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.

So, change the PMU scope for AMD and Hygon back to package.

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>
---
v4 Link: https://lore.kernel.org/all/20240905153821.3822-1-Dhananjay.Ugwekar@amd.com/ 

Changes from v4:
* Rebase on top of a fix [1] in the PMU scope patchset [2]

Base: tip/perf/core + PMU scope patchset [2] 

[1]: https://lore.kernel.org/all/8c09633c-5bf2-48a2-91a6-a0af9b9f2e8c@linux.intel.com/
[2]: https://lore.kernel.org/all/20240802151643.1691631-1-kan.liang@linux.intel.com/
---
 arch/x86/events/rapl.c | 35 ++++++++++++++++++++++++++++++++---
 1 file changed, 32 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 0f8f4eb01278..ce04dc5844c4 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -139,9 +139,32 @@ static unsigned int rapl_cntr_mask;
 static u64 rapl_timer_ms;
 static struct perf_msr *rapl_msrs;
 
+/*
+ * 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)
+
+/*
+ * Helper function to get the correct topology id 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 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
@@ -617,7 +640,7 @@ static void __init init_rapl_pmu(void)
 		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[get_rapl_pmu_idx(cpu)] = pmu;
 	}
 
 	cpus_read_unlock();
@@ -626,6 +649,12 @@ static void __init init_rapl_pmu(void)
 static int __init init_rapl_pmus(void)
 {
 	int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package();
+	int rapl_pmu_scope = PERF_PMU_SCOPE_DIE;
+
+	if (rapl_pmu_is_pkg_scope()) {
+		nr_rapl_pmu		= topology_max_packages();
+		rapl_pmu_scope		= PERF_PMU_SCOPE_PKG;
+	}
 
 	rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL);
 	if (!rapl_pmus)
@@ -641,8 +670,8 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.start		= rapl_pmu_event_start;
 	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
+	rapl_pmus->pmu.scope		= rapl_pmu_scope;
 	rapl_pmus->pmu.module		= THIS_MODULE;
-	rapl_pmus->pmu.scope		= PERF_PMU_SCOPE_DIE;
 	rapl_pmus->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
 
 	init_rapl_pmu();
-- 
2.34.1