From: Like Xu <like.xu@xxxxxxxxxxxxxxx>
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 atomically switched during
the VMX transitions just like CORE_PERF_GLOBAL_CTRL MSR.
Based on whether the platform supports x86_pmu.pebs_vmx, it has also
refactored the way to add more msrs to arr[] in intel_guest_get_msrs()
for extensibility.
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>
Signed-off-by: Zhu Lingshan <lingshan.zhu@xxxxxxxxx>
---
arch/x86/events/intel/core.c | 73 ++++++++++++++++++++++++--------
arch/x86/include/asm/kvm_host.h | 3 ++
arch/x86/include/asm/msr-index.h | 6 +++
arch/x86/kvm/vmx/pmu_intel.c | 31 ++++++++++++++
4 files changed, 95 insertions(+), 18 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9d5c415dfacd..190d8d98abf0 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3894,33 +3894,70 @@ static int intel_pmu_hw_config(struct perf_event *event)
return 0;
}
+/*
+ * Currently, the only caller of this function is the atomic_switch_perf_msrs().
+ * The host perf conext helps to prepare the values of the real hardware for
+ * a set of msrs that need to be switched atomically in a vmx transaction.
+ *
+ * For example, the pseudocode needed to add a new msr should look like:
+ *
+ * arr[(*nr)++] = (struct perf_guest_switch_msr){
+ * .msr = the hardware msr address,
+ * .host = the value the hardware has when it doesn't run a guest,
+ * .guest = the value the hardware has when it runs a guest,
+ * };
+ *
+ * These values have nothing to do with the emulated values the guest sees
+ * when it uses {RD,WR}MSR, which should be handled by the KVM context,
+ * specifically in the intel_pmu_{get,set}_msr().
+ */
static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
+ u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable;
- arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
- arr[0].host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
- arr[0].guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask;
- arr[0].guest &= ~(cpuc->pebs_enabled & x86_pmu.pebs_capable);
- *nr = 1;
+ *nr = 0;
+ arr[(*nr)++] = (struct perf_guest_switch_msr){
+ .msr = MSR_CORE_PERF_GLOBAL_CTRL,
+ .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask,
+ .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask),
+ };
- if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
- /*
- * If PMU counter has PEBS enabled it is not enough to
- * disable counter on a guest entry since PEBS memory
- * write can overshoot guest entry and corrupt guest
- * memory. Disabling PEBS solves the problem.
- *
- * 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;
- *nr = 2;
+ if (!x86_pmu.pebs)
+ return arr;
+
+ /*
+ * If PMU counter has PEBS enabled it is not enough to
+ * disable counter on a guest entry since PEBS memory
+ * write can overshoot guest entry and corrupt guest
+ * memory. Disabling PEBS solves the problem.
+ *
+ * Don't do this if the CPU already enforces it.
+ */
+ if (x86_pmu.pebs_no_isolation) {
+ arr[(*nr)++] = (struct perf_guest_switch_msr){
+ .msr = MSR_IA32_PEBS_ENABLE,
+ .host = cpuc->pebs_enabled,
+ .guest = 0,
+ };
+ return arr;
}
+ if (!x86_pmu.pebs_vmx)
+ return arr;
+
+ arr[*nr] = (struct perf_guest_switch_msr){
+ .msr = MSR_IA32_PEBS_ENABLE,
+ .host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask,
+ .guest = pebs_mask & ~cpuc->intel_ctrl_host_mask,
+ };
+
+ /* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */
+ arr[0].guest |= arr[*nr].guest;
+
+ ++(*nr);
return arr;
}
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e63d28fc7cd4..662a0c036ca2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -473,6 +473,9 @@ struct kvm_pmu {
DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
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
* pmc_in_use only once in a vcpu time slice.
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 211ba3375ee9..57ae86ca0d86 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -189,6 +189,12 @@
#define PERF_CAP_PT_IDX 16
#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..9938b485c31c 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 +560,22 @@ 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)
--
2.27.0
