@@ -103,6 +103,18 @@ static struct perf_pmu_events_attr event_attr_##v = { \
.event_str = str, \
};
+/*
+ * Intel systems that enumerate DIE domain have RAPL domains implemented
+ * per-die, however, the same is not true for AMD and Hygon processors
+ * where RAPL domains for PKG energy are in-fact per-PKG. Since
+ * logical_die_id is same as logical_package_id in absence of DIE
+ * enumeration, use topology_logical_die_id() on Intel systems and
+ * topology_logical_package_id() on AMD and Hygon systems.
+ */
+#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 +152,25 @@ 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 +571,7 @@ 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 +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(rapl_pmu_cpumask, cpu);
/* Migrate rapl events to the new target */
if (target < nr_cpu_ids) {
@@ -565,10 +594,12 @@ static int rapl_cpu_offline(unsigned int cpu)
static int rapl_cpu_online(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;
if (!pmu) {
+ unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu);
pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
if (!pmu)
return -ENOMEM;
@@ -579,14 +610,14 @@ 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 +706,10 @@ 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)