| Message ID | 20230905015116.2268926-6-li.meng@amd.com |
|---|---|
| State | New |
| Headers | show |
| Series | [V5,1/7] x86: Drop CPU_SUP_INTEL from SCHED_MC_PRIO for the expansion. | expand |
On Tue, Sep 05, 2023 at 09:51:14AM +0800, Meng, Li (Jassmine) wrote: > Preferred core rankings can be changed dynamically by the > platform based on the workload and platform conditions and > accounting for thermals and aging. > When this occurs, cpu priority need to be set. > > Signed-off-by: Meng Li <li.meng@amd.com> > Reviewed-by: Wyes Karny <wyes.karny@amd.com> > --- > drivers/cpufreq/amd-pstate.c | 36 ++++++++++++++++++++++++++++++++++-- > include/linux/amd-pstate.h | 11 +++++++++++ > 2 files changed, 45 insertions(+), 2 deletions(-) > > diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c > index 454eb6e789e7..8c19e1d50d29 100644 > --- a/drivers/cpufreq/amd-pstate.c > +++ b/drivers/cpufreq/amd-pstate.c > @@ -318,6 +318,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) > WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); > WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); > WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); > + WRITE_ONCE(cpudata->cppc_highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); > > return 0; > } > @@ -339,6 +340,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) > WRITE_ONCE(cpudata->lowest_nonlinear_perf, > cppc_perf.lowest_nonlinear_perf); > WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); > + WRITE_ONCE(cpudata->cppc_highest_perf, cppc_perf.highest_perf); > > if (cppc_state == AMD_PSTATE_ACTIVE) > return 0; > @@ -545,7 +547,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, > if (target_perf < capacity) > des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); > > - min_perf = READ_ONCE(cpudata->highest_perf); > + min_perf = READ_ONCE(cpudata->lowest_perf); > if (_min_perf < capacity) > min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); > > @@ -748,6 +750,34 @@ static void amd_pstate_init_prefcore(void) > schedule_work(&sched_prefcore_work); > } > > +static void amd_pstate_update_highest_perf(unsigned int cpu) > +{ > + struct cpufreq_policy *policy; > + struct amd_cpudata *cpudata; > + u32 prev_high = 0, cur_high = 0; > + u64 highest_perf; > + int ret; > + > + if (!prefcore) > + return; > + > + ret = amd_pstate_get_highest_perf(cpu, &highest_perf); > + if (ret) > + return; > + > + policy = cpufreq_cpu_get(cpu); > + cpudata = policy->driver_data; > + cur_high = highest_perf; > + prev_high = READ_ONCE(cpudata->cppc_highest_perf); > + > + if (prev_high != cur_high) { > + WRITE_ONCE(cpudata->cppc_highest_perf, cur_high); > + sched_set_itmt_core_prio(cur_high, cpu); > + } > + > + cpufreq_cpu_put(policy); > +} > + > static int amd_pstate_cpu_init(struct cpufreq_policy *policy) > { > int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; > @@ -912,7 +942,7 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, > u32 perf; > struct amd_cpudata *cpudata = policy->driver_data; > > - perf = READ_ONCE(cpudata->highest_perf); > + perf = READ_ONCE(cpudata->cppc_highest_perf); > > return sysfs_emit(buf, "%u\n", perf); > } > @@ -1479,6 +1509,7 @@ static struct cpufreq_driver amd_pstate_driver = { > .suspend = amd_pstate_cpu_suspend, > .resume = amd_pstate_cpu_resume, > .set_boost = amd_pstate_set_boost, > + .update_highest_perf = amd_pstate_update_highest_perf, > .name = "amd-pstate", > .attr = amd_pstate_attr, > }; > @@ -1493,6 +1524,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = { > .online = amd_pstate_epp_cpu_online, > .suspend = amd_pstate_epp_suspend, > .resume = amd_pstate_epp_resume, > + .update_highest_perf = amd_pstate_update_highest_perf, > .name = "amd-pstate-epp", > .attr = amd_pstate_epp_attr, > }; > diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h > index 446394f84606..2159fd5693fe 100644 > --- a/include/linux/amd-pstate.h > +++ b/include/linux/amd-pstate.h > @@ -31,6 +31,11 @@ struct amd_aperf_mperf { > u64 mperf; > u64 tsc; > }; > + /* For platforms that do not support the preferred core feature, the > + * highest_pef may be configured with 166 or 255, to avoid max frequency > + * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as > + * the default max perf. > + */ This seems a duplicate commments? Thanks, Ray > > /** > * struct amd_cpudata - private CPU data for AMD P-State > @@ -39,11 +44,16 @@ struct amd_aperf_mperf { > * @cppc_req_cached: cached performance request hints > * @highest_perf: the maximum performance an individual processor may reach, > * assuming ideal conditions > + * For platforms that do not support the preferred core feature, the > + * highest_pef may be configured with 166 or 255, to avoid max frequency > + * calculated wrongly. we take the fixed value as the highest_perf. > * @nominal_perf: the maximum sustained performance level of the processor, > * assuming ideal operating conditions > * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power > * savings are achieved > * @lowest_perf: the absolute lowest performance level of the processor > + * @cppc_highest_perf: the maximum performance an individual processor may reach, > + * assuming ideal conditions > * @max_freq: the frequency that mapped to highest_perf > * @min_freq: the frequency that mapped to lowest_perf > * @nominal_freq: the frequency that mapped to nominal_perf > @@ -70,6 +80,7 @@ struct amd_cpudata { > u32 nominal_perf; > u32 lowest_nonlinear_perf; > u32 lowest_perf; > + u32 cppc_highest_perf; > > u32 max_freq; > u32 min_freq; > -- > 2.34.1 >
Hi Meng Li, On 05 Sep 09:51, Meng Li wrote: > Preferred core rankings can be changed dynamically by the > platform based on the workload and platform conditions and > accounting for thermals and aging. > When this occurs, cpu priority need to be set. > > Signed-off-by: Meng Li <li.meng@amd.com> > Reviewed-by: Wyes Karny <wyes.karny@amd.com> > --- > drivers/cpufreq/amd-pstate.c | 36 ++++++++++++++++++++++++++++++++++-- > include/linux/amd-pstate.h | 11 +++++++++++ > 2 files changed, 45 insertions(+), 2 deletions(-) > > diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c > index 454eb6e789e7..8c19e1d50d29 100644 > --- a/drivers/cpufreq/amd-pstate.c > +++ b/drivers/cpufreq/amd-pstate.c > @@ -318,6 +318,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) > WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); > WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); > WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); > + WRITE_ONCE(cpudata->cppc_highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); Is there any reason to change this variable name form `prefcore_highest_perf`(in v3) to `cppc_highest_perf`? I feel `cppc_highest_perf` is bit confusing as there is already `highest_perf` variable present. How about something like `prefcore_ranking` variable name? Thanks, Wyes > > return 0; > } > @@ -339,6 +340,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) > WRITE_ONCE(cpudata->lowest_nonlinear_perf, > cppc_perf.lowest_nonlinear_perf); > WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); > + WRITE_ONCE(cpudata->cppc_highest_perf, cppc_perf.highest_perf); > > if (cppc_state == AMD_PSTATE_ACTIVE) > return 0; > @@ -545,7 +547,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, > if (target_perf < capacity) > des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); > > - min_perf = READ_ONCE(cpudata->highest_perf); > + min_perf = READ_ONCE(cpudata->lowest_perf); > if (_min_perf < capacity) > min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); > > @@ -748,6 +750,34 @@ static void amd_pstate_init_prefcore(void) > schedule_work(&sched_prefcore_work); > } > > +static void amd_pstate_update_highest_perf(unsigned int cpu) > +{ > + struct cpufreq_policy *policy; > + struct amd_cpudata *cpudata; > + u32 prev_high = 0, cur_high = 0; > + u64 highest_perf; > + int ret; > + > + if (!prefcore) > + return; > + > + ret = amd_pstate_get_highest_perf(cpu, &highest_perf); > + if (ret) > + return; > + > + policy = cpufreq_cpu_get(cpu); > + cpudata = policy->driver_data; > + cur_high = highest_perf; > + prev_high = READ_ONCE(cpudata->cppc_highest_perf); > + > + if (prev_high != cur_high) { > + WRITE_ONCE(cpudata->cppc_highest_perf, cur_high); > + sched_set_itmt_core_prio(cur_high, cpu); > + } > + > + cpufreq_cpu_put(policy); > +} > + > static int amd_pstate_cpu_init(struct cpufreq_policy *policy) > { > int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; > @@ -912,7 +942,7 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, > u32 perf; > struct amd_cpudata *cpudata = policy->driver_data; > > - perf = READ_ONCE(cpudata->highest_perf); > + perf = READ_ONCE(cpudata->cppc_highest_perf); > > return sysfs_emit(buf, "%u\n", perf); > } > @@ -1479,6 +1509,7 @@ static struct cpufreq_driver amd_pstate_driver = { > .suspend = amd_pstate_cpu_suspend, > .resume = amd_pstate_cpu_resume, > .set_boost = amd_pstate_set_boost, > + .update_highest_perf = amd_pstate_update_highest_perf, > .name = "amd-pstate", > .attr = amd_pstate_attr, > }; > @@ -1493,6 +1524,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = { > .online = amd_pstate_epp_cpu_online, > .suspend = amd_pstate_epp_suspend, > .resume = amd_pstate_epp_resume, > + .update_highest_perf = amd_pstate_update_highest_perf, > .name = "amd-pstate-epp", > .attr = amd_pstate_epp_attr, > }; > diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h > index 446394f84606..2159fd5693fe 100644 > --- a/include/linux/amd-pstate.h > +++ b/include/linux/amd-pstate.h > @@ -31,6 +31,11 @@ struct amd_aperf_mperf { > u64 mperf; > u64 tsc; > }; > + /* For platforms that do not support the preferred core feature, the > + * highest_pef may be configured with 166 or 255, to avoid max frequency > + * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as > + * the default max perf. > + */ > > /** > * struct amd_cpudata - private CPU data for AMD P-State > @@ -39,11 +44,16 @@ struct amd_aperf_mperf { > * @cppc_req_cached: cached performance request hints > * @highest_perf: the maximum performance an individual processor may reach, > * assuming ideal conditions > + * For platforms that do not support the preferred core feature, the > + * highest_pef may be configured with 166 or 255, to avoid max frequency > + * calculated wrongly. we take the fixed value as the highest_perf. > * @nominal_perf: the maximum sustained performance level of the processor, > * assuming ideal operating conditions > * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power > * savings are achieved > * @lowest_perf: the absolute lowest performance level of the processor > + * @cppc_highest_perf: the maximum performance an individual processor may reach, > + * assuming ideal conditions > * @max_freq: the frequency that mapped to highest_perf > * @min_freq: the frequency that mapped to lowest_perf > * @nominal_freq: the frequency that mapped to nominal_perf > @@ -70,6 +80,7 @@ struct amd_cpudata { > u32 nominal_perf; > u32 lowest_nonlinear_perf; > u32 lowest_perf; > + u32 cppc_highest_perf; > > u32 max_freq; > u32 min_freq; > -- > 2.34.1 >
On Tue, Sep 05, 2023 at 09:51:14AM +0800, Meng Li wrote: > +static void amd_pstate_update_highest_perf(unsigned int cpu) > +{ > + struct cpufreq_policy *policy; > + struct amd_cpudata *cpudata; > + u32 prev_high = 0, cur_high = 0; > + u64 highest_perf; > + int ret; > + > + if (!prefcore) > + return; > + > + ret = amd_pstate_get_highest_perf(cpu, &highest_perf); > + if (ret) > + return; > + > + policy = cpufreq_cpu_get(cpu); > + cpudata = policy->driver_data; > + cur_high = highest_perf; > + prev_high = READ_ONCE(cpudata->cppc_highest_perf); > + > + if (prev_high != cur_high) { > + WRITE_ONCE(cpudata->cppc_highest_perf, cur_high); > + sched_set_itmt_core_prio(cur_high, cpu); I just noticed, your cur_high is explicitly 'u32', but sched_set_itmt_core_prio() and the rest of the scheduler use 'int' (aka s32). If you somehow get that top bit set things might not work out as expected. Please double check. > + } > + > + cpufreq_cpu_put(policy); > +}
On Tue, Sep 05, 2023 at 09:51:14AM +0800, Meng Li wrote: > diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h > index 446394f84606..2159fd5693fe 100644 > --- a/include/linux/amd-pstate.h > +++ b/include/linux/amd-pstate.h > @@ -31,6 +31,11 @@ struct amd_aperf_mperf { > u64 mperf; > u64 tsc; > }; > + /* For platforms that do not support the preferred core feature, the > + * highest_pef may be configured with 166 or 255, to avoid max frequency > + * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as > + * the default max perf. > + */ Invalid comment style, also seems randomly (mis)placed.
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 454eb6e789e7..8c19e1d50d29 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -318,6 +318,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); + WRITE_ONCE(cpudata->cppc_highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); return 0; } @@ -339,6 +340,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); + WRITE_ONCE(cpudata->cppc_highest_perf, cppc_perf.highest_perf); if (cppc_state == AMD_PSTATE_ACTIVE) return 0; @@ -545,7 +547,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (target_perf < capacity) des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); - min_perf = READ_ONCE(cpudata->highest_perf); + min_perf = READ_ONCE(cpudata->lowest_perf); if (_min_perf < capacity) min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); @@ -748,6 +750,34 @@ static void amd_pstate_init_prefcore(void) schedule_work(&sched_prefcore_work); } +static void amd_pstate_update_highest_perf(unsigned int cpu) +{ + struct cpufreq_policy *policy; + struct amd_cpudata *cpudata; + u32 prev_high = 0, cur_high = 0; + u64 highest_perf; + int ret; + + if (!prefcore) + return; + + ret = amd_pstate_get_highest_perf(cpu, &highest_perf); + if (ret) + return; + + policy = cpufreq_cpu_get(cpu); + cpudata = policy->driver_data; + cur_high = highest_perf; + prev_high = READ_ONCE(cpudata->cppc_highest_perf); + + if (prev_high != cur_high) { + WRITE_ONCE(cpudata->cppc_highest_perf, cur_high); + sched_set_itmt_core_prio(cur_high, cpu); + } + + cpufreq_cpu_put(policy); +} + static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; @@ -912,7 +942,7 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, u32 perf; struct amd_cpudata *cpudata = policy->driver_data; - perf = READ_ONCE(cpudata->highest_perf); + perf = READ_ONCE(cpudata->cppc_highest_perf); return sysfs_emit(buf, "%u\n", perf); } @@ -1479,6 +1509,7 @@ static struct cpufreq_driver amd_pstate_driver = { .suspend = amd_pstate_cpu_suspend, .resume = amd_pstate_cpu_resume, .set_boost = amd_pstate_set_boost, + .update_highest_perf = amd_pstate_update_highest_perf, .name = "amd-pstate", .attr = amd_pstate_attr, }; @@ -1493,6 +1524,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = { .online = amd_pstate_epp_cpu_online, .suspend = amd_pstate_epp_suspend, .resume = amd_pstate_epp_resume, + .update_highest_perf = amd_pstate_update_highest_perf, .name = "amd-pstate-epp", .attr = amd_pstate_epp_attr, }; diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index 446394f84606..2159fd5693fe 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -31,6 +31,11 @@ struct amd_aperf_mperf { u64 mperf; u64 tsc; }; + /* For platforms that do not support the preferred core feature, the + * highest_pef may be configured with 166 or 255, to avoid max frequency + * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as + * the default max perf. + */ /** * struct amd_cpudata - private CPU data for AMD P-State @@ -39,11 +44,16 @@ struct amd_aperf_mperf { * @cppc_req_cached: cached performance request hints * @highest_perf: the maximum performance an individual processor may reach, * assuming ideal conditions + * For platforms that do not support the preferred core feature, the + * highest_pef may be configured with 166 or 255, to avoid max frequency + * calculated wrongly. we take the fixed value as the highest_perf. * @nominal_perf: the maximum sustained performance level of the processor, * assuming ideal operating conditions * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power * savings are achieved * @lowest_perf: the absolute lowest performance level of the processor + * @cppc_highest_perf: the maximum performance an individual processor may reach, + * assuming ideal conditions * @max_freq: the frequency that mapped to highest_perf * @min_freq: the frequency that mapped to lowest_perf * @nominal_freq: the frequency that mapped to nominal_perf @@ -70,6 +80,7 @@ struct amd_cpudata { u32 nominal_perf; u32 lowest_nonlinear_perf; u32 lowest_perf; + u32 cppc_highest_perf; u32 max_freq; u32 min_freq;