diff options
Diffstat (limited to 'target/i386/kvm/kvm.c')
| -rw-r--r-- | target/i386/kvm/kvm.c | 478 |
1 files changed, 263 insertions, 215 deletions
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index e68cbe9293..c5943605ee 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -31,6 +31,7 @@ #include "sysemu/kvm_int.h" #include "sysemu/runstate.h" #include "kvm_i386.h" +#include "../confidential-guest.h" #include "sev.h" #include "xen-emu.h" #include "hyperv.h" @@ -161,6 +162,51 @@ static KVMMSRHandlers msr_handlers[KVM_MSR_FILTER_MAX_RANGES]; static RateLimit bus_lock_ratelimit_ctrl; static int kvm_get_one_msr(X86CPU *cpu, int index, uint64_t *value); +static const char *vm_type_name[] = { + [KVM_X86_DEFAULT_VM] = "default", + [KVM_X86_SEV_VM] = "SEV", + [KVM_X86_SEV_ES_VM] = "SEV-ES", +}; + +bool kvm_is_vm_type_supported(int type) +{ + uint32_t machine_types; + + /* + * old KVM doesn't support KVM_CAP_VM_TYPES but KVM_X86_DEFAULT_VM + * is always supported + */ + if (type == KVM_X86_DEFAULT_VM) { + return true; + } + + machine_types = kvm_check_extension(KVM_STATE(current_machine->accelerator), + KVM_CAP_VM_TYPES); + return !!(machine_types & BIT(type)); +} + +int kvm_get_vm_type(MachineState *ms) +{ + int kvm_type = KVM_X86_DEFAULT_VM; + + if (ms->cgs) { + if (!object_dynamic_cast(OBJECT(ms->cgs), TYPE_X86_CONFIDENTIAL_GUEST)) { + error_report("configuration type %s not supported for x86 guests", + object_get_typename(OBJECT(ms->cgs))); + exit(1); + } + kvm_type = x86_confidential_guest_kvm_type( + X86_CONFIDENTIAL_GUEST(ms->cgs)); + } + + if (!kvm_is_vm_type_supported(kvm_type)) { + error_report("vm-type %s not supported by KVM", vm_type_name[kvm_type]); + exit(1); + } + + return kvm_type; +} + bool kvm_has_smm(void) { return kvm_vm_check_extension(kvm_state, KVM_CAP_X86_SMM); @@ -1706,195 +1752,22 @@ static void kvm_init_nested_state(CPUX86State *env) } } -int kvm_arch_init_vcpu(CPUState *cs) +static uint32_t kvm_x86_build_cpuid(CPUX86State *env, + struct kvm_cpuid_entry2 *entries, + uint32_t cpuid_i) { - struct { - struct kvm_cpuid2 cpuid; - struct kvm_cpuid_entry2 entries[KVM_MAX_CPUID_ENTRIES]; - } 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; + uint32_t limit, i, j; uint32_t unused; struct kvm_cpuid_entry2 *c; - uint32_t signature[3]; - int kvm_base = KVM_CPUID_SIGNATURE; - int max_nested_state_len; - int r; - Error *local_err = NULL; - - memset(&cpuid_data, 0, sizeof(cpuid_data)); - - cpuid_i = 0; - - has_xsave2 = kvm_check_extension(cs->kvm_state, KVM_CAP_XSAVE2); - - r = kvm_arch_set_tsc_khz(cs); - if (r < 0) { - return r; - } - - /* vcpu's TSC frequency is either specified by user, or following - * the value used by KVM if the former is not present. In the - * latter case, we query it from KVM and record in env->tsc_khz, - * so that vcpu's TSC frequency can be migrated later via this field. - */ - if (!env->tsc_khz) { - r = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ? - kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) : - -ENOTSUP; - if (r > 0) { - env->tsc_khz = r; - } - } - - env->apic_bus_freq = KVM_APIC_BUS_FREQUENCY; - - /* - * kvm_hyperv_expand_features() is called here for the second time in case - * KVM_CAP_SYS_HYPERV_CPUID is not supported. While we can't possibly handle - * 'query-cpu-model-expansion' in this case as we don't have a KVM vCPU to - * check which Hyper-V enlightenments are supported and which are not, we - * can still proceed and check/expand Hyper-V enlightenments here so legacy - * behavior is preserved. - */ - if (!kvm_hyperv_expand_features(cpu, &local_err)) { - error_report_err(local_err); - return -ENOSYS; - } - - if (hyperv_enabled(cpu)) { - r = hyperv_init_vcpu(cpu); - if (r) { - return r; - } - - cpuid_i = hyperv_fill_cpuids(cs, cpuid_data.entries); - kvm_base = KVM_CPUID_SIGNATURE_NEXT; - has_msr_hv_hypercall = true; - } - - if (cs->kvm_state->xen_version) { -#ifdef CONFIG_XEN_EMU - struct kvm_cpuid_entry2 *xen_max_leaf; - - memcpy(signature, "XenVMMXenVMM", 12); - - xen_max_leaf = c = &cpuid_data.entries[cpuid_i++]; - c->function = kvm_base + XEN_CPUID_SIGNATURE; - c->eax = kvm_base + XEN_CPUID_TIME; - c->ebx = signature[0]; - c->ecx = signature[1]; - c->edx = signature[2]; - - c = &cpuid_data.entries[cpuid_i++]; - c->function = kvm_base + XEN_CPUID_VENDOR; - c->eax = cs->kvm_state->xen_version; - c->ebx = 0; - c->ecx = 0; - c->edx = 0; - - c = &cpuid_data.entries[cpuid_i++]; - c->function = kvm_base + XEN_CPUID_HVM_MSR; - /* Number of hypercall-transfer pages */ - c->eax = 1; - /* Hypercall MSR base address */ - if (hyperv_enabled(cpu)) { - c->ebx = XEN_HYPERCALL_MSR_HYPERV; - kvm_xen_init(cs->kvm_state, c->ebx); - } else { - c->ebx = XEN_HYPERCALL_MSR; - } - c->ecx = 0; - c->edx = 0; - - c = &cpuid_data.entries[cpuid_i++]; - c->function = kvm_base + XEN_CPUID_TIME; - c->eax = ((!!tsc_is_stable_and_known(env) << 1) | - (!!(env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_RDTSCP) << 2)); - /* default=0 (emulate if necessary) */ - c->ebx = 0; - /* guest tsc frequency */ - c->ecx = env->user_tsc_khz; - /* guest tsc incarnation (migration count) */ - c->edx = 0; - - c = &cpuid_data.entries[cpuid_i++]; - c->function = kvm_base + XEN_CPUID_HVM; - xen_max_leaf->eax = kvm_base + XEN_CPUID_HVM; - if (cs->kvm_state->xen_version >= XEN_VERSION(4, 5)) { - c->function = kvm_base + XEN_CPUID_HVM; - - if (cpu->xen_vapic) { - c->eax |= XEN_HVM_CPUID_APIC_ACCESS_VIRT; - c->eax |= XEN_HVM_CPUID_X2APIC_VIRT; - } - - c->eax |= XEN_HVM_CPUID_IOMMU_MAPPINGS; - - if (cs->kvm_state->xen_version >= XEN_VERSION(4, 6)) { - c->eax |= XEN_HVM_CPUID_VCPU_ID_PRESENT; - c->ebx = cs->cpu_index; - } - - if (cs->kvm_state->xen_version >= XEN_VERSION(4, 17)) { - c->eax |= XEN_HVM_CPUID_UPCALL_VECTOR; - } - } - - r = kvm_xen_init_vcpu(cs); - if (r) { - return r; - } - - kvm_base += 0x100; -#else /* CONFIG_XEN_EMU */ - /* This should never happen as kvm_arch_init() would have died first. */ - fprintf(stderr, "Cannot enable Xen CPUID without Xen support\n"); - abort(); -#endif - } else if (cpu->expose_kvm) { - memcpy(signature, "KVMKVMKVM\0\0\0", 12); - c = &cpuid_data.entries[cpuid_i++]; - c->function = KVM_CPUID_SIGNATURE | kvm_base; - c->eax = KVM_CPUID_FEATURES | kvm_base; - c->ebx = signature[0]; - c->ecx = signature[1]; - c->edx = signature[2]; - - c = &cpuid_data.entries[cpuid_i++]; - c->function = KVM_CPUID_FEATURES | kvm_base; - c->eax = env->features[FEAT_KVM]; - c->edx = env->features[FEAT_KVM_HINTS]; - } cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused); - if (cpu->kvm_pv_enforce_cpuid) { - r = kvm_vcpu_enable_cap(cs, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 0, 1); - if (r < 0) { - fprintf(stderr, - "failed to enable KVM_CAP_ENFORCE_PV_FEATURE_CPUID: %s", - strerror(-r)); - abort(); - } - } - for (i = 0; i <= limit; i++) { + j = 0; if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "unsupported level value: 0x%x\n", limit); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; - + c = &entries[cpuid_i++]; switch (i) { case 2: { /* Keep reading function 2 till all the input is received */ @@ -1908,11 +1781,9 @@ int kvm_arch_init_vcpu(CPUState *cs) for (j = 1; j < times; ++j) { if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "cpuid_data is full, no space for " - "cpuid(eax:2):eax & 0xf = 0x%x\n", times); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; + c = &entries[cpuid_i++]; c->function = i; c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC; cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); @@ -1951,11 +1822,9 @@ int kvm_arch_init_vcpu(CPUState *cs) continue; } if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "cpuid_data is full, no space for " - "cpuid(eax:0x%x,ecx:0x%x)\n", i, j); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; + c = &entries[cpuid_i++]; } break; case 0x12: @@ -1970,11 +1839,9 @@ int kvm_arch_init_vcpu(CPUState *cs) } if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "cpuid_data is full, no space for " - "cpuid(eax:0x12,ecx:0x%x)\n", j); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; + c = &entries[cpuid_i++]; } break; case 0x7: @@ -1991,11 +1858,9 @@ int kvm_arch_init_vcpu(CPUState *cs) for (j = 1; j <= times; ++j) { if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "cpuid_data is full, no space for " - "cpuid(eax:0x%x,ecx:0x%x)\n", i, j); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; + c = &entries[cpuid_i++]; c->function = i; c->index = j; c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; @@ -2048,11 +1913,11 @@ int kvm_arch_init_vcpu(CPUState *cs) cpu_x86_cpuid(env, 0x80000000, 0, &limit, &unused, &unused, &unused); for (i = 0x80000000; i <= limit; i++) { + j = 0; if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "unsupported xlevel value: 0x%x\n", limit); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; + c = &entries[cpuid_i++]; switch (i) { case 0x8000001d: @@ -2067,11 +1932,9 @@ int kvm_arch_init_vcpu(CPUState *cs) break; } if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "cpuid_data is full, no space for " - "cpuid(eax:0x%x,ecx:0x%x)\n", i, j); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; + c = &entries[cpuid_i++]; } break; default: @@ -2094,11 +1957,11 @@ int kvm_arch_init_vcpu(CPUState *cs) cpu_x86_cpuid(env, 0xC0000000, 0, &limit, &unused, &unused, &unused); for (i = 0xC0000000; i <= limit; i++) { + j = 0; if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "unsupported xlevel2 value: 0x%x\n", limit); - abort(); + goto full; } - c = &cpuid_data.entries[cpuid_i++]; + c = &entries[cpuid_i++]; c->function = i; c->flags = 0; @@ -2106,6 +1969,194 @@ int kvm_arch_init_vcpu(CPUState *cs) } } + return cpuid_i; + +full: + fprintf(stderr, "cpuid_data is full, no space for " + "cpuid(eax:0x%x,ecx:0x%x)\n", i, j); + abort(); +} + +int kvm_arch_init_vcpu(CPUState *cs) +{ + struct { + struct kvm_cpuid2 cpuid; + struct kvm_cpuid_entry2 entries[KVM_MAX_CPUID_ENTRIES]; + } 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 cpuid_i; + struct kvm_cpuid_entry2 *c; + uint32_t signature[3]; + int kvm_base = KVM_CPUID_SIGNATURE; + int max_nested_state_len; + int r; + Error *local_err = NULL; + + memset(&cpuid_data, 0, sizeof(cpuid_data)); + + cpuid_i = 0; + + has_xsave2 = kvm_check_extension(cs->kvm_state, KVM_CAP_XSAVE2); + + r = kvm_arch_set_tsc_khz(cs); + if (r < 0) { + return r; + } + + /* vcpu's TSC frequency is either specified by user, or following + * the value used by KVM if the former is not present. In the + * latter case, we query it from KVM and record in env->tsc_khz, + * so that vcpu's TSC frequency can be migrated later via this field. + */ + if (!env->tsc_khz) { + r = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ? + kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) : + -ENOTSUP; + if (r > 0) { + env->tsc_khz = r; + } + } + + env->apic_bus_freq = KVM_APIC_BUS_FREQUENCY; + + /* + * kvm_hyperv_expand_features() is called here for the second time in case + * KVM_CAP_SYS_HYPERV_CPUID is not supported. While we can't possibly handle + * 'query-cpu-model-expansion' in this case as we don't have a KVM vCPU to + * check which Hyper-V enlightenments are supported and which are not, we + * can still proceed and check/expand Hyper-V enlightenments here so legacy + * behavior is preserved. + */ + if (!kvm_hyperv_expand_features(cpu, &local_err)) { + error_report_err(local_err); + return -ENOSYS; + } + + if (hyperv_enabled(cpu)) { + r = hyperv_init_vcpu(cpu); + if (r) { + return r; + } + + cpuid_i = hyperv_fill_cpuids(cs, cpuid_data.entries); + kvm_base = KVM_CPUID_SIGNATURE_NEXT; + has_msr_hv_hypercall = true; + } + + if (cs->kvm_state->xen_version) { +#ifdef CONFIG_XEN_EMU + struct kvm_cpuid_entry2 *xen_max_leaf; + + memcpy(signature, "XenVMMXenVMM", 12); + + xen_max_leaf = c = &cpuid_data.entries[cpuid_i++]; + c->function = kvm_base + XEN_CPUID_SIGNATURE; + c->eax = kvm_base + XEN_CPUID_TIME; + c->ebx = signature[0]; + c->ecx = signature[1]; + c->edx = signature[2]; + + c = &cpuid_data.entries[cpuid_i++]; + c->function = kvm_base + XEN_CPUID_VENDOR; + c->eax = cs->kvm_state->xen_version; + c->ebx = 0; + c->ecx = 0; + c->edx = 0; + + c = &cpuid_data.entries[cpuid_i++]; + c->function = kvm_base + XEN_CPUID_HVM_MSR; + /* Number of hypercall-transfer pages */ + c->eax = 1; + /* Hypercall MSR base address */ + if (hyperv_enabled(cpu)) { + c->ebx = XEN_HYPERCALL_MSR_HYPERV; + kvm_xen_init(cs->kvm_state, c->ebx); + } else { + c->ebx = XEN_HYPERCALL_MSR; + } + c->ecx = 0; + c->edx = 0; + + c = &cpuid_data.entries[cpuid_i++]; + c->function = kvm_base + XEN_CPUID_TIME; + c->eax = ((!!tsc_is_stable_and_known(env) << 1) | + (!!(env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_RDTSCP) << 2)); + /* default=0 (emulate if necessary) */ + c->ebx = 0; + /* guest tsc frequency */ + c->ecx = env->user_tsc_khz; + /* guest tsc incarnation (migration count) */ + c->edx = 0; + + c = &cpuid_data.entries[cpuid_i++]; + c->function = kvm_base + XEN_CPUID_HVM; + xen_max_leaf->eax = kvm_base + XEN_CPUID_HVM; + if (cs->kvm_state->xen_version >= XEN_VERSION(4, 5)) { + c->function = kvm_base + XEN_CPUID_HVM; + + if (cpu->xen_vapic) { + c->eax |= XEN_HVM_CPUID_APIC_ACCESS_VIRT; + c->eax |= XEN_HVM_CPUID_X2APIC_VIRT; + } + + c->eax |= XEN_HVM_CPUID_IOMMU_MAPPINGS; + + if (cs->kvm_state->xen_version >= XEN_VERSION(4, 6)) { + c->eax |= XEN_HVM_CPUID_VCPU_ID_PRESENT; + c->ebx = cs->cpu_index; + } + + if (cs->kvm_state->xen_version >= XEN_VERSION(4, 17)) { + c->eax |= XEN_HVM_CPUID_UPCALL_VECTOR; + } + } + + r = kvm_xen_init_vcpu(cs); + if (r) { + return r; + } + + kvm_base += 0x100; +#else /* CONFIG_XEN_EMU */ + /* This should never happen as kvm_arch_init() would have died first. */ + fprintf(stderr, "Cannot enable Xen CPUID without Xen support\n"); + abort(); +#endif + } else if (cpu->expose_kvm) { + memcpy(signature, "KVMKVMKVM\0\0\0", 12); + c = &cpuid_data.entries[cpuid_i++]; + c->function = KVM_CPUID_SIGNATURE | kvm_base; + c->eax = KVM_CPUID_FEATURES | kvm_base; + c->ebx = signature[0]; + c->ecx = signature[1]; + c->edx = signature[2]; + + c = &cpuid_data.entries[cpuid_i++]; + c->function = KVM_CPUID_FEATURES | kvm_base; + c->eax = env->features[FEAT_KVM]; + c->edx = env->features[FEAT_KVM_HINTS]; + } + + if (cpu->kvm_pv_enforce_cpuid) { + r = kvm_vcpu_enable_cap(cs, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 0, 1); + if (r < 0) { + fprintf(stderr, + "failed to enable KVM_CAP_ENFORCE_PV_FEATURE_CPUID: %s", + strerror(-r)); + abort(); + } + } + + cpuid_i = kvm_x86_build_cpuid(env, cpuid_data.entries, cpuid_i); cpuid_data.cpuid.nent = cpuid_i; if (((env->cpuid_version >> 8)&0xF) >= 6 @@ -2538,10 +2589,12 @@ int kvm_arch_init(MachineState *ms, KVMState *s) * mechanisms are supported in future (e.g. TDX), they'll need * their own initialization either here or elsewhere. */ - ret = sev_kvm_init(ms->cgs, &local_err); - if (ret < 0) { - error_report_err(local_err); - return ret; + if (ms->cgs) { + ret = confidential_guest_kvm_init(ms->cgs, &local_err); + if (ret < 0) { + error_report_err(local_err); + return ret; + } } has_xcrs = kvm_check_extension(s, KVM_CAP_XCRS); @@ -5612,11 +5665,6 @@ bool kvm_has_waitpkg(void) return has_msr_umwait; } -bool kvm_arch_cpu_check_are_resettable(void) -{ - return !sev_es_enabled(); -} - #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 void kvm_request_xsave_components(X86CPU *cpu, uint64_t mask) |