perf, kvm: Support the in_tx/in_tx_cp modifiers in KVM arch perfmon emulation v5

[KVM maintainers:
The underlying support for this is in perf/core now. So please merge
this patch into the KVM tree.]

This is not arch perfmon, but older CPUs will just ignore it. This makes
it possible to do at least some TSX measurements from a KVM guest

v2: Various fixes to address review feedback
v3: Ignore the bits when no CPUID. No #GP. Force raw events with TSX bits.
v4: Use reserved bits for #GP
v5: Remove obsolete argument
Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f87f7fcefa0acdc4856aa576078a34c2d4002e1e..531f47cbf1f826950ec8afa62fb98320ac63aabf 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -323,6 +323,7 @@ struct kvm_pmu {
        u64 global_ovf_ctrl;
        u64 counter_bitmask[2];
        u64 global_ctrl_mask;
+       u64 reserved_bits;
        u8 version;
        struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
        struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index c53e797e7369ad4a1086899ee65eb1e71d048d84..5c4f63151b4d90a405808bda13daa911c5b2a131 100644 (file)
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
 
 static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
                unsigned config, bool exclude_user, bool exclude_kernel,
-               bool intr)
+               bool intr, bool in_tx, bool in_tx_cp)
 {
        struct perf_event *event;
        struct perf_event_attr attr = {
@@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
                .exclude_kernel = exclude_kernel,
                .config = config,
        };
+       if (in_tx)
+               attr.config |= HSW_IN_TX;
+       if (in_tx_cp)
+               attr.config |= HSW_IN_TX_CHECKPOINTED;
 
        attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
 
@@ -226,7 +230,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
        if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
                                ARCH_PERFMON_EVENTSEL_INV |
-                               ARCH_PERFMON_EVENTSEL_CMASK))) {
+                               ARCH_PERFMON_EVENTSEL_CMASK |
+                               HSW_IN_TX |
+                               HSW_IN_TX_CHECKPOINTED))) {
                config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
                                unit_mask);
                if (config != PERF_COUNT_HW_MAX)
@@ -239,7 +245,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
        reprogram_counter(pmc, type, config,
                        !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
                        !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-                       eventsel & ARCH_PERFMON_EVENTSEL_INT);
+                       eventsel & ARCH_PERFMON_EVENTSEL_INT,
+                       (eventsel & HSW_IN_TX),
+                       (eventsel & HSW_IN_TX_CHECKPOINTED));
 }
 
 static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
@@ -256,7 +264,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
                        arch_events[fixed_pmc_events[idx]].event_type,
                        !(en & 0x2), /* exclude user */
                        !(en & 0x1), /* exclude kernel */
-                       pmi);
+                       pmi, false, false);
 }
 
 static inline u8 fixed_en_pmi(u64 ctrl, int idx)
@@ -408,7 +416,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
                        if (data == pmc->eventsel)
                                return 0;
-                       if (!(data & 0xffffffff00200000ull)) {
+                       if (!(data & pmu->reserved_bits)) {
                                reprogram_gp_counter(pmc, data);
                                return 0;
                        }
@@ -450,6 +458,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
        pmu->counter_bitmask[KVM_PMC_GP] = 0;
        pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
        pmu->version = 0;
+       pmu->reserved_bits = 0xffffffff00200000ull;
 
        entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
        if (!entry)
@@ -478,6 +487,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
        pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
                (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
        pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+       entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+       if (entry &&
+           (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+           (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+               pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)