On Wed, Jun 11, 2025 at 09:16:05AM -0700, Paul E. McKenney wrote:
> On Wed, Jun 11, 2025 at 09:05:06AM -0700, Boqun Feng wrote:
> > On Mon, Jun 09, 2025 at 02:01:24PM -0400, Joel Fernandes wrote:
> > > During rcu_read_unlock_special(), if this happens during irq_exit(), we
> > > can lockup if an IPI is issued. This is because the IPI itself triggers
> > > the irq_exit() path causing a recursive lock up.
> > >
> > > This is precisely what Xiongfeng found when invoking a BPF program on
> > > the trace_tick_stop() tracepoint As shown in the trace below. Fix by
> > > using context-tracking to tell us if we're still in an IRQ.
> > > context-tracking keeps track of the IRQ until after the tracepoint, so
> > > it cures the issues.
> > >
> > > irq_exit()
> > > __irq_exit_rcu()
> > > /* in_hardirq() returns false after this */
> > > preempt_count_sub(HARDIRQ_OFFSET)
> > > tick_irq_exit()
> >
> > @Frederic, while we are at it, what's the purpose of in_hardirq() in
> > tick_irq_exit()? For nested interrupt detection?
>
> If you are talking about the comment, these sorts of comments help
> people reading the code, the point being that some common-code function
> that invokes in_hardirq() after that point will get the wrong answer
> from it. The context-tracking code does the same for whether or not
The thing is that tick_irq_exit() is supposed to be only called in
irq_exit() IIUC (given its name), and so without nested interrupts,
in_hardirq() will also give the wrong answer.
Regards,
Boqun
> RCU is watching.
>
> Thanx, Paul
>
> > Regards,
> > Boqun
> >
> > > 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);
> > >
> > > A simple reproducer can also be obtained by doing the following in
> > > tick_irq_exit(). It will hang on boot without the patch:
> > >
> > > static inline void tick_irq_exit(void)
> > > {
> > > + rcu_read_lock();
> > > + WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, true);
> > > + rcu_read_unlock();
> > > +
> > >
> > > While at it, add some comments to this code.
> > >
> > > Reported-by: Xiongfeng Wang <wangxiongfe...@huawei.com>
> > > Closes:
> > > https://lore.kernel.org/all/9acd5f9f-6732-7701-6880-4b51190aa...@huawei.com/
> > > Tested-by: Xiongfeng Wang <wangxiongfe...@huawei.com>
> > > Signed-off-by: Joel Fernandes <joelagn...@nvidia.com>
> > [...]
>
