KVM: do not use sigtimedwait to catch SIGBUS

[mirror_qemu.git] / target / i386 / kvm.c

diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index 8e130ccf9c0aec0780ae807ad823ab56ca10432a..7698421ae7bf907269b5582f0e37fbffd0ae50f1 100644 (file)
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -64,13 +64,6 @@
  * 255 kvm_msr_entry structs */
 #define MSR_BUF_SIZE 4096
 
-#ifndef BUS_MCEERR_AR
-#define BUS_MCEERR_AR 4
-#endif
-#ifndef BUS_MCEERR_AO
-#define BUS_MCEERR_AO 5
-#endif
-
 const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
     KVM_CAP_INFO(SET_TSS_ADDR),
     KVM_CAP_INFO(EXT_CPUID),
@@ -462,70 +455,38 @@ static void hardware_memory_error(void)
     exit(1);
 }
 
-int kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
+void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
 {
     X86CPU *cpu = X86_CPU(c);
     CPUX86State *env = &cpu->env;
     ram_addr_t ram_addr;
     hwaddr paddr;
 
-    if ((env->mcg_cap & MCG_SER_P) && addr
-        && (code == BUS_MCEERR_AR || code == BUS_MCEERR_AO)) {
+    /* If we get an action required MCE, it has been injected by KVM
+     * while the VM was running.  An action optional MCE instead should
+     * be coming from the main thread, which qemu_init_sigbus identifies
+     * as the "early kill" thread.
+     */
+    assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
+
+    if ((env->mcg_cap & MCG_SER_P) && addr) {
         ram_addr = qemu_ram_addr_from_host(addr);
-        if (ram_addr == RAM_ADDR_INVALID ||
-            !kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
-            fprintf(stderr, "Hardware memory error for memory used by "
-                    "QEMU itself instead of guest system!\n");
-            /* Hope we are lucky for AO MCE */
-            if (code == BUS_MCEERR_AO) {
-                return 0;
-            } else {
-                hardware_memory_error();
-            }
-        }
-        kvm_hwpoison_page_add(ram_addr);
-        kvm_mce_inject(cpu, paddr, code);
-    } else {
-        if (code == BUS_MCEERR_AO) {
-            return 0;
-        } else if (code == BUS_MCEERR_AR) {
-            hardware_memory_error();
-        } else {
-            return 1;
+        if (ram_addr != RAM_ADDR_INVALID &&
+            kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
+            kvm_hwpoison_page_add(ram_addr);
+            kvm_mce_inject(cpu, paddr, code);
+            return;
         }
-    }
-    return 0;
-}
 
-int kvm_arch_on_sigbus(int code, void *addr)
-{
-    X86CPU *cpu = X86_CPU(first_cpu);
-
-    if ((cpu->env.mcg_cap & MCG_SER_P) && addr && code == BUS_MCEERR_AO) {
-        ram_addr_t ram_addr;
-        hwaddr paddr;
+        fprintf(stderr, "Hardware memory error for memory used by "
+                "QEMU itself instead of guest system!\n");
+    }
 
-        /* Hope we are lucky for AO MCE */
-        ram_addr = qemu_ram_addr_from_host(addr);
-        if (ram_addr == RAM_ADDR_INVALID ||
-            !kvm_physical_memory_addr_from_host(first_cpu->kvm_state,
-                                                addr, &paddr)) {
-            fprintf(stderr, "Hardware memory error for memory used by "
-                    "QEMU itself instead of guest system!: %p\n", addr);
-            return 0;
-        }
-        kvm_hwpoison_page_add(ram_addr);
-        kvm_mce_inject(X86_CPU(first_cpu), paddr, code);
-    } else {
-        if (code == BUS_MCEERR_AO) {
-            return 0;
-        } else if (code == BUS_MCEERR_AR) {
-            hardware_memory_error();
-        } else {
-            return 1;
-        }
+    if (code == BUS_MCEERR_AR) {
+        hardware_memory_error();
     }
-    return 0;
+
+    /* Hope we are lucky for AO MCE */
 }
 
 static int kvm_inject_mce_oldstyle(X86CPU *cpu)
@@ -982,12 +943,6 @@ int kvm_arch_init_vcpu(CPUState *cs)
         }
     }
 
-    cpuid_data.cpuid.padding = 0;
-    r = kvm_vcpu_ioctl(cs, KVM_SET_CPUID2, &cpuid_data);
-    if (r) {
-        goto fail;
-    }
-
     r = kvm_arch_set_tsc_khz(cs);
     if (r < 0) {
         goto fail;
@@ -1007,6 +962,36 @@ int kvm_arch_init_vcpu(CPUState *cs)
         }
     }
 
+    if (cpu->vmware_cpuid_freq
+        /* Guests depend on 0x40000000 to detect this feature, so only expose
+         * it if KVM exposes leaf 0x40000000. (Conflicts with Hyper-V) */
+        && cpu->expose_kvm
+        && kvm_base == KVM_CPUID_SIGNATURE
+        /* TSC clock must be stable and known for this feature. */
+        && ((env->features[FEAT_8000_0007_EDX] & CPUID_APM_INVTSC)
+            || env->user_tsc_khz != 0)
+        && env->tsc_khz != 0) {
+
+        c = &cpuid_data.entries[cpuid_i++];
+        c->function = KVM_CPUID_SIGNATURE | 0x10;
+        c->eax = env->tsc_khz;
+        /* LAPIC resolution of 1ns (freq: 1GHz) is hardcoded in KVM's
+         * APIC_BUS_CYCLE_NS */
+        c->ebx = 1000000;
+        c->ecx = c->edx = 0;
+
+        c = cpuid_find_entry(&cpuid_data.cpuid, kvm_base, 0);
+        c->eax = MAX(c->eax, KVM_CPUID_SIGNATURE | 0x10);
+    }
+
+    cpuid_data.cpuid.nent = cpuid_i;
+
+    cpuid_data.cpuid.padding = 0;
+    r = kvm_vcpu_ioctl(cs, KVM_SET_CPUID2, &cpuid_data);
+    if (r) {
+        goto fail;
+    }
+
     if (has_xsave) {
         env->kvm_xsave_buf = qemu_memalign(4096, sizeof(struct kvm_xsave));
     }