KVM_CAP_PMU_DISABLE is used to disable PMU virtualization on individual
x86 VMs. PMU configuration must be done prior to creating VCPUs.
To enable future extension, KVM_CAP_PMU_CAPABILITY reports available
settings via bitmask when queried via check_extension.
For VMs that have PMU virtualization disabled, usermode will need to
clear CPUID leaf 0xA to notify guests.
Signed-off-by: David Dunn <daviddunn@xxxxxxxxxx>
---
Documentation/virt/kvm/api.rst | 22 ++++++++++++++++++++++
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/svm/pmu.c | 2 +-
arch/x86/kvm/vmx/pmu_intel.c | 2 +-
arch/x86/kvm/x86.c | 12 ++++++++++++
include/uapi/linux/kvm.h | 4 ++++
tools/include/uapi/linux/kvm.h | 4 ++++
7 files changed, 45 insertions(+), 2 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index bb8cfddbb22d..ae0d52c5359e 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7559,3 +7559,25 @@ The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace
the hypercalls whose corresponding bit is in the argument, and return
ENOSYS for the others.
+
+8.35 KVM_CAP_PMU_CAPABILITY
+---------------------------
+
+:Capability KVM_CAP_PMU_CAPABILITY
+:Architectures: x86
+:Type: vm
+:Parameters: arg[0] is bitmask of PMU virtualization capabilities.
+:Returns 0 on success, -EINVAL when arg[0] contains invalid bits
+
+This capability alters PMU virtualization in KVM.
+
+Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
+PMU virtualization capabilities that can be adjusted on a VM.
+
+The argument to KVM_ENABLE_CAP is also a bitmask and selects specific
+PMU virtualization capabilities to be applied to the VM. This can
+only be invoked on a VM prior to the creation of VCPUs.
+
+At this time, KVM_CAP_PMU_DISABLE is the only capability. Setting
+this capability will disable PMU virtualization for that VM. Usermode
+should adjust CPUID leaf 0xA to reflect that the PMU is disabled.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 682ad02a4e58..5cdcd4a7671b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1232,6 +1232,7 @@ struct kvm_arch {
hpa_t hv_root_tdp;
spinlock_t hv_root_tdp_lock;
#endif
+ bool enable_pmu;
};
struct kvm_vm_stat {
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 5aa45f13b16d..d4de52409335 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -101,7 +101,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
{
struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
- if (!enable_pmu)
+ if (!vcpu->kvm->arch.enable_pmu)
return NULL;
switch (msr) {
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 466d18fc0c5d..2c5868d77268 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -487,7 +487,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->reserved_bits = 0xffffffff00200000ull;
entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
- if (!entry || !enable_pmu)
+ if (!entry || !vcpu->kvm->arch.enable_pmu)
return;
eax.full = entry->eax;
edx.full = entry->edx;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 55518b7d3b96..a033f019a3f0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4326,6 +4326,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
if (r < sizeof(struct kvm_xsave))
r = sizeof(struct kvm_xsave);
break;
+ case KVM_CAP_PMU_CAPABILITY:
+ r = enable_pmu ? KVM_CAP_PMU_MASK : 0;
+ break;
}
default:
break;
@@ -5937,6 +5940,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
kvm->arch.exit_on_emulation_error = cap->args[0];
r = 0;
break;
+ case KVM_CAP_PMU_CAPABILITY:
+ r = -EINVAL;
+ if (!enable_pmu || kvm->created_vcpus > 0 ||
+ cap->args[0] & ~KVM_CAP_PMU_MASK)
+ break;
+ kvm->arch.enable_pmu = !(cap->args[0] & KVM_CAP_PMU_DISABLE);
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
@@ -11562,6 +11573,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
kvm->arch.guest_can_read_msr_platform_info = true;
+ kvm->arch.enable_pmu = enable_pmu;
#if IS_ENABLED(CONFIG_HYPERV)
spin_lock_init(&kvm->arch.hv_root_tdp_lock);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 9563d294f181..1c5e6e172817 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1133,6 +1133,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
#define KVM_CAP_VM_GPA_BITS 207
#define KVM_CAP_XSAVE2 208
+#define KVM_CAP_PMU_CAPABILITY 209
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1972,6 +1973,9 @@ struct kvm_dirty_gfn {
#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
+#define KVM_CAP_PMU_DISABLE (1 << 0)
+#define KVM_CAP_PMU_MASK (KVM_CAP_PMU_DISABLE)
+
/**
* struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
* @flags: Some extra information for header, always 0 for now.
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 9563d294f181..a361cf6e8604 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1133,6 +1133,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
#define KVM_CAP_VM_GPA_BITS 207
#define KVM_CAP_XSAVE2 208
+#define KVM_CAP_PMU_CAPABILITY 209
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1972,6 +1973,9 @@ struct kvm_dirty_gfn {
#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
+#define KVM_CAP_PMU_DISABLE (1 << 0)
+#define KVM_CAP_PMU_MASK (KVM_PMU_CONFIG_DISABLE)
+
/**
* struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
* @flags: Some extra information for header, always 0 for now.
--
2.35.0.rc0.227.g00780c9af4-goog
