diff --git a/accel/kvm/kvm-accel-ops.c b/accel/kvm/kvm-accel-ops.c index b3c946dc4b..94c828ac8d 100644 --- a/accel/kvm/kvm-accel-ops.c +++ b/accel/kvm/kvm-accel-ops.c @@ -82,10 +82,10 @@ static bool kvm_vcpu_thread_is_idle(CPUState *cpu) static bool kvm_cpus_are_resettable(void) { - return !kvm_enabled() || kvm_cpu_check_are_resettable(); + return !kvm_enabled() || !kvm_state->guest_state_protected; } -#ifdef KVM_CAP_SET_GUEST_DEBUG +#ifdef TARGET_KVM_HAVE_GUEST_DEBUG static int kvm_update_guest_debug_ops(CPUState *cpu) { return kvm_update_guest_debug(cpu, 0); @@ -104,7 +104,7 @@ static void kvm_accel_ops_class_init(ObjectClass *oc, void *data) ops->synchronize_state = kvm_cpu_synchronize_state; ops->synchronize_pre_loadvm = kvm_cpu_synchronize_pre_loadvm; -#ifdef KVM_CAP_SET_GUEST_DEBUG +#ifdef TARGET_KVM_HAVE_GUEST_DEBUG ops->update_guest_debug = kvm_update_guest_debug_ops; ops->supports_guest_debug = kvm_supports_guest_debug; ops->insert_breakpoint = kvm_insert_breakpoint; diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 931f74256e..d7281b93f3 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -91,6 +91,8 @@ bool kvm_msi_use_devid; static bool kvm_has_guest_debug; static int kvm_sstep_flags; static bool kvm_immediate_exit; +static uint64_t kvm_supported_memory_attributes; +static bool kvm_guest_memfd_supported; static hwaddr kvm_max_slot_size = ~0; static const KVMCapabilityInfo kvm_required_capabilites[] = { @@ -282,34 +284,58 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram, static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, bool new) { KVMState *s = kvm_state; - struct kvm_userspace_memory_region mem; + struct kvm_userspace_memory_region2 mem; int ret; mem.slot = slot->slot | (kml->as_id << 16); mem.guest_phys_addr = slot->start_addr; mem.userspace_addr = (unsigned long)slot->ram; mem.flags = slot->flags; + mem.guest_memfd = slot->guest_memfd; + mem.guest_memfd_offset = slot->guest_memfd_offset; if (slot->memory_size && !new && (mem.flags ^ slot->old_flags) & KVM_MEM_READONLY) { /* Set the slot size to 0 before setting the slot to the desired * value. This is needed based on KVM commit 75d61fbc. */ mem.memory_size = 0; - ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem); + + if (kvm_guest_memfd_supported) { + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION2, &mem); + } else { + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem); + } if (ret < 0) { goto err; } } mem.memory_size = slot->memory_size; - ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem); + if (kvm_guest_memfd_supported) { + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION2, &mem); + } else { + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem); + } slot->old_flags = mem.flags; err: - trace_kvm_set_user_memory(mem.slot, mem.flags, mem.guest_phys_addr, - mem.memory_size, mem.userspace_addr, ret); + trace_kvm_set_user_memory(mem.slot >> 16, (uint16_t)mem.slot, mem.flags, + mem.guest_phys_addr, mem.memory_size, + mem.userspace_addr, mem.guest_memfd, + mem.guest_memfd_offset, ret); if (ret < 0) { - error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d," - " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s", - __func__, mem.slot, slot->start_addr, - (uint64_t)mem.memory_size, strerror(errno)); + if (kvm_guest_memfd_supported) { + error_report("%s: KVM_SET_USER_MEMORY_REGION2 failed, slot=%d," + " start=0x%" PRIx64 ", size=0x%" PRIx64 "," + " flags=0x%" PRIx32 ", guest_memfd=%" PRId32 "," + " guest_memfd_offset=0x%" PRIx64 ": %s", + __func__, mem.slot, slot->start_addr, + (uint64_t)mem.memory_size, mem.flags, + mem.guest_memfd, (uint64_t)mem.guest_memfd_offset, + strerror(errno)); + } else { + error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d," + " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s", + __func__, mem.slot, slot->start_addr, + (uint64_t)mem.memory_size, strerror(errno)); + } } return ret; } @@ -464,6 +490,10 @@ static int kvm_mem_flags(MemoryRegion *mr) if (readonly && kvm_readonly_mem_allowed) { flags |= KVM_MEM_READONLY; } + if (memory_region_has_guest_memfd(mr)) { + assert(kvm_guest_memfd_supported); + flags |= KVM_MEM_GUEST_MEMFD; + } return flags; } @@ -1265,6 +1295,36 @@ void kvm_set_max_memslot_size(hwaddr max_slot_size) kvm_max_slot_size = max_slot_size; } +static int kvm_set_memory_attributes(hwaddr start, uint64_t size, uint64_t attr) +{ + struct kvm_memory_attributes attrs; + int r; + + assert((attr & kvm_supported_memory_attributes) == attr); + attrs.attributes = attr; + attrs.address = start; + attrs.size = size; + attrs.flags = 0; + + r = kvm_vm_ioctl(kvm_state, KVM_SET_MEMORY_ATTRIBUTES, &attrs); + if (r) { + error_report("failed to set memory (0x%" HWADDR_PRIx "+0x%" PRIx64 ") " + "with attr 0x%" PRIx64 " error '%s'", + start, size, attr, strerror(errno)); + } + return r; +} + +int kvm_set_memory_attributes_private(hwaddr start, uint64_t size) +{ + return kvm_set_memory_attributes(start, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); +} + +int kvm_set_memory_attributes_shared(hwaddr start, uint64_t size) +{ + return kvm_set_memory_attributes(start, size, 0); +} + /* Called with KVMMemoryListener.slots_lock held */ static void kvm_set_phys_mem(KVMMemoryListener *kml, MemoryRegionSection *section, bool add) @@ -1361,6 +1421,9 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, mem->ram_start_offset = ram_start_offset; mem->ram = ram; mem->flags = kvm_mem_flags(mr); + mem->guest_memfd = mr->ram_block->guest_memfd; + mem->guest_memfd_offset = (uint8_t*)ram - mr->ram_block->host; + kvm_slot_init_dirty_bitmap(mem); err = kvm_set_user_memory_region(kml, mem, true); if (err) { @@ -1368,6 +1431,16 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, strerror(-err)); abort(); } + + if (memory_region_has_guest_memfd(mr)) { + err = kvm_set_memory_attributes_private(start_addr, slot_size); + if (err) { + error_report("%s: failed to set memory attribute private: %s", + __func__, strerror(-err)); + exit(1); + } + } + start_addr += slot_size; ram_start_offset += slot_size; ram += slot_size; @@ -2360,7 +2433,7 @@ static int kvm_init(MachineState *ms) s->sigmask_len = 8; accel_blocker_init(); -#ifdef KVM_CAP_SET_GUEST_DEBUG +#ifdef TARGET_KVM_HAVE_GUEST_DEBUG QTAILQ_INIT(&s->kvm_sw_breakpoints); #endif QLIST_INIT(&s->kvm_parked_vcpus); @@ -2386,6 +2459,12 @@ static int kvm_init(MachineState *ms) goto err; } + kvm_supported_memory_attributes = kvm_check_extension(s, KVM_CAP_MEMORY_ATTRIBUTES); + kvm_guest_memfd_supported = + kvm_check_extension(s, KVM_CAP_GUEST_MEMFD) && + kvm_check_extension(s, KVM_CAP_USER_MEMORY2) && + (kvm_supported_memory_attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE); + kvm_immediate_exit = kvm_check_extension(s, KVM_CAP_IMMEDIATE_EXIT); s->nr_slots = kvm_check_extension(s, KVM_CAP_NR_MEMSLOTS); @@ -2544,7 +2623,7 @@ static int kvm_init(MachineState *ms) kvm_vm_attributes_allowed = (kvm_check_extension(s, KVM_CAP_VM_ATTRIBUTES) > 0); -#ifdef KVM_CAP_SET_GUEST_DEBUG +#ifdef TARGET_KVM_HAVE_GUEST_DEBUG kvm_has_guest_debug = (kvm_check_extension(s, KVM_CAP_SET_GUEST_DEBUG) > 0); #endif @@ -2553,7 +2632,7 @@ static int kvm_init(MachineState *ms) if (kvm_has_guest_debug) { kvm_sstep_flags = SSTEP_ENABLE; -#if defined KVM_CAP_SET_GUEST_DEBUG2 +#if defined TARGET_KVM_HAVE_GUEST_DEBUG int guest_debug_flags = kvm_check_extension(s, KVM_CAP_SET_GUEST_DEBUG2); @@ -2696,14 +2775,9 @@ void kvm_flush_coalesced_mmio_buffer(void) s->coalesced_flush_in_progress = false; } -bool kvm_cpu_check_are_resettable(void) -{ - return kvm_arch_cpu_check_are_resettable(); -} - static void do_kvm_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) { - if (!cpu->vcpu_dirty) { + if (!cpu->vcpu_dirty && !kvm_state->guest_state_protected) { int ret = kvm_arch_get_registers(cpu); if (ret) { error_report("Failed to get registers: %s", strerror(-ret)); @@ -2717,7 +2791,7 @@ static void do_kvm_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) void kvm_cpu_synchronize_state(CPUState *cpu) { - if (!cpu->vcpu_dirty) { + if (!cpu->vcpu_dirty && !kvm_state->guest_state_protected) { run_on_cpu(cpu, do_kvm_cpu_synchronize_state, RUN_ON_CPU_NULL); } } @@ -2752,7 +2826,13 @@ static void do_kvm_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg) void kvm_cpu_synchronize_post_init(CPUState *cpu) { - run_on_cpu(cpu, do_kvm_cpu_synchronize_post_init, RUN_ON_CPU_NULL); + if (!kvm_state->guest_state_protected) { + /* + * This runs before the machine_init_done notifiers, and is the last + * opportunity to synchronize the state of confidential guests. + */ + run_on_cpu(cpu, do_kvm_cpu_synchronize_post_init, RUN_ON_CPU_NULL); + } } static void do_kvm_cpu_synchronize_pre_loadvm(CPUState *cpu, run_on_cpu_data arg) @@ -2820,6 +2900,94 @@ static void kvm_eat_signals(CPUState *cpu) } while (sigismember(&chkset, SIG_IPI)); } +int kvm_convert_memory(hwaddr start, hwaddr size, bool to_private) +{ + MemoryRegionSection section; + ram_addr_t offset; + MemoryRegion *mr; + RAMBlock *rb; + void *addr; + int ret = -1; + + trace_kvm_convert_memory(start, size, to_private ? "shared_to_private" : "private_to_shared"); + + if (!QEMU_PTR_IS_ALIGNED(start, qemu_real_host_page_size()) || + !QEMU_PTR_IS_ALIGNED(size, qemu_real_host_page_size())) { + return -1; + } + + if (!size) { + return -1; + } + + section = memory_region_find(get_system_memory(), start, size); + mr = section.mr; + if (!mr) { + /* + * Ignore converting non-assigned region to shared. + * + * TDX requires vMMIO region to be shared to inject #VE to guest. + * OVMF issues conservatively MapGPA(shared) on 32bit PCI MMIO region, + * and vIO-APIC 0xFEC00000 4K page. + * OVMF assigns 32bit PCI MMIO region to + * [top of low memory: typically 2GB=0xC000000, 0xFC00000) + */ + if (!to_private) { + return 0; + } + return -1; + } + + if (!memory_region_has_guest_memfd(mr)) { + /* + * Because vMMIO region must be shared, guest TD may convert vMMIO + * region to shared explicitly. Don't complain such case. See + * memory_region_type() for checking if the region is MMIO region. + */ + if (!to_private && + !memory_region_is_ram(mr) && + !memory_region_is_ram_device(mr) && + !memory_region_is_rom(mr) && + !memory_region_is_romd(mr)) { + ret = 0; + } else { + error_report("Convert non guest_memfd backed memory region " + "(0x%"HWADDR_PRIx" ,+ 0x%"HWADDR_PRIx") to %s", + start, size, to_private ? "private" : "shared"); + } + goto out_unref; + } + + if (to_private) { + ret = kvm_set_memory_attributes_private(start, size); + } else { + ret = kvm_set_memory_attributes_shared(start, size); + } + if (ret) { + goto out_unref; + } + + addr = memory_region_get_ram_ptr(mr) + section.offset_within_region; + rb = qemu_ram_block_from_host(addr, false, &offset); + + if (to_private) { + if (rb->page_size != qemu_real_host_page_size()) { + /* + * shared memory is backed by hugetlb, which is supposed to be + * pre-allocated and doesn't need to be discarded + */ + goto out_unref; + } + ret = ram_block_discard_range(rb, offset, size); + } else { + ret = ram_block_discard_guest_memfd_range(rb, offset, size); + } + +out_unref: + memory_region_unref(mr); + return ret; +} + int kvm_cpu_exec(CPUState *cpu) { struct kvm_run *run = cpu->kvm_run; @@ -2887,18 +3055,20 @@ int kvm_cpu_exec(CPUState *cpu) ret = EXCP_INTERRUPT; break; } - fprintf(stderr, "error: kvm run failed %s\n", - strerror(-run_ret)); + if (!(run_ret == -EFAULT && run->exit_reason == KVM_EXIT_MEMORY_FAULT)) { + fprintf(stderr, "error: kvm run failed %s\n", + strerror(-run_ret)); #ifdef TARGET_PPC - if (run_ret == -EBUSY) { - fprintf(stderr, - "This is probably because your SMT is enabled.\n" - "VCPU can only run on primary threads with all " - "secondary threads offline.\n"); - } + if (run_ret == -EBUSY) { + fprintf(stderr, + "This is probably because your SMT is enabled.\n" + "VCPU can only run on primary threads with all " + "secondary threads offline.\n"); + } #endif - ret = -1; - break; + ret = -1; + break; + } } trace_kvm_run_exit(cpu->cpu_index, run->exit_reason); @@ -2981,6 +3151,19 @@ int kvm_cpu_exec(CPUState *cpu) break; } break; + case KVM_EXIT_MEMORY_FAULT: + trace_kvm_memory_fault(run->memory_fault.gpa, + run->memory_fault.size, + run->memory_fault.flags); + if (run->memory_fault.flags & ~KVM_MEMORY_EXIT_FLAG_PRIVATE) { + error_report("KVM_EXIT_MEMORY_FAULT: Unknown flag 0x%" PRIx64, + (uint64_t)run->memory_fault.flags); + ret = -1; + break; + } + ret = kvm_convert_memory(run->memory_fault.gpa, run->memory_fault.size, + run->memory_fault.flags & KVM_MEMORY_EXIT_FLAG_PRIVATE); + break; default: ret = kvm_arch_handle_exit(cpu, run); break; @@ -3157,7 +3340,7 @@ bool kvm_arm_supports_user_irq(void) return kvm_check_extension(kvm_state, KVM_CAP_ARM_USER_IRQ); } -#ifdef KVM_CAP_SET_GUEST_DEBUG +#ifdef TARGET_KVM_HAVE_GUEST_DEBUG struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *cpu, vaddr pc) { struct kvm_sw_breakpoint *bp; @@ -3317,7 +3500,7 @@ void kvm_remove_all_breakpoints(CPUState *cpu) } } -#endif /* !KVM_CAP_SET_GUEST_DEBUG */ +#endif /* !TARGET_KVM_HAVE_GUEST_DEBUG */ static int kvm_set_signal_mask(CPUState *cpu, const sigset_t *sigset) { @@ -4099,3 +4282,30 @@ void query_stats_schemas_cb(StatsSchemaList **result, Error **errp) query_stats_schema_vcpu(first_cpu, &stats_args); } } + +void kvm_mark_guest_state_protected(void) +{ + kvm_state->guest_state_protected = true; +} + +int kvm_create_guest_memfd(uint64_t size, uint64_t flags, Error **errp) +{ + int fd; + struct kvm_create_guest_memfd guest_memfd = { + .size = size, + .flags = flags, + }; + + if (!kvm_guest_memfd_supported) { + error_setg(errp, "KVM does not support guest_memfd"); + return -1; + } + + fd = kvm_vm_ioctl(kvm_state, KVM_CREATE_GUEST_MEMFD, &guest_memfd); + if (fd < 0) { + error_setg_errno(errp, errno, "Error creating KVM guest_memfd"); + return -1; + } + + return fd; +} diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events index a25902597b..681ccb667d 100644 --- a/accel/kvm/trace-events +++ b/accel/kvm/trace-events @@ -15,7 +15,7 @@ kvm_irqchip_update_msi_route(int virq) "Updating MSI route virq=%d" kvm_irqchip_release_virq(int virq) "virq %d" kvm_set_ioeventfd_mmio(int fd, uint64_t addr, uint32_t val, bool assign, uint32_t size, bool datamatch) "fd: %d @0x%" PRIx64 " val=0x%x assign: %d size: %d match: %d" kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint32_t val, bool assign, uint32_t size, bool datamatch) "fd: %d @0x%x val=0x%x assign: %d size: %d match: %d" -kvm_set_user_memory(uint32_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, int ret) "Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " ret=%d" +kvm_set_user_memory(uint16_t as, uint16_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, uint32_t fd, uint64_t fd_offset, int ret) "AddrSpace#%d Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " guest_memfd=%d" " guest_memfd_offset=0x%" PRIx64 " ret=%d" kvm_clear_dirty_log(uint32_t slot, uint64_t start, uint32_t size) "slot#%"PRId32" start 0x%"PRIx64" size 0x%"PRIx32 kvm_resample_fd_notify(int gsi) "gsi %d" kvm_dirty_ring_full(int id) "vcpu %d" @@ -31,3 +31,5 @@ kvm_cpu_exec(void) "" kvm_interrupt_exit_request(void) "" kvm_io_window_exit(void) "" kvm_run_exit_system_event(int cpu_index, uint32_t event_type) "cpu_index %d, system_even_type %"PRIu32 +kvm_convert_memory(uint64_t start, uint64_t size, const char *msg) "start 0x%" PRIx64 " size 0x%" PRIx64 " %s" +kvm_memory_fault(uint64_t start, uint64_t size, uint64_t flags) "start 0x%" PRIx64 " size 0x%" PRIx64 " flags 0x%" PRIx64 diff --git a/accel/stubs/kvm-stub.c b/accel/stubs/kvm-stub.c index ca38172884..8e0eb22e61 100644 --- a/accel/stubs/kvm-stub.c +++ b/accel/stubs/kvm-stub.c @@ -129,3 +129,8 @@ bool kvm_hwpoisoned_mem(void) { return false; } + +int kvm_create_guest_memfd(uint64_t size, uint64_t flags, Error **errp) +{ + return -ENOSYS; +} diff --git a/accel/tcg/icount-common.c b/accel/tcg/icount-common.c index a4a747d1dc..8d3d3a7e9d 100644 --- a/accel/tcg/icount-common.c +++ b/accel/tcg/icount-common.c @@ -336,10 +336,8 @@ void icount_start_warp_timer(void) deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL, ~QEMU_TIMER_ATTR_EXTERNAL); if (deadline < 0) { - static bool notified; - if (!icount_sleep && !notified) { - warn_report("icount sleep disabled and no active timers"); - notified = true; + if (!icount_sleep) { + warn_report_once("icount sleep disabled and no active timers"); } return; } diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c index ac3e433cbd..3c69db7946 100644 --- a/backends/hostmem-file.c +++ b/backends/hostmem-file.c @@ -85,6 +85,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) ram_flags |= fb->readonly ? RAM_READONLY_FD : 0; ram_flags |= fb->rom == ON_OFF_AUTO_ON ? RAM_READONLY : 0; ram_flags |= backend->reserve ? 0 : RAM_NORESERVE; + ram_flags |= backend->guest_memfd ? RAM_GUEST_MEMFD : 0; ram_flags |= fb->is_pmem ? RAM_PMEM : 0; ram_flags |= RAM_NAMED_FILE; return memory_region_init_ram_from_file(&backend->mr, OBJECT(backend), name, diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c index 3923ea9364..745ead0034 100644 --- a/backends/hostmem-memfd.c +++ b/backends/hostmem-memfd.c @@ -55,6 +55,7 @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) name = host_memory_backend_get_name(backend); ram_flags = backend->share ? RAM_SHARED : 0; ram_flags |= backend->reserve ? 0 : RAM_NORESERVE; + ram_flags |= backend->guest_memfd ? RAM_GUEST_MEMFD : 0; return memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), name, backend->size, ram_flags, fd, 0, errp); } diff --git a/backends/hostmem-ram.c b/backends/hostmem-ram.c index d121249f0f..f7d81af783 100644 --- a/backends/hostmem-ram.c +++ b/backends/hostmem-ram.c @@ -30,6 +30,7 @@ ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) name = host_memory_backend_get_name(backend); ram_flags = backend->share ? RAM_SHARED : 0; ram_flags |= backend->reserve ? 0 : RAM_NORESERVE; + ram_flags |= backend->guest_memfd ? RAM_GUEST_MEMFD : 0; return memory_region_init_ram_flags_nomigrate(&backend->mr, OBJECT(backend), name, backend->size, ram_flags, errp); diff --git a/backends/hostmem.c b/backends/hostmem.c index 81a72ce40b..eb9682b4a8 100644 --- a/backends/hostmem.c +++ b/backends/hostmem.c @@ -277,6 +277,7 @@ static void host_memory_backend_init(Object *obj) /* TODO: convert access to globals to compat properties */ backend->merge = machine_mem_merge(machine); backend->dump = machine_dump_guest_core(machine); + backend->guest_memfd = machine_require_guest_memfd(machine); backend->reserve = true; backend->prealloc_threads = machine->smp.cpus; } diff --git a/configs/targets/aarch64-softmmu.mak b/configs/targets/aarch64-softmmu.mak index b4338e9568..83c22391a6 100644 --- a/configs/targets/aarch64-softmmu.mak +++ b/configs/targets/aarch64-softmmu.mak @@ -1,5 +1,6 @@ TARGET_ARCH=aarch64 TARGET_BASE_ARCH=arm TARGET_SUPPORTS_MTTCG=y +TARGET_KVM_HAVE_GUEST_DEBUG=y TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/arm-core.xml gdb-xml/arm-vfp.xml gdb-xml/arm-vfp3.xml gdb-xml/arm-vfp-sysregs.xml gdb-xml/arm-neon.xml gdb-xml/arm-m-profile.xml gdb-xml/arm-m-profile-mve.xml gdb-xml/aarch64-pauth.xml TARGET_NEED_FDT=y diff --git a/configs/targets/i386-softmmu.mak b/configs/targets/i386-softmmu.mak index 6b3c99fc86..d61b507613 100644 --- a/configs/targets/i386-softmmu.mak +++ b/configs/targets/i386-softmmu.mak @@ -1,4 +1,5 @@ TARGET_ARCH=i386 TARGET_SUPPORTS_MTTCG=y TARGET_NEED_FDT=y +TARGET_KVM_HAVE_GUEST_DEBUG=y TARGET_XML_FILES= gdb-xml/i386-32bit.xml diff --git a/configs/targets/ppc-softmmu.mak b/configs/targets/ppc-softmmu.mak index 774440108f..f3ea9c98f7 100644 --- a/configs/targets/ppc-softmmu.mak +++ b/configs/targets/ppc-softmmu.mak @@ -1,4 +1,5 @@ TARGET_ARCH=ppc TARGET_BIG_ENDIAN=y +TARGET_KVM_HAVE_GUEST_DEBUG=y TARGET_XML_FILES= gdb-xml/power-core.xml gdb-xml/power-fpu.xml gdb-xml/power-altivec.xml gdb-xml/power-spe.xml TARGET_NEED_FDT=y diff --git a/configs/targets/ppc64-softmmu.mak b/configs/targets/ppc64-softmmu.mak index ddf0c39617..1db8d8381d 100644 --- a/configs/targets/ppc64-softmmu.mak +++ b/configs/targets/ppc64-softmmu.mak @@ -2,5 +2,6 @@ TARGET_ARCH=ppc64 TARGET_BASE_ARCH=ppc TARGET_BIG_ENDIAN=y TARGET_SUPPORTS_MTTCG=y +TARGET_KVM_HAVE_GUEST_DEBUG=y TARGET_XML_FILES= gdb-xml/power64-core.xml gdb-xml/power-fpu.xml gdb-xml/power-altivec.xml gdb-xml/power-spe.xml gdb-xml/power-vsx.xml TARGET_NEED_FDT=y diff --git a/configs/targets/s390x-softmmu.mak b/configs/targets/s390x-softmmu.mak index 70d2f9f0ba..b22218aacc 100644 --- a/configs/targets/s390x-softmmu.mak +++ b/configs/targets/s390x-softmmu.mak @@ -1,4 +1,5 @@ TARGET_ARCH=s390x TARGET_BIG_ENDIAN=y TARGET_SUPPORTS_MTTCG=y +TARGET_KVM_HAVE_GUEST_DEBUG=y TARGET_XML_FILES= gdb-xml/s390x-core64.xml gdb-xml/s390-acr.xml gdb-xml/s390-fpr.xml gdb-xml/s390-vx.xml gdb-xml/s390-cr.xml gdb-xml/s390-virt.xml gdb-xml/s390-virt-kvm.xml gdb-xml/s390-gs.xml diff --git a/configs/targets/x86_64-softmmu.mak b/configs/targets/x86_64-softmmu.mak index 197817c943..c5f882e5ba 100644 --- a/configs/targets/x86_64-softmmu.mak +++ b/configs/targets/x86_64-softmmu.mak @@ -2,4 +2,5 @@ TARGET_ARCH=x86_64 TARGET_BASE_ARCH=i386 TARGET_SUPPORTS_MTTCG=y TARGET_NEED_FDT=y +TARGET_KVM_HAVE_GUEST_DEBUG=y TARGET_XML_FILES= gdb-xml/i386-64bit.xml diff --git a/docs/requirements.txt b/docs/requirements.txt index 691e5218ec..02583f209a 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,2 +1,5 @@ +# Used by readthedocs.io +# Should be in sync with the "installed" key of pythondeps.toml + sphinx==5.3.0 sphinx_rtd_theme==1.1.1 diff --git a/ebpf/meson.build b/ebpf/meson.build index c5bf9295a2..bff6156f51 100644 --- a/ebpf/meson.build +++ b/ebpf/meson.build @@ -1 +1 @@ -common_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: files('ebpf_rss-stub.c')) +system_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: files('ebpf_rss-stub.c')) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index a9a913aead..c9119ef384 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -3223,10 +3223,17 @@ static void machvirt_machine_init(void) } type_init(machvirt_machine_init); -static void virt_machine_9_0_options(MachineClass *mc) +static void virt_machine_9_1_options(MachineClass *mc) { } -DEFINE_VIRT_MACHINE_AS_LATEST(9, 0) +DEFINE_VIRT_MACHINE_AS_LATEST(9, 1) + +static void virt_machine_9_0_options(MachineClass *mc) +{ + virt_machine_9_1_options(mc); + compat_props_add(mc->compat_props, hw_compat_9_0, hw_compat_9_0_len); +} +DEFINE_VIRT_MACHINE(9, 0) static void virt_machine_8_2_options(MachineClass *mc) { diff --git a/hw/core/machine.c b/hw/core/machine.c index 37ede0e7d4..582c2df37a 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -33,6 +33,9 @@ #include "hw/virtio/virtio-iommu.h" #include "audio/audio.h" +GlobalProperty hw_compat_9_0[] = {}; +const size_t hw_compat_9_0_len = G_N_ELEMENTS(hw_compat_9_0); + GlobalProperty hw_compat_8_2[] = { { "migration", "zero-page-detection", "legacy"}, { TYPE_VIRTIO_IOMMU_PCI, "granule", "4k" }, @@ -1198,6 +1201,11 @@ bool machine_mem_merge(MachineState *machine) return machine->mem_merge; } +bool machine_require_guest_memfd(MachineState *machine) +{ + return machine->require_guest_memfd; +} + static char *cpu_slot_to_string(const CPUArchId *cpu) { GString *s = g_string_new(NULL); diff --git a/hw/core/meson.build b/hw/core/meson.build index e26f2e088c..f20d4143f7 100644 --- a/hw/core/meson.build +++ b/hw/core/meson.build @@ -3,7 +3,6 @@ hwcore_ss.add(files( 'bus.c', 'qdev-properties.c', 'qdev.c', - 'reset.c', 'resetcontainer.c', 'resettable.c', 'vmstate-if.c', @@ -12,16 +11,6 @@ hwcore_ss.add(files( 'clock.c', 'qdev-clock.c', )) -if have_system - hwcore_ss.add(files( - 'hotplug.c', - 'qdev-hotplug.c', - )) -else - hwcore_ss.add(files( - 'hotplug-stubs.c', - )) -endif common_ss.add(files('cpu-common.c')) common_ss.add(files('machine-smp.c')) @@ -40,6 +29,7 @@ system_ss.add(files( 'cpu-sysemu.c', 'fw-path-provider.c', 'gpio.c', + 'hotplug.c', 'loader.c', 'machine-hmp-cmds.c', 'machine-qmp-cmds.c', @@ -48,7 +38,9 @@ system_ss.add(files( 'null-machine.c', 'numa.c', 'qdev-fw.c', + 'qdev-hotplug.c', 'qdev-properties-system.c', + 'reset.c', 'sysbus.c', 'vm-change-state-handler.c', 'clock-vmstate.c', diff --git a/hw/display/meson.build b/hw/display/meson.build index f93a69f70f..4751aab3ba 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -3,7 +3,7 @@ hw_display_modules = {} system_ss.add(when: 'CONFIG_DDC', if_true: files('i2c-ddc.c')) system_ss.add(when: 'CONFIG_EDID', if_true: files('edid-generate.c', 'edid-region.c')) -system_ss.add(when: 'CONFIG_FW_CFG_DMA', if_true: files('ramfb.c')) +system_ss.add(when: 'CONFIG_FW_CFG_DMA', if_true: files('ramfb.c'), if_false: files('ramfb-stubs.c')) system_ss.add(when: 'CONFIG_FW_CFG_DMA', if_true: files('ramfb-standalone.c')) system_ss.add(when: 'CONFIG_VGA_CIRRUS', if_true: files('cirrus_vga.c')) diff --git a/stubs/ramfb.c b/hw/display/ramfb-stubs.c similarity index 100% rename from stubs/ramfb.c rename to hw/display/ramfb-stubs.c diff --git a/hw/display/vga.c b/hw/display/vga.c index 77f59e8c11..e91a76bf76 100644 --- a/hw/display/vga.c +++ b/hw/display/vga.c @@ -1574,22 +1574,16 @@ static void vga_draw_graphic(VGACommonState *s, int full_update) /* Horizontal pel panning bit 3 is only used in text mode. */ hpel = bits <= 8 ? s->params.hpel & 7 : 0; + bwidth = DIV_ROUND_UP(width * bits, 8); /* scanline length */ + if (hpel) { + bwidth += 4; + } region_start = (s->params.start_addr * 4); - region_end = region_start + (ram_addr_t)s->params.line_offset * height; - region_end += width * depth / 8; /* scanline length */ - region_end -= s->params.line_offset; - if (hpel) { - region_end += 4; - } - if (region_end > s->vbe_size || depth == 0 || depth == 15) { + region_end = region_start + (ram_addr_t)s->params.line_offset * (height - 1) + bwidth; + if (region_end > s->vbe_size) { /* - * We land here on: - * - wraps around (can happen with cirrus vbe modes) - * - depth == 0 (256 color palette video mode) - * - depth == 15 - * - * Take the safe and slow route: + * On wrap around take the safe and slow route: * - create a dirty bitmap snapshot for all vga memory. * - force shadowing (so all vga memory access goes * through vga_read_*() helpers). @@ -1602,6 +1596,10 @@ static void vga_draw_graphic(VGACommonState *s, int full_update) region_end = s->vbe_size; force_shadow = true; } + if (s->params.line_compare < height) { + /* split screen mode */ + region_start = 0; + } /* * Check whether we can share the surface with the backend @@ -1667,20 +1665,12 @@ static void vga_draw_graphic(VGACommonState *s, int full_update) s->params.line_compare, sr(s, VGA_SEQ_CLOCK_MODE)); #endif addr1 = (s->params.start_addr * 4); - bwidth = DIV_ROUND_UP(width * bits, 8); - if (hpel) { - bwidth += 4; - } y_start = -1; d = surface_data(surface); linesize = surface_stride(surface); y1 = 0; if (!full_update) { - if (s->params.line_compare < height) { - /* split screen mode */ - region_start = 0; - } snap = memory_region_snapshot_and_clear_dirty(&s->vram, region_start, region_end - region_start, DIRTY_MEMORY_VGA); diff --git a/hw/i386/acpi-common.c b/hw/i386/acpi-common.c index 20f19269da..0cc2919bb8 100644 --- a/hw/i386/acpi-common.c +++ b/hw/i386/acpi-common.c @@ -107,7 +107,9 @@ void acpi_build_madt(GArray *table_data, BIOSLinker *linker, acpi_table_begin(&table, table_data); /* Local APIC Address */ build_append_int_noprefix(table_data, APIC_DEFAULT_ADDRESS, 4); - build_append_int_noprefix(table_data, 1 /* PCAT_COMPAT */, 4); /* Flags */ + /* Flags. bit 0: PCAT_COMPAT */ + build_append_int_noprefix(table_data, + x86ms->pic != ON_OFF_AUTO_OFF ? 1 : 0 , 4); for (i = 0; i < apic_ids->len; i++) { pc_madt_cpu_entry(i, apic_ids, table_data, false); diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 5c21b0c4db..08c7de416f 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -78,6 +78,12 @@ { "qemu64-" TYPE_X86_CPU, "model-id", "QEMU Virtual CPU version " v, },\ { "athlon-" TYPE_X86_CPU, "model-id", "QEMU Virtual CPU version " v, }, +GlobalProperty pc_compat_9_0[] = { + { TYPE_X86_CPU, "guest-phys-bits", "0" }, + { "sev-guest", "legacy-vm-type", "true" }, +}; +const size_t pc_compat_9_0_len = G_N_ELEMENTS(pc_compat_9_0); + GlobalProperty pc_compat_8_2[] = {}; const size_t pc_compat_8_2_len = G_N_ELEMENTS(pc_compat_8_2); diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 18ba076609..8850c49c66 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -513,13 +513,26 @@ static void pc_i440fx_machine_options(MachineClass *m) "Use a different south bridge than PIIX3"); } -static void pc_i440fx_9_0_machine_options(MachineClass *m) +static void pc_i440fx_9_1_machine_options(MachineClass *m) { pc_i440fx_machine_options(m); m->alias = "pc"; m->is_default = true; } +DEFINE_I440FX_MACHINE(v9_1, "pc-i440fx-9.1", NULL, + pc_i440fx_9_1_machine_options); + +static void pc_i440fx_9_0_machine_options(MachineClass *m) +{ + pc_i440fx_9_1_machine_options(m); + m->alias = NULL; + m->is_default = false; + + compat_props_add(m->compat_props, hw_compat_9_0, hw_compat_9_0_len); + compat_props_add(m->compat_props, pc_compat_9_0, pc_compat_9_0_len); +} + DEFINE_I440FX_MACHINE(v9_0, "pc-i440fx-9.0", NULL, pc_i440fx_9_0_machine_options); @@ -528,8 +541,6 @@ static void pc_i440fx_8_2_machine_options(MachineClass *m) PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_i440fx_9_0_machine_options(m); - m->alias = NULL; - m->is_default = false; compat_props_add(m->compat_props, hw_compat_8_2, hw_compat_8_2_len); compat_props_add(m->compat_props, pc_compat_8_2, pc_compat_8_2_len); diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index c7bc8a2041..bb53a51ac1 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -219,6 +219,8 @@ static void pc_q35_init(MachineState *machine) x86ms->above_4g_mem_size, NULL); object_property_set_bool(phb, PCI_HOST_BYPASS_IOMMU, pcms->default_bus_bypass_iommu, NULL); + object_property_set_bool(phb, PCI_HOST_PROP_SMM_RANGES, + x86_machine_is_smm_enabled(x86ms), NULL); sysbus_realize_and_unref(SYS_BUS_DEVICE(phb), &error_fatal); /* pci */ @@ -365,12 +367,23 @@ static void pc_q35_machine_options(MachineClass *m) pc_q35_compat_defaults, pc_q35_compat_defaults_len); } -static void pc_q35_9_0_machine_options(MachineClass *m) +static void pc_q35_9_1_machine_options(MachineClass *m) { pc_q35_machine_options(m); m->alias = "q35"; } +DEFINE_Q35_MACHINE(v9_1, "pc-q35-9.1", NULL, + pc_q35_9_1_machine_options); + +static void pc_q35_9_0_machine_options(MachineClass *m) +{ + pc_q35_9_1_machine_options(m); + m->alias = NULL; + compat_props_add(m->compat_props, hw_compat_9_0, hw_compat_9_0_len); + compat_props_add(m->compat_props, pc_compat_9_0, pc_compat_9_0_len); +} + DEFINE_Q35_MACHINE(v9_0, "pc-q35-9.0", NULL, pc_q35_9_0_machine_options); @@ -378,7 +391,6 @@ static void pc_q35_8_2_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_q35_9_0_machine_options(m); - m->alias = NULL; m->max_cpus = 1024; compat_props_add(m->compat_props, hw_compat_8_2, hw_compat_8_2_len); compat_props_add(m->compat_props, pc_compat_8_2, pc_compat_8_2_len); diff --git a/hw/i386/x86.c b/hw/i386/x86.c index ffbda48917..3d5b51e92d 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -679,14 +679,6 @@ DeviceState *ioapic_init_secondary(GSIState *gsi_state) return dev; } -struct setup_data { - uint64_t next; - uint32_t type; - uint32_t len; - uint8_t data[]; -} __attribute__((packed)); - - /* * The entry point into the kernel for PVH boot is different from * the native entry point. The PVH entry is defined by the x86/HVM @@ -1389,6 +1381,16 @@ static void machine_set_sgx_epc(Object *obj, Visitor *v, const char *name, qapi_free_SgxEPCList(list); } +static int x86_kvm_type(MachineState *ms, const char *vm_type) +{ + /* + * No x86 machine has a kvm-type property. If one is added that has + * it, it should call kvm_get_vm_type() directly or not use it at all. + */ + assert(vm_type == NULL); + return kvm_enabled() ? kvm_get_vm_type(ms) : 0; +} + static void x86_machine_initfn(Object *obj) { X86MachineState *x86ms = X86_MACHINE(obj); @@ -1413,6 +1415,7 @@ static void x86_machine_class_init(ObjectClass *oc, void *data) mc->cpu_index_to_instance_props = x86_cpu_index_to_props; mc->get_default_cpu_node_id = x86_get_default_cpu_node_id; mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids; + mc->kvm_type = x86_kvm_type; x86mc->save_tsc_khz = true; x86mc->fwcfg_dma_enabled = true; nc->nmi_monitor_handler = x86_nmi; diff --git a/hw/m68k/virt.c b/hw/m68k/virt.c index b8e5e102e6..09bc9bdfef 100644 --- a/hw/m68k/virt.c +++ b/hw/m68k/virt.c @@ -357,10 +357,17 @@ type_init(virt_machine_register_types) } \ type_init(machvirt_machine_##major##_##minor##_init); -static void virt_machine_9_0_options(MachineClass *mc) +static void virt_machine_9_1_options(MachineClass *mc) { } -DEFINE_VIRT_MACHINE(9, 0, true) +DEFINE_VIRT_MACHINE(9, 1, true) + +static void virt_machine_9_0_options(MachineClass *mc) +{ + virt_machine_9_1_options(mc); + compat_props_add(mc->compat_props, hw_compat_9_0, hw_compat_9_0_len); +} +DEFINE_VIRT_MACHINE(9, 0, false) static void virt_machine_8_2_options(MachineClass *mc) { diff --git a/stubs/memory_device.c b/hw/mem/memory-device-stubs.c similarity index 100% rename from stubs/memory_device.c rename to hw/mem/memory-device-stubs.c diff --git a/hw/mem/meson.build b/hw/mem/meson.build index faee1fe936..1c1c6da24b 100644 --- a/hw/mem/meson.build +++ b/hw/mem/meson.build @@ -6,6 +6,7 @@ mem_ss.add(when: 'CONFIG_NVDIMM', if_true: files('nvdimm.c')) mem_ss.add(when: 'CONFIG_CXL_MEM_DEVICE', if_true: files('cxl_type3.c')) system_ss.add(when: 'CONFIG_CXL_MEM_DEVICE', if_false: files('cxl_type3_stubs.c')) +system_ss.add(when: 'CONFIG_MEM_DEVICE', if_false: files('memory-device-stubs.c')) system_ss.add_all(when: 'CONFIG_MEM_DEVICE', if_true: mem_ss) system_ss.add(when: 'CONFIG_SPARSE_MEM', if_true: files('sparse-mem.c')) diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c index 0d7d4e3f08..0b6cbaed7e 100644 --- a/hw/pci-host/q35.c +++ b/hw/pci-host/q35.c @@ -179,6 +179,8 @@ static Property q35_host_props[] = { mch.below_4g_mem_size, 0), DEFINE_PROP_SIZE(PCI_HOST_ABOVE_4G_MEM_SIZE, Q35PCIHost, mch.above_4g_mem_size, 0), + DEFINE_PROP_BOOL(PCI_HOST_PROP_SMM_RANGES, Q35PCIHost, + mch.has_smm_ranges, true), DEFINE_PROP_BOOL("x-pci-hole64-fix", Q35PCIHost, pci_hole64_fix, true), DEFINE_PROP_END_OF_LIST(), }; @@ -214,6 +216,7 @@ static void q35_host_initfn(Object *obj) /* mch's object_initialize resets the default value, set it again */ qdev_prop_set_uint64(DEVICE(s), PCI_HOST_PROP_PCI_HOLE64_SIZE, Q35_PCI_HOST_HOLE64_SIZE_DEFAULT); + object_property_add(obj, PCI_HOST_PROP_PCI_HOLE_START, "uint32", q35_host_get_pci_hole_start, NULL, NULL, NULL); @@ -476,6 +479,10 @@ static void mch_write_config(PCIDevice *d, mch_update_pciexbar(mch); } + if (!mch->has_smm_ranges) { + return; + } + if (ranges_overlap(address, len, MCH_HOST_BRIDGE_SMRAM, MCH_HOST_BRIDGE_SMRAM_SIZE)) { mch_update_smram(mch); @@ -494,10 +501,13 @@ static void mch_write_config(PCIDevice *d, static void mch_update(MCHPCIState *mch) { mch_update_pciexbar(mch); + mch_update_pam(mch); - mch_update_smram(mch); - mch_update_ext_tseg_mbytes(mch); - mch_update_smbase_smram(mch); + if (mch->has_smm_ranges) { + mch_update_smram(mch); + mch_update_ext_tseg_mbytes(mch); + mch_update_smbase_smram(mch); + } /* * pci hole goes from end-of-low-ram to io-apic. @@ -538,19 +548,21 @@ static void mch_reset(DeviceState *qdev) pci_set_quad(d->config + MCH_HOST_BRIDGE_PCIEXBAR, MCH_HOST_BRIDGE_PCIEXBAR_DEFAULT); - d->config[MCH_HOST_BRIDGE_SMRAM] = MCH_HOST_BRIDGE_SMRAM_DEFAULT; - d->config[MCH_HOST_BRIDGE_ESMRAMC] = MCH_HOST_BRIDGE_ESMRAMC_DEFAULT; - d->wmask[MCH_HOST_BRIDGE_SMRAM] = MCH_HOST_BRIDGE_SMRAM_WMASK; - d->wmask[MCH_HOST_BRIDGE_ESMRAMC] = MCH_HOST_BRIDGE_ESMRAMC_WMASK; + if (mch->has_smm_ranges) { + d->config[MCH_HOST_BRIDGE_SMRAM] = MCH_HOST_BRIDGE_SMRAM_DEFAULT; + d->config[MCH_HOST_BRIDGE_ESMRAMC] = MCH_HOST_BRIDGE_ESMRAMC_DEFAULT; + d->wmask[MCH_HOST_BRIDGE_SMRAM] = MCH_HOST_BRIDGE_SMRAM_WMASK; + d->wmask[MCH_HOST_BRIDGE_ESMRAMC] = MCH_HOST_BRIDGE_ESMRAMC_WMASK; - if (mch->ext_tseg_mbytes > 0) { - pci_set_word(d->config + MCH_HOST_BRIDGE_EXT_TSEG_MBYTES, - MCH_HOST_BRIDGE_EXT_TSEG_MBYTES_QUERY); + if (mch->ext_tseg_mbytes > 0) { + pci_set_word(d->config + MCH_HOST_BRIDGE_EXT_TSEG_MBYTES, + MCH_HOST_BRIDGE_EXT_TSEG_MBYTES_QUERY); + } + + d->config[MCH_HOST_BRIDGE_F_SMBASE] = 0; + d->wmask[MCH_HOST_BRIDGE_F_SMBASE] = 0xff; } - d->config[MCH_HOST_BRIDGE_F_SMBASE] = 0; - d->wmask[MCH_HOST_BRIDGE_F_SMBASE] = 0xff; - mch_update(mch); } @@ -568,6 +580,20 @@ static void mch_realize(PCIDevice *d, Error **errp) /* setup pci memory mapping */ pc_pci_as_mapping_init(mch->system_memory, mch->pci_address_space); + /* PAM */ + init_pam(&mch->pam_regions[0], OBJECT(mch), mch->ram_memory, + mch->system_memory, mch->pci_address_space, + PAM_BIOS_BASE, PAM_BIOS_SIZE); + for (i = 0; i < ARRAY_SIZE(mch->pam_regions) - 1; ++i) { + init_pam(&mch->pam_regions[i + 1], OBJECT(mch), mch->ram_memory, + mch->system_memory, mch->pci_address_space, + PAM_EXPAN_BASE + i * PAM_EXPAN_SIZE, PAM_EXPAN_SIZE); + } + + if (!mch->has_smm_ranges) { + return; + } + /* if *disabled* show SMRAM to all CPUs */ memory_region_init_alias(&mch->smram_region, OBJECT(mch), "smram-region", mch->pci_address_space, MCH_HOST_BRIDGE_SMRAM_C_BASE, @@ -634,15 +660,6 @@ static void mch_realize(PCIDevice *d, Error **errp) object_property_add_const_link(qdev_get_machine(), "smram", OBJECT(&mch->smram)); - - init_pam(&mch->pam_regions[0], OBJECT(mch), mch->ram_memory, - mch->system_memory, mch->pci_address_space, - PAM_BIOS_BASE, PAM_BIOS_SIZE); - for (i = 0; i < ARRAY_SIZE(mch->pam_regions) - 1; ++i) { - init_pam(&mch->pam_regions[i + 1], OBJECT(mch), mch->ram_memory, - mch->system_memory, mch->pci_address_space, - PAM_EXPAN_BASE + i * PAM_EXPAN_SIZE, PAM_EXPAN_SIZE); - } } uint64_t mch_mcfg_base(void) diff --git a/hw/ppc/pef.c b/hw/ppc/pef.c index d28ed3ba73..47553348b1 100644 --- a/hw/ppc/pef.c +++ b/hw/ppc/pef.c @@ -15,7 +15,6 @@ #include "sysemu/kvm.h" #include "migration/blocker.h" #include "exec/confidential-guest-support.h" -#include "hw/ppc/pef.h" #define TYPE_PEF_GUEST "pef-guest" OBJECT_DECLARE_SIMPLE_TYPE(PefGuest, PEF_GUEST) @@ -93,7 +92,7 @@ static int kvmppc_svm_off(Error **errp) #endif } -int pef_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) +static int pef_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) { if (!object_dynamic_cast(OBJECT(cgs), TYPE_PEF_GUEST)) { return 0; @@ -107,7 +106,7 @@ int pef_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) return kvmppc_svm_init(cgs, errp); } -int pef_kvm_reset(ConfidentialGuestSupport *cgs, Error **errp) +static int pef_kvm_reset(ConfidentialGuestSupport *cgs, Error **errp) { if (!object_dynamic_cast(OBJECT(cgs), TYPE_PEF_GUEST)) { return 0; @@ -131,6 +130,10 @@ OBJECT_DEFINE_TYPE_WITH_INTERFACES(PefGuest, static void pef_guest_class_init(ObjectClass *oc, void *data) { + ConfidentialGuestSupportClass *klass = CONFIDENTIAL_GUEST_SUPPORT_CLASS(oc); + + klass->kvm_init = pef_kvm_init; + klass->kvm_reset = pef_kvm_reset; } static void pef_guest_init(Object *obj) diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index e9bc97fee0..533ea0f914 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -75,6 +75,7 @@ #include "hw/virtio/vhost-scsi-common.h" #include "exec/ram_addr.h" +#include "exec/confidential-guest-support.h" #include "hw/usb.h" #include "qemu/config-file.h" #include "qemu/error-report.h" @@ -87,7 +88,6 @@ #include "hw/ppc/spapr_tpm_proxy.h" #include "hw/ppc/spapr_nvdimm.h" #include "hw/ppc/spapr_numa.h" -#include "hw/ppc/pef.h" #include "monitor/monitor.h" @@ -1715,7 +1715,9 @@ static void spapr_machine_reset(MachineState *machine, ShutdownCause reason) qemu_guest_getrandom_nofail(spapr->fdt_rng_seed, 32); } - pef_kvm_reset(machine->cgs, &error_fatal); + if (machine->cgs) { + confidential_guest_kvm_reset(machine->cgs, &error_fatal); + } spapr_caps_apply(spapr); spapr_nested_reset(spapr); @@ -2841,7 +2843,9 @@ static void spapr_machine_init(MachineState *machine) /* * if Secure VM (PEF) support is configured, then initialize it */ - pef_kvm_init(machine->cgs, &error_fatal); + if (machine->cgs) { + confidential_guest_kvm_init(machine->cgs, &error_fatal); + } msi_nonbroken = true; @@ -4806,14 +4810,25 @@ static void spapr_machine_latest_class_options(MachineClass *mc) type_init(spapr_machine_register_##suffix) /* - * pseries-9.0 + * pseries-9.1 */ -static void spapr_machine_9_0_class_options(MachineClass *mc) +static void spapr_machine_9_1_class_options(MachineClass *mc) { /* Defaults for the latest behaviour inherited from the base class */ } -DEFINE_SPAPR_MACHINE(9_0, "9.0", true); +DEFINE_SPAPR_MACHINE(9_1, "9.1", true); + +/* + * pseries-9.0 + */ +static void spapr_machine_9_0_class_options(MachineClass *mc) +{ + spapr_machine_9_1_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_9_0, hw_compat_9_0_len); +} + +DEFINE_SPAPR_MACHINE(9_0, "9.0", false); /* * pseries-8.2 diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index b1dcb3857f..4dcc213820 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -14,6 +14,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "exec/ram_addr.h" +#include "exec/confidential-guest-support.h" #include "hw/s390x/s390-virtio-hcall.h" #include "hw/s390x/sclp.h" #include "hw/s390x/s390_flic.h" @@ -260,7 +261,9 @@ static void ccw_init(MachineState *machine) s390_init_cpus(machine); /* Need CPU model to be determined before we can set up PV */ - s390_pv_init(machine->cgs, &error_fatal); + if (machine->cgs) { + confidential_guest_kvm_init(machine->cgs, &error_fatal); + } s390_flic_init(); @@ -859,14 +862,26 @@ bool css_migration_enabled(void) } \ type_init(ccw_machine_register_##suffix) +static void ccw_machine_9_1_instance_options(MachineState *machine) +{ +} + +static void ccw_machine_9_1_class_options(MachineClass *mc) +{ +} +DEFINE_CCW_MACHINE(9_1, "9.1", true); + static void ccw_machine_9_0_instance_options(MachineState *machine) { + ccw_machine_9_1_instance_options(machine); } static void ccw_machine_9_0_class_options(MachineClass *mc) { + ccw_machine_9_1_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_9_0, hw_compat_9_0_len); } -DEFINE_CCW_MACHINE(9_0, "9.0", true); +DEFINE_CCW_MACHINE(9_0, "9.0", false); static void ccw_machine_8_2_instance_options(MachineState *machine) { diff --git a/stubs/usb-dev-stub.c b/hw/usb/bus-stub.c similarity index 83% rename from stubs/usb-dev-stub.c rename to hw/usb/bus-stub.c index aa557692b7..fcabe8429e 100644 --- a/stubs/usb-dev-stub.c +++ b/hw/usb/bus-stub.c @@ -26,8 +26,3 @@ HumanReadableText *qmp_x_query_usb(Error **errp) error_setg(errp, "Support for USB devices not built-in"); return NULL; } - -void hmp_info_usb(Monitor *mon, const QDict *qdict) -{ - monitor_printf(mon, "Support for USB devices not built-in\n"); -} diff --git a/hw/usb/meson.build b/hw/usb/meson.build index aac3bb35f2..23f7f7acb5 100644 --- a/hw/usb/meson.build +++ b/hw/usb/meson.build @@ -9,7 +9,7 @@ system_ss.add(when: 'CONFIG_USB', if_true: files( 'desc-msos.c', 'libhw.c', 'pcap.c', -)) +), if_false: files('bus-stub.c')) # usb host adapters system_ss.add(when: 'CONFIG_USB_UHCI', if_true: files('hcd-uhci.c')) diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build index d7f18c96e6..621fc65454 100644 --- a/hw/virtio/meson.build +++ b/hw/virtio/meson.build @@ -87,6 +87,8 @@ specific_virtio_ss.add_all(when: 'CONFIG_VIRTIO_PCI', if_true: virtio_pci_ss) system_ss.add_all(when: 'CONFIG_VIRTIO', if_true: system_virtio_ss) system_ss.add(when: 'CONFIG_VIRTIO', if_false: files('vhost-stub.c')) system_ss.add(when: 'CONFIG_VIRTIO', if_false: files('virtio-stub.c')) +system_ss.add(when: 'CONFIG_VIRTIO_MD', if_false: files('virtio-md-stubs.c')) + system_ss.add(files('virtio-hmp-cmds.c')) specific_ss.add_all(when: 'CONFIG_VIRTIO', if_true: specific_virtio_ss) diff --git a/stubs/virtio-md-pci.c b/hw/virtio/virtio-md-stubs.c similarity index 100% rename from stubs/virtio-md-pci.c rename to hw/virtio/virtio-md-stubs.c diff --git a/include/exec/confidential-guest-support.h b/include/exec/confidential-guest-support.h index ba2dd4b5df..e5b188cffb 100644 --- a/include/exec/confidential-guest-support.h +++ b/include/exec/confidential-guest-support.h @@ -23,7 +23,10 @@ #include "qom/object.h" #define TYPE_CONFIDENTIAL_GUEST_SUPPORT "confidential-guest-support" -OBJECT_DECLARE_SIMPLE_TYPE(ConfidentialGuestSupport, CONFIDENTIAL_GUEST_SUPPORT) +OBJECT_DECLARE_TYPE(ConfidentialGuestSupport, + ConfidentialGuestSupportClass, + CONFIDENTIAL_GUEST_SUPPORT) + struct ConfidentialGuestSupport { Object parent; @@ -55,8 +58,37 @@ struct ConfidentialGuestSupport { typedef struct ConfidentialGuestSupportClass { ObjectClass parent; + + int (*kvm_init)(ConfidentialGuestSupport *cgs, Error **errp); + int (*kvm_reset)(ConfidentialGuestSupport *cgs, Error **errp); } ConfidentialGuestSupportClass; +static inline int confidential_guest_kvm_init(ConfidentialGuestSupport *cgs, + Error **errp) +{ + ConfidentialGuestSupportClass *klass; + + klass = CONFIDENTIAL_GUEST_SUPPORT_GET_CLASS(cgs); + if (klass->kvm_init) { + return klass->kvm_init(cgs, errp); + } + + return 0; +} + +static inline int confidential_guest_kvm_reset(ConfidentialGuestSupport *cgs, + Error **errp) +{ + ConfidentialGuestSupportClass *klass; + + klass = CONFIDENTIAL_GUEST_SUPPORT_GET_CLASS(cgs); + if (klass->kvm_reset) { + return klass->kvm_reset(cgs, errp); + } + + return 0; +} + #endif /* !CONFIG_USER_ONLY */ #endif /* QEMU_CONFIDENTIAL_GUEST_SUPPORT_H */ diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 6346df17ce..6d5318895a 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -159,6 +159,8 @@ typedef int (RAMBlockIterFunc)(RAMBlock *rb, void *opaque); int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque); int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length); +int ram_block_discard_guest_memfd_range(RAMBlock *rb, uint64_t start, + size_t length); #endif diff --git a/include/exec/memory.h b/include/exec/memory.h index 8626a355b3..679a847685 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -243,6 +243,9 @@ typedef struct IOMMUTLBEvent { /* RAM FD is opened read-only */ #define RAM_READONLY_FD (1 << 11) +/* RAM can be private that has kvm guest memfd backend */ +#define RAM_GUEST_MEMFD (1 << 12) + static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn, IOMMUNotifierFlag flags, hwaddr start, hwaddr end, @@ -1307,7 +1310,8 @@ bool memory_region_init_ram_nomigrate(MemoryRegion *mr, * @name: Region name, becomes part of RAMBlock name used in migration stream * must be unique within any device * @size: size of the region. - * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_NORESERVE. + * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_NORESERVE, + * RAM_GUEST_MEMFD. * @errp: pointer to Error*, to store an error if it happens. * * Note that this function does not do anything to cause the data in the @@ -1369,7 +1373,7 @@ bool memory_region_init_resizeable_ram(MemoryRegion *mr, * (getpagesize()) will be used. * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, * RAM_NORESERVE, RAM_PROTECTED, RAM_NAMED_FILE, RAM_READONLY, - * RAM_READONLY_FD + * RAM_READONLY_FD, RAM_GUEST_MEMFD * @path: the path in which to allocate the RAM. * @offset: offset within the file referenced by path * @errp: pointer to Error*, to store an error if it happens. @@ -1399,7 +1403,7 @@ bool memory_region_init_ram_from_file(MemoryRegion *mr, * @size: size of the region. * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, * RAM_NORESERVE, RAM_PROTECTED, RAM_NAMED_FILE, RAM_READONLY, - * RAM_READONLY_FD + * RAM_READONLY_FD, RAM_GUEST_MEMFD * @fd: the fd to mmap. * @offset: offset within the file referenced by fd * @errp: pointer to Error*, to store an error if it happens. @@ -1722,6 +1726,16 @@ static inline bool memory_region_is_romd(MemoryRegion *mr) */ bool memory_region_is_protected(MemoryRegion *mr); +/** + * memory_region_has_guest_memfd: check whether a memory region has guest_memfd + * associated + * + * Returns %true if a memory region's ram_block has valid guest_memfd assigned. + * + * @mr: the memory region being queried + */ +bool memory_region_has_guest_memfd(MemoryRegion *mr); + /** * memory_region_get_iommu: check whether a memory region is an iommu * diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index de45ba7bc9..07c8f86375 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -110,7 +110,7 @@ long qemu_maxrampagesize(void); * @mr: the memory region where the ram block is * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, * RAM_NORESERVE, RAM_PROTECTED, RAM_NAMED_FILE, RAM_READONLY, - * RAM_READONLY_FD + * RAM_READONLY_FD, RAM_GUEST_MEMFD * @mem_path or @fd: specify the backing file or device * @offset: Offset into target file * @errp: pointer to Error*, to store an error if it happens diff --git a/include/exec/ramblock.h b/include/exec/ramblock.h index 848915ea5b..459c8917de 100644 --- a/include/exec/ramblock.h +++ b/include/exec/ramblock.h @@ -41,6 +41,7 @@ struct RAMBlock { QLIST_HEAD(, RAMBlockNotifier) ramblock_notifiers; int fd; uint64_t fd_offset; + int guest_memfd; size_t page_size; /* dirty bitmap used during migration */ unsigned long *bmap; diff --git a/include/hw/boards.h b/include/hw/boards.h index 8b8f6d5c00..69c1ba45cf 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -36,6 +36,7 @@ bool machine_usb(MachineState *machine); int machine_phandle_start(MachineState *machine); bool machine_dump_guest_core(MachineState *machine); bool machine_mem_merge(MachineState *machine); +bool machine_require_guest_memfd(MachineState *machine); HotpluggableCPUList *machine_query_hotpluggable_cpus(MachineState *machine); void machine_set_cpu_numa_node(MachineState *machine, const CpuInstanceProperties *props, @@ -370,6 +371,7 @@ struct MachineState { char *dt_compatible; bool dump_guest_core; bool mem_merge; + bool require_guest_memfd; bool usb; bool usb_disabled; char *firmware; @@ -425,6 +427,9 @@ struct MachineState { } \ type_init(machine_initfn##_register_types) +extern GlobalProperty hw_compat_9_0[]; +extern const size_t hw_compat_9_0_len; + extern GlobalProperty hw_compat_8_2[]; extern const size_t hw_compat_8_2_len; diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 27a68071d7..e52290916c 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -161,6 +161,7 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level); #define PCI_HOST_PROP_PCI_HOLE64_SIZE "pci-hole64-size" #define PCI_HOST_BELOW_4G_MEM_SIZE "below-4g-mem-size" #define PCI_HOST_ABOVE_4G_MEM_SIZE "above-4g-mem-size" +#define PCI_HOST_PROP_SMM_RANGES "smm-ranges" void pc_pci_as_mapping_init(MemoryRegion *system_memory, @@ -198,6 +199,9 @@ void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size); /* sgx.c */ void pc_machine_init_sgx_epc(PCMachineState *pcms); +extern GlobalProperty pc_compat_9_0[]; +extern const size_t pc_compat_9_0_len; + extern GlobalProperty pc_compat_8_2[]; extern const size_t pc_compat_8_2_len; diff --git a/include/hw/pci-host/q35.h b/include/hw/pci-host/q35.h index bafcbe6752..22fadfa3ed 100644 --- a/include/hw/pci-host/q35.h +++ b/include/hw/pci-host/q35.h @@ -50,6 +50,7 @@ struct MCHPCIState { MemoryRegion tseg_blackhole, tseg_window; MemoryRegion smbase_blackhole, smbase_window; bool has_smram_at_smbase; + bool has_smm_ranges; Range pci_hole; uint64_t below_4g_mem_size; uint64_t above_4g_mem_size; diff --git a/include/hw/ppc/pef.h b/include/hw/ppc/pef.h deleted file mode 100644 index 707dbe524c..0000000000 --- a/include/hw/ppc/pef.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * PEF (Protected Execution Facility) for POWER support - * - * Copyright Red Hat. - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef HW_PPC_PEF_H -#define HW_PPC_PEF_H - -int pef_kvm_init(ConfidentialGuestSupport *cgs, Error **errp); -int pef_kvm_reset(ConfidentialGuestSupport *cgs, Error **errp); - -#endif /* HW_PPC_PEF_H */ diff --git a/include/qemu/config-file.h b/include/qemu/config-file.h index b82a778123..51b310fa3b 100644 --- a/include/qemu/config-file.h +++ b/include/qemu/config-file.h @@ -8,6 +8,9 @@ QemuOptsList *qemu_find_opts(const char *group); QemuOptsList *qemu_find_opts_err(const char *group, Error **errp); QemuOpts *qemu_find_opts_singleton(const char *group); +extern QemuOptsList *vm_config_groups[]; +extern QemuOptsList *drive_config_groups[]; + void qemu_add_opts(QemuOptsList *list); void qemu_add_drive_opts(QemuOptsList *list); int qemu_global_option(const char *str); diff --git a/include/standard-headers/asm-x86/bootparam.h b/include/standard-headers/asm-x86/bootparam.h index 0b06d2bff1..b582a105c0 100644 --- a/include/standard-headers/asm-x86/bootparam.h +++ b/include/standard-headers/asm-x86/bootparam.h @@ -2,21 +2,7 @@ #ifndef _ASM_X86_BOOTPARAM_H #define _ASM_X86_BOOTPARAM_H -/* setup_data/setup_indirect types */ -#define SETUP_NONE 0 -#define SETUP_E820_EXT 1 -#define SETUP_DTB 2 -#define SETUP_PCI 3 -#define SETUP_EFI 4 -#define SETUP_APPLE_PROPERTIES 5 -#define SETUP_JAILHOUSE 6 -#define SETUP_CC_BLOB 7 -#define SETUP_IMA 8 -#define SETUP_RNG_SEED 9 -#define SETUP_ENUM_MAX SETUP_RNG_SEED - -#define SETUP_INDIRECT (1<<31) -#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) +#include "standard-headers/asm-x86/setup_data.h" /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF @@ -38,6 +24,7 @@ #define XLF_EFI_KEXEC (1<<4) #define XLF_5LEVEL (1<<5) #define XLF_5LEVEL_ENABLED (1<<6) +#define XLF_MEM_ENCRYPTION (1<<7) #endif /* _ASM_X86_BOOTPARAM_H */ diff --git a/include/standard-headers/asm-x86/kvm_para.h b/include/standard-headers/asm-x86/kvm_para.h index f0235e58a1..9a011d20f0 100644 --- a/include/standard-headers/asm-x86/kvm_para.h +++ b/include/standard-headers/asm-x86/kvm_para.h @@ -92,7 +92,7 @@ struct kvm_clock_pairing { #define KVM_ASYNC_PF_DELIVERY_AS_INT (1 << 3) /* MSR_KVM_ASYNC_PF_INT */ -#define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0) +#define KVM_ASYNC_PF_VEC_MASK __GENMASK(7, 0) /* MSR_KVM_MIGRATION_CONTROL */ #define KVM_MIGRATION_READY (1 << 0) @@ -142,7 +142,6 @@ struct kvm_vcpu_pv_apf_data { uint32_t token; uint8_t pad[56]; - uint32_t enabled; }; #define KVM_PV_EOI_BIT 0 diff --git a/include/standard-headers/asm-x86/setup_data.h b/include/standard-headers/asm-x86/setup_data.h new file mode 100644 index 0000000000..09355f54c5 --- /dev/null +++ b/include/standard-headers/asm-x86/setup_data.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_X86_SETUP_DATA_H +#define _ASM_X86_SETUP_DATA_H + +/* setup_data/setup_indirect types */ +#define SETUP_NONE 0 +#define SETUP_E820_EXT 1 +#define SETUP_DTB 2 +#define SETUP_PCI 3 +#define SETUP_EFI 4 +#define SETUP_APPLE_PROPERTIES 5 +#define SETUP_JAILHOUSE 6 +#define SETUP_CC_BLOB 7 +#define SETUP_IMA 8 +#define SETUP_RNG_SEED 9 +#define SETUP_ENUM_MAX SETUP_RNG_SEED + +#define SETUP_INDIRECT (1<<31) +#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) + +#ifndef __ASSEMBLY__ + +#include "standard-headers/linux/types.h" + +/* extensible setup data list node */ +struct setup_data { + uint64_t next; + uint32_t type; + uint32_t len; + uint8_t data[]; +}; + +/* extensible setup indirect data node */ +struct setup_indirect { + uint32_t type; + uint32_t reserved; /* Reserved, must be set to zero. */ + uint64_t len; + uint64_t addr; +}; + +/* + * The E820 memory region entry of the boot protocol ABI: + */ +struct boot_e820_entry { + uint64_t addr; + uint64_t size; + uint32_t type; +} QEMU_PACKED; + +/* + * The boot loader is passing platform information via this Jailhouse-specific + * setup data structure. + */ +struct jailhouse_setup_data { + struct { + uint16_t version; + uint16_t compatible_version; + } QEMU_PACKED hdr; + struct { + uint16_t pm_timer_address; + uint16_t num_cpus; + uint64_t pci_mmconfig_base; + uint32_t tsc_khz; + uint32_t apic_khz; + uint8_t standard_ioapic; + uint8_t cpu_ids[255]; + } QEMU_PACKED v1; + struct { + uint32_t flags; + } QEMU_PACKED v2; +} QEMU_PACKED; + +/* + * IMA buffer setup data information from the previous kernel during kexec + */ +struct ima_setup_data { + uint64_t addr; + uint64_t size; +} QEMU_PACKED; + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_SETUP_DATA_H */ diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index dfb54eff6f..01503784d2 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -2023,6 +2023,53 @@ static inline int ethtool_validate_duplex(uint8_t duplex) #define IPV4_FLOW 0x10 /* hash only */ #define IPV6_FLOW 0x11 /* hash only */ #define ETHER_FLOW 0x12 /* spec only (ether_spec) */ + +/* Used for GTP-U IPv4 and IPv6. + * The format of GTP packets only includes + * elements such as TEID and GTP version. + * It is primarily intended for data communication of the UE. + */ +#define GTPU_V4_FLOW 0x13 /* hash only */ +#define GTPU_V6_FLOW 0x14 /* hash only */ + +/* Use for GTP-C IPv4 and v6. + * The format of these GTP packets does not include TEID. + * Primarily expected to be used for communication + * to create sessions for UE data communication, + * commonly referred to as CSR (Create Session Request). + */ +#define GTPC_V4_FLOW 0x15 /* hash only */ +#define GTPC_V6_FLOW 0x16 /* hash only */ + +/* Use for GTP-C IPv4 and v6. + * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. + * After session creation, it becomes this packet. + * This is mainly used for requests to realize UE handover. + */ +#define GTPC_TEID_V4_FLOW 0x17 /* hash only */ +#define GTPC_TEID_V6_FLOW 0x18 /* hash only */ + +/* Use for GTP-U and extended headers for the PSC (PDU Session Container). + * The format of these GTP packets includes TEID and QFI. + * In 5G communication using UPF (User Plane Function), + * data communication with this extended header is performed. + */ +#define GTPU_EH_V4_FLOW 0x19 /* hash only */ +#define GTPU_EH_V6_FLOW 0x1a /* hash only */ + +/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. + * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by + * UL/DL included in the PSC. + * There are differences in the data included based on Downlink/Uplink, + * and can be used to distinguish packets. + * The functions described so far are useful when you want to + * handle communication from the mobile network in UPF, PGW, etc. + */ +#define GTPU_UL_V4_FLOW 0x1b /* hash only */ +#define GTPU_UL_V6_FLOW 0x1c /* hash only */ +#define GTPU_DL_V4_FLOW 0x1d /* hash only */ +#define GTPU_DL_V6_FLOW 0x1e /* hash only */ + /* Flag to enable additional fields in struct ethtool_rx_flow_spec */ #define FLOW_EXT 0x80000000 #define FLOW_MAC_EXT 0x40000000 @@ -2037,6 +2084,7 @@ static inline int ethtool_validate_duplex(uint8_t duplex) #define RXH_IP_DST (1 << 5) #define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ #define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ +#define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */ #define RXH_DISCARD (1 << 31) #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h index fc0dcd10ae..bac9dbc49f 100644 --- a/include/standard-headers/linux/fuse.h +++ b/include/standard-headers/linux/fuse.h @@ -211,6 +211,12 @@ * 7.39 * - add FUSE_DIRECT_IO_ALLOW_MMAP * - add FUSE_STATX and related structures + * + * 7.40 + * - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH init flag + * - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag + * - add FUSE_NO_EXPORT_SUPPORT init flag + * - add FUSE_NOTIFY_RESEND, add FUSE_HAS_RESEND init flag */ #ifndef _LINUX_FUSE_H @@ -242,7 +248,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 39 +#define FUSE_KERNEL_MINOR_VERSION 40 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -349,6 +355,7 @@ struct fuse_file_lock { * FOPEN_STREAM: the file is stream-like (no file position at all) * FOPEN_NOFLUSH: don't flush data cache on close (unless FUSE_WRITEBACK_CACHE) * FOPEN_PARALLEL_DIRECT_WRITES: Allow concurrent direct writes on the same inode + * FOPEN_PASSTHROUGH: passthrough read/write io for this open file */ #define FOPEN_DIRECT_IO (1 << 0) #define FOPEN_KEEP_CACHE (1 << 1) @@ -357,6 +364,7 @@ struct fuse_file_lock { #define FOPEN_STREAM (1 << 4) #define FOPEN_NOFLUSH (1 << 5) #define FOPEN_PARALLEL_DIRECT_WRITES (1 << 6) +#define FOPEN_PASSTHROUGH (1 << 7) /** * INIT request/reply flags @@ -406,6 +414,9 @@ struct fuse_file_lock { * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. + * FUSE_NO_EXPORT_SUPPORT: explicitly disable export support + * FUSE_HAS_RESEND: kernel supports resending pending requests, and the high bit + * of the request ID indicates resend requests */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -445,6 +456,9 @@ struct fuse_file_lock { #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) #define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) +#define FUSE_PASSTHROUGH (1ULL << 37) +#define FUSE_NO_EXPORT_SUPPORT (1ULL << 38) +#define FUSE_HAS_RESEND (1ULL << 39) /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP @@ -631,6 +645,7 @@ enum fuse_notify_code { FUSE_NOTIFY_STORE = 4, FUSE_NOTIFY_RETRIEVE = 5, FUSE_NOTIFY_DELETE = 6, + FUSE_NOTIFY_RESEND = 7, FUSE_NOTIFY_CODE_MAX, }; @@ -757,7 +772,7 @@ struct fuse_create_in { struct fuse_open_out { uint64_t fh; uint32_t open_flags; - uint32_t padding; + int32_t backing_id; }; struct fuse_release_in { @@ -873,7 +888,8 @@ struct fuse_init_out { uint16_t max_pages; uint16_t map_alignment; uint32_t flags2; - uint32_t unused[7]; + uint32_t max_stack_depth; + uint32_t unused[6]; }; #define CUSE_INIT_INFO_MAX 4096 @@ -956,6 +972,14 @@ struct fuse_fallocate_in { uint32_t padding; }; +/** + * FUSE request unique ID flag + * + * Indicates whether this is a resend request. The receiver should handle this + * request accordingly. + */ +#define FUSE_UNIQUE_RESEND (1ULL << 63) + struct fuse_in_header { uint32_t len; uint32_t opcode; @@ -1045,9 +1069,18 @@ struct fuse_notify_retrieve_in { uint64_t dummy4; }; +struct fuse_backing_map { + int32_t fd; + uint32_t flags; + uint64_t padding; +}; + /* Device ioctls: */ #define FUSE_DEV_IOC_MAGIC 229 #define FUSE_DEV_IOC_CLONE _IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t) +#define FUSE_DEV_IOC_BACKING_OPEN _IOW(FUSE_DEV_IOC_MAGIC, 1, \ + struct fuse_backing_map) +#define FUSE_DEV_IOC_BACKING_CLOSE _IOW(FUSE_DEV_IOC_MAGIC, 2, uint32_t) struct fuse_lseek_in { uint64_t fh; diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index f6bab08540..2221b0c383 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -602,6 +602,7 @@ #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ #define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ +#define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */ #define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ #define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ diff --git a/include/standard-headers/linux/virtio_gpu.h b/include/standard-headers/linux/virtio_gpu.h index 2da48d3d4c..2db643ed8f 100644 --- a/include/standard-headers/linux/virtio_gpu.h +++ b/include/standard-headers/linux/virtio_gpu.h @@ -309,6 +309,8 @@ struct virtio_gpu_cmd_submit { #define VIRTIO_GPU_CAPSET_VIRGL 1 #define VIRTIO_GPU_CAPSET_VIRGL2 2 +/* 3 is reserved for gfxstream */ +#define VIRTIO_GPU_CAPSET_VENUS 4 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ struct virtio_gpu_get_capset_info { diff --git a/include/standard-headers/linux/virtio_pci.h b/include/standard-headers/linux/virtio_pci.h index 3e2bc2c97e..4010216103 100644 --- a/include/standard-headers/linux/virtio_pci.h +++ b/include/standard-headers/linux/virtio_pci.h @@ -240,7 +240,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ 0x5 #define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO 0x6 -struct QEMU_PACKED virtio_admin_cmd_hdr { +struct virtio_admin_cmd_hdr { uint16_t opcode; /* * 1 - SR-IOV @@ -252,20 +252,20 @@ struct QEMU_PACKED virtio_admin_cmd_hdr { uint64_t group_member_id; }; -struct QEMU_PACKED virtio_admin_cmd_status { +struct virtio_admin_cmd_status { uint16_t status; uint16_t status_qualifier; /* Unused, reserved for future extensions. */ uint8_t reserved2[4]; }; -struct QEMU_PACKED virtio_admin_cmd_legacy_wr_data { +struct virtio_admin_cmd_legacy_wr_data { uint8_t offset; /* Starting offset of the register(s) to write. */ uint8_t reserved[7]; uint8_t registers[]; }; -struct QEMU_PACKED virtio_admin_cmd_legacy_rd_data { +struct virtio_admin_cmd_legacy_rd_data { uint8_t offset; /* Starting offset of the register(s) to read. */ }; @@ -275,7 +275,7 @@ struct QEMU_PACKED virtio_admin_cmd_legacy_rd_data { #define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4 -struct QEMU_PACKED virtio_admin_cmd_notify_info_data { +struct virtio_admin_cmd_notify_info_data { uint8_t flags; /* 0 = end of list, 1 = owner device, 2 = member device */ uint8_t bar; /* BAR of the member or the owner device */ uint8_t padding[6]; diff --git a/include/standard-headers/linux/virtio_snd.h b/include/standard-headers/linux/virtio_snd.h index 1af96b9fc6..860f12e0a4 100644 --- a/include/standard-headers/linux/virtio_snd.h +++ b/include/standard-headers/linux/virtio_snd.h @@ -7,6 +7,14 @@ #include "standard-headers/linux/virtio_types.h" +/******************************************************************************* + * FEATURE BITS + */ +enum { + /* device supports control elements */ + VIRTIO_SND_F_CTLS = 0 +}; + /******************************************************************************* * CONFIGURATION SPACE */ @@ -17,6 +25,8 @@ struct virtio_snd_config { uint32_t streams; /* # of available channel maps */ uint32_t chmaps; + /* # of available control elements */ + uint32_t controls; }; enum { @@ -55,6 +65,15 @@ enum { /* channel map control request types */ VIRTIO_SND_R_CHMAP_INFO = 0x0200, + /* control element request types */ + VIRTIO_SND_R_CTL_INFO = 0x0300, + VIRTIO_SND_R_CTL_ENUM_ITEMS, + VIRTIO_SND_R_CTL_READ, + VIRTIO_SND_R_CTL_WRITE, + VIRTIO_SND_R_CTL_TLV_READ, + VIRTIO_SND_R_CTL_TLV_WRITE, + VIRTIO_SND_R_CTL_TLV_COMMAND, + /* jack event types */ VIRTIO_SND_EVT_JACK_CONNECTED = 0x1000, VIRTIO_SND_EVT_JACK_DISCONNECTED, @@ -63,6 +82,9 @@ enum { VIRTIO_SND_EVT_PCM_PERIOD_ELAPSED = 0x1100, VIRTIO_SND_EVT_PCM_XRUN, + /* control element event types */ + VIRTIO_SND_EVT_CTL_NOTIFY = 0x1200, + /* common status codes */ VIRTIO_SND_S_OK = 0x8000, VIRTIO_SND_S_BAD_MSG, @@ -331,4 +353,136 @@ struct virtio_snd_chmap_info { uint8_t positions[VIRTIO_SND_CHMAP_MAX_SIZE]; }; +/******************************************************************************* + * CONTROL ELEMENTS MESSAGES + */ +struct virtio_snd_ctl_hdr { + /* VIRTIO_SND_R_CTL_XXX */ + struct virtio_snd_hdr hdr; + /* 0 ... virtio_snd_config::controls - 1 */ + uint32_t control_id; +}; + +/* supported roles for control elements */ +enum { + VIRTIO_SND_CTL_ROLE_UNDEFINED = 0, + VIRTIO_SND_CTL_ROLE_VOLUME, + VIRTIO_SND_CTL_ROLE_MUTE, + VIRTIO_SND_CTL_ROLE_GAIN +}; + +/* supported value types for control elements */ +enum { + VIRTIO_SND_CTL_TYPE_BOOLEAN = 0, + VIRTIO_SND_CTL_TYPE_INTEGER, + VIRTIO_SND_CTL_TYPE_INTEGER64, + VIRTIO_SND_CTL_TYPE_ENUMERATED, + VIRTIO_SND_CTL_TYPE_BYTES, + VIRTIO_SND_CTL_TYPE_IEC958 +}; + +/* supported access rights for control elements */ +enum { + VIRTIO_SND_CTL_ACCESS_READ = 0, + VIRTIO_SND_CTL_ACCESS_WRITE, + VIRTIO_SND_CTL_ACCESS_VOLATILE, + VIRTIO_SND_CTL_ACCESS_INACTIVE, + VIRTIO_SND_CTL_ACCESS_TLV_READ, + VIRTIO_SND_CTL_ACCESS_TLV_WRITE, + VIRTIO_SND_CTL_ACCESS_TLV_COMMAND +}; + +struct virtio_snd_ctl_info { + /* common header */ + struct virtio_snd_info hdr; + /* element role (VIRTIO_SND_CTL_ROLE_XXX) */ + uint32_t role; + /* element value type (VIRTIO_SND_CTL_TYPE_XXX) */ + uint32_t type; + /* element access right bit map (1 << VIRTIO_SND_CTL_ACCESS_XXX) */ + uint32_t access; + /* # of members in the element value */ + uint32_t count; + /* index for an element with a non-unique name */ + uint32_t index; + /* name identifier string for the element */ + uint8_t name[44]; + /* additional information about the element's value */ + union { + /* VIRTIO_SND_CTL_TYPE_INTEGER */ + struct { + /* minimum supported value */ + uint32_t min; + /* maximum supported value */ + uint32_t max; + /* fixed step size for value (0 = variable size) */ + uint32_t step; + } integer; + /* VIRTIO_SND_CTL_TYPE_INTEGER64 */ + struct { + /* minimum supported value */ + uint64_t min; + /* maximum supported value */ + uint64_t max; + /* fixed step size for value (0 = variable size) */ + uint64_t step; + } integer64; + /* VIRTIO_SND_CTL_TYPE_ENUMERATED */ + struct { + /* # of options supported for value */ + uint32_t items; + } enumerated; + } value; +}; + +struct virtio_snd_ctl_enum_item { + /* option name */ + uint8_t item[64]; +}; + +struct virtio_snd_ctl_iec958 { + /* AES/IEC958 channel status bits */ + uint8_t status[24]; + /* AES/IEC958 subcode bits */ + uint8_t subcode[147]; + /* nothing */ + uint8_t pad; + /* AES/IEC958 subframe bits */ + uint8_t dig_subframe[4]; +}; + +struct virtio_snd_ctl_value { + union { + /* VIRTIO_SND_CTL_TYPE_BOOLEAN|INTEGER value */ + uint32_t integer[128]; + /* VIRTIO_SND_CTL_TYPE_INTEGER64 value */ + uint64_t integer64[64]; + /* VIRTIO_SND_CTL_TYPE_ENUMERATED value (option indexes) */ + uint32_t enumerated[128]; + /* VIRTIO_SND_CTL_TYPE_BYTES value */ + uint8_t bytes[512]; + /* VIRTIO_SND_CTL_TYPE_IEC958 value */ + struct virtio_snd_ctl_iec958 iec958; + } value; +}; + +/* supported event reason types */ +enum { + /* element's value has changed */ + VIRTIO_SND_CTL_EVT_MASK_VALUE = 0, + /* element's information has changed */ + VIRTIO_SND_CTL_EVT_MASK_INFO, + /* element's metadata has changed */ + VIRTIO_SND_CTL_EVT_MASK_TLV +}; + +struct virtio_snd_ctl_event { + /* VIRTIO_SND_EVT_CTL_NOTIFY */ + struct virtio_snd_hdr hdr; + /* 0 ... virtio_snd_config::controls - 1 */ + uint16_t control_id; + /* event reason bit map (1 << VIRTIO_SND_CTL_EVT_MASK_XXX) */ + uint16_t mask; +}; + #endif /* VIRTIO_SND_IF_H */ diff --git a/include/sysemu/hostmem.h b/include/sysemu/hostmem.h index 0e411aaa29..04b884bf42 100644 --- a/include/sysemu/hostmem.h +++ b/include/sysemu/hostmem.h @@ -74,6 +74,7 @@ struct HostMemoryBackend { uint64_t size; bool merge, dump, use_canonical_path; bool prealloc, is_mapped, share, reserve; + bool guest_memfd; uint32_t prealloc_threads; ThreadContext *prealloc_context; DECLARE_BITMAP(host_nodes, MAX_NODES + 1); diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index fad9a7e8ff..47f9e8be1b 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -224,7 +224,7 @@ void kvm_flush_coalesced_mmio_buffer(void); * calling down to kvm_arch_update_guest_debug after the generic * fields have been set. */ -#ifdef KVM_CAP_SET_GUEST_DEBUG +#ifdef TARGET_KVM_HAVE_GUEST_DEBUG int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap); #else static inline int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap) @@ -525,23 +525,23 @@ int kvm_get_one_reg(CPUState *cs, uint64_t id, void *target); /* Notify resamplefd for EOI of specific interrupts. */ void kvm_resample_fd_notify(int gsi); -/** - * kvm_cpu_check_are_resettable - return whether CPUs can be reset - * - * Returns: true: CPUs are resettable - * false: CPUs are not resettable - */ -bool kvm_cpu_check_are_resettable(void); - -bool kvm_arch_cpu_check_are_resettable(void); - bool kvm_dirty_ring_enabled(void); uint32_t kvm_dirty_ring_size(void); +void kvm_mark_guest_state_protected(void); + /** * kvm_hwpoisoned_mem - indicate if there is any hwpoisoned page * reported for the VM. */ bool kvm_hwpoisoned_mem(void); + +int kvm_create_guest_memfd(uint64_t size, uint64_t flags, Error **errp); + +int kvm_set_memory_attributes_private(hwaddr start, uint64_t size); +int kvm_set_memory_attributes_shared(hwaddr start, uint64_t size); + +int kvm_convert_memory(hwaddr start, hwaddr size, bool to_private); + #endif diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index 882e37e12c..3f3d13f816 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -30,6 +30,8 @@ typedef struct KVMSlot int as_id; /* Cache of the offset in ram address space */ ram_addr_t ram_start_offset; + int guest_memfd; + hwaddr guest_memfd_offset; } KVMSlot; typedef struct KVMMemoryUpdate { @@ -78,7 +80,7 @@ struct KVMState struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; bool coalesced_flush_in_progress; int vcpu_events; -#ifdef KVM_CAP_SET_GUEST_DEBUG +#ifdef TARGET_KVM_HAVE_GUEST_DEBUG QTAILQ_HEAD(, kvm_sw_breakpoint) kvm_sw_breakpoints; #endif int max_nested_state_len; @@ -87,6 +89,7 @@ struct KVMState bool kernel_irqchip_required; OnOffAuto kernel_irqchip_split; bool sync_mmu; + bool guest_state_protected; uint64_t manual_dirty_log_protect; /* The man page (and posix) say ioctl numbers are signed int, but * they're not. Linux, glibc and *BSD all treat ioctl numbers as diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index eb1dc1e4ed..5b4397eeb8 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -71,8 +71,6 @@ Chardev *serial_hd(int i); extern Chardev *parallel_hds[MAX_PARALLEL_PORTS]; -void hmp_info_usb(Monitor *mon, const QDict *qdict); - void add_boot_device_path(int32_t bootindex, DeviceState *dev, const char *suffix); char *get_boot_devices_list(size_t *size); diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index c59ea55cd8..2af9931ae9 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -37,9 +37,7 @@ #include #include -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM #define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -76,11 +74,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ - KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK __GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ - KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK __GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 @@ -162,6 +160,11 @@ struct kvm_sync_regs { __u64 device_irq_level; }; +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + /* * PMU filter structure. Describe a range of events with a particular * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. diff --git a/linux-headers/asm-arm64/sve_context.h b/linux-headers/asm-arm64/sve_context.h index 1d0e3e1d09..d1b1ec8cb1 100644 --- a/linux-headers/asm-arm64/sve_context.h +++ b/linux-headers/asm-arm64/sve_context.h @@ -13,6 +13,17 @@ #define __SVE_VQ_BYTES 16 /* number of bytes per quadword */ +/* + * Yes, __SVE_VQ_MAX is 512 QUADWORDS. + * + * To help ensure forward portability, this is much larger than the + * current maximum value defined by the SVE architecture. While arrays + * or static allocations can be sized based on this value, watch out! + * It will waste a surprisingly large amount of memory. + * + * Dynamic sizing based on the actual runtime vector length is likely to + * be preferable for most purposes. + */ #define __SVE_VQ_MIN 1 #define __SVE_VQ_MAX 512 diff --git a/linux-headers/asm-generic/bitsperlong.h b/linux-headers/asm-generic/bitsperlong.h index 75f320fa91..1fb4f0c9f2 100644 --- a/linux-headers/asm-generic/bitsperlong.h +++ b/linux-headers/asm-generic/bitsperlong.h @@ -24,4 +24,8 @@ #endif #endif +#ifndef __BITS_PER_LONG_LONG +#define __BITS_PER_LONG_LONG 64 +#endif + #endif /* __ASM_GENERIC_BITS_PER_LONG */ diff --git a/linux-headers/asm-loongarch/kvm.h b/linux-headers/asm-loongarch/kvm.h index 923d0bd382..109785922c 100644 --- a/linux-headers/asm-loongarch/kvm.h +++ b/linux-headers/asm-loongarch/kvm.h @@ -14,8 +14,6 @@ * Some parts derived from the x86 version of this file. */ -#define __KVM_HAVE_READONLY_MEM - #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_DIRTY_LOG_PAGE_OFFSET 64 diff --git a/linux-headers/asm-mips/kvm.h b/linux-headers/asm-mips/kvm.h index edcf717c43..9673dc9cb3 100644 --- a/linux-headers/asm-mips/kvm.h +++ b/linux-headers/asm-mips/kvm.h @@ -20,8 +20,6 @@ * Some parts derived from the x86 version of this file. */ -#define __KVM_HAVE_READONLY_MEM - #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 /* diff --git a/linux-headers/asm-powerpc/kvm.h b/linux-headers/asm-powerpc/kvm.h index 9f18fa090f..1691297a76 100644 --- a/linux-headers/asm-powerpc/kvm.h +++ b/linux-headers/asm-powerpc/kvm.h @@ -28,7 +28,6 @@ #define __KVM_HAVE_PPC_SMT #define __KVM_HAVE_IRQCHIP #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_GUEST_DEBUG /* Not always available, but if it is, this is the correct offset. */ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -733,4 +732,48 @@ struct kvm_ppc_xive_eq { #define KVM_XIVE_TIMA_PAGE_OFFSET 0 #define KVM_XIVE_ESB_PAGE_OFFSET 4 +/* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + +struct kvm_ppc_pvinfo { + /* out */ + __u32 flags; + __u32 hcall[4]; + __u8 pad[108]; +}; + +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 +#define KVM_PPC_NO_HASH 0x00000004 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h index 7499e88a94..b1c503c295 100644 --- a/linux-headers/asm-riscv/kvm.h +++ b/linux-headers/asm-riscv/kvm.h @@ -16,7 +16,6 @@ #include #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -166,6 +165,8 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_ZVFH, KVM_RISCV_ISA_EXT_ZVFHMIN, KVM_RISCV_ISA_EXT_ZFA, + KVM_RISCV_ISA_EXT_ZTSO, + KVM_RISCV_ISA_EXT_ZACAS, KVM_RISCV_ISA_EXT_MAX, }; diff --git a/linux-headers/asm-s390/kvm.h b/linux-headers/asm-s390/kvm.h index 023a2763a9..684c4e1205 100644 --- a/linux-headers/asm-s390/kvm.h +++ b/linux-headers/asm-s390/kvm.h @@ -12,7 +12,320 @@ #include #define __KVM_S390 -#define __KVM_HAVE_GUEST_DEBUG + +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + union { + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ + }; + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* ignored */ + }; +}; +/* types for kvm_s390_mem_op->op */ +#define KVM_S390_MEMOP_LOGICAL_READ 0 +#define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + +/* flags for kvm_s390_mem_op->flags */ +#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) +#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) + +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u +#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u +#define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u +#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu +#define KVM_S390_INT_IO_AI_MASK 0x04000000u + + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +struct kvm_s390_io_info { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; +}; + +struct kvm_s390_ext_info { + __u32 ext_params; + __u32 pad; + __u64 ext_params2; +}; + +struct kvm_s390_pgm_info { + __u64 trans_exc_code; + __u64 mon_code; + __u64 per_address; + __u32 data_exc_code; + __u16 code; + __u16 mon_class_nr; + __u8 per_code; + __u8 per_atmid; + __u8 exc_access_id; + __u8 per_access_id; + __u8 op_access_id; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; +}; + +struct kvm_s390_prefix_info { + __u32 address; +}; + +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 pad; + __u8 fixed_logout[16]; +}; + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; /* will stay unused for compatibility reasons */ + __u32 len; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ +}; + +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; + +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_dmp_id { + KVM_PV_DUMP_INIT, + KVM_PV_DUMP_CONFIG_STOR_STATE, + KVM_PV_DUMP_COMPLETE, + KVM_PV_DUMP_CPU, +}; + +struct kvm_s390_pv_dmp { + __u64 subcmd; + __u64 buff_addr; + __u64 buff_len; + __u64 gaddr; /* For dump storage state */ + __u64 reserved[4]; +}; + +enum pv_cmd_info_id { + KVM_PV_INFO_VM, + KVM_PV_INFO_DUMP, +}; + +struct kvm_s390_pv_info_dump { + __u64 dump_cpu_buffer_len; + __u64 dump_config_mem_buffer_per_1m; + __u64 dump_config_finalize_len; +}; + +struct kvm_s390_pv_info_vm { + __u64 inst_calls_list[4]; + __u64 max_cpus; + __u64 max_guests; + __u64 max_guest_addr; + __u64 feature_indication; +}; + +struct kvm_s390_pv_info_header { + __u32 id; + __u32 len_max; + __u32 len_written; + __u32 reserved; +}; + +struct kvm_s390_pv_info { + struct kvm_s390_pv_info_header header; + union { + struct kvm_s390_pv_info_dump dump; + struct kvm_s390_pv_info_vm vm; + }; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, + KVM_PV_DUMP, + KVM_PV_ASYNC_CLEANUP_PREPARE, + KVM_PV_ASYNC_CLEANUP_PERFORM, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) /* Device control API: s390-specific devices */ #define KVM_DEV_FLIC_GET_ALL_IRQS 1 diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index 003fb74534..31c95c2dfe 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -7,6 +7,8 @@ * */ +#include +#include #include #include #include @@ -40,7 +42,6 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 @@ -49,7 +50,6 @@ #define __KVM_HAVE_DEBUGREGS #define __KVM_HAVE_XSAVE #define __KVM_HAVE_XCRS -#define __KVM_HAVE_READONLY_MEM /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -455,8 +455,13 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 -/* attributes for system fd (group 0) */ -#define KVM_X86_XCOMP_GUEST_SUPP 0 +/* vendor-independent attributes for system fd (group 0) */ +#define KVM_X86_GRP_SYSTEM 0 +# define KVM_X86_XCOMP_GUEST_SUPP 0 + +/* vendor-specific groups and attributes for system fd */ +#define KVM_X86_GRP_SEV 1 +# define KVM_X86_SEV_VMSA_FEATURES 0 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -524,9 +529,310 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 -#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for KVM_CAP_XEN_HVM */ +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8) + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + union { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + __u64 hva; + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } u; +}; + + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 hva; + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + /* Second time is the charm; improved versions of the above ioctls. */ + KVM_SEV_INIT2, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u32 pad0; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_init { + __u64 vmsa_features; + __u32 flags; + __u32 pad[9]; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u32 pad0; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u32 pad1; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u32 pad2; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u32 pad3; + __u64 session_uaddr; + __u32 session_len; + __u32 pad4; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description @@ -547,10 +853,10 @@ struct kvm_pmu_event_filter { ((__u64)(!!(exclude)) << 55)) #define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ - (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) -#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) + (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55)) #define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ @@ -558,9 +864,11 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ /* x86-specific KVM_EXIT_HYPERCALL flags. */ -#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0) #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 +#define KVM_X86_SEV_VM 2 +#define KVM_X86_SEV_ES_VM 3 #endif /* _ASM_X86_KVM_H */ diff --git a/linux-headers/linux/bits.h b/linux-headers/linux/bits.h new file mode 100644 index 0000000000..d9897771be --- /dev/null +++ b/linux-headers/linux/bits.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* bits.h: Macros for dealing with bitmasks. */ + +#ifndef _LINUX_BITS_H +#define _LINUX_BITS_H + +#define __GENMASK(h, l) \ + (((~_UL(0)) - (_UL(1) << (l)) + 1) & \ + (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) + +#define __GENMASK_ULL(h, l) \ + (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ + (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* _LINUX_BITS_H */ diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index 17839229b2..038731cdef 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -16,6 +16,11 @@ #define KVM_API_VERSION 12 +/* + * Backwards-compatible definitions. + */ +#define __KVM_HAVE_GUEST_DEBUG + /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -85,43 +90,6 @@ struct kvm_pit_config { #define KVM_PIT_SPEAKER_DUMMY 1 -struct kvm_s390_skeys { - __u64 start_gfn; - __u64 count; - __u64 skeydata_addr; - __u32 flags; - __u32 reserved[9]; -}; - -#define KVM_S390_CMMA_PEEK (1 << 0) - -/** - * kvm_s390_cmma_log - Used for CMMA migration. - * - * Used both for input and output. - * - * @start_gfn: Guest page number to start from. - * @count: Size of the result buffer. - * @flags: Control operation mode via KVM_S390_CMMA_* flags - * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty - * pages are still remaining. - * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set - * in the PGSTE. - * @values: Pointer to the values buffer. - * - * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. - */ -struct kvm_s390_cmma_log { - __u64 start_gfn; - __u32 count; - __u32 flags; - union { - __u64 remaining; - __u64 mask; - }; - __u64 values; -}; - struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 @@ -313,11 +281,6 @@ struct kvm_run { __u32 ipb; } s390_sieic; /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; /* KVM_EXIT_S390_UCONTROL */ struct { @@ -532,43 +495,6 @@ struct kvm_translation { __u8 pad[5]; }; -/* for KVM_S390_MEM_OP */ -struct kvm_s390_mem_op { - /* in */ - __u64 gaddr; /* the guest address */ - __u64 flags; /* flags */ - __u32 size; /* amount of bytes */ - __u32 op; /* type of operation */ - __u64 buf; /* buffer in userspace */ - union { - struct { - __u8 ar; /* the access register number */ - __u8 key; /* access key, ignored if flag unset */ - __u8 pad1[6]; /* ignored */ - __u64 old_addr; /* ignored if cmpxchg flag unset */ - }; - __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* ignored */ - }; -}; -/* types for kvm_s390_mem_op->op */ -#define KVM_S390_MEMOP_LOGICAL_READ 0 -#define KVM_S390_MEMOP_LOGICAL_WRITE 1 -#define KVM_S390_MEMOP_SIDA_READ 2 -#define KVM_S390_MEMOP_SIDA_WRITE 3 -#define KVM_S390_MEMOP_ABSOLUTE_READ 4 -#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 -#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 - -/* flags for kvm_s390_mem_op->flags */ -#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) -#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) -#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) - -/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ -#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) -#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) - /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -633,124 +559,6 @@ struct kvm_mp_state { __u32 mp_state; }; -struct kvm_s390_psw { - __u64 mask; - __u64 addr; -}; - -/* valid values for type in kvm_s390_interrupt */ -#define KVM_S390_SIGP_STOP 0xfffe0000u -#define KVM_S390_PROGRAM_INT 0xfffe0001u -#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u -#define KVM_S390_RESTART 0xfffe0003u -#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u -#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u -#define KVM_S390_MCHK 0xfffe1000u -#define KVM_S390_INT_CLOCK_COMP 0xffff1004u -#define KVM_S390_INT_CPU_TIMER 0xffff1005u -#define KVM_S390_INT_VIRTIO 0xffff2603u -#define KVM_S390_INT_SERVICE 0xffff2401u -#define KVM_S390_INT_EMERGENCY 0xffff1201u -#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u -/* Anything below 0xfffe0000u is taken by INT_IO */ -#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ - (((schid)) | \ - ((ssid) << 16) | \ - ((cssid) << 18) | \ - ((ai) << 26)) -#define KVM_S390_INT_IO_MIN 0x00000000u -#define KVM_S390_INT_IO_MAX 0xfffdffffu -#define KVM_S390_INT_IO_AI_MASK 0x04000000u - - -struct kvm_s390_interrupt { - __u32 type; - __u32 parm; - __u64 parm64; -}; - -struct kvm_s390_io_info { - __u16 subchannel_id; - __u16 subchannel_nr; - __u32 io_int_parm; - __u32 io_int_word; -}; - -struct kvm_s390_ext_info { - __u32 ext_params; - __u32 pad; - __u64 ext_params2; -}; - -struct kvm_s390_pgm_info { - __u64 trans_exc_code; - __u64 mon_code; - __u64 per_address; - __u32 data_exc_code; - __u16 code; - __u16 mon_class_nr; - __u8 per_code; - __u8 per_atmid; - __u8 exc_access_id; - __u8 per_access_id; - __u8 op_access_id; -#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 -#define KVM_S390_PGM_FLAGS_ILC_0 0x02 -#define KVM_S390_PGM_FLAGS_ILC_1 0x04 -#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 -#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 - __u8 flags; - __u8 pad[2]; -}; - -struct kvm_s390_prefix_info { - __u32 address; -}; - -struct kvm_s390_extcall_info { - __u16 code; -}; - -struct kvm_s390_emerg_info { - __u16 code; -}; - -#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 -struct kvm_s390_stop_info { - __u32 flags; -}; - -struct kvm_s390_mchk_info { - __u64 cr14; - __u64 mcic; - __u64 failing_storage_address; - __u32 ext_damage_code; - __u32 pad; - __u8 fixed_logout[16]; -}; - -struct kvm_s390_irq { - __u64 type; - union { - struct kvm_s390_io_info io; - struct kvm_s390_ext_info ext; - struct kvm_s390_pgm_info pgm; - struct kvm_s390_emerg_info emerg; - struct kvm_s390_extcall_info extcall; - struct kvm_s390_prefix_info prefix; - struct kvm_s390_stop_info stop; - struct kvm_s390_mchk_info mchk; - char reserved[64]; - } u; -}; - -struct kvm_s390_irq_state { - __u64 buf; - __u32 flags; /* will stay unused for compatibility reasons */ - __u32 len; - __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; - /* for KVM_SET_GUEST_DEBUG */ #define KVM_GUESTDBG_ENABLE 0x00000001 @@ -806,50 +614,6 @@ struct kvm_enable_cap { __u8 pad[64]; }; -/* for KVM_PPC_GET_PVINFO */ - -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) - -struct kvm_ppc_pvinfo { - /* out */ - __u32 flags; - __u32 hcall[4]; - __u8 pad[108]; -}; - -/* for KVM_PPC_GET_SMMU_INFO */ -#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 - -struct kvm_ppc_one_page_size { - __u32 page_shift; /* Page shift (or 0) */ - __u32 pte_enc; /* Encoding in the HPTE (>>12) */ -}; - -struct kvm_ppc_one_seg_page_size { - __u32 page_shift; /* Base page shift of segment (or 0) */ - __u32 slb_enc; /* SLB encoding for BookS */ - struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 -#define KVM_PPC_1T_SEGMENTS 0x00000002 -#define KVM_PPC_NO_HASH 0x00000004 - -struct kvm_ppc_smmu_info { - __u64 flags; - __u32 slb_size; - __u16 data_keys; /* # storage keys supported for data */ - __u16 instr_keys; /* # storage keys supported for instructions */ - struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ -struct kvm_ppc_resize_hpt { - __u64 flags; - __u32 shift; - __u32 pad; -}; - #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ @@ -919,9 +683,7 @@ struct kvm_ppc_resize_hpt { /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 #define KVM_CAP_USER_NMI 22 -#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 -#endif #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif @@ -1152,8 +914,6 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 -#ifdef KVM_CAP_IRQ_ROUTING - struct kvm_irq_routing_irqchip { __u32 irqchip; __u32 pin; @@ -1218,42 +978,6 @@ struct kvm_irq_routing { struct kvm_irq_routing_entry entries[]; }; -#endif - -#ifdef KVM_CAP_MCE -/* x86 MCE */ -struct kvm_x86_mce { - __u64 status; - __u64 addr; - __u64 misc; - __u64 mcg_status; - __u8 bank; - __u8 pad1[7]; - __u64 pad2[3]; -}; -#endif - -#ifdef KVM_CAP_XEN_HVM -#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) -#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) -#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) -#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) -#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) -#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) -#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) -#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) - -struct kvm_xen_hvm_config { - __u32 flags; - __u32 msr; - __u64 blob_addr_32; - __u64 blob_addr_64; - __u8 blob_size_32; - __u8 blob_size_64; - __u8 pad2[30]; -}; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE @@ -1438,11 +1162,6 @@ struct kvm_vfio_spapr_tce { struct kvm_userspace_memory_region2) /* enable ucontrol for s390 */ -struct kvm_s390_ucas_mapping { - __u64 user_addr; - __u64 vcpu_addr; - __u64 length; -}; #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) @@ -1637,89 +1356,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -struct kvm_s390_pv_sec_parm { - __u64 origin; - __u64 length; -}; - -struct kvm_s390_pv_unp { - __u64 addr; - __u64 size; - __u64 tweak; -}; - -enum pv_cmd_dmp_id { - KVM_PV_DUMP_INIT, - KVM_PV_DUMP_CONFIG_STOR_STATE, - KVM_PV_DUMP_COMPLETE, - KVM_PV_DUMP_CPU, -}; - -struct kvm_s390_pv_dmp { - __u64 subcmd; - __u64 buff_addr; - __u64 buff_len; - __u64 gaddr; /* For dump storage state */ - __u64 reserved[4]; -}; - -enum pv_cmd_info_id { - KVM_PV_INFO_VM, - KVM_PV_INFO_DUMP, -}; - -struct kvm_s390_pv_info_dump { - __u64 dump_cpu_buffer_len; - __u64 dump_config_mem_buffer_per_1m; - __u64 dump_config_finalize_len; -}; - -struct kvm_s390_pv_info_vm { - __u64 inst_calls_list[4]; - __u64 max_cpus; - __u64 max_guests; - __u64 max_guest_addr; - __u64 feature_indication; -}; - -struct kvm_s390_pv_info_header { - __u32 id; - __u32 len_max; - __u32 len_written; - __u32 reserved; -}; - -struct kvm_s390_pv_info { - struct kvm_s390_pv_info_header header; - union { - struct kvm_s390_pv_info_dump dump; - struct kvm_s390_pv_info_vm vm; - }; -}; - -enum pv_cmd_id { - KVM_PV_ENABLE, - KVM_PV_DISABLE, - KVM_PV_SET_SEC_PARMS, - KVM_PV_UNPACK, - KVM_PV_VERIFY, - KVM_PV_PREP_RESET, - KVM_PV_UNSHARE_ALL, - KVM_PV_INFO, - KVM_PV_DUMP, - KVM_PV_ASYNC_CLEANUP_PREPARE, - KVM_PV_ASYNC_CLEANUP_PERFORM, -}; - -struct kvm_pv_cmd { - __u32 cmd; /* Command to be executed */ - __u16 rc; /* Ultravisor return code */ - __u16 rrc; /* Ultravisor return reason code */ - __u64 data; /* Data or address */ - __u32 flags; /* flags for future extensions. Must be 0 for now */ - __u32 reserved[3]; -}; - /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) @@ -1733,58 +1369,6 @@ struct kvm_pv_cmd { #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) -struct kvm_xen_hvm_attr { - __u16 type; - __u16 pad[3]; - union { - __u8 long_mode; - __u8 vector; - __u8 runstate_update_flag; - struct { - __u64 gfn; -#define KVM_XEN_INVALID_GFN ((__u64)-1) - } shared_info; - struct { - __u32 send_port; - __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ - __u32 flags; -#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) -#define KVM_XEN_EVTCHN_UPDATE (1 << 1) -#define KVM_XEN_EVTCHN_RESET (1 << 2) - /* - * Events sent by the guest are either looped back to - * the guest itself (potentially on a different port#) - * or signalled via an eventfd. - */ - union { - struct { - __u32 port; - __u32 vcpu; - __u32 priority; - } port; - struct { - __u32 port; /* Zero for eventfd */ - __s32 fd; - } eventfd; - __u32 padding[4]; - } deliver; - } evtchn; - __u32 xen_version; - __u64 pad[8]; - } u; -}; - - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 -#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 -#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 -#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ -#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 - /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) @@ -1795,242 +1379,6 @@ struct kvm_xen_hvm_attr { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -struct kvm_xen_vcpu_attr { - __u16 type; - __u16 pad[3]; - union { - __u64 gpa; -#define KVM_XEN_INVALID_GPA ((__u64)-1) - __u64 pad[8]; - struct { - __u64 state; - __u64 state_entry_time; - __u64 time_running; - __u64 time_runnable; - __u64 time_blocked; - __u64 time_offline; - } runstate; - __u32 vcpu_id; - struct { - __u32 port; - __u32 priority; - __u64 expires_ns; - } timer; - __u8 vector; - } u; -}; - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 -#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 -#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 - -/* Secure Encrypted Virtualization command */ -enum sev_cmd_id { - /* Guest initialization commands */ - KVM_SEV_INIT = 0, - KVM_SEV_ES_INIT, - /* Guest launch commands */ - KVM_SEV_LAUNCH_START, - KVM_SEV_LAUNCH_UPDATE_DATA, - KVM_SEV_LAUNCH_UPDATE_VMSA, - KVM_SEV_LAUNCH_SECRET, - KVM_SEV_LAUNCH_MEASURE, - KVM_SEV_LAUNCH_FINISH, - /* Guest migration commands (outgoing) */ - KVM_SEV_SEND_START, - KVM_SEV_SEND_UPDATE_DATA, - KVM_SEV_SEND_UPDATE_VMSA, - KVM_SEV_SEND_FINISH, - /* Guest migration commands (incoming) */ - KVM_SEV_RECEIVE_START, - KVM_SEV_RECEIVE_UPDATE_DATA, - KVM_SEV_RECEIVE_UPDATE_VMSA, - KVM_SEV_RECEIVE_FINISH, - /* Guest status and debug commands */ - KVM_SEV_GUEST_STATUS, - KVM_SEV_DBG_DECRYPT, - KVM_SEV_DBG_ENCRYPT, - /* Guest certificates commands */ - KVM_SEV_CERT_EXPORT, - /* Attestation report */ - KVM_SEV_GET_ATTESTATION_REPORT, - /* Guest Migration Extension */ - KVM_SEV_SEND_CANCEL, - - KVM_SEV_NR_MAX, -}; - -struct kvm_sev_cmd { - __u32 id; - __u64 data; - __u32 error; - __u32 sev_fd; -}; - -struct kvm_sev_launch_start { - __u32 handle; - __u32 policy; - __u64 dh_uaddr; - __u32 dh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_launch_update_data { - __u64 uaddr; - __u32 len; -}; - - -struct kvm_sev_launch_secret { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_launch_measure { - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_guest_status { - __u32 handle; - __u32 policy; - __u32 state; -}; - -struct kvm_sev_dbg { - __u64 src_uaddr; - __u64 dst_uaddr; - __u32 len; -}; - -struct kvm_sev_attestation_report { - __u8 mnonce[16]; - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_send_start { - __u32 policy; - __u64 pdh_cert_uaddr; - __u32 pdh_cert_len; - __u64 plat_certs_uaddr; - __u32 plat_certs_len; - __u64 amd_certs_uaddr; - __u32 amd_certs_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_send_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_receive_start { - __u32 handle; - __u32 policy; - __u64 pdh_uaddr; - __u32 pdh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_receive_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) - -struct kvm_assigned_pci_dev { - __u32 assigned_dev_id; - __u32 busnr; - __u32 devfn; - __u32 flags; - __u32 segnr; - union { - __u32 reserved[11]; - }; -}; - -#define KVM_DEV_IRQ_HOST_INTX (1 << 0) -#define KVM_DEV_IRQ_HOST_MSI (1 << 1) -#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) - -#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) -#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) -#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) - -#define KVM_DEV_IRQ_HOST_MASK 0x00ff -#define KVM_DEV_IRQ_GUEST_MASK 0xff00 - -struct kvm_assigned_irq { - __u32 assigned_dev_id; - __u32 host_irq; /* ignored (legacy field) */ - __u32 guest_irq; - __u32 flags; - union { - __u32 reserved[12]; - }; -}; - -struct kvm_assigned_msix_nr { - __u32 assigned_dev_id; - __u16 entry_nr; - __u16 padding; -}; - -#define KVM_MAX_MSIX_PER_DEV 256 -struct kvm_assigned_msix_entry { - __u32 assigned_dev_id; - __u32 gsi; - __u16 entry; /* The index of entry in the MSI-X table */ - __u16 padding[3]; -}; - -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) - -/* Available with KVM_CAP_ARM_USER_IRQ */ - -/* Bits for run->s.regs.device_irq_level */ -#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) -#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) -#define KVM_ARM_DEV_PMU (1 << 2) - -struct kvm_hyperv_eventfd { - __u32 conn_id; - __s32 fd; - __u32 flags; - __u32 padding[3]; -}; - -#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff -#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) - #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) @@ -2176,33 +1524,6 @@ struct kvm_stats_desc { /* Available with KVM_CAP_S390_ZPCI_OP */ #define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) -struct kvm_s390_zpci_op { - /* in */ - __u32 fh; /* target device */ - __u8 op; /* operation to perform */ - __u8 pad[3]; - union { - /* for KVM_S390_ZPCIOP_REG_AEN */ - struct { - __u64 ibv; /* Guest addr of interrupt bit vector */ - __u64 sb; /* Guest addr of summary bit */ - __u32 flags; - __u32 noi; /* Number of interrupts */ - __u8 isc; /* Guest interrupt subclass */ - __u8 sbo; /* Offset of guest summary bit vector */ - __u16 pad; - } reg_aen; - __u64 reserved[8]; - } u; -}; - -/* types for kvm_s390_zpci_op->op */ -#define KVM_S390_ZPCIOP_REG_AEN 0 -#define KVM_S390_ZPCIOP_DEREG_AEN 1 - -/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ -#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) - /* Available with KVM_CAP_MEMORY_ATTRIBUTES */ #define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) diff --git a/linux-headers/linux/psp-sev.h b/linux-headers/linux/psp-sev.h index bcb21339ee..c3046c6bff 100644 --- a/linux-headers/linux/psp-sev.h +++ b/linux-headers/linux/psp-sev.h @@ -28,6 +28,9 @@ enum { SEV_PEK_CERT_IMPORT, SEV_GET_ID, /* This command is deprecated, use SEV_GET_ID2 */ SEV_GET_ID2, + SNP_PLATFORM_STATUS, + SNP_COMMIT, + SNP_SET_CONFIG, SEV_MAX, }; @@ -69,6 +72,12 @@ typedef enum { SEV_RET_RESOURCE_LIMIT, SEV_RET_SECURE_DATA_INVALID, SEV_RET_INVALID_KEY = 0x27, + SEV_RET_INVALID_PAGE_SIZE, + SEV_RET_INVALID_PAGE_STATE, + SEV_RET_INVALID_MDATA_ENTRY, + SEV_RET_INVALID_PAGE_OWNER, + SEV_RET_INVALID_PAGE_AEAD_OFLOW, + SEV_RET_RMP_INIT_REQUIRED, SEV_RET_MAX, } sev_ret_code; @@ -155,6 +164,56 @@ struct sev_user_data_get_id2 { __u32 length; /* In/Out */ } __attribute__((packed)); +/** + * struct sev_user_data_snp_status - SNP status + * + * @api_major: API major version + * @api_minor: API minor version + * @state: current platform state + * @is_rmp_initialized: whether RMP is initialized or not + * @rsvd: reserved + * @build_id: firmware build id for the API version + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @vlek_en: VLEK (Version Loaded Endorsement Key) hashstick is loaded + * @rsvd1: reserved + * @guest_count: the number of guest currently managed by the firmware + * @current_tcb_version: current TCB version + * @reported_tcb_version: reported TCB version + */ +struct sev_user_data_snp_status { + __u8 api_major; /* Out */ + __u8 api_minor; /* Out */ + __u8 state; /* Out */ + __u8 is_rmp_initialized:1; /* Out */ + __u8 rsvd:7; + __u32 build_id; /* Out */ + __u32 mask_chip_id:1; /* Out */ + __u32 mask_chip_key:1; /* Out */ + __u32 vlek_en:1; /* Out */ + __u32 rsvd1:29; + __u32 guest_count; /* Out */ + __u64 current_tcb_version; /* Out */ + __u64 reported_tcb_version; /* Out */ +} __attribute__((packed)); + +/** + * struct sev_user_data_snp_config - system wide configuration value for SNP. + * + * @reported_tcb: the TCB version to report in the guest attestation report. + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @rsvd: reserved + * @rsvd1: reserved + */ +struct sev_user_data_snp_config { + __u64 reported_tcb ; /* In */ + __u32 mask_chip_id:1; /* In */ + __u32 mask_chip_key:1; /* In */ + __u32 rsvd:30; /* In */ + __u8 rsvd1[52]; +} __attribute__((packed)); + /** * struct sev_issue_cmd - SEV ioctl parameters * diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index 649560c685..bea6973906 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -227,4 +227,11 @@ */ #define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \ struct vhost_vring_state) + +/* Get the queue size of a specific virtqueue. + * userspace set the vring index in vhost_vring_state.index + * kernel set the queue size in vhost_vring_state.num + */ +#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x80, \ + struct vhost_vring_state) #endif diff --git a/meson.build b/meson.build index 91a0aa64c6..84e59dcbb4 100644 --- a/meson.build +++ b/meson.build @@ -3451,8 +3451,12 @@ subdir('qom') subdir('authz') subdir('crypto') subdir('ui') -subdir('hw') subdir('gdbstub') +if have_system + subdir('hw') +else + subdir('hw/core') +endif if enable_modules libmodulecommon = static_library('module-common', files('module-common.c') + genh, pic: true, c_args: '-DBUILD_DSO') @@ -3481,7 +3485,7 @@ util_ss = util_ss.apply({}) libqemuutil = static_library('qemuutil', build_by_default: false, sources: util_ss.sources() + stub_ss.sources() + genh, - dependencies: [util_ss.dependencies(), libm, threads, glib, socket, malloc, pixman]) + dependencies: [util_ss.dependencies(), libm, threads, glib, socket, malloc]) qemuutil = declare_dependency(link_with: libqemuutil, sources: genh + version_res, dependencies: [event_loop_base]) diff --git a/stubs/colo.c b/migration/colo-stubs.c similarity index 100% rename from stubs/colo.c rename to migration/colo-stubs.c diff --git a/migration/meson.build b/migration/meson.build index 1eeb915ff6..f76b1ba328 100644 --- a/migration/meson.build +++ b/migration/meson.build @@ -34,6 +34,8 @@ system_ss.add(files( if get_option('replication').allowed() system_ss.add(files('colo-failover.c', 'colo.c')) +else + system_ss.add(files('colo-stubs.c')) endif system_ss.add(when: rdma, if_true: files('rdma.c')) diff --git a/monitor/meson.build b/monitor/meson.build index 5269492cf0..a71523a1ce 100644 --- a/monitor/meson.build +++ b/monitor/meson.build @@ -4,6 +4,7 @@ system_ss.add(files( 'fds.c', 'hmp-cmds.c', 'hmp.c', + 'qemu-config-qmp.c', )) system_ss.add([spice_headers, files('qmp-cmds.c')]) diff --git a/monitor/qemu-config-qmp.c b/monitor/qemu-config-qmp.c new file mode 100644 index 0000000000..24477a0e44 --- /dev/null +++ b/monitor/qemu-config-qmp.c @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qapi/qapi-commands-misc.h" +#include "qapi/qmp/qlist.h" +#include "qemu/option.h" +#include "qemu/config-file.h" +#include "hw/boards.h" + +static CommandLineParameterInfoList *query_option_descs(const QemuOptDesc *desc) +{ + CommandLineParameterInfoList *param_list = NULL; + CommandLineParameterInfo *info; + int i; + + for (i = 0; desc[i].name != NULL; i++) { + info = g_malloc0(sizeof(*info)); + info->name = g_strdup(desc[i].name); + + switch (desc[i].type) { + case QEMU_OPT_STRING: + info->type = COMMAND_LINE_PARAMETER_TYPE_STRING; + break; + case QEMU_OPT_BOOL: + info->type = COMMAND_LINE_PARAMETER_TYPE_BOOLEAN; + break; + case QEMU_OPT_NUMBER: + info->type = COMMAND_LINE_PARAMETER_TYPE_NUMBER; + break; + case QEMU_OPT_SIZE: + info->type = COMMAND_LINE_PARAMETER_TYPE_SIZE; + break; + } + + info->help = g_strdup(desc[i].help); + info->q_default = g_strdup(desc[i].def_value_str); + + QAPI_LIST_PREPEND(param_list, info); + } + + return param_list; +} + +/* remove repeated entry from the info list */ +static void cleanup_infolist(CommandLineParameterInfoList *head) +{ + CommandLineParameterInfoList *pre_entry, *cur, *del_entry; + + cur = head; + while (cur->next) { + pre_entry = head; + while (pre_entry != cur->next) { + if (!strcmp(pre_entry->value->name, cur->next->value->name)) { + del_entry = cur->next; + cur->next = cur->next->next; + del_entry->next = NULL; + qapi_free_CommandLineParameterInfoList(del_entry); + break; + } + pre_entry = pre_entry->next; + } + cur = cur->next; + } +} + +/* merge the description items of two parameter infolists */ +static void connect_infolist(CommandLineParameterInfoList *head, + CommandLineParameterInfoList *new) +{ + CommandLineParameterInfoList *cur; + + cur = head; + while (cur->next) { + cur = cur->next; + } + cur->next = new; +} + +/* access all the local QemuOptsLists for drive option */ +static CommandLineParameterInfoList *get_drive_infolist(void) +{ + CommandLineParameterInfoList *head = NULL, *cur; + int i; + + for (i = 0; drive_config_groups[i] != NULL; i++) { + if (!head) { + head = query_option_descs(drive_config_groups[i]->desc); + } else { + cur = query_option_descs(drive_config_groups[i]->desc); + connect_infolist(head, cur); + } + } + cleanup_infolist(head); + + return head; +} + +static CommandLineParameterInfo *objprop_to_cmdline_prop(ObjectProperty *prop) +{ + CommandLineParameterInfo *info; + + info = g_malloc0(sizeof(*info)); + info->name = g_strdup(prop->name); + + if (g_str_equal(prop->type, "bool") || g_str_equal(prop->type, "OnOffAuto")) { + info->type = COMMAND_LINE_PARAMETER_TYPE_BOOLEAN; + } else if (g_str_equal(prop->type, "int")) { + info->type = COMMAND_LINE_PARAMETER_TYPE_NUMBER; + } else if (g_str_equal(prop->type, "size")) { + info->type = COMMAND_LINE_PARAMETER_TYPE_SIZE; + } else { + info->type = COMMAND_LINE_PARAMETER_TYPE_STRING; + } + + if (prop->description) { + info->help = g_strdup(prop->description); + } + + return info; +} + +static CommandLineParameterInfoList *query_all_machine_properties(void) +{ + CommandLineParameterInfoList *params = NULL, *clpiter; + CommandLineParameterInfo *info; + GSList *machines, *curr_mach; + ObjectPropertyIterator op_iter; + ObjectProperty *prop; + bool is_new; + + machines = object_class_get_list(TYPE_MACHINE, false); + assert(machines); + + /* Loop over all machine classes */ + for (curr_mach = machines; curr_mach; curr_mach = curr_mach->next) { + object_class_property_iter_init(&op_iter, curr_mach->data); + /* ... and over the properties of each machine: */ + while ((prop = object_property_iter_next(&op_iter))) { + if (!prop->set) { + continue; + } + /* + * Check whether the property has already been put into the list + * (via another machine class) + */ + is_new = true; + for (clpiter = params; clpiter != NULL; clpiter = clpiter->next) { + if (g_str_equal(clpiter->value->name, prop->name)) { + is_new = false; + break; + } + } + /* If it hasn't been added before, add it now to the list */ + if (is_new) { + info = objprop_to_cmdline_prop(prop); + QAPI_LIST_PREPEND(params, info); + } + } + } + + g_slist_free(machines); + + /* Add entry for the "type" parameter */ + info = g_malloc0(sizeof(*info)); + info->name = g_strdup("type"); + info->type = COMMAND_LINE_PARAMETER_TYPE_STRING; + info->help = g_strdup("machine type"); + QAPI_LIST_PREPEND(params, info); + + return params; +} + +CommandLineOptionInfoList *qmp_query_command_line_options(const char *option, + Error **errp) +{ + CommandLineOptionInfoList *conf_list = NULL; + CommandLineOptionInfo *info; + int i; + + for (i = 0; vm_config_groups[i] != NULL; i++) { + if (!option || !strcmp(option, vm_config_groups[i]->name)) { + info = g_malloc0(sizeof(*info)); + info->option = g_strdup(vm_config_groups[i]->name); + if (!strcmp("drive", vm_config_groups[i]->name)) { + info->parameters = get_drive_infolist(); + } else { + info->parameters = + query_option_descs(vm_config_groups[i]->desc); + } + QAPI_LIST_PREPEND(conf_list, info); + } + } + + if (!option || !strcmp(option, "machine")) { + info = g_malloc0(sizeof(*info)); + info->option = g_strdup("machine"); + info->parameters = query_all_machine_properties(); + QAPI_LIST_PREPEND(conf_list, info); + } + + if (conf_list == NULL) { + error_setg(errp, "invalid option name: %s", option); + } + + return conf_list; +} diff --git a/stubs/colo-compare.c b/net/colo-stubs.c similarity index 100% rename from stubs/colo-compare.c rename to net/colo-stubs.c diff --git a/net/meson.build b/net/meson.build index 9432a588e4..e0cd71470e 100644 --- a/net/meson.build +++ b/net/meson.build @@ -20,6 +20,8 @@ if get_option('replication').allowed() or \ get_option('colo_proxy').allowed() system_ss.add(files('colo-compare.c')) system_ss.add(files('colo.c')) +else + system_ss.add(files('colo-stubs.c')) endif if get_option('colo_proxy').allowed() diff --git a/pythondeps.toml b/pythondeps.toml index 0e88415999..9c16602d30 100644 --- a/pythondeps.toml +++ b/pythondeps.toml @@ -22,6 +22,7 @@ meson = { accepted = ">=0.63.0", installed = "1.2.3", canary = "meson" } [docs] +# Please keep the installed versions in sync with docs/requirements.txt sphinx = { accepted = ">=1.6", installed = "5.3.0", canary = "sphinx-build" } sphinx_rtd_theme = { accepted = ">=0.5", installed = "1.1.1" } diff --git a/qapi/qom.json b/qapi/qom.json index 85e6b4f84a..38dde6d785 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -898,6 +898,14 @@ # designated guest firmware page for measured boot with -kernel # (default: false) (since 6.2) # +# @legacy-vm-type: Use legacy KVM_SEV_INIT KVM interface for creating the VM. +# The newer KVM_SEV_INIT2 interface syncs additional vCPU +# state when initializing the VMSA structures, which will +# result in a different guest measurement. Set this to +# maintain compatibility with older QEMU or kernel versions +# that rely on legacy KVM_SEV_INIT behavior. +# (default: false) (since 9.1) +# # Since: 2.12 ## { 'struct': 'SevGuestProperties', @@ -908,7 +916,8 @@ '*handle': 'uint32', '*cbitpos': 'uint32', 'reduced-phys-bits': 'uint32', - '*kernel-hashes': 'bool' } } + '*kernel-hashes': 'bool', + '*legacy-vm-type': 'bool' } } ## # @ThreadContextProperties: diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index a0006eec6f..5f20434d5c 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -61,7 +61,7 @@ cp_portable() { -e 'linux/const' \ -e 'linux/kernel' \ -e 'linux/sysinfo' \ - -e 'asm-generic/kvm_para' \ + -e 'asm/setup_data.h' \ > /dev/null then echo "Unexpected #include in input file $f". @@ -77,6 +77,7 @@ cp_portable() { -e 's/__be\([0-9][0-9]*\)/uint\1_t/g' \ -e 's/"\(input-event-codes\.h\)"/"standard-headers\/linux\/\1"/' \ -e 's/]*\)>/"standard-headers\/linux\/\1"/' \ + -e 's/]*\)>/"standard-headers\/asm-'$arch'\/\1"/' \ -e 's/__bitwise//' \ -e 's/__attribute__((packed))/QEMU_PACKED/' \ -e 's/__inline__/inline/' \ @@ -155,17 +156,20 @@ for arch in $ARCHLIST; do "$tmpdir/include/asm/bootparam.h" > "$tmpdir/bootparam.h" cp_portable "$tmpdir/bootparam.h" \ "$output/include/standard-headers/asm-$arch" + cp_portable "$tmpdir/include/asm/setup_data.h" \ + "$output/standard-headers/asm-x86" fi if [ $arch = riscv ]; then cp "$tmpdir/include/asm/ptrace.h" "$output/linux-headers/asm-riscv/" fi done +arch= rm -rf "$output/linux-headers/linux" mkdir -p "$output/linux-headers/linux" for header in const.h stddef.h kvm.h vfio.h vfio_ccw.h vfio_zdev.h vhost.h \ psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h \ - vduse.h iommufd.h; do + vduse.h iommufd.h bits.h; do cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux" done diff --git a/semihosting/meson.build b/semihosting/meson.build index b07cbd980f..34933e5a19 100644 --- a/semihosting/meson.build +++ b/semihosting/meson.build @@ -9,5 +9,8 @@ specific_ss.add(when: ['CONFIG_SEMIHOSTING', 'CONFIG_SYSTEM_ONLY'], if_true: fil 'uaccess.c', )) +common_ss.add(when: ['CONFIG_SEMIHOSTING', 'CONFIG_SYSTEM_ONLY'], if_false: files('stubs-all.c')) +system_ss.add(when: ['CONFIG_SEMIHOSTING'], if_false: files('stubs-system.c')) + specific_ss.add(when: ['CONFIG_ARM_COMPATIBLE_SEMIHOSTING'], if_true: files('arm-compat-semi.c')) diff --git a/stubs/semihost-all.c b/semihosting/stubs-all.c similarity index 100% rename from stubs/semihost-all.c rename to semihosting/stubs-all.c diff --git a/stubs/semihost.c b/semihosting/stubs-system.c similarity index 100% rename from stubs/semihost.c rename to semihosting/stubs-system.c diff --git a/stubs/fdset.c b/stubs/fdset.c index 56b3663d58..d7c39a28ac 100644 --- a/stubs/fdset.c +++ b/stubs/fdset.c @@ -1,5 +1,7 @@ #include "qemu/osdep.h" +#include "qapi/error.h" #include "monitor/monitor.h" +#include "../monitor/monitor-internal.h" int monitor_fdset_dup_fd_add(int64_t fdset_id, int flags) { @@ -15,3 +17,7 @@ int64_t monitor_fdset_dup_fd_find(int dup_fd) void monitor_fdset_dup_fd_remove(int dupfd) { } + +void monitor_fdsets_cleanup(void) +{ +} diff --git a/hw/core/hotplug-stubs.c b/stubs/hotplug-stubs.c similarity index 100% rename from hw/core/hotplug-stubs.c rename to stubs/hotplug-stubs.c diff --git a/stubs/isa-bus.c b/stubs/isa-bus.c deleted file mode 100644 index 522f448997..0000000000 --- a/stubs/isa-bus.c +++ /dev/null @@ -1,7 +0,0 @@ -#include "qemu/osdep.h" -#include "hw/isa/isa.h" - -ISADevice *isa_create_simple(ISABus *bus, const char *name) -{ - g_assert_not_reached(); -} diff --git a/stubs/meson.build b/stubs/meson.build index 0bf25e6ca5..8ee1fd5753 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -1,67 +1,86 @@ -stub_ss.add(files('bdrv-next-monitor-owned.c')) -stub_ss.add(files('blk-commit-all.c')) -stub_ss.add(files('blk-exp-close-all.c')) -stub_ss.add(files('blockdev-close-all-bdrv-states.c')) -stub_ss.add(files('change-state-handler.c')) -stub_ss.add(files('cmos.c')) +# If possible, add new files to other directories, by using "if_false". +# If you need them here, try to add them under one of the if statements +# below, so that it is clear who needs the stubbed functionality. + stub_ss.add(files('cpu-get-clock.c')) -stub_ss.add(files('cpus-get-virtual-clock.c')) -stub_ss.add(files('qemu-timer-notify-cb.c')) -stub_ss.add(files('icount.c')) -stub_ss.add(files('dump.c')) -stub_ss.add(files('error-printf.c')) stub_ss.add(files('fdset.c')) -stub_ss.add(files('gdbstub.c')) -stub_ss.add(files('get-vm-name.c')) -stub_ss.add(files('graph-lock.c')) -if linux_io_uring.found() - stub_ss.add(files('io_uring.c')) -endif stub_ss.add(files('iothread-lock.c')) -if have_block - stub_ss.add(files('iothread-lock-block.c')) -endif -stub_ss.add(files('isa-bus.c')) stub_ss.add(files('is-daemonized.c')) -if libaio.found() - stub_ss.add(files('linux-aio.c')) -endif -stub_ss.add(files('migr-blocker.c')) -stub_ss.add(files('module-opts.c')) -stub_ss.add(files('monitor.c')) stub_ss.add(files('monitor-core.c')) -stub_ss.add(files('physmem.c')) -stub_ss.add(files('qemu-timer-notify-cb.c')) -stub_ss.add(files('memory_device.c')) -stub_ss.add(files('qmp-command-available.c')) -stub_ss.add(files('qmp-quit.c')) -stub_ss.add(files('qtest.c')) -stub_ss.add(files('ram-block.c')) -stub_ss.add(files('ramfb.c')) -stub_ss.add(files('replay.c')) -stub_ss.add(files('runstate-check.c')) -stub_ss.add(files('sysbus.c')) -stub_ss.add(files('target-get-monitor-def.c')) -stub_ss.add(files('target-monitor-defs.c')) +stub_ss.add(files('replay-mode.c')) stub_ss.add(files('trace-control.c')) -stub_ss.add(files('uuid.c')) -stub_ss.add(files('colo.c')) -stub_ss.add(files('colo-compare.c')) -stub_ss.add(files('vmstate.c')) -stub_ss.add(files('vm-stop.c')) -stub_ss.add(files('win32-kbd-hook.c')) -stub_ss.add(files('cpu-synchronize-state.c')) -if have_block or have_ga + +if have_block + stub_ss.add(files('bdrv-next-monitor-owned.c')) + stub_ss.add(files('blk-commit-all.c')) + stub_ss.add(files('blk-exp-close-all.c')) + stub_ss.add(files('blockdev-close-all-bdrv-states.c')) + stub_ss.add(files('change-state-handler.c')) + stub_ss.add(files('get-vm-name.c')) + stub_ss.add(files('iothread-lock-block.c')) + stub_ss.add(files('migr-blocker.c')) + stub_ss.add(files('physmem.c')) + stub_ss.add(files('ram-block.c')) stub_ss.add(files('replay-tools.c')) + stub_ss.add(files('runstate-check.c')) + stub_ss.add(files('uuid.c')) endif -if have_system - stub_ss.add(files('fw_cfg.c')) - stub_ss.add(files('pci-bus.c')) - stub_ss.add(files('semihost.c')) - stub_ss.add(files('usb-dev-stub.c')) - stub_ss.add(files('xen-hw-stub.c')) - stub_ss.add(files('virtio-md-pci.c')) -else + +if have_block or have_ga + # stubs for hooks in util/main-loop.c, util/async.c etc. + stub_ss.add(files('cpus-get-virtual-clock.c')) + stub_ss.add(files('icount.c')) + stub_ss.add(files('graph-lock.c')) + if linux_io_uring.found() + stub_ss.add(files('io_uring.c')) + endif + if libaio.found() + stub_ss.add(files('linux-aio.c')) + endif + stub_ss.add(files('qemu-timer-notify-cb.c')) + + # stubs for monitor + stub_ss.add(files('monitor-internal.c')) + stub_ss.add(files('qmp-command-available.c')) + stub_ss.add(files('qmp-quit.c')) +endif + +if have_block or have_user + stub_ss.add(files('qtest.c')) + stub_ss.add(files('vm-stop.c')) + stub_ss.add(files('vmstate.c')) + + # more symbols provided by the monitor + stub_ss.add(files('error-printf.c')) +endif + +if have_user + # Symbols that are used by hw/core. + stub_ss.add(files('cpu-synchronize-state.c')) stub_ss.add(files('qdev.c')) endif -stub_ss.add(files('semihost-all.c')) + +if have_system + # Symbols that are only needed in some configurations. Try not + # adding more of these. If the symbol is used in specific_ss, + # in particular, consider defining a preprocessor macro via + # Kconfig or configs/targets/. + stub_ss.add(files('dump.c')) + stub_ss.add(files('cmos.c')) + stub_ss.add(files('fw_cfg.c')) + stub_ss.add(files('target-get-monitor-def.c')) + stub_ss.add(files('target-monitor-defs.c')) + stub_ss.add(files('win32-kbd-hook.c')) + stub_ss.add(files('xen-hw-stub.c')) +endif + +if have_system or have_user + stub_ss.add(files('gdbstub.c')) + + # Also included in have_system for --disable-tcg builds + stub_ss.add(files('replay.c')) + + # Also included in have_system for tests/unit/test-qdev-global-props + stub_ss.add(files('hotplug-stubs.c')) + stub_ss.add(files('sysbus.c')) +endif diff --git a/stubs/module-opts.c b/stubs/module-opts.c deleted file mode 100644 index 5412429ea8..0000000000 --- a/stubs/module-opts.c +++ /dev/null @@ -1,2 +0,0 @@ -#include "qemu/osdep.h" -#include "qemu/config-file.h" diff --git a/stubs/monitor-core.c b/stubs/monitor-core.c index afa477aae6..1894cdfe1f 100644 --- a/stubs/monitor-core.c +++ b/stubs/monitor-core.c @@ -12,10 +12,6 @@ Monitor *monitor_set_cur(Coroutine *co, Monitor *mon) return NULL; } -void monitor_init_qmp(Chardev *chr, bool pretty, Error **errp) -{ -} - void qapi_event_emit(QAPIEvent event, QDict *qdict) { } @@ -24,5 +20,3 @@ int monitor_vprintf(Monitor *mon, const char *fmt, va_list ap) { abort(); } - - diff --git a/stubs/monitor.c b/stubs/monitor-internal.c similarity index 79% rename from stubs/monitor.c rename to stubs/monitor-internal.c index 20786ac4ff..4fece49d53 100644 --- a/stubs/monitor.c +++ b/stubs/monitor-internal.c @@ -1,7 +1,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "monitor/monitor.h" -#include "../monitor/monitor-internal.h" int monitor_get_fd(Monitor *mon, const char *name, Error **errp) { @@ -12,7 +11,3 @@ int monitor_get_fd(Monitor *mon, const char *name, Error **errp) void monitor_init_hmp(Chardev *chr, bool use_readline, Error **errp) { } - -void monitor_fdsets_cleanup(void) -{ -} diff --git a/stubs/pci-bus.c b/stubs/pci-bus.c deleted file mode 100644 index a8932fa932..0000000000 --- a/stubs/pci-bus.c +++ /dev/null @@ -1,7 +0,0 @@ -#include "qemu/osdep.h" -#include "hw/pci/pci.h" - -PCIDevice *pci_create_simple(PCIBus *bus, int devfn, const char *name) -{ - g_assert_not_reached(); -} diff --git a/stubs/qdev.c b/stubs/qdev.c index 6869f6f90a..7e957b3e52 100644 --- a/stubs/qdev.c +++ b/stubs/qdev.c @@ -20,9 +20,3 @@ void qapi_event_send_device_deleted(const char *device, { /* Nothing to do. */ } - -void qapi_event_send_device_unplug_guest_error(const char *device, - const char *path) -{ - /* Nothing to do. */ -} diff --git a/stubs/qtest.c b/stubs/qtest.c index 4666a49d7d..39e376eb67 100644 --- a/stubs/qtest.c +++ b/stubs/qtest.c @@ -13,13 +13,3 @@ /* Needed for qtest_allowed() */ bool qtest_allowed; - -bool qtest_driver(void) -{ - return false; -} - -int64_t qtest_get_virtual_clock(void) -{ - return 0; -} diff --git a/stubs/replay-mode.c b/stubs/replay-mode.c new file mode 100644 index 0000000000..264be9d96c --- /dev/null +++ b/stubs/replay-mode.c @@ -0,0 +1,4 @@ +#include "qemu/osdep.h" +#include "sysemu/replay.h" + +ReplayMode replay_mode; diff --git a/stubs/replay.c b/stubs/replay.c index 42c92e4acb..b4dd6a566e 100644 --- a/stubs/replay.c +++ b/stubs/replay.c @@ -1,8 +1,6 @@ #include "qemu/osdep.h" #include "exec/replay-core.h" -ReplayMode replay_mode; - void replay_finish(void) { } diff --git a/system/memory.c b/system/memory.c index a229a79988..c756950c0c 100644 --- a/system/memory.c +++ b/system/memory.c @@ -1850,6 +1850,11 @@ bool memory_region_is_protected(MemoryRegion *mr) return mr->ram && (mr->ram_block->flags & RAM_PROTECTED); } +bool memory_region_has_guest_memfd(MemoryRegion *mr) +{ + return mr->ram_block && mr->ram_block->guest_memfd >= 0; +} + uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr) { uint8_t mask = mr->dirty_log_mask; diff --git a/system/physmem.c b/system/physmem.c index a4fe3d2bf8..c3d04ca921 100644 --- a/system/physmem.c +++ b/system/physmem.c @@ -1808,6 +1808,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp) const bool shared = qemu_ram_is_shared(new_block); RAMBlock *block; RAMBlock *last_block = NULL; + bool free_on_error = false; ram_addr_t old_ram_size, new_ram_size; Error *err = NULL; @@ -1837,6 +1838,26 @@ static void ram_block_add(RAMBlock *new_block, Error **errp) return; } memory_try_enable_merging(new_block->host, new_block->max_length); + free_on_error = true; + } + } + + if (new_block->flags & RAM_GUEST_MEMFD) { + assert(kvm_enabled()); + assert(new_block->guest_memfd < 0); + + if (ram_block_discard_require(true) < 0) { + error_setg_errno(errp, errno, + "cannot set up private guest memory: discard currently blocked"); + error_append_hint(errp, "Are you using assigned devices?\n"); + goto out_free; + } + + new_block->guest_memfd = kvm_create_guest_memfd(new_block->max_length, + 0, errp); + if (new_block->guest_memfd < 0) { + qemu_mutex_unlock_ramlist(); + goto out_free; } } @@ -1888,6 +1909,13 @@ static void ram_block_add(RAMBlock *new_block, Error **errp) ram_block_notify_add(new_block->host, new_block->used_length, new_block->max_length); } + return; + +out_free: + if (free_on_error) { + qemu_anon_ram_free(new_block->host, new_block->max_length); + new_block->host = NULL; + } } #ifdef CONFIG_POSIX @@ -1902,7 +1930,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, /* Just support these ram flags by now. */ assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_NORESERVE | RAM_PROTECTED | RAM_NAMED_FILE | RAM_READONLY | - RAM_READONLY_FD)) == 0); + RAM_READONLY_FD | RAM_GUEST_MEMFD)) == 0); if (xen_enabled()) { error_setg(errp, "-mem-path not supported with Xen"); @@ -1939,6 +1967,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, new_block->used_length = size; new_block->max_length = size; new_block->flags = ram_flags; + new_block->guest_memfd = -1; new_block->host = file_ram_alloc(new_block, size, fd, !file_size, offset, errp); if (!new_block->host) { @@ -2018,7 +2047,7 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size, int align; assert((ram_flags & ~(RAM_SHARED | RAM_RESIZEABLE | RAM_PREALLOC | - RAM_NORESERVE)) == 0); + RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0); assert(!host ^ (ram_flags & RAM_PREALLOC)); align = qemu_real_host_page_size(); @@ -2033,6 +2062,7 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size, new_block->max_length = max_size; assert(max_size >= size); new_block->fd = -1; + new_block->guest_memfd = -1; new_block->page_size = qemu_real_host_page_size(); new_block->host = host; new_block->flags = ram_flags; @@ -2055,7 +2085,7 @@ RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags, MemoryRegion *mr, Error **errp) { - assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE)) == 0); + assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0); return qemu_ram_alloc_internal(size, size, NULL, NULL, ram_flags, mr, errp); } @@ -2083,6 +2113,12 @@ static void reclaim_ramblock(RAMBlock *block) } else { qemu_anon_ram_free(block->host, block->max_length); } + + if (block->guest_memfd >= 0) { + close(block->guest_memfd); + ram_block_discard_require(false); + } + g_free(block); } @@ -3685,6 +3721,29 @@ err: return ret; } +int ram_block_discard_guest_memfd_range(RAMBlock *rb, uint64_t start, + size_t length) +{ + int ret = -1; + +#ifdef CONFIG_FALLOCATE_PUNCH_HOLE + ret = fallocate(rb->guest_memfd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + start, length); + + if (ret) { + ret = -errno; + error_report("%s: Failed to fallocate %s:%" PRIx64 " +%zx (%d)", + __func__, rb->idstr, start, length, ret); + } +#else + ret = -ENOSYS; + error_report("%s: fallocate not available %s:%" PRIx64 " +%zx (%d)", + __func__, rb->idstr, start, length, ret); +#endif + + return ret; +} + bool ramblock_is_pmem(RAMBlock *rb) { return rb->flags & RAM_PMEM; diff --git a/system/runstate.c b/system/runstate.c index d6ab860eca..cb4905a40f 100644 --- a/system/runstate.c +++ b/system/runstate.c @@ -501,7 +501,20 @@ void qemu_system_reset(ShutdownCause reason) default: qapi_event_send_reset(shutdown_caused_by_guest(reason), reason); } - cpu_synchronize_all_post_reset(); + + /* + * Some boards use the machine reset callback to point CPUs to the firmware + * entry point. Assume that this is not the case for boards that support + * non-resettable CPUs (currently used only for confidential guests), in + * which case cpu_synchronize_all_post_init() is enough because + * it does _more_ than cpu_synchronize_all_post_reset(). + */ + if (cpus_are_resettable()) { + cpu_synchronize_all_post_reset(); + } else { + assert(runstate_check(RUN_STATE_PRELAUNCH)); + } + vm_set_suspended(false); } diff --git a/target/arm/kvm.c b/target/arm/kvm.c index ab85d628a8..21ebbf3b8f 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -1598,11 +1598,6 @@ int kvm_arch_msi_data_to_gsi(uint32_t data) return (data - 32) & 0xffff; } -bool kvm_arch_cpu_check_are_resettable(void) -{ - return true; -} - static void kvm_arch_get_eager_split_size(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) diff --git a/target/i386/confidential-guest.c b/target/i386/confidential-guest.c new file mode 100644 index 0000000000..b3727845ad --- /dev/null +++ b/target/i386/confidential-guest.c @@ -0,0 +1,33 @@ +/* + * QEMU Confidential Guest support + * + * Copyright (C) 2024 Red Hat, Inc. + * + * Authors: + * Paolo Bonzini + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" + +#include "confidential-guest.h" + +OBJECT_DEFINE_ABSTRACT_TYPE(X86ConfidentialGuest, + x86_confidential_guest, + X86_CONFIDENTIAL_GUEST, + CONFIDENTIAL_GUEST_SUPPORT) + +static void x86_confidential_guest_class_init(ObjectClass *oc, void *data) +{ +} + +static void x86_confidential_guest_init(Object *obj) +{ +} + +static void x86_confidential_guest_finalize(Object *obj) +{ +} diff --git a/target/i386/confidential-guest.h b/target/i386/confidential-guest.h new file mode 100644 index 0000000000..532e172a60 --- /dev/null +++ b/target/i386/confidential-guest.h @@ -0,0 +1,59 @@ +/* + * x86-specific confidential guest methods. + * + * Copyright (c) 2024 Red Hat Inc. + * + * Authors: + * Paolo Bonzini + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#ifndef TARGET_I386_CG_H +#define TARGET_I386_CG_H + +#include "qom/object.h" + +#include "exec/confidential-guest-support.h" + +#define TYPE_X86_CONFIDENTIAL_GUEST "x86-confidential-guest" + +OBJECT_DECLARE_TYPE(X86ConfidentialGuest, + X86ConfidentialGuestClass, + X86_CONFIDENTIAL_GUEST) + +struct X86ConfidentialGuest { + /* */ + ConfidentialGuestSupport parent_obj; +}; + +/** + * X86ConfidentialGuestClass: + * + * Class to be implemented by confidential-guest-support concrete objects + * for the x86 target. + */ +struct X86ConfidentialGuestClass { + /* */ + ConfidentialGuestSupportClass parent; + + /* */ + int (*kvm_type)(X86ConfidentialGuest *cg); +}; + +/** + * x86_confidential_guest_kvm_type: + * + * Calls #X86ConfidentialGuestClass.unplug callback of @plug_handler. + */ +static inline int x86_confidential_guest_kvm_type(X86ConfidentialGuest *cg) +{ + X86ConfidentialGuestClass *klass = X86_CONFIDENTIAL_GUEST_GET_CLASS(cg); + + if (klass->kvm_type) { + return klass->kvm_type(cg); + } else { + return 0; + } +} +#endif diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 33760a2ee1..fd6af0d763 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -1158,8 +1158,8 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { NULL, "sbdr-ssdp-no", "fbsdp-no", "psdp-no", NULL, "fb-clear", NULL, NULL, NULL, NULL, NULL, NULL, - "pbrsb-no", NULL, "gds-no", NULL, - NULL, NULL, NULL, NULL, + "pbrsb-no", NULL, "gds-no", "rfds-no", + "rfds-clear", NULL, NULL, NULL, }, .msr = { .index = MSR_IA32_ARCH_CAPABILITIES, @@ -3822,6 +3822,16 @@ static const X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ } }, }, + { + .version = 7, + .note = "TSX, taa-no", + .props = (PropValue[]) { + /* Restore TSX features removed by -v2 above */ + { "hle", "on" }, + { "rtm", "on" }, + { /* end of list */ } + }, + }, { /* end of list */ } } }, @@ -4099,6 +4109,132 @@ static const X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ }, }, }, + { + .name = "SierraForest", + .level = 0x23, + .vendor = CPUID_VENDOR_INTEL, + .family = 6, + .model = 175, + .stepping = 0, + /* + * please keep the ascending order so that we can have a clear view of + * bit position of each feature. + */ + .features[FEAT_1_EDX] = + CPUID_FP87 | CPUID_VME | CPUID_DE | CPUID_PSE | CPUID_TSC | + CPUID_MSR | CPUID_PAE | CPUID_MCE | CPUID_CX8 | CPUID_APIC | + CPUID_SEP | CPUID_MTRR | CPUID_PGE | CPUID_MCA | CPUID_CMOV | + CPUID_PAT | CPUID_PSE36 | CPUID_CLFLUSH | CPUID_MMX | CPUID_FXSR | + CPUID_SSE | CPUID_SSE2, + .features[FEAT_1_ECX] = + CPUID_EXT_SSE3 | CPUID_EXT_PCLMULQDQ | CPUID_EXT_SSSE3 | + CPUID_EXT_FMA | CPUID_EXT_CX16 | CPUID_EXT_PCID | CPUID_EXT_SSE41 | + CPUID_EXT_SSE42 | CPUID_EXT_X2APIC | CPUID_EXT_MOVBE | + CPUID_EXT_POPCNT | CPUID_EXT_TSC_DEADLINE_TIMER | CPUID_EXT_AES | + CPUID_EXT_XSAVE | CPUID_EXT_AVX | CPUID_EXT_F16C | CPUID_EXT_RDRAND, + .features[FEAT_8000_0001_EDX] = + CPUID_EXT2_SYSCALL | CPUID_EXT2_NX | CPUID_EXT2_PDPE1GB | + CPUID_EXT2_RDTSCP | CPUID_EXT2_LM, + .features[FEAT_8000_0001_ECX] = + CPUID_EXT3_LAHF_LM | CPUID_EXT3_ABM | CPUID_EXT3_3DNOWPREFETCH, + .features[FEAT_8000_0008_EBX] = + CPUID_8000_0008_EBX_WBNOINVD, + .features[FEAT_7_0_EBX] = + CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 | + CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_ERMS | + CPUID_7_0_EBX_INVPCID | CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX | + CPUID_7_0_EBX_SMAP | CPUID_7_0_EBX_CLFLUSHOPT | CPUID_7_0_EBX_CLWB | + CPUID_7_0_EBX_SHA_NI, + .features[FEAT_7_0_ECX] = + CPUID_7_0_ECX_UMIP | CPUID_7_0_ECX_PKU | CPUID_7_0_ECX_GFNI | + CPUID_7_0_ECX_VAES | CPUID_7_0_ECX_VPCLMULQDQ | + CPUID_7_0_ECX_RDPID | CPUID_7_0_ECX_BUS_LOCK_DETECT, + .features[FEAT_7_0_EDX] = + CPUID_7_0_EDX_FSRM | CPUID_7_0_EDX_SERIALIZE | + CPUID_7_0_EDX_SPEC_CTRL | CPUID_7_0_EDX_ARCH_CAPABILITIES | + CPUID_7_0_EDX_SPEC_CTRL_SSBD, + .features[FEAT_ARCH_CAPABILITIES] = + MSR_ARCH_CAP_RDCL_NO | MSR_ARCH_CAP_IBRS_ALL | + MSR_ARCH_CAP_SKIP_L1DFL_VMENTRY | MSR_ARCH_CAP_MDS_NO | + MSR_ARCH_CAP_PSCHANGE_MC_NO | MSR_ARCH_CAP_SBDR_SSDP_NO | + MSR_ARCH_CAP_FBSDP_NO | MSR_ARCH_CAP_PSDP_NO | + MSR_ARCH_CAP_PBRSB_NO, + .features[FEAT_XSAVE] = + CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | + CPUID_XSAVE_XGETBV1 | CPUID_XSAVE_XSAVES, + .features[FEAT_6_EAX] = + CPUID_6_EAX_ARAT, + .features[FEAT_7_1_EAX] = + CPUID_7_1_EAX_AVX_VNNI | CPUID_7_1_EAX_CMPCCXADD | + CPUID_7_1_EAX_FSRS | CPUID_7_1_EAX_AVX_IFMA, + .features[FEAT_7_1_EDX] = + CPUID_7_1_EDX_AVX_VNNI_INT8 | CPUID_7_1_EDX_AVX_NE_CONVERT, + .features[FEAT_7_2_EDX] = + CPUID_7_2_EDX_MCDT_NO, + .features[FEAT_VMX_BASIC] = + MSR_VMX_BASIC_INS_OUTS | MSR_VMX_BASIC_TRUE_CTLS, + .features[FEAT_VMX_ENTRY_CTLS] = + VMX_VM_ENTRY_LOAD_DEBUG_CONTROLS | VMX_VM_ENTRY_IA32E_MODE | + VMX_VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | + VMX_VM_ENTRY_LOAD_IA32_PAT | VMX_VM_ENTRY_LOAD_IA32_EFER, + .features[FEAT_VMX_EPT_VPID_CAPS] = + MSR_VMX_EPT_EXECONLY | MSR_VMX_EPT_PAGE_WALK_LENGTH_4 | + MSR_VMX_EPT_WB | MSR_VMX_EPT_2MB | MSR_VMX_EPT_1GB | + MSR_VMX_EPT_INVEPT | MSR_VMX_EPT_AD_BITS | + MSR_VMX_EPT_INVEPT_SINGLE_CONTEXT | MSR_VMX_EPT_INVEPT_ALL_CONTEXT | + MSR_VMX_EPT_INVVPID | MSR_VMX_EPT_INVVPID_SINGLE_ADDR | + MSR_VMX_EPT_INVVPID_SINGLE_CONTEXT | + MSR_VMX_EPT_INVVPID_ALL_CONTEXT | + MSR_VMX_EPT_INVVPID_SINGLE_CONTEXT_NOGLOBALS, + .features[FEAT_VMX_EXIT_CTLS] = + VMX_VM_EXIT_SAVE_DEBUG_CONTROLS | + VMX_VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | + VMX_VM_EXIT_ACK_INTR_ON_EXIT | VMX_VM_EXIT_SAVE_IA32_PAT | + VMX_VM_EXIT_LOAD_IA32_PAT | VMX_VM_EXIT_SAVE_IA32_EFER | + VMX_VM_EXIT_LOAD_IA32_EFER | VMX_VM_EXIT_SAVE_VMX_PREEMPTION_TIMER, + .features[FEAT_VMX_MISC] = + MSR_VMX_MISC_STORE_LMA | MSR_VMX_MISC_ACTIVITY_HLT | + MSR_VMX_MISC_VMWRITE_VMEXIT, + .features[FEAT_VMX_PINBASED_CTLS] = + VMX_PIN_BASED_EXT_INTR_MASK | VMX_PIN_BASED_NMI_EXITING | + VMX_PIN_BASED_VIRTUAL_NMIS | VMX_PIN_BASED_VMX_PREEMPTION_TIMER | + VMX_PIN_BASED_POSTED_INTR, + .features[FEAT_VMX_PROCBASED_CTLS] = + VMX_CPU_BASED_VIRTUAL_INTR_PENDING | + VMX_CPU_BASED_USE_TSC_OFFSETING | VMX_CPU_BASED_HLT_EXITING | + VMX_CPU_BASED_INVLPG_EXITING | VMX_CPU_BASED_MWAIT_EXITING | + VMX_CPU_BASED_RDPMC_EXITING | VMX_CPU_BASED_RDTSC_EXITING | + VMX_CPU_BASED_CR3_LOAD_EXITING | VMX_CPU_BASED_CR3_STORE_EXITING | + VMX_CPU_BASED_CR8_LOAD_EXITING | VMX_CPU_BASED_CR8_STORE_EXITING | + VMX_CPU_BASED_TPR_SHADOW | VMX_CPU_BASED_VIRTUAL_NMI_PENDING | + VMX_CPU_BASED_MOV_DR_EXITING | VMX_CPU_BASED_UNCOND_IO_EXITING | + VMX_CPU_BASED_USE_IO_BITMAPS | VMX_CPU_BASED_MONITOR_TRAP_FLAG | + VMX_CPU_BASED_USE_MSR_BITMAPS | VMX_CPU_BASED_MONITOR_EXITING | + VMX_CPU_BASED_PAUSE_EXITING | + VMX_CPU_BASED_ACTIVATE_SECONDARY_CONTROLS, + .features[FEAT_VMX_SECONDARY_CTLS] = + VMX_SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + VMX_SECONDARY_EXEC_ENABLE_EPT | VMX_SECONDARY_EXEC_DESC | + VMX_SECONDARY_EXEC_RDTSCP | + VMX_SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + VMX_SECONDARY_EXEC_ENABLE_VPID | VMX_SECONDARY_EXEC_WBINVD_EXITING | + VMX_SECONDARY_EXEC_UNRESTRICTED_GUEST | + VMX_SECONDARY_EXEC_APIC_REGISTER_VIRT | + VMX_SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | + VMX_SECONDARY_EXEC_RDRAND_EXITING | + VMX_SECONDARY_EXEC_ENABLE_INVPCID | + VMX_SECONDARY_EXEC_ENABLE_VMFUNC | VMX_SECONDARY_EXEC_SHADOW_VMCS | + VMX_SECONDARY_EXEC_RDSEED_EXITING | VMX_SECONDARY_EXEC_ENABLE_PML | + VMX_SECONDARY_EXEC_XSAVES, + .features[FEAT_VMX_VMFUNC] = + MSR_VMX_VMFUNC_EPT_SWITCHING, + .xlevel = 0x80000008, + .model_id = "Intel Xeon Processor (SierraForest)", + .versions = (X86CPUVersionDefinition[]) { + { .version = 1 }, + { /* end of list */ }, + }, + }, { .name = "Denverton", .level = 21, @@ -6570,6 +6706,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, if (env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) { /* 64 bit processor */ *eax |= (cpu_x86_virtual_addr_width(env) << 8); + *eax |= (cpu->guest_phys_bits << 16); } *ebx = env->features[FEAT_8000_0008_EBX]; if (cs->nr_cores * cs->nr_threads > 1) { @@ -7230,7 +7367,6 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) X86CPUClass *xcc = X86_CPU_GET_CLASS(dev); CPUX86State *env = &cpu->env; Error *local_err = NULL; - static bool ht_warned; unsigned requested_lbr_fmt; #if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) @@ -7329,6 +7465,14 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) goto out; } + if (cpu->guest_phys_bits == -1) { + /* + * If it was not set by the user, or by the accelerator via + * cpu_exec_realizefn, clear. + */ + cpu->guest_phys_bits = 0; + } + if (cpu->ucode_rev == 0) { /* * The default is the same as KVM's. Note that this check @@ -7379,6 +7523,14 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) if (cpu->phys_bits == 0) { cpu->phys_bits = TCG_PHYS_ADDR_BITS; } + if (cpu->guest_phys_bits && + (cpu->guest_phys_bits > cpu->phys_bits || + cpu->guest_phys_bits < 32)) { + error_setg(errp, "guest-phys-bits should be between 32 and %u " + " (but is %u)", + cpu->phys_bits, cpu->guest_phys_bits); + return; + } } else { /* For 32 bit systems don't use the user set value, but keep * phys_bits consistent with what we tell the guest. @@ -7387,6 +7539,10 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) error_setg(errp, "phys-bits is not user-configurable in 32 bit"); return; } + if (cpu->guest_phys_bits != 0) { + error_setg(errp, "guest-phys-bits is not user-configurable in 32 bit"); + return; + } if (env->features[FEAT_1_EDX] & (CPUID_PSE36 | CPUID_PAE)) { cpu->phys_bits = 36; @@ -7453,13 +7609,11 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) */ if (IS_AMD_CPU(env) && !(env->features[FEAT_8000_0001_ECX] & CPUID_EXT3_TOPOEXT) && - cs->nr_threads > 1 && !ht_warned) { - warn_report("This family of AMD CPU doesn't support " - "hyperthreading(%d)", - cs->nr_threads); - error_printf("Please configure -smp options properly" - " or try enabling topoext feature.\n"); - ht_warned = true; + cs->nr_threads > 1) { + warn_report_once("This family of AMD CPU doesn't support " + "hyperthreading(%d). Please configure -smp " + "options properly or try enabling topoext " + "feature.", cs->nr_threads); } #ifndef CONFIG_USER_ONLY @@ -7887,6 +8041,7 @@ static Property x86_cpu_properties[] = { DEFINE_PROP_BOOL("x-force-features", X86CPU, force_features, false), DEFINE_PROP_BOOL("kvm", X86CPU, expose_kvm, true), DEFINE_PROP_UINT32("phys-bits", X86CPU, phys_bits, 0), + DEFINE_PROP_UINT32("guest-phys-bits", X86CPU, guest_phys_bits, -1), DEFINE_PROP_BOOL("host-phys-bits", X86CPU, host_phys_bits, false), DEFINE_PROP_UINT8("host-phys-bits-limit", X86CPU, host_phys_bits_limit, 0), DEFINE_PROP_BOOL("fill-mtrr-mask", X86CPU, fill_mtrr_mask, true), diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 6b05738079..6112e27bfd 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -2027,6 +2027,14 @@ struct ArchCPU { /* Number of physical address bits supported */ uint32_t phys_bits; + /* + * Number of guest physical address bits available. Usually this is + * identical to host physical address bits. With NPT or EPT 4-level + * paging, guest physical address space might be restricted to 48 bits + * even if the host cpu supports more physical address bits. + */ + uint32_t guest_phys_bits; + /* in order to simplify APIC support, we leave this pointer to the user */ struct DeviceState *apic_state; diff --git a/target/i386/host-cpu.c b/target/i386/host-cpu.c index 92ecb7254b..280e427c01 100644 --- a/target/i386/host-cpu.c +++ b/target/i386/host-cpu.c @@ -55,18 +55,15 @@ static uint32_t host_cpu_adjust_phys_bits(X86CPU *cpu) { uint32_t host_phys_bits = host_cpu_phys_bits(); uint32_t phys_bits = cpu->phys_bits; - static bool warned; /* * Print a warning if the user set it to a value that's not the * host value. */ - if (phys_bits != host_phys_bits && phys_bits != 0 && - !warned) { - warn_report("Host physical bits (%u)" - " does not match phys-bits property (%u)", - host_phys_bits, phys_bits); - warned = true; + if (phys_bits != host_phys_bits && phys_bits != 0) { + warn_report_once("Host physical bits (%u)" + " does not match phys-bits property (%u)", + host_phys_bits, phys_bits); } if (cpu->host_phys_bits) { diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c index 9c791b7b05..f76972e47e 100644 --- a/target/i386/kvm/kvm-cpu.c +++ b/target/i386/kvm/kvm-cpu.c @@ -18,10 +18,32 @@ #include "kvm_i386.h" #include "hw/core/accel-cpu.h" +static void kvm_set_guest_phys_bits(CPUState *cs) +{ + X86CPU *cpu = X86_CPU(cs); + uint32_t eax, guest_phys_bits; + + eax = kvm_arch_get_supported_cpuid(cs->kvm_state, 0x80000008, 0, R_EAX); + guest_phys_bits = (eax >> 16) & 0xff; + if (!guest_phys_bits) { + return; + } + cpu->guest_phys_bits = guest_phys_bits; + if (cpu->guest_phys_bits > cpu->phys_bits) { + cpu->guest_phys_bits = cpu->phys_bits; + } + + if (cpu->host_phys_bits && cpu->host_phys_bits_limit && + cpu->guest_phys_bits > cpu->host_phys_bits_limit) { + cpu->guest_phys_bits = cpu->host_phys_bits_limit; + } +} + static bool kvm_cpu_realizefn(CPUState *cs, Error **errp) { X86CPU *cpu = X86_CPU(cs); CPUX86State *env = &cpu->env; + bool ret; /* * The realize order is important, since x86_cpu_realize() checks if @@ -32,13 +54,15 @@ static bool kvm_cpu_realizefn(CPUState *cs, Error **errp) * * realize order: * - * x86_cpu_realize(): - * -> x86_cpu_expand_features() - * -> cpu_exec_realizefn(): - * -> accel_cpu_common_realize() - * kvm_cpu_realizefn() -> host_cpu_realizefn() - * -> cpu_common_realizefn() - * -> check/update ucode_rev, phys_bits, mwait + * x86_cpu_realizefn(): + * x86_cpu_expand_features() + * cpu_exec_realizefn(): + * accel_cpu_common_realize() + * kvm_cpu_realizefn() + * host_cpu_realizefn() + * kvm_set_guest_phys_bits() + * check/update ucode_rev, phys_bits, guest_phys_bits, mwait + * cpu_common_realizefn() (via xcc->parent_realize) */ if (cpu->max_features) { if (enable_cpu_pm && kvm_has_waitpkg()) { @@ -50,7 +74,17 @@ static bool kvm_cpu_realizefn(CPUState *cs, Error **errp) MSR_IA32_UCODE_REV); } } - return host_cpu_realizefn(cs, errp); + ret = host_cpu_realizefn(cs, errp); + if (!ret) { + return ret; + } + + if ((env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) && + cpu->guest_phys_bits == -1) { + kvm_set_guest_phys_bits(cs); + } + + return true; } static bool lmce_supported(void) 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); @@ -1706,6 +1752,231 @@ 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 limit, i, j; + uint32_t unused; + struct kvm_cpuid_entry2 *c; + + cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused); + + for (i = 0; i <= limit; i++) { + j = 0; + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + goto full; + } + c = &entries[cpuid_i++]; + switch (i) { + case 2: { + /* Keep reading function 2 till all the input is received */ + int times; + + c->function = i; + c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC | + KVM_CPUID_FLAG_STATE_READ_NEXT; + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); + times = c->eax & 0xff; + + for (j = 1; j < times; ++j) { + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + goto full; + } + 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); + } + break; + } + case 0x1f: + if (env->nr_dies < 2) { + cpuid_i--; + break; + } + /* fallthrough */ + case 4: + case 0xb: + case 0xd: + for (j = 0; ; j++) { + if (i == 0xd && j == 64) { + break; + } + + c->function = i; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + c->index = j; + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); + + if (i == 4 && c->eax == 0) { + break; + } + if (i == 0xb && !(c->ecx & 0xff00)) { + break; + } + if (i == 0x1f && !(c->ecx & 0xff00)) { + break; + } + if (i == 0xd && c->eax == 0) { + continue; + } + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + goto full; + } + c = &entries[cpuid_i++]; + } + break; + case 0x12: + for (j = 0; ; j++) { + c->function = i; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + c->index = j; + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); + + if (j > 1 && (c->eax & 0xf) != 1) { + break; + } + + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + goto full; + } + c = &entries[cpuid_i++]; + } + break; + case 0x7: + case 0x14: + case 0x1d: + case 0x1e: { + uint32_t times; + + c->function = i; + c->index = 0; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); + times = c->eax; + + for (j = 1; j <= times; ++j) { + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + goto full; + } + c = &entries[cpuid_i++]; + c->function = i; + c->index = j; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); + } + break; + } + default: + c->function = i; + c->flags = 0; + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); + if (!c->eax && !c->ebx && !c->ecx && !c->edx) { + /* + * KVM already returns all zeroes if a CPUID entry is missing, + * so we can omit it and avoid hitting KVM's 80-entry limit. + */ + cpuid_i--; + } + break; + } + } + + if (limit >= 0x0a) { + uint32_t eax, edx; + + cpu_x86_cpuid(env, 0x0a, 0, &eax, &unused, &unused, &edx); + + has_architectural_pmu_version = eax & 0xff; + if (has_architectural_pmu_version > 0) { + num_architectural_pmu_gp_counters = (eax & 0xff00) >> 8; + + /* Shouldn't be more than 32, since that's the number of bits + * available in EBX to tell us _which_ counters are available. + * Play it safe. + */ + if (num_architectural_pmu_gp_counters > MAX_GP_COUNTERS) { + num_architectural_pmu_gp_counters = MAX_GP_COUNTERS; + } + + if (has_architectural_pmu_version > 1) { + num_architectural_pmu_fixed_counters = edx & 0x1f; + + if (num_architectural_pmu_fixed_counters > MAX_FIXED_COUNTERS) { + num_architectural_pmu_fixed_counters = MAX_FIXED_COUNTERS; + } + } + } + } + + 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) { + goto full; + } + c = &entries[cpuid_i++]; + + switch (i) { + case 0x8000001d: + /* Query for all AMD cache information leaves */ + for (j = 0; ; j++) { + c->function = i; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + c->index = j; + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); + + if (c->eax == 0) { + break; + } + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + goto full; + } + c = &entries[cpuid_i++]; + } + break; + default: + c->function = i; + c->flags = 0; + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); + if (!c->eax && !c->ebx && !c->ecx && !c->edx) { + /* + * KVM already returns all zeroes if a CPUID entry is missing, + * so we can omit it and avoid hitting KVM's 80-entry limit. + */ + cpuid_i--; + } + break; + } + } + + /* Call Centaur's CPUID instructions they are supported. */ + if (env->cpuid_xlevel2 > 0) { + 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) { + goto full; + } + c = &entries[cpuid_i++]; + + c->function = i; + c->flags = 0; + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); + } + } + + 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 { @@ -1722,8 +1993,7 @@ int kvm_arch_init_vcpu(CPUState *cs) X86CPU *cpu = X86_CPU(cs); CPUX86State *env = &cpu->env; - uint32_t limit, i, j, cpuid_i; - uint32_t unused; + uint32_t cpuid_i; struct kvm_cpuid_entry2 *c; uint32_t signature[3]; int kvm_base = KVM_CPUID_SIGNATURE; @@ -1876,8 +2146,6 @@ int kvm_arch_init_vcpu(CPUState *cs) 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) { @@ -1888,224 +2156,7 @@ int kvm_arch_init_vcpu(CPUState *cs) } } - for (i = 0; i <= limit; i++) { - if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "unsupported level value: 0x%x\n", limit); - abort(); - } - c = &cpuid_data.entries[cpuid_i++]; - - switch (i) { - case 2: { - /* Keep reading function 2 till all the input is received */ - int times; - - c->function = i; - c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC | - KVM_CPUID_FLAG_STATE_READ_NEXT; - cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); - times = c->eax & 0xff; - - 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(); - } - c = &cpuid_data.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); - } - break; - } - case 0x1f: - if (env->nr_dies < 2) { - cpuid_i--; - break; - } - /* fallthrough */ - case 4: - case 0xb: - case 0xd: - for (j = 0; ; j++) { - if (i == 0xd && j == 64) { - break; - } - - c->function = i; - c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - c->index = j; - cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); - - if (i == 4 && c->eax == 0) { - break; - } - if (i == 0xb && !(c->ecx & 0xff00)) { - break; - } - if (i == 0x1f && !(c->ecx & 0xff00)) { - break; - } - if (i == 0xd && c->eax == 0) { - 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(); - } - c = &cpuid_data.entries[cpuid_i++]; - } - break; - case 0x12: - for (j = 0; ; j++) { - c->function = i; - c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - c->index = j; - cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); - - if (j > 1 && (c->eax & 0xf) != 1) { - break; - } - - 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(); - } - c = &cpuid_data.entries[cpuid_i++]; - } - break; - case 0x7: - case 0x14: - case 0x1d: - case 0x1e: { - uint32_t times; - - c->function = i; - c->index = 0; - c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); - times = c->eax; - - 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(); - } - c = &cpuid_data.entries[cpuid_i++]; - c->function = i; - c->index = j; - c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); - } - break; - } - default: - c->function = i; - c->flags = 0; - cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); - if (!c->eax && !c->ebx && !c->ecx && !c->edx) { - /* - * KVM already returns all zeroes if a CPUID entry is missing, - * so we can omit it and avoid hitting KVM's 80-entry limit. - */ - cpuid_i--; - } - break; - } - } - - if (limit >= 0x0a) { - uint32_t eax, edx; - - cpu_x86_cpuid(env, 0x0a, 0, &eax, &unused, &unused, &edx); - - has_architectural_pmu_version = eax & 0xff; - if (has_architectural_pmu_version > 0) { - num_architectural_pmu_gp_counters = (eax & 0xff00) >> 8; - - /* Shouldn't be more than 32, since that's the number of bits - * available in EBX to tell us _which_ counters are available. - * Play it safe. - */ - if (num_architectural_pmu_gp_counters > MAX_GP_COUNTERS) { - num_architectural_pmu_gp_counters = MAX_GP_COUNTERS; - } - - if (has_architectural_pmu_version > 1) { - num_architectural_pmu_fixed_counters = edx & 0x1f; - - if (num_architectural_pmu_fixed_counters > MAX_FIXED_COUNTERS) { - num_architectural_pmu_fixed_counters = MAX_FIXED_COUNTERS; - } - } - } - } - - cpu_x86_cpuid(env, 0x80000000, 0, &limit, &unused, &unused, &unused); - - for (i = 0x80000000; i <= limit; i++) { - if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "unsupported xlevel value: 0x%x\n", limit); - abort(); - } - c = &cpuid_data.entries[cpuid_i++]; - - switch (i) { - case 0x8000001d: - /* Query for all AMD cache information leaves */ - for (j = 0; ; j++) { - c->function = i; - c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - c->index = j; - cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); - - if (c->eax == 0) { - 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(); - } - c = &cpuid_data.entries[cpuid_i++]; - } - break; - default: - c->function = i; - c->flags = 0; - cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); - if (!c->eax && !c->ebx && !c->ecx && !c->edx) { - /* - * KVM already returns all zeroes if a CPUID entry is missing, - * so we can omit it and avoid hitting KVM's 80-entry limit. - */ - cpuid_i--; - } - break; - } - } - - /* Call Centaur's CPUID instructions they are supported. */ - if (env->cpuid_xlevel2 > 0) { - cpu_x86_cpuid(env, 0xC0000000, 0, &limit, &unused, &unused, &unused); - - for (i = 0xC0000000; i <= limit; i++) { - if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { - fprintf(stderr, "unsupported xlevel2 value: 0x%x\n", limit); - abort(); - } - c = &cpuid_data.entries[cpuid_i++]; - - c->function = i; - c->flags = 0; - cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); - } - } - + 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) diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h index 30fedcffea..6b44844d95 100644 --- a/target/i386/kvm/kvm_i386.h +++ b/target/i386/kvm/kvm_i386.h @@ -37,6 +37,7 @@ bool kvm_hv_vpindex_settable(void); bool kvm_enable_sgx_provisioning(KVMState *s); bool kvm_hyperv_expand_features(X86CPU *cpu, Error **errp); +int kvm_get_vm_type(MachineState *ms); void kvm_arch_reset_vcpu(X86CPU *cs); void kvm_arch_after_reset_vcpu(X86CPU *cpu); void kvm_arch_do_init_vcpu(X86CPU *cs); @@ -49,6 +50,7 @@ void kvm_request_xsave_components(X86CPU *cpu, uint64_t mask); #ifdef CONFIG_KVM +bool kvm_is_vm_type_supported(int type); bool kvm_has_adjust_clock_stable(void); bool kvm_has_exception_payload(void); void kvm_synchronize_all_tsc(void); diff --git a/target/i386/kvm/meson.build b/target/i386/kvm/meson.build index 84d9143e60..e7850981e6 100644 --- a/target/i386/kvm/meson.build +++ b/target/i386/kvm/meson.build @@ -7,8 +7,6 @@ i386_kvm_ss.add(files( i386_kvm_ss.add(when: 'CONFIG_XEN_EMU', if_true: files('xen-emu.c')) -i386_kvm_ss.add(when: 'CONFIG_SEV', if_false: files('sev-stub.c')) - i386_system_ss.add(when: 'CONFIG_HYPERV', if_true: files('hyperv.c'), if_false: files('hyperv-stub.c')) i386_system_ss.add_all(when: 'CONFIG_KVM', if_true: i386_kvm_ss) diff --git a/target/i386/kvm/sev-stub.c b/target/i386/kvm/sev-stub.c deleted file mode 100644 index 1be5341e8a..0000000000 --- a/target/i386/kvm/sev-stub.c +++ /dev/null @@ -1,21 +0,0 @@ -/* - * QEMU SEV stub - * - * Copyright Advanced Micro Devices 2018 - * - * Authors: - * Brijesh Singh - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "sev.h" - -int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) -{ - /* If we get here, cgs must be some non-SEV thing */ - return 0; -} diff --git a/target/i386/meson.build b/target/i386/meson.build index 7c74bfa859..8abce725f8 100644 --- a/target/i386/meson.build +++ b/target/i386/meson.build @@ -6,7 +6,7 @@ i386_ss.add(files( 'xsave_helper.c', 'cpu-dump.c', )) -i386_ss.add(when: 'CONFIG_SEV', if_true: files('host-cpu.c')) +i386_ss.add(when: 'CONFIG_SEV', if_true: files('host-cpu.c', 'confidential-guest.c')) # x86 cpu type i386_ss.add(when: 'CONFIG_KVM', if_true: files('host-cpu.c')) diff --git a/target/i386/sev.c b/target/i386/sev.c index 72930ff0dc..d30b68c11e 100644 --- a/target/i386/sev.c +++ b/target/i386/sev.c @@ -26,6 +26,7 @@ #include "qemu/error-report.h" #include "crypto/hash.h" #include "sysemu/kvm.h" +#include "kvm/kvm_i386.h" #include "sev.h" #include "sysemu/sysemu.h" #include "sysemu/runstate.h" @@ -35,7 +36,7 @@ #include "monitor/monitor.h" #include "monitor/hmp-target.h" #include "qapi/qapi-commands-misc-target.h" -#include "exec/confidential-guest-support.h" +#include "confidential-guest.h" #include "hw/i386/pc.h" #include "exec/address-spaces.h" @@ -54,7 +55,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(SevGuestState, SEV_GUEST) * -machine ...,memory-encryption=sev0 */ struct SevGuestState { - ConfidentialGuestSupport parent_obj; + X86ConfidentialGuest parent_obj; + + int kvm_type; /* configuration parameters */ char *sev_device; @@ -64,6 +67,7 @@ struct SevGuestState { uint32_t cbitpos; uint32_t reduced_phys_bits; bool kernel_hashes; + bool legacy_vm_type; /* runtime state */ uint32_t handle; @@ -353,63 +357,16 @@ static void sev_guest_set_kernel_hashes(Object *obj, bool value, Error **errp) sev->kernel_hashes = value; } -static void -sev_guest_class_init(ObjectClass *oc, void *data) +static bool sev_guest_get_legacy_vm_type(Object *obj, Error **errp) { - object_class_property_add_str(oc, "sev-device", - sev_guest_get_sev_device, - sev_guest_set_sev_device); - object_class_property_set_description(oc, "sev-device", - "SEV device to use"); - object_class_property_add_str(oc, "dh-cert-file", - sev_guest_get_dh_cert_file, - sev_guest_set_dh_cert_file); - object_class_property_set_description(oc, "dh-cert-file", - "guest owners DH certificate (encoded with base64)"); - object_class_property_add_str(oc, "session-file", - sev_guest_get_session_file, - sev_guest_set_session_file); - object_class_property_set_description(oc, "session-file", - "guest owners session parameters (encoded with base64)"); - object_class_property_add_bool(oc, "kernel-hashes", - sev_guest_get_kernel_hashes, - sev_guest_set_kernel_hashes); - object_class_property_set_description(oc, "kernel-hashes", - "add kernel hashes to guest firmware for measured Linux boot"); + return SEV_GUEST(obj)->legacy_vm_type; } -static void -sev_guest_instance_init(Object *obj) +static void sev_guest_set_legacy_vm_type(Object *obj, bool value, Error **errp) { - SevGuestState *sev = SEV_GUEST(obj); - - sev->sev_device = g_strdup(DEFAULT_SEV_DEVICE); - sev->policy = DEFAULT_GUEST_POLICY; - object_property_add_uint32_ptr(obj, "policy", &sev->policy, - OBJ_PROP_FLAG_READWRITE); - object_property_add_uint32_ptr(obj, "handle", &sev->handle, - OBJ_PROP_FLAG_READWRITE); - object_property_add_uint32_ptr(obj, "cbitpos", &sev->cbitpos, - OBJ_PROP_FLAG_READWRITE); - object_property_add_uint32_ptr(obj, "reduced-phys-bits", - &sev->reduced_phys_bits, - OBJ_PROP_FLAG_READWRITE); + SEV_GUEST(obj)->legacy_vm_type = value; } -/* sev guest info */ -static const TypeInfo sev_guest_info = { - .parent = TYPE_CONFIDENTIAL_GUEST_SUPPORT, - .name = TYPE_SEV_GUEST, - .instance_size = sizeof(SevGuestState), - .instance_finalize = sev_guest_finalize, - .class_init = sev_guest_class_init, - .instance_init = sev_guest_instance_init, - .interfaces = (InterfaceInfo[]) { - { TYPE_USER_CREATABLE }, - { } - } -}; - bool sev_enabled(void) { @@ -812,6 +769,7 @@ sev_launch_get_measure(Notifier *notifier, void *unused) if (ret) { exit(1); } + kvm_mark_guest_state_protected(); } /* query the measurement blob length */ @@ -906,20 +864,35 @@ sev_vm_state_change(void *opaque, bool running, RunState state) } } -int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) +static int sev_kvm_type(X86ConfidentialGuest *cg) { - SevGuestState *sev - = (SevGuestState *)object_dynamic_cast(OBJECT(cgs), TYPE_SEV_GUEST); + SevGuestState *sev = SEV_GUEST(cg); + int kvm_type; + + if (sev->kvm_type != -1) { + goto out; + } + + kvm_type = (sev->policy & SEV_POLICY_ES) ? KVM_X86_SEV_ES_VM : KVM_X86_SEV_VM; + if (kvm_is_vm_type_supported(kvm_type) && !sev->legacy_vm_type) { + sev->kvm_type = kvm_type; + } else { + sev->kvm_type = KVM_X86_DEFAULT_VM; + } + +out: + return sev->kvm_type; +} + +static int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) +{ + SevGuestState *sev = SEV_GUEST(cgs); char *devname; int ret, fw_error, cmd; uint32_t ebx; uint32_t host_cbitpos; struct sev_user_data_status status = {}; - if (!sev) { - return 0; - } - ret = ram_block_discard_disable(true); if (ret) { error_report("%s: cannot disable RAM discard", __func__); @@ -990,13 +963,19 @@ int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) __func__); goto err; } - cmd = KVM_SEV_ES_INIT; - } else { - cmd = KVM_SEV_INIT; } trace_kvm_sev_init(); - ret = sev_ioctl(sev->sev_fd, cmd, NULL, &fw_error); + if (sev_kvm_type(X86_CONFIDENTIAL_GUEST(sev)) == KVM_X86_DEFAULT_VM) { + cmd = sev_es_enabled() ? KVM_SEV_ES_INIT : KVM_SEV_INIT; + + ret = sev_ioctl(sev->sev_fd, cmd, NULL, &fw_error); + } else { + struct kvm_sev_init args = { 0 }; + + ret = sev_ioctl(sev->sev_fd, KVM_SEV_INIT2, &args, &fw_error); + } + if (ret) { error_setg(errp, "%s: failed to initialize ret=%d fw_error=%d '%s'", __func__, ret, fw_error, fw_error_to_str(fw_error)); @@ -1384,6 +1363,77 @@ bool sev_add_kernel_loader_hashes(SevKernelLoaderContext *ctx, Error **errp) return ret; } +static void +sev_guest_class_init(ObjectClass *oc, void *data) +{ + ConfidentialGuestSupportClass *klass = CONFIDENTIAL_GUEST_SUPPORT_CLASS(oc); + X86ConfidentialGuestClass *x86_klass = X86_CONFIDENTIAL_GUEST_CLASS(oc); + + klass->kvm_init = sev_kvm_init; + x86_klass->kvm_type = sev_kvm_type; + + object_class_property_add_str(oc, "sev-device", + sev_guest_get_sev_device, + sev_guest_set_sev_device); + object_class_property_set_description(oc, "sev-device", + "SEV device to use"); + object_class_property_add_str(oc, "dh-cert-file", + sev_guest_get_dh_cert_file, + sev_guest_set_dh_cert_file); + object_class_property_set_description(oc, "dh-cert-file", + "guest owners DH certificate (encoded with base64)"); + object_class_property_add_str(oc, "session-file", + sev_guest_get_session_file, + sev_guest_set_session_file); + object_class_property_set_description(oc, "session-file", + "guest owners session parameters (encoded with base64)"); + object_class_property_add_bool(oc, "kernel-hashes", + sev_guest_get_kernel_hashes, + sev_guest_set_kernel_hashes); + object_class_property_set_description(oc, "kernel-hashes", + "add kernel hashes to guest firmware for measured Linux boot"); + object_class_property_add_bool(oc, "legacy-vm-type", + sev_guest_get_legacy_vm_type, + sev_guest_set_legacy_vm_type); + object_class_property_set_description(oc, "legacy-vm-type", + "use legacy VM type to maintain measurement compatibility with older QEMU or kernel versions."); +} + +static void +sev_guest_instance_init(Object *obj) +{ + SevGuestState *sev = SEV_GUEST(obj); + + sev->kvm_type = -1; + + sev->sev_device = g_strdup(DEFAULT_SEV_DEVICE); + sev->policy = DEFAULT_GUEST_POLICY; + object_property_add_uint32_ptr(obj, "policy", &sev->policy, + OBJ_PROP_FLAG_READWRITE); + object_property_add_uint32_ptr(obj, "handle", &sev->handle, + OBJ_PROP_FLAG_READWRITE); + object_property_add_uint32_ptr(obj, "cbitpos", &sev->cbitpos, + OBJ_PROP_FLAG_READWRITE); + object_property_add_uint32_ptr(obj, "reduced-phys-bits", + &sev->reduced_phys_bits, + OBJ_PROP_FLAG_READWRITE); + object_apply_compat_props(obj); +} + +/* sev guest info */ +static const TypeInfo sev_guest_info = { + .parent = TYPE_X86_CONFIDENTIAL_GUEST, + .name = TYPE_SEV_GUEST, + .instance_size = sizeof(SevGuestState), + .instance_finalize = sev_guest_finalize, + .class_init = sev_guest_class_init, + .instance_init = sev_guest_instance_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + static void sev_register_types(void) { diff --git a/target/i386/sev.h b/target/i386/sev.h index e7499c95b1..9e10d09539 100644 --- a/target/i386/sev.h +++ b/target/i386/sev.h @@ -57,6 +57,4 @@ int sev_inject_launch_secret(const char *hdr, const char *secret, int sev_es_save_reset_vector(void *flash_ptr, uint64_t flash_size); void sev_es_set_reset_vector(CPUState *cpu); -int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp); - #endif diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index 76a42c679c..c05d9e5225 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -5846,9 +5846,10 @@ static bool disas_insn(DisasContext *s, CPUState *cpu) gen_op_st_v(s, MO_16, s->T0, s->A0); gen_add_A0_im(s, 2); tcg_gen_ld_tl(s->T0, tcg_env, offsetof(CPUX86State, gdt.base)); - if (dflag == MO_16) { - tcg_gen_andi_tl(s->T0, s->T0, 0xffffff); - } + /* + * NB: Despite a confusing description in Intel CPU documentation, + * all 32-bits are written regardless of operand size. + */ gen_op_st_v(s, CODE64(s) + MO_32, s->T0, s->A0); break; @@ -5901,9 +5902,10 @@ static bool disas_insn(DisasContext *s, CPUState *cpu) gen_op_st_v(s, MO_16, s->T0, s->A0); gen_add_A0_im(s, 2); tcg_gen_ld_tl(s->T0, tcg_env, offsetof(CPUX86State, idt.base)); - if (dflag == MO_16) { - tcg_gen_andi_tl(s->T0, s->T0, 0xffffff); - } + /* + * NB: Despite a confusing description in Intel CPU documentation, + * all 32-bits are written regardless of operand size. + */ gen_op_st_v(s, CODE64(s) + MO_32, s->T0, s->A0); break; diff --git a/target/loongarch/kvm/kvm.c b/target/loongarch/kvm/kvm.c index d630cc39cb..8224d94333 100644 --- a/target/loongarch/kvm/kvm.c +++ b/target/loongarch/kvm/kvm.c @@ -733,11 +733,6 @@ bool kvm_arch_stop_on_emulation_error(CPUState *cs) return true; } -bool kvm_arch_cpu_check_are_resettable(void) -{ - return true; -} - int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) { int ret = 0; diff --git a/target/mips/kvm.c b/target/mips/kvm.c index 6c52e59f55..a631ab544f 100644 --- a/target/mips/kvm.c +++ b/target/mips/kvm.c @@ -1273,11 +1273,6 @@ int kvm_arch_get_default_type(MachineState *machine) return -1; } -bool kvm_arch_cpu_check_are_resettable(void) -{ - return true; -} - void kvm_arch_accel_class_init(ObjectClass *oc) { } diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c index 8231feb2d4..63930d4a77 100644 --- a/target/ppc/kvm.c +++ b/target/ppc/kvm.c @@ -2956,11 +2956,6 @@ void kvmppc_set_reg_tb_offset(PowerPCCPU *cpu, int64_t tb_offset) } } -bool kvm_arch_cpu_check_are_resettable(void) -{ - return true; -} - void kvm_arch_accel_class_init(ObjectClass *oc) { } diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c index 6a6c6cae80..49d2f3ad58 100644 --- a/target/riscv/kvm/kvm-cpu.c +++ b/target/riscv/kvm/kvm-cpu.c @@ -1475,11 +1475,6 @@ void kvm_riscv_set_irq(RISCVCPU *cpu, int irq, int level) } } -bool kvm_arch_cpu_check_are_resettable(void) -{ - return true; -} - static int aia_mode; static const char *kvm_aia_mode_str(uint64_t mode) diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c index 4ce809c5d4..4dcd757cdc 100644 --- a/target/s390x/kvm/kvm.c +++ b/target/s390x/kvm/kvm.c @@ -2622,11 +2622,6 @@ void kvm_s390_stop_interrupt(S390CPU *cpu) kvm_s390_vcpu_interrupt(cpu, &irq); } -bool kvm_arch_cpu_check_are_resettable(void) -{ - return true; -} - int kvm_s390_get_zpci_op(void) { return cap_zpci_op; diff --git a/target/s390x/kvm/pv.c b/target/s390x/kvm/pv.c index 7ca7faec73..dde836d21a 100644 --- a/target/s390x/kvm/pv.c +++ b/target/s390x/kvm/pv.c @@ -334,12 +334,17 @@ static bool s390_pv_guest_check(ConfidentialGuestSupport *cgs, Error **errp) return s390_pv_check_cpus(errp); } -int s390_pv_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) +static int s390_pv_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) { if (!object_dynamic_cast(OBJECT(cgs), TYPE_S390_PV_GUEST)) { return 0; } + if (!kvm_enabled()) { + error_setg(errp, "Protected Virtualization requires KVM"); + return -1; + } + if (!s390_has_feat(S390_FEAT_UNPACK)) { error_setg(errp, "CPU model does not support Protected Virtualization"); @@ -364,6 +369,9 @@ OBJECT_DEFINE_TYPE_WITH_INTERFACES(S390PVGuest, static void s390_pv_guest_class_init(ObjectClass *oc, void *data) { + ConfidentialGuestSupportClass *klass = CONFIDENTIAL_GUEST_SUPPORT_CLASS(oc); + + klass->kvm_init = s390_pv_kvm_init; } static void s390_pv_guest_init(Object *obj) diff --git a/target/s390x/kvm/pv.h b/target/s390x/kvm/pv.h index 5877d28ff1..4b40817439 100644 --- a/target/s390x/kvm/pv.h +++ b/target/s390x/kvm/pv.h @@ -80,18 +80,4 @@ static inline int kvm_s390_dump_mem_state(uint64_t addr, size_t len, static inline int kvm_s390_dump_completion_data(void *buff) { return 0; } #endif /* CONFIG_KVM */ -int s390_pv_kvm_init(ConfidentialGuestSupport *cgs, Error **errp); -static inline int s390_pv_init(ConfidentialGuestSupport *cgs, Error **errp) -{ - if (!cgs) { - return 0; - } - if (kvm_enabled()) { - return s390_pv_kvm_init(cgs, errp); - } - - error_setg(errp, "Protected Virtualization requires KVM"); - return -1; -} - #endif /* HW_S390_PV_H */ diff --git a/tests/meson.build b/tests/meson.build index 0a6f96f8f8..acb6807094 100644 --- a/tests/meson.build +++ b/tests/meson.build @@ -78,9 +78,9 @@ subdir('decode') if 'CONFIG_TCG' in config_all_accel subdir('fp') + subdir('plugin') endif -subdir('plugin') subdir('unit') subdir('qapi-schema') subdir('qtest') diff --git a/tests/unit/meson.build b/tests/unit/meson.build index 228a21d03c..26c109c968 100644 --- a/tests/unit/meson.build +++ b/tests/unit/meson.build @@ -18,7 +18,6 @@ tests = { 'test-forward-visitor': [testqapi], 'test-string-input-visitor': [testqapi], 'test-string-output-visitor': [testqapi], - 'test-opts-visitor': [testqapi], 'test-visitor-serialization': [testqapi], 'test-bitmap': [], 'test-resv-mem': [], @@ -46,12 +45,8 @@ tests = { 'test-qemu-opts': [], 'test-keyval': [testqapi], 'test-logging': [], - 'test-uuid': [], - 'ptimer-test': ['ptimer-test-stubs.c', meson.project_source_root() / 'hw/core/ptimer.c'], 'test-qapi-util': [], 'test-interval-tree': [], - 'test-xs-node': [qom], - 'test-virtio-dmabuf': [meson.project_source_root() / 'hw/display/virtio-dmabuf.c'], } if have_system or have_tools @@ -97,6 +92,8 @@ if have_block 'test-crypto-ivgen': [io], 'test-crypto-afsplit': [io], 'test-crypto-block': [io], + 'test-timed-average': [], + 'test-uuid': [], } if gnutls.found() and \ tasn1.found() and \ @@ -131,10 +128,13 @@ endif if have_system tests += { + 'ptimer-test': ['ptimer-test-stubs.c', meson.project_source_root() / 'hw/core/ptimer.c'], 'test-iov': [], + 'test-opts-visitor': [testqapi], + 'test-xs-node': [qom], + 'test-virtio-dmabuf': [meson.project_source_root() / 'hw/display/virtio-dmabuf.c'], 'test-qmp-cmds': [testqapi], 'test-xbzrle': [migration], - 'test-timed-average': [], 'test-util-sockets': ['socket-helpers.c'], 'test-base64': [], 'test-bufferiszero': [], diff --git a/util/meson.build b/util/meson.build index 0ef9886be0..2ad57b10ba 100644 --- a/util/meson.build +++ b/util/meson.build @@ -60,7 +60,6 @@ util_ss.add(files('stats64.c')) util_ss.add(files('systemd.c')) util_ss.add(files('transactions.c')) util_ss.add(files('guest-random.c')) -util_ss.add(files('yank.c')) util_ss.add(files('int128.c')) util_ss.add(files('memalign.c')) util_ss.add(files('interval-tree.c')) @@ -117,6 +116,7 @@ if have_block util_ss.add(files('vfio-helpers.c')) util_ss.add(files('chardev_open.c')) endif + util_ss.add(files('yank.c')) endif if cpu == 'aarch64' diff --git a/util/qemu-config.c b/util/qemu-config.c index 42076efe1e..a90c18dad2 100644 --- a/util/qemu-config.c +++ b/util/qemu-config.c @@ -1,16 +1,14 @@ #include "qemu/osdep.h" #include "block/qdict.h" /* for qdict_extract_subqdict() */ #include "qapi/error.h" -#include "qapi/qapi-commands-misc.h" #include "qapi/qmp/qdict.h" #include "qapi/qmp/qlist.h" #include "qemu/error-report.h" #include "qemu/option.h" #include "qemu/config-file.h" -#include "hw/boards.h" -static QemuOptsList *vm_config_groups[48]; -static QemuOptsList *drive_config_groups[5]; +QemuOptsList *vm_config_groups[48]; +QemuOptsList *drive_config_groups[5]; static QemuOptsList *find_list(QemuOptsList **lists, const char *group, Error **errp) @@ -55,204 +53,6 @@ QemuOpts *qemu_find_opts_singleton(const char *group) return opts; } -static CommandLineParameterInfoList *query_option_descs(const QemuOptDesc *desc) -{ - CommandLineParameterInfoList *param_list = NULL; - CommandLineParameterInfo *info; - int i; - - for (i = 0; desc[i].name != NULL; i++) { - info = g_malloc0(sizeof(*info)); - info->name = g_strdup(desc[i].name); - - switch (desc[i].type) { - case QEMU_OPT_STRING: - info->type = COMMAND_LINE_PARAMETER_TYPE_STRING; - break; - case QEMU_OPT_BOOL: - info->type = COMMAND_LINE_PARAMETER_TYPE_BOOLEAN; - break; - case QEMU_OPT_NUMBER: - info->type = COMMAND_LINE_PARAMETER_TYPE_NUMBER; - break; - case QEMU_OPT_SIZE: - info->type = COMMAND_LINE_PARAMETER_TYPE_SIZE; - break; - } - - info->help = g_strdup(desc[i].help); - info->q_default = g_strdup(desc[i].def_value_str); - - QAPI_LIST_PREPEND(param_list, info); - } - - return param_list; -} - -/* remove repeated entry from the info list */ -static void cleanup_infolist(CommandLineParameterInfoList *head) -{ - CommandLineParameterInfoList *pre_entry, *cur, *del_entry; - - cur = head; - while (cur->next) { - pre_entry = head; - while (pre_entry != cur->next) { - if (!strcmp(pre_entry->value->name, cur->next->value->name)) { - del_entry = cur->next; - cur->next = cur->next->next; - del_entry->next = NULL; - qapi_free_CommandLineParameterInfoList(del_entry); - break; - } - pre_entry = pre_entry->next; - } - cur = cur->next; - } -} - -/* merge the description items of two parameter infolists */ -static void connect_infolist(CommandLineParameterInfoList *head, - CommandLineParameterInfoList *new) -{ - CommandLineParameterInfoList *cur; - - cur = head; - while (cur->next) { - cur = cur->next; - } - cur->next = new; -} - -/* access all the local QemuOptsLists for drive option */ -static CommandLineParameterInfoList *get_drive_infolist(void) -{ - CommandLineParameterInfoList *head = NULL, *cur; - int i; - - for (i = 0; drive_config_groups[i] != NULL; i++) { - if (!head) { - head = query_option_descs(drive_config_groups[i]->desc); - } else { - cur = query_option_descs(drive_config_groups[i]->desc); - connect_infolist(head, cur); - } - } - cleanup_infolist(head); - - return head; -} - -static CommandLineParameterInfo *objprop_to_cmdline_prop(ObjectProperty *prop) -{ - CommandLineParameterInfo *info; - - info = g_malloc0(sizeof(*info)); - info->name = g_strdup(prop->name); - - if (g_str_equal(prop->type, "bool") || g_str_equal(prop->type, "OnOffAuto")) { - info->type = COMMAND_LINE_PARAMETER_TYPE_BOOLEAN; - } else if (g_str_equal(prop->type, "int")) { - info->type = COMMAND_LINE_PARAMETER_TYPE_NUMBER; - } else if (g_str_equal(prop->type, "size")) { - info->type = COMMAND_LINE_PARAMETER_TYPE_SIZE; - } else { - info->type = COMMAND_LINE_PARAMETER_TYPE_STRING; - } - - if (prop->description) { - info->help = g_strdup(prop->description); - } - - return info; -} - -static CommandLineParameterInfoList *query_all_machine_properties(void) -{ - CommandLineParameterInfoList *params = NULL, *clpiter; - CommandLineParameterInfo *info; - GSList *machines, *curr_mach; - ObjectPropertyIterator op_iter; - ObjectProperty *prop; - bool is_new; - - machines = object_class_get_list(TYPE_MACHINE, false); - assert(machines); - - /* Loop over all machine classes */ - for (curr_mach = machines; curr_mach; curr_mach = curr_mach->next) { - object_class_property_iter_init(&op_iter, curr_mach->data); - /* ... and over the properties of each machine: */ - while ((prop = object_property_iter_next(&op_iter))) { - if (!prop->set) { - continue; - } - /* - * Check whether the property has already been put into the list - * (via another machine class) - */ - is_new = true; - for (clpiter = params; clpiter != NULL; clpiter = clpiter->next) { - if (g_str_equal(clpiter->value->name, prop->name)) { - is_new = false; - break; - } - } - /* If it hasn't been added before, add it now to the list */ - if (is_new) { - info = objprop_to_cmdline_prop(prop); - QAPI_LIST_PREPEND(params, info); - } - } - } - - g_slist_free(machines); - - /* Add entry for the "type" parameter */ - info = g_malloc0(sizeof(*info)); - info->name = g_strdup("type"); - info->type = COMMAND_LINE_PARAMETER_TYPE_STRING; - info->help = g_strdup("machine type"); - QAPI_LIST_PREPEND(params, info); - - return params; -} - -CommandLineOptionInfoList *qmp_query_command_line_options(const char *option, - Error **errp) -{ - CommandLineOptionInfoList *conf_list = NULL; - CommandLineOptionInfo *info; - int i; - - for (i = 0; vm_config_groups[i] != NULL; i++) { - if (!option || !strcmp(option, vm_config_groups[i]->name)) { - info = g_malloc0(sizeof(*info)); - info->option = g_strdup(vm_config_groups[i]->name); - if (!strcmp("drive", vm_config_groups[i]->name)) { - info->parameters = get_drive_infolist(); - } else { - info->parameters = - query_option_descs(vm_config_groups[i]->desc); - } - QAPI_LIST_PREPEND(conf_list, info); - } - } - - if (!option || !strcmp(option, "machine")) { - info = g_malloc0(sizeof(*info)); - info->option = g_strdup("machine"); - info->parameters = query_all_machine_properties(); - QAPI_LIST_PREPEND(conf_list, info); - } - - if (conf_list == NULL) { - error_setg(errp, "invalid option name: %s", option); - } - - return conf_list; -} - QemuOptsList *qemu_find_opts_err(const char *group, Error **errp) { return find_list(vm_config_groups, group, errp);