The AMD PMU virtualization is not disabled when configuring "-cpu host,-pmu" in the QEMU command line on an AMD server. Neither "-cpu host,-pmu" nor "-cpu EPYC" effectively disables AMD PMU virtualization in such an environment. As a result, VM logs typically show: [ 0.510611] Performance Events: Fam17h+ core perfctr, AMD PMU driver. whereas the expected logs should be: [ 0.596381] Performance Events: PMU not available due to virtualization, using software events only. [ 0.600972] NMI watchdog: Perf NMI watchdog permanently disabled This discrepancy occurs because AMD PMU does not use CPUID to determine whether PMU virtualization is supported. To address this, we introduce a new property, 'pmu-cap-disabled', for KVM acceleration. This property sets KVM_PMU_CAP_DISABLE if KVM_CAP_PMU_CAPABILITY is supported. Note that this feature currently supports only x86 hosts, as KVM_CAP_PMU_CAPABILITY is used exclusively for x86 systems. Signed-off-by: Dongli Zhang <dongli.zhang@xxxxxxxxxx> --- Another previous solution to re-use '-cpu host,-pmu': https://lore.kernel.org/all/20221119122901.2469-1-dongli.zhang@xxxxxxxxxx/ accel/kvm/kvm-all.c | 1 + include/sysemu/kvm_int.h | 1 + qemu-options.hx | 9 ++++++- target/i386/cpu.c | 2 +- target/i386/kvm/kvm.c | 52 ++++++++++++++++++++++++++++++++++++++ target/i386/kvm/kvm_i386.h | 2 ++ 6 files changed, 65 insertions(+), 2 deletions(-) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 801cff16a5..8b5ba45cf7 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -3933,6 +3933,7 @@ static void kvm_accel_instance_init(Object *obj) s->xen_evtchn_max_pirq = 256; s->device = NULL; s->msr_energy.enable = false; + s->pmu_cap_disabled = false; } /** diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index a1e72763da..cdee1a481c 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -166,6 +166,7 @@ struct KVMState uint16_t xen_gnttab_max_frames; uint16_t xen_evtchn_max_pirq; char *device; + bool pmu_cap_disabled; }; void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, diff --git a/qemu-options.hx b/qemu-options.hx index dacc9790a4..9684424835 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -191,7 +191,8 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel, " eager-split-size=n (KVM Eager Page Split chunk size, default 0, disabled. ARM only)\n" " notify-vmexit=run|internal-error|disable,notify-window=n (enable notify VM exit and set notify window, x86 only)\n" " thread=single|multi (enable multi-threaded TCG)\n" - " device=path (KVM device path, default /dev/kvm)\n", QEMU_ARCH_ALL) + " device=path (KVM device path, default /dev/kvm)\n" + " pmu-cap-disabled=true|false (disable KVM_CAP_PMU_CAPABILITY, x86 only, default false)\n", QEMU_ARCH_ALL) SRST ``-accel name[,prop=value[,...]]`` This is used to enable an accelerator. Depending on the target @@ -277,6 +278,12 @@ SRST option can be used to pass the KVM device to use via a file descriptor by setting the value to ``/dev/fdset/NN``. + ``pmu-cap-disabled=true|false`` + When using the KVM accelerator, it controls the disabling of + KVM_CAP_PMU_CAPABILITY via KVM_PMU_CAP_DISABLE. When this capability is + disabled, PMU virtualization is turned off at the KVM module level. + Note that this functionality is supported for x86 hosts only. + ERST DEF("smp", HAS_ARG, QEMU_OPTION_smp, diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 4490a7a8d6..c97ed74a47 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -7102,7 +7102,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, case 0x80000022: *eax = *ebx = *ecx = *edx = 0; /* AMD Extended Performance Monitoring and Debug */ - if (kvm_enabled() && cpu->enable_pmu && + if (kvm_enabled() && cpu->enable_pmu && !kvm_pmu_cap_disabled() && (env->features[FEAT_8000_0001_ECX] & CPUID_EXT3_PERFCORE) && (env->features[FEAT_8000_0022_EAX] & CPUID_8000_0022_EAX_PERFMON_V2)) { *eax |= CPUID_8000_0022_EAX_PERFMON_V2; diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 8e17942c3b..ed73b1e7e0 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -166,6 +166,7 @@ static bool has_msr_vmx_procbased_ctls2; static bool has_msr_perf_capabs; static bool has_msr_pkrs; static bool has_msr_hwcr; +static bool has_pmu_cap; static uint32_t has_architectural_pmu_version; static uint32_t num_architectural_pmu_gp_counters; @@ -3196,6 +3197,11 @@ static void kvm_vm_enable_energy_msrs(KVMState *s) return; } +bool kvm_pmu_cap_disabled(void) +{ + return kvm_state->pmu_cap_disabled; +} + int kvm_arch_init(MachineState *ms, KVMState *s) { int ret; @@ -3335,6 +3341,23 @@ int kvm_arch_init(MachineState *ms, KVMState *s) } } + has_pmu_cap = kvm_check_extension(s, KVM_CAP_PMU_CAPABILITY); + + if (s->pmu_cap_disabled) { + if (has_pmu_cap) { + ret = kvm_vm_enable_cap(s, KVM_CAP_PMU_CAPABILITY, 0, + KVM_PMU_CAP_DISABLE); + if (ret < 0) { + s->pmu_cap_disabled = false; + error_report("kvm: Failed to disable pmu cap: %s", + strerror(-ret)); + } + } else { + s->pmu_cap_disabled = false; + error_report("kvm: KVM_CAP_PMU_CAPABILITY is not supported"); + } + } + return 0; } @@ -6525,6 +6548,29 @@ static void kvm_arch_set_xen_evtchn_max_pirq(Object *obj, Visitor *v, s->xen_evtchn_max_pirq = value; } +static void kvm_set_pmu_cap_disabled(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + bool pmu_cap_disabled; + Error *error = NULL; + + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has " + "been initialized"); + return; + } + + visit_type_bool(v, name, &pmu_cap_disabled, &error); + if (error) { + error_propagate(errp, error); + return; + } + + s->pmu_cap_disabled = pmu_cap_disabled; +} + void kvm_arch_accel_class_init(ObjectClass *oc) { object_class_property_add_enum(oc, "notify-vmexit", "NotifyVMexitOption", @@ -6564,6 +6610,12 @@ void kvm_arch_accel_class_init(ObjectClass *oc) NULL, NULL); object_class_property_set_description(oc, "xen-evtchn-max-pirq", "Maximum number of Xen PIRQs"); + + object_class_property_add(oc, "pmu-cap-disabled", "bool", + NULL, kvm_set_pmu_cap_disabled, + NULL, NULL); + object_class_property_set_description(oc, "pmu-cap-disabled", + "Disable KVM_CAP_PMU_CAPABILITY"); } void kvm_set_max_apic_id(uint32_t max_apic_id) diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h index 9de9c0d303..03522de9d1 100644 --- a/target/i386/kvm/kvm_i386.h +++ b/target/i386/kvm/kvm_i386.h @@ -49,6 +49,8 @@ uint64_t kvm_arch_get_supported_msr_feature(KVMState *s, uint32_t index); void kvm_set_max_apic_id(uint32_t max_apic_id); void kvm_request_xsave_components(X86CPU *cpu, uint64_t mask); +bool kvm_pmu_cap_disabled(void); + #ifdef CONFIG_KVM bool kvm_is_vm_type_supported(int type); -- 2.39.3
