From: "Mi, Dapeng" <dapeng1.mi@linux.intel.com>
To: Zide Chen <zide.chen@intel.com>,
Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Peter Zijlstra <peterz@infradead.org>
Cc: kvm@vger.kernel.org, Jim Mattson <jmattson@google.com>,
Yosry Ahmed <yosry@kernel.org>, Andi Kleen <ak@linux.intel.com>,
Stephane Eranian <eranian@google.com>,
linux-kernel@vger.kernel.org, Mingwei Zhang <mizhang@google.com>,
Das Sandipan <Sandipan.Das@amd.com>,
Shukla Manali <Manali.Shukla@amd.com>,
Xudong Hao <xudong.hao@intel.com>
Subject: Re: [PATCH v4 09/21] KVM: x86/pmu: Switch to bitmask-based KVM PMU capabilities
Date: Fri, 13 Nov 2026 14:40:43 +0800 [thread overview]
Message-ID: <792c8390-5c39-4e60-bbd5-0901f3d5b2a1@linux.intel.com> (raw)
In-Reply-To: <20261112203227.289379-10-zide.chen@intel.com>
On 11/13/2026 4:32 AM, Zide Chen wrote:
> From: Dapeng Mi <dapeng1.mi@linux.intel.com>
>
> Intel platforms support non-contiguous fixed counters via CPUID.0AH:ECX
> starting with PerfMon v5, and support non-contiguous GP counters
> through the Architectural PerfMon Extension (CPUID leaf 23H).
>
> struct x86_pmu_capability now exposes {,fixed_}cntr_mask64 bitmaps,
> which may contain sparse bits representing non-contiguous counters.
> Switch KVM's kvm_host_pmu and kvm_pmu_cap consumers over to the new
> bitmask fields, including iterating kvm_host_pmu bitmasks directly in
> VMX and SVM PMU MSR intercept setup.
>
> CPUID.0AH:EAX[15:8] and CPUID.0AH:EDX[4:0] enumerate only contiguous
> counters. Derive these values from kvm_pmu_cap.{,fixed_}cntr_mask64 as
> the number of consecutive counters starting at index 0.
>
> Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
> Co-developed-by: Zide Chen <zide.chen@intel.com>
> Signed-off-by: Zide Chen <zide.chen@intel.com>
> ---
> v4:
> - Cleanly substitute kvm_pmu_cap.num_counters_{gp,fixed} with
> find_first_zero_bit() in intel_pmu_refresh() without throwaway
> code churn.
> - Use find_first_zero_bit() instead of hweight64() for AMD CPUID
> 0x80000022 EBX[3:0] (NumCorePmc) and svm_set_cpu_caps() to enumerate
> contiguous counters. (Yosry)
> - Do not carry over Jim's Reviewed-by from v3 due to reworking counter
> clamping in intel_pmu_refresh().
>
> v3:
> - Iterate kvm_host_pmu bitmasks directly in VMX and SVM intercept loops.
> - Clamp nr_{gp,fixed}_counters to the number of contiguous counters
> supported by KVM in intel_pmu_refresh(). (Jim, Sashiko)
> - Drop redundant !enable_mediated_pmu clamp on fixed_cntr_mask64.
> (Sashiko)
> ---
> arch/x86/kvm/cpuid.c | 17 ++++++++++++++---
> arch/x86/kvm/msrs.c | 12 ++++++------
> arch/x86/kvm/pmu.c | 17 ++++++++---------
> arch/x86/kvm/svm/pmu.c | 2 +-
> arch/x86/kvm/svm/svm.c | 8 ++++----
> arch/x86/kvm/vmx/pmu_intel.c | 18 +++++++++++++++---
> arch/x86/kvm/vmx/vmx.c | 4 ++--
> 7 files changed, 50 insertions(+), 28 deletions(-)
>
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index adafd6fa2c54..427871ec365f 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -1535,10 +1535,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
> }
>
> eax.split.version_id = kvm_pmu_cap.version;
> - eax.split.num_counters = kvm_pmu_cap.num_counters_gp;
> +
> + /* Contiguous GP counters only. */
> + eax.split.num_counters =
> + find_first_zero_bit(kvm_pmu_cap.cntr_mask,
> + KVM_MAX_NR_GP_COUNTERS);
> eax.split.bit_width = kvm_pmu_cap.bit_width_gp;
> eax.split.mask_length = kvm_pmu_cap.events_mask_len;
> - edx.split.num_counters_fixed = kvm_pmu_cap.num_counters_fixed;
> +
> + /* Contiguous fixed counters only. */
> + edx.split.num_counters_fixed =
> + find_first_zero_bit(kvm_pmu_cap.fixed_cntr_mask,
> + KVM_MAX_NR_FIXED_COUNTERS);
> edx.split.bit_width_fixed = kvm_pmu_cap.bit_width_fixed;
>
> if (kvm_pmu_cap.version)
> @@ -1903,7 +1911,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
>
> cpuid_entry_override(entry, CPUID_8000_0022_EAX);
>
> - ebx.split.num_core_pmc = kvm_pmu_cap.num_counters_gp;
> + /* Contiguous GP counters only. */
> + ebx.split.num_core_pmc =
> + find_first_zero_bit(kvm_pmu_cap.cntr_mask,
> + KVM_MAX_NR_GP_COUNTERS);
> entry->ebx = ebx.full;
> break;
> }
> diff --git a/arch/x86/kvm/msrs.c b/arch/x86/kvm/msrs.c
> index e91650af44c2..01fb130a7d24 100644
> --- a/arch/x86/kvm/msrs.c
> +++ b/arch/x86/kvm/msrs.c
> @@ -2621,20 +2621,20 @@ static void kvm_probe_msr_to_save(u32 msr_index)
> break;
> case MSR_ARCH_PERFMON_PERFCTR0 ...
> MSR_ARCH_PERFMON_PERFCTR0 + KVM_MAX_NR_GP_COUNTERS - 1:
> - if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >=
> - kvm_pmu_cap.num_counters_gp)
> + if (!(BIT_ULL(msr_index - MSR_ARCH_PERFMON_PERFCTR0) &
> + kvm_pmu_cap.cntr_mask64))
> return;
> break;
> case MSR_ARCH_PERFMON_EVENTSEL0 ...
> MSR_ARCH_PERFMON_EVENTSEL0 + KVM_MAX_NR_GP_COUNTERS - 1:
> - if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >=
> - kvm_pmu_cap.num_counters_gp)
> + if (!(BIT_ULL(msr_index - MSR_ARCH_PERFMON_EVENTSEL0) &
> + kvm_pmu_cap.cntr_mask64))
> return;
> break;
> case MSR_ARCH_PERFMON_FIXED_CTR0 ...
> MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_MAX_NR_FIXED_COUNTERS - 1:
> - if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >=
> - kvm_pmu_cap.num_counters_fixed)
> + if (!(BIT_ULL(msr_index - MSR_ARCH_PERFMON_FIXED_CTR0) &
> + kvm_pmu_cap.fixed_cntr_mask64))
> return;
> break;
> case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
> index d203cbc7fd12..e1999a6c85d7 100644
> --- a/arch/x86/kvm/pmu.c
> +++ b/arch/x86/kvm/pmu.c
> @@ -20,7 +20,6 @@
> #include <asm/perf_event.h>
> #include <asm/cpu_device_id.h>
> #include "x86.h"
> -#include "cpuid.h"
> #include "lapic.h"
> #include "pmu.h"
>
> @@ -156,8 +155,8 @@ void kvm_init_pmu_capability(struct kvm_pmu_ops *pmu_ops)
> * there are a non-zero number of counters, but fewer than what
> * is architecturally required.
> */
> - if (!kvm_host_pmu.num_counters_gp ||
> - WARN_ON_ONCE(kvm_host_pmu.num_counters_gp < min_nr_gp_ctrs))
> + if (!kvm_host_pmu.cntr_mask64 ||
> + WARN_ON_ONCE(hweight64(kvm_host_pmu.cntr_mask64) < min_nr_gp_ctrs))
> enable_pmu = false;
> else if (is_intel && !kvm_host_pmu.version)
> enable_pmu = false;
> @@ -177,10 +176,10 @@ void kvm_init_pmu_capability(struct kvm_pmu_ops *pmu_ops)
>
> memcpy(&kvm_pmu_cap, &kvm_host_pmu, sizeof(kvm_host_pmu));
> kvm_pmu_cap.version = min(kvm_pmu_cap.version, 2);
> - kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp,
> - pmu_ops->MAX_NR_GP_COUNTERS);
> - kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed,
> - KVM_MAX_NR_FIXED_COUNTERS);
> + kvm_pmu_cap.cntr_mask64 &=
> + GENMASK_ULL(pmu_ops->MAX_NR_GP_COUNTERS - 1, 0);
> + kvm_pmu_cap.fixed_cntr_mask64 &=
> + GENMASK_ULL(KVM_MAX_NR_FIXED_COUNTERS - 1, 0);
>
> kvm_pmu_eventsel.INSTRUCTIONS_RETIRED =
> perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS);
> @@ -788,8 +787,8 @@ static bool kvm_need_any_pmc_intercept(struct kvm_vcpu *vcpu)
> * KVM's capabilities are constrained based on KVM support, i.e. KVM's
> * capabilities themselves may be a subset of hardware capabilities.
> */
> - return kvm_gp_pmc_mask(pmu) != BIT_ULL(kvm_host_pmu.num_counters_gp) - 1 ||
> - kvm_fixed_pmc_mask(pmu) != BIT_ULL(kvm_host_pmu.num_counters_fixed) - 1;
> + return kvm_gp_pmc_mask(pmu) != kvm_host_pmu.cntr_mask64 ||
> + kvm_fixed_pmc_mask(pmu) != kvm_host_pmu.fixed_cntr_mask64;
> }
>
> bool kvm_need_perf_global_ctrl_intercept(struct kvm_vcpu *vcpu)
> diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
> index 64215024e70e..5eedf9b35fce 100644
> --- a/arch/x86/kvm/svm/pmu.c
> +++ b/arch/x86/kvm/svm/pmu.c
> @@ -196,7 +196,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
> }
>
> pmu->pmc_exists64 = (BIT_ULL(nr_gp_counters) - 1) &
> - (BIT_ULL(kvm_pmu_cap.num_counters_gp) - 1);
> + kvm_pmu_cap.cntr_mask64;
>
> if (pmu->version > 1) {
> pmu->global_ctrl_rsvd = ~pmu->pmc_exists64;
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index e21abcedea70..5b9c9d149486 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -773,7 +773,7 @@ static void svm_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
> MSR_TYPE_RW, intercept || !test_bit(i, &gp_mask));
>
> intercept |= !guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE);
> - for (i = 0; i < kvm_pmu_cap.num_counters_gp; i++)
> + for_each_set_bit(i, kvm_host_pmu.cntr_mask, AMD64_NUM_COUNTERS_CORE)
> svm_set_intercept_for_msr(vcpu, MSR_F15H_PERF_CTR + 2 * i,
> MSR_TYPE_RW, intercept || !test_bit(i, &gp_mask));
>
> @@ -5719,9 +5719,9 @@ static __init void svm_set_cpu_caps(void)
> * access to enough counters to virtualize "core" support,
> * otherwise limit vPMU support to the legacy number of counters.
> */
> - if (kvm_pmu_cap.num_counters_gp < AMD64_NUM_COUNTERS_CORE)
> - kvm_pmu_cap.num_counters_gp = min(AMD64_NUM_COUNTERS,
> - kvm_pmu_cap.num_counters_gp);
> + if (find_first_zero_bit(kvm_pmu_cap.cntr_mask,
> + KVM_MAX_NR_GP_COUNTERS) < AMD64_NUM_COUNTERS_CORE)
> + kvm_pmu_cap.cntr_mask64 &= GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0);
> else
> kvm_cpu_cap_check_and_set(X86_FEATURE_PERFCTR_CORE);
>
> diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
> index 68d23c7877a2..a240b74ac704 100644
> --- a/arch/x86/kvm/vmx/pmu_intel.c
> +++ b/arch/x86/kvm/vmx/pmu_intel.c
> @@ -493,7 +493,8 @@ static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index)
> * 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);
> + WARN_ON_ONCE(!eventsel &&
> + (kvm_pmu_cap.fixed_cntr_mask64 & BIT_ULL(index)));
> return eventsel;
> }
>
> @@ -548,12 +549,23 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
> kvm_pmu_cap.events_mask_len);
> pmu->available_event_types = ~entry->ebx & (BIT_ULL(eax.split.mask_length) - 1);
>
> + /*
> + * CPUID.0AH:EDX[4:0] can only enumerate contiguous counters. Clamp the
> + * value to the number of contiguous fixed counters supported by KVM.
> + */
> nr_fixed_counters = min_t(int, edx.split.num_counters_fixed,
> - kvm_pmu_cap.num_counters_fixed);
> + find_first_zero_bit(kvm_pmu_cap.fixed_cntr_mask,
> + KVM_MAX_NR_FIXED_COUNTERS));
> +
> fixed_mask = BIT_ULL(nr_fixed_counters) - 1;
>
> + /*
> + * CPUID.0AH:EAX[15:8] can only enumerate contiguous counters. Clamp the
> + * value to the number of contiguous GP counters supported by KVM.
> + */
> nr_gp_counters = min_t(int, eax.split.num_counters,
> - kvm_pmu_cap.num_counters_gp);
> + find_first_zero_bit(kvm_pmu_cap.cntr_mask,
> + KVM_MAX_NR_GP_COUNTERS));
> pmu->pmc_exists64 = BIT_ULL(nr_gp_counters) - 1;
>
> entry = kvm_find_cpuid_entry_index(vcpu, 7, 0);
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 944ecbf351cf..9db6107943ec 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -4264,7 +4264,7 @@ static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
>
> vm_exit_controls_changebit(vmx, vm_exit_controls_bits, has_mediated_pmu);
>
> - for (i = 0; i < kvm_pmu_cap.num_counters_gp; i++) {
> + for_each_set_bit(i, kvm_host_pmu.cntr_mask, INTEL_PMC_MAX_GENERIC) {
Nit: This seems a long standing bug, kvm_host_pmu instead of kvm_pmu_cap
should be used here. Better put a stand-alone patch to fix this issue at
the header of this patch series if possible.
Thanks.
> bool pmc_intercept = intercept || !test_bit(i, &gp_mask);
>
> vmx_set_intercept_for_msr(vcpu, MSR_IA32_PERFCTR0 + i,
> @@ -4273,7 +4273,7 @@ static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
> pmc_intercept || !fw_writes_is_enabled(vcpu));
> }
>
> - for (i = 0; i < kvm_pmu_cap.num_counters_fixed; i++) {
> + for_each_set_bit(i, kvm_host_pmu.fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
> bool pmc_intercept = intercept || !test_bit(i, &fixed_mask);
>
> vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_FIXED_CTR0 + i,
next prev parent reply other threads:[~2026-11-13 6:40 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-12 20:32 [PATCH v4 00/21] KVM: x86/pmu: Add mediated vPMU PerfMon v5 support Zide Chen
2026-11-12 20:32 ` [PATCH v4 01/21] KVM: SVM: Drop counter MSR checks in amd_is_valid_msr() Zide Chen
2026-11-12 20:32 ` [PATCH v4 02/21] KVM: x86/pmu: Remove redundant Perf Global Status MSR bit definitions Zide Chen
2026-11-12 20:32 ` [PATCH v4 03/21] KVM: x86/pmu: Rename all_valid_pmc_idx to pmc_exists Zide Chen
2026-11-12 20:32 ` [PATCH v4 04/21] KVM: x86/pmu: Rename reserved_bits to eventsel_rsvd in kvm_pmu Zide Chen
2026-11-12 20:32 ` [PATCH v4 05/21] KVM: x86/pmu: Use pmc_exists in PMC lookup helpers Zide Chen
2026-11-12 20:32 ` [PATCH v4 06/21] KVM: x86/pmu: Drop nr_arch_{gp,fixed}_counters from kvm_pmu Zide Chen
2026-11-12 20:32 ` [PATCH v4 07/21] KVM: x86/pmu: Expose kvm_host_pmu to vendor modules Zide Chen
2026-11-12 20:32 ` [PATCH v4 08/21] perf/x86: Plumb counter bitmap from x86_pmu to x86_pmu_cap Zide Chen
2026-11-12 20:32 ` [PATCH v4 09/21] KVM: x86/pmu: Switch to bitmask-based KVM PMU capabilities Zide Chen
2026-11-13 6:40 ` Mi, Dapeng [this message]
2026-11-12 20:32 ` [PATCH v4 10/21] perf/x86: Remove num_counters_{gp,fixed} from x86_pmu_capability Zide Chen
2026-11-12 20:32 ` [PATCH v4 11/21] KVM: x86/pmu: Document GLOBAL_STATUS_RESET passthrough erratum Zide Chen
2026-11-12 20:32 ` [PATCH v4 12/21] KVM: x86/pmu: Mark CondChgd reserved in global_status_rsvd Zide Chen
2026-11-12 20:32 ` [PATCH v4 13/21] KVM: x86/pmu: Emulate IA32_PERF_GLOBAL_STATUS_SET MSR Zide Chen
2026-11-12 20:32 ` [PATCH v4 14/21] KVM: x86/pmu: Emulate IA32_PERF_GLOBAL_INUSE MSR Zide Chen
2026-11-12 20:32 ` [PATCH v4 15/21] KVM: x86/pmu: Clamp pmu->version to kvm_pmu_cap.version Zide Chen
2026-11-12 20:32 ` [PATCH v4 16/21] KVM: x86/pmu: Populate CPUID.0AH:ECX fixed-counter bitmap Zide Chen
2026-11-12 20:32 ` [PATCH v4 17/21] KVM: x86/pmu: Factor out fixed counter control bit calculation Zide Chen
2026-11-12 20:32 ` [PATCH v4 18/21] KVM: x86/pmu: Mask only OS/USR bits when filtering fixed counters Zide Chen
2026-11-12 20:32 ` [PATCH v4 19/21] KVM: x86/pmu: Ignore AnyThread bit if CPUID.0AH:EDX[15] is set Zide Chen
2026-11-12 20:32 ` [PATCH v4 20/21] KVM: x86/pmu: Advertise PerfMon version 5 on Intel hosts Zide Chen
2026-11-12 20:32 ` [PATCH v4 21/21] KVM: selftests: Support fixed counters bitmap in pmu_counters_test Zide Chen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=792c8390-5c39-4e60-bbd5-0901f3d5b2a1@linux.intel.com \
--to=dapeng1.mi@linux.intel.com \
--cc=Manali.Shukla@amd.com \
--cc=Sandipan.Das@amd.com \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mizhang@google.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=seanjc@google.com \
--cc=xudong.hao@intel.com \
--cc=yosry@kernel.org \
--cc=zide.chen@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®