io_uring: switch normal task_work to a mpscq

Like the local task_work list, the normal (tctx) task_work list is an
llist, and hence needs the O(n) llist_reverse_order() pass before
running entries in queue order. On top of that, capped runs - sqpoll
processing IORING_TW_CAP_ENTRIES_VALUE entries at a time - need the
claimed-but-unprocessed leftovers carried in a separate retry_list,
as they can't be pushed back to the shared list.

Switch tctx->task_list to a mpscq, like what was done for the
DEFER_TASKRUN paths as well.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 11 insertions, 1 deletions

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 3e07c7059d7b..f511e96865b6 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -131,6 +131,11 @@ struct io_uring_task {
 	const struct io_ring_ctx 	*last;
 	struct task_struct		*task;
 	struct io_wq			*io_wq;
+	/*
+	 * Consumer cursor for ->task_list. Only popped by the task itself,
+	 * or by ->fallback_work once the task can no longer run task_work.
+	 */
+	struct llist_node		*task_head;
 	struct file			*registered_rings[IO_RINGFD_REG_MAX];
 
 	struct xarray			xa;
@@ -139,8 +144,13 @@ struct io_uring_task {
 	atomic_t			inflight_tracked;
 	struct percpu_counter		inflight;
 
+	/* drains ->task_list once the task can no longer run task_work */
+	struct work_struct		fallback_work;
+
 	struct { /* task_work */
-		struct llist_head	task_list;
+		struct mpscq		task_list;
+		/* BIT(0) guards adding tw only once */
+		unsigned long		tw_pending;
 		struct callback_head	task_work;
 	} ____cacheline_aligned_in_smp;
 };