[PATCH 1/1] io_uring: clean up tctx_task_work()

[Pavel Begunkov <asml.silence@gmail.com>]

After recent fixes, tctx_task_work() always does proper spinlocking
before looking into ->task_list, so now we don't need atomics for
->task_state, replace it with non-atomic task_running using the critical
section.

Tide it up, combine two separate block with spinlocking, and always try
to splice in there, so we do less locking when new requests are arriving
during the function execution.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 fs/io_uring.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 345ec0d44b66..57f7b6311395 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -470,8 +470,8 @@ struct io_uring_task {
 
 	spinlock_t		task_lock;
 	struct io_wq_work_list	task_list;
-	unsigned long		task_state;
 	struct callback_head	task_work;
+	bool			task_running;
 };
 
 /*
@@ -1954,9 +1954,13 @@ static void tctx_task_work(struct callback_head *cb)
 		spin_lock_irq(&tctx->task_lock);
 		node = tctx->task_list.first;
 		INIT_WQ_LIST(&tctx->task_list);
+		if (!node)
+			tctx->task_running = false;
 		spin_unlock_irq(&tctx->task_lock);
+		if (!node)
+			break;
 
-		while (node) {
+		do {
 			struct io_wq_work_node *next = node->next;
 			struct io_kiocb *req = container_of(node, struct io_kiocb,
 							    io_task_work.node);
@@ -1968,19 +1972,8 @@ static void tctx_task_work(struct callback_head *cb)
 			}
 			req->io_task_work.func(req);
 			node = next;
-		}
-		if (wq_list_empty(&tctx->task_list)) {
-			spin_lock_irq(&tctx->task_lock);
-			clear_bit(0, &tctx->task_state);
-			if (wq_list_empty(&tctx->task_list)) {
-				spin_unlock_irq(&tctx->task_lock);
-				break;
-			}
-			spin_unlock_irq(&tctx->task_lock);
-			/* another tctx_task_work() is enqueued, yield */
-			if (test_and_set_bit(0, &tctx->task_state))
-				break;
-		}
+		} while (node);
+
 		cond_resched();
 	}
 
@@ -1994,16 +1987,19 @@ static void io_req_task_work_add(struct io_kiocb *req)
 	enum task_work_notify_mode notify;
 	struct io_wq_work_node *node;
 	unsigned long flags;
+	bool running;
 
 	WARN_ON_ONCE(!tctx);
 
 	spin_lock_irqsave(&tctx->task_lock, flags);
 	wq_list_add_tail(&req->io_task_work.node, &tctx->task_list);
+	running = tctx->task_running;
+	if (!running)
+		tctx->task_running = true;
 	spin_unlock_irqrestore(&tctx->task_lock, flags);
 
 	/* task_work already pending, we're done */
-	if (test_bit(0, &tctx->task_state) ||
-	    test_and_set_bit(0, &tctx->task_state))
+	if (running)
 		return;
 
 	/*
@@ -2018,7 +2014,6 @@ static void io_req_task_work_add(struct io_kiocb *req)
 		return;
 	}
 
-	clear_bit(0, &tctx->task_state);
 	spin_lock_irqsave(&tctx->task_lock, flags);
 	node = tctx->task_list.first;
 	INIT_WQ_LIST(&tctx->task_list);
-- 
2.32.0