiesce = false;