[Qemu-devel] [PATCH v4 1/3] target-i386: KVM: add basic Intel LMCE support

[Haozhong Zhang]

From: Ashok Raj <address@hidden>

This patch adds the support to inject SRAR and SRAO as LMCE, i.e. they
are injected to only one VCPU rather than broadcast to all VCPUs. As KVM
reports LMCE support on Intel platforms, this features is only available
on Intel platforms.

LMCE is disabled by default and can be enabled/disabled by cpu option
'lmce=on/off'.

Signed-off-by: Ashok Raj <address@hidden>
[Haozhong: Enable LMCE only on Intel platforms
           Disable LMCE by default and add a cpu option 'lmce'
           Disable LMCE if missing KVM support
           Remove MCG_LMCE_P from MCE_CAP_DEF
           Minor code style changes]
Signed-off-by: Haozhong Zhang <address@hidden>
---
 target-i386/cpu.c | 23 +++++++++++++++++++++++
 target-i386/cpu.h | 12 ++++++++++++
 target-i386/kvm.c | 35 +++++++++++++++++++++++++++++++----
 3 files changed, 66 insertions(+), 4 deletions(-)

diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index 895a386..bd35db2 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -2777,15 +2777,37 @@ static void x86_cpu_machine_reset_cb(void *opaque)
 }
 #endif
 
+static bool lmce_supported(void)
+{
+    uint64_t mce_cap;
+
+    if (!kvm_enabled() ||
+        kvm_ioctl(kvm_state, KVM_X86_GET_MCE_CAP_SUPPORTED, &mce_cap) < 0) {
+        return false;
+    }
+
+    return !!(mce_cap & MCG_LMCE_P);
+}
+
 static void mce_init(X86CPU *cpu)
 {
     CPUX86State *cenv = &cpu->env;
     unsigned int bank;
+    Error *local_err = NULL;
 
     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;
+
+        if (cpu->enable_lmce) {
+            if (!lmce_supported()) {
+                error_setg(&local_err, "KVM unavailable or LMCE not 
supported");
+                error_propagate(&error_abort, local_err);
+            }
+            cenv->mcg_cap |= MCG_LMCE_P;
+        }
+
         cenv->mcg_ctl = ~(uint64_t)0;
         for (bank = 0; bank < MCE_BANKS_DEF; bank++) {
             cenv->mce_banks[bank * 4] = ~(uint64_t)0;
@@ -3206,6 +3228,7 @@ static Property x86_cpu_properties[] = {
     DEFINE_PROP_UINT32("xlevel", X86CPU, env.cpuid_xlevel, 0),
     DEFINE_PROP_UINT32("xlevel2", X86CPU, env.cpuid_xlevel2, 0),
     DEFINE_PROP_STRING("hv-vendor-id", X86CPU, hyperv_vendor_id),
+    DEFINE_PROP_BOOL("lmce", X86CPU, enable_lmce, false),
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 0426459..f0cb04f 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -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
 
@@ -1106,6 +1111,7 @@ 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;
@@ -1173,6 +1179,12 @@ 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;
+
     /* in order to simplify APIC support, we leave this pointer to the
        user */
     struct DeviceState *apic_state;
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index abf50e6..ea442b3 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -107,6 +107,8 @@ static int has_xsave;
 static int has_xcrs;
 static int has_pit_state2;
 
+static bool has_msr_mcg_ext_ctl;
+
 int kvm_has_pit_state2(void)
 {
     return has_pit_state2;
@@ -378,10 +380,12 @@ 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;
@@ -390,10 +394,19 @@ 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)
@@ -878,7 +891,12 @@ int kvm_arch_init_vcpu(CPUState *cs)
     c = cpuid_find_entry(&cpuid_data.cpuid, 1, 0);
     if (c) {
         has_msr_feature_control = !!(c->ecx & CPUID_EXT_VMX) ||
-                                  !!(c->ecx & CPUID_EXT_SMX);
+                                  !!(c->ecx & CPUID_EXT_SMX) ||
+                                  !!(env->mcg_cap & MCG_LMCE_P);
+    }
+
+    if (has_msr_feature_control && (env->mcg_cap & MCG_LMCE_P)) {
+        has_msr_mcg_ext_ctl = true;
     }
 
     c = cpuid_find_entry(&cpuid_data.cpuid, 0x80000007, 0);
@@ -1702,6 +1720,9 @@ 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]);
         }
@@ -2005,6 +2026,9 @@ 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);
         }
@@ -2133,6 +2157,9 @@ 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;
-- 
2.9.0