Re: [PATCH v6 2/8] KVM: x86/pmu: Support Intel fixed counter 3 on mediated vPMU

[Mi, Dapeng]

Reviewed-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>

On 6/30/2026 7:19 AM, Zide Chen wrote:
> From: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
>
> Starting with Ice Lake, Intel introduced fixed counter 3, which counts
> TOPDOWN.SLOTS - the number of available slots for an unhalted logical
> processor.  It serves as the denominator for top-level metrics in the
> Top-down Microarchitecture Analysis method.
>
> Emulating this counter on legacy vPMU would require introducing a new
> generic perf encoding for the Intel-specific TOPDOWN.SLOTS event in
> order to call perf_get_hw_event_config().  This is undesirable as it
> would pollute the generic perf event encoding.
>
> Moreover, KVM does not intend to emulate IA32_PERF_METRICS in the
> legacy vPMU model, and without IA32_PERF_METRICS, emulating this
> counter has little practical value.  Therefore, expose fixed counter
> 3 to guests only when mediated vPMU is enabled.
>
> Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
> Co-developed-by: Zide Chen <zide.chen@xxxxxxxxx>
> Signed-off-by: Zide Chen <zide.chen@xxxxxxxxx>
> ---
> v6:
> - Update comments to replace 2 with KVM_MAX_NR_INTEL_FIXED_COUNTERS - 1.
> v3:
> - Move the non-contiguous counter filter code to pmu.c
> v2:
> - Don't advertise fixed counter 3 to userspace if the host doesn't
>   support it.
> ---
>  arch/x86/include/asm/kvm_host.h |  2 +-
>  arch/x86/kvm/msrs.c             |  4 ++--
>  arch/x86/kvm/pmu.c              | 18 +++++++++++++++++-
>  3 files changed, 20 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index d8700eb848b4..dc9e4e8bfc07 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -609,7 +609,7 @@ struct kvm_pmc {
>  #define KVM_MAX_NR_GP_COUNTERS		KVM_MAX(KVM_MAX_NR_INTEL_GP_COUNTERS, \
>  						KVM_MAX_NR_AMD_GP_COUNTERS)
>  
> -#define KVM_MAX_NR_INTEL_FIXED_COUNTERS	3
> +#define KVM_MAX_NR_INTEL_FIXED_COUNTERS	4
>  #define KVM_MAX_NR_AMD_FIXED_COUNTERS	0
>  #define KVM_MAX_NR_FIXED_COUNTERS	KVM_MAX(KVM_MAX_NR_INTEL_FIXED_COUNTERS, \
>  						KVM_MAX_NR_AMD_FIXED_COUNTERS)
> diff --git a/arch/x86/kvm/msrs.c b/arch/x86/kvm/msrs.c
> index c230b18d87e3..3bf42d90ad14 100644
> --- a/arch/x86/kvm/msrs.c
> +++ b/arch/x86/kvm/msrs.c
> @@ -228,7 +228,7 @@ static const u32 msrs_to_save_base[] = {
>  
>  static const u32 msrs_to_save_pmu[] = {
>  	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
> -	MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
> +	MSR_ARCH_PERFMON_FIXED_CTR2, MSR_ARCH_PERFMON_FIXED_CTR3,
>  	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
>  	MSR_CORE_PERF_GLOBAL_CTRL,
>  	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
> @@ -2688,7 +2688,7 @@ void kvm_init_msr_lists(void)
>  {
>  	unsigned i;
>  
> -	BUILD_BUG_ON_MSG(KVM_MAX_NR_FIXED_COUNTERS != 3,
> +	BUILD_BUG_ON_MSG(KVM_MAX_NR_FIXED_COUNTERS != 4,
>  			 "Please update the fixed PMCs in msrs_to_save_pmu[]");
>  
>  	num_msrs_to_save = 0;
> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
> index 62d0ed99ebe9..f82ba63767d0 100644
> --- a/arch/x86/kvm/pmu.c
> +++ b/arch/x86/kvm/pmu.c
> @@ -99,7 +99,8 @@ 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_MAX_NR_INTEL_GP_COUNTERS-1] <=> gp counters
> - *                 [KVM_FIXED_PMC_BASE_IDX .. KVM_FIXED_PMC_BASE_IDX + 2] <=> fixed
> + *                 [KVM_FIXED_PMC_BASE_IDX .. KVM_FIXED_PMC_BASE_IDX +
> + *                  KVM_MAX_NR_INTEL_FIXED_COUNTERS - 1] <=> fixed
>   *        * AMD:   [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H
>   *          and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters
>   */
> @@ -134,6 +135,8 @@ void kvm_init_pmu_capability(struct kvm_pmu_ops *pmu_ops)
>  {
>  	bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;
>  	int min_nr_gp_ctrs = pmu_ops->MIN_NR_GP_COUNTERS;
> +	union cpuid10_edx edx;
> +	u32 eax, ebx, ecx;
>  
>  	/*
>  	 * Hybrid PMUs don't play nice with virtualization without careful
> @@ -181,6 +184,19 @@ void kvm_init_pmu_capability(struct kvm_pmu_ops *pmu_ops)
>  	kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed,
>  					     KVM_MAX_NR_FIXED_COUNTERS);
>  
> +	/*
> +	 * Currently, KVM doesn't support non-contiguous fixed counters; make
> +	 * sure only contiguous ones are retained in kvm_pmu_cap.
> +	 */
> +	if (kvm_host_pmu.version >= 5) {
> +		cpuid(0xa, &eax, &ebx, &ecx, &edx.full);
> +		if (kvm_pmu_cap.num_counters_fixed > edx.split.num_counters_fixed)
> +			kvm_pmu_cap.num_counters_fixed = edx.split.num_counters_fixed;
> +	}
> +
> +	if (!enable_mediated_pmu && kvm_pmu_cap.num_counters_fixed > 3)
> +		kvm_pmu_cap.num_counters_fixed = 3;
> +
>  	kvm_pmu_eventsel.INSTRUCTIONS_RETIRED =
>  		perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS);
>  	kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED =