#include <linux/kvm.h>
#include "standard-headers/asm-x86/kvm_para.h"
-#include "qemu-common.h"
#include "cpu.h"
#include "sysemu/sysemu.h"
#include "sysemu/hw_accel.h"
static bool has_msr_spec_ctrl;
static bool has_msr_virt_ssbd;
static bool has_msr_smi_count;
+static bool has_msr_arch_capabs;
+static bool has_msr_core_capabs;
static uint32_t has_architectural_pmu_version;
static uint32_t num_architectural_pmu_gp_counters;
static bool has_msr_mcg_ext_ctl;
static struct kvm_cpuid2 *cpuid_cache;
+static struct kvm_msr_list *kvm_feature_msrs;
int kvm_has_pit_state2(void)
{
if (host_tsx_blacklisted()) {
ret &= ~(CPUID_7_0_EBX_RTM | CPUID_7_0_EBX_HLE);
}
+ } else if (function == 7 && index == 0 && reg == R_EDX) {
+ /*
+ * Linux v4.17-v4.20 incorrectly return ARCH_CAPABILITIES on SVM hosts.
+ * We can detect the bug by checking if MSR_IA32_ARCH_CAPABILITIES is
+ * returned by KVM_GET_MSR_INDEX_LIST.
+ */
+ if (!has_msr_arch_capabs) {
+ ret &= ~CPUID_7_0_EDX_ARCH_CAPABILITIES;
+ }
} else if (function == 0x80000001 && reg == R_ECX) {
/*
* It's safe to enable TOPOEXT even if it's not returned by
return ret;
}
+uint32_t kvm_arch_get_supported_msr_feature(KVMState *s, uint32_t index)
+{
+ struct {
+ struct kvm_msrs info;
+ struct kvm_msr_entry entries[1];
+ } msr_data;
+ uint32_t ret;
+
+ if (kvm_feature_msrs == NULL) { /* Host doesn't support feature MSRs */
+ return 0;
+ }
+
+ /* Check if requested MSR is supported feature MSR */
+ int i;
+ for (i = 0; i < kvm_feature_msrs->nmsrs; i++)
+ if (kvm_feature_msrs->indices[i] == index) {
+ break;
+ }
+ if (i == kvm_feature_msrs->nmsrs) {
+ return 0; /* if the feature MSR is not supported, simply return 0 */
+ }
+
+ msr_data.info.nmsrs = 1;
+ msr_data.entries[0].index = index;
+
+ ret = kvm_ioctl(s, KVM_GET_MSRS, &msr_data);
+ if (ret != 1) {
+ error_report("KVM get MSR (index=0x%x) feature failed, %s",
+ index, strerror(-ret));
+ exit(1);
+ }
+
+ return msr_data.entries[0].data;
+}
+
+
typedef struct HWPoisonPage {
ram_addr_t ram_addr;
QLIST_ENTRY(HWPoisonPage) list;
#define KVM_CPUID_SIGNATURE_NEXT 0x40000100
#endif
-static bool hyperv_hypercall_available(X86CPU *cpu)
-{
- return cpu->hyperv_vapic ||
- (cpu->hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_RETRY);
-}
-
static bool hyperv_enabled(X86CPU *cpu)
{
CPUState *cs = CPU(cpu);
return kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV) > 0 &&
- (hyperv_hypercall_available(cpu) ||
- cpu->hyperv_time ||
- cpu->hyperv_relaxed_timing ||
- cpu->hyperv_crash ||
- cpu->hyperv_reset ||
- cpu->hyperv_vpindex ||
- cpu->hyperv_runtime ||
- cpu->hyperv_synic ||
- cpu->hyperv_stimer ||
- cpu->hyperv_reenlightenment ||
- cpu->hyperv_tlbflush ||
- cpu->hyperv_ipi);
+ ((cpu->hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_RETRY) ||
+ cpu->hyperv_features || cpu->hyperv_passthrough);
}
static int kvm_arch_set_tsc_khz(CPUState *cs)
|| env->user_tsc_khz;
}
-static int hyperv_handle_properties(CPUState *cs)
+static struct {
+ const char *desc;
+ struct {
+ uint32_t fw;
+ uint32_t bits;
+ } flags[2];
+ uint64_t dependencies;
+} kvm_hyperv_properties[] = {
+ [HYPERV_FEAT_RELAXED] = {
+ .desc = "relaxed timing (hv-relaxed)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_HYPERCALL_AVAILABLE},
+ {.fw = FEAT_HV_RECOMM_EAX,
+ .bits = HV_RELAXED_TIMING_RECOMMENDED}
+ }
+ },
+ [HYPERV_FEAT_VAPIC] = {
+ .desc = "virtual APIC (hv-vapic)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_HYPERCALL_AVAILABLE | HV_APIC_ACCESS_AVAILABLE},
+ {.fw = FEAT_HV_RECOMM_EAX,
+ .bits = HV_APIC_ACCESS_RECOMMENDED}
+ }
+ },
+ [HYPERV_FEAT_TIME] = {
+ .desc = "clocksources (hv-time)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_HYPERCALL_AVAILABLE | HV_TIME_REF_COUNT_AVAILABLE |
+ HV_REFERENCE_TSC_AVAILABLE}
+ }
+ },
+ [HYPERV_FEAT_CRASH] = {
+ .desc = "crash MSRs (hv-crash)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EDX,
+ .bits = HV_GUEST_CRASH_MSR_AVAILABLE}
+ }
+ },
+ [HYPERV_FEAT_RESET] = {
+ .desc = "reset MSR (hv-reset)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_RESET_AVAILABLE}
+ }
+ },
+ [HYPERV_FEAT_VPINDEX] = {
+ .desc = "VP_INDEX MSR (hv-vpindex)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_VP_INDEX_AVAILABLE}
+ }
+ },
+ [HYPERV_FEAT_RUNTIME] = {
+ .desc = "VP_RUNTIME MSR (hv-runtime)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_VP_RUNTIME_AVAILABLE}
+ }
+ },
+ [HYPERV_FEAT_SYNIC] = {
+ .desc = "synthetic interrupt controller (hv-synic)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_SYNIC_AVAILABLE}
+ }
+ },
+ [HYPERV_FEAT_STIMER] = {
+ .desc = "synthetic timers (hv-stimer)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_SYNTIMERS_AVAILABLE}
+ },
+ .dependencies = BIT(HYPERV_FEAT_SYNIC) | BIT(HYPERV_FEAT_TIME)
+ },
+ [HYPERV_FEAT_FREQUENCIES] = {
+ .desc = "frequency MSRs (hv-frequencies)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_ACCESS_FREQUENCY_MSRS},
+ {.fw = FEAT_HYPERV_EDX,
+ .bits = HV_FREQUENCY_MSRS_AVAILABLE}
+ }
+ },
+ [HYPERV_FEAT_REENLIGHTENMENT] = {
+ .desc = "reenlightenment MSRs (hv-reenlightenment)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EAX,
+ .bits = HV_ACCESS_REENLIGHTENMENTS_CONTROL}
+ }
+ },
+ [HYPERV_FEAT_TLBFLUSH] = {
+ .desc = "paravirtualized TLB flush (hv-tlbflush)",
+ .flags = {
+ {.fw = FEAT_HV_RECOMM_EAX,
+ .bits = HV_REMOTE_TLB_FLUSH_RECOMMENDED |
+ HV_EX_PROCESSOR_MASKS_RECOMMENDED}
+ },
+ .dependencies = BIT(HYPERV_FEAT_VPINDEX)
+ },
+ [HYPERV_FEAT_EVMCS] = {
+ .desc = "enlightened VMCS (hv-evmcs)",
+ .flags = {
+ {.fw = FEAT_HV_RECOMM_EAX,
+ .bits = HV_ENLIGHTENED_VMCS_RECOMMENDED}
+ },
+ .dependencies = BIT(HYPERV_FEAT_VAPIC)
+ },
+ [HYPERV_FEAT_IPI] = {
+ .desc = "paravirtualized IPI (hv-ipi)",
+ .flags = {
+ {.fw = FEAT_HV_RECOMM_EAX,
+ .bits = HV_CLUSTER_IPI_RECOMMENDED |
+ HV_EX_PROCESSOR_MASKS_RECOMMENDED}
+ },
+ .dependencies = BIT(HYPERV_FEAT_VPINDEX)
+ },
+ [HYPERV_FEAT_STIMER_DIRECT] = {
+ .desc = "direct mode synthetic timers (hv-stimer-direct)",
+ .flags = {
+ {.fw = FEAT_HYPERV_EDX,
+ .bits = HV_STIMER_DIRECT_MODE_AVAILABLE}
+ },
+ .dependencies = BIT(HYPERV_FEAT_STIMER)
+ },
+};
+
+static struct kvm_cpuid2 *try_get_hv_cpuid(CPUState *cs, int max)
+{
+ struct kvm_cpuid2 *cpuid;
+ int r, size;
+
+ size = sizeof(*cpuid) + max * sizeof(*cpuid->entries);
+ cpuid = g_malloc0(size);
+ cpuid->nent = max;
+
+ r = kvm_vcpu_ioctl(cs, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+ if (r == 0 && cpuid->nent >= max) {
+ r = -E2BIG;
+ }
+ if (r < 0) {
+ if (r == -E2BIG) {
+ g_free(cpuid);
+ return NULL;
+ } else {
+ fprintf(stderr, "KVM_GET_SUPPORTED_HV_CPUID failed: %s\n",
+ strerror(-r));
+ exit(1);
+ }
+ }
+ return cpuid;
+}
+
+/*
+ * Run KVM_GET_SUPPORTED_HV_CPUID ioctl(), allocating a buffer large enough
+ * for all entries.
+ */
+static struct kvm_cpuid2 *get_supported_hv_cpuid(CPUState *cs)
+{
+ struct kvm_cpuid2 *cpuid;
+ int max = 7; /* 0x40000000..0x40000005, 0x4000000A */
+
+ /*
+ * When the buffer is too small, KVM_GET_SUPPORTED_HV_CPUID fails with
+ * -E2BIG, however, it doesn't report back the right size. Keep increasing
+ * it and re-trying until we succeed.
+ */
+ while ((cpuid = try_get_hv_cpuid(cs, max)) == NULL) {
+ max++;
+ }
+ return cpuid;
+}
+
+/*
+ * When KVM_GET_SUPPORTED_HV_CPUID is not supported we fill CPUID feature
+ * leaves from KVM_CAP_HYPERV* and present MSRs data.
+ */
+static struct kvm_cpuid2 *get_supported_hv_cpuid_legacy(CPUState *cs)
{
X86CPU *cpu = X86_CPU(cs);
- CPUX86State *env = &cpu->env;
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_cpuid_entry2 *entry_feat, *entry_recomm;
+
+ /* HV_CPUID_FEATURES, HV_CPUID_ENLIGHTMENT_INFO */
+ cpuid = g_malloc0(sizeof(*cpuid) + 2 * sizeof(*cpuid->entries));
+ cpuid->nent = 2;
+
+ /* HV_CPUID_VENDOR_AND_MAX_FUNCTIONS */
+ entry_feat = &cpuid->entries[0];
+ entry_feat->function = HV_CPUID_FEATURES;
- if (cpu->hyperv_relaxed_timing) {
- env->features[FEAT_HYPERV_EAX] |= HV_HYPERCALL_AVAILABLE;
+ entry_recomm = &cpuid->entries[1];
+ entry_recomm->function = HV_CPUID_ENLIGHTMENT_INFO;
+ entry_recomm->ebx = cpu->hyperv_spinlock_attempts;
+
+ if (kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV) > 0) {
+ entry_feat->eax |= HV_HYPERCALL_AVAILABLE;
+ entry_feat->eax |= HV_APIC_ACCESS_AVAILABLE;
+ entry_feat->edx |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE;
+ entry_recomm->eax |= HV_RELAXED_TIMING_RECOMMENDED;
+ entry_recomm->eax |= HV_APIC_ACCESS_RECOMMENDED;
}
- if (cpu->hyperv_vapic) {
- env->features[FEAT_HYPERV_EAX] |= HV_HYPERCALL_AVAILABLE;
- env->features[FEAT_HYPERV_EAX] |= HV_APIC_ACCESS_AVAILABLE;
+
+ if (kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV_TIME) > 0) {
+ entry_feat->eax |= HV_TIME_REF_COUNT_AVAILABLE;
+ entry_feat->eax |= HV_REFERENCE_TSC_AVAILABLE;
}
- if (cpu->hyperv_time) {
- if (kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV_TIME) <= 0) {
- fprintf(stderr, "Hyper-V clocksources "
- "(requested by 'hv-time' cpu flag) "
- "are not supported by kernel\n");
- return -ENOSYS;
- }
- env->features[FEAT_HYPERV_EAX] |= HV_HYPERCALL_AVAILABLE;
- env->features[FEAT_HYPERV_EAX] |= HV_TIME_REF_COUNT_AVAILABLE;
- env->features[FEAT_HYPERV_EAX] |= HV_REFERENCE_TSC_AVAILABLE;
+
+ if (has_msr_hv_frequencies) {
+ entry_feat->eax |= HV_ACCESS_FREQUENCY_MSRS;
+ entry_feat->edx |= HV_FREQUENCY_MSRS_AVAILABLE;
}
- if (cpu->hyperv_frequencies) {
- if (!has_msr_hv_frequencies) {
- fprintf(stderr, "Hyper-V frequency MSRs "
- "(requested by 'hv-frequencies' cpu flag) "
- "are not supported by kernel\n");
- return -ENOSYS;
- }
- env->features[FEAT_HYPERV_EAX] |= HV_ACCESS_FREQUENCY_MSRS;
- env->features[FEAT_HYPERV_EDX] |= HV_FREQUENCY_MSRS_AVAILABLE;
+
+ if (has_msr_hv_crash) {
+ entry_feat->edx |= HV_GUEST_CRASH_MSR_AVAILABLE;
}
- if (cpu->hyperv_crash) {
- if (!has_msr_hv_crash) {
- fprintf(stderr, "Hyper-V crash MSRs "
- "(requested by 'hv-crash' cpu flag) "
- "are not supported by kernel\n");
- return -ENOSYS;
- }
- env->features[FEAT_HYPERV_EDX] |= HV_GUEST_CRASH_MSR_AVAILABLE;
+
+ if (has_msr_hv_reenlightenment) {
+ entry_feat->eax |= HV_ACCESS_REENLIGHTENMENTS_CONTROL;
}
- if (cpu->hyperv_reenlightenment) {
- if (!has_msr_hv_reenlightenment) {
- fprintf(stderr,
- "Hyper-V Reenlightenment MSRs "
- "(requested by 'hv-reenlightenment' cpu flag) "
- "are not supported by kernel\n");
- return -ENOSYS;
+
+ if (has_msr_hv_reset) {
+ entry_feat->eax |= HV_RESET_AVAILABLE;
+ }
+
+ if (has_msr_hv_vpindex) {
+ entry_feat->eax |= HV_VP_INDEX_AVAILABLE;
+ }
+
+ if (has_msr_hv_runtime) {
+ entry_feat->eax |= HV_VP_RUNTIME_AVAILABLE;
+ }
+
+ if (has_msr_hv_synic) {
+ unsigned int cap = cpu->hyperv_synic_kvm_only ?
+ KVM_CAP_HYPERV_SYNIC : KVM_CAP_HYPERV_SYNIC2;
+
+ if (kvm_check_extension(cs->kvm_state, cap) > 0) {
+ entry_feat->eax |= HV_SYNIC_AVAILABLE;
}
- env->features[FEAT_HYPERV_EAX] |= HV_ACCESS_REENLIGHTENMENTS_CONTROL;
}
- env->features[FEAT_HYPERV_EDX] |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE;
- if (cpu->hyperv_reset) {
- if (!has_msr_hv_reset) {
- fprintf(stderr, "Hyper-V reset MSR "
- "(requested by 'hv-reset' cpu flag) "
- "is not supported by kernel\n");
- return -ENOSYS;
+
+ if (has_msr_hv_stimer) {
+ entry_feat->eax |= HV_SYNTIMERS_AVAILABLE;
+ }
+
+ if (kvm_check_extension(cs->kvm_state,
+ KVM_CAP_HYPERV_TLBFLUSH) > 0) {
+ entry_recomm->eax |= HV_REMOTE_TLB_FLUSH_RECOMMENDED;
+ entry_recomm->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
+ }
+
+ if (kvm_check_extension(cs->kvm_state,
+ KVM_CAP_HYPERV_ENLIGHTENED_VMCS) > 0) {
+ entry_recomm->eax |= HV_ENLIGHTENED_VMCS_RECOMMENDED;
+ }
+
+ if (kvm_check_extension(cs->kvm_state,
+ KVM_CAP_HYPERV_SEND_IPI) > 0) {
+ entry_recomm->eax |= HV_CLUSTER_IPI_RECOMMENDED;
+ entry_recomm->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
+ }
+
+ return cpuid;
+}
+
+static int hv_cpuid_get_fw(struct kvm_cpuid2 *cpuid, int fw, uint32_t *r)
+{
+ struct kvm_cpuid_entry2 *entry;
+ uint32_t func;
+ int reg;
+
+ switch (fw) {
+ case FEAT_HYPERV_EAX:
+ reg = R_EAX;
+ func = HV_CPUID_FEATURES;
+ break;
+ case FEAT_HYPERV_EDX:
+ reg = R_EDX;
+ func = HV_CPUID_FEATURES;
+ break;
+ case FEAT_HV_RECOMM_EAX:
+ reg = R_EAX;
+ func = HV_CPUID_ENLIGHTMENT_INFO;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ entry = cpuid_find_entry(cpuid, func, 0);
+ if (!entry) {
+ return -ENOENT;
+ }
+
+ switch (reg) {
+ case R_EAX:
+ *r = entry->eax;
+ break;
+ case R_EDX:
+ *r = entry->edx;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int hv_cpuid_check_and_set(CPUState *cs, struct kvm_cpuid2 *cpuid,
+ int feature)
+{
+ X86CPU *cpu = X86_CPU(cs);
+ CPUX86State *env = &cpu->env;
+ uint32_t r, fw, bits;
+ uint64_t deps;
+ int i, dep_feat = 0;
+
+ if (!hyperv_feat_enabled(cpu, feature) && !cpu->hyperv_passthrough) {
+ return 0;
+ }
+
+ deps = kvm_hyperv_properties[feature].dependencies;
+ while ((dep_feat = find_next_bit(&deps, 64, dep_feat)) < 64) {
+ if (!(hyperv_feat_enabled(cpu, dep_feat))) {
+ fprintf(stderr,
+ "Hyper-V %s requires Hyper-V %s\n",
+ kvm_hyperv_properties[feature].desc,
+ kvm_hyperv_properties[dep_feat].desc);
+ return 1;
}
- env->features[FEAT_HYPERV_EAX] |= HV_RESET_AVAILABLE;
+ dep_feat++;
}
- if (cpu->hyperv_vpindex) {
- if (!has_msr_hv_vpindex) {
- fprintf(stderr, "Hyper-V VP_INDEX MSR "
- "(requested by 'hv-vpindex' cpu flag) "
- "is not supported by kernel\n");
- return -ENOSYS;
+
+ for (i = 0; i < ARRAY_SIZE(kvm_hyperv_properties[feature].flags); i++) {
+ fw = kvm_hyperv_properties[feature].flags[i].fw;
+ bits = kvm_hyperv_properties[feature].flags[i].bits;
+
+ if (!fw) {
+ continue;
}
- env->features[FEAT_HYPERV_EAX] |= HV_VP_INDEX_AVAILABLE;
+
+ if (hv_cpuid_get_fw(cpuid, fw, &r) || (r & bits) != bits) {
+ if (hyperv_feat_enabled(cpu, feature)) {
+ fprintf(stderr,
+ "Hyper-V %s is not supported by kernel\n",
+ kvm_hyperv_properties[feature].desc);
+ return 1;
+ } else {
+ return 0;
+ }
+ }
+
+ env->features[fw] |= bits;
}
- if (cpu->hyperv_runtime) {
- if (!has_msr_hv_runtime) {
- fprintf(stderr, "Hyper-V VP_RUNTIME MSR "
- "(requested by 'hv-runtime' cpu flag) "
- "is not supported by kernel\n");
+
+ if (cpu->hyperv_passthrough) {
+ cpu->hyperv_features |= BIT(feature);
+ }
+
+ return 0;
+}
+
+/*
+ * Fill in Hyper-V CPUIDs. Returns the number of entries filled in cpuid_ent in
+ * case of success, errno < 0 in case of failure and 0 when no Hyper-V
+ * extentions are enabled.
+ */
+static int hyperv_handle_properties(CPUState *cs,
+ struct kvm_cpuid_entry2 *cpuid_ent)
+{
+ X86CPU *cpu = X86_CPU(cs);
+ CPUX86State *env = &cpu->env;
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_cpuid_entry2 *c;
+ uint32_t signature[3];
+ uint32_t cpuid_i = 0;
+ int r;
+
+ if (!hyperv_enabled(cpu))
+ return 0;
+
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS) ||
+ cpu->hyperv_passthrough) {
+ uint16_t evmcs_version;
+
+ r = kvm_vcpu_enable_cap(cs, KVM_CAP_HYPERV_ENLIGHTENED_VMCS, 0,
+ (uintptr_t)&evmcs_version);
+
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS) && r) {
+ fprintf(stderr, "Hyper-V %s is not supported by kernel\n",
+ kvm_hyperv_properties[HYPERV_FEAT_EVMCS].desc);
return -ENOSYS;
}
- env->features[FEAT_HYPERV_EAX] |= HV_VP_RUNTIME_AVAILABLE;
+
+ if (!r) {
+ env->features[FEAT_HV_RECOMM_EAX] |=
+ HV_ENLIGHTENED_VMCS_RECOMMENDED;
+ env->features[FEAT_HV_NESTED_EAX] = evmcs_version;
+ }
}
- if (cpu->hyperv_synic) {
- unsigned int cap = KVM_CAP_HYPERV_SYNIC;
- if (!cpu->hyperv_synic_kvm_only) {
- if (!cpu->hyperv_vpindex) {
- fprintf(stderr, "Hyper-V SynIC "
- "(requested by 'hv-synic' cpu flag) "
- "requires Hyper-V VP_INDEX ('hv-vpindex')\n");
- return -ENOSYS;
- }
- cap = KVM_CAP_HYPERV_SYNIC2;
+
+ if (kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV_CPUID) > 0) {
+ cpuid = get_supported_hv_cpuid(cs);
+ } else {
+ cpuid = get_supported_hv_cpuid_legacy(cs);
+ }
+
+ if (cpu->hyperv_passthrough) {
+ memcpy(cpuid_ent, &cpuid->entries[0],
+ cpuid->nent * sizeof(cpuid->entries[0]));
+
+ c = cpuid_find_entry(cpuid, HV_CPUID_FEATURES, 0);
+ if (c) {
+ env->features[FEAT_HYPERV_EAX] = c->eax;
+ env->features[FEAT_HYPERV_EBX] = c->ebx;
+ env->features[FEAT_HYPERV_EDX] = c->eax;
}
+ c = cpuid_find_entry(cpuid, HV_CPUID_ENLIGHTMENT_INFO, 0);
+ if (c) {
+ env->features[FEAT_HV_RECOMM_EAX] = c->eax;
- if (!has_msr_hv_synic || !kvm_check_extension(cs->kvm_state, cap)) {
- fprintf(stderr, "Hyper-V SynIC (requested by 'hv-synic' cpu flag) "
- "is not supported by kernel\n");
- return -ENOSYS;
+ /* hv-spinlocks may have been overriden */
+ if (cpu->hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_RETRY) {
+ c->ebx = cpu->hyperv_spinlock_attempts;
+ }
+ }
+ c = cpuid_find_entry(cpuid, HV_CPUID_NESTED_FEATURES, 0);
+ if (c) {
+ env->features[FEAT_HV_NESTED_EAX] = c->eax;
}
+ }
+
+ /* Features */
+ r = hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_RELAXED);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_VAPIC);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_TIME);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_CRASH);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_RESET);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_VPINDEX);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_RUNTIME);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_SYNIC);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_STIMER);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_FREQUENCIES);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_REENLIGHTENMENT);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_TLBFLUSH);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_EVMCS);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_IPI);
+ r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_STIMER_DIRECT);
+
+ /* Additional dependencies not covered by kvm_hyperv_properties[] */
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC) &&
+ !cpu->hyperv_synic_kvm_only &&
+ !hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX)) {
+ fprintf(stderr, "Hyper-V %s requires Hyper-V %s\n",
+ kvm_hyperv_properties[HYPERV_FEAT_SYNIC].desc,
+ kvm_hyperv_properties[HYPERV_FEAT_VPINDEX].desc);
+ r |= 1;
+ }
+
+ /* Not exposed by KVM but needed to make CPU hotplug in Windows work */
+ env->features[FEAT_HYPERV_EDX] |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE;
- env->features[FEAT_HYPERV_EAX] |= HV_SYNIC_AVAILABLE;
+ if (r) {
+ r = -ENOSYS;
+ goto free;
}
- if (cpu->hyperv_stimer) {
- if (!has_msr_hv_stimer) {
- fprintf(stderr, "Hyper-V timers aren't supported by kernel\n");
- return -ENOSYS;
+
+ if (cpu->hyperv_passthrough) {
+ /* We already copied all feature words from KVM as is */
+ r = cpuid->nent;
+ goto free;
+ }
+
+ c = &cpuid_ent[cpuid_i++];
+ c->function = HV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+ if (!cpu->hyperv_vendor_id) {
+ memcpy(signature, "Microsoft Hv", 12);
+ } else {
+ size_t len = strlen(cpu->hyperv_vendor_id);
+
+ if (len > 12) {
+ error_report("hv-vendor-id truncated to 12 characters");
+ len = 12;
}
- env->features[FEAT_HYPERV_EAX] |= HV_SYNTIMERS_AVAILABLE;
+ memset(signature, 0, 12);
+ memcpy(signature, cpu->hyperv_vendor_id, len);
+ }
+ c->eax = hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS) ?
+ HV_CPUID_NESTED_FEATURES : HV_CPUID_IMPLEMENT_LIMITS;
+ c->ebx = signature[0];
+ c->ecx = signature[1];
+ c->edx = signature[2];
+
+ c = &cpuid_ent[cpuid_i++];
+ c->function = HV_CPUID_INTERFACE;
+ memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12);
+ c->eax = signature[0];
+ c->ebx = 0;
+ c->ecx = 0;
+ c->edx = 0;
+
+ c = &cpuid_ent[cpuid_i++];
+ c->function = HV_CPUID_VERSION;
+ c->eax = 0x00001bbc;
+ c->ebx = 0x00060001;
+
+ c = &cpuid_ent[cpuid_i++];
+ c->function = HV_CPUID_FEATURES;
+ c->eax = env->features[FEAT_HYPERV_EAX];
+ c->ebx = env->features[FEAT_HYPERV_EBX];
+ c->edx = env->features[FEAT_HYPERV_EDX];
+
+ c = &cpuid_ent[cpuid_i++];
+ c->function = HV_CPUID_ENLIGHTMENT_INFO;
+ c->eax = env->features[FEAT_HV_RECOMM_EAX];
+ c->ebx = cpu->hyperv_spinlock_attempts;
+
+ c = &cpuid_ent[cpuid_i++];
+ c->function = HV_CPUID_IMPLEMENT_LIMITS;
+ c->eax = cpu->hv_max_vps;
+ c->ebx = 0x40;
+
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS)) {
+ __u32 function;
+
+ /* Create zeroed 0x40000006..0x40000009 leaves */
+ for (function = HV_CPUID_IMPLEMENT_LIMITS + 1;
+ function < HV_CPUID_NESTED_FEATURES; function++) {
+ c = &cpuid_ent[cpuid_i++];
+ c->function = function;
+ }
+
+ c = &cpuid_ent[cpuid_i++];
+ c->function = HV_CPUID_NESTED_FEATURES;
+ c->eax = env->features[FEAT_HV_NESTED_EAX];
}
- return 0;
+ r = cpuid_i;
+
+free:
+ g_free(cpuid);
+
+ return r;
}
+static Error *hv_passthrough_mig_blocker;
+
static int hyperv_init_vcpu(X86CPU *cpu)
{
CPUState *cs = CPU(cpu);
+ Error *local_err = NULL;
int ret;
- if (cpu->hyperv_vpindex && !hv_vpindex_settable) {
+ if (cpu->hyperv_passthrough && hv_passthrough_mig_blocker == NULL) {
+ error_setg(&hv_passthrough_mig_blocker,
+ "'hv-passthrough' CPU flag prevents migration, use explicit"
+ " set of hv-* flags instead");
+ ret = migrate_add_blocker(hv_passthrough_mig_blocker, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ error_free(hv_passthrough_mig_blocker);
+ return ret;
+ }
+ }
+
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX) && !hv_vpindex_settable) {
/*
* the kernel doesn't support setting vp_index; assert that its value
* is in sync
}
}
- if (cpu->hyperv_synic) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC)) {
uint32_t synic_cap = cpu->hyperv_synic_kvm_only ?
KVM_CAP_HYPERV_SYNIC : KVM_CAP_HYPERV_SYNIC2;
ret = kvm_vcpu_enable_cap(cs, synic_cap, 0);
}
static Error *invtsc_mig_blocker;
+static Error *vmx_mig_blocker;
#define KVM_MAX_CPUID_ENTRIES 100
struct {
struct kvm_cpuid2 cpuid;
struct kvm_cpuid_entry2 entries[KVM_MAX_CPUID_ENTRIES];
- } QEMU_PACKED cpuid_data;
+ } cpuid_data;
+ /*
+ * The kernel defines these structs with padding fields so there
+ * should be no extra padding in our cpuid_data struct.
+ */
+ QEMU_BUILD_BUG_ON(sizeof(cpuid_data) !=
+ sizeof(struct kvm_cpuid2) +
+ sizeof(struct kvm_cpuid_entry2) * KVM_MAX_CPUID_ENTRIES);
+
X86CPU *cpu = X86_CPU(cs);
CPUX86State *env = &cpu->env;
uint32_t limit, i, j, cpuid_i;
r = kvm_arch_set_tsc_khz(cs);
if (r < 0) {
- goto fail;
+ return r;
}
/* vcpu's TSC frequency is either specified by user, or following
}
/* Paravirtualization CPUIDs */
- if (hyperv_enabled(cpu)) {
- c = &cpuid_data.entries[cpuid_i++];
- c->function = HV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
- if (!cpu->hyperv_vendor_id) {
- memcpy(signature, "Microsoft Hv", 12);
- } else {
- size_t len = strlen(cpu->hyperv_vendor_id);
-
- if (len > 12) {
- error_report("hv-vendor-id truncated to 12 characters");
- len = 12;
- }
- memset(signature, 0, 12);
- memcpy(signature, cpu->hyperv_vendor_id, len);
- }
- c->eax = HV_CPUID_MIN;
- c->ebx = signature[0];
- c->ecx = signature[1];
- c->edx = signature[2];
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = HV_CPUID_INTERFACE;
- memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12);
- c->eax = signature[0];
- c->ebx = 0;
- c->ecx = 0;
- c->edx = 0;
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = HV_CPUID_VERSION;
- c->eax = 0x00001bbc;
- c->ebx = 0x00060001;
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = HV_CPUID_FEATURES;
- r = hyperv_handle_properties(cs);
- if (r) {
- return r;
- }
- c->eax = env->features[FEAT_HYPERV_EAX];
- c->ebx = env->features[FEAT_HYPERV_EBX];
- c->edx = env->features[FEAT_HYPERV_EDX];
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = HV_CPUID_ENLIGHTMENT_INFO;
- if (cpu->hyperv_relaxed_timing) {
- c->eax |= HV_RELAXED_TIMING_RECOMMENDED;
- }
- if (cpu->hyperv_vapic) {
- c->eax |= HV_APIC_ACCESS_RECOMMENDED;
- }
- if (cpu->hyperv_tlbflush) {
- if (kvm_check_extension(cs->kvm_state,
- KVM_CAP_HYPERV_TLBFLUSH) <= 0) {
- fprintf(stderr, "Hyper-V TLB flush support "
- "(requested by 'hv-tlbflush' cpu flag) "
- " is not supported by kernel\n");
- return -ENOSYS;
- }
- c->eax |= HV_REMOTE_TLB_FLUSH_RECOMMENDED;
- c->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
- }
- if (cpu->hyperv_ipi) {
- if (kvm_check_extension(cs->kvm_state,
- KVM_CAP_HYPERV_SEND_IPI) <= 0) {
- fprintf(stderr, "Hyper-V IPI send support "
- "(requested by 'hv-ipi' cpu flag) "
- " is not supported by kernel\n");
- return -ENOSYS;
- }
- c->eax |= HV_CLUSTER_IPI_RECOMMENDED;
- c->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
- }
-
- c->ebx = cpu->hyperv_spinlock_attempts;
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = HV_CPUID_IMPLEMENT_LIMITS;
-
- c->eax = cpu->hv_max_vps;
- c->ebx = 0x40;
-
+ r = hyperv_handle_properties(cs, cpuid_data.entries);
+ if (r < 0) {
+ return r;
+ } else if (r > 0) {
+ cpuid_i = r;
kvm_base = KVM_CPUID_SIGNATURE_NEXT;
has_msr_hv_hypercall = true;
}
!!(c->ecx & CPUID_EXT_SMX);
}
+ if ((env->features[FEAT_1_ECX] & CPUID_EXT_VMX) && !vmx_mig_blocker) {
+ error_setg(&vmx_mig_blocker,
+ "Nested VMX virtualization does not support live migration yet");
+ r = migrate_add_blocker(vmx_mig_blocker, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ error_free(vmx_mig_blocker);
+ return r;
+ }
+ }
+
if (env->mcg_cap & MCG_LMCE_P) {
has_msr_mcg_ext_ctl = has_msr_feature_control = true;
}
if (!env->user_tsc_khz) {
if ((env->features[FEAT_8000_0007_EDX] & CPUID_APM_INVTSC) &&
invtsc_mig_blocker == NULL) {
- /* for migration */
error_setg(&invtsc_mig_blocker,
"State blocked by non-migratable CPU device"
" (invtsc flag)");
if (local_err) {
error_report_err(local_err);
error_free(invtsc_mig_blocker);
- goto fail;
+ goto fail2;
}
- /* for savevm */
- vmstate_x86_cpu.unmigratable = 1;
}
}
fail:
migrate_del_blocker(invtsc_mig_blocker);
+ fail2:
+ migrate_del_blocker(vmx_mig_blocker);
+
return r;
}
+int kvm_arch_destroy_vcpu(CPUState *cs)
+{
+ X86CPU *cpu = X86_CPU(cs);
+
+ if (cpu->kvm_msr_buf) {
+ g_free(cpu->kvm_msr_buf);
+ cpu->kvm_msr_buf = NULL;
+ }
+
+ return 0;
+}
+
void kvm_arch_reset_vcpu(X86CPU *cpu)
{
CPUX86State *env = &cpu->env;
env->mp_state = KVM_MP_STATE_RUNNABLE;
}
- if (cpu->hyperv_synic) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC)) {
int i;
for (i = 0; i < ARRAY_SIZE(env->msr_hv_synic_sint); i++) {
env->msr_hv_synic_sint[i] = HV_SINT_MASKED;
}
}
+static int kvm_get_supported_feature_msrs(KVMState *s)
+{
+ int ret = 0;
+
+ if (kvm_feature_msrs != NULL) {
+ return 0;
+ }
+
+ if (!kvm_check_extension(s, KVM_CAP_GET_MSR_FEATURES)) {
+ return 0;
+ }
+
+ struct kvm_msr_list msr_list;
+
+ msr_list.nmsrs = 0;
+ ret = kvm_ioctl(s, KVM_GET_MSR_FEATURE_INDEX_LIST, &msr_list);
+ if (ret < 0 && ret != -E2BIG) {
+ error_report("Fetch KVM feature MSR list failed: %s",
+ strerror(-ret));
+ return ret;
+ }
+
+ assert(msr_list.nmsrs > 0);
+ kvm_feature_msrs = (struct kvm_msr_list *) \
+ g_malloc0(sizeof(msr_list) +
+ msr_list.nmsrs * sizeof(msr_list.indices[0]));
+
+ kvm_feature_msrs->nmsrs = msr_list.nmsrs;
+ ret = kvm_ioctl(s, KVM_GET_MSR_FEATURE_INDEX_LIST, kvm_feature_msrs);
+
+ if (ret < 0) {
+ error_report("Fetch KVM feature MSR list failed: %s",
+ strerror(-ret));
+ g_free(kvm_feature_msrs);
+ kvm_feature_msrs = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
static int kvm_get_supported_msrs(KVMState *s)
{
static int kvm_supported_msrs;
case MSR_VIRT_SSBD:
has_msr_virt_ssbd = true;
break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ has_msr_arch_capabs = true;
+ break;
+ case MSR_IA32_CORE_CAPABILITY:
+ has_msr_core_capabs = true;
+ break;
}
}
}
return ret;
}
+ kvm_get_supported_feature_msrs(s);
+
uname(&utsname);
lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;
}
#endif
+ /* If host supports feature MSR, write down. */
+ if (has_msr_arch_capabs) {
+ kvm_msr_entry_add(cpu, MSR_IA32_ARCH_CAPABILITIES,
+ env->features[FEAT_ARCH_CAPABILITIES]);
+ }
+
+ if (has_msr_core_capabs) {
+ kvm_msr_entry_add(cpu, MSR_IA32_CORE_CAPABILITY,
+ env->features[FEAT_CORE_CAPABILITY]);
+ }
+
/*
* The following MSRs have side effects on the guest or are too heavy
* for normal writeback. Limit them to reset or full state updates.
kvm_msr_entry_add(cpu, HV_X64_MSR_HYPERCALL,
env->msr_hv_hypercall);
}
- if (cpu->hyperv_time) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_TIME)) {
kvm_msr_entry_add(cpu, HV_X64_MSR_REFERENCE_TSC,
env->msr_hv_tsc);
}
- if (cpu->hyperv_reenlightenment) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_REENLIGHTENMENT)) {
kvm_msr_entry_add(cpu, HV_X64_MSR_REENLIGHTENMENT_CONTROL,
env->msr_hv_reenlightenment_control);
kvm_msr_entry_add(cpu, HV_X64_MSR_TSC_EMULATION_CONTROL,
env->msr_hv_tsc_emulation_status);
}
}
- if (cpu->hyperv_vapic) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_VAPIC)) {
kvm_msr_entry_add(cpu, HV_X64_MSR_APIC_ASSIST_PAGE,
env->msr_hv_vapic);
}
if (has_msr_hv_runtime) {
kvm_msr_entry_add(cpu, HV_X64_MSR_VP_RUNTIME, env->msr_hv_runtime);
}
- if (cpu->hyperv_vpindex && hv_vpindex_settable) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX)
+ && hv_vpindex_settable) {
kvm_msr_entry_add(cpu, HV_X64_MSR_VP_INDEX,
hyperv_vp_index(CPU(cpu)));
}
- if (cpu->hyperv_synic) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC)) {
int j;
kvm_msr_entry_add(cpu, HV_X64_MSR_SVERSION, HV_SYNIC_VERSION);
kvm_msr_entry_add(cpu, HV_X64_MSR_HYPERCALL, 0);
kvm_msr_entry_add(cpu, HV_X64_MSR_GUEST_OS_ID, 0);
}
- if (cpu->hyperv_vapic) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_VAPIC)) {
kvm_msr_entry_add(cpu, HV_X64_MSR_APIC_ASSIST_PAGE, 0);
}
- if (cpu->hyperv_time) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_TIME)) {
kvm_msr_entry_add(cpu, HV_X64_MSR_REFERENCE_TSC, 0);
}
- if (cpu->hyperv_reenlightenment) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_REENLIGHTENMENT)) {
kvm_msr_entry_add(cpu, HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0);
kvm_msr_entry_add(cpu, HV_X64_MSR_TSC_EMULATION_CONTROL, 0);
kvm_msr_entry_add(cpu, HV_X64_MSR_TSC_EMULATION_STATUS, 0);
if (has_msr_hv_runtime) {
kvm_msr_entry_add(cpu, HV_X64_MSR_VP_RUNTIME, 0);
}
- if (cpu->hyperv_synic) {
+ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC)) {
uint32_t msr;
kvm_msr_entry_add(cpu, HV_X64_MSR_SCONTROL, 0);
static void kvm_update_msi_routes_all(void *private, bool global,
uint32_t index, uint32_t mask)
{
- int cnt = 0;
+ int cnt = 0, vector;
MSIRouteEntry *entry;
MSIMessage msg;
PCIDevice *dev;
/* TODO: explicit route update */
QLIST_FOREACH(entry, &msi_route_list, list) {
cnt++;
+ vector = entry->vector;
dev = entry->dev;
- if (!msix_enabled(dev) && !msi_enabled(dev)) {
+ if (msix_enabled(dev) && !msix_is_masked(dev, vector)) {
+ msg = msix_get_message(dev, vector);
+ } else if (msi_enabled(dev) && !msi_is_masked(dev, vector)) {
+ msg = msi_get_message(dev, vector);
+ } else {
+ /*
+ * Either MSI/MSIX is disabled for the device, or the
+ * specific message was masked out. Skip this one.
+ */
continue;
}
- msg = pci_get_msi_message(dev, entry->vector);
kvm_irqchip_update_msi_route(kvm_state, entry->virq, msg, dev);
}
kvm_irqchip_commit_routes(kvm_state);