stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: stable@vger.kernel.org
Subject: [PATCH 6.12.y 1/9] io_uring: enable toggle of iowait usage when waiting on CQEs
Date: Sat, 21 Nov 2026 21:31:13 +0000	[thread overview]
Message-ID: <20261121213121.1789042-2-axboe@kernel.dk> (raw)
In-Reply-To: <20261121213121.1789042-1-axboe@kernel.dk>

Commit 07754bfd9aee59063f8549f6e4d455eae636ecc7 upstream.

By default, io_uring marks a waiting task as being in iowait, if it's
sleeping waiting on events and there are pending requests. This isn't
necessarily always useful, and may be confusing on non-storage setups
where iowait isn't expected. It can also cause extra power usage, by
preventing the CPU from entering lower sleep states.

This adds a new enter flag, IORING_ENTER_NO_IOWAIT. If set, then
io_uring will not account the sleeping task as being in iowait. If the
kernel supports this feature, then it will be marked by having the
IORING_FEAT_NO_IOWAIT feature flag set.

As the kernel currently does not support separating the iowait
accounting and CPU frequency boosting, the IORING_ENTER_NO_IOWAIT
controls both of these at the same time. In the future, if those do end
up being split, then it'd be possible to control them separately.
However, it seems more likely that the kernel will decouple iowait and
CPU frequency boosting anyway.

[ 6.12: only the NO_IOWAIT flag bits are added, the EXT_ARG_REG and
  RW_ATTR bits before them don't exist here. io_get_ext_arg() has no
  ctx argument. ]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  2 ++
 io_uring/io_uring.c           | 31 +++++++++++++++++++------------
 2 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index fdd7b931ea1d..e777e6b128e8 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -518,6 +518,7 @@ struct io_cqring_offsets {
 #define IORING_ENTER_EXT_ARG		(1U << 3)
 #define IORING_ENTER_REGISTERED_RING	(1U << 4)
 #define IORING_ENTER_ABS_TIMER		(1U << 5)
+#define IORING_ENTER_NO_IOWAIT		(1U << 7)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success
@@ -554,6 +555,7 @@ struct io_uring_params {
 #define IORING_FEAT_REG_REG_RING	(1U << 13)
 #define IORING_FEAT_RECVSEND_BUNDLE	(1U << 14)
 #define IORING_FEAT_MIN_TIMEOUT		(1U << 15)
+#define IORING_FEAT_NO_IOWAIT		(1U << 17)
 
 /*
  * io_uring_register(2) opcodes and arguments
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 09551e3907f9..630b306a849f 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2532,8 +2532,17 @@ static int io_cqring_schedule_timeout(struct io_wait_queue *iowq,
 	return READ_ONCE(iowq->hit_timeout) ? -ETIME : 0;
 }
 
+struct ext_arg {
+	size_t argsz;
+	struct __kernel_timespec __user *ts;
+	const sigset_t __user *sig;
+	ktime_t min_time;
+	bool iowait;
+};
+
 static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 				     struct io_wait_queue *iowq,
+				     struct ext_arg *ext_arg,
 				     ktime_t start_time)
 {
 	int ret = 0;
@@ -2543,7 +2552,7 @@ static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 	 * can take into account that the task is waiting for IO - turns out
 	 * to be important for low QD IO.
 	 */
-	if (current_pending_io())
+	if (ext_arg->iowait && current_pending_io())
 		current->in_iowait = 1;
 	if (iowq->timeout != KTIME_MAX || iowq->min_timeout)
 		ret = io_cqring_schedule_timeout(iowq, ctx->clockid, start_time);
@@ -2556,6 +2565,7 @@ static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 /* If this returns > 0, the caller should retry */
 static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 					  struct io_wait_queue *iowq,
+					  struct ext_arg *ext_arg,
 					  ktime_t start_time)
 {
 	if (unlikely(READ_ONCE(ctx->check_cq)))
@@ -2569,16 +2579,9 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 	if (unlikely(io_should_wake(iowq)))
 		return 0;
 
-	return __io_cqring_wait_schedule(ctx, iowq, start_time);
+	return __io_cqring_wait_schedule(ctx, iowq, ext_arg, start_time);
 }
 
-struct ext_arg {
-	size_t argsz;
-	struct __kernel_timespec __user *ts;
-	const sigset_t __user *sig;
-	ktime_t min_time;
-};
-
 /*
  * Wait until events become available, if we don't already have some. The
  * application must reap them itself, as they reside on the shared cq ring.
@@ -2660,7 +2663,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
 							TASK_INTERRUPTIBLE);
 		}
 
-		ret = io_cqring_wait_schedule(ctx, &iowq, start_time);
+		ret = io_cqring_wait_schedule(ctx, &iowq, ext_arg, start_time);
 		__set_current_state(TASK_RUNNING);
 		atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
 
@@ -3363,6 +3366,8 @@ static int io_get_ext_arg(unsigned flags, const void __user *argp,
 {
 	struct io_uring_getevents_arg arg;
 
+	ext_arg->iowait = !(flags & IORING_ENTER_NO_IOWAIT);
+
 	/*
 	 * If EXT_ARG isn't set, then we have no timespec and the argp pointer
 	 * is just a pointer to the sigset_t.
@@ -3399,7 +3404,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
 			       IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG |
 			       IORING_ENTER_REGISTERED_RING |
-			       IORING_ENTER_ABS_TIMER)))
+			       IORING_ENTER_ABS_TIMER |
+			       IORING_ENTER_NO_IOWAIT)))
 		return -EINVAL;
 
 	/*
@@ -3786,7 +3792,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 			IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
 			IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP |
 			IORING_FEAT_LINKED_FILE | IORING_FEAT_REG_REG_RING |
-			IORING_FEAT_RECVSEND_BUNDLE | IORING_FEAT_MIN_TIMEOUT;
+			IORING_FEAT_RECVSEND_BUNDLE | IORING_FEAT_MIN_TIMEOUT |
+			IORING_FEAT_NO_IOWAIT;
 
 	if (copy_to_user(params, p, sizeof(*p))) {
 		ret = -EFAULT;
-- 
2.55.0


  reply	other threads:[~2026-11-21 21:31 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-21 21:31 [PATCH 6.12.y 0/9] io_uring fixes for 6.12-stable Jens Axboe
2026-11-21 21:31 ` Jens Axboe [this message]
2026-11-21 21:31 ` [PATCH 6.12.y 2/9] io_uring/napi: don't end the single NAPI busy poll early on need_resched() Jens Axboe
2026-11-21 21:31 ` [PATCH 6.12.y 3/9] io_uring: fail soft links on negative IOU_COMPLETE results Jens Axboe
2026-11-21 21:31 ` [PATCH 6.12.y 4/9] io_uring/futex: fail soft links when cancelling a wait Jens Axboe
2026-11-21 21:31 ` [PATCH 6.12.y 5/9] io_uring/rw: fail soft links on IOPOLL short or error IO Jens Axboe
2026-11-21 21:31 ` [PATCH 6.12.y 6/9] io_uring/timeout: don't rearm a multishot timeout on cancel Jens Axboe
2026-11-21 21:31 ` [PATCH 6.12.y 7/9] io_uring/rsrc: keep the old file when a file update fails Jens Axboe
2026-11-21 21:31 ` [PATCH 6.12.y 8/9] io_uring/kbuf: initialize arg->out_len from arg->max_len in io_buffers_select() Jens Axboe
2026-11-21 21:31 ` [PATCH 6.12.y 9/9] io_uring/io-wq: apply the current cpuset to new workers Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261121213121.1789042-2-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).