On Thu, May 14, 2020 at 04:30:53PM +0800, Like Xu wrote:
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.cThis is unreadable gunk, what?
index ea4faae56473..db185dca903d 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -646,6 +646,43 @@ static void intel_pmu_lbr_cleanup(struct kvm_vcpu *vcpu)
intel_pmu_free_lbr_event(vcpu);
}
+static bool intel_pmu_lbr_is_availabile(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+ if (!pmu->lbr_event)
+ return false;
+
+ if (event_is_oncpu(pmu->lbr_event)) {
+ intel_pmu_intercept_lbr_msrs(vcpu, false);
+ } else {
+ intel_pmu_intercept_lbr_msrs(vcpu, true);
+ return false;
+ }
+
+ return true;
+}
It's not true. The guest LBR event with 'ERROR state' or 'oncpu != -1' would be
+/*More unreadable nonsense; when the events go into ERROR state, it's a
+ * Higher priority host perf events (e.g. cpu pinned) could reclaim the
+ * pmu resources (e.g. LBR) that were assigned to the guest. This is
+ * usually done via ipi calls (more details in perf_install_in_context).
+ *
+ * Before entering the non-root mode (with irq disabled here), double
+ * confirm that the pmu features enabled to the guest are not reclaimed
+ * by higher priority host events. Otherwise, disallow vcpu's access to
+ * the reclaimed features.
+ */
+static void intel_pmu_availability_check(struct kvm_vcpu *vcpu)
+{
+ lockdep_assert_irqs_disabled();
+
+ if (lbr_is_enabled(vcpu) && !intel_pmu_lbr_is_availabile(vcpu) &&
+ (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+ pr_warn_ratelimited("kvm: vcpu-%d: LBR is temporarily unavailable.\n",
+ vcpu->vcpu_id);
permanent fail, they'll not come back.
In fact, availability_check() is only called here for just one time.
+}AFAICT you just did a call out to the kvm_pmu crud in
+
struct kvm_pmu_ops intel_pmu_ops = {
.find_arch_event = intel_find_arch_event,
.find_fixed_event = intel_find_fixed_event,
@@ -662,4 +699,5 @@ struct kvm_pmu_ops intel_pmu_ops = {
.reset = intel_pmu_reset,
.deliver_pmi = intel_pmu_deliver_pmi,
.lbr_cleanup = intel_pmu_lbr_cleanup,
+ .availability_check = intel_pmu_availability_check,
};
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9969d663826a..80d036c5f64a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6696,8 +6696,10 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
pt_guest_enter(vmx);
- if (vcpu_to_pmu(vcpu)->version)
+ if (vcpu_to_pmu(vcpu)->version) {
atomic_switch_perf_msrs(vmx);
+ kvm_x86_ops.pmu_ops->availability_check(vcpu);
+ }
atomic_switch_perf_msrs(), why do another call?