| Message ID | 20240711102436.4432-3-Dhananjay.Ugwekar@amd.com |
|---|---|
| State | New |
| Headers | show |
| Series | Add per-core RAPL energy counter support for AMD CPUs | expand |
On Thu, 2024-07-11 at 10:24 +0000, 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. > > Replacing these macros with their package counterparts fixes the > energy-pkg event for AMD CPUs. > > However due to the difference between the scope of energy-pkg event > for > Intel and AMD CPUs, we have to replace these macros conditionally > only for > AMD CPUs. > > 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 > > Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> > Fixes: 63edbaa48a57 ("x86/cpu/topology: Add support for the AMD > 0x80000026 leaf") You still missed my Reviewed-by tag for this one. :) https://lore.kernel.org/all/e1f70a09f85dbd0ee3f32dffea37993e141269d0.camel@intel.com/ thanks, rui > --- > Changes in v4: > * Invert the pkg scope check in init_rapl_pmus() (Peter) > * Add comments to explain the pkg scope check (Peter) > > PS: Scope check logic is still kept the same (i.e., all Intel systems > being > considered as die scope), Rui will be modifying it to limit the die- > scope > only to Cascadelake-AP in a future patch on top of this patchset. > --- > arch/x86/events/rapl.c | 39 ++++++++++++++++++++++++++++++++++----- > 1 file changed, 34 insertions(+), 5 deletions(-) > > diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c > index 0c5e7a7c43ac..df71f38ad98d 100644 > --- a/arch/x86/events/rapl.c > +++ b/arch/x86/events/rapl.c > @@ -103,6 +103,13 @@ static struct perf_pmu_events_attr > event_attr_##v = { \ > .event_str = > str, \ > }; > > +/* > + * RAPL PMU scope for AMD is package whereas for Intel it is die. > + */ > +#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 +147,25 @@ 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 > @@ -543,6 +566,7 @@ static struct perf_msr amd_rapl_msrs[] = { > > static int rapl_cpu_offline(unsigned int cpu) > { > + const struct cpumask *rapl_pmu_cpumask = > get_rapl_pmu_cpumask(cpu); > struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); > int target; > > @@ -552,7 +576,7 @@ 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(rapl_pmu_cpumask, cpu); > > /* Migrate rapl events to the new target */ > if (target < nr_cpu_ids) { > @@ -565,6 +589,8 @@ static int rapl_cpu_offline(unsigned int cpu) > > static int rapl_cpu_online(unsigned int cpu) > { > + unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); > + const struct cpumask *rapl_pmu_cpumask = > get_rapl_pmu_cpumask(cpu); > struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); > int target; > > @@ -579,14 +605,14 @@ 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, rapl_pmu_cpumask); > if (target < nr_cpu_ids) > return 0; > > @@ -675,7 +701,10 @@ 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 Peter, Rui,
After Ian's comments on the series, I have decided to rethink the approach of
adding a new PMU for the per-core RAPL counters.
However this patch is still needed as a fix for the
commit ("x86/cpu/topology: Add support for the AMD 0x80000026 leaf"), I will be
sending this separately along with a similar fix for powercap/intel_rapl_common.
Thanks,
Dhananjay
On 7/11/2024 3:54 PM, 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.
>
> Replacing these macros with their package counterparts fixes the
> energy-pkg event for AMD CPUs.
>
> However due to the difference between the scope of energy-pkg event for
> Intel and AMD CPUs, we have to replace these macros conditionally only for
> AMD CPUs.
>
> 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
>
> Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
> Fixes: 63edbaa48a57 ("x86/cpu/topology: Add support for the AMD 0x80000026 leaf")
> ---
> Changes in v4:
> * Invert the pkg scope check in init_rapl_pmus() (Peter)
> * Add comments to explain the pkg scope check (Peter)
>
> PS: Scope check logic is still kept the same (i.e., all Intel systems being
> considered as die scope), Rui will be modifying it to limit the die-scope
> only to Cascadelake-AP in a future patch on top of this patchset.
> ---
> arch/x86/events/rapl.c | 39 ++++++++++++++++++++++++++++++++++-----
> 1 file changed, 34 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
> index 0c5e7a7c43ac..df71f38ad98d 100644
> --- a/arch/x86/events/rapl.c
> +++ b/arch/x86/events/rapl.c
> @@ -103,6 +103,13 @@ static struct perf_pmu_events_attr event_attr_##v = { \
> .event_str = str, \
> };
>
> +/*
> + * RAPL PMU scope for AMD is package whereas for Intel it is die.
> + */
> +#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 +147,25 @@ 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
> @@ -543,6 +566,7 @@ static struct perf_msr amd_rapl_msrs[] = {
>
> static int rapl_cpu_offline(unsigned int cpu)
> {
> + const struct cpumask *rapl_pmu_cpumask = get_rapl_pmu_cpumask(cpu);
> struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
> int target;
>
> @@ -552,7 +576,7 @@ 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(rapl_pmu_cpumask, cpu);
>
> /* Migrate rapl events to the new target */
> if (target < nr_cpu_ids) {
> @@ -565,6 +589,8 @@ static int rapl_cpu_offline(unsigned int cpu)
>
> static int rapl_cpu_online(unsigned int cpu)
> {
> + unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu);
> + const struct cpumask *rapl_pmu_cpumask = get_rapl_pmu_cpumask(cpu);
> struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
> int target;
>
> @@ -579,14 +605,14 @@ 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, rapl_pmu_cpumask);
> if (target < nr_cpu_ids)
> return 0;
>
> @@ -675,7 +701,10 @@ 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 0c5e7a7c43ac..df71f38ad98d 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -103,6 +103,13 @@ static struct perf_pmu_events_attr event_attr_##v = { \ .event_str = str, \ }; +/* + * RAPL PMU scope for AMD is package whereas for Intel it is die. + */ +#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 +147,25 @@ 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 @@ -543,6 +566,7 @@ static struct perf_msr amd_rapl_msrs[] = { static int rapl_cpu_offline(unsigned int cpu) { + const struct cpumask *rapl_pmu_cpumask = get_rapl_pmu_cpumask(cpu); struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; @@ -552,7 +576,7 @@ 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(rapl_pmu_cpumask, cpu); /* Migrate rapl events to the new target */ if (target < nr_cpu_ids) { @@ -565,6 +589,8 @@ static int rapl_cpu_offline(unsigned int cpu) static int rapl_cpu_online(unsigned int cpu) { + unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); + const struct cpumask *rapl_pmu_cpumask = get_rapl_pmu_cpumask(cpu); struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; @@ -579,14 +605,14 @@ 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, rapl_pmu_cpumask); if (target < nr_cpu_ids) return 0; @@ -675,7 +701,10 @@ 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)
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. Replacing these macros with their package counterparts fixes the energy-pkg event for AMD CPUs. However due to the difference between the scope of energy-pkg event for Intel and AMD CPUs, we have to replace these macros conditionally only for AMD CPUs. 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 Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Fixes: 63edbaa48a57 ("x86/cpu/topology: Add support for the AMD 0x80000026 leaf") --- Changes in v4: * Invert the pkg scope check in init_rapl_pmus() (Peter) * Add comments to explain the pkg scope check (Peter) PS: Scope check logic is still kept the same (i.e., all Intel systems being considered as die scope), Rui will be modifying it to limit the die-scope only to Cascadelake-AP in a future patch on top of this patchset. --- arch/x86/events/rapl.c | 39 ++++++++++++++++++++++++++++++++++----- 1 file changed, 34 insertions(+), 5 deletions(-)