Message ID | 20240730044917.4680-2-Dhananjay.Ugwekar@amd.com |
---|---|
State | Accepted |
Commit | 8d72eba1cf8cecd76a2b4c1dd7673c2dc775f514 |
Headers | show |
Series | RAPL driver fixes for AMD CPUs | expand |
Hi Dhananjay, On 2024-07-30 12:49 a.m., Dhananjay Ugwekar wrote: > After commit ("x86/cpu/topology: Add support for the AMD 0x80000026 leaf"), > on AMD processors that support extended CPUID leaf 0x80000026, the > topology_die_cpumask() and topology_logical_die_id() macros, no longer > return the package cpumask and package id, instead they return the CCD > (Core Complex Die) mask and id respectively. This leads to the energy-pkg > event scope to be modified to CCD instead of package. > > For more historical context, please refer to commit 32fb480e0a2c > ("powercap/intel_rapl: Support multi-die/package"), which initially changed > the RAPL scope from package to die for all systems, as Intel systems > with Die enumeration have RAPL scope as die, and those without die > enumeration were not affected by it. So, all systems(Intel, AMD, Hygon), > worked correctly with topology_logical_die_id() until recently, but this > changed after the "0x80000026 leaf" commit mentioned above. > > Replacing topology_logical_die_id() with topology_physical_package_id() > conditionally only for AMD and Hygon fixes the energy-pkg event. > > On a 12 CCD 1 Package AMD Zen4 Genoa machine: > > Before: > $ cat /sys/devices/power/cpumask > 0,8,16,24,32,40,48,56,64,72,80,88. > > The expected cpumask here is supposed to be just "0", as it is a package > scope event, only one CPU will be collecting the event for all the CPUs in > the package. > > After: > $ cat /sys/devices/power/cpumask > 0 > > Fixes: 63edbaa48a57 ("x86/cpu/topology: Add support for the AMD 0x80000026 leaf") > Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> > Reviewed-by: Zhang Rui <rui.zhang@intel.com> > --- > Changes in v2: > * Updated the scope description comment > * Dont create rapl_pmu_cpumask and rapl_pmu_idx local variables, as they're > used only once, instead call the get_* functions directly where needed > * Check topology_logical_(die/package)_id return value > ---> arch/x86/events/rapl.c | 47 +++++++++++++++++++++++++++++++++++++----- > 1 file changed, 42 insertions(+), 5 deletions(-) I just posted a patch set to clean up the hotplug code in perf. https://lore.kernel.org/lkml/20240802151643.1691631-1-kan.liang@linux.intel.com/ With the cleanup patch set, the fix may be simplified as below. diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index b70ad880c5bc..801697be4118 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -646,6 +646,10 @@ static int __init init_rapl_pmus(void) rapl_pmus->pmu.module = THIS_MODULE; rapl_pmus->pmu.scope = PERF_PMU_SCOPE_DIE; rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; + + if (rapl_pmu_is_pkg_scope()) + rapl_pmus->pmu.scope = PERF_PMU_SCOPE_PKG; + return 0; } Could you please take a look at the cleanup patch and give it a try? Thanks, Kan > > diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c > index b985ca79cf97..7097c0f6a71f 100644 > --- a/arch/x86/events/rapl.c > +++ b/arch/x86/events/rapl.c > @@ -103,6 +103,19 @@ static struct perf_pmu_events_attr event_attr_##v = { \ > .event_str = str, \ > }; > > +/* > + * RAPL Package energy counter scope: > + * 1. AMD/HYGON platforms have a per-PKG package energy counter > + * 2. For Intel platforms > + * 2.1. CLX-AP is multi-die and its RAPL MSRs are die-scope > + * 2.2. Other Intel platforms are single die systems so the scope can be > + * considered as either pkg-scope or die-scope, and we are considering > + * them as die-scope. > + */ > +#define rapl_pmu_is_pkg_scope() \ > + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \ > + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) > + > struct rapl_pmu { > raw_spinlock_t lock; > int n_active; > @@ -140,9 +153,25 @@ static unsigned int rapl_cntr_mask; > static u64 rapl_timer_ms; > static struct perf_msr *rapl_msrs; > > +/* > + * Helper functions to get the correct topology macros according to the > + * RAPL PMU scope. > + */ > +static inline unsigned int get_rapl_pmu_idx(int cpu) > +{ > + return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) : > + topology_logical_die_id(cpu); > +} > + > +static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu) > +{ > + return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) : > + topology_die_cpumask(cpu); > +} > + > static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) > { > - unsigned int rapl_pmu_idx = topology_logical_die_id(cpu); > + unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); > > /* > * The unsigned check also catches the '-1' return value for non > @@ -552,7 +581,7 @@ static int rapl_cpu_offline(unsigned int cpu) > > pmu->cpu = -1; > /* Find a new cpu to collect rapl events */ > - target = cpumask_any_but(topology_die_cpumask(cpu), cpu); > + target = cpumask_any_but(get_rapl_pmu_cpumask(cpu), cpu); > > /* Migrate rapl events to the new target */ > if (target < nr_cpu_ids) { > @@ -565,6 +594,11 @@ static int rapl_cpu_offline(unsigned int cpu) > > static int rapl_cpu_online(unsigned int cpu) > { > + s32 rapl_pmu_idx = get_rapl_pmu_idx(cpu); > + if (rapl_pmu_idx < 0) { > + pr_err("topology_logical_(package/die)_id() returned a negative value"); > + return -EINVAL; > + } > struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); > int target; > > @@ -579,14 +613,14 @@ static int rapl_cpu_online(unsigned int cpu) > pmu->timer_interval = ms_to_ktime(rapl_timer_ms); > rapl_hrtimer_init(pmu); > > - rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu; > + rapl_pmus->pmus[rapl_pmu_idx] = pmu; > } > > /* > * Check if there is an online cpu in the package which collects rapl > * events already. > */ > - target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu)); > + target = cpumask_any_and(&rapl_cpu_mask, get_rapl_pmu_cpumask(cpu)); > if (target < nr_cpu_ids) > return 0; > > @@ -675,7 +709,10 @@ static const struct attribute_group *rapl_attr_update[] = { > > static int __init init_rapl_pmus(void) > { > - int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package(); > + int nr_rapl_pmu = topology_max_packages(); > + > + if (!rapl_pmu_is_pkg_scope()) > + nr_rapl_pmu *= topology_max_dies_per_package(); > > rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); > if (!rapl_pmus)
Hello Kan, On 8/2/2024 8:56 PM, Liang, Kan wrote: > Hi Dhananjay, > > On 2024-07-30 12:49 a.m., Dhananjay Ugwekar wrote: >> After commit ("x86/cpu/topology: Add support for the AMD 0x80000026 leaf"), >> on AMD processors that support extended CPUID leaf 0x80000026, the >> topology_die_cpumask() and topology_logical_die_id() macros, no longer >> return the package cpumask and package id, instead they return the CCD >> (Core Complex Die) mask and id respectively. This leads to the energy-pkg >> event scope to be modified to CCD instead of package. >> >> For more historical context, please refer to commit 32fb480e0a2c >> ("powercap/intel_rapl: Support multi-die/package"), which initially changed >> the RAPL scope from package to die for all systems, as Intel systems >> with Die enumeration have RAPL scope as die, and those without die >> enumeration were not affected by it. So, all systems(Intel, AMD, Hygon), >> worked correctly with topology_logical_die_id() until recently, but this >> changed after the "0x80000026 leaf" commit mentioned above. >> >> Replacing topology_logical_die_id() with topology_physical_package_id() >> conditionally only for AMD and Hygon fixes the energy-pkg event. >> >> On a 12 CCD 1 Package AMD Zen4 Genoa machine: >> >> Before: >> $ cat /sys/devices/power/cpumask >> 0,8,16,24,32,40,48,56,64,72,80,88. >> >> The expected cpumask here is supposed to be just "0", as it is a package >> scope event, only one CPU will be collecting the event for all the CPUs in >> the package. >> >> After: >> $ cat /sys/devices/power/cpumask >> 0 >> >> Fixes: 63edbaa48a57 ("x86/cpu/topology: Add support for the AMD 0x80000026 leaf") >> Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> >> Reviewed-by: Zhang Rui <rui.zhang@intel.com> >> --- >> Changes in v2: >> * Updated the scope description comment >> * Dont create rapl_pmu_cpumask and rapl_pmu_idx local variables, as they're >> used only once, instead call the get_* functions directly where needed >> * Check topology_logical_(die/package)_id return value >> ---> arch/x86/events/rapl.c | 47 +++++++++++++++++++++++++++++++++++++----- >> 1 file changed, 42 insertions(+), 5 deletions(-) > > I just posted a patch set to clean up the hotplug code in perf. > https://lore.kernel.org/lkml/20240802151643.1691631-1-kan.liang@linux.intel.com/ > > With the cleanup patch set, the fix may be simplified as below. > > diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c > index b70ad880c5bc..801697be4118 100644 > --- a/arch/x86/events/rapl.c > +++ b/arch/x86/events/rapl.c > @@ -646,6 +646,10 @@ static int __init init_rapl_pmus(void) > rapl_pmus->pmu.module = THIS_MODULE; > rapl_pmus->pmu.scope = PERF_PMU_SCOPE_DIE; > rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; > + > + if (rapl_pmu_is_pkg_scope()) > + rapl_pmus->pmu.scope = PERF_PMU_SCOPE_PKG; > + > return 0; > } > > Could you please take a look at the cleanup patch and give it a try? Sorry for the late reply, I was out sick for last few days. I tried out my fix(modified) on top your patchset, the energy-pkg event seems to be working correctly, On a Zen4 Genoa EPYC server: When idle, ~$ sudo perf stat -a -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': 33.93 Joules power/energy-pkg/ 1.001969742 seconds time elapsed After running stress-ng: ~$ sudo perf stat -a -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': 376.16 Joules power/energy-pkg/ 1.003985155 seconds time elapsed Please feel free to add my tested-by on your hotplug cleanup patchset. Thanks, Dhananjay > > Thanks, > Kan >> >> diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c >> index b985ca79cf97..7097c0f6a71f 100644 >> --- a/arch/x86/events/rapl.c >> +++ b/arch/x86/events/rapl.c >> @@ -103,6 +103,19 @@ static struct perf_pmu_events_attr event_attr_##v = { \ >> .event_str = str, \ >> }; >> >> +/* >> + * RAPL Package energy counter scope: >> + * 1. AMD/HYGON platforms have a per-PKG package energy counter >> + * 2. For Intel platforms >> + * 2.1. CLX-AP is multi-die and its RAPL MSRs are die-scope >> + * 2.2. Other Intel platforms are single die systems so the scope can be >> + * considered as either pkg-scope or die-scope, and we are considering >> + * them as die-scope. >> + */ >> +#define rapl_pmu_is_pkg_scope() \ >> + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \ >> + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) >> + >> struct rapl_pmu { >> raw_spinlock_t lock; >> int n_active; >> @@ -140,9 +153,25 @@ static unsigned int rapl_cntr_mask; >> static u64 rapl_timer_ms; >> static struct perf_msr *rapl_msrs; >> >> +/* >> + * Helper functions to get the correct topology macros according to the >> + * RAPL PMU scope. >> + */ >> +static inline unsigned int get_rapl_pmu_idx(int cpu) >> +{ >> + return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) : >> + topology_logical_die_id(cpu); >> +} >> + >> +static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu) >> +{ >> + return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) : >> + topology_die_cpumask(cpu); >> +} >> + >> static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) >> { >> - unsigned int rapl_pmu_idx = topology_logical_die_id(cpu); >> + unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); >> >> /* >> * The unsigned check also catches the '-1' return value for non >> @@ -552,7 +581,7 @@ static int rapl_cpu_offline(unsigned int cpu) >> >> pmu->cpu = -1; >> /* Find a new cpu to collect rapl events */ >> - target = cpumask_any_but(topology_die_cpumask(cpu), cpu); >> + target = cpumask_any_but(get_rapl_pmu_cpumask(cpu), cpu); >> >> /* Migrate rapl events to the new target */ >> if (target < nr_cpu_ids) { >> @@ -565,6 +594,11 @@ static int rapl_cpu_offline(unsigned int cpu) >> >> static int rapl_cpu_online(unsigned int cpu) >> { >> + s32 rapl_pmu_idx = get_rapl_pmu_idx(cpu); >> + if (rapl_pmu_idx < 0) { >> + pr_err("topology_logical_(package/die)_id() returned a negative value"); >> + return -EINVAL; >> + } >> struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); >> int target; >> >> @@ -579,14 +613,14 @@ static int rapl_cpu_online(unsigned int cpu) >> pmu->timer_interval = ms_to_ktime(rapl_timer_ms); >> rapl_hrtimer_init(pmu); >> >> - rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu; >> + rapl_pmus->pmus[rapl_pmu_idx] = pmu; >> } >> >> /* >> * Check if there is an online cpu in the package which collects rapl >> * events already. >> */ >> - target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu)); >> + target = cpumask_any_and(&rapl_cpu_mask, get_rapl_pmu_cpumask(cpu)); >> if (target < nr_cpu_ids) >> return 0; >> >> @@ -675,7 +709,10 @@ static const struct attribute_group *rapl_attr_update[] = { >> >> static int __init init_rapl_pmus(void) >> { >> - int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package(); >> + int nr_rapl_pmu = topology_max_packages(); >> + >> + if (!rapl_pmu_is_pkg_scope()) >> + nr_rapl_pmu *= topology_max_dies_per_package(); >> >> rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); >> if (!rapl_pmus)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index b985ca79cf97..7097c0f6a71f 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -103,6 +103,19 @@ static struct perf_pmu_events_attr event_attr_##v = { \ .event_str = str, \ }; +/* + * RAPL Package energy counter scope: + * 1. AMD/HYGON platforms have a per-PKG package energy counter + * 2. For Intel platforms + * 2.1. CLX-AP is multi-die and its RAPL MSRs are die-scope + * 2.2. Other Intel platforms are single die systems so the scope can be + * considered as either pkg-scope or die-scope, and we are considering + * them as die-scope. + */ +#define rapl_pmu_is_pkg_scope() \ + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \ + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) + struct rapl_pmu { raw_spinlock_t lock; int n_active; @@ -140,9 +153,25 @@ static unsigned int rapl_cntr_mask; static u64 rapl_timer_ms; static struct perf_msr *rapl_msrs; +/* + * Helper functions to get the correct topology macros according to the + * RAPL PMU scope. + */ +static inline unsigned int get_rapl_pmu_idx(int cpu) +{ + return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) : + topology_logical_die_id(cpu); +} + +static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu) +{ + return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) : + topology_die_cpumask(cpu); +} + static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - unsigned int rapl_pmu_idx = topology_logical_die_id(cpu); + unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); /* * The unsigned check also catches the '-1' return value for non @@ -552,7 +581,7 @@ static int rapl_cpu_offline(unsigned int cpu) pmu->cpu = -1; /* Find a new cpu to collect rapl events */ - target = cpumask_any_but(topology_die_cpumask(cpu), cpu); + target = cpumask_any_but(get_rapl_pmu_cpumask(cpu), cpu); /* Migrate rapl events to the new target */ if (target < nr_cpu_ids) { @@ -565,6 +594,11 @@ static int rapl_cpu_offline(unsigned int cpu) static int rapl_cpu_online(unsigned int cpu) { + s32 rapl_pmu_idx = get_rapl_pmu_idx(cpu); + if (rapl_pmu_idx < 0) { + pr_err("topology_logical_(package/die)_id() returned a negative value"); + return -EINVAL; + } struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; @@ -579,14 +613,14 @@ static int rapl_cpu_online(unsigned int cpu) pmu->timer_interval = ms_to_ktime(rapl_timer_ms); rapl_hrtimer_init(pmu); - rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu; + rapl_pmus->pmus[rapl_pmu_idx] = pmu; } /* * Check if there is an online cpu in the package which collects rapl * events already. */ - target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu)); + target = cpumask_any_and(&rapl_cpu_mask, get_rapl_pmu_cpumask(cpu)); if (target < nr_cpu_ids) return 0; @@ -675,7 +709,10 @@ static const struct attribute_group *rapl_attr_update[] = { static int __init init_rapl_pmus(void) { - int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package(); + int nr_rapl_pmu = topology_max_packages(); + + if (!rapl_pmu_is_pkg_scope()) + nr_rapl_pmu *= topology_max_dies_per_package(); rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); if (!rapl_pmus)