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>
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 v6 6/8] KVM: x86/pmu: Move RDPMC emulation into per-vendor callbacks
Date: Mon, 29 Jun 2026 16:19:35 -0700	[thread overview]
Message-ID: <20260629231938.15129-7-zide.chen@intel.com> (raw)
In-Reply-To: <20260629231938.15129-1-zide.chen@intel.com>

The current RDPMC emulation splits responsibility: rdpmc_ecx_to_pmc()
in each vendor returns a kvm_pmc, then common code calls
pmc_read_counter().

This design cannot support RDPMC reads that don't map to a counter,
such as PERF_METRICS on Intel platforms.

Replace rdpmc_ecx_to_pmc() with emulate_rdpmc(), which takes full
ownership of the emulation and writes the result directly into @data.

Also drop the redundant bitmask in intel_emulate_rdpmc() since
pmc_read_counter() already applies the counter's bit-width mask.

No functional change intended.

Signed-off-by: Zide Chen <zide.chen@intel.com>
---
v6: new patch.
---
 arch/x86/include/asm/kvm-x86-pmu-ops.h |  2 +-
 arch/x86/kvm/pmu.c                     |  9 +--------
 arch/x86/kvm/pmu.h                     |  4 ++--
 arch/x86/kvm/svm/pmu.c                 | 13 +++++++++----
 arch/x86/kvm/vmx/pmu_intel.c           | 25 ++++++++++++-------------
 5 files changed, 25 insertions(+), 28 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index 4a223c2793e3..4b50ed058aed 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -13,7 +13,7 @@
  * KVM_X86_PMU_OP_OPTIONAL() can be used for those functions that can have
  * a NULL definition.
  */
-KVM_X86_PMU_OP(rdpmc_ecx_to_pmc)
+KVM_X86_PMU_OP(emulate_rdpmc)
 KVM_X86_PMU_OP(msr_idx_to_pmc)
 KVM_X86_PMU_OP_OPTIONAL(check_rdpmc_early)
 KVM_X86_PMU_OP(is_valid_msr)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index f82ba63767d0..8ef2d4761790 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -768,8 +768,6 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	struct kvm_pmc *pmc;
-	u64 mask = ~0ull;
 
 	if (!pmu->version)
 		return 1;
@@ -777,17 +775,12 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
-	pmc = kvm_pmu_call(rdpmc_ecx_to_pmc)(vcpu, idx, &mask);
-	if (!pmc)
-		return 1;
-
 	if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCE) &&
 	    (kvm_x86_call(get_cpl)(vcpu) != 0) &&
 	    kvm_is_cr0_bit_set(vcpu, X86_CR0_PE))
 		return 1;
 
-	*data = pmc_read_counter(pmc) & mask;
-	return 0;
+	return kvm_pmu_call(emulate_rdpmc)(vcpu, idx, data);
 }
 
 static bool kvm_need_any_pmc_intercept(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 3066cade5790..cdbefda844b9 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -24,8 +24,8 @@
 #define KVM_FIXED_PMC_BASE_IDX INTEL_PMC_IDX_FIXED
 
 struct kvm_pmu_ops {
-	struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,
-		unsigned int idx, u64 *mask);
+	int (*emulate_rdpmc)(struct kvm_vcpu *vcpu, unsigned int idx,
+			     u64 *data);
 	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*check_rdpmc_early)(struct kvm_vcpu *vcpu, unsigned int idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index c18286545a7a..0517fd4bbcd7 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -84,10 +84,15 @@ static int amd_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx)
 }
 
 /* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
-	unsigned int idx, u64 *mask)
+static int amd_emulate_rdpmc(struct kvm_vcpu *vcpu, unsigned int idx, u64 *data)
 {
-	return amd_pmu_get_pmc(vcpu_to_pmu(vcpu), idx);
+	struct kvm_pmc *pmc = amd_pmu_get_pmc(vcpu_to_pmu(vcpu), idx);
+
+	if (!pmc)
+		return 1;
+
+	*data = pmc_read_counter(pmc);
+	return 0;
 }
 
 static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
@@ -302,7 +307,7 @@ static bool amd_pmc_is_disabled_in_current_mode(struct kvm_pmc *pmc)
 }
 
 struct kvm_pmu_ops amd_pmu_ops __initdata = {
-	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
+	.emulate_rdpmc = amd_emulate_rdpmc,
 	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
 	.check_rdpmc_early = amd_check_rdpmc_early,
 	.is_valid_msr = amd_is_valid_msr,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 225afd3937c3..080677372c9b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -84,14 +84,13 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 	}
 }
 
-static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
-					    unsigned int idx, u64 *mask)
+static int intel_emulate_rdpmc(struct kvm_vcpu *vcpu, unsigned int idx,
+			       u64 *data)
 {
 	unsigned int type = idx & INTEL_RDPMC_TYPE_MASK;
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	struct kvm_pmc *counters;
+	struct kvm_pmc *counters, *pmc;
 	unsigned int num_counters;
-	u64 bitmask;
 
 	/*
 	 * The encoding of ECX for RDPMC is different for architectural versus
@@ -104,7 +103,9 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 	 * as KVM doesn't support such PMUs.
 	 */
 	if (WARN_ON_ONCE(!pmu->version))
-		return NULL;
+		return 1;
+
+	idx &= INTEL_RDPMC_INDEX_MASK;
 
 	/*
 	 * General Purpose (GP) PMCs are supported on all PMUs, and fixed PMCs
@@ -118,23 +119,21 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 	case INTEL_RDPMC_FIXED:
 		counters = pmu->fixed_counters;
 		num_counters = pmu->nr_arch_fixed_counters;
-		bitmask = pmu->counter_bitmask[KVM_PMC_FIXED];
 		break;
 	case INTEL_RDPMC_GP:
 		counters = pmu->gp_counters;
 		num_counters = pmu->nr_arch_gp_counters;
-		bitmask = pmu->counter_bitmask[KVM_PMC_GP];
 		break;
 	default:
-		return NULL;
+		return 1;
 	}
 
-	idx &= INTEL_RDPMC_INDEX_MASK;
 	if (idx >= num_counters)
-		return NULL;
+		return 1;
 
-	*mask &= bitmask;
-	return &counters[array_index_nospec(idx, num_counters)];
+	pmc = &counters[array_index_nospec(idx, num_counters)];
+	*data = pmc_read_counter(pmc);
+	return 0;
 }
 
 static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr)
@@ -865,7 +864,7 @@ static void intel_mediated_pmu_put(struct kvm_vcpu *vcpu)
 }
 
 struct kvm_pmu_ops intel_pmu_ops __initdata = {
-	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
+	.emulate_rdpmc = intel_emulate_rdpmc,
 	.msr_idx_to_pmc = intel_msr_idx_to_pmc,
 	.is_valid_msr = intel_is_valid_msr,
 	.get_msr = intel_pmu_get_msr,
-- 
2.54.0


  parent reply	other threads:[~2026-06-29 23:28 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-29 23:19 [PATCH V6 0/8] KVM: x86/pmu: Add hardware Topdown metrics support Zide Chen
2026-06-29 23:19 ` [PATCH v6 1/8] KVM: x86/pmu: Do not map fixed counters >= 3 to generic perf events Zide Chen
2026-06-30  2:13   ` Mi, Dapeng
2026-06-29 23:19 ` [PATCH v6 2/8] KVM: x86/pmu: Support Intel fixed counter 3 on mediated vPMU Zide Chen
2026-06-30  2:16   ` Mi, Dapeng
2026-06-29 23:19 ` [PATCH v6 3/8] KVM: x86/pmu: Rename and move vcpu_get_perf_capabilities() to pmu.h Zide Chen
2026-06-30  2:18   ` Mi, Dapeng
2026-06-29 23:19 ` [PATCH v6 4/8] KVM: x86/pmu: Snapshot host IA32_PERF_CAPABILITIES in kvm_host Zide Chen
2026-06-30  2:19   ` Mi, Dapeng
2026-06-29 23:19 ` [PATCH v6 5/8] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU Zide Chen
2026-06-30  2:20   ` Mi, Dapeng
2026-06-29 23:19 ` Zide Chen [this message]
2026-06-30  2:23   ` [PATCH v6 6/8] KVM: x86/pmu: Move RDPMC emulation into per-vendor callbacks Mi, Dapeng
2026-06-29 23:19 ` [PATCH v6 7/8] KVM: x86/pmu: Emulate RDPMC on performance metrics Zide Chen
2026-06-30  2:23   ` Mi, Dapeng
2026-06-29 23:19 ` [PATCH v6 8/8] KVM: selftests: Add PERF_METRICS and fixed counter 3 tests Zide Chen
2026-06-29 23:45   ` sashiko-bot
2026-06-30  2:36   ` Mi, Dapeng

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=20260629231938.15129-7-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=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