@@ -95,6 +95,7 @@
#define VM_EXIT_CLEAR_BNDCFGS 0x00800000
#define VM_EXIT_PT_CONCEAL_PIP 0x01000000
#define VM_EXIT_CLEAR_IA32_RTIT_CTL 0x02000000
+#define VM_EXIT_CLEAR_IA32_LBR_CTL 0x04000000
#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff
@@ -108,6 +109,7 @@
#define VM_ENTRY_LOAD_BNDCFGS 0x00010000
#define VM_ENTRY_PT_CONCEAL_PIP 0x00020000
#define VM_ENTRY_LOAD_IA32_RTIT_CTL 0x00040000
+#define VM_ENTRY_LOAD_IA32_LBR_CTL 0x00200000
#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff
@@ -378,20 +378,29 @@ static inline bool vmx_pt_mode_is_host_guest(void)
return pt_mode == PT_MODE_HOST_GUEST;
}
-static inline u64 vmx_get_perf_capabilities(void)
+static inline bool cpu_has_vmx_arch_lbr(void)
{
- u64 perf_cap = 0;
-
- if (boot_cpu_has(X86_FEATURE_PDCM))
- rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap);
-
- perf_cap &= PMU_CAP_LBR_FMT;
+ return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_IA32_LBR_CTL) &&
+ (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_LBR_CTL);
+}
+static inline u64 vmx_get_perf_capabilities(void)
+{
/*
* Since counters are virtualized, KVM would support full
* width counting unconditionally, even if the host lacks it.
*/
- return PMU_CAP_FW_WRITES | perf_cap;
+ u64 perf_cap = PMU_CAP_FW_WRITES;
+ u64 host_perf_cap = 0;
+
+ if (boot_cpu_has(X86_FEATURE_PDCM))
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
+
+ perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+ if (boot_cpu_has(X86_FEATURE_ARCH_LBR) && !cpu_has_vmx_arch_lbr())
+ perf_cap &= ~PMU_CAP_LBR_FMT;
+
+ return perf_cap;
}
static inline u64 vmx_supported_debugctl(void)
@@ -181,12 +181,16 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr)
bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu)
{
+ if (kvm_cpu_cap_has(X86_FEATURE_ARCH_LBR))
+ return guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR);
+
/*
* As a first step, a guest could only enable LBR feature if its
* cpu model is the same as the host because the LBR registers
* would be pass-through to the guest and they're model specific.
*/
- return boot_cpu_data.x86_model == guest_cpuid_model(vcpu);
+ return !boot_cpu_has(X86_FEATURE_ARCH_LBR) &&
+ boot_cpu_data.x86_model == guest_cpuid_model(vcpu);
}
bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu)
@@ -204,8 +208,11 @@ static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index)
if (!intel_pmu_lbr_is_enabled(vcpu))
return ret;
- ret = (index == MSR_LBR_SELECT) || (index == MSR_LBR_TOS) ||
- (index >= records->from && index < records->from + records->nr) ||
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR))
+ ret = (index == MSR_LBR_SELECT) || (index == MSR_LBR_TOS);
+
+ if (!ret)
+ ret = (index >= records->from && index < records->from + records->nr) ||
(index >= records->to && index < records->to + records->nr);
if (!ret && records->info)
@@ -696,6 +703,9 @@ static void vmx_update_intercept_for_lbr_msrs(struct kvm_vcpu *vcpu, bool set)
vmx_set_intercept_for_msr(vcpu, lbr->info + i, MSR_TYPE_RW, set);
}
+ if (guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR))
+ return;
+
vmx_set_intercept_for_msr(vcpu, MSR_LBR_SELECT, MSR_TYPE_RW, set);
vmx_set_intercept_for_msr(vcpu, MSR_LBR_TOS, MSR_TYPE_RW, set);
}
@@ -739,10 +749,13 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+ bool lbr_enable = guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR) ?
+ (vmcs_read64(GUEST_IA32_LBR_CTL) & ARCH_LBR_CTL_LBREN) :
+ (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR);
if (!lbr_desc->event) {
vmx_disable_lbr_msrs_passthrough(vcpu);
- if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
+ if (lbr_enable)
goto warn;
if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
goto warn;
@@ -765,7 +778,11 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
{
- if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+ bool lbr_enable = guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR) ?
+ (vmcs_read64(GUEST_IA32_LBR_CTL) & ARCH_LBR_CTL_LBREN) :
+ (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR);
+
+ if (!lbr_enable)
intel_pmu_release_guest_lbr_event(vcpu);
}
@@ -670,6 +670,9 @@ static bool is_valid_passthrough_msr(u32 msr)
case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31:
case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8:
case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8:
+ case MSR_ARCH_LBR_FROM_0 ... MSR_ARCH_LBR_FROM_0 + 31:
+ case MSR_ARCH_LBR_TO_0 ... MSR_ARCH_LBR_TO_0 + 31:
+ case MSR_ARCH_LBR_INFO_0 ... MSR_ARCH_LBR_INFO_0 + 31:
/* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */
return true;
}
@@ -1396,6 +1399,26 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
decache_tsc_multiplier(vmx);
}
+static inline unsigned long get_lbrctlmsr(void)
+{
+ unsigned long lbrctlmsr = 0;
+
+ if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
+ return 0;
+
+ rdmsrl(MSR_ARCH_LBR_CTL, lbrctlmsr);
+
+ return lbrctlmsr;
+}
+
+static inline void update_lbrctlmsr(unsigned long lbrctlmsr)
+{
+ if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
+ return;
+
+ wrmsrl(MSR_ARCH_LBR_CTL, lbrctlmsr);
+}
+
/*
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
@@ -1409,6 +1432,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
vmx_vcpu_pi_load(vcpu, cpu);
vmx->host_debugctlmsr = get_debugctlmsr();
+ vmx->host_lbrctlmsr = get_lbrctlmsr();
}
static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
@@ -2595,7 +2619,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
VM_EXIT_LOAD_IA32_EFER |
VM_EXIT_CLEAR_BNDCFGS |
VM_EXIT_PT_CONCEAL_PIP |
- VM_EXIT_CLEAR_IA32_RTIT_CTL;
+ VM_EXIT_CLEAR_IA32_RTIT_CTL |
+ VM_EXIT_CLEAR_IA32_LBR_CTL;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
&_vmexit_control) < 0)
return -EIO;
@@ -2619,7 +2644,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
VM_ENTRY_LOAD_IA32_EFER |
VM_ENTRY_LOAD_BNDCFGS |
VM_ENTRY_PT_CONCEAL_PIP |
- VM_ENTRY_LOAD_IA32_RTIT_CTL;
+ VM_ENTRY_LOAD_IA32_RTIT_CTL |
+ VM_ENTRY_LOAD_IA32_LBR_CTL;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
&_vmentry_control) < 0)
return -EIO;
@@ -6828,6 +6854,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
if (vmx->host_debugctlmsr)
update_debugctlmsr(vmx->host_debugctlmsr);
+ if (vmx->host_lbrctlmsr)
+ update_lbrctlmsr(vmx->host_lbrctlmsr);
#ifndef CONFIG_X86_64
/*
@@ -328,6 +328,7 @@ struct vcpu_vmx {
u64 current_tsc_ratio;
unsigned long host_debugctlmsr;
+ unsigned long host_lbrctlmsr;
/*
* Only bits masked by msr_ia32_feature_control_valid_bits can be set in
New VMX controls bits for Arch LBR are added. When bit 21 in vmentry_ctrl is set, VM entry will write the value from the "Guest IA32_LBR_CTL" guest state field to IA32_LBR_CTL. When bit 26 in vmexit_ctrl is set, VM exit will clear IA32_LBR_CTL after the value has been saved to the "Guest IA32_LBR_CTL" guest state field. The host value would be saved before vm-entry and restored after vm-exit like the legacy host_debugctlmsr; To enable guest Arch LBR, KVM should set both the "Load Guest IA32_LBR_CTL" entry control and the "Clear IA32_LBR_CTL" exit control bits. If these two conditions cannot be met, KVM will clear the LBR_FMT bits and will not expose the Arch LBR feature. If Arch LBR is exposed on KVM, the guest should set both the ARCH_LBR CPUID and the same LBR_FMT value as the host via MSR_IA32_PERF_CAPABILITIES to enable guest Arch LBR. KVM will bypass the host/guest x86 cpu model check and the records msrs can still be pass-through to guest as usual and work like a model-specific LBR. KVM is consistent with the host and does not support the LER entry. Signed-off-by: Like Xu <like.xu@linux.intel.com> --- arch/x86/include/asm/vmx.h | 2 ++ arch/x86/kvm/vmx/capabilities.h | 25 +++++++++++++++++-------- arch/x86/kvm/vmx/pmu_intel.c | 27 ++++++++++++++++++++++----- arch/x86/kvm/vmx/vmx.c | 32 ++++++++++++++++++++++++++++++-- arch/x86/kvm/vmx/vmx.h | 1 + 5 files changed, 72 insertions(+), 15 deletions(-)