* [PATCH] intel_idle: replace conditionals with static_cpu_has(X86_FEATURE_ARAT)
@ 2017-10-06 17:19 ` Jason Baron
2017-10-06 18:36 ` Jacob Pan
0 siblings, 1 reply; 4+ messages in thread
From: Jason Baron @ 2017-10-06 17:19 UTC (permalink / raw)
To: linux-pm, linux-kernel; +Cc: Jacob Pan, Len Brown, Rafael J. Wysocki
If the 'arat' cpu flag is set, then the conditionals in intel_idle() that
guard calling tick_broadcast_enter()/exit() will never be true. Use
static_cpu_has(X86_FEATURE_ARAT) to create a fast path to replace
the conditional.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/idle/intel_idle.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 5dc7ea4..5db5e31 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -913,8 +913,7 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
struct cpuidle_state *state = &drv->states[index];
unsigned long eax = flg2MWAIT(state->flags);
unsigned int cstate;
-
- cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) + 1;
+ bool uninitialized_var(tick);
/*
* NB: if CPUIDLE_FLAG_TLB_FLUSHED is set, this idle transition
@@ -923,12 +922,19 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
* useful with this knowledge.
*/
- if (!(lapic_timer_reliable_states & (1 << (cstate))))
- tick_broadcast_enter();
+ if (!static_cpu_has(X86_FEATURE_ARAT)) {
+ cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
+ MWAIT_CSTATE_MASK) + 1;
+ tick = false;
+ if (!(lapic_timer_reliable_states & (1 << (cstate)))) {
+ tick = true;
+ tick_broadcast_enter();
+ }
+ }
mwait_idle_with_hints(eax, ecx);
- if (!(lapic_timer_reliable_states & (1 << (cstate))))
+ if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
tick_broadcast_exit();
return index;
--
2.6.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH] intel_idle: replace conditionals with static_cpu_has(X86_FEATURE_ARAT)
2017-10-06 17:19 ` [PATCH] intel_idle: replace conditionals with static_cpu_has(X86_FEATURE_ARAT) Jason Baron
@ 2017-10-06 18:36 ` Jacob Pan
2017-10-06 18:41 ` Jason Baron
0 siblings, 1 reply; 4+ messages in thread
From: Jacob Pan @ 2017-10-06 18:36 UTC (permalink / raw)
To: Jason Baron; +Cc: linux-pm, linux-kernel, jacob.jun.pan
On Fri, 6 Oct 2017 13:19:45 -0400
Jason Baron <jbaron@akamai.com> wrote:
> If the 'arat' cpu flag is set, then the conditionals in intel_idle()
> that guard calling tick_broadcast_enter()/exit() will never be true.
> Use static_cpu_has(X86_FEATURE_ARAT) to create a fast path to replace
> the conditional.
>
> Signed-off-by: Jason Baron <jbaron@akamai.com>
> Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Cc: Len Brown <lenb@kernel.org>
> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> ---
> drivers/idle/intel_idle.c | 16 +++++++++++-----
> 1 file changed, 11 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
> index 5dc7ea4..5db5e31 100644
> --- a/drivers/idle/intel_idle.c
> +++ b/drivers/idle/intel_idle.c
> @@ -913,8 +913,7 @@ static __cpuidle int intel_idle(struct
> cpuidle_device *dev, struct cpuidle_state *state =
> &drv->states[index]; unsigned long eax = flg2MWAIT(state->flags);
> unsigned int cstate;
> -
> - cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
> MWAIT_CSTATE_MASK) + 1;
> + bool uninitialized_var(tick);
>
> /*
> * NB: if CPUIDLE_FLAG_TLB_FLUSHED is set, this idle
> transition @@ -923,12 +922,19 @@ static __cpuidle int
> intel_idle(struct cpuidle_device *dev,
> * useful with this knowledge.
> */
>
> - if (!(lapic_timer_reliable_states & (1 << (cstate))))
> - tick_broadcast_enter();
> + if (!static_cpu_has(X86_FEATURE_ARAT)) {
> + cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
> + MWAIT_CSTATE_MASK) + 1;
> + tick = false;
> + if (!(lapic_timer_reliable_states & (1 <<
> (cstate)))) {
> + tick = true;
> + tick_broadcast_enter();
> + }
> + }
>
> mwait_idle_with_hints(eax, ecx);
>
> - if (!(lapic_timer_reliable_states & (1 << (cstate))))
> + if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
> tick_broadcast_exit();
>
> return index;
Seems better to have a function pointer set up at init time to select
whether we do tick_broadcast or not (two functions). There is no need to
check CPU feature on every entry.
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] intel_idle: replace conditionals with static_cpu_has(X86_FEATURE_ARAT)
2017-10-06 18:36 ` Jacob Pan
@ 2017-10-06 18:41 ` Jason Baron
2017-10-06 21:09 ` Jacob Pan
0 siblings, 1 reply; 4+ messages in thread
From: Jason Baron @ 2017-10-06 18:41 UTC (permalink / raw)
To: Jacob Pan; +Cc: linux-pm, linux-kernel
On 10/06/2017 02:36 PM, Jacob Pan wrote:
> On Fri, 6 Oct 2017 13:19:45 -0400
> Jason Baron <jbaron@akamai.com> wrote:
>
>> If the 'arat' cpu flag is set, then the conditionals in intel_idle()
>> that guard calling tick_broadcast_enter()/exit() will never be true.
>> Use static_cpu_has(X86_FEATURE_ARAT) to create a fast path to replace
>> the conditional.
>>
>> Signed-off-by: Jason Baron <jbaron@akamai.com>
>> Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
>> Cc: Len Brown <lenb@kernel.org>
>> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
>> ---
>> drivers/idle/intel_idle.c | 16 +++++++++++-----
>> 1 file changed, 11 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
>> index 5dc7ea4..5db5e31 100644
>> --- a/drivers/idle/intel_idle.c
>> +++ b/drivers/idle/intel_idle.c
>> @@ -913,8 +913,7 @@ static __cpuidle int intel_idle(struct
>> cpuidle_device *dev, struct cpuidle_state *state =
>> &drv->states[index]; unsigned long eax = flg2MWAIT(state->flags);
>> unsigned int cstate;
>> -
>> - cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
>> MWAIT_CSTATE_MASK) + 1;
>> + bool uninitialized_var(tick);
>>
>> /*
>> * NB: if CPUIDLE_FLAG_TLB_FLUSHED is set, this idle
>> transition @@ -923,12 +922,19 @@ static __cpuidle int
>> intel_idle(struct cpuidle_device *dev,
>> * useful with this knowledge.
>> */
>>
>> - if (!(lapic_timer_reliable_states & (1 << (cstate))))
>> - tick_broadcast_enter();
>> + if (!static_cpu_has(X86_FEATURE_ARAT)) {
>> + cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
>> + MWAIT_CSTATE_MASK) + 1;
>> + tick = false;
>> + if (!(lapic_timer_reliable_states & (1 <<
>> (cstate)))) {
>> + tick = true;
>> + tick_broadcast_enter();
>> + }
>> + }
>>
>> mwait_idle_with_hints(eax, ecx);
>>
>> - if (!(lapic_timer_reliable_states & (1 << (cstate))))
>> + if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
>> tick_broadcast_exit();
>>
>> return index;
>
> Seems better to have a function pointer set up at init time to select
> whether we do tick_broadcast or not (two functions). There is no need to
> check CPU feature on every entry.
>
Hi,
static_cpu_has() uses alternatives patching, so the cpu feature is not
tested on every entry. With the arat flag set you just have two nops in
the straight-line code path with this patch.
Thanks,
-Jason
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] intel_idle: replace conditionals with static_cpu_has(X86_FEATURE_ARAT)
2017-10-06 18:41 ` Jason Baron
@ 2017-10-06 21:09 ` Jacob Pan
0 siblings, 0 replies; 4+ messages in thread
From: Jacob Pan @ 2017-10-06 21:09 UTC (permalink / raw)
To: Jason Baron; +Cc: linux-pm, linux-kernel, jacob.jun.pan
On Fri, 6 Oct 2017 14:41:07 -0400
Jason Baron <jbaron@akamai.com> wrote:
> On 10/06/2017 02:36 PM, Jacob Pan wrote:
> > On Fri, 6 Oct 2017 13:19:45 -0400
> > Jason Baron <jbaron@akamai.com> wrote:
> >
> >> If the 'arat' cpu flag is set, then the conditionals in
> >> intel_idle() that guard calling tick_broadcast_enter()/exit() will
> >> never be true. Use static_cpu_has(X86_FEATURE_ARAT) to create a
> >> fast path to replace the conditional.
> >>
> >> Signed-off-by: Jason Baron <jbaron@akamai.com>
> >> Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
> >> Cc: Len Brown <lenb@kernel.org>
> >> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> >> ---
> >> drivers/idle/intel_idle.c | 16 +++++++++++-----
> >> 1 file changed, 11 insertions(+), 5 deletions(-)
> >>
> >> diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
> >> index 5dc7ea4..5db5e31 100644
> >> --- a/drivers/idle/intel_idle.c
> >> +++ b/drivers/idle/intel_idle.c
> >> @@ -913,8 +913,7 @@ static __cpuidle int intel_idle(struct
> >> cpuidle_device *dev, struct cpuidle_state *state =
> >> &drv->states[index]; unsigned long eax = flg2MWAIT(state->flags);
> >> unsigned int cstate;
> >> -
> >> - cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
> >> MWAIT_CSTATE_MASK) + 1;
> >> + bool uninitialized_var(tick);
> >>
> >> /*
> >> * NB: if CPUIDLE_FLAG_TLB_FLUSHED is set, this idle
> >> transition @@ -923,12 +922,19 @@ static __cpuidle int
> >> intel_idle(struct cpuidle_device *dev,
> >> * useful with this knowledge.
> >> */
> >>
> >> - if (!(lapic_timer_reliable_states & (1 << (cstate))))
> >> - tick_broadcast_enter();
> >> + if (!static_cpu_has(X86_FEATURE_ARAT)) {
> >> + cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
> >> + MWAIT_CSTATE_MASK) + 1;
> >> + tick = false;
> >> + if (!(lapic_timer_reliable_states & (1 <<
> >> (cstate)))) {
> >> + tick = true;
> >> + tick_broadcast_enter();
> >> + }
> >> + }
> >>
> >> mwait_idle_with_hints(eax, ecx);
> >>
> >> - if (!(lapic_timer_reliable_states & (1 << (cstate))))
> >> + if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
> >> tick_broadcast_exit();
> >>
> >> return index;
> >
> > Seems better to have a function pointer set up at init time to
> > select whether we do tick_broadcast or not (two functions). There
> > is no need to check CPU feature on every entry.
> >
>
> Hi,
>
> static_cpu_has() uses alternatives patching, so the cpu feature is not
> tested on every entry. With the arat flag set you just have two nops
> in the straight-line code path with this patch.
>
Thanks for explaining, i didn't know it was self modifying.
Acked-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2017-10-06 21:06 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <bug-109051-18156@https.bugzilla.kernel.org/>
2017-10-06 17:19 ` [PATCH] intel_idle: replace conditionals with static_cpu_has(X86_FEATURE_ARAT) Jason Baron
2017-10-06 18:36 ` Jacob Pan
2017-10-06 18:41 ` Jason Baron
2017-10-06 21:09 ` Jacob Pan
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).