[PATCH v2 12/17] KVM: x86/pmu: Disable guest PEBS when counters are cross-mapped

[Like Xu <like.xu@linux.intel.com>]

KVM will check if a guest PEBS counter X is cross-mapped to the host
counter Y. In this case, the applicable_counter field in the guest PEBS
records is filled with the real host counter index(s) which is incorrect.

Currently, KVM will disable guest PEBS before vm-entry and the later
patches would do more emulations in the KVM to keep PEBS functionality
work as host, such as rewriting applicable_counter field in the guest
PEBS records buffer.

The cross-mapped check should be done right before vm-entry but after
local_irq_disable() since perf scheduler would rotate the pmc->perf_event
to another host counter or make the event into error state via hrtimer irq.

Signed-off-by: Like Xu <like.xu@linux.intel.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/pmu.c              | 25 +++++++++++++++++++++++++
 arch/x86/kvm/pmu.h              |  1 +
 arch/x86/kvm/vmx/vmx.c          |  3 +++
 arch/x86/kvm/x86.c              |  4 ++++
 5 files changed, 35 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 37df29061a4d..bffb384485da 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -455,6 +455,8 @@ struct kvm_pmu {
 	u64 pebs_data_cfg;
 	u64 pebs_data_cfg_mask;
 
+	bool counter_cross_mapped;
+
 	/*
 	 * The gate to release perf_events not marked in
 	 * pmc_in_use only once in a vcpu time slice.
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index f8aa4724d67b..a6c5951a5728 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -549,3 +549,28 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
 	kfree(filter);
 	return r;
 }
+
+/*
+ * The caller needs to ensure that there is no time window for
+ * perf hrtimer irq or any chance to reschedule pmc->perf_event.
+ */
+void kvm_pmu_counter_cross_mapped_check(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = NULL;
+	int bit;
+
+	pmu->counter_cross_mapped = false;
+
+	for_each_set_bit(bit, (unsigned long *)&pmu->pebs_enable, X86_PMC_IDX_MAX) {
+		pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, bit);
+
+		if (!pmc || !pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc))
+			continue;
+
+		if (pmc->perf_event && (pmc->idx != pmc->perf_event->hw.idx)) {
+			pmu->counter_cross_mapped = true;
+			break;
+		}
+	}
+}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index ee8f15cc4b5e..f5ec94e9a1dc 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -163,6 +163,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu);
 void kvm_pmu_cleanup(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
+void kvm_pmu_counter_cross_mapped_check(struct kvm_vcpu *vcpu);
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx);
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3b62907c8959..302808ec9699 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6556,6 +6556,9 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 	if (!msrs)
 		return;
 
+	if (pmu->counter_cross_mapped)
+		msrs[1].guest = 0;
+
 	if (nr_msrs > 2 && msrs[1].guest) {
 		msrs[2].guest = pmu->ds_area;
 		if (nr_msrs > 3)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b5963a36bf6b..88a544e6379f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8859,6 +8859,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 * result in virtual interrupt delivery.
 	 */
 	local_irq_disable();
+
+	if (vcpu_to_pmu(vcpu)->global_ctrl & vcpu_to_pmu(vcpu)->pebs_enable)
+		kvm_pmu_counter_cross_mapped_check(vcpu);
+
 	vcpu->mode = IN_GUEST_MODE;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-- 
2.21.3