On Tue, Jun 03, 2025 at 03:22:42PM -0400, Joel Fernandes wrote:
>
>
> On 6/3/2025 3:03 PM, Joel Fernandes wrote:
> >
> >
> > On 6/3/2025 2:59 PM, Joel Fernandes wrote:
> >> On Fri, May 30, 2025 at 09:55:45AM +0800, Xiongfeng Wang wrote:
> >>> Hi Joel,
> >>>
> >>> On 2025/5/29 0:30, Joel Fernandes wrote:
> >>>> On Wed, May 21, 2025 at 5:43 AM Xiongfeng Wang
> >>>> <wangxiongfe...@huawei.com> wrote:
> >>>>>
> >>>>> Hi RCU experts,
> >>>>>
> >>>>> When I ran syskaller in Linux 6.6 with CONFIG_PREEMPT_RCU enabled, I got
> >>>>> the following soft lockup. The Calltrace is too long. I put it in the
> >>>>> end.
> >>>>> The issue can also be reproduced in the latest kernel.
> >>>>>
> >>>>> The issue is as follows. CPU3 is waiting for a spin_lock, which is got
> >>>>> by CPU1.
> >>>>> But CPU1 stuck in the following dead loop.
> >>>>>
> >>>>> irq_exit()
> >>>>> __irq_exit_rcu()
> >>>>> /* in_hardirq() returns false after this */
> >>>>> preempt_count_sub(HARDIRQ_OFFSET)
> >>>>> tick_irq_exit()
> >>>>> tick_nohz_irq_exit()
> >>>>> tick_nohz_stop_sched_tick()
> >>>>> trace_tick_stop() /* a bpf prog is hooked on this trace
> >>>>> point */
> >>>>> __bpf_trace_tick_stop()
> >>>>> bpf_trace_run2()
> >>>>> rcu_read_unlock_special()
> >>>>> /* will send a IPI to itself */
> >>>>> irq_work_queue_on(&rdp->defer_qs_iw,
> >>>>> rdp->cpu);
> >>>>>
> >>>>> /* after interrupt is enabled again, the irq_work is called */
> >>>>> asm_sysvec_irq_work()
> >>>>> sysvec_irq_work()
> >>>>> irq_exit() /* after handled the irq_work, we again enter into
> >>>>> irq_exit() */
> >>>>> __irq_exit_rcu()
> >>>>> ...skip...
> >>>>> /* we queue a irq_work again, and enter a dead loop */
> >>>>> irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu);
> >>>>
The following is a candidate fix (among other fixes being
considered/discussed). The change is to check if context tracking thinks
we're in IRQ and if so, avoid the irq_work. IMO, this should be rare enough
that it shouldn't be an issue and it is dangerous to self-IPI consistently
while we're exiting an IRQ anyway.
Thoughts? Xiongfeng, do you want to try it?
Btw, I could easily reproduce it as a boot hang by doing:
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -638,6 +638,10 @@ void irq_enter(void)
static inline void tick_irq_exit(void)
{
+ rcu_read_lock();
+ WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, true);
+ rcu_read_unlock();
+
#ifdef CONFIG_NO_HZ_COMMON
int cpu = smp_processor_id();
---8<-----------------------
From: Joel Fernandes <joelagn...@nvidia.com>
Subject: [PATCH] Do not schedule irq_work when IRQ is exiting
Signed-off-by: Joel Fernandes <joelagn...@nvidia.com>
---
include/linux/context_tracking_irq.h | 2 ++
kernel/context_tracking.c | 12 ++++++++++++
kernel/rcu/tree_plugin.h | 3 ++-
3 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/include/linux/context_tracking_irq.h
b/include/linux/context_tracking_irq.h
index 197916ee91a4..35a5ad971514 100644
--- a/include/linux/context_tracking_irq.h
+++ b/include/linux/context_tracking_irq.h
@@ -9,6 +9,7 @@ void ct_irq_enter_irqson(void);
void ct_irq_exit_irqson(void);
void ct_nmi_enter(void);
void ct_nmi_exit(void);
+bool ct_in_irq(void);
#else
static __always_inline void ct_irq_enter(void) { }
static __always_inline void ct_irq_exit(void) { }
@@ -16,6 +17,7 @@ static inline void ct_irq_enter_irqson(void) { }
static inline void ct_irq_exit_irqson(void) { }
static __always_inline void ct_nmi_enter(void) { }
static __always_inline void ct_nmi_exit(void) { }
+static inline bool ct_in_irq(void) { return false; }
#endif
#endif
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index fb5be6e9b423..8e8055cf04af 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -392,6 +392,18 @@ noinstr void ct_irq_exit(void)
ct_nmi_exit();
}
+/**
+ * ct_in_irq - check if CPU is currently in a tracked IRQ context.
+ *
+ * Returns true if ct_irq_enter() has been called and ct_irq_exit()
+ * has not yet been called. This indicates the CPU is currently
+ * processing an interrupt.
+ */
+bool ct_in_irq(void)
+{
+ return ct_nmi_nesting() != 0;
+}
+
/*
* Wrapper for ct_irq_enter() where interrupts are enabled.
*
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3c0bbbbb686f..a3eebd4c841e 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -673,7 +673,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
set_tsk_need_resched(current);
set_preempt_need_resched();
if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
- expboost && !rdp->defer_qs_iw_pending &&
cpu_online(rdp->cpu)) {
+ expboost && !rdp->defer_qs_iw_pending &&
cpu_online(rdp->cpu) &&
+ !ct_in_irq()) {
// Get scheduler to re-evaluate and call hooks.
// If !IRQ_WORK, FQS scan will eventually IPI.
if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)
&&
--
2.34.1
