[PATCH v4 07/16] KVM: x86/pmu: Add IA32_PEBS_ENABLE MSR emulation for extended PEBS
From: Like Xu
Date: Mon Mar 29 2021 - 01:51:04 EST
If IA32_PERF_CAPABILITIES.PEBS_BASELINE [bit 14] is set, the
IA32_PEBS_ENABLE MSR exists and all architecturally enumerated fixed
and general purpose counters have corresponding bits in IA32_PEBS_ENABLE
that enable generation of PEBS records. The general-purpose counter bits
start at bit IA32_PEBS_ENABLE[0], and the fixed counter bits start at
bit IA32_PEBS_ENABLE[32].
When guest PEBS is enabled, the IA32_PEBS_ENABLE MSR will be
added to the perf_guest_switch_msr() and switched during the
VMX transitions just like CORE_PERF_GLOBAL_CTRL MSR.
Originally-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Co-developed-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Co-developed-by: Luwei Kang <luwei.kang@xxxxxxxxx>
Signed-off-by: Luwei Kang <luwei.kang@xxxxxxxxx>
Signed-off-by: Like Xu <like.xu@xxxxxxxxxxxxxxx>
---
arch/x86/events/intel/core.c | 17 +++++++++++++----
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/include/asm/msr-index.h | 6 ++++++
arch/x86/kvm/vmx/pmu_intel.c | 28 ++++++++++++++++++++++++++++
4 files changed, 48 insertions(+), 4 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index e8fee7cf767f..2ca8ed61f444 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3851,7 +3851,11 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
arr[0].guest &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
*nr = 1;
- if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
+ if (x86_pmu.pebs) {
+ arr[1].msr = MSR_IA32_PEBS_ENABLE;
+ arr[1].host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask;
+ arr[1].guest = cpuc->pebs_enabled & ~cpuc->intel_ctrl_host_mask;
+
/*
* If PMU counter has PEBS enabled it is not enough to
* disable counter on a guest entry since PEBS memory
@@ -3860,9 +3864,14 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
*
* Don't do this if the CPU already enforces it.
*/
- arr[1].msr = MSR_IA32_PEBS_ENABLE;
- arr[1].host = cpuc->pebs_enabled;
- arr[1].guest = 0;
+ if (x86_pmu.pebs_no_isolation)
+ arr[1].guest = 0;
+
+ if (arr[1].guest)
+ arr[0].guest |= arr[1].guest;
+ else
+ arr[1].guest = arr[1].host;
+
*nr = 2;
}
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9b814bdc9137..f620485d7836 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -461,6 +461,7 @@ struct kvm_pmu {
DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
u64 pebs_enable;
+ u64 pebs_enable_mask;
/*
* The gate to release perf_events not marked in
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 546d6ecf0a35..9afcad882f4f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -186,6 +186,12 @@
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
+#define PERF_CAP_PEBS_TRAP BIT_ULL(6)
+#define PERF_CAP_ARCH_REG BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT 0xf00
+#define PERF_CAP_PEBS_BASELINE BIT_ULL(14)
+#define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+ PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
#define MSR_IA32_RTIT_CTL 0x00000570
#define RTIT_CTL_TRACEEN BIT(0)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index ac7fe714e6c1..0700d6d739f7 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -220,6 +220,9 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
ret = pmu->version > 1;
break;
+ case MSR_IA32_PEBS_ENABLE:
+ ret = vcpu->arch.perf_capabilities & PERF_CAP_PEBS_FORMAT;
+ break;
default:
ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) ||
@@ -367,6 +370,9 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
msr_info->data = pmu->global_ovf_ctrl;
return 0;
+ case MSR_IA32_PEBS_ENABLE:
+ msr_info->data = pmu->pebs_enable;
+ return 0;
default:
if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
(pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -427,6 +433,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 0;
}
break;
+ case MSR_IA32_PEBS_ENABLE:
+ if (pmu->pebs_enable == data)
+ return 0;
+ if (!(data & pmu->pebs_enable_mask)) {
+ pmu->pebs_enable = data;
+ return 0;
+ }
+ break;
default:
if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
(pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -479,6 +493,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->version = 0;
pmu->reserved_bits = 0xffffffff00200000ull;
pmu->fixed_ctr_ctrl_mask = ~0ull;
+ pmu->pebs_enable_mask = ~0ull;
entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
if (!entry)
@@ -545,6 +560,19 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
if (lbr_desc->records.nr)
bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_IDX_FIXED_VLBR, 1);
+
+ if (vcpu->arch.perf_capabilities & PERF_CAP_PEBS_FORMAT) {
+ if (vcpu->arch.perf_capabilities & PERF_CAP_PEBS_BASELINE) {
+ pmu->pebs_enable_mask = ~pmu->global_ctrl;
+ pmu->reserved_bits &= ~ICL_EVENTSEL_ADAPTIVE;
+ for (i = 0; i < pmu->nr_arch_fixed_counters; i++)
+ pmu->fixed_ctr_ctrl_mask &=
+ ~(1ULL << (INTEL_PMC_IDX_FIXED + i * 4));
+ } else
+ pmu->pebs_enable_mask = ~((1ull << pmu->nr_arch_gp_counters) - 1);
+ } else {
+ vcpu->arch.perf_capabilities &= ~PERF_CAP_PEBS_MASK;
+ }
}
static void intel_pmu_init(struct kvm_vcpu *vcpu)
--
2.29.2