The commit is pushed to "branch-rh10-6.12.0-55.52.1.5.x.vz10-ovz" and will
appear at [email protected]:openvz/vzkernel.git
after rh10-6.12.0-55.52.1.5.28.vz10
------>
commit eeaebe10aab0d338fdce3d727b60e81e334d426a
Author: Denis V. Lunev <[email protected]>
Date: Tue May 26 19:18:23 2026 +0200
x86/kvm: skip kvm_pmu_trigger_event() when guest PMU is disabled
kvm_pmu_trigger_event() is called from several KVM x86 hot paths to feed
the emulated INSTRUCTIONS_RETIRED / BRANCH_INSTRUCTIONS_RETIRED PMC events:
* kvm_skip_emulated_instruction() - once per emulated-instruction skip
(CPUID exits, hypercalls, fastpath MSR writes, ...)
* x86_emulate_instruction() - on every successfully emulated instruction
(MMIO, real-mode emulation), with a second call for branch instructions
* nested_vmx_run() - on guest VMRUN, counts as a branch instruction
The function does a stack bitmap allocation, a bitmap_and against
pmu->global_ctrl, indirect calls to pmc_event_is_allowed() and
cpl_is_matched(), and an empty kvm_for_each_pmc() walk before returning
when nothing is programmed. On guests with PMU disabled at the per-VM level
(<pmu state='off'/>), all of this work is dead-weight on every traversal.
Guard each call site with a check on kvm->arch.enable_pmu. The unlikely()
hint keeps the hot path straight-line and places the (rarely-taken) call
out-of-line for better I-cache density. Adjacent calls in
x86_emulate_instruction() share one guard.
The CPUID-skip site is hottest, so most of the measured impact comes from
there - but gating the remaining three call sites for consistency avoids a
"one gated, three not" state.
Measured on at_cpu_cpuid (-k 0, VSTOR-131579 methodology), guest PMU off,
on top of a Nova-side default-PMU-off VM config:
AMD Zen2 (epyc01, EPYC 7302): +2.7%, ~57 cyc/VMEXIT saved
Intel Ice Lake-SP (hw-hdd01): +0.6%, ~26 cyc/VMEXIT saved
The AMD bias is consistent with the per-call retpoline + unret + Safe-RET
tax on Zen2/Zen3 with default mitigations: removing an entire call/return
sequence from the AMD hot path saves more than the same removal on Intel
with Enhanced/Auto IBRS.
https://virtuozzo.atlassian.net/browse/VSTOR-132543
https://virtuozzo.atlassian.net/browse/VSTOR-132471
Feature: kvm
Signed-off-by: Denis V. Lunev <[email protected]>
---
arch/x86/kvm/vmx/nested.c | 3 ++-
arch/x86/kvm/x86.c | 11 +++++++----
2 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 5df2c6bffab83..76589a1664682 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3684,7 +3684,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool
launch)
return 1;
}
- kvm_pmu_trigger_event(vcpu,
kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);
+ if (unlikely(vcpu->kvm->arch.enable_pmu))
+ kvm_pmu_trigger_event(vcpu,
kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);
if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
return nested_vmx_failInvalid(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1249fbbe26951..8a872cbb18ad7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8957,7 +8957,8 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
if (unlikely(!r))
return 0;
- kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
+ if (unlikely(vcpu->kvm->arch.enable_pmu))
+ kvm_pmu_trigger_event(vcpu,
kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
/*
* rflags is the old, "raw" value of the flags. The new value has
@@ -9283,9 +9284,11 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t
cr2_or_gpa,
*/
if (!ctxt->have_exception ||
exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
- kvm_pmu_trigger_event(vcpu,
kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
- if (ctxt->is_branch)
- kvm_pmu_trigger_event(vcpu,
kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);
+ if (unlikely(vcpu->kvm->arch.enable_pmu)) {
+ kvm_pmu_trigger_event(vcpu,
kvm_pmu_eventsel.INSTRUCTIONS_RETIRED);
+ if (ctxt->is_branch)
+ kvm_pmu_trigger_event(vcpu,
kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED);
+ }
kvm_rip_write(vcpu, ctxt->eip);
if (r && (ctxt->tf || (vcpu->guest_debug &
KVM_GUESTDBG_SINGLESTEP)))
r = kvm_vcpu_do_singlestep(vcpu);
_______________________________________________
Devel mailing list
[email protected]
https://lists.openvz.org/mailman/listinfo/devel
