1 files changed, 114 insertions, 158 deletions

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 315c7c2ba89b..77012b2eca0e 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)
 {
@@ -84,83 +50,67 @@ 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;
+
+	/*
+	 * 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;
 
-	idx &= ~(3u << 30);
-	if (fixed) {
+	/*
+	 * 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)];
 }
 
 static inline u64 vcpu_get_perf_capabilities(struct kvm_vcpu *vcpu)
 {
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
+	if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM))
 		return 0;
 
 	return vcpu->arch.perf_capabilities;
@@ -210,7 +160,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 		ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT;
 		break;
 	case MSR_IA32_DS_AREA:
-		ret = guest_cpuid_has(vcpu, X86_FEATURE_DS);
+		ret = guest_cpu_cap_has(vcpu, X86_FEATURE_DS);
 		break;
 	case MSR_PEBS_DATA_CFG:
 		perf_capabilities = vcpu_get_perf_capabilities(vcpu);
@@ -398,14 +348,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 	switch (msr) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
-		if (data & pmu->fixed_ctr_ctrl_mask)
+		if (data & pmu->fixed_ctr_ctrl_rsvd)
 			return 1;
 
 		if (pmu->fixed_ctr_ctrl != data)
 			reprogram_fixed_counters(pmu, data);
 		break;
 	case MSR_IA32_PEBS_ENABLE:
-		if (data & pmu->pebs_enable_mask)
+		if (data & pmu->pebs_enable_rsvd)
 			return 1;
 
 		if (pmu->pebs_enable != data) {
@@ -415,13 +365,13 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		}
 		break;
 	case MSR_IA32_DS_AREA:
-		if (is_noncanonical_address(data, vcpu))
+		if (is_noncanonical_msr_address(data, vcpu))
 			return 1;
 
 		pmu->ds_area = data;
 		break;
 	case MSR_PEBS_DATA_CFG:
-		if (data & pmu->pebs_data_cfg_mask)
+		if (data & pmu->pebs_data_cfg_rsvd)
 			return 1;
 
 		pmu->pebs_data_cfg = data;
@@ -464,20 +414,46 @@ 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;
+	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;
 
-	BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_events) != KVM_PMC_MAX_FIXED);
+	BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_MAX_NR_INTEL_FIXED_COUTNERS);
+	BUILD_BUG_ON(index >= KVM_MAX_NR_INTEL_FIXED_COUTNERS);
 
-	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];
+	/*
+	 * 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;
+}
 
-		pmc->eventsel = (intel_arch_events[event].unit_mask << 8) |
-				 intel_arch_events[event].eventsel;
-	}
+static void intel_pmu_enable_fixed_counter_bits(struct kvm_pmu *pmu, u64 bits)
+{
+	int i;
+
+	for (i = 0; i < pmu->nr_arch_fixed_counters; i++)
+		pmu->fixed_ctr_ctrl_rsvd &= ~intel_fixed_bits_by_idx(i, bits);
 }
 
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
@@ -488,21 +464,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	union cpuid10_eax eax;
 	union cpuid10_edx edx;
 	u64 perf_capabilities;
-	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;
+	u64 counter_rsvd;
 
 	memset(&lbr_desc->records, 0, sizeof(lbr_desc->records));
 
@@ -515,8 +477,9 @@ 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;
 
@@ -543,25 +506,26 @@ 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));
-	pmu->global_ctrl_mask = counter_mask;
+	intel_pmu_enable_fixed_counter_bits(pmu, INTEL_FIXED_0_KERNEL |
+						 INTEL_FIXED_0_USER |
+						 INTEL_FIXED_0_ENABLE_PMI);
+
+	counter_rsvd = ~(((1ull << pmu->nr_arch_gp_counters) - 1) |
+		(((1ull << pmu->nr_arch_fixed_counters) - 1) << KVM_FIXED_PMC_BASE_IDX));
+	pmu->global_ctrl_rsvd = counter_rsvd;
 
 	/*
 	 * GLOBAL_STATUS and GLOBAL_OVF_CONTROL (a.k.a. GLOBAL_STATUS_RESET)
 	 * share reserved bit definitions.  The kernel just happens to use
 	 * OVF_CTRL for the names.
 	 */
-	pmu->global_status_mask = pmu->global_ctrl_mask
+	pmu->global_status_rsvd = pmu->global_ctrl_rsvd
 			& ~(MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF |
 			    MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD);
 	if (vmx_pt_mode_is_host_guest())
-		pmu->global_status_mask &=
+		pmu->global_status_rsvd &=
 				~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI;
 
 	entry = kvm_find_cpuid_entry_index(vcpu, 7, 0);
@@ -580,7 +544,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	perf_capabilities = vcpu_get_perf_capabilities(vcpu);
 	if (cpuid_model_is_consistent(vcpu) &&
 	    (perf_capabilities & PMU_CAP_LBR_FMT))
-		x86_perf_get_lbr(&lbr_desc->records);
+		memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps));
 	else
 		lbr_desc->records.nr = 0;
 
@@ -589,15 +553,12 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 
 	if (perf_capabilities & PERF_CAP_PEBS_FORMAT) {
 		if (perf_capabilities & PERF_CAP_PEBS_BASELINE) {
-			pmu->pebs_enable_mask = counter_mask;
+			pmu->pebs_enable_rsvd = counter_rsvd;
 			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));
-			}
-			pmu->pebs_data_cfg_mask = ~0xff00000full;
+			pmu->pebs_data_cfg_rsvd = ~0xff00000full;
+			intel_pmu_enable_fixed_counter_bits(pmu, ICL_FIXED_0_ADAPTIVE);
 		} else {
-			pmu->pebs_enable_mask =
+			pmu->pebs_enable_rsvd =
 				~((1ull << pmu->nr_arch_gp_counters) - 1);
 		}
 	}
@@ -609,18 +570,19 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
 
-	for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) {
+	for (i = 0; i < KVM_MAX_NR_INTEL_GP_COUNTERS; i++) {
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
 		pmu->gp_counters[i].current_config = 0;
 	}
 
-	for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
+	for (i = 0; i < KVM_MAX_NR_INTEL_FIXED_COUTNERS; 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 +710,8 @@ 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 +726,8 @@ 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,
@@ -781,6 +737,6 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = {
 	.deliver_pmi = intel_pmu_deliver_pmi,
 	.cleanup = intel_pmu_cleanup,
 	.EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT,
-	.MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC,
+	.MAX_NR_GP_COUNTERS = KVM_MAX_NR_INTEL_GP_COUNTERS,
 	.MIN_NR_GP_COUNTERS = 1,
 };