Add internal state for PMUv3 emulation without programmable event counters. When fixed-counters-only mode is active, KVM reports no programmable counters and hides PMCEID, avoiding event-counter state whose behavior can depend on the selected hardware PMU.
The cycle counter still uses a host perf event. Unlike the normal PMU path, fixed-counters-only mode may create that event from the hardware PMU attached to the VCPU's current pCPU. If the VCPU later loads on a pCPU that is not covered by the existing event's PMU, request a PMU reload so the cycle counter can be recreated against the new pCPU's PMU. Keep this affinity check limited to fixed-counters-only VMs; the normal programmable-counter mode continues to use the VM-wide PMU and does not need per-load reload decisions. Registered pPMUs must cover every CPU on which fixed-counters-only emulation runs. On ACPI systems, a CPU brought online after PMU probing may have an unregistered PMU implementation. Full coverage is also not guaranteed when ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS is present. Fixed-counters-only emulation is not supported once a vCPU runs on an uncovered CPU. If event creation detects such a CPU, warn and add TAINT_CPU_OUT_OF_SPEC. Add a separate internal flag for explicit userspace PMU selection. The UAPI wiring added later will use it to keep explicit PMU selection and fixed-counters-only mode mutually exclusive while still allowing fixed-counters-only mode to replace the default PMU selected during KVM_ARM_VCPU_INIT. The UAPI wiring that sets the fixed-counters-only flag and records explicit PMU selection is added later in the series. Assisted-by: Codex:gpt-5.5 Signed-off-by: Akihiko Odaki <[email protected]> --- arch/arm64/include/asm/kvm_host.h | 4 +++ arch/arm64/kvm/arm.c | 2 ++ arch/arm64/kvm/pmu-emul.c | 60 ++++++++++++++++++++++++++++++++++----- include/kvm/arm_pmu.h | 2 ++ 4 files changed, 61 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 766c5cb32f54..d273bfc4cbaf 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -367,6 +367,10 @@ struct kvm_arch { #define KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS 10 /* Unhandled SEAs are taken to userspace */ #define KVM_ARCH_FLAG_EXIT_SEA 11 + /* PMUv3 is emulated with an explicitly specified hardware PMU */ +#define KVM_ARCH_FLAG_PMU_V3_EXPLICIT 12 + /* PMUv3 is emulated without programmable event counters */ +#define KVM_ARCH_FLAG_PMU_V3_FIXED_COUNTERS_ONLY 13 unsigned long flags; /* VM-wide vCPU feature set */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 55b07926ce2e..4b1f06a36055 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -665,6 +665,7 @@ static bool kvm_vcpu_should_clear_twe(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_s2_mmu *mmu; + int last_cpu = vcpu->cpu; int *last_ran; if (is_protected_kvm_enabled()) @@ -714,6 +715,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (has_vhe()) kvm_vcpu_load_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); + kvm_vcpu_load_pmu(vcpu, last_cpu); kvm_vcpu_pmu_restore_guest(vcpu); if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu); diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index a303752c5e61..9c1e2f3e41db 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -83,6 +83,11 @@ u64 kvm_pmu_evtyper_mask(struct kvm *kvm) return mask; } +static bool kvm_pmu_fixed_counters_only(struct kvm *kvm) +{ + return test_bit(KVM_ARCH_FLAG_PMU_V3_FIXED_COUNTERS_ONLY, &kvm->arch.flags); +} + /** * kvm_pmc_is_64bit - determine if counter is 64bit * @pmc: counter context @@ -725,14 +730,10 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(int cpu) return NULL; } -/** - * kvm_pmu_create_perf_event - create a perf event for a counter - * @pmc: Counter context - */ -static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) +static void kvm_pmu_create_perf_event_with_pmu(struct kvm_pmc *pmc, + struct arm_pmu *arm_pmu) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); - struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu; struct perf_event *event; struct perf_event_attr attr; int eventsel; @@ -766,7 +767,7 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) * Don't create an event if we're running on hardware that requires * PMUv3 event translation and we couldn't find a valid mapping. */ - eventsel = kvm_map_pmu_event(vcpu->kvm->arch.arm_pmu, eventsel); + eventsel = kvm_map_pmu_event(arm_pmu, eventsel); if (eventsel < 0) return; @@ -811,6 +812,32 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) pmc->perf_event = event; } +/** + * kvm_pmu_create_perf_event - create a perf event for a counter + * @pmc: Counter context + */ +static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) +{ + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); + struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu; + + if (kvm_pmu_fixed_counters_only(vcpu->kvm)) { + do { + arm_pmu = kvm_pmu_probe_armpmu(READ_ONCE(vcpu->cpu)); + + if (!arm_pmu) { + pr_warn_once("kvm: Unsupported PMU variation detected.\n"); + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + return; + } + + kvm_pmu_create_perf_event_with_pmu(pmc, arm_pmu); + } while (!cpumask_test_cpu(READ_ONCE(vcpu->cpu), &arm_pmu->supported_cpus)); + } else { + kvm_pmu_create_perf_event_with_pmu(pmc, arm_pmu); + } +} + /** * kvm_pmu_set_counter_event_type - set selected counter to monitor some event * @vcpu: The vcpu pointer @@ -897,6 +924,13 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) u64 val, mask = 0; int base, i, nr_events; + /* + * Hide the hardware PMU's event set to keep PMCEID stable across + * physical CPU migration. + */ + if (kvm_pmu_fixed_counters_only(vcpu->kvm)) + return 0; + if (!pmceid1) { val = compute_pmceid0(vcpu); base = 0; @@ -924,6 +958,15 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return val & mask; } +void kvm_vcpu_load_pmu(struct kvm_vcpu *vcpu, int last_cpu) +{ + if (!kvm_pmu_fixed_counters_only(vcpu->kvm) || vcpu->cpu == last_cpu || last_cpu == -1) + return; + + if (kvm_pmu_probe_armpmu(vcpu->cpu) != kvm_pmu_probe_armpmu(last_cpu)) + kvm_pmu_request_recreate(vcpu); +} + void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; @@ -1048,6 +1091,9 @@ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) { struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; + if (kvm_pmu_fixed_counters_only(kvm)) + return 0; + /* * Under KVM_ARM_VCPU_PMU_V3_STRICT no PMU exists until userspace sets * one, so this can be reached before arm_pmu is set. Report no diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index fca00f7f4c0a..33d81461f5cd 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -63,6 +63,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_apply_mdcr(struct kvm_vcpu *vcpu, u64 old, u64 val); void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx); +void kvm_vcpu_load_pmu(struct kvm_vcpu *vcpu, int last_cpu); void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu); int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); @@ -176,6 +177,7 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} +static inline void kvm_vcpu_load_pmu(struct kvm_vcpu *vcpu, int last_cpu) {} static inline void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) {} static inline u8 kvm_arm_pmu_get_pmuver_limit(void) { -- 2.55.0
