From: Matt Fleming <matt@readmodwrite.com>
To: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Tejun Heo <tj@kernel.org>, Andrea Righi <arighi@nvidia.com>,
sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org,
kernel-team@cloudflare.com
Subject: Re: sched_ext/lavd hard lockup in old call_rcu_tasks_generic needadjust path
Date: Tue, 16 Jun 2026 11:56:19 +0100 [thread overview]
Message-ID: <ajErr_GEejCD7n47@matt-Precision-5490> (raw)
In-Reply-To: <3bbd4298-eb01-4784-bee5-caab3d3647b9@paulmck-laptop>
On Fri, Jun 12, 2026 at 07:00:31AM -0700, Paul E. McKenney wrote:
>
> Huh. Looks like I did not implement RCU Tasks Trace in terms of SRCU
> any time too soon. But there is also RCU Tasks and RCU Tasks Rude.
>
> If we don't backport the SRCU patches, then the obvious alternative is
> for call_rcu_tasks*() to defer to IRQ work when invoked with interrupts
> disabled. Or is there a better way?
What about something like this?
----8<----
From 6b2dc5002f3413f4f89eb1735259d065b7003a52 Mon Sep 17 00:00:00 2001
From: Matt Fleming <mfleming@cloudflare.com>
Date: Mon, 15 Jun 2026 11:19:43 +0100
Subject: [PATCH] rcu-tasks: Defer callback queue adjustment to irq_work
call_rcu_tasks_generic() can run from BPF task-storage teardown while
sched_ext still holds rq->lock. The RCU Tasks kthread can concurrently
hold cbs_gbl_lock while printing under it, then wake a task on the same
rq while the caller waits for cbs_gbl_lock.
Queue the adjustment through irq_work instead. This keeps callback
enqueueing synchronous while moving cbs_gbl_lock acquisition out of the
caller context.
Signed-off-by: Matt Fleming <mfleming@cloudflare.com>
---
kernel/rcu/tasks.h | 33 +++++++++++++++++++++++----------
1 file changed, 23 insertions(+), 10 deletions(-)
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 2dc044fd126e..92aead9fc200 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -104,6 +104,7 @@ struct rcu_tasks {
unsigned long n_ipis;
unsigned long n_ipis_fails;
struct task_struct *kthread_ptr;
+ struct irq_work cbs_adjust_irq_work;
unsigned long lazy_jiffies;
rcu_tasks_gp_func_t gp_func;
pregp_func_t pregp_func;
@@ -129,6 +130,7 @@ struct rcu_tasks {
};
static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp);
+static void call_rcu_tasks_iw_adjust(struct irq_work *iwp);
#define DEFINE_RCU_TASKS(rt_name, gp, call, n) \
static DEFINE_PER_CPU(struct rcu_tasks_percpu, rt_name ## __percpu) = { \
@@ -144,6 +146,7 @@ static struct rcu_tasks rt_name = \
.call_func = call, \
.wait_state = TASK_UNINTERRUPTIBLE, \
.rtpcpu = &rt_name ## __percpu, \
+ .cbs_adjust_irq_work = IRQ_WORK_INIT_HARD(call_rcu_tasks_iw_adjust), \
.lazy_jiffies = DIV_ROUND_UP(HZ, 4), \
.name = n, \
.percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS), \
@@ -342,6 +345,24 @@ static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp)
rcuwait_wake_up(&rtp->cbs_wait);
}
+static void call_rcu_tasks_iw_adjust(struct irq_work *iwp)
+{
+ unsigned long flags;
+ bool expanded = false;
+ struct rcu_tasks *rtp = container_of(iwp, struct rcu_tasks, cbs_adjust_irq_work);
+
+ raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
+ if (rtp->percpu_enqueue_lim != rcu_task_cpu_ids) {
+ WRITE_ONCE(rtp->percpu_enqueue_shift, 0);
+ WRITE_ONCE(rtp->percpu_dequeue_lim, rcu_task_cpu_ids);
+ smp_store_release(&rtp->percpu_enqueue_lim, rcu_task_cpu_ids);
+ expanded = true;
+ }
+ raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
+ if (expanded)
+ pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name);
+}
+
// Enqueue a callback for the specified flavor of Tasks RCU.
static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
struct rcu_tasks *rtp)
@@ -389,16 +410,8 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
rtpcp->urgent_gp = 3;
rcu_segcblist_enqueue(&rtpcp->cblist, rhp);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
- if (unlikely(needadjust)) {
- raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
- if (rtp->percpu_enqueue_lim != rcu_task_cpu_ids) {
- WRITE_ONCE(rtp->percpu_enqueue_shift, 0);
- WRITE_ONCE(rtp->percpu_dequeue_lim, rcu_task_cpu_ids);
- smp_store_release(&rtp->percpu_enqueue_lim, rcu_task_cpu_ids);
- pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name);
- }
- raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
- }
+ if (unlikely(needadjust))
+ irq_work_queue(&rtp->cbs_adjust_irq_work);
rcu_read_unlock();
/* We can't create the thread unless interrupts are enabled. */
if (needwake && READ_ONCE(rtp->kthread_ptr))
--
2.43.0
next prev parent reply other threads:[~2026-06-16 10:56 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-09 10:47 sched_ext/lavd hard lockup in old call_rcu_tasks_generic needadjust path Matt Fleming
2026-06-09 11:23 ` Paul E. McKenney
2026-06-11 13:02 ` Matt Fleming
2026-06-11 13:45 ` Paul E. McKenney
2026-06-12 10:55 ` Matt Fleming
2026-06-12 14:00 ` Paul E. McKenney
2026-06-16 10:56 ` Matt Fleming [this message]
2026-06-17 3:24 ` Paul E. McKenney
2026-06-18 6:56 ` Matt Fleming
2026-06-18 15:55 ` Paul E. McKenney
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=ajErr_GEejCD7n47@matt-Precision-5490 \
--to=matt@readmodwrite.com \
--cc=arighi@nvidia.com \
--cc=kernel-team@cloudflare.com \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@kernel.org \
--cc=sched-ext@lists.linux.dev \
--cc=tj@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