@@ -2815,7 +2815,8 @@ static void mce_init(X86CPU *cpu)
if (((cenv->cpuid_version >> 8) & 0xf) >= 6
&& (cenv->features[FEAT_1_EDX] & (CPUID_MCE | CPUID_MCA)) ==
(CPUID_MCE | CPUID_MCA)) {
- cenv->mcg_cap = MCE_CAP_DEF | MCE_BANKS_DEF;
+ cenv->mcg_cap = MCE_CAP_DEF | MCE_BANKS_DEF |
+ (cpu->enable_lmce ? MCG_LMCE_P : 0);
cenv->mcg_ctl = ~(uint64_t)0;
for (bank = 0; bank < MCE_BANKS_DEF; bank++) {
cenv->mce_banks[bank * 4] = ~(uint64_t)0;
@@ -3262,6 +3263,7 @@ static Property x86_cpu_properties[] = {
DEFINE_PROP_UINT32("xlevel2", X86CPU, env.cpuid_xlevel2, 0),
DEFINE_PROP_STRING("hv-vendor-id", X86CPU, hyperv_vendor_id),
DEFINE_PROP_BOOL("cpuid-0xb", X86CPU, enable_cpuid_0xb, true),
+ DEFINE_PROP_BOOL("lmce", X86CPU, enable_lmce, false),
DEFINE_PROP_END_OF_LIST()
};
@@ -292,6 +292,7 @@
#define MCG_CTL_P (1ULL<<8) /* MCG_CAP register available */
#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */
+#define MCG_LMCE_P (1ULL<<27) /* Local Machine Check Supported */
#define MCE_CAP_DEF (MCG_CTL_P|MCG_SER_P)
#define MCE_BANKS_DEF 10
@@ -301,6 +302,9 @@
#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */
#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */
#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */
+#define MCG_STATUS_LMCE (1ULL<<3) /* Local MCE signaled */
+
+#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Local MCE enabled */
#define MCI_STATUS_VAL (1ULL<<63) /* valid error */
#define MCI_STATUS_OVER (1ULL<<62) /* previous errors lost */
@@ -343,6 +347,7 @@
#define MSR_MCG_CAP 0x179
#define MSR_MCG_STATUS 0x17a
#define MSR_MCG_CTL 0x17b
+#define MSR_MCG_EXT_CTL 0x4d0
#define MSR_P6_EVNTSEL0 0x186
@@ -1111,6 +1116,7 @@ typedef struct CPUX86State {
uint64_t mcg_cap;
uint64_t mcg_ctl;
+ uint64_t mcg_ext_ctl;
uint64_t mce_banks[MCE_BANKS_DEF*4];
uint64_t tsc_aux;
@@ -1178,6 +1184,12 @@ struct X86CPU {
*/
bool enable_pmu;
+ /* 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.
+ */
+ bool enable_lmce;
+
/* Compatibility bits for old machine types: */
bool enable_cpuid_0xb;
@@ -106,6 +106,8 @@ static int has_xsave;
static int has_xcrs;
static int has_pit_state2;
+static bool has_msr_mcg_ext_ctl;
+
static struct kvm_cpuid2 *cpuid_cache;
int kvm_has_pit_state2(void)
@@ -382,10 +384,12 @@ static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap,
static void kvm_mce_inject(X86CPU *cpu, hwaddr paddr, int code)
{
+ CPUState *cs = CPU(cpu);
CPUX86State *env = &cpu->env;
uint64_t status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN |
MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S;
uint64_t mcg_status = MCG_STATUS_MCIP;
+ int flags = 0;
if (code == BUS_MCEERR_AR) {
status |= MCI_STATUS_AR | 0x134;
@@ -394,10 +398,19 @@ static void kvm_mce_inject(X86CPU *cpu, hwaddr paddr, int code)
status |= 0xc0;
mcg_status |= MCG_STATUS_RIPV;
}
+
+ flags = cpu_x86_support_mca_broadcast(env) ? MCE_INJECT_BROADCAST : 0;
+ /* We need to read back the value of MSR_EXT_MCG_CTL that was set by the
+ * guest kernel back into env->mcg_ext_ctl.
+ */
+ cpu_synchronize_state(cs);
+ if (env->mcg_ext_ctl & MCG_EXT_CTL_LMCE_EN) {
+ mcg_status |= MCG_STATUS_LMCE;
+ flags = 0;
+ }
+
cpu_x86_inject_mce(NULL, cpu, 9, status, mcg_status, paddr,
- (MCM_ADDR_PHYS << 6) | 0xc,
- cpu_x86_support_mca_broadcast(env) ?
- MCE_INJECT_BROADCAST : 0);
+ (MCM_ADDR_PHYS << 6) | 0xc, flags);
}
static void hardware_memory_error(void)
@@ -865,6 +878,10 @@ int kvm_arch_init_vcpu(CPUState *cs)
unsupported_caps = env->mcg_cap & ~(mcg_cap | MCG_CAP_BANKS_MASK);
if (unsupported_caps) {
+ if (unsupported_caps & MCG_LMCE_P) {
+ error_report("kvm: LMCE not supported");
+ return -ENOTSUP;
+ }
error_report("warning: Unsupported MCG_CAP bits: 0x%" PRIx64,
unsupported_caps);
}
@@ -885,6 +902,10 @@ int kvm_arch_init_vcpu(CPUState *cs)
!!(c->ecx & CPUID_EXT_SMX);
}
+ if (env->mcg_cap & MCG_LMCE_P) {
+ has_msr_mcg_ext_ctl = has_msr_feature_control = true;
+ }
+
c = cpuid_find_entry(&cpuid_data.cpuid, 0x80000007, 0);
if (c && (c->edx & 1<<8) && invtsc_mig_blocker == NULL) {
/* for migration */
@@ -1705,6 +1726,9 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
kvm_msr_entry_add(cpu, MSR_MCG_STATUS, env->mcg_status);
kvm_msr_entry_add(cpu, MSR_MCG_CTL, env->mcg_ctl);
+ if (has_msr_mcg_ext_ctl) {
+ kvm_msr_entry_add(cpu, MSR_MCG_EXT_CTL, env->mcg_ext_ctl);
+ }
for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++) {
kvm_msr_entry_add(cpu, MSR_MC0_CTL + i, env->mce_banks[i]);
}
@@ -2008,6 +2032,9 @@ static int kvm_get_msrs(X86CPU *cpu)
if (env->mcg_cap) {
kvm_msr_entry_add(cpu, MSR_MCG_STATUS, 0);
kvm_msr_entry_add(cpu, MSR_MCG_CTL, 0);
+ if (has_msr_mcg_ext_ctl) {
+ kvm_msr_entry_add(cpu, MSR_MCG_EXT_CTL, 0);
+ }
for (i = 0; i < (env->mcg_cap & 0xff) * 4; i++) {
kvm_msr_entry_add(cpu, MSR_MC0_CTL + i, 0);
}
@@ -2136,6 +2163,9 @@ static int kvm_get_msrs(X86CPU *cpu)
case MSR_MCG_CTL:
env->mcg_ctl = msrs[i].data;
break;
+ case MSR_MCG_EXT_CTL:
+ env->mcg_ext_ctl = msrs[i].data;
+ break;
case MSR_IA32_MISC_ENABLE:
env->msr_ia32_misc_enable = msrs[i].data;
break;
@@ -896,6 +896,24 @@ static const VMStateDescription vmstate_tsc_khz = {
}
};
+static bool mcg_ext_ctl_needed(void *opaque)
+{
+ X86CPU *cpu = opaque;
+ CPUX86State *env = &cpu->env;
+ return cpu->enable_lmce && env->mcg_ext_ctl;
+}
+
+static const VMStateDescription vmstate_mcg_ext_ctl = {
+ .name = "cpu/mcg_ext_ctl",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = mcg_ext_ctl_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT64(env.mcg_ext_ctl, X86CPU),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
VMStateDescription vmstate_x86_cpu = {
.name = "cpu",
.version_id = 12,
@@ -1022,6 +1040,7 @@ VMStateDescription vmstate_x86_cpu = {
#ifdef TARGET_X86_64
&vmstate_pkru,
#endif
+ &vmstate_mcg_ext_ctl,
NULL
}
};