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, Andi Kleen <ak@linux.intel.com>,
Jim Mattson <jmattson@google.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 v2 09/16] KVM: x86/pmu: Switch to bitmask-based KVM PMU capabilities
Date: Tue, 1 Sep 2026 11:32:47 +0800 [thread overview]
Message-ID: <c12b2e2f-8872-405a-98e1-e594889797b4@linux.intel.com> (raw)
In-Reply-To: <20260827223755.143247-10-zide.chen@intel.com>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
On 8/28/2026 6:37 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.
>
> 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>
> ---
> arch/x86/kvm/cpuid.c | 14 +++++++++++---
> arch/x86/kvm/msrs.c | 12 ++++++------
> arch/x86/kvm/pmu.c | 21 ++++++++++++---------
> arch/x86/kvm/svm/pmu.c | 2 +-
> arch/x86/kvm/svm/svm.c | 9 +++++----
> arch/x86/kvm/vmx/pmu_intel.c | 7 ++++---
> arch/x86/kvm/vmx/vmx.c | 7 +++++--
> 7 files changed, 44 insertions(+), 28 deletions(-)
>
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index ddb022cb203a..106e719e7aee 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -1528,10 +1528,18 @@ 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)
> @@ -1896,7 +1904,7 @@ 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;
> + ebx.split.num_core_pmc = hweight64(kvm_pmu_cap.cntr_mask64);
> entry->ebx = ebx.full;
> break;
> }
> diff --git a/arch/x86/kvm/msrs.c b/arch/x86/kvm/msrs.c
> index 66fa7140d65d..49ab49f7c96e 100644
> --- a/arch/x86/kvm/msrs.c
> +++ b/arch/x86/kvm/msrs.c
> @@ -2610,20 +2610,20 @@ 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 7837e2e1af98..437a7bc49bf8 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 +176,14 @@ 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);
> +
> + /* Legacy vPMU exposes at most 3 fixed counters. */
> + if (!enable_mediated_pmu)
> + kvm_pmu_cap.fixed_cntr_mask64 &= GENMASK_ULL(2, 0);
>
> kvm_pmu_eventsel.INSTRUCTIONS_RETIRED =
> perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS);
> @@ -786,8 +789,8 @@ 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 0943ccc1d6b8..fb5a298244ec 100644
> --- a/arch/x86/kvm/svm/pmu.c
> +++ b/arch/x86/kvm/svm/pmu.c
> @@ -203,7 +203,7 @@ 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 fb8442a08b63..6f3427027e99 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -754,6 +754,7 @@ static void svm_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
> bool intercept = !kvm_vcpu_has_mediated_pmu(vcpu);
> struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
> unsigned long gp_mask = kvm_gp_pmc_mask(pmu);
> + unsigned long host_only_gp_mask;
> int i;
>
> if (!enable_mediated_pmu)
> @@ -772,7 +773,8 @@ static void svm_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
> svm_set_intercept_for_msr(vcpu, MSR_F15H_PERF_CTR + 2 * i,
> MSR_TYPE_RW, intercept);
>
> - for ( ; i < kvm_pmu_cap.num_counters_gp; i++)
> + host_only_gp_mask = kvm_pmu_cap.cntr_mask64 & ~gp_mask;
> + kvm_for_each_gp_counter(i, host_only_gp_mask)
> svm_enable_intercept_for_msr(vcpu, MSR_F15H_PERF_CTR + 2 * i,
> MSR_TYPE_RW);
>
> @@ -5563,9 +5565,8 @@ 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 (hweight64(kvm_pmu_cap.cntr_mask64) < 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 926d1c57f8bf..4df55a3e21da 100644
> --- a/arch/x86/kvm/vmx/pmu_intel.c
> +++ b/arch/x86/kvm/vmx/pmu_intel.c
> @@ -491,7 +491,8 @@ 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;
> }
>
> @@ -548,7 +549,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
> pmu->available_event_types = ~entry->ebx & (BIT_ULL(eax.split.mask_length) - 1);
>
> fixed_cntr_mask = BIT_ULL(edx.split.num_counters_fixed) - 1;
> - fixed_cntr_mask &= BIT_ULL(kvm_pmu_cap.num_counters_fixed) - 1;
> + fixed_cntr_mask &= kvm_pmu_cap.fixed_cntr_mask64;
>
> /*
> * The number of counters comes from guest CPUID data. Clamp the value
> @@ -556,7 +557,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
> */
> nr_gp_counters = min_t(int, eax.split.num_counters, X86_PMC_IDX_MAX - 1);
> pmu->pmc_exists64 = (BIT_ULL(nr_gp_counters) - 1) &
> - (BIT_ULL(kvm_pmu_cap.num_counters_gp) - 1);
> + kvm_pmu_cap.cntr_mask64;
>
> entry = kvm_find_cpuid_entry_index(vcpu, 7, 0);
> if (entry &&
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index be994adbd954..56daf5c61082 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -4230,6 +4230,7 @@ static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
> bool has_mediated_pmu = kvm_vcpu_has_mediated_pmu(vcpu);
> struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
> struct vcpu_vmx *vmx = to_vmx(vcpu);
> + unsigned long host_only_gp_mask, host_only_fixed_mask;
> unsigned long fixed_mask = kvm_fixed_pmc_mask(pmu);
> unsigned long gp_mask = kvm_gp_pmc_mask(pmu);
> bool intercept = !has_mediated_pmu;
> @@ -4252,23 +4253,25 @@ static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
>
> vm_exit_controls_changebit(vmx, vm_exit_controls_bits, has_mediated_pmu);
>
> + host_only_gp_mask = kvm_host_pmu.cntr_mask64 & ~gp_mask;
> kvm_for_each_gp_counter(i, gp_mask) {
> vmx_set_intercept_for_msr(vcpu, MSR_IA32_PERFCTR0 + i,
> MSR_TYPE_RW, intercept);
> vmx_set_intercept_for_msr(vcpu, MSR_IA32_PMC0 + i, MSR_TYPE_RW,
> intercept || !fw_writes_is_enabled(vcpu));
> }
> - for ( ; i < kvm_pmu_cap.num_counters_gp; i++) {
> + for_each_set_bit(i, &host_only_gp_mask, INTEL_PMC_MAX_GENERIC) {
> vmx_set_intercept_for_msr(vcpu, MSR_IA32_PERFCTR0 + i,
> MSR_TYPE_RW, true);
> vmx_set_intercept_for_msr(vcpu, MSR_IA32_PMC0 + i,
> MSR_TYPE_RW, true);
> }
>
> + host_only_fixed_mask = kvm_host_pmu.fixed_cntr_mask64 & ~fixed_mask;
> kvm_for_each_fixed_counter(i, fixed_mask)
> vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_FIXED_CTR0 + i,
> MSR_TYPE_RW, intercept);
> - for ( ; i < kvm_pmu_cap.num_counters_fixed; i++)
> + for_each_set_bit(i, &host_only_fixed_mask, INTEL_PMC_MAX_FIXED)
> vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_FIXED_CTR0 + i,
> MSR_TYPE_RW, true);
>
next prev parent reply other threads:[~2026-09-01 3:32 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-27 22:37 [PATCH] KVM: x86/pmu: Add mediated vPMU PerfMon v5 support Zide Chen
2026-08-27 22:37 ` [PATCH v2 01/16] KVM: x86/pmu: Remove redundant Perf Global Status MSR bit definitions Zide Chen
2026-08-27 22:57 ` sashiko-bot
2026-08-28 13:51 ` Chen, Zide
2026-09-01 2:07 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 02/16] KVM: x86/pmu: Rename all_valid_pmc_idx to pmc_exists Zide Chen
2026-09-01 2:09 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 03/16] KVM: x86/pmu: Rename reserved_bits to eventsel_rsvd in kvm_pmu Zide Chen
2026-09-01 2:17 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 04/16] KVM: x86/pmu: Gate BUFFER_OVF reserved bit on guest DS Zide Chen
2026-09-01 2:30 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 05/16] KVM: x86/pmu: Add PMC bitmap accessor helpers Zide Chen
2026-09-01 2:43 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 06/16] KVM: x86/pmu: Drop nr_arch_{gp,fixed}_counters from kvm_pmu Zide Chen
2026-09-01 3:07 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 07/16] KVM: x86/pmu: Expose kvm_host_pmu to vendor modules Zide Chen
2026-09-01 3:08 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 08/16] perf/x86: Plumb counter bitmap from x86_pmu to x86_pmu_cap Zide Chen
2026-08-27 22:37 ` [PATCH v2 09/16] KVM: x86/pmu: Switch to bitmask-based KVM PMU capabilities Zide Chen
2026-09-01 3:32 ` Mi, Dapeng [this message]
2026-08-27 22:37 ` [PATCH v2 10/16] perf/x86: Remove num_counters_{gp,fixed} from x86_pmu_capability Zide Chen
2026-08-27 22:37 ` [PATCH v2 11/16] KVM: x86/pmu: Emulate the GLOBAL_STATUS_SET and GLOBAL_INUSE MSRs Zide Chen
2026-08-27 23:05 ` sashiko-bot
2026-08-28 20:22 ` Chen, Zide
2026-09-01 6:45 ` Mi, Dapeng
2026-09-01 14:20 ` Chen, Zide
2026-09-02 0:44 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 12/16] KVM: x86/pmu: Populate CPUID.0AH:ECX fixed-counter bitmap Zide Chen
2026-09-01 6:50 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 13/16] KVM: x86/pmu: Factor out fixed counter control bit calculation Zide Chen
2026-09-01 6:57 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 14/16] KVM: x86/pmu: Ignore AnyThread bit if CPUID.0AH:EDX[15] is set Zide Chen
2026-09-01 8:01 ` Mi, Dapeng
2026-08-27 22:37 ` [PATCH v2 15/16] KVM: x86/pmu: Advertise PerfMon version 5 on Intel hosts Zide Chen
2026-08-27 22:37 ` [PATCH v2 16/16] KVM: selftests: Support fixed counters bitmap in pmu_counters_test Zide Chen
2026-08-29 9:30 ` [PATCH] KVM: x86/pmu: Add mediated vPMU PerfMon v5 support Peter Zijlstra
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=c12b2e2f-8872-405a-98e1-e594889797b4@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=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