KVM: x86/pmu: Drop amd_event_mapping[] in the KVM context

All gp or fixed counters have been reprogrammed using PERF_TYPE_RAW,
which means that the table that maps perf_hw_id to event select values is
no longer useful, at least for AMD.

For Intel, the logic to check if the pmu event reported by Intel cpuid is
not available is still required, in which case pmc_perf_hw_id() could be
renamed to hw_event_is_unavail() and a bool value is returned to replace
the semantics of "PERF_COUNT_HW_MAX+1".
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220518132512.37864-12-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm-x86-pmu-ops.h

@@ -12,7 +12,7 @@ BUILD_BUG_ON(1)
  * a NULL definition, for example if "static_call_cond()" will be used
  * at the call sites.
  */
-KVM_X86_PMU_OP(pmc_perf_hw_id)
+KVM_X86_PMU_OP(hw_event_available)
 KVM_X86_PMU_OP(pmc_is_enabled)
 KVM_X86_PMU_OP(pmc_idx_to_pmc)
 KVM_X86_PMU_OP(rdpmc_ecx_to_pmc)

arch/x86/kvm/pmu.c

@@ -158,9 +158,6 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 	};
 	bool pebs = test_bit(pmc->idx, (unsigned long *)&pmu->pebs_enable);
 
-	if (type == PERF_TYPE_HARDWARE && config >= PERF_COUNT_HW_MAX)
-		return;
-
 	attr.sample_period = get_sample_period(pmc, pmc->counter);
 
 	if ((attr.config & HSW_IN_TX_CHECKPOINTED) &&
@@ -258,6 +255,9 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc)
 	__u64 key;
 	int idx;
 
+	if (!static_call(kvm_x86_pmu_hw_event_available)(pmc))
+		return false;
+
 	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
 	if (!filter)
 		goto out;

arch/x86/kvm/pmu.h

@@ -22,7 +22,7 @@ struct kvm_event_hw_type_mapping {
 };
 
 struct kvm_pmu_ops {
-	unsigned int (*pmc_perf_hw_id)(struct kvm_pmc *pmc);
+	bool (*hw_event_available)(struct kvm_pmc *pmc);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
 	struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,

arch/x86/kvm/svm/pmu.c

@@ -33,34 +33,6 @@ enum index {
 	INDEX_ERROR,
 };
 
-/* duplicated from amd_perfmon_event_map, K7 and above should work. */
-static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
-	[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
-	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
-	[2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
-	[3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
-	[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
-	[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
-	[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
-	[7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
-};
-
-/* duplicated from amd_f17h_perfmon_event_map. */
-static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = {
-	[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
-	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
-	[2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES },
-	[3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES },
-	[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
-	[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
-	[6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
-	[7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
-};
-
-/* amd_pmc_perf_hw_id depends on these being the same size */
-static_assert(ARRAY_SIZE(amd_event_mapping) ==
-	     ARRAY_SIZE(amd_f17h_event_mapping));
-
 static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type)
 {
 	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
@@ -154,31 +126,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	return &pmu->gp_counters[msr_to_index(msr)];
 }
 
-static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc)
+static bool amd_hw_event_available(struct kvm_pmc *pmc)
 {
-	struct kvm_event_hw_type_mapping *event_mapping;
-	u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
-	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
-	int i;
-
-	/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */
-	if (WARN_ON(pmc_is_fixed(pmc)))
-		return PERF_COUNT_HW_MAX;
-
-	if (guest_cpuid_family(pmc->vcpu) >= 0x17)
-		event_mapping = amd_f17h_event_mapping;
-	else
-		event_mapping = amd_event_mapping;
-
-	for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++)
-		if (event_mapping[i].eventsel == event_select
-		    && event_mapping[i].unit_mask == unit_mask)
-			break;
-
-	if (i == ARRAY_SIZE(amd_event_mapping))
-		return PERF_COUNT_HW_MAX;
-
-	return event_mapping[i].event_type;
+	return true;
 }
 
 /* check if a PMC is enabled by comparing it against global_ctrl bits. Because
@@ -345,7 +295,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu)
 }
 
 struct kvm_pmu_ops amd_pmu_ops __initdata = {
-	.pmc_perf_hw_id = amd_pmc_perf_hw_id,
+	.hw_event_available = amd_hw_event_available,
 	.pmc_is_enabled = amd_pmc_is_enabled,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
 	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,

arch/x86/kvm/vmx/pmu_intel.c

@@ -84,7 +84,7 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
 	}
 }
 
-static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
+static bool intel_hw_event_available(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
@@ -98,15 +98,12 @@ static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
 
 		/* disable event that reported as not present by cpuid */
 		if ((i < 7) && !(pmu->available_event_types & (1 << i)))
-			return PERF_COUNT_HW_MAX + 1;
+			return false;
 
 		break;
 	}
 
-	if (i == ARRAY_SIZE(intel_arch_events))
-		return PERF_COUNT_HW_MAX;
-
-	return intel_arch_events[i].event_type;
+	return true;
 }
 
 /* check if a PMC is enabled by comparing it with globl_ctrl bits. */
@@ -814,7 +811,7 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu)
 }
 
 struct kvm_pmu_ops intel_pmu_ops __initdata = {
-	.pmc_perf_hw_id = intel_pmc_perf_hw_id,
+	.hw_event_available = intel_hw_event_available,
 	.pmc_is_enabled = intel_pmc_is_enabled,
 	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
 	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,