[PATCH RESEND v2 1/2] target/i386/kvm: introduce 'pmu-cap-disabled' to set KVM_PMU_CAP_DISABLE

[Dongli Zhang]

The "perf stat" at the VM side still works even we set "-cpu host,-pmu" in
the QEMU command line. That is, neither "-cpu host,-pmu" nor "-cpu EPYC"
could disable the pmu virtualization in an AMD environment.

We still see below at VM kernel side ...

[    0.510611] Performance Events: Fam17h+ core perfctr, AMD PMU driver.

... although we expect something like below.

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

This is because the AMD pmu (v1) does not rely on cpuid to decide if the
pmu virtualization is supported.

We introduce a new property 'pmu-cap-disabled' for KVM accel to set
KVM_PMU_CAP_DISABLE if KVM_CAP_PMU_CAPABILITY is supported. Only x86 host
is supported because currently KVM uses KVM_CAP_PMU_CAPABILITY only for
x86.

Cc: Joe Jin <joe.jin@oracle.com>
Cc: Like Xu <likexu@tencent.com>
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
---
Changed since v1:
- In version 1 we did not introduce the new property. We ioctl
  KVM_PMU_CAP_DISABLE only before the creation of the 1st vcpu. We had
  introduced a helpfer function to do this job before creating the 1st
  KVM vcpu in v1.

 accel/kvm/kvm-all.c      |  1 +
 include/sysemu/kvm_int.h |  1 +
 qemu-options.hx          |  7 ++++++
 target/i386/kvm/kvm.c    | 46 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 55 insertions(+)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 7679f397ae..238098e991 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -3763,6 +3763,7 @@ static void kvm_accel_instance_init(Object *obj)
     s->xen_version = 0;
     s->xen_gnttab_max_frames = 64;
     s->xen_evtchn_max_pirq = 256;
+    s->pmu_cap_disabled = false;
 }
 
 /**
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index 511b42bde5..cbbe08ec54 100644
--- a/include/sysemu/kvm_int.h
+++ b/include/sysemu/kvm_int.h
@@ -123,6 +123,7 @@ struct KVMState
     uint32_t xen_caps;
     uint16_t xen_gnttab_max_frames;
     uint16_t xen_evtchn_max_pirq;
+    bool pmu_cap_disabled;
 };
 
 void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
diff --git a/qemu-options.hx b/qemu-options.hx
index b57489d7ca..1976c0ca3e 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -187,6 +187,7 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel,
     "                tb-size=n (TCG translation block cache size)\n"
     "                dirty-ring-size=n (KVM dirty ring GFN count, default 0)\n"
     "                notify-vmexit=run|internal-error|disable,notify-window=n 
(enable notify VM exit and set notify window, x86 only)\n"
+    "                pmu-cap-disabled=true|false (disable 
KVM_CAP_PMU_CAPABILITY, x86 only, default false)\n"
     "                thread=single|multi (enable multi-threaded TCG)\n", 
QEMU_ARCH_ALL)
 SRST
 ``-accel name[,prop=value[,...]]``
@@ -254,6 +255,12 @@ SRST
         open up for a specified of time (i.e. notify-window).
         Default: notify-vmexit=run,notify-window=0.
 
+    ``pmu-cap-disabled=true|false``
+        When the KVM accelerator is used, it controls whether to disable the
+        KVM_CAP_PMU_CAPABILITY via KVM_PMU_CAP_DISABLE. When disabled, the
+        PMU virtualization is disabled at the KVM module side. This is for
+        x86 host only.
+
 ERST
 
 DEF("smp", HAS_ARG, QEMU_OPTION_smp,
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index de531842f6..bf4136fa1b 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -129,6 +129,7 @@ static bool has_msr_ucode_rev;
 static bool has_msr_vmx_procbased_ctls2;
 static bool has_msr_perf_capabs;
 static bool has_msr_pkrs;
+static bool has_pmu_cap;
 
 static uint32_t has_architectural_pmu_version;
 static uint32_t num_architectural_pmu_gp_counters;
@@ -2767,6 +2768,23 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
         }
     }
 
+    has_pmu_cap = kvm_check_extension(s, KVM_CAP_PMU_CAPABILITY);
+
+    if (s->pmu_cap_disabled) {
+        if (has_pmu_cap) {
+            ret = kvm_vm_enable_cap(s, KVM_CAP_PMU_CAPABILITY, 0,
+                                    KVM_PMU_CAP_DISABLE);
+            if (ret < 0) {
+                s->pmu_cap_disabled = false;
+                error_report("kvm: Failed to disable pmu cap: %s",
+                             strerror(-ret));
+            }
+        } else {
+            s->pmu_cap_disabled = false;
+            error_report("kvm: KVM_CAP_PMU_CAPABILITY is not supported");
+        }
+    }
+
     return 0;
 }
 
@@ -5951,6 +5969,28 @@ static void kvm_arch_set_xen_evtchn_max_pirq(Object 
*obj, Visitor *v,
     s->xen_evtchn_max_pirq = value;
 }
 
+static void kvm_set_pmu_cap_disabled(Object *obj, Visitor *v,
+                                     const char *name, void *opaque,
+                                     Error **errp)
+{
+    KVMState *s = KVM_STATE(obj);
+    bool pmu_cap_disabled;
+    Error *error = NULL;
+
+    if (s->fd != -1) {
+        error_setg(errp, "Cannot set properties after the accelerator has been 
initialized");
+        return;
+    }
+
+    visit_type_bool(v, name, &pmu_cap_disabled, &error);
+    if (error) {
+        error_propagate(errp, error);
+        return;
+    }
+
+    s->pmu_cap_disabled = pmu_cap_disabled;
+}
+
 void kvm_arch_accel_class_init(ObjectClass *oc)
 {
     object_class_property_add_enum(oc, "notify-vmexit", "NotifyVMexitOption",
@@ -5990,6 +6030,12 @@ void kvm_arch_accel_class_init(ObjectClass *oc)
                               NULL, NULL);
     object_class_property_set_description(oc, "xen-evtchn-max-pirq",
                                           "Maximum number of Xen PIRQs");
+
+    object_class_property_add(oc, "pmu-cap-disabled", "bool",
+                              NULL, kvm_set_pmu_cap_disabled,
+                              NULL, NULL);
+    object_class_property_set_description(oc, "pmu-cap-disabled",
+                                          "Disable KVM_CAP_PMU_CAPABILITY");
 }
 
 void kvm_set_max_apic_id(uint32_t max_apic_id)
-- 
2.34.1