[RFC,v3,25/58] KVM: x86/pmu: Introduce PMU operator to check if rdpmc passthrough allowed

Commit Message

Mingwei Zhang Aug. 1, 2024, 4:58 a.m. UTC

Introduce a vendor specific API to check if rdpmc passthrough allowed.
RDPMC passthrough requires guest VM have the full ownership of all
counters. These include general purpose counters and fixed counters and
some vendor specific MSRs such as PERF_METRICS. Since PERF_METRICS MSR is
Intel specific, putting the check into vendor specific code.

Signed-off-by: Mingwei Zhang <[e-mail]>
Tested-by: Yongwei Ma <[e-mail]>
---
 arch/x86/include/asm/kvm-x86-pmu-ops.h |  1 +
 arch/x86/kvm/pmu.c                     |  1 +
 arch/x86/kvm/pmu.h                     |  1 +
 arch/x86/kvm/svm/pmu.c                 |  6 ++++++
 arch/x86/kvm/vmx/pmu_intel.c           | 16 ++++++++++++++++
 5 files changed, 25 insertions(+)

Patch

diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index f852b13aeefe..fd986d5146e4 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -20,6 +20,7 @@  KVM_X86_PMU_OP(get_msr)
 KVM_X86_PMU_OP(set_msr)
 KVM_X86_PMU_OP(refresh)
 KVM_X86_PMU_OP(init)
+KVM_X86_PMU_OP(is_rdpmc_passthru_allowed)
 KVM_X86_PMU_OP_OPTIONAL(reset)
 KVM_X86_PMU_OP_OPTIONAL(deliver_pmi)
 KVM_X86_PMU_OP_OPTIONAL(cleanup)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 19104e16a986..3afefe4cf6e2 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -102,6 +102,7 @@  bool kvm_pmu_check_rdpmc_passthrough(struct kvm_vcpu *vcpu)
 
 	if (is_passthrough_pmu_enabled(vcpu) &&
 	    !enable_vmware_backdoor &&
+	    static_call(kvm_x86_pmu_is_rdpmc_passthru_allowed)(vcpu) &&
 	    pmu->nr_arch_gp_counters == kvm_pmu_cap.num_counters_gp &&
 	    pmu->nr_arch_fixed_counters == kvm_pmu_cap.num_counters_fixed &&
 	    pmu->counter_bitmask[KVM_PMC_GP] == (((u64)1 << kvm_pmu_cap.bit_width_gp) - 1) &&
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 91941a0f6e47..e1af6d07b191 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -40,6 +40,7 @@  struct kvm_pmu_ops {
 	void (*reset)(struct kvm_vcpu *vcpu);
 	void (*deliver_pmi)(struct kvm_vcpu *vcpu);
 	void (*cleanup)(struct kvm_vcpu *vcpu);
+	bool (*is_rdpmc_passthru_allowed)(struct kvm_vcpu *vcpu);
 
 	const u64 EVENTSEL_EVENT;
 	const int MAX_NR_GP_COUNTERS;
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index dfcc38bd97d3..6b471b1ec9b8 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -228,6 +228,11 @@  static void amd_pmu_init(struct kvm_vcpu *vcpu)
 	}
 }
 
+static bool amd_is_rdpmc_passthru_allowed(struct kvm_vcpu *vcpu)
+{
+	return true;
+}
+
 struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
@@ -237,6 +242,7 @@  struct kvm_pmu_ops amd_pmu_ops __initdata = {
 	.set_msr = amd_pmu_set_msr,
 	.refresh = amd_pmu_refresh,
 	.init = amd_pmu_init,
+	.is_rdpmc_passthru_allowed = amd_is_rdpmc_passthru_allowed,
 	.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
 	.MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC,
 	.MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index e417fd91e5fe..02c9019c6f85 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -725,6 +725,21 @@  void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu)
 	}
 }
 
+static bool intel_is_rdpmc_passthru_allowed(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Per Intel SDM vol. 2 for RDPMC, MSR_PERF_METRICS is accessible by
+	 * with type 0x2000 in ECX[31:16], while the index value in ECX[15:0] is
+	 * implementation specific. Therefore, if the host has this MSR, but
+	 * does not expose it to the guest, RDPMC has to be intercepted.
+	 */
+	if ((host_perf_cap & PMU_CAP_PERF_METRICS) &&
+	    !(vcpu_get_perf_capabilities(vcpu) & PMU_CAP_PERF_METRICS))
+		return false;
+
+	return true;
+}
+
 struct kvm_pmu_ops intel_pmu_ops __initdata = {
 	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = intel_msr_idx_to_pmc,
@@ -736,6 +751,7 @@  struct kvm_pmu_ops intel_pmu_ops __initdata = {
 	.reset = intel_pmu_reset,
 	.deliver_pmi = intel_pmu_deliver_pmi,
 	.cleanup = intel_pmu_cleanup,
+	.is_rdpmc_passthru_allowed = intel_is_rdpmc_passthru_allowed,
 	.EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT,
 	.MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC,
 	.MIN_NR_GP_COUNTERS = 1,