| Message ID | 1393353337-19778-1-git-send-email-dirk.j.brandewie@intel.com (mailing list archive) |
|---|---|
| State | Accepted, archived |
| Headers | show |
On Tuesday, February 25, 2014 10:35:37 AM dirk.brandewie@gmail.com wrote: > From: Dirk Brandewie <dirk.j.brandewie@intel.com> > > Commit fcb6a15c2e Take core C0 time into account for core busy calculation. > > Introduced a regression on some processor SKUs supported by > intel_pstate. This was caused by the truncation caused by using > integer math to calculate core busy and C0 percentages. > > On a i7-4770K processor operating at 800Mhz going to 100% utilization > the percent busy of the CPU using integer math is 22% it actually is > 22.85%. This value scaled to the current frequency returned 97 which > the PID interpreted as no error and did not adjust the P state. > > Tested on i7-4770K, i7-2600, i5-3230M > > References: > https://lkml.org/lkml/2014/2/19/626 > https://bugzilla.kernel.org/show_bug.cgi?id=70941 > > Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Queued up as a fix for 3.14. Thanks! > --- > drivers/cpufreq/intel_pstate.c | 28 ++++++++++++++++++---------- > 1 file changed, 18 insertions(+), 10 deletions(-) > > diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c > index e908161..2cd36b9 100644 > --- a/drivers/cpufreq/intel_pstate.c > +++ b/drivers/cpufreq/intel_pstate.c > @@ -39,9 +39,10 @@ > #define BYT_TURBO_RATIOS 0x66c > > > -#define FRAC_BITS 8 > +#define FRAC_BITS 6 > #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) > #define fp_toint(X) ((X) >> FRAC_BITS) > +#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS) > > static inline int32_t mul_fp(int32_t x, int32_t y) > { > @@ -556,18 +557,20 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) > static inline void intel_pstate_calc_busy(struct cpudata *cpu, > struct sample *sample) > { > - u64 core_pct; > - u64 c0_pct; > + int32_t core_pct; > + int32_t c0_pct; > > - core_pct = div64_u64(sample->aperf * 100, sample->mperf); > + core_pct = div_fp(int_tofp((sample->aperf)), > + int_tofp((sample->mperf))); > + core_pct = mul_fp(core_pct, int_tofp(100)); > + FP_ROUNDUP(core_pct); > + > + c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc)); > > - c0_pct = div64_u64(sample->mperf * 100, sample->tsc); > sample->freq = fp_toint( > - mul_fp(int_tofp(cpu->pstate.max_pstate), > - int_tofp(core_pct * 1000))); > + mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); > > - sample->core_pct_busy = mul_fp(int_tofp(core_pct), > - div_fp(int_tofp(c0_pct + 1), int_tofp(100))); > + sample->core_pct_busy = mul_fp(core_pct, c0_pct); > } > > static inline void intel_pstate_sample(struct cpudata *cpu) > @@ -579,6 +582,10 @@ static inline void intel_pstate_sample(struct cpudata *cpu) > rdmsrl(MSR_IA32_MPERF, mperf); > tsc = native_read_tsc(); > > + aperf = aperf >> FRAC_BITS; > + mperf = mperf >> FRAC_BITS; > + tsc = tsc >> FRAC_BITS; > + > cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT; > cpu->samples[cpu->sample_ptr].aperf = aperf; > cpu->samples[cpu->sample_ptr].mperf = mperf; > @@ -610,7 +617,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) > core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; > max_pstate = int_tofp(cpu->pstate.max_pstate); > current_pstate = int_tofp(cpu->pstate.current_pstate); > - return mul_fp(core_busy, div_fp(max_pstate, current_pstate)); > + core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); > + return FP_ROUNDUP(core_busy); > } > > static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) >
On my i3-4330 this patch fixed the problem. works fine Thanks Am 26.02.2014 01:39, schrieb Rafael J. Wysocki: > On Tuesday, February 25, 2014 10:35:37 AM dirk.brandewie@gmail.com wrote: >> From: Dirk Brandewie <dirk.j.brandewie@intel.com> >> >> Commit fcb6a15c2e Take core C0 time into account for core busy calculation. >> >> Introduced a regression on some processor SKUs supported by >> intel_pstate. This was caused by the truncation caused by using >> integer math to calculate core busy and C0 percentages. >> >> On a i7-4770K processor operating at 800Mhz going to 100% utilization >> the percent busy of the CPU using integer math is 22% it actually is >> 22.85%. This value scaled to the current frequency returned 97 which >> the PID interpreted as no error and did not adjust the P state. >> >> Tested on i7-4770K, i7-2600, i5-3230M >> >> References: >> https://lkml.org/lkml/2014/2/19/626 >> https://bugzilla.kernel.org/show_bug.cgi?id=70941 >> >> Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> > Queued up as a fix for 3.14. > > Thanks! > >> --- >> drivers/cpufreq/intel_pstate.c | 28 ++++++++++++++++++---------- >> 1 file changed, 18 insertions(+), 10 deletions(-) >> >> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c >> index e908161..2cd36b9 100644 >> --- a/drivers/cpufreq/intel_pstate.c >> +++ b/drivers/cpufreq/intel_pstate.c >> @@ -39,9 +39,10 @@ >> #define BYT_TURBO_RATIOS 0x66c >> >> >> -#define FRAC_BITS 8 >> +#define FRAC_BITS 6 >> #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) >> #define fp_toint(X) ((X) >> FRAC_BITS) >> +#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS) >> >> static inline int32_t mul_fp(int32_t x, int32_t y) >> { >> @@ -556,18 +557,20 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) >> static inline void intel_pstate_calc_busy(struct cpudata *cpu, >> struct sample *sample) >> { >> - u64 core_pct; >> - u64 c0_pct; >> + int32_t core_pct; >> + int32_t c0_pct; >> >> - core_pct = div64_u64(sample->aperf * 100, sample->mperf); >> + core_pct = div_fp(int_tofp((sample->aperf)), >> + int_tofp((sample->mperf))); >> + core_pct = mul_fp(core_pct, int_tofp(100)); >> + FP_ROUNDUP(core_pct); >> + >> + c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc)); >> >> - c0_pct = div64_u64(sample->mperf * 100, sample->tsc); >> sample->freq = fp_toint( >> - mul_fp(int_tofp(cpu->pstate.max_pstate), >> - int_tofp(core_pct * 1000))); >> + mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); >> >> - sample->core_pct_busy = mul_fp(int_tofp(core_pct), >> - div_fp(int_tofp(c0_pct + 1), int_tofp(100))); >> + sample->core_pct_busy = mul_fp(core_pct, c0_pct); >> } >> >> static inline void intel_pstate_sample(struct cpudata *cpu) >> @@ -579,6 +582,10 @@ static inline void intel_pstate_sample(struct cpudata *cpu) >> rdmsrl(MSR_IA32_MPERF, mperf); >> tsc = native_read_tsc(); >> >> + aperf = aperf >> FRAC_BITS; >> + mperf = mperf >> FRAC_BITS; >> + tsc = tsc >> FRAC_BITS; >> + >> cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT; >> cpu->samples[cpu->sample_ptr].aperf = aperf; >> cpu->samples[cpu->sample_ptr].mperf = mperf; >> @@ -610,7 +617,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) >> core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; >> max_pstate = int_tofp(cpu->pstate.max_pstate); >> current_pstate = int_tofp(cpu->pstate.current_pstate); >> - return mul_fp(core_busy, div_fp(max_pstate, current_pstate)); >> + core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); >> + return FP_ROUNDUP(core_busy); >> } >> >> static inline void intel_pstate_adjust_busy_pstate(struct cpudata *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
On Tue, Feb 25, 2014 at 10:35:37AM -0800, dirk.brandewie@gmail.com wrote: > From: Dirk Brandewie <dirk.j.brandewie@intel.com> > > Commit fcb6a15c2e Take core C0 time into account for core busy calculation. > > Introduced a regression on some processor SKUs supported by > intel_pstate. This was caused by the truncation caused by using > integer math to calculate core busy and C0 percentages. > > On a i7-4770K processor operating at 800Mhz going to 100% utilization > the percent busy of the CPU using integer math is 22% it actually is > 22.85%. This value scaled to the current frequency returned 97 which > the PID interpreted as no error and did not adjust the P state. > > Tested on i7-4770K, i7-2600, i5-3230M > > References: > https://lkml.org/lkml/2014/2/19/626 > https://bugzilla.kernel.org/show_bug.cgi?id=70941 > > Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com> Thanks, this fixed the issue for me: Tested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> -- 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
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index e908161..2cd36b9 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -39,9 +39,10 @@ #define BYT_TURBO_RATIOS 0x66c -#define FRAC_BITS 8 +#define FRAC_BITS 6 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) #define fp_toint(X) ((X) >> FRAC_BITS) +#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS) static inline int32_t mul_fp(int32_t x, int32_t y) { @@ -556,18 +557,20 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) static inline void intel_pstate_calc_busy(struct cpudata *cpu, struct sample *sample) { - u64 core_pct; - u64 c0_pct; + int32_t core_pct; + int32_t c0_pct; - core_pct = div64_u64(sample->aperf * 100, sample->mperf); + core_pct = div_fp(int_tofp((sample->aperf)), + int_tofp((sample->mperf))); + core_pct = mul_fp(core_pct, int_tofp(100)); + FP_ROUNDUP(core_pct); + + c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc)); - c0_pct = div64_u64(sample->mperf * 100, sample->tsc); sample->freq = fp_toint( - mul_fp(int_tofp(cpu->pstate.max_pstate), - int_tofp(core_pct * 1000))); + mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); - sample->core_pct_busy = mul_fp(int_tofp(core_pct), - div_fp(int_tofp(c0_pct + 1), int_tofp(100))); + sample->core_pct_busy = mul_fp(core_pct, c0_pct); } static inline void intel_pstate_sample(struct cpudata *cpu) @@ -579,6 +582,10 @@ static inline void intel_pstate_sample(struct cpudata *cpu) rdmsrl(MSR_IA32_MPERF, mperf); tsc = native_read_tsc(); + aperf = aperf >> FRAC_BITS; + mperf = mperf >> FRAC_BITS; + tsc = tsc >> FRAC_BITS; + cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT; cpu->samples[cpu->sample_ptr].aperf = aperf; cpu->samples[cpu->sample_ptr].mperf = mperf; @@ -610,7 +617,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; max_pstate = int_tofp(cpu->pstate.max_pstate); current_pstate = int_tofp(cpu->pstate.current_pstate); - return mul_fp(core_busy, div_fp(max_pstate, current_pstate)); + core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); + return FP_ROUNDUP(core_busy); } static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)