From: Jens Axboe <axboe@kernel.dk>
To: stable@vger.kernel.org
Subject: [PATCH 6.6.y 08/19] io_uring/sqpoll: manage task_work privately
Date: Sat, 21 Nov 2026 21:30:38 +0000 [thread overview]
Message-ID: <20261121213049.1788332-9-axboe@kernel.dk> (raw)
In-Reply-To: <20261121213049.1788332-1-axboe@kernel.dk>
Commit af5d68f8892f8ee8f137648b79ceb2abc153a19b upstream.
Decouple from task_work running, and cap the number of entries we process
at the time. If we exceed that number, push remaining entries to a retry
list that we'll process first next time.
We cap the number of entries to process at 8, which is fairly random.
We just want to get enough per-ctx batching here, while not processing
endlessly.
Since we manually run PF_IO_WORKER related task_work anyway as the task
never exits to userspace, with this we no longer need to add an actual
task_work item to the per-process list.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
[axboe: 6.6 runs normal task_work in LIFO order, so don't reverse the
list in tctx_task_work_run(), and its trace_io_uring_task_work_run()
still takes the 'loops' argument. Run the retry_list in io_sq_thread()
before the IO_SQ_THREAD_EXITING marking that 6.6 has]
---
io_uring/io_uring.c | 42 +++++++++++++++++++++++++++++++++---------
io_uring/io_uring.h | 24 ++++++++++++++++++------
io_uring/sqpoll.c | 29 ++++++++++++++++++++++++++++-
3 files changed, 79 insertions(+), 16 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ddae460e06c0..3fd27002f4f7 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1197,7 +1197,14 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts)
percpu_ref_put(&ctx->refs);
}
-static void handle_tw_list(struct llist_node *node, unsigned int *count)
+/*
+ * Run queued task_work, returning the number of entries processed in *count.
+ * If more entries than max_entries are available, stop processing once this
+ * is reached and return the rest of the list.
+ */
+struct llist_node *io_handle_tw_list(struct llist_node *node,
+ unsigned int *count,
+ unsigned int max_entries)
{
struct io_ring_ctx *ctx = NULL;
struct io_tw_state ts = { };
@@ -1226,9 +1233,10 @@ static void handle_tw_list(struct llist_node *node, unsigned int *count)
ctx = NULL;
cond_resched();
}
- } while (node);
+ } while (node && *count < max_entries);
ctx_flush_and_put(ctx, &ts);
+ return node;
}
/**
@@ -1274,27 +1282,39 @@ static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
}
}
-void tctx_task_work(struct callback_head *cb)
+struct llist_node *tctx_task_work_run(struct io_uring_task *tctx,
+ unsigned int max_entries,
+ unsigned int *count)
{
- struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
- task_work);
struct llist_node *node;
- unsigned int count = 0;
if (unlikely(current->flags & PF_EXITING)) {
io_fallback_tw(tctx, true);
- return;
+ return NULL;
}
node = llist_del_all(&tctx->task_list);
if (node)
- handle_tw_list(node, &count);
+ node = io_handle_tw_list(node, count, max_entries);
/* relaxed read is enough as only the task itself sets ->in_cancel */
if (unlikely(atomic_read(&tctx->in_cancel)))
io_uring_drop_tctx_refs(current);
- trace_io_uring_task_work_run(tctx, count, 1);
+ trace_io_uring_task_work_run(tctx, *count, 1);
+ return node;
+}
+
+void tctx_task_work(struct callback_head *cb)
+{
+ struct io_uring_task *tctx;
+ struct llist_node *ret;
+ unsigned int count = 0;
+
+ tctx = container_of(cb, struct io_uring_task, task_work);
+ ret = tctx_task_work_run(tctx, UINT_MAX, &count);
+ /* can't happen */
+ WARN_ON_ONCE(ret);
}
static void io_poll_wq_wake_rcu(struct rcu_head *rcu)
@@ -1388,6 +1408,10 @@ static void io_req_normal_work_add(struct io_kiocb *req)
if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
+ /* SQPOLL doesn't need the task_work added, it'll run it itself */
+ if (ctx->flags & IORING_SETUP_SQPOLL)
+ return;
+
if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method)))
return;
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index a3c97ffb4d14..0d749588ab21 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -77,6 +77,8 @@ void io_req_task_queue(struct io_kiocb *req);
void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts);
void io_req_task_queue_fail(struct io_kiocb *req, int ret);
void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts);
+struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries);
+struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
void tctx_task_work(struct callback_head *cb);
__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
int io_uring_alloc_task_context(struct task_struct *task,
@@ -338,6 +340,8 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
static inline int io_run_task_work(void)
{
+ bool ret = false;
+
/*
* Always check-and-clear the task_work notification signal. With how
* signaling works for task_work, we can find it set with nothing to
@@ -349,18 +353,26 @@ static inline int io_run_task_work(void)
* PF_IO_WORKER never returns to userspace, so check here if we have
* notify work that needs processing.
*/
- if (current->flags & PF_IO_WORKER &&
- test_thread_flag(TIF_NOTIFY_RESUME)) {
- __set_current_state(TASK_RUNNING);
- resume_user_mode_work(NULL);
+ if (current->flags & PF_IO_WORKER) {
+ if (test_thread_flag(TIF_NOTIFY_RESUME)) {
+ __set_current_state(TASK_RUNNING);
+ resume_user_mode_work(NULL);
+ }
+ if (current->io_uring) {
+ unsigned int count = 0;
+
+ tctx_task_work_run(current->io_uring, UINT_MAX, &count);
+ if (count)
+ ret = true;
+ }
}
if (task_work_pending(current)) {
__set_current_state(TASK_RUNNING);
task_work_run();
- return 1;
+ ret = true;
}
- return 0;
+ return ret;
}
static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 75065de8d7d3..716cb3cc7e2c 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -19,6 +19,7 @@
#include "sqpoll.h"
#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
+#define IORING_TW_CAP_ENTRIES_VALUE 8
enum {
IO_SQ_THREAD_SHOULD_STOP = 0,
@@ -238,8 +239,31 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
}
+/*
+ * Run task_work, processing the retry_list first. The retry_list holds
+ * entries that we passed on in the previous run, if we had more task_work
+ * than we were asked to process. Newly queued task_work isn't run until the
+ * retry list has been fully processed.
+ */
+static unsigned int io_sq_tw(struct llist_node **retry_list, int max_entries)
+{
+ struct io_uring_task *tctx = current->io_uring;
+ unsigned int count = 0;
+
+ if (*retry_list) {
+ *retry_list = io_handle_tw_list(*retry_list, &count, max_entries);
+ if (count >= max_entries)
+ return count;
+ max_entries -= count;
+ }
+
+ *retry_list = tctx_task_work_run(tctx, max_entries, &count);
+ return count;
+}
+
static int io_sq_thread(void *data)
{
+ struct llist_node *retry_list = NULL;
struct io_sq_data *sqd = data;
struct io_ring_ctx *ctx;
unsigned long timeout = 0;
@@ -284,7 +308,7 @@ static int io_sq_thread(void *data)
if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
sqt_spin = true;
}
- if (io_run_task_work())
+ if (io_sq_tw(&retry_list, IORING_TW_CAP_ENTRIES_VALUE))
sqt_spin = true;
if (sqt_spin || !time_after(jiffies, timeout)) {
@@ -346,6 +370,9 @@ static int io_sq_thread(void *data)
timeout = jiffies + sqd->sq_thread_idle;
}
+ if (retry_list)
+ io_sq_tw(&retry_list, UINT_MAX);
+
/*
* Cancelation drops sqd->lock while it waits, and a ring could attach
* to a thread that is on its way out. A fatal signal doesn't set the
--
2.55.0
next prev parent reply other threads:[~2026-11-21 21:31 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-21 21:30 [PATCH 6.6.y 00/19] io_uring fixes for 6.6-stable Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 01/19] io_uring: enable toggle of iowait usage when waiting on CQEs Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 02/19] io_uring: fail soft links on negative IOU_COMPLETE results Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 03/19] io_uring/rw: fail soft links on IOPOLL short or error IO Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 04/19] io_uring/timeout: don't rearm a multishot timeout on cancel Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 05/19] io_uring/rsrc: keep the old file when a file update fails Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 06/19] io_uring: cleanup handle_tw_list() calling convention Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 07/19] io_uring: pass in counter to handle_tw_list() rather than return it Jens Axboe
2026-11-21 21:30 ` Jens Axboe [this message]
2026-11-21 21:30 ` [PATCH 6.6.y 09/19] io_uring: wake SQPOLL task when task_work is added to an empty queue Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 10/19] io_uring/sqpoll: use the correct check for pending task_work Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 11/19] io_uring/sqpoll: early exit thread if task_context wasn't allocated Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 12/19] io_uring/sqpoll: ensure that normal task_work is also run timely Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 13/19] io_uring: signal SQPOLL task_work with TWA_SIGNAL_NO_IPI Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 14/19] io_uring/sqpoll: ensure task state is TASK_RUNNING when running task_work Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 15/19] io_uring: don't touch sqd->thread off tw add Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 16/19] io_uring/sqpoll: zero sqd->thread on tctx errors Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 17/19] io_uring/sqpoll: Increase task_work submission batch size Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 18/19] io_uring: fix task_work add use-after-free with SQPOLL Jens Axboe
2026-11-21 21:30 ` [PATCH 6.6.y 19/19] io_uring/sqpoll: do the return-to-userspace work in the SQPOLL thread 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=20261121213049.1788332-9-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