KVM: x86/pmu: Fix and isolate TSX-specific performance event logic

HSW_IN_TX* bits are used in generic code which are not supported on
AMD. Worse, these bits overlap with AMD EventSelect[11:8] and hence
using HSW_IN_TX* bits unconditionally in generic code is resulting in
unintentional pmu behavior on AMD. For example, if EventSelect[11:8]
is 0x2, pmc_reprogram_counter() wrongly assumes that
HSW_IN_TX_CHECKPOINTED is set and thus forces sampling period to be 0.

Also per the SDM, both bits 32 and 33 "may only be set if the processor
supports HLE or RTM" and for "IN_TXCP (bit 33): this bit may only be set
for IA32_PERFEVTSEL2."

Opportunistically eliminate code redundancy, because if the HSW_IN_TX*
bit is set in pmc->eventsel, it is already set in attr.config.

Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Reported-by: Jim Mattson <jmattson@google.com>
Fixes: 103af0a98788 ("perf, kvm: Support the in_tx/in_tx_cp modifiers in KVM arch perfmon emulation v5")
Co-developed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220309084257.88931-1-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 902b6d7002156b5a78a357a8404f71b415e81def..eca39f56c23153556c094104b59ea52a1b1e0d91 100644 (file)
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -96,8 +96,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 
 static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
                                  u64 config, bool exclude_user,
-                                 bool exclude_kernel, bool intr,
-                                 bool in_tx, bool in_tx_cp)
+                                 bool exclude_kernel, bool intr)
 {
        struct perf_event *event;
        struct perf_event_attr attr = {
@@ -116,16 +115,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 
        attr.sample_period = get_sample_period(pmc, pmc->counter);
 
-       if (in_tx)
-               attr.config |= HSW_IN_TX;
-       if (in_tx_cp) {
+       if ((attr.config & HSW_IN_TX_CHECKPOINTED) &&
+           guest_cpuid_is_intel(pmc->vcpu)) {
                /*
                 * HSW_IN_TX_CHECKPOINTED is not supported with nonzero
                 * period. Just clear the sample period so at least
                 * allocating the counter doesn't fail.
                 */
                attr.sample_period = 0;
-               attr.config |= HSW_IN_TX_CHECKPOINTED;
        }
 
        event = perf_event_create_kernel_counter(&attr, -1, current,
@@ -233,9 +230,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
        pmc_reprogram_counter(pmc, type, config,
                              !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
                              !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-                             eventsel & ARCH_PERFMON_EVENTSEL_INT,
-                             (eventsel & HSW_IN_TX),
-                             (eventsel & HSW_IN_TX_CHECKPOINTED));
+                             eventsel & ARCH_PERFMON_EVENTSEL_INT);
 }
 EXPORT_SYMBOL_GPL(reprogram_gp_counter);
 
@@ -271,7 +266,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
                              kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc),
                              !(en_field & 0x2), /* exclude user */
                              !(en_field & 0x1), /* exclude kernel */
-                             pmi, false, false);
+                             pmi);
 }
 EXPORT_SYMBOL_GPL(reprogram_fixed_counter);
 

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index da71160a50d6cc77a4e2fa0454b60a3adfc07f9e..efa172a7278e9b91bdeacbe9a64dd3c9d4e98571 100644 (file)
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -389,6 +389,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
        struct kvm_pmc *pmc;
        u32 msr = msr_info->index;
        u64 data = msr_info->data;
+       u64 reserved_bits;
 
        switch (msr) {
        case MSR_CORE_PERF_FIXED_CTR_CTRL:
@@ -443,7 +444,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
                        if (data == pmc->eventsel)
                                return 0;
-                       if (!(data & pmu->reserved_bits)) {
+                       reserved_bits = pmu->reserved_bits;
+                       if ((pmc->idx == 2) &&
+                           (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED))
+                               reserved_bits ^= HSW_IN_TX_CHECKPOINTED;
+                       if (!(data & reserved_bits)) {
                                reprogram_gp_counter(pmc, data);
                                return 0;
                        }
@@ -534,8 +539,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
        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;
+           (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) {
+               pmu->reserved_bits ^= HSW_IN_TX;
+               pmu->raw_event_mask |= (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED);
+       }
 
        bitmap_set(pmu->all_valid_pmc_idx,
                0, pmu->nr_arch_gp_counters);