[PATCH 12/15] perf/x86/intel: Make ACR static_call update architectural

[Dapeng Mi]

Auto counter reload (ACR) is an architectural feature, but the
intel_pmu_enable_acr_event() static_call update is currently done in a
model-specific way.

This is only necessary because older platforms such as PTL/WCL only
support ACR on E-core, which made the boot-time capability check on
P-core impossible in the generic init path. Later platforms such as
DMR/NVL support ACR on booting P-core and can detect it architecturally.

Make the intel_pmu_enable_acr_event() static_call update architectural
so ACR can be enabled correctly on supported CPUs without relying on
model-specific setup.

Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
---
 arch/x86/events/intel/core.c | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3fc3795534bf..0d360fba4b79 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6365,6 +6365,25 @@ static inline void __intel_update_large_pebs_flags(struct pmu *pmu)
 
 #define counter_mask(_gp, _fixed) ((_gp) | ((u64)(_fixed) << INTEL_PMC_IDX_FIXED))
 
+static bool intel_pmu_support_acr(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	union cpuid35_eax eax_0;
+	union cpuid35_ebx ebx_0;
+
+	if (!this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
+		return false;
+
+	cpuid(ARCH_PERFMON_EXT_LEAF, &eax_0.full, &ebx_0.full, &ecx, &edx);
+	if (eax_0.split.acr_subleaf) {
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
+			    &eax, &ebx, &ecx, &edx);
+		return !!counter_mask(eax, ebx);
+	}
+
+	return false;
+}
+
 static void update_pmu_cap_from_perfmonext(struct pmu *pmu)
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -8112,7 +8131,6 @@ static __always_inline void intel_pmu_init_pnc(struct pmu *pmu)
 	hybrid(pmu, event_constraints) = intel_pnc_event_constraints;
 	hybrid(pmu, pebs_constraints) = intel_pnc_pebs_event_constraints;
 	hybrid(pmu, extra_regs) = intel_pnc_extra_regs;
-	static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
 }
 
 static __always_inline void intel_pmu_init_cyc(struct pmu *pmu)
@@ -8160,7 +8178,6 @@ static __always_inline void intel_pmu_init_arw(struct pmu *pmu)
 	hybrid(pmu, event_constraints) = intel_arw_event_constraints;
 	hybrid(pmu, pebs_constraints) = intel_dkt_pebs_event_constraints;
 	hybrid(pmu, extra_regs) = intel_arw_extra_regs;
-	static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
 }
 
 __init int intel_pmu_init(void)
@@ -9127,6 +9144,12 @@ __init int intel_pmu_init(void)
 	if (!is_hybrid())
 		intel_update_pmu_caps(NULL);
 
+	if (x86_pmu.acr_cntr_mask64 || intel_pmu_support_acr()) {
+		static_call_update(intel_pmu_enable_acr_event,
+				   intel_pmu_enable_acr);
+		pr_cont("Auto counter reload, ");
+	}
+
 	if (x86_pmu.arch_pebs) {
 		static_call_update(intel_pmu_disable_event_ext,
 				   intel_pmu_disable_event_ext);
-- 
2.34.1