Add a new capability, KVM_CAP_PMU_CAPABILITY, that takes a bitmask of
settings/features to allow userspace to configure PMU virtualization on
a per-VM basis. For now, support a single flag, KVM_CAP_PMU_DISABLE,
to allow disabling PMU virtualization for a VM even when KVM is configured
with enable_pmu=true a module level.
To keep KVM simple, disallow changing VM's PMU configuration after vCPUs
have been created.
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 | 17 +++++++++++++++++
include/uapi/linux/kvm.h | 3 +++
tools/include/uapi/linux/kvm.h | 3 +++
7 files changed, 48 insertions(+), 2 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index a4267104db50..df836965b347 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7561,3 +7561,25 @@ 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 10815b672a26..61e9050a3488 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1233,6 +1233,7 @@ 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 03fab48b149c..4e5b1eeeb77c 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 eaa3b5b89c5e..0803a1388bbf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -110,6 +110,8 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE)
+#define KVM_CAP_PMU_VALID_MASK KVM_CAP_PMU_DISABLE
+
#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
@@ -4331,6 +4333,9 @@ 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_VALID_MASK : 0;
+ break;
}
default:
break;
@@ -6005,6 +6010,17 @@ 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 || (cap->args[0] & ~KVM_CAP_PMU_VALID_MASK))
+ break;
+ mutex_lock(&kvm->lock);
+ if (!kvm->created_vcpus) {
+ kvm->arch.enable_pmu = !(cap->args[0] & KVM_CAP_PMU_DISABLE);
+ r = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ break;
default:
r = -EINVAL;
break;
@@ -11591,6 +11607,7 @@ 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 5191b57e1562..3d6046295755 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_GPA_BITS 207
#define KVM_CAP_XSAVE2 208
#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PMU_CAPABILITY 210
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1970,6 +1971,8 @@ 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)
+
/**
* 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 5191b57e1562..3d6046295755 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_GPA_BITS 207
#define KVM_CAP_XSAVE2 208
#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PMU_CAPABILITY 210
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1970,6 +1971,8 @@ 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)
+
/**
* struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
* @flags: Some extra information for header, always 0 for now.
--
2.35.1.265.g69c8d7142f-goog
