[PULL 06/23] target/i386: Add lbr-fmt vPMU option to support guest LBR

[Paolo Bonzini]

From: Yang Weijiang <weijiang.yang@intel.com>

The Last Branch Recording (LBR) is a performance monitor unit (PMU)
feature on Intel processors which records a running trace of the most
recent branches taken by the processor in the LBR stack. This option
indicates the LBR format to enable for guest perf.

The LBR feature is enabled if below conditions are met:
1) KVM is enabled and the PMU is enabled.
2) msr-based-feature IA32_PERF_CAPABILITIES is supporterd on KVM.
3) Supported returned value for lbr_fmt from above msr is non-zero.
4) Guest vcpu model does support FEAT_1_ECX.CPUID_EXT_PDCM.
5) User-provided lbr-fmt value doesn't violate its bitmask (0x3f).
6) Target guest LBR format matches that of host.

Co-developed-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
Message-Id: <20220215195258.29149-3-weijiang.yang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/cpu.c | 40 ++++++++++++++++++++++++++++++++++++++++
 target/i386/cpu.h | 10 ++++++++++
 2 files changed, 50 insertions(+)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 6083e556f5..856a8659e8 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -6275,6 +6275,7 @@ static void x86_cpu_realizefn(DeviceState *dev, Error 
**errp)
     CPUX86State *env = &cpu->env;
     Error *local_err = NULL;
     static bool ht_warned;
+    unsigned requested_lbr_fmt;
 
     if (cpu->apic_id == UNASSIGNED_APIC_ID) {
         error_setg(errp, "apic-id property was not initialized properly");
@@ -6292,6 +6293,42 @@ static void x86_cpu_realizefn(DeviceState *dev, Error 
**errp)
         goto out;
     }
 
+    /*
+     * Override env->features[FEAT_PERF_CAPABILITIES].LBR_FMT
+     * with user-provided setting.
+     */
+    if (cpu->lbr_fmt != ~PERF_CAP_LBR_FMT) {
+        if ((cpu->lbr_fmt & PERF_CAP_LBR_FMT) != cpu->lbr_fmt) {
+            error_setg(errp, "invalid lbr-fmt");
+            return;
+        }
+        env->features[FEAT_PERF_CAPABILITIES] &= ~PERF_CAP_LBR_FMT;
+        env->features[FEAT_PERF_CAPABILITIES] |= cpu->lbr_fmt;
+    }
+
+    /*
+     * vPMU LBR is supported when 1) KVM is enabled 2) Option pmu=on and
+     * 3)vPMU LBR format matches that of host setting.
+     */
+    requested_lbr_fmt =
+        env->features[FEAT_PERF_CAPABILITIES] & PERF_CAP_LBR_FMT;
+    if (requested_lbr_fmt && kvm_enabled()) {
+        uint64_t host_perf_cap =
+            x86_cpu_get_supported_feature_word(FEAT_PERF_CAPABILITIES, false);
+        unsigned host_lbr_fmt = host_perf_cap & PERF_CAP_LBR_FMT;
+
+        if (!cpu->enable_pmu) {
+            error_setg(errp, "vPMU: LBR is unsupported without pmu=on");
+            return;
+        }
+        if (requested_lbr_fmt != host_lbr_fmt) {
+            error_setg(errp, "vPMU: the lbr-fmt value (0x%x) does not match "
+                        "the host value (0x%x).",
+                        requested_lbr_fmt, host_lbr_fmt);
+            return;
+        }
+    }
+
     x86_cpu_filter_features(cpu, cpu->check_cpuid || cpu->enforce_cpuid);
 
     if (cpu->enforce_cpuid && x86_cpu_have_filtered_features(cpu)) {
@@ -6644,6 +6681,8 @@ static void x86_cpu_initfn(Object *obj)
     object_property_add_alias(obj, "sse4_2", obj, "sse4.2");
 
     object_property_add_alias(obj, "hv-apicv", obj, "hv-avic");
+    cpu->lbr_fmt = ~PERF_CAP_LBR_FMT;
+    object_property_add_alias(obj, "lbr_fmt", obj, "lbr-fmt");
 
     if (xcc->model) {
         x86_cpu_load_model(cpu, xcc->model);
@@ -6798,6 +6837,7 @@ static Property x86_cpu_properties[] = {
 #endif
     DEFINE_PROP_INT32("node-id", X86CPU, node_id, CPU_UNSET_NUMA_NODE_ID),
     DEFINE_PROP_BOOL("pmu", X86CPU, enable_pmu, false),
+    DEFINE_PROP_UINT64_CHECKMASK("lbr-fmt", X86CPU, lbr_fmt, PERF_CAP_LBR_FMT),
 
     DEFINE_PROP_UINT32("hv-spinlocks", X86CPU, hyperv_spinlock_attempts,
                        HYPERV_SPINLOCK_NEVER_NOTIFY),
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 9661f9fbd1..6730df5dbf 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -386,6 +386,7 @@ typedef enum X86Seg {
 #define ARCH_CAP_TSX_CTRL_MSR          (1<<7)
 
 #define MSR_IA32_PERF_CAPABILITIES      0x345
+#define PERF_CAP_LBR_FMT                0x3f
 
 #define MSR_IA32_TSX_CTRL              0x122
 #define MSR_IA32_TSCDEADLINE            0x6e0
@@ -1810,6 +1811,15 @@ struct ArchCPU {
      */
     bool enable_pmu;
 
+    /*
+     * Enable LBR_FMT bits of IA32_PERF_CAPABILITIES MSR.
+     * This can't be initialized with a default because it doesn't have
+     * stable ABI support yet. It is only allowed to pass all LBR_FMT bits
+     * returned by kvm_arch_get_supported_msr_feature()(which depends on both
+     * host CPU and kernel capabilities) to the guest.
+     */
+    uint64_t lbr_fmt;
+
     /* LMCE support can be enabled/disabled via cpu option 'lmce=on/off'. It is
      * disabled by default to avoid breaking migration between QEMU with
      * different LMCE configurations.
-- 
2.36.0