diff options
Diffstat (limited to 'target/i386/kvm/kvm.c')
| -rw-r--r-- | target/i386/kvm/kvm.c | 257 |
1 files changed, 172 insertions, 85 deletions
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 6c749d4..309f043 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -38,6 +38,7 @@ #include "kvm_i386.h" #include "../confidential-guest.h" #include "sev.h" +#include "tdx.h" #include "xen-emu.h" #include "hyperv.h" #include "hyperv-proto.h" @@ -67,6 +68,7 @@ #include "hw/pci/msix.h" #include "migration/blocker.h" #include "exec/memattrs.h" +#include "exec/target_page.h" #include "trace.h" #include CONFIG_DEVICES @@ -191,6 +193,7 @@ static const char *vm_type_name[] = { [KVM_X86_SEV_VM] = "SEV", [KVM_X86_SEV_ES_VM] = "SEV-ES", [KVM_X86_SNP_VM] = "SEV-SNP", + [KVM_X86_TDX_VM] = "TDX", }; bool kvm_is_vm_type_supported(int type) @@ -325,7 +328,7 @@ void kvm_synchronize_all_tsc(void) { CPUState *cpu; - if (kvm_enabled()) { + if (kvm_enabled() && !is_tdx_vm()) { CPU_FOREACH(cpu) { run_on_cpu(cpu, do_kvm_synchronize_tsc, RUN_ON_CPU_NULL); } @@ -391,7 +394,7 @@ static bool host_tsx_broken(void) /* Returns the value for a specific register on the cpuid entry */ -static uint32_t cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, int reg) +uint32_t cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, int reg) { uint32_t ret = 0; switch (reg) { @@ -413,9 +416,9 @@ static uint32_t cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, int reg) /* Find matching entry for function/index on kvm_cpuid2 struct */ -static struct kvm_cpuid_entry2 *cpuid_find_entry(struct kvm_cpuid2 *cpuid, - uint32_t function, - uint32_t index) +struct kvm_cpuid_entry2 *cpuid_find_entry(struct kvm_cpuid2 *cpuid, + uint32_t function, + uint32_t index) { int i; for (i = 0; i < cpuid->nent; ++i) { @@ -571,7 +574,7 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, } if (current_machine->cgs) { - ret = x86_confidential_guest_mask_cpuid_features( + ret = x86_confidential_guest_adjust_cpuid_features( X86_CONFIDENTIAL_GUEST(current_machine->cgs), function, index, reg, ret); } @@ -650,6 +653,23 @@ uint64_t kvm_arch_get_supported_msr_feature(KVMState *s, uint32_t index) must_be_one = (uint32_t)value; can_be_one = (uint32_t)(value >> 32); return can_be_one & ~must_be_one; + case MSR_IA32_ARCH_CAPABILITIES: + /* + * Special handling for fb-clear bit in ARCH_CAPABILITIES MSR. + * KVM will only report the bit if it is enabled in the host, + * but, for live migration capability purposes, we want to + * expose the bit to the guest even if it is disabled in the + * host, as long as the host itself is not vulnerable to + * the issue that the fb-clear bit is meant to mitigate. + */ + if ((value & MSR_ARCH_CAP_MDS_NO) && + (value & MSR_ARCH_CAP_TAA_NO) && + (value & MSR_ARCH_CAP_SBDR_SSDP_NO) && + (value & MSR_ARCH_CAP_FBSDP_NO) && + (value & MSR_ARCH_CAP_PSDP_NO)) { + value |= MSR_ARCH_CAP_FB_CLEAR; + } + return value; default: return value; @@ -867,6 +887,15 @@ static int kvm_arch_set_tsc_khz(CPUState *cs) int r, cur_freq; bool set_ioctl = false; + /* + * TSC of TD vcpu is immutable, it cannot be set/changed via vcpu scope + * VM_SET_TSC_KHZ, but only be initialized via VM scope VM_SET_TSC_KHZ + * before ioctl KVM_TDX_INIT_VM in tdx_pre_create_vcpu() + */ + if (is_tdx_vm()) { + return 0; + } + if (!env->tsc_khz) { return 0; } @@ -1778,8 +1807,6 @@ static int hyperv_init_vcpu(X86CPU *cpu) static Error *invtsc_mig_blocker; -#define KVM_MAX_CPUID_ENTRIES 100 - static void kvm_init_xsave(CPUX86State *env) { if (has_xsave2) { @@ -1822,9 +1849,8 @@ static void kvm_init_nested_state(CPUX86State *env) } } -static uint32_t kvm_x86_build_cpuid(CPUX86State *env, - struct kvm_cpuid_entry2 *entries, - uint32_t cpuid_i) +uint32_t kvm_x86_build_cpuid(CPUX86State *env, struct kvm_cpuid_entry2 *entries, + uint32_t cpuid_i) { uint32_t limit, i, j; uint32_t unused; @@ -1863,7 +1889,7 @@ static uint32_t kvm_x86_build_cpuid(CPUX86State *env, break; } case 0x1f: - if (!x86_has_extended_topo(env->avail_cpu_topo)) { + if (!x86_has_cpuid_0x1f(env_archcpu(env))) { cpuid_i--; break; } @@ -2051,6 +2077,15 @@ full: abort(); } +int kvm_arch_pre_create_vcpu(CPUState *cpu, Error **errp) +{ + if (is_tdx_vm()) { + return tdx_pre_create_vcpu(cpu, errp); + } + + return 0; +} + int kvm_arch_init_vcpu(CPUState *cs) { struct { @@ -2075,6 +2110,14 @@ int kvm_arch_init_vcpu(CPUState *cs) int r; Error *local_err = NULL; + if (current_machine->cgs) { + r = x86_confidential_guest_check_features( + X86_CONFIDENTIAL_GUEST(current_machine->cgs), cs); + if (r < 0) { + return r; + } + } + memset(&cpuid_data, 0, sizeof(cpuid_data)); cpuid_i = 0; @@ -2233,7 +2276,7 @@ int kvm_arch_init_vcpu(CPUState *cs) 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 + if (x86_cpu_family(env->cpuid_version) >= 6 && (env->features[FEAT_1_EDX] & (CPUID_MCE | CPUID_MCA)) == (CPUID_MCE | CPUID_MCA)) { uint64_t mcg_cap, unsupported_caps; @@ -2674,6 +2717,7 @@ static MemoryRegion smram_as_mem; static void register_smram_listener(Notifier *n, void *unused) { + CPUState *cpu; MemoryRegion *smram = (MemoryRegion *) object_resolve_path("/machine/smram", NULL); @@ -2697,7 +2741,11 @@ static void register_smram_listener(Notifier *n, void *unused) address_space_init(&smram_address_space, &smram_as_root, "KVM-SMRAM"); kvm_memory_listener_register(kvm_state, &smram_listener, - &smram_address_space, 1, "kvm-smram"); + &smram_address_space, X86ASIdx_SMM, "kvm-smram"); + + CPU_FOREACH(cpu) { + cpu_address_space_init(cpu, X86ASIdx_SMM, "cpu-smm", &smram_as_root); + } } static void *kvm_msr_energy_thread(void *data) @@ -3205,16 +3253,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s) Error *local_err = NULL; /* - * Initialize SEV context, if required - * - * If no memory encryption is requested (ms->cgs == NULL) this is - * a no-op. - * - * It's also a no-op if a non-SEV confidential guest support - * mechanism is selected. SEV is the only mechanism available to - * select on x86 at present, so this doesn't arise, but if new - * mechanisms are supported in future (e.g. TDX), they'll need - * their own initialization either here or elsewhere. + * Initialize confidential guest (SEV/TDX) context, if required */ if (ms->cgs) { ret = confidential_guest_kvm_init(ms->cgs, &local_err); @@ -3289,8 +3328,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s) return ret; } - if (kvm_check_extension(s, KVM_CAP_X86_SMM) && - object_dynamic_cast(OBJECT(ms), TYPE_X86_MACHINE) && + if (object_dynamic_cast(OBJECT(ms), TYPE_X86_MACHINE) && x86_machine_is_smm_enabled(X86_MACHINE(ms))) { smram_machine_done.notify = register_smram_listener; qemu_add_machine_init_done_notifier(&smram_machine_done); @@ -3855,36 +3893,38 @@ static void kvm_init_msrs(X86CPU *cpu) CPUX86State *env = &cpu->env; kvm_msr_buf_reset(cpu); - 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]); - } + if (!is_tdx_vm()) { + 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]); + } + + if (has_msr_perf_capabs && cpu->enable_pmu) { + kvm_msr_entry_add_perf(cpu, env->features); + } - if (has_msr_perf_capabs && cpu->enable_pmu) { - kvm_msr_entry_add_perf(cpu, env->features); + /* + * Older kernels do not include VMX MSRs in KVM_GET_MSR_INDEX_LIST, but + * all kernels with MSR features should have them. + */ + if (kvm_feature_msrs && cpu_has_vmx(env)) { + kvm_msr_entry_add_vmx(cpu, env->features); + } } if (has_msr_ucode_rev) { kvm_msr_entry_add(cpu, MSR_IA32_UCODE_REV, cpu->ucode_rev); } - - /* - * Older kernels do not include VMX MSRs in KVM_GET_MSR_INDEX_LIST, but - * all kernels with MSR features should have them. - */ - if (kvm_feature_msrs && cpu_has_vmx(env)) { - kvm_msr_entry_add_vmx(cpu, env->features); - } - assert(kvm_buf_set_msrs(cpu) == 0); } -static int kvm_put_msrs(X86CPU *cpu, int level) +static int kvm_put_msrs(X86CPU *cpu, KvmPutState level) { CPUX86State *env = &cpu->env; int i; @@ -5004,7 +5044,7 @@ static int kvm_get_apic(X86CPU *cpu) return 0; } -static int kvm_put_vcpu_events(X86CPU *cpu, int level) +static int kvm_put_vcpu_events(X86CPU *cpu, KvmPutState level) { CPUState *cs = CPU(cpu); CPUX86State *env = &cpu->env; @@ -5043,7 +5083,7 @@ static int kvm_put_vcpu_events(X86CPU *cpu, int level) */ events.smi.pending = cs->interrupt_request & CPU_INTERRUPT_SMI; events.smi.latched_init = cs->interrupt_request & CPU_INTERRUPT_INIT; - cs->interrupt_request &= ~(CPU_INTERRUPT_INIT | CPU_INTERRUPT_SMI); + cpu_reset_interrupt(cs, CPU_INTERRUPT_INIT | CPU_INTERRUPT_SMI); } else { /* Keep these in cs->interrupt_request. */ events.smi.pending = 0; @@ -5247,7 +5287,7 @@ static int kvm_get_nested_state(X86CPU *cpu) return ret; } -int kvm_arch_put_registers(CPUState *cpu, int level, Error **errp) +int kvm_arch_put_registers(CPUState *cpu, KvmPutState level, Error **errp) { X86CPU *x86_cpu = X86_CPU(cpu); int ret; @@ -5430,10 +5470,10 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run) int ret; /* Inject NMI */ - if (cpu->interrupt_request & (CPU_INTERRUPT_NMI | CPU_INTERRUPT_SMI)) { - if (cpu->interrupt_request & CPU_INTERRUPT_NMI) { + if (cpu_test_interrupt(cpu, CPU_INTERRUPT_NMI | CPU_INTERRUPT_SMI)) { + if (cpu_test_interrupt(cpu, CPU_INTERRUPT_NMI)) { bql_lock(); - cpu->interrupt_request &= ~CPU_INTERRUPT_NMI; + cpu_reset_interrupt(cpu, CPU_INTERRUPT_NMI); bql_unlock(); DPRINTF("injected NMI\n"); ret = kvm_vcpu_ioctl(cpu, KVM_NMI); @@ -5442,9 +5482,9 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run) strerror(-ret)); } } - if (cpu->interrupt_request & CPU_INTERRUPT_SMI) { + if (cpu_test_interrupt(cpu, CPU_INTERRUPT_SMI)) { bql_lock(); - cpu->interrupt_request &= ~CPU_INTERRUPT_SMI; + cpu_reset_interrupt(cpu, CPU_INTERRUPT_SMI); bql_unlock(); DPRINTF("injected SMI\n"); ret = kvm_vcpu_ioctl(cpu, KVM_SMI); @@ -5455,32 +5495,31 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run) } } - if (!kvm_pic_in_kernel()) { - bql_lock(); - } /* Force the VCPU out of its inner loop to process any INIT requests * or (for userspace APIC, but it is cheap to combine the checks here) * pending TPR access reports. */ - if (cpu->interrupt_request & (CPU_INTERRUPT_INIT | CPU_INTERRUPT_TPR)) { - if ((cpu->interrupt_request & CPU_INTERRUPT_INIT) && + if (cpu_test_interrupt(cpu, CPU_INTERRUPT_INIT | CPU_INTERRUPT_TPR)) { + if (cpu_test_interrupt(cpu, CPU_INTERRUPT_INIT) && !(env->hflags & HF_SMM_MASK)) { - cpu->exit_request = 1; + qatomic_set(&cpu->exit_request, true); } - if (cpu->interrupt_request & CPU_INTERRUPT_TPR) { - cpu->exit_request = 1; + if (cpu_test_interrupt(cpu, CPU_INTERRUPT_TPR)) { + qatomic_set(&cpu->exit_request, true); } } if (!kvm_pic_in_kernel()) { /* Try to inject an interrupt if the guest can accept it */ if (run->ready_for_interrupt_injection && - (cpu->interrupt_request & CPU_INTERRUPT_HARD) && + cpu_test_interrupt(cpu, CPU_INTERRUPT_HARD) && (env->eflags & IF_MASK)) { int irq; - cpu->interrupt_request &= ~CPU_INTERRUPT_HARD; + bql_lock(); + + cpu_reset_interrupt(cpu, CPU_INTERRUPT_HARD); irq = cpu_get_pic_interrupt(env); if (irq >= 0) { struct kvm_interrupt intr; @@ -5494,13 +5533,14 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run) strerror(-ret)); } } + bql_unlock(); } /* If we have an interrupt but the guest is not ready to receive an * interrupt, request an interrupt window exit. This will * cause a return to userspace as soon as the guest is ready to * receive interrupts. */ - if ((cpu->interrupt_request & CPU_INTERRUPT_HARD)) { + if (cpu_test_interrupt(cpu, CPU_INTERRUPT_HARD)) { run->request_interrupt_window = 1; } else { run->request_interrupt_window = 0; @@ -5508,8 +5548,6 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run) DPRINTF("setting tpr\n"); run->cr8 = cpu_get_apic_tpr(x86_cpu->apic_state); - - bql_unlock(); } } @@ -5572,18 +5610,18 @@ int kvm_arch_process_async_events(CPUState *cs) X86CPU *cpu = X86_CPU(cs); CPUX86State *env = &cpu->env; - if (cs->interrupt_request & CPU_INTERRUPT_MCE) { + if (cpu_test_interrupt(cs, CPU_INTERRUPT_MCE)) { /* We must not raise CPU_INTERRUPT_MCE if it's not supported. */ assert(env->mcg_cap); - cs->interrupt_request &= ~CPU_INTERRUPT_MCE; + cpu_reset_interrupt(cs, CPU_INTERRUPT_MCE); kvm_cpu_synchronize_state(cs); if (env->exception_nr == EXCP08_DBLE) { /* this means triple fault */ qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); - cs->exit_request = 1; + qatomic_set(&cs->exit_request, true); return 0; } kvm_queue_exception(env, EXCP12_MCHK, 0, 0); @@ -5595,7 +5633,7 @@ int kvm_arch_process_async_events(CPUState *cs) } } - if ((cs->interrupt_request & CPU_INTERRUPT_INIT) && + if (cpu_test_interrupt(cs, CPU_INTERRUPT_INIT) && !(env->hflags & HF_SMM_MASK)) { kvm_cpu_synchronize_state(cs); do_cpu_init(cpu); @@ -5605,21 +5643,21 @@ int kvm_arch_process_async_events(CPUState *cs) return 0; } - if (cs->interrupt_request & CPU_INTERRUPT_POLL) { - cs->interrupt_request &= ~CPU_INTERRUPT_POLL; + if (cpu_test_interrupt(cs, CPU_INTERRUPT_POLL)) { + cpu_reset_interrupt(cs, CPU_INTERRUPT_POLL); apic_poll_irq(cpu->apic_state); } - if (((cs->interrupt_request & CPU_INTERRUPT_HARD) && + if ((cpu_test_interrupt(cs, CPU_INTERRUPT_HARD) && (env->eflags & IF_MASK)) || - (cs->interrupt_request & CPU_INTERRUPT_NMI)) { + cpu_test_interrupt(cs, CPU_INTERRUPT_NMI)) { cs->halted = 0; } - if (cs->interrupt_request & CPU_INTERRUPT_SIPI) { + if (cpu_test_interrupt(cs, CPU_INTERRUPT_SIPI)) { kvm_cpu_synchronize_state(cs); do_cpu_sipi(cpu); } - if (cs->interrupt_request & CPU_INTERRUPT_TPR) { - cs->interrupt_request &= ~CPU_INTERRUPT_TPR; + if (cpu_test_interrupt(cs, CPU_INTERRUPT_TPR)) { + cpu_reset_interrupt(cs, CPU_INTERRUPT_TPR); kvm_cpu_synchronize_state(cs); apic_handle_tpr_access_report(cpu->apic_state, env->eip, env->tpr_access_type); @@ -5633,9 +5671,9 @@ static int kvm_handle_halt(X86CPU *cpu) CPUState *cs = CPU(cpu); CPUX86State *env = &cpu->env; - if (!((cs->interrupt_request & CPU_INTERRUPT_HARD) && + if (!(cpu_test_interrupt(cs, CPU_INTERRUPT_HARD) && (env->eflags & IF_MASK)) && - !(cs->interrupt_request & CPU_INTERRUPT_NMI)) { + !cpu_test_interrupt(cs, CPU_INTERRUPT_NMI)) { cs->halted = 1; return EXCP_HLT; } @@ -5999,9 +6037,11 @@ static bool host_supports_vmx(void) * because private/shared page tracking is already provided through other * means, these 2 use-cases should be treated as being mutually-exclusive. */ -static int kvm_handle_hc_map_gpa_range(struct kvm_run *run) +static int kvm_handle_hc_map_gpa_range(X86CPU *cpu, struct kvm_run *run) { + struct kvm_pre_fault_memory mem; uint64_t gpa, size, attributes; + int ret; if (!machine_require_guest_memfd(current_machine)) return -EINVAL; @@ -6012,13 +6052,32 @@ static int kvm_handle_hc_map_gpa_range(struct kvm_run *run) trace_kvm_hc_map_gpa_range(gpa, size, attributes, run->hypercall.flags); - return kvm_convert_memory(gpa, size, attributes & KVM_MAP_GPA_RANGE_ENCRYPTED); + ret = kvm_convert_memory(gpa, size, attributes & KVM_MAP_GPA_RANGE_ENCRYPTED); + if (ret || !kvm_pre_fault_memory_supported) { + return ret; + } + + /* + * Opportunistically pre-fault memory in. Failures are ignored so that any + * errors in faulting in the memory will get captured in KVM page fault + * path when the guest first accesses the page. + */ + memset(&mem, 0, sizeof(mem)); + mem.gpa = gpa; + mem.size = size; + while (mem.size) { + if (kvm_vcpu_ioctl(CPU(cpu), KVM_PRE_FAULT_MEMORY, &mem)) { + break; + } + } + + return 0; } -static int kvm_handle_hypercall(struct kvm_run *run) +static int kvm_handle_hypercall(X86CPU *cpu, struct kvm_run *run) { if (run->hypercall.nr == KVM_HC_MAP_GPA_RANGE) - return kvm_handle_hc_map_gpa_range(run); + return kvm_handle_hc_map_gpa_range(cpu, run); return -EINVAL; } @@ -6118,7 +6177,35 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) break; #endif case KVM_EXIT_HYPERCALL: - ret = kvm_handle_hypercall(run); + ret = kvm_handle_hypercall(cpu, run); + break; + case KVM_EXIT_SYSTEM_EVENT: + switch (run->system_event.type) { + case KVM_SYSTEM_EVENT_TDX_FATAL: + ret = tdx_handle_report_fatal_error(cpu, run); + break; + default: + ret = -1; + break; + } + break; + case KVM_EXIT_TDX: + /* + * run->tdx is already set up for the case where userspace + * does not handle the TDVMCALL. + */ + switch (run->tdx.nr) { + case TDVMCALL_GET_QUOTE: + tdx_handle_get_quote(cpu, run); + break; + case TDVMCALL_GET_TD_VM_CALL_INFO: + tdx_handle_get_tdvmcall_info(cpu, run); + break; + case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT: + tdx_handle_setup_event_notify_interrupt(cpu, run); + break; + } + ret = 0; break; default: fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason); |