From: Like Xu <likexu@xxxxxxxxxxx>
commit 75189d1de1b377e580ebd2d2c55914631eac9c64 upstream.
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@xxxxxxxxxxxx>
Signed-off-by: Like Xu <likexu@xxxxxxxxxxx>
Reviewed-by: Yanan Wang <wangyanan55@xxxxxxxxxx>
Tested-by: Yanan Wang <wangyanan55@xxxxxxxxxx>
Reviewed-by: Jim Mattson <jmattson@xxxxxxxxxx>
Message-Id: <20220409015226.38619-1-likexu@xxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kvm/pmu.h | 9 +++++++++
arch/x86/kvm/svm/pmu.c | 1 +
arch/x86/kvm/vmx/pmu_intel.c | 8 ++------
3 files changed, 12 insertions(+), 6 deletions(-)
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -140,6 +140,15 @@ static inline u64 get_sample_period(stru
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);
--- 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_vc
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 */
--- 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_
!(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)
