perf/x86/intel: Add CPUID enumeration for the auto counter reload

The counters that support the auto counter reload feature can be
enumerated in the CPUID Leaf 0x23 sub-leaf 0x2.

Add acr_cntr_mask to store the mask of counters which are reloadable.
Add acr_cause_mask to store the mask of counters which can cause reload.
Since the e-core and p-core may have different numbers of counters,
track the masks in the struct x86_hybrid_pmu as well.

Signed-off-by: Kan Liang <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Tested-by: Thomas Falcon <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Kan Liang

arch/x86/events/intel/core.c

@@ -5069,6 +5069,16 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 		pmu->fixed_cntr_mask64 = fixed_cntr;
 	}
 
+	if (eax.split.acr_subleaf) {
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
+			    &cntr, &fixed_cntr, &ecx, &edx);
+		/* The mask of the counters which can be reloaded */
+		pmu->acr_cntr_mask64 = cntr | ((u64)fixed_cntr << INTEL_PMC_IDX_FIXED);
+
+		/* The mask of the counters which can cause a reload of reloadable counters */
+		pmu->acr_cause_mask64 = ecx | ((u64)edx << INTEL_PMC_IDX_FIXED);
+	}
+
 	if (!intel_pmu_broken_perf_cap()) {
 		/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
 		rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);

arch/x86/events/perf_event.h

@@ -708,6 +708,15 @@ struct x86_hybrid_pmu {
 			u64		fixed_cntr_mask64;
 			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	};
+
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	struct event_constraint		unconstrained;
 
 	u64				hw_cache_event_ids
@@ -806,6 +815,14 @@ struct x86_pmu {
 			u64		fixed_cntr_mask64;
 			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	};
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	int		cntval_bits;
 	u64		cntval_mask;
 	union {

arch/x86/include/asm/perf_event.h

@@ -195,6 +195,7 @@ union cpuid10_edx {
  */
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
+#define ARCH_PERFMON_ACR_LEAF			0x2
 
 union cpuid35_eax {
 	struct {