Merge tag 'kvm-x86-pmu-6.9' of https://github.com/kvm-x86/linux into HEAD

KVM x86 PMU changes for 6.9:

 - Fix several bugs where KVM speciously prevents the guest from utilizing
   fixed counters and architectural event encodings based on whether or not
   guest CPUID reports support for the _architectural_ encoding.

 - Fix a variety of bugs in KVM's emulation of RDPMC, e.g. for "fast" reads,
   priority of VMX interception vs #GP, PMC types in architectural PMUs, etc.

 - Add a selftest to verify KVM correctly emulates RDMPC, counter availability,
   and a variety of other PMC-related behaviors that depend on guest CPUID,
   i.e. are difficult to validate via KVM-Unit-Tests.

 - Zero out PMU metadata on AMD if the virtual PMU is disabled to avoid wasting
   cycles, e.g. when checking if a PMC event needs to be synthesized when
   skipping an instruction.

 - Optimize triggering of emulated events, e.g. for "count instructions" events
   when skipping an instruction, which yields a ~10% performance improvement in
   VM-Exit microbenchmarks when a vPMU is exposed to the guest.

 - Tighten the check for "PMI in guest" to reduce false positives if an NMI
   arrives in the host while KVM is handling an IRQ VM-Exit.

11 files changed, 267 insertions, 237 deletions

diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index 058bc636356a..f852b13aeefe 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -12,11 +12,9 @@ BUILD_BUG_ON(1)
  * a NULL definition, for example if "static_call_cond()" will be used
  * at the call sites.
  */
-KVM_X86_PMU_OP(hw_event_available)
-KVM_X86_PMU_OP(pmc_idx_to_pmc)
 KVM_X86_PMU_OP(rdpmc_ecx_to_pmc)
 KVM_X86_PMU_OP(msr_idx_to_pmc)
-KVM_X86_PMU_OP(is_valid_rdpmc_ecx)
+KVM_X86_PMU_OP_OPTIONAL(check_rdpmc_early)
 KVM_X86_PMU_OP(is_valid_msr)
 KVM_X86_PMU_OP(get_msr)
 KVM_X86_PMU_OP(set_msr)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8116839cb263..9e7b1a00e265 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,6 +536,7 @@ struct kvm_pmc {
 #define KVM_PMC_MAX_FIXED	3
 #define MSR_ARCH_PERFMON_FIXED_CTR_MAX	(MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1)
 #define KVM_AMD_PMC_MAX_GENERIC	6
+
 struct kvm_pmu {
 	u8 version;
 	unsigned nr_arch_gp_counters;
@@ -1889,8 +1890,16 @@ static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
 }
 #endif /* CONFIG_HYPERV */
 
+enum kvm_intr_type {
+	/* Values are arbitrary, but must be non-zero. */
+	KVM_HANDLING_IRQ = 1,
+	KVM_HANDLING_NMI,
+};
+
+/* Enable perf NMI and timer modes to work, and minimise false positives. */
 #define kvm_arch_pmi_in_guest(vcpu) \
-	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
+	((vcpu) && (vcpu)->arch.handling_intr_from_guest && \
+	 (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI)))
 
 void __init kvm_mmu_x86_module_init(void);
 int kvm_mmu_vendor_module_init(void);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 3328c7c7f2f9..5d4c86133453 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3955,7 +3955,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
 	 * protected mode.
 	 */
 	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) ||
-	    ctxt->ops->check_pmc(ctxt, rcx))
+	    ctxt->ops->check_rdpmc_early(ctxt, rcx))
 		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 153977c556f4..5382646162a3 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -208,7 +208,7 @@ struct x86_emulate_ops {
 	int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
 	int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
 	int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
-	int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
+	int (*check_rdpmc_early)(struct x86_emulate_ctxt *ctxt, u32 pmc);
 	int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata);
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 87cc6c8809ad..c397b28e3d1b 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -29,6 +29,9 @@
 struct x86_pmu_capability __read_mostly kvm_pmu_cap;
 EXPORT_SYMBOL_GPL(kvm_pmu_cap);
 
+struct kvm_pmu_emulated_event_selectors __read_mostly kvm_pmu_eventsel;
+EXPORT_SYMBOL_GPL(kvm_pmu_eventsel);
+
 /* Precise Distribution of Instructions Retired (PDIR) */
 static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL),
@@ -67,7 +70,7 @@ static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = {
  *        all perf counters (both gp and fixed). The mapping relationship
  *        between pmc and perf counters is as the following:
  *        * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters
- *                 [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed
+ *                 [KVM_FIXED_PMC_BASE_IDX .. KVM_FIXED_PMC_BASE_IDX + 2] <=> fixed
  *        * AMD:   [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H
  *          and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters
  */
@@ -411,7 +414,7 @@ static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f,
 static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter,
 				   int idx)
 {
-	int fixed_idx = idx - INTEL_PMC_IDX_FIXED;
+	int fixed_idx = idx - KVM_FIXED_PMC_BASE_IDX;
 
 	if (filter->action == KVM_PMU_EVENT_DENY &&
 	    test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap))
@@ -441,11 +444,10 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc)
 static bool pmc_event_is_allowed(struct kvm_pmc *pmc)
 {
 	return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) &&
-	       static_call(kvm_x86_pmu_hw_event_available)(pmc) &&
 	       check_pmu_event_filter(pmc);
 }
 
-static void reprogram_counter(struct kvm_pmc *pmc)
+static int reprogram_counter(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	u64 eventsel = pmc->eventsel;
@@ -456,7 +458,7 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 	emulate_overflow = pmc_pause_counter(pmc);
 
 	if (!pmc_event_is_allowed(pmc))
-		goto reprogram_complete;
+		return 0;
 
 	if (emulate_overflow)
 		__kvm_perf_overflow(pmc, false);
@@ -466,7 +468,7 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 
 	if (pmc_is_fixed(pmc)) {
 		fixed_ctr_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl,
-						  pmc->idx - INTEL_PMC_IDX_FIXED);
+						  pmc->idx - KVM_FIXED_PMC_BASE_IDX);
 		if (fixed_ctr_ctrl & 0x1)
 			eventsel |= ARCH_PERFMON_EVENTSEL_OS;
 		if (fixed_ctr_ctrl & 0x2)
@@ -477,43 +479,45 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 	}
 
 	if (pmc->current_config == new_config && pmc_resume_counter(pmc))
-		goto reprogram_complete;
+		return 0;
 
 	pmc_release_perf_event(pmc);
 
 	pmc->current_config = new_config;
 
-	/*
-	 * If reprogramming fails, e.g. due to contention, leave the counter's
-	 * regprogram bit set, i.e. opportunistically try again on the next PMU
-	 * refresh.  Don't make a new request as doing so can stall the guest
-	 * if reprogramming repeatedly fails.
-	 */
-	if (pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
-				  (eventsel & pmu->raw_event_mask),
-				  !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
-				  !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-				  eventsel & ARCH_PERFMON_EVENTSEL_INT))
-		return;
-
-reprogram_complete:
-	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+	return pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
+				     (eventsel & pmu->raw_event_mask),
+				     !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+				     !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+				     eventsel & ARCH_PERFMON_EVENTSEL_INT);
 }
 
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 {
+	DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
 	int bit;
 
-	for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
-		struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, bit);
+	bitmap_copy(bitmap, pmu->reprogram_pmi, X86_PMC_IDX_MAX);
 
-		if (unlikely(!pmc)) {
-			clear_bit(bit, pmu->reprogram_pmi);
-			continue;
-		}
+	/*
+	 * The reprogramming bitmap can be written asynchronously by something
+	 * other than the task that holds vcpu->mutex, take care to clear only
+	 * the bits that will actually processed.
+	 */
+	BUILD_BUG_ON(sizeof(bitmap) != sizeof(atomic64_t));
+	atomic64_andnot(*(s64 *)bitmap, &pmu->__reprogram_pmi);
 
-		reprogram_counter(pmc);
+	kvm_for_each_pmc(pmu, pmc, bit, bitmap) {
+		/*
+		 * If reprogramming fails, e.g. due to contention, re-set the
+		 * regprogram bit set, i.e. opportunistically try again on the
+		 * next PMU refresh.  Don't make a new request as doing so can
+		 * stall the guest if reprogramming repeatedly fails.
+		 */
+		if (reprogram_counter(pmc))
+			set_bit(pmc->idx, pmu->reprogram_pmi);
 	}
 
 	/*
@@ -525,10 +529,20 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 		kvm_pmu_cleanup(vcpu);
 }
 
-/* check if idx is a valid index to access PMU */
-bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx)
 {
-	return static_call(kvm_x86_pmu_is_valid_rdpmc_ecx)(vcpu, idx);
+	/*
+	 * On Intel, VMX interception has priority over RDPMC exceptions that
+	 * aren't already handled by the emulator, i.e. there are no additional
+	 * check needed for Intel PMUs.
+	 *
+	 * On AMD, _all_ exceptions on RDPMC have priority over SVM intercepts,
+	 * i.e. an invalid PMC results in a #GP, not #VMEXIT.
+	 */
+	if (!kvm_pmu_ops.check_rdpmc_early)
+		return 0;
+
+	return static_call(kvm_x86_pmu_check_rdpmc_early)(vcpu, idx);
 }
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx)
@@ -567,10 +581,9 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
-	bool fast_mode = idx & (1u << 31);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
-	u64 mask = fast_mode ? ~0u : ~0ull;
+	u64 mask = ~0ull;
 
 	if (!pmu->version)
 		return 1;
@@ -716,11 +729,7 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 
 	bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX);
 
-	for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) {
-		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
-		if (!pmc)
-			continue;
-
+	kvm_for_each_pmc(pmu, pmc, i, pmu->all_valid_pmc_idx) {
 		pmc_stop_counter(pmc);
 		pmc->counter = 0;
 		pmc->emulated_counter = 0;
@@ -741,6 +750,8 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
  */
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
 	if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm))
 		return;
 
@@ -750,8 +761,22 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 	 */
 	kvm_pmu_reset(vcpu);
 
-	bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX);
-	static_call(kvm_x86_pmu_refresh)(vcpu);
+	pmu->version = 0;
+	pmu->nr_arch_gp_counters = 0;
+	pmu->nr_arch_fixed_counters = 0;
+	pmu->counter_bitmask[KVM_PMC_GP] = 0;
+	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
+	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->raw_event_mask = X86_RAW_EVENT_MASK;
+	pmu->global_ctrl_mask = ~0ull;
+	pmu->global_status_mask = ~0ull;
+	pmu->fixed_ctr_ctrl_mask = ~0ull;
+	pmu->pebs_enable_mask = ~0ull;
+	pmu->pebs_data_cfg_mask = ~0ull;
+	bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX);
+
+	if (vcpu->kvm->arch.enable_pmu)
+		static_call(kvm_x86_pmu_refresh)(vcpu);
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
@@ -776,10 +801,8 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
 	bitmap_andnot(bitmask, pmu->all_valid_pmc_idx,
 		      pmu->pmc_in_use, X86_PMC_IDX_MAX);
 
-	for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) {
-		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
-
-		if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
+	kvm_for_each_pmc(pmu, pmc, i, bitmask) {
+		if (pmc->perf_event && !pmc_speculative_in_use(pmc))
 			pmc_stop_counter(pmc);
 	}
 
@@ -799,13 +822,6 @@ static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
 	kvm_pmu_request_counter_reprogram(pmc);
 }
 
-static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
-	unsigned int perf_hw_id)
-{
-	return !((pmc->eventsel ^ perf_get_hw_event_config(perf_hw_id)) &
-		AMD64_RAW_EVENT_MASK_NB);
-}
-
 static inline bool cpl_is_matched(struct kvm_pmc *pmc)
 {
 	bool select_os, select_user;
@@ -817,29 +833,56 @@ static inline bool cpl_is_matched(struct kvm_pmc *pmc)
 		select_user = config & ARCH_PERFMON_EVENTSEL_USR;
 	} else {
 		config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl,
-					  pmc->idx - INTEL_PMC_IDX_FIXED);
+					  pmc->idx - KVM_FIXED_PMC_BASE_IDX);
 		select_os = config & 0x1;
 		select_user = config & 0x2;
 	}
 
+	/*
+	 * Skip the CPL lookup, which isn't free on Intel, if the result will
+	 * be the same regardless of the CPL.
+	 */
+	if (select_os == select_user)
+		return select_os;
+
 	return (static_call(kvm_x86_get_cpl)(pmc->vcpu) == 0) ? select_os : select_user;
 }
 
-void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id)
+void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel)
 {
+	DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
 	int i;
 
-	for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) {
-		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
+	BUILD_BUG_ON(sizeof(pmu->global_ctrl) * BITS_PER_BYTE != X86_PMC_IDX_MAX);
 
-		if (!pmc || !pmc_event_is_allowed(pmc))
+	if (!kvm_pmu_has_perf_global_ctrl(pmu))
+		bitmap_copy(bitmap, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX);
+	else if (!bitmap_and(bitmap, pmu->all_valid_pmc_idx,
+			     (unsigned long *)&pmu->global_ctrl, X86_PMC_IDX_MAX))
+		return;
+
+	kvm_for_each_pmc(pmu, pmc, i, bitmap) {
+		/*
+		 * Ignore checks for edge detect (all events currently emulated
+		 * but KVM are always rising edges), pin control (unsupported
+		 * by modern CPUs), and counter mask and its invert flag (KVM
+		 * doesn't emulate multiple events in a single clock cycle).
+		 *
+		 * Note, the uppermost nibble of AMD's mask overlaps Intel's
+		 * IN_TX (bit 32) and IN_TXCP (bit 33), as well as two reserved
+		 * bits (bits 35:34).  Checking the "in HLE/RTM transaction"
+		 * flags is correct as the vCPU can't be in a transaction if
+		 * KVM is emulating an instruction.  Checking the reserved bits
+		 * might be wrong if they are defined in the future, but so
+		 * could ignoring them, so do the simple thing for now.
+		 */
+		if (((pmc->eventsel ^ eventsel) & AMD64_RAW_EVENT_MASK_NB) ||
+		    !pmc_event_is_allowed(pmc) || !cpl_is_matched(pmc))
 			continue;
 
-		/* Ignore checks for edge detect, pin control, invert and CMASK bits */
-		if (eventsel_match_perf_hw_id(pmc, perf_hw_id) && cpl_is_matched(pmc))
-			kvm_pmu_incr_counter(pmc);
+		kvm_pmu_incr_counter(pmc);
 	}
 }
 EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 7caeb3d8d4fd..4d52b0b539ba 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -4,6 +4,8 @@
 
 #include <linux/nospec.h>
 
+#include <asm/kvm_host.h>
+
 #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu)
 #define pmu_to_vcpu(pmu)  (container_of((pmu), struct kvm_vcpu, arch.pmu))
 #define pmc_to_pmu(pmc)   (&(pmc)->vcpu->arch.pmu)
@@ -18,13 +20,18 @@
 #define VMWARE_BACKDOOR_PMC_REAL_TIME		0x10001
 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME	0x10002
 
+#define KVM_FIXED_PMC_BASE_IDX INTEL_PMC_IDX_FIXED
+
+struct kvm_pmu_emulated_event_selectors {
+	u64 INSTRUCTIONS_RETIRED;
+	u64 BRANCH_INSTRUCTIONS_RETIRED;
+};
+
 struct kvm_pmu_ops {
-	bool (*hw_event_available)(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,
 		unsigned int idx, u64 *mask);
 	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr);
-	bool (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx);
+	int (*check_rdpmc_early)(struct kvm_vcpu *vcpu, unsigned int idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -55,6 +62,38 @@ static inline bool kvm_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu)
 	return pmu->version > 1;
 }
 
+/*
+ * KVM tracks all counters in 64-bit bitmaps, with general purpose counters
+ * mapped to bits 31:0 and fixed counters mapped to 63:32, e.g. fixed counter 0
+ * is tracked internally via index 32.  On Intel, (AMD doesn't support fixed
+ * counters), this mirrors how fixed counters are mapped to PERF_GLOBAL_CTRL
+ * and similar MSRs, i.e. tracking fixed counters at base index 32 reduces the
+ * amounter of boilerplate needed to iterate over PMCs *and* simplifies common
+ * enabling/disable/reset operations.
+ *
+ * WARNING!  This helper is only for lookups that are initiated by KVM, it is
+ * NOT safe for guest lookups, e.g. will do the wrong thing if passed a raw
+ * ECX value from RDPMC (fixed counters are accessed by setting bit 30 in ECX
+ * for RDPMC, not by adding 32 to the fixed counter index).
+ */
+static inline struct kvm_pmc *kvm_pmc_idx_to_pmc(struct kvm_pmu *pmu, int idx)
+{
+	if (idx < pmu->nr_arch_gp_counters)
+		return &pmu->gp_counters[idx];
+
+	idx -= KVM_FIXED_PMC_BASE_IDX;
+	if (idx >= 0 && idx < pmu->nr_arch_fixed_counters)
+		return &pmu->fixed_counters[idx];
+
+	return NULL;
+}
+
+#define kvm_for_each_pmc(pmu, pmc, i, bitmap)			\
+	for_each_set_bit(i, bitmap, X86_PMC_IDX_MAX)		\
+		if (!(pmc = kvm_pmc_idx_to_pmc(pmu, i)))	\
+			continue;				\
+		else						\
+
 static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -131,12 +170,13 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
 
 	if (pmc_is_fixed(pmc))
 		return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
-					pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
+					pmc->idx - KVM_FIXED_PMC_BASE_IDX) & 0x3;
 
 	return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
 }
 
 extern struct x86_pmu_capability kvm_pmu_cap;
+extern struct kvm_pmu_emulated_event_selectors kvm_pmu_eventsel;
 
 static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops)
 {
@@ -178,6 +218,11 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops)
 					  pmu_ops->MAX_NR_GP_COUNTERS);
 	kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed,
 					     KVM_PMC_MAX_FIXED);
+
+	kvm_pmu_eventsel.INSTRUCTIONS_RETIRED =
+		perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS);
+	kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED =
+		perf_get_hw_event_config(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 }
 
 static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc)
@@ -216,7 +261,7 @@ static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc)
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
+int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx);
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -225,7 +270,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu);
 void kvm_pmu_cleanup(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
-void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id);
+void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel);
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx);
 
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index b6a7ad4d6914..dfcc38bd97d3 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -25,7 +25,7 @@ enum pmu_type {
 	PMU_TYPE_EVNTSEL,
 };
 
-static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
+static struct kvm_pmc *amd_pmu_get_pmc(struct kvm_pmu *pmu, int pmc_idx)
 {
 	unsigned int num_counters = pmu->nr_arch_gp_counters;
 
@@ -70,28 +70,24 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 		return NULL;
 	}
 
-	return amd_pmc_idx_to_pmc(pmu, idx);
+	return amd_pmu_get_pmc(pmu, idx);
 }
 
-static bool amd_hw_event_available(struct kvm_pmc *pmc)
-{
-	return true;
-}
-
-static bool 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)
 {
-	return amd_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30));
+	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)
@@ -233,11 +229,9 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 }
 
 struct kvm_pmu_ops amd_pmu_ops __initdata = {
-	.hw_event_available = amd_hw_event_available,
-	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
 	.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,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0cd977f22c4b..d05ddf751491 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3606,7 +3606,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return 1;
 	}
 
-	kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+	kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);
 
 	if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
 		return nested_vmx_failInvalid(vcpu);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 315c7c2ba89b..12ade343a17e 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -20,53 +20,19 @@
 #include "nested.h"
 #include "pmu.h"
 
-#define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
-
-enum intel_pmu_architectural_events {
-	/*
-	 * The order of the architectural events matters as support for each
-	 * event is enumerated via CPUID using the index of the event.
-	 */
-	INTEL_ARCH_CPU_CYCLES,
-	INTEL_ARCH_INSTRUCTIONS_RETIRED,
-	INTEL_ARCH_REFERENCE_CYCLES,
-	INTEL_ARCH_LLC_REFERENCES,
-	INTEL_ARCH_LLC_MISSES,
-	INTEL_ARCH_BRANCHES_RETIRED,
-	INTEL_ARCH_BRANCHES_MISPREDICTED,
-
-	NR_REAL_INTEL_ARCH_EVENTS,
-
-	/*
-	 * Pseudo-architectural event used to implement IA32_FIXED_CTR2, a.k.a.
-	 * TSC reference cycles.  The architectural reference cycles event may
-	 * or may not actually use the TSC as the reference, e.g. might use the
-	 * core crystal clock or the bus clock (yeah, "architectural").
-	 */
-	PSEUDO_ARCH_REFERENCE_CYCLES = NR_REAL_INTEL_ARCH_EVENTS,
-	NR_INTEL_ARCH_EVENTS,
-};
+/*
+ * Perf's "BASE" is wildly misleading, architectural PMUs use bits 31:16 of ECX
+ * to encode the "type" of counter to read, i.e. this is not a "base".  And to
+ * further confuse things, non-architectural PMUs use bit 31 as a flag for
+ * "fast" reads, whereas the "type" is an explicit value.
+ */
+#define INTEL_RDPMC_GP		0
+#define INTEL_RDPMC_FIXED	INTEL_PMC_FIXED_RDPMC_BASE
 
-static struct {
-	u8 eventsel;
-	u8 unit_mask;
-} const intel_arch_events[] = {
-	[INTEL_ARCH_CPU_CYCLES]			= { 0x3c, 0x00 },
-	[INTEL_ARCH_INSTRUCTIONS_RETIRED]	= { 0xc0, 0x00 },
-	[INTEL_ARCH_REFERENCE_CYCLES]		= { 0x3c, 0x01 },
-	[INTEL_ARCH_LLC_REFERENCES]		= { 0x2e, 0x4f },
-	[INTEL_ARCH_LLC_MISSES]			= { 0x2e, 0x41 },
-	[INTEL_ARCH_BRANCHES_RETIRED]		= { 0xc4, 0x00 },
-	[INTEL_ARCH_BRANCHES_MISPREDICTED]	= { 0xc5, 0x00 },
-	[PSEUDO_ARCH_REFERENCE_CYCLES]		= { 0x00, 0x03 },
-};
+#define INTEL_RDPMC_TYPE_MASK	GENMASK(31, 16)
+#define INTEL_RDPMC_INDEX_MASK	GENMASK(15, 0)
 
-/* mapping between fixed pmc index and intel_arch_events array */
-static int fixed_pmc_events[] = {
-	[0] = INTEL_ARCH_INSTRUCTIONS_RETIRED,
-	[1] = INTEL_ARCH_CPU_CYCLES,
-	[2] = PSEUDO_ARCH_REFERENCE_CYCLES,
-};
+#define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
 
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 {
@@ -84,77 +50,61 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 
 		pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i);
 
-		__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
+		__set_bit(KVM_FIXED_PMC_BASE_IDX + i, pmu->pmc_in_use);
 		kvm_pmu_request_counter_reprogram(pmc);
 	}
 }
 
-static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
-{
-	if (pmc_idx < INTEL_PMC_IDX_FIXED) {
-		return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx,
-				  MSR_P6_EVNTSEL0);
-	} else {
-		u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED;
-
-		return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0);
-	}
-}
-
-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;
-	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
-	int i;
-
-	BUILD_BUG_ON(ARRAY_SIZE(intel_arch_events) != NR_INTEL_ARCH_EVENTS);
-
-	/*
-	 * Disallow events reported as unavailable in guest CPUID.  Note, this
-	 * doesn't apply to pseudo-architectural events.
-	 */
-	for (i = 0; i < NR_REAL_INTEL_ARCH_EVENTS; i++) {
-		if (intel_arch_events[i].eventsel != event_select ||
-		    intel_arch_events[i].unit_mask != unit_mask)
-			continue;
-
-		return pmu->available_event_types & BIT(i);
-	}
-
-	return true;
-}
-
-static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
-{
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	bool fixed = idx & (1u << 30);
-
-	idx &= ~(3u << 30);
-
-	return fixed ? idx < pmu->nr_arch_fixed_counters
-		     : idx < pmu->nr_arch_gp_counters;
-}
-
 static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 					    unsigned int idx, u64 *mask)
 {
+	unsigned int type = idx & INTEL_RDPMC_TYPE_MASK;
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	bool fixed = idx & (1u << 30);
 	struct kvm_pmc *counters;
 	unsigned int num_counters;
+	u64 bitmask;
 
-	idx &= ~(3u << 30);
-	if (fixed) {
+	/*
+	 * The encoding of ECX for RDPMC is different for architectural versus
+	 * non-architecturals PMUs (PMUs with version '0').  For architectural
+	 * PMUs, bits 31:16 specify the PMC type and bits 15:0 specify the PMC
+	 * index.  For non-architectural PMUs, bit 31 is a "fast" flag, and
+	 * bits 30:0 specify the PMC index.
+	 *
+	 * Yell and reject attempts to read PMCs for a non-architectural PMU,
+	 * as KVM doesn't support such PMUs.
+	 */
+	if (WARN_ON_ONCE(!pmu->version))
+		return NULL;
+
+	/*
+	 * General Purpose (GP) PMCs are supported on all PMUs, and fixed PMCs
+	 * are supported on all architectural PMUs, i.e. on all virtual PMUs
+	 * supported by KVM.  Note, KVM only emulates fixed PMCs for PMU v2+,
+	 * but the type itself is still valid, i.e. let RDPMC fail due to
+	 * accessing a non-existent counter.  Reject attempts to read all other
+	 * types, which are unknown/unsupported.
+	 */
+	switch (type) {
+	case INTEL_RDPMC_FIXED:
 		counters = pmu->fixed_counters;
 		num_counters = pmu->nr_arch_fixed_counters;
-	} else {
+		bitmask = pmu->counter_bitmask[KVM_PMC_FIXED];
+		break;
+	case INTEL_RDPMC_GP:
 		counters = pmu->gp_counters;
 		num_counters = pmu->nr_arch_gp_counters;
+		bitmask = pmu->counter_bitmask[KVM_PMC_GP];
+		break;
+	default:
+		return NULL;
 	}
+
+	idx &= INTEL_RDPMC_INDEX_MASK;
 	if (idx >= num_counters)
 		return NULL;
-	*mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP];
+
+	*mask &= bitmask;
 	return &counters[array_index_nospec(idx, num_counters)];
 }
 
@@ -464,20 +414,38 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return 0;
 }
 
-static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu)
+/*
+ * Map fixed counter events to architectural general purpose event encodings.
+ * Perf doesn't provide APIs to allow KVM to directly program a fixed counter,
+ * and so KVM instead programs the architectural event to effectively request
+ * the fixed counter.  Perf isn't guaranteed to use a fixed counter and may
+ * instead program the encoding into a general purpose counter, e.g. if a
+ * different perf_event is already utilizing the requested counter, but the end
+ * result is the same (ignoring the fact that using a general purpose counter
+ * will likely exacerbate counter contention).
+ *
+ * Forcibly inlined to allow asserting on @index at build time, and there should
+ * never be more than one user.
+ */
+static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index)
 {
-	int i;
-
-	BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_events) != KVM_PMC_MAX_FIXED);
+	const enum perf_hw_id fixed_pmc_perf_ids[] = {
+		[0] = PERF_COUNT_HW_INSTRUCTIONS,
+		[1] = PERF_COUNT_HW_CPU_CYCLES,
+		[2] = PERF_COUNT_HW_REF_CPU_CYCLES,
+	};
+	u64 eventsel;
 
-	for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
-		int index = array_index_nospec(i, KVM_PMC_MAX_FIXED);
-		struct kvm_pmc *pmc = &pmu->fixed_counters[index];
-		u32 event = fixed_pmc_events[index];
+	BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_PMC_MAX_FIXED);
+	BUILD_BUG_ON(index >= KVM_PMC_MAX_FIXED);
 
-		pmc->eventsel = (intel_arch_events[event].unit_mask << 8) |
-				 intel_arch_events[event].eventsel;
-	}
+	/*
+	 * Yell if perf reports support for a fixed counter but perf doesn't
+	 * have a known encoding for the associated general purpose event.
+	 */
+	eventsel = perf_get_hw_event_config(fixed_pmc_perf_ids[index]);
+	WARN_ON_ONCE(!eventsel && index < kvm_pmu_cap.num_counters_fixed);
+	return eventsel;
 }
 
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
@@ -491,19 +459,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	u64 counter_mask;
 	int i;
 
-	pmu->nr_arch_gp_counters = 0;
-	pmu->nr_arch_fixed_counters = 0;
-	pmu->counter_bitmask[KVM_PMC_GP] = 0;
-	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
-	pmu->version = 0;
-	pmu->reserved_bits = 0xffffffff00200000ull;
-	pmu->raw_event_mask = X86_RAW_EVENT_MASK;
-	pmu->global_ctrl_mask = ~0ull;
-	pmu->global_status_mask = ~0ull;
-	pmu->fixed_ctr_ctrl_mask = ~0ull;
-	pmu->pebs_enable_mask = ~0ull;
-	pmu->pebs_data_cfg_mask = ~0ull;
-
 	memset(&lbr_desc->records, 0, sizeof(lbr_desc->records));
 
 	/*
@@ -515,8 +470,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		return;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa);
-	if (!entry || !vcpu->kvm->arch.enable_pmu)
+	if (!entry)
 		return;
+
 	eax.full = entry->eax;
 	edx.full = entry->edx;
 
@@ -543,13 +499,12 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 						  kvm_pmu_cap.bit_width_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
-		setup_fixed_pmc_eventsel(pmu);
 	}
 
 	for (i = 0; i < pmu->nr_arch_fixed_counters; i++)
 		pmu->fixed_ctr_ctrl_mask &= ~(0xbull << (i * 4));
 	counter_mask = ~(((1ull << pmu->nr_arch_gp_counters) - 1) |
-		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED));
+		(((1ull << pmu->nr_arch_fixed_counters) - 1) << KVM_FIXED_PMC_BASE_IDX));
 	pmu->global_ctrl_mask = counter_mask;
 
 	/*
@@ -593,7 +548,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 			pmu->reserved_bits &= ~ICL_EVENTSEL_ADAPTIVE;
 			for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
 				pmu->fixed_ctr_ctrl_mask &=
-					~(1ULL << (INTEL_PMC_IDX_FIXED + i * 4));
+					~(1ULL << (KVM_FIXED_PMC_BASE_IDX + i * 4));
 			}
 			pmu->pebs_data_cfg_mask = ~0xff00000full;
 		} else {
@@ -619,8 +574,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 	for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
 		pmu->fixed_counters[i].type = KVM_PMC_FIXED;
 		pmu->fixed_counters[i].vcpu = vcpu;
-		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
+		pmu->fixed_counters[i].idx = i + KVM_FIXED_PMC_BASE_IDX;
 		pmu->fixed_counters[i].current_config = 0;
+		pmu->fixed_counters[i].eventsel = intel_get_fixed_pmc_eventsel(i);
 	}
 
 	lbr_desc->records.nr = 0;
@@ -748,11 +704,8 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu)
 	struct kvm_pmc *pmc = NULL;
 	int bit, hw_idx;
 
-	for_each_set_bit(bit, (unsigned long *)&pmu->global_ctrl,
-			 X86_PMC_IDX_MAX) {
-		pmc = intel_pmc_idx_to_pmc(pmu, bit);
-
-		if (!pmc || !pmc_speculative_in_use(pmc) ||
+	kvm_for_each_pmc(pmu, pmc, bit, (unsigned long *)&pmu->global_ctrl) {
+		if (!pmc_speculative_in_use(pmc) ||
 		    !pmc_is_globally_enabled(pmc) || !pmc->perf_event)
 			continue;
 
@@ -767,11 +720,8 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu)
 }
 
 struct kvm_pmu_ops intel_pmu_ops __initdata = {
-	.hw_event_available = intel_hw_event_available,
-	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
 	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = intel_msr_idx_to_pmc,
-	.is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx,
 	.is_valid_msr = intel_is_valid_msr,
 	.get_msr = intel_pmu_get_msr,
 	.set_msr = intel_pmu_set_msr,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 064862d87b9e..171ff4d1b7cb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8394,12 +8394,9 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
 }
 
-static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
-			      u32 pmc)
+static int emulator_check_rdpmc_early(struct x86_emulate_ctxt *ctxt, u32 pmc)
 {
-	if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc))
-		return 0;
-	return -EINVAL;
+	return kvm_pmu_check_rdpmc_early(emul_to_vcpu(ctxt), pmc);
 }
 
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
@@ -8531,7 +8528,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.set_msr_with_filter = emulator_set_msr_with_filter,
 	.get_msr_with_filter = emulator_get_msr_with_filter,
 	.get_msr             = emulator_get_msr,
-	.check_pmc	     = emulator_check_pmc,
+	.check_rdpmc_early   = emulator_check_rdpmc_early,
 	.read_pmc            = emulator_read_pmc,
 	.halt                = emulator_halt,
 	.wbinvd              = emulator_wbinvd,
@@ -8904,7 +8901,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	if (unlikely(!r))
 		return 0;
 
-	kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS);
+	kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
 
 	/*
 	 * rflags is the old, "raw" value of the flags.  The new value has
@@ -9217,9 +9214,9 @@ writeback:
 		 */
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
-			kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS);
+			kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
 			if (ctxt->is_branch)
-				kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+				kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);
 			kvm_rip_write(vcpu, ctxt->eip);
 			if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
 				r = kvm_vcpu_do_singlestep(vcpu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 2f7e19166658..4dc38092d599 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -431,12 +431,6 @@ static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm)
 	return kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_ENABLED;
 }
 
-enum kvm_intr_type {
-	/* Values are arbitrary, but must be non-zero. */
-	KVM_HANDLING_IRQ = 1,
-	KVM_HANDLING_NMI,
-};
-
 static __always_inline void kvm_before_interrupt(struct kvm_vcpu *vcpu,
 						 enum kvm_intr_type intr)
 {