Kernel KVM virtualization development
 help / color / mirror / Atom feed
From: Zide Chen <zide.chen@intel.com>
To: Sean Christopherson <seanjc@google.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	Jim Mattson <jmattson@google.com>,
	Mingwei Zhang <mizhang@google.com>,
	Zide Chen <zide.chen@intel.com>,
	Das Sandipan <Sandipan.Das@amd.com>,
	Shukla Manali <Manali.Shukla@amd.com>,
	Dapeng Mi <dapeng1.mi@linux.intel.com>,
	Falcon Thomas <thomas.falcon@intel.com>,
	Xudong Hao <xudong.hao@intel.com>
Subject: [PATCH 08/15] KVM: x86/pmu: Switch to bitmask-based KVM PMU capabilities
Date: Tue,  7 Jul 2026 11:33:58 -0700	[thread overview]
Message-ID: <20260707183405.15571-9-zide.chen@intel.com> (raw)
In-Reply-To: <20260707183405.15571-1-zide.chen@intel.com>

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           | 34 +++++++++++-----------------------
 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, 43 insertions(+), 42 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 2698fa42cd97..151a4794f834 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1514,10 +1514,18 @@ 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)
@@ -1882,7 +1890,7 @@ 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 c751a8dbd45d..7524d019f1be 100644
--- a/arch/x86/kvm/msrs.c
+++ b/arch/x86/kvm/msrs.c
@@ -2631,20 +2631,20 @@ 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 3647ce3f0e3f..bc2ca60114e9 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"
 
@@ -136,8 +135,6 @@ 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
@@ -159,8 +156,8 @@ 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;
@@ -180,23 +177,14 @@ 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);
 
-	/*
-	 * 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;
+	/* 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);
@@ -796,8 +784,8 @@ 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 02cf960a215a..d519eba518bf 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -208,7 +208,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 	}
 
 	pmu->all_valid_pmc_mask64 = (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->all_valid_pmc_mask64;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 3b3e98b6abb6..002cdd074fd7 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)
@@ -769,7 +770,8 @@ 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_set_pmc_idx(i, host_only_gp_mask, AMD_GP)
 		svm_enable_intercept_for_msr(vcpu, MSR_F15H_PERF_CTR + 2 * i,
 					     MSR_TYPE_RW);
 
@@ -5574,9 +5576,8 @@ 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 31422bd20d96..425f17aa9be2 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -518,7 +518,8 @@ static 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;
 }
 
@@ -575,7 +576,7 @@ 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
@@ -583,7 +584,7 @@ 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->all_valid_pmc_mask64 = (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 0a6880bb7ebe..2a59bbe52bd8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4226,6 +4226,7 @@ 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;
@@ -4248,23 +4249,25 @@ 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_set_pmc_idx(i, gp_mask, INTEL_GP) {
 		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_set_pmc_idx(i, fixed_mask, INTEL_FIXED)
 		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);
 
-- 
2.54.0


  parent reply	other threads:[~2026-07-07 18:44 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-07 18:33 [PATCH 00/15] KVM: x86/pmu: Add mediated vPMU PerfMon v5 support Zide Chen
2026-07-07 18:33 ` [PATCH 01/15] KVM: x86/pmu: Remove redundant Perf Global Status MSR bit definitions Zide Chen
2026-07-07 18:33 ` [PATCH 02/15] KVM: x86/pmu: Rename all_valid_pmc_idx to all_valid_pmc_mask Zide Chen
2026-07-07 18:33 ` [PATCH 03/15] KVM: x86/pmu: Rename reserved_bits to eventsel_rsvd in kvm_pmu Zide Chen
2026-07-07 18:33 ` [PATCH 04/15] KVM: x86/pmu: Add PMC bitmap accessor helpers Zide Chen
2026-07-07 18:33 ` [PATCH 05/15] KVM: x86/pmu: Drop nr_arch_{gp,fixed}_counters from kvm_pmu Zide Chen
2026-07-07 18:33 ` [PATCH 06/15] KVM: x86/pmu: Expose kvm_host_pmu to vendor modules Zide Chen
2026-07-07 18:33 ` [PATCH 07/15] perf/x86: Plumb counter bitmap from x86_pmu to x86_pmu_cap Zide Chen
2026-07-07 18:33 ` Zide Chen [this message]
2026-07-07 18:33 ` [PATCH 09/15] perf/x86: Remove num_counters_{gp,fixed} from x86_pmu_capability Zide Chen
2026-07-07 18:34 ` [PATCH 10/15] KVM: x86/pmu: Emulate the GLOBAL_STATUS_SET and GLOBAL_INUSE MSRs Zide Chen
2026-07-07 18:34 ` [PATCH 11/15] KVM: x86/pmu: Emulate streamlined Freeze-LBR-on-PMI Zide Chen
2026-07-07 18:34 ` [PATCH 12/15] KVM: x86/pmu: Populate CPUID.0AH:ECX fixed-counter bitmap Zide Chen
2026-07-07 18:34 ` [PATCH 13/15] KVM: x86/pmu: Ignore AnyThread bit if CPUID.0AH:EDX[15] is not set Zide Chen
2026-07-07 18:34 ` [PATCH 14/15] KVM: x86/pmu: Advertise PerfMon version 5 on Intel hosts Zide Chen
2026-07-07 18:34 ` [PATCH 15/15] 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=20260707183405.15571-9-zide.chen@intel.com \
    --to=zide.chen@intel.com \
    --cc=Manali.Shukla@amd.com \
    --cc=Sandipan.Das@amd.com \
    --cc=dapeng1.mi@linux.intel.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=thomas.falcon@intel.com \
    --cc=xudong.hao@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