On Fri, Jun 12, 2020 at 11:27:21AM +0200, Thomas Gleixner wrote:
> "Paul E. McKenney" writes:
> > +static __always_inline bool rcu_needs_irq_enter(void)
> > +{
> > + return !IS_ENABLED(CONFIG_TINY_RCU) &&
> > + (context_tracking_enabled_cpu(smp_processor_id()) ||
> >
Andy Lutomirski writes:
>
> This is saying we were idle and __rcu_is_watching() correctly returned
> false. We got sysvec_apic_timer_interrupt(), which did
> rcu_irq_enter() and then turned on IRQs for softirq processing. Then
> we got sysvec_call_function_single() inside that, and
>
"Paul E. McKenney" writes:
> +static __always_inline bool rcu_needs_irq_enter(void)
> +{
> + return !IS_ENABLED(CONFIG_TINY_RCU) &&
> + (context_tracking_enabled_cpu(smp_processor_id()) ||
> is_idle_task(current));
This reintroduces the #PF problem which started the whole
On Thu, Jun 11, 2020 at 4:53 PM Paul E. McKenney wrote:
>
> RCU needs to detect when one if its interrupt handlers interrupted an idle
> state, where an idle state is either the idle loop itself or nohz_full
> userspace execution. When a CPU has been interrupted from one of these
> idle states,
On Thu, Jun 11, 2020 at 04:53:05PM -0700, Paul E. McKenney wrote:
> RCU needs to detect when one if its interrupt handlers interrupted an idle
> state, where an idle state is either the idle loop itself or nohz_full
> userspace execution. When a CPU has been interrupted from one of these
> idle
RCU needs to detect when one if its interrupt handlers interrupted an idle
state, where an idle state is either the idle loop itself or nohz_full
userspace execution. When a CPU has been interrupted from one of these
idle states, RCU can report a quiescent state, helping the current grace
period
6 matches
Mail list logo
