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 +#include + #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 @@ -20,54 +20,20 @@ #include "nested.h" #include "pmu.h" +/* + * 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 + +#define INTEL_RDPMC_TYPE_MASK GENMASK(31, 16) +#define INTEL_RDPMC_INDEX_MASK GENMASK(15, 0) + #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, -}; - -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 }, -}; - -/* 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, -}; - static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { struct kvm_pmc *pmc; @@ -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; + 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_PMC_MAX_FIXED); + BUILD_BUG_ON(index >= KVM_PMC_MAX_FIXED); - 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]; - - 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 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, */ 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) { diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index b0f13fafa155..19f5710bb456 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -36,6 +36,7 @@ LIBKVM_x86_64 += lib/x86_64/apic.c LIBKVM_x86_64 += lib/x86_64/handlers.S LIBKVM_x86_64 += lib/x86_64/hyperv.c LIBKVM_x86_64 += lib/x86_64/memstress.c +LIBKVM_x86_64 += lib/x86_64/pmu.c LIBKVM_x86_64 += lib/x86_64/processor.c LIBKVM_x86_64 += lib/x86_64/sev.c LIBKVM_x86_64 += lib/x86_64/svm.c @@ -82,6 +83,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test +TEST_GEN_PROGS_x86_64 += x86_64/pmu_counters_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 9ff131a6a1a5..3e0db283a46a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -270,6 +270,10 @@ bool get_kvm_param_bool(const char *param); bool get_kvm_intel_param_bool(const char *param); bool get_kvm_amd_param_bool(const char *param); +int get_kvm_param_integer(const char *param); +int get_kvm_intel_param_integer(const char *param); +int get_kvm_amd_param_integer(const char *param); + unsigned int kvm_check_cap(long cap); static inline bool kvm_has_cap(long cap) diff --git a/tools/testing/selftests/kvm/include/x86_64/pmu.h b/tools/testing/selftests/kvm/include/x86_64/pmu.h new file mode 100644 index 000000000000..3c10c4dc0ae8 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/pmu.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023, Tencent, Inc. + */ +#ifndef SELFTEST_KVM_PMU_H +#define SELFTEST_KVM_PMU_H + +#include + +#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300 + +/* + * Encode an eventsel+umask pair into event-select MSR format. Note, this is + * technically AMD's format, as Intel's format only supports 8 bits for the + * event selector, i.e. doesn't use bits 24:16 for the selector. But, OR-ing + * in '0' is a nop and won't clobber the CMASK. + */ +#define RAW_EVENT(eventsel, umask) (((eventsel & 0xf00UL) << 24) | \ + ((eventsel) & 0xff) | \ + ((umask) & 0xff) << 8) + +/* + * These are technically Intel's definitions, but except for CMASK (see above), + * AMD's layout is compatible with Intel's. + */ +#define ARCH_PERFMON_EVENTSEL_EVENT GENMASK_ULL(7, 0) +#define ARCH_PERFMON_EVENTSEL_UMASK GENMASK_ULL(15, 8) +#define ARCH_PERFMON_EVENTSEL_USR BIT_ULL(16) +#define ARCH_PERFMON_EVENTSEL_OS BIT_ULL(17) +#define ARCH_PERFMON_EVENTSEL_EDGE BIT_ULL(18) +#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL BIT_ULL(19) +#define ARCH_PERFMON_EVENTSEL_INT BIT_ULL(20) +#define ARCH_PERFMON_EVENTSEL_ANY BIT_ULL(21) +#define ARCH_PERFMON_EVENTSEL_ENABLE BIT_ULL(22) +#define ARCH_PERFMON_EVENTSEL_INV BIT_ULL(23) +#define ARCH_PERFMON_EVENTSEL_CMASK GENMASK_ULL(31, 24) + +/* RDPMC control flags, Intel only. */ +#define INTEL_RDPMC_METRICS BIT_ULL(29) +#define INTEL_RDPMC_FIXED BIT_ULL(30) +#define INTEL_RDPMC_FAST BIT_ULL(31) + +/* Fixed PMC controls, Intel only. */ +#define FIXED_PMC_GLOBAL_CTRL_ENABLE(_idx) BIT_ULL((32 + (_idx))) + +#define FIXED_PMC_KERNEL BIT_ULL(0) +#define FIXED_PMC_USER BIT_ULL(1) +#define FIXED_PMC_ANYTHREAD BIT_ULL(2) +#define FIXED_PMC_ENABLE_PMI BIT_ULL(3) +#define FIXED_PMC_NR_BITS 4 +#define FIXED_PMC_CTRL(_idx, _val) ((_val) << ((_idx) * FIXED_PMC_NR_BITS)) + +#define PMU_CAP_FW_WRITES BIT_ULL(13) +#define PMU_CAP_LBR_FMT 0x3f + +#define INTEL_ARCH_CPU_CYCLES RAW_EVENT(0x3c, 0x00) +#define INTEL_ARCH_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00) +#define INTEL_ARCH_REFERENCE_CYCLES RAW_EVENT(0x3c, 0x01) +#define INTEL_ARCH_LLC_REFERENCES RAW_EVENT(0x2e, 0x4f) +#define INTEL_ARCH_LLC_MISSES RAW_EVENT(0x2e, 0x41) +#define INTEL_ARCH_BRANCHES_RETIRED RAW_EVENT(0xc4, 0x00) +#define INTEL_ARCH_BRANCHES_MISPREDICTED RAW_EVENT(0xc5, 0x00) +#define INTEL_ARCH_TOPDOWN_SLOTS RAW_EVENT(0xa4, 0x01) + +#define AMD_ZEN_CORE_CYCLES RAW_EVENT(0x76, 0x00) +#define AMD_ZEN_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00) +#define AMD_ZEN_BRANCHES_RETIRED RAW_EVENT(0xc2, 0x00) +#define AMD_ZEN_BRANCHES_MISPREDICTED RAW_EVENT(0xc3, 0x00) + +/* + * Note! The order and thus the index of the architectural events matters as + * support for each event is enumerated via CPUID using the index of the event. + */ +enum intel_pmu_architectural_events { + INTEL_ARCH_CPU_CYCLES_INDEX, + INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX, + INTEL_ARCH_REFERENCE_CYCLES_INDEX, + INTEL_ARCH_LLC_REFERENCES_INDEX, + INTEL_ARCH_LLC_MISSES_INDEX, + INTEL_ARCH_BRANCHES_RETIRED_INDEX, + INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX, + INTEL_ARCH_TOPDOWN_SLOTS_INDEX, + NR_INTEL_ARCH_EVENTS, +}; + +enum amd_pmu_zen_events { + AMD_ZEN_CORE_CYCLES_INDEX, + AMD_ZEN_INSTRUCTIONS_INDEX, + AMD_ZEN_BRANCHES_INDEX, + AMD_ZEN_BRANCH_MISSES_INDEX, + NR_AMD_ZEN_EVENTS, +}; + +extern const uint64_t intel_pmu_arch_events[]; +extern const uint64_t amd_pmu_zen_events[]; + +#endif /* SELFTEST_KVM_PMU_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index d2534a4a077b..3bd03b088dda 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -29,6 +29,9 @@ enum vm_guest_x86_subtype { VM_SUBTYPE_SEV_ES, }; +/* Forced emulation prefix, used to invoke the emulator unconditionally. */ +#define KVM_FEP "ud2; .byte 'k', 'v', 'm';" + #define NMI_VECTOR 0x02 #define X86_EFLAGS_FIXED (1u << 1) @@ -289,24 +292,41 @@ struct kvm_x86_cpu_property { * that indicates the feature is _not_ supported, and a property that states * the length of the bit mask of unsupported features. A feature is supported * if the size of the bit mask is larger than the "unavailable" bit, and said - * bit is not set. + * bit is not set. Fixed counters also bizarre enumeration, but inverted from + * arch events for general purpose counters. Fixed counters are supported if a + * feature flag is set **OR** the total number of fixed counters is greater + * than index of the counter. * - * Wrap the "unavailable" feature to simplify checking whether or not a given - * architectural event is supported. + * Wrap the events for general purpose and fixed counters to simplify checking + * whether or not a given architectural event is supported. */ struct kvm_x86_pmu_feature { - struct kvm_x86_cpu_feature anti_feature; + struct kvm_x86_cpu_feature f; }; -#define KVM_X86_PMU_FEATURE(name, __bit) \ -({ \ - struct kvm_x86_pmu_feature feature = { \ - .anti_feature = KVM_X86_CPU_FEATURE(0xa, 0, EBX, __bit), \ - }; \ - \ - feature; \ +#define KVM_X86_PMU_FEATURE(__reg, __bit) \ +({ \ + struct kvm_x86_pmu_feature feature = { \ + .f = KVM_X86_CPU_FEATURE(0xa, 0, __reg, __bit), \ + }; \ + \ + kvm_static_assert(KVM_CPUID_##__reg == KVM_CPUID_EBX || \ + KVM_CPUID_##__reg == KVM_CPUID_ECX); \ + feature; \ }) -#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(BRANCH_INSNS_RETIRED, 5) +#define X86_PMU_FEATURE_CPU_CYCLES KVM_X86_PMU_FEATURE(EBX, 0) +#define X86_PMU_FEATURE_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 1) +#define X86_PMU_FEATURE_REFERENCE_CYCLES KVM_X86_PMU_FEATURE(EBX, 2) +#define X86_PMU_FEATURE_LLC_REFERENCES KVM_X86_PMU_FEATURE(EBX, 3) +#define X86_PMU_FEATURE_LLC_MISSES KVM_X86_PMU_FEATURE(EBX, 4) +#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 5) +#define X86_PMU_FEATURE_BRANCHES_MISPREDICTED KVM_X86_PMU_FEATURE(EBX, 6) +#define X86_PMU_FEATURE_TOPDOWN_SLOTS KVM_X86_PMU_FEATURE(EBX, 7) + +#define X86_PMU_FEATURE_INSNS_RETIRED_FIXED KVM_X86_PMU_FEATURE(ECX, 0) +#define X86_PMU_FEATURE_CPU_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 1) +#define X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 2) +#define X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED KVM_X86_PMU_FEATURE(ECX, 3) static inline unsigned int x86_family(unsigned int eax) { @@ -705,10 +725,16 @@ static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + uint32_t nr_bits; - return nr_bits > feature.anti_feature.bit && - !this_cpu_has(feature.anti_feature); + if (feature.f.reg == KVM_CPUID_EBX) { + nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + return nr_bits > feature.f.bit && !this_cpu_has(feature.f); + } + + GUEST_ASSERT(feature.f.reg == KVM_CPUID_ECX); + nr_bits = this_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + return nr_bits > feature.f.bit || this_cpu_has(feature.f); } static __always_inline uint64_t this_cpu_supported_xcr0(void) @@ -924,10 +950,16 @@ static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + uint32_t nr_bits; - return nr_bits > feature.anti_feature.bit && - !kvm_cpu_has(feature.anti_feature); + if (feature.f.reg == KVM_CPUID_EBX) { + nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + return nr_bits > feature.f.bit && !kvm_cpu_has(feature.f); + } + + TEST_ASSERT_EQ(feature.f.reg, KVM_CPUID_ECX); + nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + return nr_bits > feature.f.bit || kvm_cpu_has(feature.f); } static __always_inline uint64_t kvm_cpu_supported_xcr0(void) @@ -1002,7 +1034,9 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); } -void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); +void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_property property, + uint32_t value); void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu, @@ -1128,16 +1162,19 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, * r9 = exception vector (non-zero) * r10 = error code */ -#define KVM_ASM_SAFE(insn) \ +#define __KVM_ASM_SAFE(insn, fep) \ "mov $" __stringify(KVM_EXCEPTION_MAGIC) ", %%r9\n\t" \ "lea 1f(%%rip), %%r10\n\t" \ "lea 2f(%%rip), %%r11\n\t" \ - "1: " insn "\n\t" \ + fep "1: " insn "\n\t" \ "xor %%r9, %%r9\n\t" \ "2:\n\t" \ "mov %%r9b, %[vector]\n\t" \ "mov %%r10, %[error_code]\n\t" +#define KVM_ASM_SAFE(insn) __KVM_ASM_SAFE(insn, "") +#define KVM_ASM_SAFE_FEP(insn) __KVM_ASM_SAFE(insn, KVM_FEP) + #define KVM_ASM_SAFE_OUTPUTS(v, ec) [vector] "=qm"(v), [error_code] "=rm"(ec) #define KVM_ASM_SAFE_CLOBBERS "r9", "r10", "r11" @@ -1164,21 +1201,58 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, vector; \ }) -static inline uint8_t rdmsr_safe(uint32_t msr, uint64_t *val) -{ - uint64_t error_code; - uint8_t vector; - uint32_t a, d; +#define kvm_asm_safe_fep(insn, inputs...) \ +({ \ + uint64_t ign_error_code; \ + uint8_t vector; \ + \ + asm volatile(KVM_ASM_SAFE(insn) \ + : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ + : inputs \ + : KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) - asm volatile(KVM_ASM_SAFE("rdmsr") - : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector, error_code) - : "c"(msr) - : KVM_ASM_SAFE_CLOBBERS); +#define kvm_asm_safe_ec_fep(insn, error_code, inputs...) \ +({ \ + uint8_t vector; \ + \ + asm volatile(KVM_ASM_SAFE_FEP(insn) \ + : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ + : inputs \ + : KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) - *val = (uint64_t)a | ((uint64_t)d << 32); - return vector; +#define BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP) \ +static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ +{ \ + uint64_t error_code; \ + uint8_t vector; \ + uint32_t a, d; \ + \ + asm volatile(KVM_ASM_SAFE##_FEP(#insn) \ + : "=a"(a), "=d"(d), \ + KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ + : "c"(idx) \ + : KVM_ASM_SAFE_CLOBBERS); \ + \ + *val = (uint64_t)a | ((uint64_t)d << 32); \ + return vector; \ } +/* + * Generate {insn}_safe() and {insn}_safe_fep() helpers for instructions that + * use ECX as in input index, and EDX:EAX as a 64-bit output. + */ +#define BUILD_READ_U64_SAFE_HELPERS(insn) \ + BUILD_READ_U64_SAFE_HELPER(insn, , ) \ + BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP) \ + +BUILD_READ_U64_SAFE_HELPERS(rdmsr) +BUILD_READ_U64_SAFE_HELPERS(rdpmc) +BUILD_READ_U64_SAFE_HELPERS(xgetbv) + static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) { return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr)); @@ -1194,6 +1268,16 @@ static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) bool kvm_is_tdp_enabled(void); +static inline bool kvm_is_pmu_enabled(void) +{ + return get_kvm_param_bool("enable_pmu"); +} + +static inline bool kvm_is_forced_emulation_enabled(void) +{ + return !!get_kvm_param_integer("force_emulation_prefix"); +} + uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, int *level); uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 13b92f995bde..b2262b5fad9e 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -52,13 +52,13 @@ int open_kvm_dev_path_or_exit(void) return _open_kvm_dev_path_or_exit(O_RDONLY); } -static bool get_module_param_bool(const char *module_name, const char *param) +static ssize_t get_module_param(const char *module_name, const char *param, + void *buffer, size_t buffer_size) { const int path_size = 128; char path[path_size]; - char value; - ssize_t r; - int fd; + ssize_t bytes_read; + int fd, r; r = snprintf(path, path_size, "/sys/module/%s/parameters/%s", module_name, param); @@ -67,11 +67,46 @@ static bool get_module_param_bool(const char *module_name, const char *param) fd = open_path_or_exit(path, O_RDONLY); - r = read(fd, &value, 1); - TEST_ASSERT(r == 1, "read(%s) failed", path); + bytes_read = read(fd, buffer, buffer_size); + TEST_ASSERT(bytes_read > 0, "read(%s) returned %ld, wanted %ld bytes", + path, bytes_read, buffer_size); r = close(fd); TEST_ASSERT(!r, "close(%s) failed", path); + return bytes_read; +} + +static int get_module_param_integer(const char *module_name, const char *param) +{ + /* + * 16 bytes to hold a 64-bit value (1 byte per char), 1 byte for the + * NUL char, and 1 byte because the kernel sucks and inserts a newline + * at the end. + */ + char value[16 + 1 + 1]; + ssize_t r; + + memset(value, '\0', sizeof(value)); + + r = get_module_param(module_name, param, value, sizeof(value)); + TEST_ASSERT(value[r - 1] == '\n', + "Expected trailing newline, got char '%c'", value[r - 1]); + + /* + * Squash the newline, otherwise atoi_paranoid() will complain about + * trailing non-NUL characters in the string. + */ + value[r - 1] = '\0'; + return atoi_paranoid(value); +} + +static bool get_module_param_bool(const char *module_name, const char *param) +{ + char value; + ssize_t r; + + r = get_module_param(module_name, param, &value, sizeof(value)); + TEST_ASSERT_EQ(r, 1); if (value == 'Y') return true; @@ -96,6 +131,21 @@ bool get_kvm_amd_param_bool(const char *param) return get_module_param_bool("kvm_amd", param); } +int get_kvm_param_integer(const char *param) +{ + return get_module_param_integer("kvm", param); +} + +int get_kvm_intel_param_integer(const char *param) +{ + return get_module_param_integer("kvm_intel", param); +} + +int get_kvm_amd_param_integer(const char *param) +{ + return get_module_param_integer("kvm_amd", param); +} + /* * Capability * diff --git a/tools/testing/selftests/kvm/lib/x86_64/pmu.c b/tools/testing/selftests/kvm/lib/x86_64/pmu.c new file mode 100644 index 000000000000..f31f0427c17c --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/pmu.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023, Tencent, Inc. + */ + +#include + +#include + +#include "kvm_util.h" +#include "pmu.h" + +const uint64_t intel_pmu_arch_events[] = { + 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, + INTEL_ARCH_TOPDOWN_SLOTS, +}; +kvm_static_assert(ARRAY_SIZE(intel_pmu_arch_events) == NR_INTEL_ARCH_EVENTS); + +const uint64_t amd_pmu_zen_events[] = { + AMD_ZEN_CORE_CYCLES, + AMD_ZEN_INSTRUCTIONS_RETIRED, + AMD_ZEN_BRANCHES_RETIRED, + AMD_ZEN_BRANCHES_MISPREDICTED, +}; +kvm_static_assert(ARRAY_SIZE(amd_pmu_zen_events) == NR_AMD_ZEN_EVENTS); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c3bb2eb38cff..74a4c736c9ae 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -781,12 +781,21 @@ void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid) vcpu_set_cpuid(vcpu); } -void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr) +void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_property property, + uint32_t value) { - struct kvm_cpuid_entry2 *entry = vcpu_get_cpuid_entry(vcpu, 0x80000008); + struct kvm_cpuid_entry2 *entry; + + entry = __vcpu_get_cpuid_entry(vcpu, property.function, property.index); + + (&entry->eax)[property.reg] &= ~GENMASK(property.hi_bit, property.lo_bit); + (&entry->eax)[property.reg] |= value << property.lo_bit; - entry->eax = (entry->eax & ~0xff) | maxphyaddr; vcpu_set_cpuid(vcpu); + + /* Sanity check that @value doesn't exceed the bounds in any way. */ + TEST_ASSERT_EQ(kvm_cpuid_property(vcpu->cpuid, property), value); } void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c new file mode 100644 index 000000000000..29609b52f8fa --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c @@ -0,0 +1,620 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023, Tencent, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include + +#include "pmu.h" +#include "processor.h" + +/* Number of LOOP instructions for the guest measurement payload. */ +#define NUM_BRANCHES 10 +/* + * Number of "extra" instructions that will be counted, i.e. the number of + * instructions that are needed to set up the loop and then disabled the + * counter. 1 CLFLUSH/CLFLUSHOPT/NOP, 1 MFENCE, 2 MOV, 2 XOR, 1 WRMSR. + */ +#define NUM_EXTRA_INSNS 7 +#define NUM_INSNS_RETIRED (NUM_BRANCHES + NUM_EXTRA_INSNS) + +static uint8_t kvm_pmu_version; +static bool kvm_has_perf_caps; +static bool is_forced_emulation_enabled; + +static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + void *guest_code, + uint8_t pmu_version, + uint64_t perf_capabilities) +{ + struct kvm_vm *vm; + + vm = vm_create_with_one_vcpu(vcpu, guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(*vcpu); + + sync_global_to_guest(vm, kvm_pmu_version); + sync_global_to_guest(vm, is_forced_emulation_enabled); + + /* + * Set PERF_CAPABILITIES before PMU version as KVM disallows enabling + * features via PERF_CAPABILITIES if the guest doesn't have a vPMU. + */ + if (kvm_has_perf_caps) + vcpu_set_msr(*vcpu, MSR_IA32_PERF_CAPABILITIES, perf_capabilities); + + vcpu_set_cpuid_property(*vcpu, X86_PROPERTY_PMU_VERSION, pmu_version); + return vm; +} + +static void run_vcpu(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + do { + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_PRINTF: + pr_info("%s", uc.buffer); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } while (uc.cmd != UCALL_DONE); +} + +static uint8_t guest_get_pmu_version(void) +{ + /* + * Return the effective PMU version, i.e. the minimum between what KVM + * supports and what is enumerated to the guest. The host deliberately + * advertises a PMU version to the guest beyond what is actually + * supported by KVM to verify KVM doesn't freak out and do something + * bizarre with an architecturally valid, but unsupported, version. + */ + return min_t(uint8_t, kvm_pmu_version, this_cpu_property(X86_PROPERTY_PMU_VERSION)); +} + +/* + * If an architectural event is supported and guaranteed to generate at least + * one "hit, assert that its count is non-zero. If an event isn't supported or + * the test can't guarantee the associated action will occur, then all bets are + * off regarding the count, i.e. no checks can be done. + * + * Sanity check that in all cases, the event doesn't count when it's disabled, + * and that KVM correctly emulates the write of an arbitrary value. + */ +static void guest_assert_event_count(uint8_t idx, + struct kvm_x86_pmu_feature event, + uint32_t pmc, uint32_t pmc_msr) +{ + uint64_t count; + + count = _rdpmc(pmc); + if (!this_pmu_has(event)) + goto sanity_checks; + + switch (idx) { + case INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX: + GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED); + break; + case INTEL_ARCH_BRANCHES_RETIRED_INDEX: + GUEST_ASSERT_EQ(count, NUM_BRANCHES); + break; + case INTEL_ARCH_LLC_REFERENCES_INDEX: + case INTEL_ARCH_LLC_MISSES_INDEX: + if (!this_cpu_has(X86_FEATURE_CLFLUSHOPT) && + !this_cpu_has(X86_FEATURE_CLFLUSH)) + break; + fallthrough; + case INTEL_ARCH_CPU_CYCLES_INDEX: + case INTEL_ARCH_REFERENCE_CYCLES_INDEX: + GUEST_ASSERT_NE(count, 0); + break; + case INTEL_ARCH_TOPDOWN_SLOTS_INDEX: + GUEST_ASSERT(count >= NUM_INSNS_RETIRED); + break; + default: + break; + } + +sanity_checks: + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + GUEST_ASSERT_EQ(_rdpmc(pmc), count); + + wrmsr(pmc_msr, 0xdead); + GUEST_ASSERT_EQ(_rdpmc(pmc), 0xdead); +} + +/* + * Enable and disable the PMC in a monolithic asm blob to ensure that the + * compiler can't insert _any_ code into the measured sequence. Note, ECX + * doesn't need to be clobbered as the input value, @pmc_msr, is restored + * before the end of the sequence. + * + * If CLFUSH{,OPT} is supported, flush the cacheline containing (at least) the + * start of the loop to force LLC references and misses, i.e. to allow testing + * that those events actually count. + * + * If forced emulation is enabled (and specified), force emulation on a subset + * of the measured code to verify that KVM correctly emulates instructions and + * branches retired events in conjunction with hardware also counting said + * events. + */ +#define GUEST_MEASURE_EVENT(_msr, _value, clflush, FEP) \ +do { \ + __asm__ __volatile__("wrmsr\n\t" \ + clflush "\n\t" \ + "mfence\n\t" \ + "1: mov $" __stringify(NUM_BRANCHES) ", %%ecx\n\t" \ + FEP "loop .\n\t" \ + FEP "mov %%edi, %%ecx\n\t" \ + FEP "xor %%eax, %%eax\n\t" \ + FEP "xor %%edx, %%edx\n\t" \ + "wrmsr\n\t" \ + :: "a"((uint32_t)_value), "d"(_value >> 32), \ + "c"(_msr), "D"(_msr) \ + ); \ +} while (0) + +#define GUEST_TEST_EVENT(_idx, _event, _pmc, _pmc_msr, _ctrl_msr, _value, FEP) \ +do { \ + wrmsr(pmc_msr, 0); \ + \ + if (this_cpu_has(X86_FEATURE_CLFLUSHOPT)) \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt 1f", FEP); \ + else if (this_cpu_has(X86_FEATURE_CLFLUSH)) \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush 1f", FEP); \ + else \ + GUEST_MEASURE_EVENT(_ctrl_msr, _value, "nop", FEP); \ + \ + guest_assert_event_count(_idx, _event, _pmc, _pmc_msr); \ +} while (0) + +static void __guest_test_arch_event(uint8_t idx, struct kvm_x86_pmu_feature event, + uint32_t pmc, uint32_t pmc_msr, + uint32_t ctrl_msr, uint64_t ctrl_msr_value) +{ + GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, ""); + + if (is_forced_emulation_enabled) + GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, KVM_FEP); +} + +#define X86_PMU_FEATURE_NULL \ +({ \ + struct kvm_x86_pmu_feature feature = {}; \ + \ + feature; \ +}) + +static bool pmu_is_null_feature(struct kvm_x86_pmu_feature event) +{ + return !(*(u64 *)&event); +} + +static void guest_test_arch_event(uint8_t idx) +{ + const struct { + struct kvm_x86_pmu_feature gp_event; + struct kvm_x86_pmu_feature fixed_event; + } intel_event_to_feature[] = { + [INTEL_ARCH_CPU_CYCLES_INDEX] = { X86_PMU_FEATURE_CPU_CYCLES, X86_PMU_FEATURE_CPU_CYCLES_FIXED }, + [INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX] = { X86_PMU_FEATURE_INSNS_RETIRED, X86_PMU_FEATURE_INSNS_RETIRED_FIXED }, + /* + * Note, the fixed counter for reference cycles is NOT the same + * as the general purpose architectural event. The fixed counter + * explicitly counts at the same frequency as the TSC, whereas + * the GP event counts at a fixed, but uarch specific, frequency. + * Bundle them here for simplicity. + */ + [INTEL_ARCH_REFERENCE_CYCLES_INDEX] = { X86_PMU_FEATURE_REFERENCE_CYCLES, X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED }, + [INTEL_ARCH_LLC_REFERENCES_INDEX] = { X86_PMU_FEATURE_LLC_REFERENCES, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_LLC_MISSES_INDEX] = { X86_PMU_FEATURE_LLC_MISSES, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_BRANCHES_RETIRED_INDEX] = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_SLOTS_INDEX] = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED }, + }; + + uint32_t nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + uint32_t pmu_version = guest_get_pmu_version(); + /* PERF_GLOBAL_CTRL exists only for Architectural PMU Version 2+. */ + bool guest_has_perf_global_ctrl = pmu_version >= 2; + struct kvm_x86_pmu_feature gp_event, fixed_event; + uint32_t base_pmc_msr; + unsigned int i; + + /* The host side shouldn't invoke this without a guest PMU. */ + GUEST_ASSERT(pmu_version); + + if (this_cpu_has(X86_FEATURE_PDCM) && + rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES) + base_pmc_msr = MSR_IA32_PMC0; + else + base_pmc_msr = MSR_IA32_PERFCTR0; + + gp_event = intel_event_to_feature[idx].gp_event; + GUEST_ASSERT_EQ(idx, gp_event.f.bit); + + GUEST_ASSERT(nr_gp_counters); + + for (i = 0; i < nr_gp_counters; i++) { + uint64_t eventsel = ARCH_PERFMON_EVENTSEL_OS | + ARCH_PERFMON_EVENTSEL_ENABLE | + intel_pmu_arch_events[idx]; + + wrmsr(MSR_P6_EVNTSEL0 + i, 0); + if (guest_has_perf_global_ctrl) + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, BIT_ULL(i)); + + __guest_test_arch_event(idx, gp_event, i, base_pmc_msr + i, + MSR_P6_EVNTSEL0 + i, eventsel); + } + + if (!guest_has_perf_global_ctrl) + return; + + fixed_event = intel_event_to_feature[idx].fixed_event; + if (pmu_is_null_feature(fixed_event) || !this_pmu_has(fixed_event)) + return; + + i = fixed_event.f.bit; + + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL)); + + __guest_test_arch_event(idx, fixed_event, i | INTEL_RDPMC_FIXED, + MSR_CORE_PERF_FIXED_CTR0 + i, + MSR_CORE_PERF_GLOBAL_CTRL, + FIXED_PMC_GLOBAL_CTRL_ENABLE(i)); +} + +static void guest_test_arch_events(void) +{ + uint8_t i; + + for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++) + guest_test_arch_event(i); + + GUEST_DONE(); +} + +static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, + uint8_t length, uint8_t unavailable_mask) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + /* Testing arch events requires a vPMU (there are no negative tests). */ + if (!pmu_version) + return; + + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_arch_events, + pmu_version, perf_capabilities); + + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH, + length); + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EVENTS_MASK, + unavailable_mask); + + run_vcpu(vcpu); + + kvm_vm_free(vm); +} + +/* + * Limit testing to MSRs that are actually defined by Intel (in the SDM). MSRs + * that aren't defined counter MSRs *probably* don't exist, but there's no + * guarantee that currently undefined MSR indices won't be used for something + * other than PMCs in the future. + */ +#define MAX_NR_GP_COUNTERS 8 +#define MAX_NR_FIXED_COUNTERS 3 + +#define GUEST_ASSERT_PMC_MSR_ACCESS(insn, msr, expect_gp, vector) \ +__GUEST_ASSERT(expect_gp ? vector == GP_VECTOR : !vector, \ + "Expected %s on " #insn "(0x%x), got vector %u", \ + expect_gp ? "#GP" : "no fault", msr, vector) \ + +#define GUEST_ASSERT_PMC_VALUE(insn, msr, val, expected) \ + __GUEST_ASSERT(val == expected_val, \ + "Expected " #insn "(0x%x) to yield 0x%lx, got 0x%lx", \ + msr, expected_val, val); + +static void guest_test_rdpmc(uint32_t rdpmc_idx, bool expect_success, + uint64_t expected_val) +{ + uint8_t vector; + uint64_t val; + + vector = rdpmc_safe(rdpmc_idx, &val); + GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector); + if (expect_success) + GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val); + + if (!is_forced_emulation_enabled) + return; + + vector = rdpmc_safe_fep(rdpmc_idx, &val); + GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector); + if (expect_success) + GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val); +} + +static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters, + uint8_t nr_counters, uint32_t or_mask) +{ + const bool pmu_has_fast_mode = !guest_get_pmu_version(); + uint8_t i; + + for (i = 0; i < nr_possible_counters; i++) { + /* + * TODO: Test a value that validates full-width writes and the + * width of the counters. + */ + const uint64_t test_val = 0xffff; + const uint32_t msr = base_msr + i; + + /* + * Fixed counters are supported if the counter is less than the + * number of enumerated contiguous counters *or* the counter is + * explicitly enumerated in the supported counters mask. + */ + const bool expect_success = i < nr_counters || (or_mask & BIT(i)); + + /* + * KVM drops writes to MSR_P6_PERFCTR[0|1] if the counters are + * unsupported, i.e. doesn't #GP and reads back '0'. + */ + const uint64_t expected_val = expect_success ? test_val : 0; + const bool expect_gp = !expect_success && msr != MSR_P6_PERFCTR0 && + msr != MSR_P6_PERFCTR1; + uint32_t rdpmc_idx; + uint8_t vector; + uint64_t val; + + vector = wrmsr_safe(msr, test_val); + GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector); + + vector = rdmsr_safe(msr, &val); + GUEST_ASSERT_PMC_MSR_ACCESS(RDMSR, msr, expect_gp, vector); + + /* On #GP, the result of RDMSR is undefined. */ + if (!expect_gp) + GUEST_ASSERT_PMC_VALUE(RDMSR, msr, val, expected_val); + + /* + * Redo the read tests with RDPMC, which has different indexing + * semantics and additional capabilities. + */ + rdpmc_idx = i; + if (base_msr == MSR_CORE_PERF_FIXED_CTR0) + rdpmc_idx |= INTEL_RDPMC_FIXED; + + guest_test_rdpmc(rdpmc_idx, expect_success, expected_val); + + /* + * KVM doesn't support non-architectural PMUs, i.e. it should + * impossible to have fast mode RDPMC. Verify that attempting + * to use fast RDPMC always #GPs. + */ + GUEST_ASSERT(!expect_success || !pmu_has_fast_mode); + rdpmc_idx |= INTEL_RDPMC_FAST; + guest_test_rdpmc(rdpmc_idx, false, -1ull); + + vector = wrmsr_safe(msr, 0); + GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector); + } +} + +static void guest_test_gp_counters(void) +{ + uint8_t nr_gp_counters = 0; + uint32_t base_msr; + + if (guest_get_pmu_version()) + nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + + if (this_cpu_has(X86_FEATURE_PDCM) && + rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES) + base_msr = MSR_IA32_PMC0; + else + base_msr = MSR_IA32_PERFCTR0; + + guest_rd_wr_counters(base_msr, MAX_NR_GP_COUNTERS, nr_gp_counters, 0); + GUEST_DONE(); +} + +static void test_gp_counters(uint8_t pmu_version, uint64_t perf_capabilities, + uint8_t nr_gp_counters) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_gp_counters, + pmu_version, perf_capabilities); + + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_GP_COUNTERS, + nr_gp_counters); + + run_vcpu(vcpu); + + kvm_vm_free(vm); +} + +static void guest_test_fixed_counters(void) +{ + uint64_t supported_bitmask = 0; + uint8_t nr_fixed_counters = 0; + uint8_t i; + + /* Fixed counters require Architectural vPMU Version 2+. */ + if (guest_get_pmu_version() >= 2) + nr_fixed_counters = this_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + + /* + * The supported bitmask for fixed counters was introduced in PMU + * version 5. + */ + if (guest_get_pmu_version() >= 5) + supported_bitmask = this_cpu_property(X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK); + + guest_rd_wr_counters(MSR_CORE_PERF_FIXED_CTR0, MAX_NR_FIXED_COUNTERS, + nr_fixed_counters, supported_bitmask); + + for (i = 0; i < MAX_NR_FIXED_COUNTERS; i++) { + uint8_t vector; + uint64_t val; + + if (i >= nr_fixed_counters && !(supported_bitmask & BIT_ULL(i))) { + vector = wrmsr_safe(MSR_CORE_PERF_FIXED_CTR_CTRL, + FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL)); + __GUEST_ASSERT(vector == GP_VECTOR, + "Expected #GP for counter %u in FIXED_CTR_CTRL", i); + + vector = wrmsr_safe(MSR_CORE_PERF_GLOBAL_CTRL, + FIXED_PMC_GLOBAL_CTRL_ENABLE(i)); + __GUEST_ASSERT(vector == GP_VECTOR, + "Expected #GP for counter %u in PERF_GLOBAL_CTRL", i); + continue; + } + + wrmsr(MSR_CORE_PERF_FIXED_CTR0 + i, 0); + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL)); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(i)); + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + val = rdmsr(MSR_CORE_PERF_FIXED_CTR0 + i); + + GUEST_ASSERT_NE(val, 0); + } + GUEST_DONE(); +} + +static void test_fixed_counters(uint8_t pmu_version, uint64_t perf_capabilities, + uint8_t nr_fixed_counters, + uint32_t supported_bitmask) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_fixed_counters, + pmu_version, perf_capabilities); + + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK, + supported_bitmask); + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_FIXED_COUNTERS, + nr_fixed_counters); + + run_vcpu(vcpu); + + kvm_vm_free(vm); +} + +static void test_intel_counters(void) +{ + uint8_t nr_arch_events = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS); + uint8_t nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + uint8_t pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); + unsigned int i; + uint8_t v, j; + uint32_t k; + + const uint64_t perf_caps[] = { + 0, + PMU_CAP_FW_WRITES, + }; + + /* + * Test up to PMU v5, which is the current maximum version defined by + * Intel, i.e. is the last version that is guaranteed to be backwards + * compatible with KVM's existing behavior. + */ + uint8_t max_pmu_version = max_t(typeof(pmu_version), pmu_version, 5); + + /* + * Detect the existence of events that aren't supported by selftests. + * This will (obviously) fail any time the kernel adds support for a + * new event, but it's worth paying that price to keep the test fresh. + */ + TEST_ASSERT(nr_arch_events <= NR_INTEL_ARCH_EVENTS, + "New architectural event(s) detected; please update this test (length = %u, mask = %x)", + nr_arch_events, kvm_cpu_property(X86_PROPERTY_PMU_EVENTS_MASK)); + + /* + * Force iterating over known arch events regardless of whether or not + * KVM/hardware supports a given event. + */ + nr_arch_events = max_t(typeof(nr_arch_events), nr_arch_events, NR_INTEL_ARCH_EVENTS); + + for (v = 0; v <= max_pmu_version; v++) { + for (i = 0; i < ARRAY_SIZE(perf_caps); i++) { + if (!kvm_has_perf_caps && perf_caps[i]) + continue; + + pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n", + v, perf_caps[i]); + /* + * To keep the total runtime reasonable, test every + * possible non-zero, non-reserved bitmap combination + * only with the native PMU version and the full bit + * vector length. + */ + if (v == pmu_version) { + for (k = 1; k < (BIT(nr_arch_events) - 1); k++) + test_arch_events(v, perf_caps[i], nr_arch_events, k); + } + /* + * Test single bits for all PMU version and lengths up + * the number of events +1 (to verify KVM doesn't do + * weird things if the guest length is greater than the + * host length). Explicitly test a mask of '0' and all + * ones i.e. all events being available and unavailable. + */ + for (j = 0; j <= nr_arch_events + 1; j++) { + test_arch_events(v, perf_caps[i], j, 0); + test_arch_events(v, perf_caps[i], j, 0xff); + + for (k = 0; k < nr_arch_events; k++) + test_arch_events(v, perf_caps[i], j, BIT(k)); + } + + pr_info("Testing GP counters, PMU version %u, perf_caps = %lx\n", + v, perf_caps[i]); + for (j = 0; j <= nr_gp_counters; j++) + test_gp_counters(v, perf_caps[i], j); + + pr_info("Testing fixed counters, PMU version %u, perf_caps = %lx\n", + v, perf_caps[i]); + for (j = 0; j <= nr_fixed_counters; j++) { + for (k = 0; k <= (BIT(nr_fixed_counters) - 1); k++) + test_fixed_counters(v, perf_caps[i], j, k); + } + } + } +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_is_pmu_enabled()); + + TEST_REQUIRE(host_cpu_is_intel); + TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); + TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); + + kvm_pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); + kvm_has_perf_caps = kvm_cpu_has(X86_FEATURE_PDCM); + is_forced_emulation_enabled = kvm_is_forced_emulation_enabled(); + + test_intel_counters(); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index a3bd54b925ab..3c85d1ae9893 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -11,72 +11,18 @@ */ #define _GNU_SOURCE /* for program_invocation_short_name */ -#include "test_util.h" + #include "kvm_util.h" +#include "pmu.h" #include "processor.h" - -/* - * In lieu of copying perf_event.h into tools... - */ -#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) -#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) - -/* End of stuff taken from perf_event.h. */ - -/* Oddly, this isn't in perf_event.h. */ -#define ARCH_PERFMON_BRANCHES_RETIRED 5 +#include "test_util.h" #define NUM_BRANCHES 42 -#define INTEL_PMC_IDX_FIXED 32 - -/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ -#define MAX_FILTER_EVENTS 300 #define MAX_TEST_EVENTS 10 #define PMU_EVENT_FILTER_INVALID_ACTION (KVM_PMU_EVENT_DENY + 1) #define PMU_EVENT_FILTER_INVALID_FLAGS (KVM_PMU_EVENT_FLAGS_VALID_MASK << 1) -#define PMU_EVENT_FILTER_INVALID_NEVENTS (MAX_FILTER_EVENTS + 1) - -/* - * This is how the event selector and unit mask are stored in an AMD - * core performance event-select register. Intel's format is similar, - * but the event selector is only 8 bits. - */ -#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \ - (umask & 0xff) << 8) - -/* - * "Branch instructions retired", from the Intel SDM, volume 3, - * "Pre-defined Architectural Performance Events." - */ - -#define INTEL_BR_RETIRED EVENT(0xc4, 0) - -/* - * "Retired branch instructions", from Processor Programming Reference - * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, - * Preliminary Processor Programming Reference (PPR) for AMD Family - * 17h Model 31h, Revision B0 Processors, and Preliminary Processor - * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision - * B1 Processors Volume 1 of 2. - */ - -#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0) - - -/* - * "Retired instructions", from Processor Programming Reference - * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, - * Preliminary Processor Programming Reference (PPR) for AMD Family - * 17h Model 31h, Revision B0 Processors, and Preliminary Processor - * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision - * B1 Processors Volume 1 of 2. - * --- and --- - * "Instructions retired", from the Intel SDM, volume 3, - * "Pre-defined Architectural Performance Events." - */ - -#define INST_RETIRED EVENT(0xc0, 0) +#define PMU_EVENT_FILTER_INVALID_NEVENTS (KVM_PMU_EVENT_FILTER_MAX_EVENTS + 1) struct __kvm_pmu_event_filter { __u32 action; @@ -84,26 +30,28 @@ struct __kvm_pmu_event_filter { __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; - __u64 events[MAX_FILTER_EVENTS]; + __u64 events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; }; /* - * This event list comprises Intel's eight architectural events plus - * AMD's "retired branch instructions" for Zen[123] (and possibly - * other AMD CPUs). + * This event list comprises Intel's known architectural events, plus AMD's + * "retired branch instructions" for Zen1-Zen3 (and* possibly other AMD CPUs). + * Note, AMD and Intel use the same encoding for instructions retired. */ +kvm_static_assert(INTEL_ARCH_INSTRUCTIONS_RETIRED == AMD_ZEN_INSTRUCTIONS_RETIRED); + static const struct __kvm_pmu_event_filter base_event_filter = { .nevents = ARRAY_SIZE(base_event_filter.events), .events = { - EVENT(0x3c, 0), - INST_RETIRED, - EVENT(0x3c, 1), - EVENT(0x2e, 0x4f), - EVENT(0x2e, 0x41), - EVENT(0xc4, 0), - EVENT(0xc5, 0), - EVENT(0xa4, 1), - AMD_ZEN_BR_RETIRED, + 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, + INTEL_ARCH_TOPDOWN_SLOTS, + AMD_ZEN_BRANCHES_RETIRED, }, }; @@ -165,9 +113,9 @@ static void intel_guest_code(void) for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | INTEL_ARCH_BRANCHES_RETIRED); wrmsr(MSR_P6_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | INTEL_ARCH_INSTRUCTIONS_RETIRED); wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x3); run_and_measure_loop(MSR_IA32_PMC0); @@ -189,9 +137,9 @@ static void amd_guest_code(void) for (;;) { wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BRANCHES_RETIRED); wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | - ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); + ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_INSTRUCTIONS_RETIRED); run_and_measure_loop(MSR_K7_PERFCTR0); GUEST_SYNC(0); @@ -312,7 +260,7 @@ static void test_amd_deny_list(struct kvm_vcpu *vcpu) .action = KVM_PMU_EVENT_DENY, .nevents = 1, .events = { - EVENT(0x1C2, 0), + RAW_EVENT(0x1C2, 0), }, }; @@ -347,9 +295,9 @@ static void test_not_member_deny_list(struct kvm_vcpu *vcpu) f.action = KVM_PMU_EVENT_DENY; - remove_event(&f, INST_RETIRED); - remove_event(&f, INTEL_BR_RETIRED); - remove_event(&f, AMD_ZEN_BR_RETIRED); + remove_event(&f, INTEL_ARCH_INSTRUCTIONS_RETIRED); + remove_event(&f, INTEL_ARCH_BRANCHES_RETIRED); + remove_event(&f, AMD_ZEN_BRANCHES_RETIRED); test_with_filter(vcpu, &f); ASSERT_PMC_COUNTING_INSTRUCTIONS(); @@ -361,9 +309,9 @@ static void test_not_member_allow_list(struct kvm_vcpu *vcpu) f.action = KVM_PMU_EVENT_ALLOW; - remove_event(&f, INST_RETIRED); - remove_event(&f, INTEL_BR_RETIRED); - remove_event(&f, AMD_ZEN_BR_RETIRED); + remove_event(&f, INTEL_ARCH_INSTRUCTIONS_RETIRED); + remove_event(&f, INTEL_ARCH_BRANCHES_RETIRED); + remove_event(&f, AMD_ZEN_BRANCHES_RETIRED); test_with_filter(vcpu, &f); ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); @@ -452,9 +400,9 @@ static bool use_amd_pmu(void) * - Sapphire Rapids, Ice Lake, Cascade Lake, Skylake. */ #define MEM_INST_RETIRED 0xD0 -#define MEM_INST_RETIRED_LOAD EVENT(MEM_INST_RETIRED, 0x81) -#define MEM_INST_RETIRED_STORE EVENT(MEM_INST_RETIRED, 0x82) -#define MEM_INST_RETIRED_LOAD_STORE EVENT(MEM_INST_RETIRED, 0x83) +#define MEM_INST_RETIRED_LOAD RAW_EVENT(MEM_INST_RETIRED, 0x81) +#define MEM_INST_RETIRED_STORE RAW_EVENT(MEM_INST_RETIRED, 0x82) +#define MEM_INST_RETIRED_LOAD_STORE RAW_EVENT(MEM_INST_RETIRED, 0x83) static bool supports_event_mem_inst_retired(void) { @@ -486,9 +434,9 @@ static bool supports_event_mem_inst_retired(void) * B1 Processors Volume 1 of 2. */ #define LS_DISPATCH 0x29 -#define LS_DISPATCH_LOAD EVENT(LS_DISPATCH, BIT(0)) -#define LS_DISPATCH_STORE EVENT(LS_DISPATCH, BIT(1)) -#define LS_DISPATCH_LOAD_STORE EVENT(LS_DISPATCH, BIT(2)) +#define LS_DISPATCH_LOAD RAW_EVENT(LS_DISPATCH, BIT(0)) +#define LS_DISPATCH_STORE RAW_EVENT(LS_DISPATCH, BIT(1)) +#define LS_DISPATCH_LOAD_STORE RAW_EVENT(LS_DISPATCH, BIT(2)) #define INCLUDE_MASKED_ENTRY(event_select, mask, match) \ KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, false) @@ -729,14 +677,14 @@ static void add_dummy_events(uint64_t *events, int nevents) static void test_masked_events(struct kvm_vcpu *vcpu) { - int nevents = MAX_FILTER_EVENTS - MAX_TEST_EVENTS; - uint64_t events[MAX_FILTER_EVENTS]; + int nevents = KVM_PMU_EVENT_FILTER_MAX_EVENTS - MAX_TEST_EVENTS; + uint64_t events[KVM_PMU_EVENT_FILTER_MAX_EVENTS]; /* Run the test cases against a sparse PMU event filter. */ run_masked_events_tests(vcpu, events, 0); /* Run the test cases against a dense PMU event filter. */ - add_dummy_events(events, MAX_FILTER_EVENTS); + add_dummy_events(events, KVM_PMU_EVENT_FILTER_MAX_EVENTS); run_masked_events_tests(vcpu, events, nevents); } @@ -809,20 +757,19 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu) TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed"); } -static void intel_run_fixed_counter_guest_code(uint8_t fixed_ctr_idx) +static void intel_run_fixed_counter_guest_code(uint8_t idx) { for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); - wrmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx, 0); + wrmsr(MSR_CORE_PERF_FIXED_CTR0 + idx, 0); /* Only OS_EN bit is enabled for fixed counter[idx]. */ - wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, BIT_ULL(4 * fixed_ctr_idx)); - wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, - BIT_ULL(INTEL_PMC_IDX_FIXED + fixed_ctr_idx)); + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(idx, FIXED_PMC_KERNEL)); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(idx)); __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); - GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx)); + GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + idx)); } } @@ -920,7 +867,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu, *vcpu2 = NULL; struct kvm_vm *vm; - TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); + TEST_REQUIRE(kvm_is_pmu_enabled()); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS)); diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c index 1a46dd7bb391..416207c38a17 100644 --- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c +++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c @@ -63,7 +63,7 @@ int main(int argc, char *argv[]) vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); - vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR); + vcpu_set_cpuid_property(vcpu, X86_PROPERTY_MAX_PHY_ADDR, MAXPHYADDR); rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable"); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c index 9591a5fd54d7..f4f61a2d2464 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -13,10 +13,7 @@ #include "kvm_util.h" #include "vmx.h" -/* Forced emulation prefix, used to invoke the emulator unconditionally. */ -#define KVM_FEP "ud2; .byte 'k', 'v', 'm';" -#define KVM_FEP_LENGTH 5 -static int fep_available = 1; +static bool fep_available; #define MSR_NON_EXISTENT 0x474f4f00 @@ -261,13 +258,6 @@ static void guest_code_filter_allow(void) GUEST_ASSERT(data == 2); GUEST_ASSERT(guest_exception_count == 0); - /* - * Test to see if the instruction emulator is available (ie: the module - * parameter 'kvm.force_emulation_prefix=1' is set). This instruction - * will #UD if it isn't available. - */ - __asm__ __volatile__(KVM_FEP "nop"); - if (fep_available) { /* Let userspace know we aren't done. */ GUEST_SYNC(0); @@ -389,12 +379,6 @@ static void guest_fep_gp_handler(struct ex_regs *regs) &em_wrmsr_start, &em_wrmsr_end); } -static void guest_ud_handler(struct ex_regs *regs) -{ - fep_available = 0; - regs->rip += KVM_FEP_LENGTH; -} - static void check_for_guest_assert(struct kvm_vcpu *vcpu) { struct ucall uc; @@ -533,8 +517,11 @@ KVM_ONE_VCPU_TEST_SUITE(user_msr); KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) { struct kvm_vm *vm = vcpu->vm; + uint64_t cmd; int rc; + sync_global_to_guest(vm, fep_available); + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER); @@ -561,11 +548,11 @@ KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) run_guest_then_process_wrmsr(vcpu, MSR_NON_EXISTENT); run_guest_then_process_rdmsr(vcpu, MSR_NON_EXISTENT); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); vcpu_run(vcpu); - vm_install_exception_handler(vm, UD_VECTOR, NULL); + cmd = process_ucall(vcpu); - if (process_ucall(vcpu) != UCALL_DONE) { + if (fep_available) { + TEST_ASSERT_EQ(cmd, UCALL_SYNC); vm_install_exception_handler(vm, GP_VECTOR, guest_fep_gp_handler); /* Process emulated rdmsr and wrmsr instructions. */ @@ -583,6 +570,7 @@ KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) /* Confirm the guest completed without issues. */ run_guest_then_process_ucall_done(vcpu); } else { + TEST_ASSERT_EQ(cmd, UCALL_DONE); printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n"); } } @@ -786,5 +774,7 @@ KVM_ONE_VCPU_TEST(user_msr, user_exit_msr_flags, NULL) int main(int argc, char *argv[]) { + fep_available = kvm_is_forced_emulation_enabled(); + return test_harness_run(argc, argv); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 876442fadada..ea0cb3cae0f7 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -213,7 +213,7 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, lbr_perf_capabilities, guest_code) int main(int argc, char *argv[]) { - TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); + TEST_REQUIRE(kvm_is_pmu_enabled()); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION));