1 files changed, 150 insertions, 41 deletions

diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index e745f443b6a8..4d52b0b539ba 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -4,10 +4,15 @@
 
 #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)
 
+#define MSR_IA32_MISC_ENABLE_PMU_RO_MASK (MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL |	\
+					  MSR_IA32_MISC_ENABLE_BTS_UNAVAIL)
+
 /* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */
 #define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf)
 
@@ -15,20 +20,18 @@
 #define VMWARE_BACKDOOR_PMC_REAL_TIME		0x10001
 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME	0x10002
 
-struct kvm_event_hw_type_mapping {
-	u8 eventsel;
-	u8 unit_mask;
-	unsigned event_type;
+#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 {
-	unsigned int (*pmc_perf_hw_id)(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,
 		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);
@@ -37,10 +40,60 @@ struct kvm_pmu_ops {
 	void (*reset)(struct kvm_vcpu *vcpu);
 	void (*deliver_pmi)(struct kvm_vcpu *vcpu);
 	void (*cleanup)(struct kvm_vcpu *vcpu);
+
+	const u64 EVENTSEL_EVENT;
+	const int MAX_NR_GP_COUNTERS;
+	const int MIN_NR_GP_COUNTERS;
 };
 
 void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops);
 
+static inline bool kvm_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu)
+{
+	/*
+	 * Architecturally, Intel's SDM states that IA32_PERF_GLOBAL_CTRL is
+	 * supported if "CPUID.0AH: EAX[7:0] > 0", i.e. if the PMU version is
+	 * greater than zero.  However, KVM only exposes and emulates the MSR
+	 * to/for the guest if the guest PMU supports at least "Architectural
+	 * Performance Monitoring Version 2".
+	 *
+	 * AMD's version of PERF_GLOBAL_CTRL conveniently shows up with v2.
+	 */
+	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);
@@ -52,7 +105,8 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 {
 	u64 counter, enabled, running;
 
-	counter = pmc->counter;
+	counter = pmc->counter + pmc->emulated_counter;
+
 	if (pmc->perf_event && !pmc->is_paused)
 		counter += perf_event_read_value(pmc->perf_event,
 						 &enabled, &running);
@@ -60,23 +114,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
-static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
-{
-	if (pmc->perf_event) {
-		perf_event_release_kernel(pmc->perf_event);
-		pmc->perf_event = NULL;
-		pmc->current_config = 0;
-		pmc_to_pmu(pmc)->event_count--;
-	}
-}
-
-static inline void pmc_stop_counter(struct kvm_pmc *pmc)
-{
-	if (pmc->perf_event) {
-		pmc->counter = pmc_read_counter(pmc);
-		pmc_release_perf_event(pmc);
-	}
-}
+void pmc_write_counter(struct kvm_pmc *pmc, u64 val);
 
 static inline bool pmc_is_gp(struct kvm_pmc *pmc)
 {
@@ -126,42 +164,113 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
 	return NULL;
 }
 
-static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value)
+static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	if (pmc_is_fixed(pmc))
+		return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+					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)
 {
-	u64 sample_period = (-counter_value) & pmc_bitmask(pmc);
+	bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;
+	int min_nr_gp_ctrs = pmu_ops->MIN_NR_GP_COUNTERS;
+
+	/*
+	 * Hybrid PMUs don't play nice with virtualization without careful
+	 * configuration by userspace, and KVM's APIs for reporting supported
+	 * vPMU features do not account for hybrid PMUs.  Disable vPMU support
+	 * for hybrid PMUs until KVM gains a way to let userspace opt-in.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+		enable_pmu = false;
+
+	if (enable_pmu) {
+		perf_get_x86_pmu_capability(&kvm_pmu_cap);
+
+		/*
+		 * WARN if perf did NOT disable hardware PMU if the number of
+		 * architecturally required GP counters aren't present, i.e. if
+		 * there are a non-zero number of counters, but fewer than what
+		 * is architecturally required.
+		 */
+		if (!kvm_pmu_cap.num_counters_gp ||
+		    WARN_ON_ONCE(kvm_pmu_cap.num_counters_gp < min_nr_gp_ctrs))
+			enable_pmu = false;
+		else if (is_intel && !kvm_pmu_cap.version)
+			enable_pmu = false;
+	}
+
+	if (!enable_pmu) {
+		memset(&kvm_pmu_cap, 0, sizeof(kvm_pmu_cap));
+		return;
+	}
+
+	kvm_pmu_cap.version = min(kvm_pmu_cap.version, 2);
+	kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp,
+					  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);
+}
 
-	if (!sample_period)
-		sample_period = pmc_bitmask(pmc) + 1;
-	return sample_period;
+static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc)
+{
+	set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+	kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 }
 
-static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
+static inline void reprogram_counters(struct kvm_pmu *pmu, u64 diff)
 {
-	if (!pmc->perf_event || pmc->is_paused)
+	int bit;
+
+	if (!diff)
 		return;
 
-	perf_event_period(pmc->perf_event,
-			  get_sample_period(pmc, pmc->counter));
+	for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX)
+		set_bit(bit, pmu->reprogram_pmi);
+	kvm_make_request(KVM_REQ_PMU, pmu_to_vcpu(pmu));
 }
 
-void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel);
-void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx);
-void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
+/*
+ * Check if a PMC is enabled by comparing it against global_ctrl bits.
+ *
+ * If the vPMU doesn't have global_ctrl MSR, all vPMCs are enabled.
+ */
+static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	if (!kvm_pmu_has_perf_global_ctrl(pmu))
+		return true;
+
+	return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl);
+}
 
 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);
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
-void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 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);