The lbr stack is model specific, for example, SKX has 32 lbr stack
entries while HSW has 16 entries, so a HSW guest running on a SKX
machine may not get accurate perf results. Currently, we forbid the
guest lbr enabling when the guest and host see different lbr stack
entries or the host and guest see different lbr stack msr indices.
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxx>
Signed-off-by: Wei Wang <wei.w.wang@xxxxxxxxx>
---
arch/x86/kvm/pmu.c | 8 +++
arch/x86/kvm/pmu.h | 2 +
arch/x86/kvm/vmx/pmu_intel.c | 136 +++++++++++++++++++++++++++++++++++++++++++
arch/x86/kvm/x86.c | 3 +-
4 files changed, 147 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 46875bb..26fac6c 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -331,6 +331,14 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
return 0;
}
+bool kvm_pmu_lbr_enable(struct kvm_vcpu *vcpu)
+{
+ if (kvm_x86_ops->pmu_ops->lbr_enable)
+ return kvm_x86_ops->pmu_ops->lbr_enable(vcpu);
+
+ return false;
+}
+
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
{
if (lapic_in_kernel(vcpu))
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 58265f7..d9eec9a 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -29,6 +29,7 @@ struct kvm_pmu_ops {
u64 *mask);
int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
+ bool (*lbr_enable)(struct kvm_vcpu *vcpu);
int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
void (*refresh)(struct kvm_vcpu *vcpu);
@@ -107,6 +108,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel);
void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx);
void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
+bool kvm_pmu_lbr_enable(struct kvm_vcpu *vcpu);
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 4dea0e0..6294a86 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -12,6 +12,7 @@
#include <linux/kvm_host.h>
#include <linux/perf_event.h>
#include <asm/perf_event.h>
+#include <asm/intel-family.h>
#include "x86.h"
#include "cpuid.h"
#include "lapic.h"
@@ -162,6 +163,140 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
return ret;
}
+static bool intel_pmu_lbr_enable(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ u8 vcpu_model = guest_cpuid_model(vcpu);
+ unsigned int vcpu_lbr_from, vcpu_lbr_nr;
+
+ if (x86_perf_get_lbr_stack(&kvm->arch.lbr_stack))
+ return false;
+
+ if (guest_cpuid_family(vcpu) != boot_cpu_data.x86)
+ return false;
+
+ /*
+ * It could be possible that people have vcpus of old model run on
+ * physcal cpus of newer model, for example a BDW guest on a SKX
+ * machine (but not possible to be the other way around).
+ * The BDW guest may not get accurate results on a SKX machine as it
+ * only reads 16 entries of the lbr stack while there are 32 entries
+ * of recordings. We currently forbid the lbr enabling when the vcpu
+ * and physical cpu see different lbr stack entries or the guest lbr
+ * msr indices are not compatible with the host.
+ */
+ switch (vcpu_model) {
+ case INTEL_FAM6_CORE2_MEROM:
+ case INTEL_FAM6_CORE2_MEROM_L:
+ case INTEL_FAM6_CORE2_PENRYN:
+ case INTEL_FAM6_CORE2_DUNNINGTON:
+ /* intel_pmu_lbr_init_core() */
+ vcpu_lbr_nr = 4;
+ vcpu_lbr_from = MSR_LBR_CORE_FROM;
+ break;
+ case INTEL_FAM6_NEHALEM:
+ case INTEL_FAM6_NEHALEM_EP:
+ case INTEL_FAM6_NEHALEM_EX:
+ /* intel_pmu_lbr_init_nhm() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_ATOM_BONNELL:
+ case INTEL_FAM6_ATOM_BONNELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL:
+ case INTEL_FAM6_ATOM_SALTWELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+ /* intel_pmu_lbr_init_atom() */
+ vcpu_lbr_nr = 8;
+ vcpu_lbr_from = MSR_LBR_CORE_FROM;
+ break;
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_X:
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
+ case INTEL_FAM6_ATOM_AIRMONT:
+ case INTEL_FAM6_ATOM_AIRMONT_MID:
+ /* intel_pmu_lbr_init_slm() */
+ vcpu_lbr_nr = 8;
+ vcpu_lbr_from = MSR_LBR_CORE_FROM;
+ break;
+ case INTEL_FAM6_ATOM_GOLDMONT:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
+ /* intel_pmu_lbr_init_skl(); */
+ vcpu_lbr_nr = 32;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ /* intel_pmu_lbr_init_skl()*/
+ vcpu_lbr_nr = 32;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_WESTMERE:
+ case INTEL_FAM6_WESTMERE_EP:
+ case INTEL_FAM6_WESTMERE_EX:
+ /* intel_pmu_lbr_init_nhm() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_SANDYBRIDGE:
+ case INTEL_FAM6_SANDYBRIDGE_X:
+ /* intel_pmu_lbr_init_snb() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_IVYBRIDGE:
+ case INTEL_FAM6_IVYBRIDGE_X:
+ /* intel_pmu_lbr_init_snb() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_HASWELL_CORE:
+ case INTEL_FAM6_HASWELL_X:
+ case INTEL_FAM6_HASWELL_ULT:
+ case INTEL_FAM6_HASWELL_GT3E:
+ /* intel_pmu_lbr_init_hsw() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_BROADWELL_CORE:
+ case INTEL_FAM6_BROADWELL_XEON_D:
+ case INTEL_FAM6_BROADWELL_GT3E:
+ case INTEL_FAM6_BROADWELL_X:
+ /* intel_pmu_lbr_init_hsw() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_XEON_PHI_KNL:
+ case INTEL_FAM6_XEON_PHI_KNM:
+ /* intel_pmu_lbr_init_knl() */
+ vcpu_lbr_nr = 8;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_SKYLAKE_MOBILE:
+ case INTEL_FAM6_SKYLAKE_DESKTOP:
+ case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_FAM6_KABYLAKE_MOBILE:
+ case INTEL_FAM6_KABYLAKE_DESKTOP:
+ /* intel_pmu_lbr_init_skl() */
+ vcpu_lbr_nr = 32;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ default:
+ vcpu_lbr_nr = 0;
+ vcpu_lbr_from = 0;
+ pr_warn("%s: vcpu model not supported %d\n", __func__,
+ vcpu_model);
+ }
+
+ if (vcpu_lbr_nr != kvm->arch.lbr_stack.nr ||
+ vcpu_lbr_from != kvm->arch.lbr_stack.from) {
+ pr_warn("%s: vcpu model %x incompatible to pcpu %x\n",
+ __func__, vcpu_model, boot_cpu_data.x86_model);
+ return false;
+ }
+
+ return true;
+}
+
static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -366,6 +501,7 @@ struct kvm_pmu_ops intel_pmu_ops = {
.msr_idx_to_pmc = intel_msr_idx_to_pmc,
.is_valid_msr_idx = intel_is_valid_msr_idx,
.is_valid_msr = intel_is_valid_msr,
+ .lbr_enable = intel_pmu_lbr_enable,
.get_msr = intel_pmu_get_msr,
.set_msr = intel_pmu_set_msr,
.refresh = intel_pmu_refresh,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e1eb1be..da45962 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4675,8 +4675,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
break;
case KVM_CAP_X86_GUEST_LBR:
r = -EINVAL;
- if (cap->args[0] &&
- x86_perf_get_lbr_stack(&kvm->arch.lbr_stack))
+ if (cap->args[0] && !kvm_pmu_lbr_enable(kvm->vcpus[0]))
break;
if (copy_to_user((void __user *)cap->args[1],
--
2.7.4
