KVM: x86/pmu: Update AMD PMC sample period to fix guest NMI-watchdog

NMI-watchdog is one of the favorite features of kernel developers,
but it does not work in AMD guest even with vPMU enabled and worse,
the system misrepresents this capability via /proc.

This is a PMC emulation error. KVM does not pass the latest valid
value to perf_event in time when guest NMI-watchdog is running, thus
the perf_event corresponding to the watchdog counter will enter the
old state at some point after the first guest NMI injection, forcing
the hardware register PMC0 to be constantly written to 0x800000000001.

Meanwhile, the running counter should accurately reflect its new value
based on the latest coordinated pmc->counter (from vPMC's point of view)
rather than the value written directly by the guest.

Fixes: 168d918f2643 ("KVM: x86: Adjust counter sample period after a wrmsr")
Reported-by: Dongli Cao <caodongli@kingsoft.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Tested-by: Yanan Wang <wangyanan55@huawei.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20220409015226.38619-1-likexu@tencent.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 9e66fba..22992b0 100644 (file)
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -138,6 +138,15 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value)
        return sample_period;
 }
 
+static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
+{
+       if (!pmc->perf_event || pmc->is_paused)
+               return;
+
+       perf_event_period(pmc->perf_event,
+                         get_sample_period(pmc, pmc->counter));
+}
+
 void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel);
 void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx);
 void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);

diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 24eb935..b148608 100644 (file)
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -257,6 +257,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
        pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
        if (pmc) {
                pmc->counter += data - pmc_read_counter(pmc);
+               pmc_update_sample_period(pmc);
                return 0;
        }
        /* MSR_EVNTSELn */

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index bc3f851..b82b670 100644 (file)
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -431,15 +431,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                            !(msr & MSR_PMC_FULL_WIDTH_BIT))
                                data = (s64)(s32)data;
                        pmc->counter += data - pmc_read_counter(pmc);
-                       if (pmc->perf_event && !pmc->is_paused)
-                               perf_event_period(pmc->perf_event,
-                                                 get_sample_period(pmc, data));
+                       pmc_update_sample_period(pmc);
                        return 0;
                } else if ((pmc = get_fixed_pmc(pmu, msr))) {
                        pmc->counter += data - pmc_read_counter(pmc);
-                       if (pmc->perf_event && !pmc->is_paused)
-                               perf_event_period(pmc->perf_event,
-                                                 get_sample_period(pmc, data));
+                       pmc_update_sample_period(pmc);
                        return 0;
                } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
                        if (data == pmc->eventsel)