[PATCH 8/8] io_uring: batch completion in prior_task_list

[Hao Xu <haoxu@linux.alibaba.com>]

In previous patches, we have already gathered some tw with
io_req_task_complete() as callback in prior_task_list, let's complete
them in batch. This is better than before in cases where !locked.

Signed-off-by: Hao Xu <haoxu@linux.alibaba.com>
---
 fs/io_uring.c | 39 +++++++++++++++++++++++++++++++--------
 1 file changed, 31 insertions(+), 8 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 231d0a47025b..4d71179228af 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2156,6 +2156,23 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req)
 	return io_put_kbuf(req, kbuf);
 }
 
+static void handle_prior_tw_list(struct io_wq_work_node *node, struct io_ring_ctx *ctx)
+{
+	spin_lock(&ctx->completion_lock);
+	do {
+		struct io_wq_work_node *next = node->next;
+		struct io_kiocb *req = container_of(node, struct io_kiocb,
+						    io_task_work.node);
+
+		__io_req_complete_post(req, req->result, io_put_rw_kbuf(req));
+		node = next;
+	} while (node);
+
+	io_commit_cqring(ctx);
+	spin_unlock(&ctx->completion_lock);
+	io_cqring_ev_posted(ctx);
+}
+
 static void handle_tw_list(struct io_wq_work_node *node, struct io_ring_ctx **ctx, bool *locked)
 {
 	do {
@@ -2178,31 +2195,37 @@ static void handle_tw_list(struct io_wq_work_node *node, struct io_ring_ctx **ct
 static void tctx_task_work(struct callback_head *cb)
 {
 	bool locked = false;
-	struct io_ring_ctx *ctx = NULL;
+	struct io_ring_ctx *ctx = NULL, *tw_ctx;
 	struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
 						  task_work);
 
 	while (1) {
-		struct io_wq_work_node *node;
-		struct io_wq_work_list *merged_list;
+		struct io_wq_work_node *node1, *node2;
 
 		if (!tctx->prior_task_list.first &&
 		    !tctx->task_list.first && locked)
 			io_submit_flush_completions(ctx);
 
 		spin_lock_irq(&tctx->task_lock);
-		merged_list = wq_list_merge(&tctx->prior_task_list, &tctx->task_list);
-		node = merged_list->first;
+		node1 = tctx->prior_task_list.first;
+		node2 = tctx->task_list.first;
+		tw_ctx = tctx->tw_ctx;
 		INIT_WQ_LIST(&tctx->task_list);
 		INIT_WQ_LIST(&tctx->prior_task_list);
 		tctx->nr = tctx->prior_nr = 0;
-		if (!node)
+		tctx->tw_ctx = NULL;
+		if (!node1 && !node2)
 			tctx->task_running = false;
 		spin_unlock_irq(&tctx->task_lock);
-		if (!node)
+		if (!node1 && !node2)
 			break;
 
-		handle_tw_list(node, &ctx, &locked);
+		if (tw_ctx)
+			handle_prior_tw_list(node1, tw_ctx);
+		else if (node1)
+			handle_tw_list(node1, &ctx, &locked);
+
+		handle_tw_list(node2, &ctx, &locked);
 		cond_resched();
 	}
 
-- 
2.24.4