On 6/24/2025 3:43 PM, Dongli Zhang wrote:
> When PMU is enabled in QEMU, there is a chance that PMU virtualization is
> completely disabled by the KVM module parameter kvm.enable_pmu=N.
>
> The kvm.enable_pmu parameter is introduced since Linux v5.17.
> Its permission is 0444. It does not change until a reload of the KVM
> module.
>
> Read the kvm.enable_pmu value from the module sysfs to give a chance to
> provide more information about vPMU enablement.
>
> Signed-off-by: Dongli Zhang <dongli.zh...@oracle.com>
> Reviewed-by: Zhao Liu <zhao1....@intel.com>
> ---
> Changed since v2:
> - Rework the code flow following Zhao's suggestion.
> - Return error when:
> (*kvm_enable_pmu == 'N' && X86_CPU(cpu)->enable_pmu)
> Changed since v3:
> - Re-split the cases into enable_pmu and !enable_pmu, following Zhao's
> suggestion.
> - Rework the commit messages.
> - Bring back global static variable 'kvm_pmu_disabled' from v2.
> Changed since v4:
> - Add Reviewed-by from Zhao.
> Changed since v5:
> - Rebase on top of most recent QEMU.
>
> target/i386/kvm/kvm.c | 61 +++++++++++++++++++++++++++++++------------
> 1 file changed, 44 insertions(+), 17 deletions(-)
>
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index 824148688d..d191dd1da3 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -186,6 +186,10 @@ static int has_triple_fault_event;
> static bool has_msr_mcg_ext_ctl;
>
> static int pmu_cap;
> +/*
> + * Read from /sys/module/kvm/parameters/enable_pmu.
> + */
> +static bool kvm_pmu_disabled;
>
> static struct kvm_cpuid2 *cpuid_cache;
> static struct kvm_cpuid2 *hv_cpuid_cache;
> @@ -2050,23 +2054,30 @@ int kvm_arch_pre_create_vcpu(CPUState *cpu, Error
> **errp)
> 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 (X86_CPU(cpu)->enable_pmu) {
> + if (kvm_pmu_disabled) {
> + warn_report("Failed to enable PMU since "
> + "KVM's enable_pmu parameter is disabled");
> + }
> + } else {
> + /*
> + * 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) {
> + 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;
> + }
> }
> }
> }
> @@ -3273,6 +3284,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
> int ret;
> struct utsname utsname;
> Error *local_err = NULL;
> + g_autofree char *kvm_enable_pmu;
>
> /*
> * Initialize confidential guest (SEV/TDX) context, if required
> @@ -3409,6 +3421,21 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>
> pmu_cap = kvm_check_extension(s, KVM_CAP_PMU_CAPABILITY);
>
> + /*
> + * The enable_pmu parameter is introduced since Linux v5.17,
> + * give a chance to provide more information about vPMU
> + * enablement.
> + *
> + * The kvm.enable_pmu's permission is 0444. It does not change
> + * until a reload of the KVM module.
> + */
> + if (g_file_get_contents("/sys/module/kvm/parameters/enable_pmu",
> + &kvm_enable_pmu, NULL, NULL)) {
> + if (*kvm_enable_pmu == 'N') {
> + kvm_pmu_disabled = true;
> + }
> + }
> +
> return 0;
> }
>
Reviewed-by: Dapeng Mi <dapeng1...@linux.intel.com>
