io_uring/napi: postpone napi timeout adjustment

Remove io_napi_adjust_timeout() and move the adjustments out of the
common path into __io_napi_busy_loop(). Now the limit it's calculated
based on struct io_wait_queue::timeout, for which we query current time
another time. The overhead shouldn't be a problem, it's a polling path,
however that can be optimised later by additionally saving the delta
time value in io_cqring_wait().

Signed-off-by: Pavel Begunkov <[email protected]>
Link: https://lore.kernel.org/r/88e14686e245b3b42ff90a3c4d70895d48676206.1723039801.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <[email protected]>

Author: isilence

io_uring/io_uring.c

@@ -2423,7 +2423,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 		dt = timespec64_to_ktime(ts);
 		iowq.timeout = ktime_add(dt, ktime_get());
-		io_napi_adjust_timeout(ctx, &iowq, dt);
 	}
 
 	if (sig) {

io_uring/napi.c

@@ -269,27 +269,6 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
 	return 0;
 }
 
-/*
- * __io_napi_adjust_timeout() - adjust busy loop timeout
- * @ctx: pointer to io-uring context structure
- * @iowq: pointer to io wait queue
- * @ts: pointer to timespec or NULL
- *
- * Adjust the busy loop timeout according to timespec and busy poll timeout.
- * If the specified NAPI timeout is bigger than the wait timeout, then adjust
- * the NAPI timeout accordingly.
- */
-void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
-			      ktime_t to_wait)
-{
-	ktime_t poll_dt = READ_ONCE(ctx->napi_busy_poll_dt);
-
-	if (to_wait)
-		poll_dt = min(poll_dt, to_wait);
-
-	iowq->napi_busy_poll_dt = poll_dt;
-}
-
 /*
  * __io_napi_busy_loop() - execute busy poll loop
  * @ctx: pointer to io-uring context structure
@@ -302,6 +281,13 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
 	if (ctx->flags & IORING_SETUP_SQPOLL)
 		return;
 
+	iowq->napi_busy_poll_dt = READ_ONCE(ctx->napi_busy_poll_dt);
+	if (iowq->timeout != KTIME_MAX) {
+		ktime_t dt = ktime_sub(iowq->timeout, ktime_get());
+
+		iowq->napi_busy_poll_dt = min_t(u64, iowq->napi_busy_poll_dt, dt);
+	}
+
 	iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
 	io_napi_blocking_busy_loop(ctx, iowq);
 }

io_uring/napi.h

@@ -17,8 +17,6 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg);
 
 void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock);
 
-void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
-		struct io_wait_queue *iowq, ktime_t to_wait);
 void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq);
 int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx);
 
@@ -27,15 +25,6 @@ static inline bool io_napi(struct io_ring_ctx *ctx)
 	return !list_empty(&ctx->napi_list);
 }
 
-static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
-					  struct io_wait_queue *iowq,
-					  ktime_t to_wait)
-{
-	if (!io_napi(ctx))
-		return;
-	__io_napi_adjust_timeout(ctx, iowq, to_wait);
-}
-
 static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
 				     struct io_wait_queue *iowq)
 {
@@ -86,11 +75,6 @@ static inline bool io_napi(struct io_ring_ctx *ctx)
 static inline void io_napi_add(struct io_kiocb *req)
 {
 }
-static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
-					  struct io_wait_queue *iowq,
-					  ktime_t to_wait)
-{
-}
 static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
 				     struct io_wait_queue *iowq)
 {