linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] intel_pstate: Do not skip samples partially
@ 2016-03-10 22:45 Rafael J. Wysocki
  2016-03-10 22:53 ` Srinivas Pandruvada
  0 siblings, 1 reply; 2+ messages in thread
From: Rafael J. Wysocki @ 2016-03-10 22:45 UTC (permalink / raw)
  To: Srinivas Pandruvada, Linux PM list
  Cc: Linux Kernel Mailing List, Philippe Longepe

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

If the current value of MPERF or the current value of TSC is the
same as the previous one, respectively, intel_pstate_sample() bails
out early and skips the sample.

However, intel_pstate_adjust_busy_pstate() is still called in that
case which is not correct, so modify intel_pstate_sample() to
return a bool value indicating whether or not the sample has been
taken and use it to decide whether or not to call
intel_pstate_adjust_busy_pstate().

While at it, remove redundant parentheses from the MPERF/TSC
check in intel_pstate_sample().

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---

On top of my linux-next branch.

---
 drivers/cpufreq/intel_pstate.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

Index: linux-pm/drivers/cpufreq/intel_pstate.c
===================================================================
--- linux-pm.orig/drivers/cpufreq/intel_pstate.c
+++ linux-pm/drivers/cpufreq/intel_pstate.c
@@ -890,7 +890,7 @@ static inline void intel_pstate_calc_bus
 	sample->core_pct_busy = (int32_t)core_pct;
 }
 
-static inline void intel_pstate_sample(struct cpudata *cpu, u64 time)
+static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
 {
 	u64 aperf, mperf;
 	unsigned long flags;
@@ -900,9 +900,9 @@ static inline void intel_pstate_sample(s
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
 	tsc = rdtsc();
-	if ((cpu->prev_mperf == mperf) || (cpu->prev_tsc == tsc)) {
+	if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) {
 		local_irq_restore(flags);
-		return;
+		return false;
 	}
 	local_irq_restore(flags);
 
@@ -920,6 +920,7 @@ static inline void intel_pstate_sample(s
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
 	cpu->prev_tsc = tsc;
+	return true;
 }
 
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
@@ -1026,8 +1027,9 @@ static void intel_pstate_update_util(str
 	u64 delta_ns = time - cpu->sample.time;
 
 	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
-		intel_pstate_sample(cpu, time);
-		if (!hwp_active)
+		bool sample_taken = intel_pstate_sample(cpu, time);
+
+		if (sample_taken && !hwp_active)
 			intel_pstate_adjust_busy_pstate(cpu);
 	}
 }


^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [PATCH] intel_pstate: Do not skip samples partially
  2016-03-10 22:45 [PATCH] intel_pstate: Do not skip samples partially Rafael J. Wysocki
@ 2016-03-10 22:53 ` Srinivas Pandruvada
  0 siblings, 0 replies; 2+ messages in thread
From: Srinivas Pandruvada @ 2016-03-10 22:53 UTC (permalink / raw)
  To: Rafael J. Wysocki, Linux PM list
  Cc: Linux Kernel Mailing List, Philippe Longepe

On Thu, 2016-03-10 at 23:45 +0100, Rafael J. Wysocki wrote:
> From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> 
> If the current value of MPERF or the current value of TSC is the
> same as the previous one, respectively, intel_pstate_sample() bails
> out early and skips the sample.
> 
> However, intel_pstate_adjust_busy_pstate() is still called in that
> case which is not correct, so modify intel_pstate_sample() to
> return a bool value indicating whether or not the sample has been
> taken and use it to decide whether or not to call
> intel_pstate_adjust_busy_pstate().
> 
> While at it, remove redundant parentheses from the MPERF/TSC
> check in intel_pstate_sample().
> 
> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> ---
> 
> On top of my linux-next branch.
> 
> ---
>  drivers/cpufreq/intel_pstate.c |   12 +++++++-----
>  1 file changed, 7 insertions(+), 5 deletions(-)
> 
> Index: linux-pm/drivers/cpufreq/intel_pstate.c
> ===================================================================
> --- linux-pm.orig/drivers/cpufreq/intel_pstate.c
> +++ linux-pm/drivers/cpufreq/intel_pstate.c
> @@ -890,7 +890,7 @@ static inline void intel_pstate_calc_bus
>  	sample->core_pct_busy = (int32_t)core_pct;
>  }
>  
> -static inline void intel_pstate_sample(struct cpudata *cpu, u64
> time)
> +static inline bool intel_pstate_sample(struct cpudata *cpu, u64
> time)
>  {
>  	u64 aperf, mperf;
>  	unsigned long flags;
> @@ -900,9 +900,9 @@ static inline void intel_pstate_sample(s
>  	rdmsrl(MSR_IA32_APERF, aperf);
>  	rdmsrl(MSR_IA32_MPERF, mperf);
>  	tsc = rdtsc();
> -	if ((cpu->prev_mperf == mperf) || (cpu->prev_tsc == tsc)) {
> +	if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) {
>  		local_irq_restore(flags);
> -		return;
> +		return false;
>  	}
>  	local_irq_restore(flags);
>  
> @@ -920,6 +920,7 @@ static inline void intel_pstate_sample(s
>  	cpu->prev_aperf = aperf;
>  	cpu->prev_mperf = mperf;
>  	cpu->prev_tsc = tsc;
> +	return true;
>  }
>  
>  static inline int32_t get_target_pstate_use_cpu_load(struct cpudata
> *cpu)
> @@ -1026,8 +1027,9 @@ static void intel_pstate_update_util(str
>  	u64 delta_ns = time - cpu->sample.time;
>  
>  	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
> -		intel_pstate_sample(cpu, time);
> -		if (!hwp_active)
> +		bool sample_taken = intel_pstate_sample(cpu, time);
> +
> +		if (sample_taken && !hwp_active)
>  			intel_pstate_adjust_busy_pstate(cpu);
>  	}
>  }
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pm"
> in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2016-03-10 22:55 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-03-10 22:45 [PATCH] intel_pstate: Do not skip samples partially Rafael J. Wysocki
2016-03-10 22:53 ` Srinivas Pandruvada

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).