On Mon, Nov 23, 2020 at 3:35 PM Peter Zijlstra <pet...@infradead.org> wrote:
>
> On Mon, Nov 23, 2020 at 02:54:47PM +0100, Rafael J. Wysocki wrote:
>
> > intel_idle_init_cstates_acpi() needs to be updated too as it doesn't
> > pick up the flags automatically.
>
> Ooh, it has two different state init routines :-/, sorry I missed that.
> See below.
>
> > It looks like CPUIDLE_FLAG_RCU_IDLE needs to be copied too.
>
> I might need more clue again; processor_idle() needs this because it
> calls into ACPI (acpi_idle_enter_bm()) for that BM crud. I didn't find
> anything like that here.
>
>
> ---
> Subject: intel_idle: Fix intel_idle() vs tracing
> From: Peter Zijlstra <pet...@infradead.org>
> Date: Fri Nov 20 11:28:35 CET 2020
>
> cpuidle->enter() callbacks should not call into tracing because RCU
> has already been disabled. Instead of doing the broadcast thing
> itself, simply advertise to the cpuidle core that those states stop
> the timer.
>
> Signed-off-by: Peter Zijlstra (Intel) <pet...@infradead.org>

Acked-by: Rafael J. Wysocki <rafael.j.wyso...@intel.com>

with a very minor nit below.

> ---
>  drivers/idle/intel_idle.c |   40 +++++++++++++++++++++++-----------------
>  1 file changed, 23 insertions(+), 17 deletions(-)
>
> --- a/drivers/idle/intel_idle.c
> +++ b/drivers/idle/intel_idle.c
> @@ -126,26 +126,9 @@ static __cpuidle int intel_idle(struct c
>         struct cpuidle_state *state = &drv->states[index];
>         unsigned long eax = flg2MWAIT(state->flags);
>         unsigned long ecx = 1; /* break on interrupt flag */
> -       bool tick;
> -
> -       if (!static_cpu_has(X86_FEATURE_ARAT)) {
> -               /*
> -                * Switch over to one-shot tick broadcast if the target 
> C-state
> -                * is deeper than C1.
> -                */
> -               if ((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) {
> -                       tick = true;
> -                       tick_broadcast_enter();
> -               } else {
> -                       tick = false;
> -               }
> -       }
>
>         mwait_idle_with_hints(eax, ecx);
>
> -       if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
> -               tick_broadcast_exit();
> -
>         return index;
>  }
>
> @@ -1227,6 +1210,23 @@ static bool __init intel_idle_acpi_cst_e
>         return false;
>  }
>
> +static bool __init intel_idle_state_needs_timer_stop(struct cpuidle_state 
> *state)
> +{
> +       unsigned long eax = flg2MWAIT(state->flags);
> +
> +       if (boot_cpu_has(X86_FEATURE_ARAT))
> +               return false;
> +
> +       /*
> +        * Switch over to one-shot tick broadcast if the target C-state
> +        * is deeper than C1.
> +        */
> +       if ((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK)
> +               return true;
> +
> +       return false;

The above can be written as

return !!((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK);

> +}
> +
>  static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
>  {
>         int cstate, limit = min_t(int, CPUIDLE_STATE_MAX, 
> acpi_state_table.count);
> @@ -1269,6 +1269,9 @@ static void __init intel_idle_init_cstat
>                 if (disabled_states_mask & BIT(cstate))
>                         state->flags |= CPUIDLE_FLAG_OFF;
>
> +               if (intel_idle_state_needs_timer_stop(state))
> +                       state->flags |= CPUIDLE_FLAG_TIMER_STOP;
> +
>                 state->enter = intel_idle;
>                 state->enter_s2idle = intel_idle_s2idle;
>         }
> @@ -1507,6 +1510,9 @@ static void __init intel_idle_init_cstat
>                      !(cpuidle_state_table[cstate].flags & 
> CPUIDLE_FLAG_ALWAYS_ENABLE)))
>                         drv->states[drv->state_count].flags |= 
> CPUIDLE_FLAG_OFF;
>
> +               if 
> (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count]))
> +                       drv->states[drv->state_count].flags |= 
> CPUIDLE_FLAG_TIMER_STOP;
> +
>                 drv->state_count++;
>         }
>

Reply via email to