From: Xiong Zhang <xiong.y.zhang@xxxxxxxxxxxxxxx>
When passthrough PMU is enabled by kvm and perf, KVM call
perf_get_mediated_pmu() to exclusive own x86 core PMU at VM creation, KVM
call perf_put_mediated_pmu() to return x86 core PMU to host perf at VM
destroy.
When perf_get_mediated_pmu() fail, the host has system wide perf events
without exclude_guest = 1 which must be disabled to enable VM with
passthrough PMU.
Once VM with passthrough PMU starts, perf will refuse to create system wide
perf event without exclude_guest = 1 until the vm is closed.
Signed-off-by: Xiong Zhang <xiong.y.zhang@xxxxxxxxxxxxxxx>
---
arch/x86/kvm/x86.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index db395c00955f..3152587eca5b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6674,8 +6674,11 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
if (!kvm->created_vcpus) {
kvm->arch.enable_pmu = !(cap->args[0] & KVM_PMU_CAP_DISABLE);
/* Disable passthrough PMU if enable_pmu is false. */
- if (!kvm->arch.enable_pmu)
+ if (!kvm->arch.enable_pmu) {
+ if (kvm->arch.enable_passthrough_pmu)
+ perf_put_mediated_pmu();
kvm->arch.enable_passthrough_pmu = false;
+ }
r = 0;
}
mutex_unlock(&kvm->lock);
@@ -12578,6 +12581,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.guest_can_read_msr_platform_info = true;
kvm->arch.enable_pmu = enable_pmu;
kvm->arch.enable_passthrough_pmu = enable_passthrough_pmu;
+ if (kvm->arch.enable_passthrough_pmu) {
+ ret = perf_get_mediated_pmu();
+ if (ret < 0) {
+ kvm_err("failed to enable mediated passthrough pmu, please disable system wide perf events\n");
+ goto out_uninit_mmu;
+ }
+ }
+
#if IS_ENABLED(CONFIG_HYPERV)
spin_lock_init(&kvm->arch.hv_root_tdp_lock);
@@ -12726,6 +12737,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
__x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
mutex_unlock(&kvm->slots_lock);
}
+ if (kvm->arch.enable_passthrough_pmu)
+ perf_put_mediated_pmu();
kvm_unload_vcpu_mmus(kvm);
static_call_cond(kvm_x86_vm_destroy)(kvm);
kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
--
2.45.0.rc1.225.g2a3ae87e7f-goog
