1 files changed, 96 insertions, 182 deletions

diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 035da07500e8..bc062285fbf5 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -9,6 +9,8 @@
  *
  * Implementation is based on pmu_intel.c file
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
@@ -16,192 +18,76 @@
 #include "cpuid.h"
 #include "lapic.h"
 #include "pmu.h"
+#include "svm.h"
 
 enum pmu_type {
 	PMU_TYPE_COUNTER = 0,
 	PMU_TYPE_EVNTSEL,
 };
 
-enum index {
-	INDEX_ZERO = 0,
-	INDEX_ONE,
-	INDEX_TWO,
-	INDEX_THREE,
-	INDEX_FOUR,
-	INDEX_FIVE,
-	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 },
-};
-
-static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type)
+static struct kvm_pmc *amd_pmu_get_pmc(struct kvm_pmu *pmu, int pmc_idx)
 {
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+	unsigned int num_counters = pmu->nr_arch_gp_counters;
 
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
-		if (type == PMU_TYPE_COUNTER)
-			return MSR_F15H_PERF_CTR;
-		else
-			return MSR_F15H_PERF_CTL;
-	} else {
-		if (type == PMU_TYPE_COUNTER)
-			return MSR_K7_PERFCTR0;
-		else
-			return MSR_K7_EVNTSEL0;
-	}
-}
+	if (pmc_idx >= num_counters)
+		return NULL;
 
-static enum index msr_to_index(u32 msr)
-{
-	switch (msr) {
-	case MSR_F15H_PERF_CTL0:
-	case MSR_F15H_PERF_CTR0:
-	case MSR_K7_EVNTSEL0:
-	case MSR_K7_PERFCTR0:
-		return INDEX_ZERO;
-	case MSR_F15H_PERF_CTL1:
-	case MSR_F15H_PERF_CTR1:
-	case MSR_K7_EVNTSEL1:
-	case MSR_K7_PERFCTR1:
-		return INDEX_ONE;
-	case MSR_F15H_PERF_CTL2:
-	case MSR_F15H_PERF_CTR2:
-	case MSR_K7_EVNTSEL2:
-	case MSR_K7_PERFCTR2:
-		return INDEX_TWO;
-	case MSR_F15H_PERF_CTL3:
-	case MSR_F15H_PERF_CTR3:
-	case MSR_K7_EVNTSEL3:
-	case MSR_K7_PERFCTR3:
-		return INDEX_THREE;
-	case MSR_F15H_PERF_CTL4:
-	case MSR_F15H_PERF_CTR4:
-		return INDEX_FOUR;
-	case MSR_F15H_PERF_CTL5:
-	case MSR_F15H_PERF_CTR5:
-		return INDEX_FIVE;
-	default:
-		return INDEX_ERROR;
-	}
+	return &pmu->gp_counters[array_index_nospec(pmc_idx, num_counters)];
 }
 
 static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 					     enum pmu_type type)
 {
+	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+	unsigned int idx;
+
+	if (!pmu->version)
+		return NULL;
+
 	switch (msr) {
-	case MSR_F15H_PERF_CTL0:
-	case MSR_F15H_PERF_CTL1:
-	case MSR_F15H_PERF_CTL2:
-	case MSR_F15H_PERF_CTL3:
-	case MSR_F15H_PERF_CTL4:
-	case MSR_F15H_PERF_CTL5:
+	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
+		if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		/*
+		 * Each PMU counter has a pair of CTL and CTR MSRs. CTLn
+		 * MSRs (accessed via EVNTSEL) are even, CTRn MSRs are odd.
+		 */
+		idx = (unsigned int)((msr - MSR_F15H_PERF_CTL0) / 2);
+		if (!(msr & 0x1) != (type == PMU_TYPE_EVNTSEL))
+			return NULL;
+		break;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
 		if (type != PMU_TYPE_EVNTSEL)
 			return NULL;
+		idx = msr - MSR_K7_EVNTSEL0;
 		break;
-	case MSR_F15H_PERF_CTR0:
-	case MSR_F15H_PERF_CTR1:
-	case MSR_F15H_PERF_CTR2:
-	case MSR_F15H_PERF_CTR3:
-	case MSR_F15H_PERF_CTR4:
-	case MSR_F15H_PERF_CTR5:
 	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
 		if (type != PMU_TYPE_COUNTER)
 			return NULL;
+		idx = msr - MSR_K7_PERFCTR0;
 		break;
 	default:
 		return NULL;
 	}
 
-	return &pmu->gp_counters[msr_to_index(msr)];
+	return amd_pmu_get_pmc(pmu, idx);
 }
 
-static unsigned amd_find_arch_event(struct kvm_pmu *pmu,
-				    u8 event_select,
-				    u8 unit_mask)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++)
-		if (amd_event_mapping[i].eventsel == event_select
-		    && amd_event_mapping[i].unit_mask == unit_mask)
-			break;
-
-	if (i == ARRAY_SIZE(amd_event_mapping))
-		return PERF_COUNT_HW_MAX;
-
-	return amd_event_mapping[i].event_type;
-}
-
-/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */
-static unsigned amd_find_fixed_event(int idx)
-{
-	return PERF_COUNT_HW_MAX;
-}
-
-/* check if a PMC is enabled by comparing it against global_ctrl bits. Because
- * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE).
- */
-static bool amd_pmc_is_enabled(struct kvm_pmc *pmc)
-{
-	return true;
-}
-
-static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
-{
-	unsigned int base = get_msr_base(pmu, PMU_TYPE_COUNTER);
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
-
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
-		/*
-		 * The idx is contiguous. The MSRs are not. The counter MSRs
-		 * are interleaved with the event select MSRs.
-		 */
-		pmc_idx *= 2;
-	}
-
-	return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER);
-}
-
-/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+static int amd_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
-	idx &= ~(3u << 30);
+	if (idx >= pmu->nr_arch_gp_counters)
+		return -EINVAL;
 
-	return (idx >= pmu->nr_arch_gp_counters);
+	return 0;
 }
 
 /* idx is the ECX register of RDPMC instruction */
 static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 	unsigned int idx, u64 *mask)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	struct kvm_pmc *counters;
-
-	idx &= ~(3u << 30);
-	if (idx >= pmu->nr_arch_gp_counters)
-		return NULL;
-	counters = pmu->gp_counters;
-
-	return &counters[idx];
-}
-
-static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
-{
-	/* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough.  */
-	return false;
+	return amd_pmu_get_pmc(vcpu_to_pmu(vcpu), idx);
 }
 
 static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
@@ -215,6 +101,30 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
 	return pmc;
 }
 
+static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	switch (msr) {
+	case MSR_K7_EVNTSEL0 ... MSR_K7_PERFCTR3:
+		return pmu->version > 0;
+	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
+		return guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE);
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET:
+		return pmu->version > 1;
+	default:
+		if (msr > MSR_F15H_PERF_CTR5 &&
+		    msr < MSR_F15H_PERF_CTL0 + 2 * pmu->nr_arch_gp_counters)
+			return pmu->version > 1;
+		break;
+	}
+
+	return amd_msr_idx_to_pmc(vcpu, msr);
+}
+
 static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -247,18 +157,18 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	/* MSR_PERFCTRn */
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
 	if (pmc) {
-		pmc->counter += data - pmc_read_counter(pmc);
+		pmc_write_counter(pmc, data);
 		return 0;
 	}
 	/* MSR_EVNTSELn */
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
 	if (pmc) {
-		if (data == pmc->eventsel)
-			return 0;
-		if (!(data & pmu->reserved_bits)) {
-			reprogram_gp_counter(pmc, data);
-			return 0;
+		data &= ~pmu->reserved_bits;
+		if (data != pmc->eventsel) {
+			pmc->eventsel = data;
+			kvm_pmu_request_counter_reprogram(pmc);
 		}
+		return 0;
 	}
 
 	return 1;
@@ -267,20 +177,39 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	union cpuid_0x80000022_ebx ebx;
 
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+	pmu->version = 1;
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFMON_V2)) {
+		pmu->version = 2;
+		/*
+		 * Note, PERFMON_V2 is also in 0x80000022.0x0, i.e. the guest
+		 * CPUID entry is guaranteed to be non-NULL.
+		 */
+		BUILD_BUG_ON(x86_feature_cpuid(X86_FEATURE_PERFMON_V2).function != 0x80000022 ||
+			     x86_feature_cpuid(X86_FEATURE_PERFMON_V2).index);
+		ebx.full = kvm_find_cpuid_entry_index(vcpu, 0x80000022, 0)->ebx;
+		pmu->nr_arch_gp_counters = ebx.split.num_core_pmc;
+	} else if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS_CORE;
-	else
+	} else {
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
+	}
 
-	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
-	pmu->reserved_bits = 0xffffffff00200000ull;
-	pmu->version = 1;
+	pmu->nr_arch_gp_counters = min_t(unsigned int, pmu->nr_arch_gp_counters,
+					 kvm_pmu_cap.num_counters_gp);
+
+	if (pmu->version > 1) {
+		pmu->global_ctrl_rsvd = ~(BIT_ULL(pmu->nr_arch_gp_counters) - 1);
+		pmu->global_status_rsvd = pmu->global_ctrl_rsvd;
+	}
+
+	pmu->counter_bitmask[KVM_PMC_GP] = BIT_ULL(48) - 1;
+	pmu->reserved_bits = 0xfffffff000280000ull;
+	pmu->raw_event_mask = AMD64_RAW_EVENT_MASK;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
-	pmu->global_status = 0;
-	bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters);
 }
 
 static void amd_pmu_init(struct kvm_vcpu *vcpu)
@@ -288,9 +217,9 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	int i;
 
-	BUILD_BUG_ON(AMD64_NUM_COUNTERS_CORE > INTEL_PMC_MAX_GENERIC);
+	BUILD_BUG_ON(KVM_MAX_NR_AMD_GP_COUNTERS > AMD64_NUM_COUNTERS_CORE);
 
-	for (i = 0; i < AMD64_NUM_COUNTERS_CORE ; i++) {
+	for (i = 0; i < KVM_MAX_NR_AMD_GP_COUNTERS; i++) {
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
@@ -298,31 +227,16 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void amd_pmu_reset(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	int i;
-
-	for (i = 0; i < AMD64_NUM_COUNTERS_CORE; i++) {
-		struct kvm_pmc *pmc = &pmu->gp_counters[i];
-
-		pmc_stop_counter(pmc);
-		pmc->counter = pmc->eventsel = 0;
-	}
-}
-
-struct kvm_pmu_ops amd_pmu_ops = {
-	.find_arch_event = amd_find_arch_event,
-	.find_fixed_event = amd_find_fixed_event,
-	.pmc_is_enabled = amd_pmc_is_enabled,
-	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
+struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
-	.is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx,
+	.check_rdpmc_early = amd_check_rdpmc_early,
 	.is_valid_msr = amd_is_valid_msr,
 	.get_msr = amd_pmu_get_msr,
 	.set_msr = amd_pmu_set_msr,
 	.refresh = amd_pmu_refresh,
 	.init = amd_pmu_init,
-	.reset = amd_pmu_reset,
+	.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
+	.MAX_NR_GP_COUNTERS = KVM_MAX_NR_AMD_GP_COUNTERS,
+	.MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS,
 };