From: Like Xu <likexu@xxxxxxxxxxx>
The check logic in the pmc_resume_counter() to determine whether
a perf_event is reusable is partial and flawed, especially when it
comes to a pseudocode sequence (not correct but clearly valid) like:
- enabling a counter and its PEBS bit
- enable global_ctrl
- run workload
- disable only the PEBS bit, leaving the global_ctrl bit enabled
In this corner case, a perf_event created for PEBS can be reused by
a normal counter before it has been released and recreated, and when this
normal counter overflows, it triggers a PEBS interrupt (precise_ip != 0).
To address this issue, the reuse check has been revamped and KVM will
go back to do reprogram_counter() when any bit of guest PEBS_ENABLE
msr has changed, which is similar to what global_ctrl_changed() does.
Fixes: 79f3e3b58386 ("KVM: x86/pmu: Reprogram PEBS event to emulate guest PEBS counter")
Signed-off-by: Like Xu <likexu@xxxxxxxxxxx>
---
arch/x86/kvm/pmu.c | 4 ++--
arch/x86/kvm/vmx/pmu_intel.c | 14 +++++++-------
2 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 08ee0fed63d5..2c03fe208093 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -232,8 +232,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
get_sample_period(pmc, pmc->counter)))
return false;
- if (!test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) &&
- pmc->perf_event->attr.precise_ip)
+ if (test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) !=
+ (!!pmc->perf_event->attr.precise_ip))
return false;
/* reuse perf_event to serve as pmc_reprogram_counter() does*/
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 1588627974fa..5f6b9f596f16 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -68,15 +68,11 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
}
}
-/* function is called when global control register has been updated. */
-static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+static void reprogram_counters(struct kvm_pmu *pmu, u64 diff)
{
int bit;
- u64 diff = pmu->global_ctrl ^ data;
struct kvm_pmc *pmc;
- pmu->global_ctrl = data;
-
for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) {
pmc = intel_pmc_idx_to_pmc(pmu, bit);
if (pmc)
@@ -404,7 +400,7 @@ 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;
+ u64 reserved_bits, diff;
switch (msr) {
case MSR_CORE_PERF_FIXED_CTR_CTRL:
@@ -425,7 +421,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (pmu->global_ctrl == data)
return 0;
if (kvm_valid_perf_global_ctrl(pmu, data)) {
- global_ctrl_changed(pmu, data);
+ diff = pmu->global_ctrl ^ data;
+ pmu->global_ctrl = data;
+ reprogram_counters(pmu, diff);
return 0;
}
break;
@@ -440,7 +438,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (pmu->pebs_enable == data)
return 0;
if (!(data & pmu->pebs_enable_mask)) {
+ diff = pmu->pebs_enable ^ data;
pmu->pebs_enable = data;
+ reprogram_counters(pmu, diff);
return 0;
}
break;
--
2.37.0
