Commit 3833744651 for qemu.org

commit 383374465155c682ddd6bb4002cdcd09995c9b7f
Author: Dongli Zhang <dongli.zhang@oracle.com>
Date:   Thu Jan 8 23:53:56 2026 -0800

    target/i386/kvm: set KVM_PMU_CAP_DISABLE if "-pmu" is configured

    Although AMD PERFCORE and PerfMonV2 are removed when "-pmu" is configured,
    there is no way to fully disable KVM AMD PMU virtualization. Neither
    "-cpu host,-pmu" nor "-cpu EPYC" achieves this.

    As a result, the following message still appears in the VM dmesg:

    [    0.263615] Performance Events: AMD PMU driver.

    However, the expected output should be:

    [    0.596381] Performance Events: PMU not available due to virtualization, using software events only.
    [    0.600972] NMI watchdog: Perf NMI watchdog permanently disabled

    This occurs because AMD does not use any CPUID bit to indicate PMU
    availability.

    To address this, KVM_CAP_PMU_CAPABILITY is used to set KVM_PMU_CAP_DISABLE
    when "-pmu" is configured.

    Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
    Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
    Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
    Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
    Reviewed-by: Zide Chen <zide.chen@intel.com>
    Link: https://lore.kernel.org/r/20260109075508.113097-2-dongli.zhang@oracle.com
    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 0c940d4b64..69748420fd 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -178,6 +178,8 @@ static int has_triple_fault_event;

 static bool has_msr_mcg_ext_ctl;

+static int pmu_cap;
+
 static struct kvm_cpuid2 *cpuid_cache;
 static struct kvm_cpuid2 *hv_cpuid_cache;
 static struct kvm_msr_list *kvm_feature_msrs;
@@ -2079,6 +2081,33 @@ full:

 int kvm_arch_pre_create_vcpu(CPUState *cpu, Error **errp)
 {
+    static bool first = true;
+    int ret;
+
+    if (first) {
+        first = false;
+
+        /*
+         * Since Linux v5.18, KVM provides a VM-level capability to easily
+         * disable PMUs; however, QEMU has been providing PMU property per
+         * CPU since v1.6. In order to accommodate both, have to configure
+         * the VM-level capability here.
+         *
+         * KVM_PMU_CAP_DISABLE doesn't change the PMU
+         * behavior on Intel platform because current "pmu" property works
+         * as expected.
+         */
+        if ((pmu_cap & KVM_PMU_CAP_DISABLE) && !X86_CPU(cpu)->enable_pmu) {
+            ret = kvm_vm_enable_cap(kvm_state, KVM_CAP_PMU_CAPABILITY, 0,
+                                    KVM_PMU_CAP_DISABLE);
+            if (ret < 0) {
+                error_setg_errno(errp, -ret,
+                                 "Failed to set KVM_PMU_CAP_DISABLE");
+                return ret;
+            }
+        }
+    }
+
     if (is_tdx_vm()) {
         return tdx_pre_create_vcpu(cpu, errp);
     }
@@ -3390,6 +3419,8 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
         }
     }

+    pmu_cap = kvm_check_extension(s, KVM_CAP_PMU_CAPABILITY);
+
     return 0;
 }