diff options
64 files changed, 1397 insertions, 38 deletions
diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c index 93976f4ece..6cbd2c3f97 100644 --- a/accel/hvf/hvf-accel-ops.c +++ b/accel/hvf/hvf-accel-ops.c @@ -295,6 +295,7 @@ static void hvf_region_del(MemoryListener *listener, } static MemoryListener hvf_memory_listener = { + .name = "hvf", .priority = 10, .region_add = hvf_region_add, .region_del = hvf_region_del, diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index cace5ffe64..db8d83b137 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -1129,6 +1129,7 @@ static void kvm_coalesce_pio_del(MemoryListener *listener, } static MemoryListener kvm_coalesced_pio_listener = { + .name = "kvm-coalesced-pio", .coalesced_io_add = kvm_coalesce_pio_add, .coalesced_io_del = kvm_coalesce_pio_del, }; @@ -1633,7 +1634,7 @@ static void kvm_io_ioeventfd_del(MemoryListener *listener, } void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, - AddressSpace *as, int as_id) + AddressSpace *as, int as_id, const char *name) { int i; @@ -1649,6 +1650,7 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, kml->listener.log_start = kvm_log_start; kml->listener.log_stop = kvm_log_stop; kml->listener.priority = 10; + kml->listener.name = name; if (s->kvm_dirty_ring_size) { kml->listener.log_sync_global = kvm_log_sync_global; @@ -1669,6 +1671,7 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, } static MemoryListener kvm_io_listener = { + .name = "kvm-io", .eventfd_add = kvm_io_ioeventfd_add, .eventfd_del = kvm_io_ioeventfd_del, .priority = 10, @@ -2579,7 +2582,7 @@ static int kvm_init(MachineState *ms) s->memory_listener.listener.coalesced_io_del = kvm_uncoalesce_mmio_region; kvm_memory_listener_register(s, &s->memory_listener, - &address_space_memory, 0); + &address_space_memory, 0, "kvm-memory"); if (kvm_eventfds_allowed) { memory_listener_register(&kvm_io_listener, &address_space_io); diff --git a/backends/hostmem-epc.c b/backends/hostmem-epc.c new file mode 100644 index 0000000000..b47f98b6a3 --- /dev/null +++ b/backends/hostmem-epc.c @@ -0,0 +1,82 @@ +/* + * QEMU host SGX EPC memory backend + * + * Copyright (C) 2019 Intel Corporation + * + * Authors: + * Sean Christopherson <sean.j.christopherson@intel.com> + * + * 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 <sys/ioctl.h> + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qom/object_interfaces.h" +#include "qapi/error.h" +#include "sysemu/hostmem.h" +#include "hw/i386/hostmem-epc.h" + +static void +sgx_epc_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) +{ + uint32_t ram_flags; + char *name; + int fd; + + if (!backend->size) { + error_setg(errp, "can't create backend with size 0"); + return; + } + + fd = qemu_open_old("/dev/sgx_vepc", O_RDWR); + if (fd < 0) { + error_setg_errno(errp, errno, + "failed to open /dev/sgx_vepc to alloc SGX EPC"); + return; + } + + name = object_get_canonical_path(OBJECT(backend)); + ram_flags = (backend->share ? RAM_SHARED : 0) | RAM_PROTECTED; + memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), + name, backend->size, ram_flags, + fd, 0, errp); + g_free(name); +} + +static void sgx_epc_backend_instance_init(Object *obj) +{ + HostMemoryBackend *m = MEMORY_BACKEND(obj); + + m->share = true; + m->merge = false; + m->dump = false; +} + +static void sgx_epc_backend_class_init(ObjectClass *oc, void *data) +{ + HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc); + + bc->alloc = sgx_epc_backend_memory_alloc; +} + +static const TypeInfo sgx_epc_backed_info = { + .name = TYPE_MEMORY_BACKEND_EPC, + .parent = TYPE_MEMORY_BACKEND, + .instance_init = sgx_epc_backend_instance_init, + .class_init = sgx_epc_backend_class_init, + .instance_size = sizeof(HostMemoryBackendEpc), +}; + +static void register_types(void) +{ + int fd = qemu_open_old("/dev/sgx_vepc", O_RDWR); + if (fd >= 0) { + close(fd); + + type_register_static(&sgx_epc_backed_info); + } +} + +type_init(register_types); diff --git a/backends/meson.build b/backends/meson.build index d4221831fc..6e68945528 100644 --- a/backends/meson.build +++ b/backends/meson.build @@ -16,5 +16,6 @@ softmmu_ss.add(when: ['CONFIG_VHOST_USER', 'CONFIG_VIRTIO'], if_true: files('vho softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost.c')) softmmu_ss.add(when: ['CONFIG_VIRTIO_CRYPTO', 'CONFIG_VHOST_CRYPTO'], if_true: files('cryptodev-vhost-user.c')) softmmu_ss.add(when: 'CONFIG_GIO', if_true: [files('dbus-vmstate.c'), gio]) +softmmu_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c')) subdir('tpm') diff --git a/configs/devices/i386-softmmu/default.mak b/configs/devices/i386-softmmu/default.mak index 84d1a2487c..598c6646df 100644 --- a/configs/devices/i386-softmmu/default.mak +++ b/configs/devices/i386-softmmu/default.mak @@ -22,6 +22,7 @@ #CONFIG_TPM_CRB=n #CONFIG_TPM_TIS_ISA=n #CONFIG_VTD=n +#CONFIG_SGX=n # Boards: # diff --git a/docs/system/i386/sgx.rst b/docs/system/i386/sgx.rst new file mode 100644 index 0000000000..f103ae2a2f --- /dev/null +++ b/docs/system/i386/sgx.rst @@ -0,0 +1,165 @@ +Software Guard eXtensions (SGX) +=============================== + +Overview +-------- + +Intel Software Guard eXtensions (SGX) is a set of instructions and mechanisms +for memory accesses in order to provide security accesses for sensitive +applications and data. SGX allows an application to use it's pariticular +address space as an *enclave*, which is a protected area provides confidentiality +and integrity even in the presence of privileged malware. Accesses to the +enclave memory area from any software not resident in the enclave are prevented, +including those from privileged software. + +Virtual SGX +----------- + +SGX feature is exposed to guest via SGX CPUID. Looking at SGX CPUID, we can +report the same CPUID info to guest as on host for most of SGX CPUID. With +reporting the same CPUID guest is able to use full capacity of SGX, and KVM +doesn't need to emulate those info. + +The guest's EPC base and size are determined by Qemu, and KVM needs Qemu to +notify such info to it before it can initialize SGX for guest. + +Virtual EPC +~~~~~~~~~~~ + +By default, Qemu does not assign EPC to a VM, i.e. fully enabling SGX in a VM +requires explicit allocation of EPC to the VM. Similar to other specialized +memory types, e.g. hugetlbfs, EPC is exposed as a memory backend. + +SGX EPC is enumerated through CPUID, i.e. EPC "devices" need to be realized +prior to realizing the vCPUs themselves, which occurs long before generic +devices are parsed and realized. This limitation means that EPC does not +require -maxmem as EPC is not treated as {cold,hot}plugged memory. + +Qemu does not artificially restrict the number of EPC sections exposed to a +guest, e.g. Qemu will happily allow you to create 64 1M EPC sections. Be aware +that some kernels may not recognize all EPC sections, e.g. the Linux SGX driver +is hardwired to support only 8 EPC sections. + +The following Qemu snippet creates two EPC sections, with 64M pre-allocated +to the VM and an additional 28M mapped but not allocated:: + + -object memory-backend-epc,id=mem1,size=64M,prealloc=on \ + -object memory-backend-epc,id=mem2,size=28M \ + -M sgx-epc.0.memdev=mem1,sgx-epc.1.memdev=mem2 + +Note: + +The size and location of the virtual EPC are far less restricted compared +to physical EPC. Because physical EPC is protected via range registers, +the size of the physical EPC must be a power of two (though software sees +a subset of the full EPC, e.g. 92M or 128M) and the EPC must be naturally +aligned. KVM SGX's virtual EPC is purely a software construct and only +requires the size and location to be page aligned. Qemu enforces the EPC +size is a multiple of 4k and will ensure the base of the EPC is 4k aligned. +To simplify the implementation, EPC is always located above 4g in the guest +physical address space. + +Migration +~~~~~~~~~ + +Qemu/KVM doesn't prevent live migrating SGX VMs, although from hardware's +perspective, SGX doesn't support live migration, since both EPC and the SGX +key hierarchy are bound to the physical platform. However live migration +can be supported in the sense if guest software stack can support recreating +enclaves when it suffers sudden lose of EPC; and if guest enclaves can detect +SGX keys being changed, and handle gracefully. For instance, when ERESUME fails +with #PF.SGX, guest software can gracefully detect it and recreate enclaves; +and when enclave fails to unseal sensitive information from outside, it can +detect such error and sensitive information can be provisioned to it again. + +CPUID +~~~~~ + +Due to its myriad dependencies, SGX is currently not listed as supported +in any of Qemu's built-in CPU configuration. To expose SGX (and SGX Launch +Control) to a guest, you must either use `-cpu host` to pass-through the +host CPU model, or explicitly enable SGX when using a built-in CPU model, +e.g. via `-cpu <model>,+sgx` or `-cpu <model>,+sgx,+sgxlc`. + +All SGX sub-features enumerated through CPUID, e.g. SGX2, MISCSELECT, +ATTRIBUTES, etc... can be restricted via CPUID flags. Be aware that enforcing +restriction of MISCSELECT, ATTRIBUTES and XFRM requires intercepting ECREATE, +i.e. may marginally reduce SGX performance in the guest. All SGX sub-features +controlled via -cpu are prefixed with "sgx", e.g.:: + + $ qemu-system-x86_64 -cpu help | xargs printf "%s\n" | grep sgx + sgx + sgx-debug + sgx-encls-c + sgx-enclv + sgx-exinfo + sgx-kss + sgx-mode64 + sgx-provisionkey + sgx-tokenkey + sgx1 + sgx2 + sgxlc + +The following Qemu snippet passes through the host CPU but restricts access to +the provision and EINIT token keys:: + + -cpu host,-sgx-provisionkey,-sgx-tokenkey + +SGX sub-features cannot be emulated, i.e. sub-features that are not present +in hardware cannot be forced on via '-cpu'. + +Virtualize SGX Launch Control +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Qemu SGX support for Launch Control (LC) is passive, in the sense that it +does not actively change the LC configuration. Qemu SGX provides the user +the ability to set/clear the CPUID flag (and by extension the associated +IA32_FEATURE_CONTROL MSR bit in fw_cfg) and saves/restores the LE Hash MSRs +when getting/putting guest state, but Qemu does not add new controls to +directly modify the LC configuration. Similar to hardware behavior, locking +the LC configuration to a non-Intel value is left to guest firmware. Unlike +host bios setting for SGX launch control(LC), there is no special bios setting +for SGX guest by our design. If host is in locked mode, we can still allow +creating VM with SGX. + +Feature Control +~~~~~~~~~~~~~~~ + +Qemu SGX updates the `etc/msr_feature_control` fw_cfg entry to set the SGX +(bit 18) and SGX LC (bit 17) flags based on their respective CPUID support, +i.e. existing guest firmware will automatically set SGX and SGX LC accordingly, +assuming said firmware supports fw_cfg.msr_feature_control. + +Launching a guest +----------------- + +To launch a SGX guest: + +.. parsed-literal:: + + |qemu_system_x86| \\ + -cpu host,+sgx-provisionkey \\ + -object memory-backend-epc,id=mem1,size=64M,prealloc=on \\ + -object memory-backend-epc,id=mem2,size=28M \\ + -M sgx-epc.0.memdev=mem1,sgx-epc.1.memdev=mem2 + +Utilizing SGX in the guest requires a kernel/OS with SGX support. +The support can be determined in guest by:: + + $ grep sgx /proc/cpuinfo + +and SGX epc info by:: + + $ dmesg | grep sgx + [ 1.242142] sgx: EPC section 0x180000000-0x181bfffff + [ 1.242319] sgx: EPC section 0x181c00000-0x1837fffff + +References +---------- + +- `SGX Homepage <https://software.intel.com/sgx>`__ + +- `SGX SDK <https://github.com/intel/linux-sgx.git>`__ + +- SGX specification: Intel SDM Volume 3 diff --git a/docs/system/target-i386.rst b/docs/system/target-i386.rst index c9720a8cd1..6a86d63863 100644 --- a/docs/system/target-i386.rst +++ b/docs/system/target-i386.rst @@ -26,6 +26,7 @@ Architectural features :maxdepth: 1 i386/cpu + i386/sgx .. _pcsys_005freq: diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx index 27206ac049..4c966e8a6b 100644 --- a/hmp-commands-info.hx +++ b/hmp-commands-info.hx @@ -877,3 +877,18 @@ SRST ``info dirty_rate`` Display the vcpu dirty rate information. ERST + +#if defined(TARGET_I386) + { + .name = "sgx", + .args_type = "", + .params = "", + .help = "show intel SGX information", + .cmd = hmp_info_sgx, + }, +#endif + +SRST + ``info sgx`` + Show intel SGX information. +ERST diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index ddedcef0b2..962d2c981b 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -6,6 +6,10 @@ config SEV select X86_FW_OVMF depends on KVM +config SGX + bool + depends on KVM + config PC bool imply APPLESMC @@ -21,6 +25,7 @@ config PC imply PVPANIC_ISA imply QXL imply SEV + imply SGX imply SGA imply TEST_DEVICES imply TPM_CRB diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index dfaa47cdc2..f4d6ae3d02 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -1841,6 +1841,28 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } #endif + if (pcms->sgx_epc.size != 0) { + uint64_t epc_base = pcms->sgx_epc.base; + uint64_t epc_size = pcms->sgx_epc.size; + + dev = aml_device("EPC"); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("INT0E0C"))); + aml_append(dev, aml_name_decl("_STR", + aml_unicode("Enclave Page Cache 1.0"))); + crs = aml_resource_template(); + aml_append(crs, + aml_qword_memory(AML_POS_DECODE, AML_MIN_FIXED, + AML_MAX_FIXED, AML_NON_CACHEABLE, + AML_READ_WRITE, 0, epc_base, + epc_base + epc_size - 1, 0, epc_size)); + aml_append(dev, aml_name_decl("_CRS", crs)); + + method = aml_method("_STA", 0, AML_NOTSERIALIZED); + aml_append(method, aml_return(aml_int(0x0f))); + aml_append(dev, method); + + aml_append(sb_scope, dev); + } aml_append(dsdt, sb_scope); /* copy AML table into ACPI tables blob and patch header there */ diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c index 4e68d5dea4..a283785a8d 100644 --- a/hw/i386/fw_cfg.c +++ b/hw/i386/fw_cfg.c @@ -159,7 +159,7 @@ void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg) { X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu); CPUX86State *env = &cpu->env; - uint32_t unused, ecx, edx; + uint32_t unused, ebx, ecx, edx; uint64_t feature_control_bits = 0; uint64_t *val; @@ -174,6 +174,16 @@ void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg) feature_control_bits |= FEATURE_CONTROL_LMCE; } + if (env->cpuid_level >= 7) { + cpu_x86_cpuid(env, 0x7, 0, &unused, &ebx, &ecx, &unused); + if (ebx & CPUID_7_0_EBX_SGX) { + feature_control_bits |= FEATURE_CONTROL_SGX; + } + if (ecx & CPUID_7_0_ECX_SGX_LC) { + feature_control_bits |= FEATURE_CONTROL_SGX_LC; + } + } + if (!feature_control_bits) { return; } diff --git a/hw/i386/meson.build b/hw/i386/meson.build index 80dad29f2b..c502965219 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -16,6 +16,8 @@ i386_ss.add(when: 'CONFIG_Q35', if_true: files('pc_q35.c')) i386_ss.add(when: 'CONFIG_VMMOUSE', if_true: files('vmmouse.c')) i386_ss.add(when: 'CONFIG_VMPORT', if_true: files('vmport.c')) i386_ss.add(when: 'CONFIG_VTD', if_true: files('intel_iommu.c')) +i386_ss.add(when: 'CONFIG_SGX', if_true: files('sgx-epc.c','sgx.c'), + if_false: files('sgx-stub.c')) i386_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-common.c')) i386_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device_x86.c')) diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 557d49c9f8..df457eceba 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -889,6 +889,10 @@ void pc_memory_init(PCMachineState *pcms, e820_add_entry(0x100000000ULL, x86ms->above_4g_mem_size, E820_RAM); } + if (pcms->sgx_epc.size != 0) { + e820_add_entry(pcms->sgx_epc.base, pcms->sgx_epc.size, E820_RESERVED); + } + if (!pcmc->has_reserved_memory && (machine->ram_slots || (machine->maxram_size > machine->ram_size))) { @@ -919,8 +923,15 @@ void pc_memory_init(PCMachineState *pcms, exit(EXIT_FAILURE); } + if (pcms->sgx_epc.size != 0) { + machine->device_memory->base = sgx_epc_above_4g_end(&pcms->sgx_epc); + } else { + machine->device_memory->base = + 0x100000000ULL + x86ms->above_4g_mem_size; + } + machine->device_memory->base = - ROUND_UP(0x100000000ULL + x86ms->above_4g_mem_size, 1 * GiB); + ROUND_UP(machine->device_memory->base, 1 * GiB); if (pcmc->enforce_aligned_dimm) { /* size device region assuming 1G page max alignment per slot */ @@ -1005,6 +1016,8 @@ uint64_t pc_pci_hole64_start(void) if (!pcmc->broken_reserved_end) { hole64_start += memory_region_size(&ms->device_memory->mr); } + } else if (pcms->sgx_epc.size != 0) { + hole64_start = sgx_epc_above_4g_end(&pcms->sgx_epc); } else { hole64_start = 0x100000000ULL + x86ms->above_4g_mem_size; } diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index c5da7739ce..6cc834aff6 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -153,6 +153,7 @@ static void pc_init1(MachineState *machine, } } + pc_machine_init_sgx_epc(pcms); x86_cpus_init(x86ms, pcmc->default_cpu_version); if (pcmc->kvmclock_enabled) { diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 46cd542d17..5481d5c965 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -177,6 +177,7 @@ static void pc_q35_init(MachineState *machine) x86ms->below_4g_mem_size = machine->ram_size; } + pc_machine_init_sgx_epc(pcms); x86_cpus_init(x86ms, pcmc->default_cpu_version); kvmclock_create(pcmc->kvmclock_create_always); diff --git a/hw/i386/sgx-epc.c b/hw/i386/sgx-epc.c new file mode 100644 index 0000000000..55e2217eae --- /dev/null +++ b/hw/i386/sgx-epc.c @@ -0,0 +1,184 @@ +/* + * SGX EPC device + * + * Copyright (C) 2019 Intel Corporation + * + * Authors: + * Sean Christopherson <sean.j.christopherson@intel.com> + * + * 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 "hw/i386/pc.h" +#include "hw/i386/sgx-epc.h" +#include "hw/mem/memory-device.h" +#include "hw/qdev-properties.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "target/i386/cpu.h" +#include "exec/address-spaces.h" + +static Property sgx_epc_properties[] = { + DEFINE_PROP_UINT64(SGX_EPC_ADDR_PROP, SGXEPCDevice, addr, 0), + DEFINE_PROP_LINK(SGX_EPC_MEMDEV_PROP, SGXEPCDevice, hostmem, + TYPE_MEMORY_BACKEND_EPC, HostMemoryBackendEpc *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void sgx_epc_get_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + Error *local_err = NULL; + uint64_t value; + + value = memory_device_get_region_size(MEMORY_DEVICE(obj), &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + visit_type_uint64(v, name, &value, errp); +} + +static void sgx_epc_init(Object *obj) +{ + object_property_add(obj, SGX_EPC_SIZE_PROP, "uint64", sgx_epc_get_size, + NULL, NULL, NULL); +} + +static void sgx_epc_realize(DeviceState *dev, Error **errp) +{ + PCMachineState *pcms = PC_MACHINE(qdev_get_machine()); + X86MachineState *x86ms = X86_MACHINE(pcms); + MemoryDeviceState *md = MEMORY_DEVICE(dev); + SGXEPCState *sgx_epc = &pcms->sgx_epc; + SGXEPCDevice *epc = SGX_EPC(dev); + HostMemoryBackend *hostmem; + const char *path; + + if (x86ms->boot_cpus != 0) { + error_setg(errp, "'" TYPE_SGX_EPC "' can't be created after vCPUs," + "e.g. via -device"); + return; + } + + if (!epc->hostmem) { + error_setg(errp, "'" SGX_EPC_MEMDEV_PROP "' property is not set"); + return; + } + hostmem = MEMORY_BACKEND(epc->hostmem); + if (host_memory_backend_is_mapped(hostmem)) { + path = object_get_canonical_path_component(OBJECT(hostmem)); + error_setg(errp, "can't use already busy memdev: %s", path); + return; + } + + epc->addr = sgx_epc->base + sgx_epc->size; + + memory_region_add_subregion(&sgx_epc->mr, epc->addr - sgx_epc->base, + host_memory_backend_get_memory(hostmem)); + + host_memory_backend_set_mapped(hostmem, true); + + sgx_epc->sections = g_renew(SGXEPCDevice *, sgx_epc->sections, + sgx_epc->nr_sections + 1); + sgx_epc->sections[sgx_epc->nr_sections++] = epc; + + sgx_epc->size += memory_device_get_region_size(md, errp); +} + +static void sgx_epc_unrealize(DeviceState *dev) +{ + SGXEPCDevice *epc = SGX_EPC(dev); + HostMemoryBackend *hostmem = MEMORY_BACKEND(epc->hostmem); + + host_memory_backend_set_mapped(hostmem, false); +} + +static uint64_t sgx_epc_md_get_addr(const MemoryDeviceState *md) +{ + const SGXEPCDevice *epc = SGX_EPC(md); + + return epc->addr; +} + +static void sgx_epc_md_set_addr(MemoryDeviceState *md, uint64_t addr, + Error **errp) +{ + object_property_set_uint(OBJECT(md), SGX_EPC_ADDR_PROP, addr, errp); +} + +static uint64_t sgx_epc_md_get_plugged_size(const MemoryDeviceState *md, + Error **errp) +{ + return 0; +} + +static MemoryRegion *sgx_epc_md_get_memory_region(MemoryDeviceState *md, + Error **errp) +{ + SGXEPCDevice *epc = SGX_EPC(md); + HostMemoryBackend *hostmem; + + if (!epc->hostmem) { + error_setg(errp, "'" SGX_EPC_MEMDEV_PROP "' property must be set"); + return NULL; + } + + hostmem = MEMORY_BACKEND(epc->hostmem); + return host_memory_backend_get_memory(hostmem); +} + +static void sgx_epc_md_fill_device_info(const MemoryDeviceState *md, + MemoryDeviceInfo *info) +{ + SgxEPCDeviceInfo *se = g_new0(SgxEPCDeviceInfo, 1); + SGXEPCDevice *epc = SGX_EPC(md); + + se->memaddr = epc->addr; + se->size = object_property_get_uint(OBJECT(epc), SGX_EPC_SIZE_PROP, + NULL); + se->memdev = object_get_canonical_path(OBJECT(epc->hostmem)); + + info->u.sgx_epc.data = se; + info->type = MEMORY_DEVICE_INFO_KIND_SGX_EPC; +} + +static void sgx_epc_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(oc); + + dc->hotpluggable = false; + dc->realize = sgx_epc_realize; + dc->unrealize = sgx_epc_unrealize; + dc->desc = "SGX EPC section"; + device_class_set_props(dc, sgx_epc_properties); + + mdc->get_addr = sgx_epc_md_get_addr; + mdc->set_addr = sgx_epc_md_set_addr; + mdc->get_plugged_size = sgx_epc_md_get_plugged_size; + mdc->get_memory_region = sgx_epc_md_get_memory_region; + mdc->fill_device_info = sgx_epc_md_fill_device_info; +} + +static TypeInfo sgx_epc_info = { + .name = TYPE_SGX_EPC, + .parent = TYPE_DEVICE, + .instance_size = sizeof(SGXEPCDevice), + .instance_init = sgx_epc_init, + .class_init = sgx_epc_class_init, + .class_size = sizeof(DeviceClass), + .interfaces = (InterfaceInfo[]) { + { TYPE_MEMORY_DEVICE }, + { } + }, +}; + +static void sgx_epc_register_types(void) +{ + type_register_static(&sgx_epc_info); +} + +type_init(sgx_epc_register_types) diff --git a/hw/i386/sgx-stub.c b/hw/i386/sgx-stub.c new file mode 100644 index 0000000000..3be9f5ca32 --- /dev/null +++ b/hw/i386/sgx-stub.c @@ -0,0 +1,26 @@ +#include "qemu/osdep.h" +#include "hw/i386/pc.h" +#include "hw/i386/sgx-epc.h" +#include "hw/i386/sgx.h" + +SGXInfo *sgx_get_info(Error **errp) +{ + error_setg(errp, "SGX support is not compiled in"); + return NULL; +} + +SGXInfo *sgx_get_capabilities(Error **errp) +{ + error_setg(errp, "SGX support is not compiled in"); + return NULL; +} + +void pc_machine_init_sgx_epc(PCMachineState *pcms) +{ + memset(&pcms->sgx_epc, 0, sizeof(SGXEPCState)); +} + +int sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size) +{ + g_assert_not_reached(); +} diff --git a/hw/i386/sgx.c b/hw/i386/sgx.c new file mode 100644 index 0000000000..e481e9358f --- /dev/null +++ b/hw/i386/sgx.c @@ -0,0 +1,170 @@ +/* + * SGX common code + * + * Copyright (C) 2021 Intel Corporation + * + * Authors: + * Yang Zhong<yang.zhong@intel.com> + * Sean Christopherson <sean.j.christopherson@intel.com> + * + * 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 "hw/i386/pc.h" +#include "hw/i386/sgx-epc.h" +#include "hw/mem/memory-device.h" +#include "monitor/qdev.h" +#include "qapi/error.h" +#include "exec/address-spaces.h" +#include "hw/i386/sgx.h" +#include "sysemu/hw_accel.h" + +#define SGX_MAX_EPC_SECTIONS 8 +#define SGX_CPUID_EPC_INVALID 0x0 + +/* A valid EPC section. */ +#define SGX_CPUID_EPC_SECTION 0x1 +#define SGX_CPUID_EPC_MASK 0xF + +static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high) +{ + return (low & MAKE_64BIT_MASK(12, 20)) + + ((high & MAKE_64BIT_MASK(0, 20)) << 32); +} + +static uint64_t sgx_calc_host_epc_section_size(void) +{ + uint32_t i, type; + uint32_t eax, ebx, ecx, edx; + uint64_t size = 0; + + for (i = 0; i < SGX_MAX_EPC_SECTIONS; i++) { + host_cpuid(0x12, i + 2, &eax, &ebx, &ecx, &edx); + + type = eax & SGX_CPUID_EPC_MASK; + if (type == SGX_CPUID_EPC_INVALID) { + break; + } + + if (type != SGX_CPUID_EPC_SECTION) { + break; + } + + size += sgx_calc_section_metric(ecx, edx); + } + + return size; +} + +SGXInfo *sgx_get_capabilities(Error **errp) +{ + SGXInfo *info = NULL; + uint32_t eax, ebx, ecx, edx; + + int fd = qemu_open_old("/dev/sgx_vepc", O_RDWR); + if (fd < 0) { + error_setg(errp, "SGX is not enabled in KVM"); + return NULL; + } + + info = g_new0(SGXInfo, 1); + host_cpuid(0x7, 0, &eax, &ebx, &ecx, &edx); + + info->sgx = ebx & (1U << 2) ? true : false; + info->flc = ecx & (1U << 30) ? true : false; + + host_cpuid(0x12, 0, &eax, &ebx, &ecx, &edx); + info->sgx1 = eax & (1U << 0) ? true : false; + info->sgx2 = eax & (1U << 1) ? true : false; + + info->section_size = sgx_calc_host_epc_section_size(); + + close(fd); + + return info; +} + +SGXInfo *sgx_get_info(Error **errp) +{ + SGXInfo *info = NULL; + X86MachineState *x86ms; + PCMachineState *pcms = + (PCMachineState *)object_dynamic_cast(qdev_get_machine(), + TYPE_PC_MACHINE); + if (!pcms) { + error_setg(errp, "SGX is only supported on PC machines"); + return NULL; + } + + x86ms = X86_MACHINE(pcms); + if (!x86ms->sgx_epc_list) { + error_setg(errp, "No EPC regions defined, SGX not available"); + return NULL; + } + + SGXEPCState *sgx_epc = &pcms->sgx_epc; + info = g_new0(SGXInfo, 1); + + info->sgx = true; + info->sgx1 = true; + info->sgx2 = true; + info->flc = true; + info->section_size = sgx_epc->size; + + return info; +} + +int sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size) +{ + PCMachineState *pcms = PC_MACHINE(qdev_get_machine()); + SGXEPCDevice *epc; + + if (pcms->sgx_epc.size == 0 || pcms->sgx_epc.nr_sections <= section_nr) { + return 1; + } + + epc = pcms->sgx_epc.sections[section_nr]; + + *addr = epc->addr; + *size = memory_device_get_region_size(MEMORY_DEVICE(epc), &error_fatal); + + return 0; +} + +void pc_machine_init_sgx_epc(PCMachineState *pcms) +{ + SGXEPCState *sgx_epc = &pcms->sgx_epc; + X86MachineState *x86ms = X86_MACHINE(pcms); + SgxEPCList *list = NULL; + Object *obj; + + memset(sgx_epc, 0, sizeof(SGXEPCState)); + if (!x86ms->sgx_epc_list) { + return; + } + + sgx_epc->base = 0x100000000ULL + x86ms->above_4g_mem_size; + + memory_region_init(&sgx_epc->mr, OBJECT(pcms), "sgx-epc", UINT64_MAX); + memory_region_add_subregion(get_system_memory(), sgx_epc->base, + &sgx_epc->mr); + + for (list = x86ms->sgx_epc_list; list; list = list->next) { + obj = object_new("sgx-epc"); + + /* set the memdev link with memory backend */ + object_property_parse(obj, SGX_EPC_MEMDEV_PROP, list->value->memdev, + &error_fatal); + object_property_set_bool(obj, "realized", true, &error_fatal); + object_unref(obj); + } + + if ((sgx_epc->base + sgx_epc->size) < sgx_epc->base) { + error_report("Size of all 'sgx-epc' =0x%"PRIu64" causes EPC to wrap", + sgx_epc->size); + exit(EXIT_FAILURE); + } + + memory_region_set_size(&sgx_epc->mr, sgx_epc->size); +} diff --git a/hw/i386/x86.c b/hw/i386/x86.c index 00448ed55a..41ef9a84a9 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -30,6 +30,8 @@ #include "qapi/error.h" #include "qapi/qmp/qerror.h" #include "qapi/qapi-visit-common.h" +#include "qapi/clone-visitor.h" +#include "qapi/qapi-visit-machine.h" #include "qapi/visitor.h" #include "sysemu/qtest.h" #include "sysemu/whpx.h" @@ -1263,6 +1265,27 @@ static void x86_machine_set_bus_lock_ratelimit(Object *obj, Visitor *v, visit_type_uint64(v, name, &x86ms->bus_lock_ratelimit, errp); } +static void machine_get_sgx_epc(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + X86MachineState *x86ms = X86_MACHINE(obj); + SgxEPCList *list = x86ms->sgx_epc_list; + + visit_type_SgxEPCList(v, name, &list, errp); +} + +static void machine_set_sgx_epc(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + X86MachineState *x86ms = X86_MACHINE(obj); + SgxEPCList *list; + + list = x86ms->sgx_epc_list; + visit_type_SgxEPCList(v, name, &x86ms->sgx_epc_list, errp); + + qapi_free_SgxEPCList(list); +} + static void x86_machine_initfn(Object *obj) { X86MachineState *x86ms = X86_MACHINE(obj); @@ -1322,6 +1345,12 @@ static void x86_machine_class_init(ObjectClass *oc, void *data) x86_machine_set_bus_lock_ratelimit, NULL, NULL); object_class_property_set_description(oc, X86_MACHINE_BUS_LOCK_RATELIMIT, "Set the ratelimit for the bus locks acquired in VMs"); + + object_class_property_add(oc, "sgx-epc", "SgxEPC", + machine_get_sgx_epc, machine_set_sgx_epc, + NULL, NULL); + object_class_property_set_description(oc, "sgx-epc", + "SGX EPC device"); } static const TypeInfo x86_machine_info = { diff --git a/hw/i386/xen/xen-hvm.c b/hw/i386/xen/xen-hvm.c index 9b432773f0..e3d3d5cf89 100644 --- a/hw/i386/xen/xen-hvm.c +++ b/hw/i386/xen/xen-hvm.c @@ -721,6 +721,7 @@ static void xen_log_global_stop(MemoryListener *listener) } static MemoryListener xen_memory_listener = { + .name = "xen-memory", .region_add = xen_region_add, .region_del = xen_region_del, .log_start = xen_log_start, @@ -732,6 +733,7 @@ static MemoryListener xen_memory_listener = { }; static MemoryListener xen_io_listener = { + .name = "xen-io", .region_add = xen_io_add, .region_del = xen_io_del, .priority = 10, diff --git a/hw/intc/openpic_kvm.c b/hw/intc/openpic_kvm.c index 21da680389..557dd0c2bf 100644 --- a/hw/intc/openpic_kvm.c +++ b/hw/intc/openpic_kvm.c @@ -234,6 +234,7 @@ static void kvm_openpic_realize(DeviceState *dev, Error **errp) opp->mem_listener.region_add = kvm_openpic_region_add; opp->mem_listener.region_del = kvm_openpic_region_del; + opp->mem_listener.name = "openpic-kvm"; memory_listener_register(&opp->mem_listener, &address_space_memory); /* indicate pic capabilities */ diff --git a/hw/remote/proxy-memory-listener.c b/hw/remote/proxy-memory-listener.c index 901dbf1357..882c9b4854 100644 --- a/hw/remote/proxy-memory-listener.c +++ b/hw/remote/proxy-memory-listener.c @@ -219,6 +219,7 @@ void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener, proxy_listener->listener.region_add = proxy_memory_listener_region_addnop; proxy_listener->listener.region_nop = proxy_memory_listener_region_addnop; proxy_listener->listener.priority = 10; + proxy_listener->listener.name = "proxy"; memory_listener_register(&proxy_listener->listener, &address_space_memory); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 8728d4d5c2..a784b219e6 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -562,6 +562,7 @@ static bool vfio_listener_skipped_section(MemoryRegionSection *section) { return (!memory_region_is_ram(section->mr) && !memory_region_is_iommu(section->mr)) || + memory_region_is_protected(section->mr) || /* * Sizing an enabled 64-bit BAR can cause spurious mappings to * addresses in the upper part of the 64-bit address space. These @@ -1434,6 +1435,7 @@ static void vfio_listener_log_sync(MemoryListener *listener, } static const MemoryListener vfio_memory_listener = { + .name = "vfio", .region_add = vfio_listener_region_add, .region_del = vfio_listener_region_del, .log_global_start = vfio_listener_log_global_start, diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c index ea3f70bd2f..04c6e67f8f 100644 --- a/hw/vfio/spapr.c +++ b/hw/vfio/spapr.c @@ -136,6 +136,7 @@ static void vfio_prereg_listener_region_del(MemoryListener *listener, } const MemoryListener vfio_prereg_listener = { + .name = "vfio-pre-reg", .region_add = vfio_prereg_listener_region_add, .region_del = vfio_prereg_listener_region_del, }; diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 7633ea66d1..47d7a5a23d 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -246,6 +246,7 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener, * depends on the addnop(). */ static const MemoryListener vhost_vdpa_memory_listener = { + .name = "vhost-vdpa", .commit = vhost_vdpa_listener_commit, .region_add = vhost_vdpa_listener_region_add, .region_del = vhost_vdpa_listener_region_del, diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index b4b29413e6..437347ad01 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -1366,6 +1366,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, hdev->features = features; hdev->memory_listener = (MemoryListener) { + .name = "vhost", .begin = vhost_begin, .commit = vhost_commit, .region_add = vhost_region_addnop, @@ -1381,6 +1382,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, }; hdev->iommu_listener = (MemoryListener) { + .name = "vhost-iommu", .region_add = vhost_iommu_region_add, .region_del = vhost_iommu_region_del, }; diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 3a1f6c520c..240759ff0b 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -3670,6 +3670,7 @@ static void virtio_device_realize(DeviceState *dev, Error **errp) } vdev->listener.commit = virtio_memory_listener_commit; + vdev->listener.name = "virtio"; memory_listener_register(&vdev->listener, vdev->dma_as); } diff --git a/hw/xen/xen_pt.c b/hw/xen/xen_pt.c index 232482d65f..ca0a98187e 100644 --- a/hw/xen/xen_pt.c +++ b/hw/xen/xen_pt.c @@ -689,12 +689,14 @@ static void xen_pt_io_region_del(MemoryListener *l, MemoryRegionSection *sec) } static const MemoryListener xen_pt_memory_listener = { + .name = "xen-pt-mem", .region_add = xen_pt_region_add, .region_del = xen_pt_region_del, .priority = 10, }; static const MemoryListener xen_pt_io_listener = { + .name = "xen-pt-io", .region_add = xen_pt_io_region_add, .region_del = xen_pt_io_region_del, .priority = 10, diff --git a/include/exec/memory.h b/include/exec/memory.h index c3d417d317..a185b6dcb8 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -190,6 +190,9 @@ typedef struct IOMMUTLBEvent { */ #define RAM_NORESERVE (1 << 7) +/* RAM that isn't accessible through normal means. */ +#define RAM_PROTECTED (1 << 8) + static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn, IOMMUNotifierFlag flags, hwaddr start, hwaddr end, @@ -979,6 +982,14 @@ struct MemoryListener { */ unsigned priority; + /** + * @name: + * + * Name of the listener. It can be used in contexts where we'd like to + * identify one memory listener with the rest. + */ + const char *name; + /* private: */ AddressSpace *address_space; QTAILQ_ENTRY(MemoryListener) link; @@ -1267,7 +1278,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr, * @name: the name of the region. * @size: size of the region. * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, - * RAM_NORESERVE. + * RAM_NORESERVE, RAM_PROTECTED. * @fd: the fd to mmap. * @offset: offset within the file referenced by fd * @errp: pointer to Error*, to store an error if it happens. @@ -1569,6 +1580,16 @@ static inline bool memory_region_is_romd(MemoryRegion *mr) } /** + * memory_region_is_protected: check whether a memory region is protected + * + * Returns %true if a memory region is protected RAM and cannot be accessed + * via standard mechanisms, e.g. DMA. + * + * @mr: the memory region being queried + */ +bool memory_region_is_protected(MemoryRegion *mr); + +/** * memory_region_get_iommu: check whether a memory region is an iommu * * Returns pointer to IOMMUMemoryRegion if a memory region is an iommu, diff --git a/include/hw/i386/hostmem-epc.h b/include/hw/i386/hostmem-epc.h new file mode 100644 index 0000000000..846c726085 --- /dev/null +++ b/include/hw/i386/hostmem-epc.h @@ -0,0 +1,28 @@ +/* + * SGX EPC backend + * + * Copyright (C) 2019 Intel Corporation + * + * Authors: + * Sean Christopherson <sean.j.christopherson@intel.com> + * + * 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 QEMU_HOSTMEM_EPC_H +#define QEMU_HOSTMEM_EPC_H + +#include "sysemu/hostmem.h" + +#define TYPE_MEMORY_BACKEND_EPC "memory-backend-epc" + +#define MEMORY_BACKEND_EPC(obj) \ + OBJECT_CHECK(HostMemoryBackendEpc, (obj), TYPE_MEMORY_BACKEND_EPC) + +typedef struct HostMemoryBackendEpc HostMemoryBackendEpc; + +struct HostMemoryBackendEpc { + HostMemoryBackend parent_obj; +}; + +#endif diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 4d2e35a152..5748d7c55f 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -12,6 +12,7 @@ #include "hw/acpi/acpi_dev_interface.h" #include "hw/hotplug.h" #include "qom/object.h" +#include "hw/i386/sgx-epc.h" #define HPET_INTCAP "hpet-intcap" @@ -49,6 +50,8 @@ typedef struct PCMachineState { /* ACPI Memory hotplug IO base address */ hwaddr memhp_io_base; + + SGXEPCState sgx_epc; } PCMachineState; #define PC_MACHINE_ACPI_DEVICE_PROP "acpi-device" @@ -192,6 +195,9 @@ void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size); void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, const CPUArchIdList *apic_ids, GArray *entry); +/* sgx.c */ +void pc_machine_init_sgx_epc(PCMachineState *pcms); + extern GlobalProperty pc_compat_6_1[]; extern const size_t pc_compat_6_1_len; diff --git a/include/hw/i386/sgx-epc.h b/include/hw/i386/sgx-epc.h new file mode 100644 index 0000000000..65a68ca753 --- /dev/null +++ b/include/hw/i386/sgx-epc.h @@ -0,0 +1,67 @@ +/* + * SGX EPC device + * + * Copyright (C) 2019 Intel Corporation + * + * Authors: + * Sean Christopherson <sean.j.christopherson@intel.com> + * + * 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 QEMU_SGX_EPC_H +#define QEMU_SGX_EPC_H + +#include "hw/i386/hostmem-epc.h" + +#define TYPE_SGX_EPC "sgx-epc" +#define SGX_EPC(obj) \ + OBJECT_CHECK(SGXEPCDevice, (obj), TYPE_SGX_EPC) +#define SGX_EPC_CLASS(oc) \ + OBJECT_CLASS_CHECK(SGXEPCDeviceClass, (oc), TYPE_SGX_EPC) +#define SGX_EPC_GET_CLASS(obj) \ + OBJECT_GET_CLASS(SGXEPCDeviceClass, (obj), TYPE_SGX_EPC) + +#define SGX_EPC_ADDR_PROP "addr" +#define SGX_EPC_SIZE_PROP "size" +#define SGX_EPC_MEMDEV_PROP "memdev" + +/** + * SGXEPCDevice: + * @addr: starting guest physical address, where @SGXEPCDevice is mapped. + * Default value: 0, means that address is auto-allocated. + * @hostmem: host memory backend providing memory for @SGXEPCDevice + */ +typedef struct SGXEPCDevice { + /* private */ + DeviceState parent_obj; + + /* public */ + uint64_t addr; + HostMemoryBackendEpc *hostmem; +} SGXEPCDevice; + +/* + * @base: address in guest physical address space where EPC regions start + * @mr: address space container for memory devices + */ +typedef struct SGXEPCState { + uint64_t base; + uint64_t size; + + MemoryRegion mr; + + struct SGXEPCDevice **sections; + int nr_sections; +} SGXEPCState; + +int sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size); + +static inline uint64_t sgx_epc_above_4g_end(SGXEPCState *sgx_epc) +{ + assert(sgx_epc != NULL && sgx_epc->base >= 0x100000000ULL); + + return sgx_epc->base + sgx_epc->size; +} + +#endif diff --git a/include/hw/i386/sgx.h b/include/hw/i386/sgx.h new file mode 100644 index 0000000000..16fc25725c --- /dev/null +++ b/include/hw/i386/sgx.h @@ -0,0 +1,12 @@ +#ifndef QEMU_SGX_H +#define QEMU_SGX_H + +#include "qom/object.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qapi/qapi-types-misc-target.h" + +SGXInfo *sgx_get_info(Error **errp); +SGXInfo *sgx_get_capabilities(Error **errp); + +#endif diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h index 6e9244a82c..23267a3674 100644 --- a/include/hw/i386/x86.h +++ b/include/hw/i386/x86.h @@ -62,6 +62,7 @@ struct X86MachineState { unsigned pci_irq_mask; unsigned apic_id_limit; uint16_t boot_cpus; + SgxEPCList *sgx_epc_list; OnOffAuto smm; OnOffAuto acpi; diff --git a/include/monitor/hmp-target.h b/include/monitor/hmp-target.h index 60fc92722a..dc53add7ee 100644 --- a/include/monitor/hmp-target.h +++ b/include/monitor/hmp-target.h @@ -49,5 +49,6 @@ void hmp_info_tlb(Monitor *mon, const QDict *qdict); void hmp_mce(Monitor *mon, const QDict *qdict); void hmp_info_local_apic(Monitor *mon, const QDict *qdict); void hmp_info_io_apic(Monitor *mon, const QDict *qdict); +void hmp_info_sgx(Monitor *mon, const QDict *qdict); #endif /* MONITOR_HMP_TARGET_H */ diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index c788452cd9..1f5487d9b7 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -37,7 +37,7 @@ typedef struct KVMMemoryListener { } KVMMemoryListener; void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, - AddressSpace *as, int as_id); + AddressSpace *as, int as_id, const char *name); void kvm_set_max_memslot_size(hwaddr max_slot_size); diff --git a/io/dns-resolver.c b/io/dns-resolver.c index a5946a93bf..53b0e8407a 100644 --- a/io/dns-resolver.c +++ b/io/dns-resolver.c @@ -122,7 +122,7 @@ static int qio_dns_resolver_lookup_sync_inet(QIODNSResolver *resolver, .ipv4 = iaddr->ipv4, .has_ipv6 = iaddr->has_ipv6, .ipv6 = iaddr->ipv6, -#ifdef IPPROTO_MPTCP +#ifdef HAVE_IPPROTO_MPTCP .has_mptcp = iaddr->has_mptcp, .mptcp = iaddr->mptcp, #endif diff --git a/meson.build b/meson.build index 7bdbbbdf02..60f4f45165 100644 --- a/meson.build +++ b/meson.build @@ -106,14 +106,14 @@ if targetos != 'darwin' endif edk2_targets = [ 'arm-softmmu', 'aarch64-softmmu', 'i386-softmmu', 'x86_64-softmmu' ] -install_edk2_blobs = false -if get_option('install_blobs') - foreach target : target_dirs - install_edk2_blobs = install_edk2_blobs or target in edk2_targets - endforeach -endif - -bzip2 = find_program('bzip2', required: install_edk2_blobs) +unpack_edk2_blobs = false +foreach target : edk2_targets + if target in target_dirs + bzip2 = find_program('bzip2', required: get_option('install_blobs')) + unpack_edk2_blobs = bzip2.found() + break + endif +endforeach ################## # Compiler flags # @@ -1374,6 +1374,8 @@ config_host_data.set('HAVE_OPTRESET', cc.has_header_symbol('getopt.h', 'optreset')) config_host_data.set('HAVE_UTMPX', cc.has_header_symbol('utmpx.h', 'struct utmpx')) +config_host_data.set('HAVE_IPPROTO_MPTCP', + cc.has_header_symbol('netinet/in.h', 'IPPROTO_MPTCP')) # has_member config_host_data.set('HAVE_SIGEV_NOTIFY_THREAD_ID', diff --git a/meson_options.txt b/meson_options.txt index a9a9b8f4c6..2c89e79e8b 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -120,7 +120,7 @@ option('usb_redir', type : 'feature', value : 'auto', description: 'libusbredir support') option('virglrenderer', type : 'feature', value : 'auto', description: 'virgl rendering support') -option('vnc', type : 'feature', value : 'enabled', +option('vnc', type : 'feature', value : 'auto', description: 'VNC server') option('vnc_jpeg', type : 'feature', value : 'auto', description: 'JPEG lossy compression for VNC server') diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index b5e71d9e6f..bcaa41350e 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -1823,6 +1823,7 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict) VirtioMEMDeviceInfo *vmi; MemoryDeviceInfo *value; PCDIMMDeviceInfo *di; + SgxEPCDeviceInfo *se; for (info = info_list; info; info = info->next) { value = info->value; @@ -1870,6 +1871,15 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict) vmi->block_size); monitor_printf(mon, " memdev: %s\n", vmi->memdev); break; + case MEMORY_DEVICE_INFO_KIND_SGX_EPC: + se = value->u.sgx_epc.data; + monitor_printf(mon, "Memory device [%s]: \"%s\"\n", + MemoryDeviceInfoKind_str(value->type), + se->id ? se->id : ""); + monitor_printf(mon, " memaddr: 0x%" PRIx64 "\n", se->memaddr); + monitor_printf(mon, " size: %" PRIu64 "\n", se->size); + monitor_printf(mon, " memdev: %s\n", se->memdev); + break; default: g_assert_not_reached(); } diff --git a/pc-bios/descriptors/meson.build b/pc-bios/descriptors/meson.build index 29efa16d99..66f85d01c4 100644 --- a/pc-bios/descriptors/meson.build +++ b/pc-bios/descriptors/meson.build @@ -1,4 +1,4 @@ -if install_edk2_blobs +if unpack_edk2_blobs and get_option('install_blobs') foreach f: [ '50-edk2-i386-secure.json', '50-edk2-x86_64-secure.json', @@ -10,7 +10,7 @@ if install_edk2_blobs configure_file(input: files(f), output: f, configuration: {'DATADIR': get_option('prefix') / qemu_datadir}, - install: get_option('install_blobs'), + install: true, install_dir: qemu_datadir / 'firmware') endforeach endif diff --git a/pc-bios/meson.build b/pc-bios/meson.build index f2b32598af..a44c9bc127 100644 --- a/pc-bios/meson.build +++ b/pc-bios/meson.build @@ -1,4 +1,5 @@ -if install_edk2_blobs +roms = [] +if unpack_edk2_blobs fds = [ 'edk2-aarch64-code.fd', 'edk2-arm-code.fd', @@ -11,7 +12,7 @@ if install_edk2_blobs ] foreach f : fds - custom_target(f, + roms += custom_target(f, build_by_default: have_system, output: f, input: '@0@.bz2'.format(f), diff --git a/qapi/machine.json b/qapi/machine.json index 66bc34ed8b..f1c4983b64 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -1195,12 +1195,35 @@ } ## +# @SgxEPCDeviceInfo: +# +# Sgx EPC state information +# +# @id: device's ID +# +# @memaddr: physical address in memory, where device is mapped +# +# @size: size of memory that the device provides +# +# @memdev: memory backend linked with device +# +# Since: 6.2 +## +{ 'struct': 'SgxEPCDeviceInfo', + 'data': { '*id': 'str', + 'memaddr': 'size', + 'size': 'size', + 'memdev': 'str' + } +} + +## # @MemoryDeviceInfoKind: # # Since: 2.1 ## { 'enum': 'MemoryDeviceInfoKind', - 'data': [ 'dimm', 'nvdimm', 'virtio-pmem', 'virtio-mem' ] } + 'data': [ 'dimm', 'nvdimm', 'virtio-pmem', 'virtio-mem', 'sgx-epc' ] } ## # @PCDIMMDeviceInfoWrapper: @@ -1227,12 +1250,20 @@ 'data': { 'data': 'VirtioMEMDeviceInfo' } } ## +# @SgxEPCDeviceInfoWrapper: +# +# Since: 6.2 +## +{ 'struct': 'SgxEPCDeviceInfoWrapper', + 'data': { 'data': 'SgxEPCDeviceInfo' } } + +## # @MemoryDeviceInfo: # # Union containing information about a memory device # # nvdimm is included since 2.12. virtio-pmem is included since 4.1. -# virtio-mem is included since 5.1. +# virtio-mem is included since 5.1. sgx-epc is included since 6.2. # # Since: 2.1 ## @@ -1242,11 +1273,37 @@ 'data': { 'dimm': 'PCDIMMDeviceInfoWrapper', 'nvdimm': 'PCDIMMDeviceInfoWrapper', 'virtio-pmem': 'VirtioPMEMDeviceInfoWrapper', - 'virtio-mem': 'VirtioMEMDeviceInfoWrapper' + 'virtio-mem': 'VirtioMEMDeviceInfoWrapper', + 'sgx-epc': 'SgxEPCDeviceInfoWrapper' } } ## +# @SgxEPC: +# +# Sgx EPC cmdline information +# +# @memdev: memory backend linked with device +# +# Since: 6.2 +## +{ 'struct': 'SgxEPC', + 'data': { 'memdev': 'str' } } + +## +# @SgxEPCProperties: +# +# SGX properties of machine types. +# +# @sgx-epc: list of ids of memory-backend-epc objects. +# +# Since: 6.2 +## +{ 'struct': 'SgxEPCProperties', + 'data': { 'sgx-epc': ['SgxEPC'] } +} + +## # @query-memory-devices: # # Lists available memory devices and their state diff --git a/qapi/misc-target.json b/qapi/misc-target.json index 3b05ad3dbf..594fbd1577 100644 --- a/qapi/misc-target.json +++ b/qapi/misc-target.json @@ -333,3 +333,64 @@ { 'command': 'query-sev-attestation-report', 'data': { 'mnonce': 'str' }, 'returns': 'SevAttestationReport', 'if': 'TARGET_I386' } + +## +# @SGXInfo: +# +# Information about intel Safe Guard eXtension (SGX) support +# +# @sgx: true if SGX is supported +# +# @sgx1: true if SGX1 is supported +# +# @sgx2: true if SGX2 is supported +# +# @flc: true if FLC is supported +# +# @section-size: The EPC section size for guest +# +# Since: 6.2 +## +{ 'struct': 'SGXInfo', + 'data': { 'sgx': 'bool', + 'sgx1': 'bool', + 'sgx2': 'bool', + 'flc': 'bool', + 'section-size': 'uint64'}, + 'if': 'TARGET_I386' } + +## +# @query-sgx: +# +# Returns information about SGX +# +# Returns: @SGXInfo +# +# Since: 6.2 +# +# Example: +# +# -> { "execute": "query-sgx" } +# <- { "return": { "sgx": true, "sgx1" : true, "sgx2" : true, +# "flc": true, "section-size" : 0 } } +# +## +{ 'command': 'query-sgx', 'returns': 'SGXInfo', 'if': 'TARGET_I386' } + +## +# @query-sgx-capabilities: +# +# Returns information from host SGX capabilities +# +# Returns: @SGXInfo +# +# Since: 6.2 +# +# Example: +# +# -> { "execute": "query-sgx-capabilities" } +# <- { "return": { "sgx": true, "sgx1" : true, "sgx2" : true, +# "flc": true, "section-size" : 0 } } +# +## +{ 'command': 'query-sgx-capabilities', 'returns': 'SGXInfo', 'if': 'TARGET_I386' } diff --git a/qapi/qom.json b/qapi/qom.json index a25616bc7a..0222bb4506 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -648,6 +648,23 @@ '*seal': 'bool' } } ## +# @MemoryBackendEpcProperties: +# +# Properties for memory-backend-epc objects. +# +# The @share boolean option is true by default with epc +# +# The @merge boolean option is false by default with epc +# +# The @dump boolean option is false by default with epc +# +# Since: 6.2 +## +{ 'struct': 'MemoryBackendEpcProperties', + 'base': 'MemoryBackendProperties', + 'data': {} } + +## # @PrManagerHelperProperties: # # Properties for pr-manager-helper objects. @@ -797,6 +814,7 @@ { 'name': 'memory-backend-memfd', 'if': 'CONFIG_LINUX' }, 'memory-backend-ram', + 'memory-backend-epc', 'pef-guest', 'pr-manager-helper', 'qtest', @@ -855,6 +873,7 @@ 'memory-backend-memfd': { 'type': 'MemoryBackendMemfdProperties', 'if': 'CONFIG_LINUX' }, 'memory-backend-ram': 'MemoryBackendProperties', + 'memory-backend-epc': 'MemoryBackendEpcProperties', 'pr-manager-helper': 'PrManagerHelperProperties', 'qtest': 'QtestProperties', 'rng-builtin': 'RngProperties', diff --git a/qapi/sockets.json b/qapi/sockets.json index ef4b16d6f2..5773d9fcc4 100644 --- a/qapi/sockets.json +++ b/qapi/sockets.json @@ -69,7 +69,7 @@ '*ipv4': 'bool', '*ipv6': 'bool', '*keep-alive': 'bool', - '*mptcp': { 'type': 'bool', 'if': 'IPPROTO_MPTCP' } } } + '*mptcp': { 'type': 'bool', 'if': 'HAVE_IPPROTO_MPTCP' } } } ## # @UnixSocketAddress: diff --git a/qemu-options.hx b/qemu-options.hx index 8f603cc7e6..ceca52818a 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -126,8 +126,14 @@ SRST -m 512M ERST -HXCOMM Deprecated by -machine -DEF("M", HAS_ARG, QEMU_OPTION_M, "", QEMU_ARCH_ALL) +DEF("M", HAS_ARG, QEMU_OPTION_M, + " sgx-epc.0.memdev=memid\n", + QEMU_ARCH_ALL) + +SRST +``sgx-epc.0.memdev=@var{memid}`` + Define an SGX EPC section. +ERST DEF("cpu", HAS_ARG, QEMU_OPTION_cpu, "-cpu cpu select CPU ('-cpu help' for list)\n", QEMU_ARCH_ALL) diff --git a/softmmu/memory.c b/softmmu/memory.c index bfedaf9c4d..db182e5d3d 100644 --- a/softmmu/memory.c +++ b/softmmu/memory.c @@ -1811,6 +1811,11 @@ bool memory_region_is_ram_device(MemoryRegion *mr) return mr->ram_device; } +bool memory_region_is_protected(MemoryRegion *mr) +{ + return mr->ram && (mr->ram_block->flags & RAM_PROTECTED); +} + uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr) { uint8_t mask = mr->dirty_log_mask; @@ -2149,6 +2154,7 @@ static void memory_region_sync_dirty_bitmap(MemoryRegion *mr) } } flatview_unref(view); + trace_memory_region_sync_dirty(mr ? mr->name : "(all)", listener->name, 0); } else if (listener->log_sync_global) { /* * No matter whether MR is specified, what we can do here @@ -2156,6 +2162,7 @@ static void memory_region_sync_dirty_bitmap(MemoryRegion *mr) * sync in a finer granularity. */ listener->log_sync_global(listener); + trace_memory_region_sync_dirty(mr ? mr->name : "(all)", listener->name, 1); } } } diff --git a/softmmu/physmem.c b/softmmu/physmem.c index 23e77cb771..f67ad29981 100644 --- a/softmmu/physmem.c +++ b/softmmu/physmem.c @@ -756,6 +756,7 @@ void cpu_address_space_init(CPUState *cpu, int asidx, if (tcg_enabled()) { newas->tcg_as_listener.log_global_after_sync = tcg_log_global_after_sync; newas->tcg_as_listener.commit = tcg_commit; + newas->tcg_as_listener.name = "tcg"; memory_listener_register(&newas->tcg_as_listener, as); } } @@ -2055,7 +2056,8 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, int64_t file_size, file_align; /* Just support these ram flags by now. */ - assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_NORESERVE)) == 0); + assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_NORESERVE | + RAM_PROTECTED)) == 0); if (xen_enabled()) { error_setg(errp, "-mem-path not supported with Xen"); diff --git a/softmmu/trace-events b/softmmu/trace-events index 7b278590a0..bf1469990e 100644 --- a/softmmu/trace-events +++ b/softmmu/trace-events @@ -15,6 +15,7 @@ memory_region_subpage_read(int cpu_index, void *mr, uint64_t offset, uint64_t va memory_region_subpage_write(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" value 0x%"PRIx64" size %u" memory_region_ram_device_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u" memory_region_ram_device_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u" +memory_region_sync_dirty(const char *mr, const char *listener, int global) "mr '%s' listener '%s' synced (global=%d)" flatview_new(void *view, void *root) "%p (root %p)" flatview_destroy(void *view, void *root) "%p (root %p)" flatview_destroy_rcu(void *view, void *root) "%p (root %p)" diff --git a/target/arm/kvm.c b/target/arm/kvm.c index 94b970bbf9..bbf1ce7ba3 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -335,6 +335,7 @@ static void kvm_arm_devlistener_del(MemoryListener *listener, } static MemoryListener devlistener = { + .name = "kvm-arm", .region_add = kvm_arm_devlistener_add, .region_del = kvm_arm_devlistener_del, }; diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 6b029f1bdf..cacec605bf 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -36,6 +36,7 @@ #ifndef CONFIG_USER_ONLY #include "exec/address-spaces.h" #include "hw/boards.h" +#include "hw/i386/sgx-epc.h" #endif #include "disas/capstone.h" @@ -654,6 +655,9 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1, /* missing: CPUID_XSAVE_XSAVEC, CPUID_XSAVE_XSAVES */ #define TCG_14_0_ECX_FEATURES 0 +#define TCG_SGX_12_0_EAX_FEATURES 0 +#define TCG_SGX_12_0_EBX_FEATURES 0 +#define TCG_SGX_12_1_EAX_FEATURES 0 FeatureWordInfo feature_word_info[FEATURE_WORDS] = { [FEAT_1_EDX] = { @@ -795,7 +799,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { [FEAT_7_0_EBX] = { .type = CPUID_FEATURE_WORD, .feat_names = { - "fsgsbase", "tsc-adjust", NULL, "bmi1", + "fsgsbase", "tsc-adjust", "sgx", "bmi1", "hle", "avx2", NULL, "smep", "bmi2", "erms", "invpcid", "rtm", NULL, NULL, "mpx", NULL, @@ -821,7 +825,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { "la57", NULL, NULL, NULL, NULL, NULL, "rdpid", NULL, "bus-lock-detect", "cldemote", NULL, "movdiri", - "movdir64b", NULL, NULL, "pks", + "movdir64b", NULL, "sgxlc", "pks", }, .cpuid = { .eax = 7, @@ -1182,6 +1186,65 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .tcg_features = TCG_14_0_ECX_FEATURES, }, + [FEAT_SGX_12_0_EAX] = { + .type = CPUID_FEATURE_WORD, + .feat_names = { + "sgx1", "sgx2", NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + }, + .cpuid = { + .eax = 0x12, + .needs_ecx = true, .ecx = 0, + .reg = R_EAX, + }, + .tcg_features = TCG_SGX_12_0_EAX_FEATURES, + }, + + [FEAT_SGX_12_0_EBX] = { + .type = CPUID_FEATURE_WORD, + .feat_names = { + "sgx-exinfo" , NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + }, + .cpuid = { + .eax = 0x12, + .needs_ecx = true, .ecx = 0, + .reg = R_EBX, + }, + .tcg_features = TCG_SGX_12_0_EBX_FEATURES, + }, + + [FEAT_SGX_12_1_EAX] = { + .type = CPUID_FEATURE_WORD, + .feat_names = { + NULL, "sgx-debug", "sgx-mode64", NULL, + "sgx-provisionkey", "sgx-tokenkey", NULL, "sgx-kss", + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + }, + .cpuid = { + .eax = 0x12, + .needs_ecx = true, .ecx = 1, + .reg = R_EAX, + }, + .tcg_features = TCG_SGX_12_1_EAX_FEATURES, + }, }; typedef struct FeatureMask { @@ -5272,6 +5335,25 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, *ecx |= CPUID_7_0_ECX_OSPKE; } *edx = env->features[FEAT_7_0_EDX]; /* Feature flags */ + + /* + * SGX cannot be emulated in software. If hardware does not + * support enabling SGX and/or SGX flexible launch control, + * then we need to update the VM's CPUID values accordingly. + */ + if ((*ebx & CPUID_7_0_EBX_SGX) && + (!kvm_enabled() || + !(kvm_arch_get_supported_cpuid(cs->kvm_state, 0x7, 0, R_EBX) & + CPUID_7_0_EBX_SGX))) { + *ebx &= ~CPUID_7_0_EBX_SGX; + } + + if ((*ecx & CPUID_7_0_ECX_SGX_LC) && + (!(*ebx & CPUID_7_0_EBX_SGX) || !kvm_enabled() || + !(kvm_arch_get_supported_cpuid(cs->kvm_state, 0x7, 0, R_ECX) & + CPUID_7_0_ECX_SGX_LC))) { + *ecx &= ~CPUID_7_0_ECX_SGX_LC; + } } else if (count == 1) { *eax = env->features[FEAT_7_1_EAX]; *ebx = 0; @@ -5407,6 +5489,66 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, } break; } + case 0x12: +#ifndef CONFIG_USER_ONLY + if (!kvm_enabled() || + !(env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_SGX)) { + *eax = *ebx = *ecx = *edx = 0; + break; + } + + /* + * SGX sub-leafs CPUID.0x12.{0x2..N} enumerate EPC sections. Retrieve + * the EPC properties, e.g. confidentiality and integrity, from the + * host's first EPC section, i.e. assume there is one EPC section or + * that all EPC sections have the same security properties. + */ + if (count > 1) { + uint64_t epc_addr, epc_size; + + if (sgx_epc_get_section(count - 2, &epc_addr, &epc_size)) { + *eax = *ebx = *ecx = *edx = 0; + break; + } + host_cpuid(index, 2, eax, ebx, ecx, edx); + *eax = (uint32_t)(epc_addr & 0xfffff000) | 0x1; + *ebx = (uint32_t)(epc_addr >> 32); + *ecx = (uint32_t)(epc_size & 0xfffff000) | (*ecx & 0xf); + *edx = (uint32_t)(epc_size >> 32); + break; + } + + /* + * SGX sub-leafs CPUID.0x12.{0x0,0x1} are heavily dependent on hardware + * and KVM, i.e. QEMU cannot emulate features to override what KVM + * supports. Features can be further restricted by userspace, but not + * made more permissive. + */ + *eax = kvm_arch_get_supported_cpuid(cs->kvm_state, 0x12, count, R_EAX); + *ebx = kvm_arch_get_supported_cpuid(cs->kvm_state, 0x12, count, R_EBX); + *ecx = kvm_arch_get_supported_cpuid(cs->kvm_state, 0x12, count, R_ECX); + *edx = kvm_arch_get_supported_cpuid(cs->kvm_state, 0x12, count, R_EDX); + + if (count == 0) { + *eax &= env->features[FEAT_SGX_12_0_EAX]; + *ebx &= env->features[FEAT_SGX_12_0_EBX]; + } else { + *eax &= env->features[FEAT_SGX_12_1_EAX]; + *ebx &= 0; /* ebx reserve */ + *ecx &= env->features[FEAT_XSAVE_COMP_LO]; + *edx &= env->features[FEAT_XSAVE_COMP_HI]; + + /* FP and SSE are always allowed regardless of XSAVE/XCR0. */ + *ecx |= XSTATE_FP_MASK | XSTATE_SSE_MASK; + + /* Access to PROVISIONKEY requires additional credentials. */ + if ((*eax & (1U << 4)) && + !kvm_enable_sgx_provisioning(cs->kvm_state)) { + *eax &= ~(1U << 4); + } + } +#endif + break; case 0x14: { /* Intel Processor Trace Enumeration */ *eax = 0; @@ -5638,6 +5780,17 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, } } +static void x86_cpu_set_sgxlepubkeyhash(CPUX86State *env) +{ +#ifndef CONFIG_USER_ONLY + /* Those default values are defined in Skylake HW */ + env->msr_ia32_sgxlepubkeyhash[0] = 0xa6053e051270b7acULL; + env->msr_ia32_sgxlepubkeyhash[1] = 0x6cfbe8ba8b3b413dULL; + env->msr_ia32_sgxlepubkeyhash[2] = 0xc4916d99f2b3735dULL; + env->msr_ia32_sgxlepubkeyhash[3] = 0xd4f8c05909f9bb3bULL; +#endif +} + static void x86_cpu_reset(DeviceState *dev) { CPUState *s = CPU(dev); @@ -5770,6 +5923,8 @@ static void x86_cpu_reset(DeviceState *dev) if (kvm_enabled()) { kvm_arch_reset_vcpu(cpu); } + + x86_cpu_set_sgxlepubkeyhash(env); #endif } @@ -5999,6 +6154,11 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) if (sev_enabled()) { x86_cpu_adjust_level(cpu, &env->cpuid_min_xlevel, 0x8000001F); } + + /* SGX requires CPUID[0x12] for EPC enumeration */ + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_SGX) { + x86_cpu_adjust_level(cpu, &env->cpuid_min_level, 0x12); + } } /* Set cpuid_*level* based on cpuid_min_*level, if not explicitly set */ @@ -6152,6 +6312,8 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) & CPUID_EXT2_AMD_ALIASES); } + x86_cpu_set_sgxlepubkeyhash(env); + /* * note: the call to the framework needs to happen after feature expansion, * but before the checks/modifications to ucode_rev, mwait, phys_bits. @@ -6839,7 +7001,6 @@ static const TypeInfo x86_cpu_type_info = { .class_init = x86_cpu_common_class_init, }; - /* "base" CPU model, used by query-cpu-model-expansion */ static void x86_cpu_base_class_init(ObjectClass *oc, void *data) { diff --git a/target/i386/cpu.h b/target/i386/cpu.h index c2954c71ea..29552dc2a7 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -389,9 +389,17 @@ typedef enum X86Seg { #define MSR_IA32_PKRS 0x6e1 #define FEATURE_CONTROL_LOCKED (1<<0) +#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1ULL << 1) #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) +#define FEATURE_CONTROL_SGX_LC (1ULL << 17) +#define FEATURE_CONTROL_SGX (1ULL << 18) #define FEATURE_CONTROL_LMCE (1<<20) +#define MSR_IA32_SGXLEPUBKEYHASH0 0x8c +#define MSR_IA32_SGXLEPUBKEYHASH1 0x8d +#define MSR_IA32_SGXLEPUBKEYHASH2 0x8e +#define MSR_IA32_SGXLEPUBKEYHASH3 0x8f + #define MSR_P6_PERFCTR0 0xc1 #define MSR_IA32_SMBASE 0x9e @@ -570,6 +578,9 @@ typedef enum FeatureWord { FEAT_VMX_BASIC, FEAT_VMX_VMFUNC, FEAT_14_0_ECX, + FEAT_SGX_12_0_EAX, /* CPUID[EAX=0x12,ECX=0].EAX (SGX) */ + FEAT_SGX_12_0_EBX, /* CPUID[EAX=0x12,ECX=0].EBX (SGX MISCSELECT[31:0]) */ + FEAT_SGX_12_1_EAX, /* CPUID[EAX=0x12,ECX=1].EAX (SGX ATTRIBUTES[31:0]) */ FEATURE_WORDS, } FeatureWord; @@ -718,6 +729,8 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS]; /* Support RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE */ #define CPUID_7_0_EBX_FSGSBASE (1U << 0) +/* Support SGX */ +#define CPUID_7_0_EBX_SGX (1U << 2) /* 1st Group of Advanced Bit Manipulation Extensions */ #define CPUID_7_0_EBX_BMI1 (1U << 3) /* Hardware Lock Elision */ @@ -805,6 +818,8 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS]; #define CPUID_7_0_ECX_MOVDIRI (1U << 27) /* Move 64 Bytes as Direct Store Instruction */ #define CPUID_7_0_ECX_MOVDIR64B (1U << 28) +/* Support SGX Launch Control */ +#define CPUID_7_0_ECX_SGX_LC (1U << 30) /* Protection Keys for Supervisor-mode Pages */ #define CPUID_7_0_ECX_PKS (1U << 31) @@ -1501,6 +1516,7 @@ typedef struct CPUX86State { uint64_t mcg_status; uint64_t msr_ia32_misc_enable; uint64_t msr_ia32_feature_control; + uint64_t msr_ia32_sgxlepubkeyhash[4]; uint64_t msr_fixed_ctr_ctrl; uint64_t msr_global_ctrl; diff --git a/target/i386/hax/hax-mem.c b/target/i386/hax/hax-mem.c index 8d44edbffd..a226d174d8 100644 --- a/target/i386/hax/hax-mem.c +++ b/target/i386/hax/hax-mem.c @@ -285,6 +285,7 @@ static void hax_log_sync(MemoryListener *listener, } static MemoryListener hax_memory_listener = { + .name = "hax", .begin = hax_transaction_begin, .commit = hax_transaction_commit, .region_add = hax_region_add, diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 500d2e0e68..7f1b060e6d 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -1703,6 +1703,25 @@ int kvm_arch_init_vcpu(CPUState *cs) } break; case 0x7: + 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 0x14: { uint32_t times; @@ -1877,6 +1896,11 @@ int kvm_arch_init_vcpu(CPUState *cs) !!(c->ecx & CPUID_EXT_SMX); } + c = cpuid_find_entry(&cpuid_data.cpuid, 7, 0); + if (c && (c->ebx & CPUID_7_0_EBX_SGX)) { + has_msr_feature_control = true; + } + if (env->mcg_cap & MCG_LMCE_P) { has_msr_mcg_ext_ctl = has_msr_feature_control = true; } @@ -2224,7 +2248,7 @@ static void register_smram_listener(Notifier *n, void *unused) address_space_init(&smram_address_space, &smram_as_root, "KVM-SMRAM"); kvm_memory_listener_register(kvm_state, &smram_listener, - &smram_address_space, 1); + &smram_address_space, 1, "kvm-smram"); } int kvm_arch_init(MachineState *ms, KVMState *s) @@ -3107,6 +3131,17 @@ static int kvm_put_msrs(X86CPU *cpu, int level) } } + if (env->features[FEAT_7_0_ECX] & CPUID_7_0_ECX_SGX_LC) { + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH0, + env->msr_ia32_sgxlepubkeyhash[0]); + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH1, + env->msr_ia32_sgxlepubkeyhash[1]); + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH2, + env->msr_ia32_sgxlepubkeyhash[2]); + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH3, + env->msr_ia32_sgxlepubkeyhash[3]); + } + /* Note: MSR_IA32_FEATURE_CONTROL is written separately, see * kvm_put_msr_feature_control. */ } @@ -3446,6 +3481,13 @@ static int kvm_get_msrs(X86CPU *cpu) } } + if (env->features[FEAT_7_0_ECX] & CPUID_7_0_ECX_SGX_LC) { + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH0, 0); + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH1, 0); + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH2, 0); + kvm_msr_entry_add(cpu, MSR_IA32_SGXLEPUBKEYHASH3, 0); + } + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_MSRS, cpu->kvm_msr_buf); if (ret < 0) { return ret; @@ -3735,6 +3777,10 @@ static int kvm_get_msrs(X86CPU *cpu) case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: env->msr_rtit_addrs[index - MSR_IA32_RTIT_ADDR0_A] = msrs[i].data; break; + case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: + env->msr_ia32_sgxlepubkeyhash[index - MSR_IA32_SGXLEPUBKEYHASH0] = + msrs[i].data; + break; } } @@ -4617,6 +4663,35 @@ void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg) } } +static bool has_sgx_provisioning; + +static bool __kvm_enable_sgx_provisioning(KVMState *s) +{ + int fd, ret; + + if (!kvm_vm_check_extension(s, KVM_CAP_SGX_ATTRIBUTE)) { + return false; + } + + fd = qemu_open_old("/dev/sgx_provision", O_RDONLY); + if (fd < 0) { + return false; + } + + ret = kvm_vm_enable_cap(s, KVM_CAP_SGX_ATTRIBUTE, 0, fd); + if (ret) { + error_report("Could not enable SGX PROVISIONKEY: %s", strerror(-ret)); + exit(1); + } + close(fd); + return true; +} + +bool kvm_enable_sgx_provisioning(KVMState *s) +{ + return MEMORIZE(__kvm_enable_sgx_provisioning(s), has_sgx_provisioning); +} + static bool host_supports_vmx(void) { uint32_t ecx, unused; diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h index 54667b35f0..a978509d50 100644 --- a/target/i386/kvm/kvm_i386.h +++ b/target/i386/kvm/kvm_i386.h @@ -51,4 +51,6 @@ bool kvm_hyperv_expand_features(X86CPU *cpu, Error **errp); uint64_t kvm_swizzle_msi_ext_dest_id(uint64_t address); +bool kvm_enable_sgx_provisioning(KVMState *s); + #endif diff --git a/target/i386/machine.c b/target/i386/machine.c index b0943118d1..4367931623 100644 --- a/target/i386/machine.c +++ b/target/i386/machine.c @@ -1415,6 +1415,25 @@ static const VMStateDescription vmstate_msr_tsx_ctrl = { } }; +static bool intel_sgx_msrs_needed(void *opaque) +{ + X86CPU *cpu = opaque; + CPUX86State *env = &cpu->env; + + return !!(env->features[FEAT_7_0_ECX] & CPUID_7_0_ECX_SGX_LC); +} + +static const VMStateDescription vmstate_msr_intel_sgx = { + .name = "cpu/intel_sgx", + .version_id = 1, + .minimum_version_id = 1, + .needed = intel_sgx_msrs_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64_ARRAY(env.msr_ia32_sgxlepubkeyhash, X86CPU, 4), + VMSTATE_END_OF_LIST() + } +}; + const VMStateDescription vmstate_x86_cpu = { .name = "cpu", .version_id = 12, @@ -1551,6 +1570,7 @@ const VMStateDescription vmstate_x86_cpu = { &vmstate_nested_state, #endif &vmstate_msr_tsx_ctrl, + &vmstate_msr_intel_sgx, NULL } }; diff --git a/target/i386/monitor.c b/target/i386/monitor.c index 119211f0b0..196c1c9e77 100644 --- a/target/i386/monitor.c +++ b/target/i386/monitor.c @@ -35,6 +35,7 @@ #include "qapi/qapi-commands-misc-target.h" #include "qapi/qapi-commands-misc.h" #include "hw/i386/pc.h" +#include "hw/i386/sgx.h" /* Perform linear address sign extension */ static hwaddr addr_canonical(CPUArchState *env, hwaddr addr) @@ -763,3 +764,34 @@ qmp_query_sev_attestation_report(const char *mnonce, Error **errp) { return sev_get_attestation_report(mnonce, errp); } + +SGXInfo *qmp_query_sgx(Error **errp) +{ + return sgx_get_info(errp); +} + +void hmp_info_sgx(Monitor *mon, const QDict *qdict) +{ + Error *err = NULL; + g_autoptr(SGXInfo) info = qmp_query_sgx(&err); + + if (err) { + error_report_err(err); + return; + } + monitor_printf(mon, "SGX support: %s\n", + info->sgx ? "enabled" : "disabled"); + monitor_printf(mon, "SGX1 support: %s\n", + info->sgx1 ? "enabled" : "disabled"); + monitor_printf(mon, "SGX2 support: %s\n", + info->sgx2 ? "enabled" : "disabled"); + monitor_printf(mon, "FLC support: %s\n", + info->flc ? "enabled" : "disabled"); + monitor_printf(mon, "size: %" PRIu64 "\n", + info->section_size); +} + +SGXInfo *qmp_query_sgx_capabilities(Error **errp) +{ + return sgx_get_capabilities(errp); +} diff --git a/target/i386/nvmm/nvmm-all.c b/target/i386/nvmm/nvmm-all.c index a488b00e90..14c996f968 100644 --- a/target/i386/nvmm/nvmm-all.c +++ b/target/i386/nvmm/nvmm-all.c @@ -1123,6 +1123,7 @@ nvmm_log_sync(MemoryListener *listener, MemoryRegionSection *section) } static MemoryListener nvmm_memory_listener = { + .name = "nvmm", .begin = nvmm_transaction_begin, .commit = nvmm_transaction_commit, .region_add = nvmm_region_add, diff --git a/target/i386/sev.c b/target/i386/sev.c index 0b2c8f594a..fa7210473a 100644 --- a/target/i386/sev.c +++ b/target/i386/sev.c @@ -565,7 +565,7 @@ static int sev_read_file_base64(const char *filename, guchar **data, gsize *len) { gsize sz; - gchar *base64; + g_autofree gchar *base64 = NULL; GError *error = NULL; if (!g_file_get_contents(filename, &base64, &sz, &error)) { diff --git a/target/i386/whpx/whpx-all.c b/target/i386/whpx/whpx-all.c index 3e925b9da7..ef896da0a2 100644 --- a/target/i386/whpx/whpx-all.c +++ b/target/i386/whpx/whpx-all.c @@ -1598,6 +1598,7 @@ static void whpx_log_sync(MemoryListener *listener, } static MemoryListener whpx_memory_listener = { + .name = "whpx", .begin = whpx_transaction_begin, .commit = whpx_transaction_commit, .region_add = whpx_region_add, diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index 757bb8499a..19444d4752 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -68,12 +68,12 @@ qtests_i386 = \ (config_all_devices.has_key('CONFIG_RTL8139_PCI') ? ['rtl8139-test'] : []) + \ (config_all_devices.has_key('CONFIG_E1000E_PCI_EXPRESS') ? ['fuzz-e1000e-test'] : []) + \ (config_all_devices.has_key('CONFIG_ESP_PCI') ? ['am53c974-test'] : []) + \ + (unpack_edk2_blobs ? ['bios-tables-test'] : []) + \ qtests_pci + \ ['fdc-test', 'ide-test', 'hd-geo-test', 'boot-order-test', - 'bios-tables-test', 'rtc-test', 'i440fx-test', 'fw_cfg-test', @@ -180,7 +180,7 @@ qtests_arm = \ # TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional qtests_aarch64 = \ - (cpu != 'arm' ? ['bios-tables-test'] : []) + \ + (cpu != 'arm' and unpack_edk2_blobs ? ['bios-tables-test'] : []) + \ (config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-test'] : []) + \ (config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-swtpm-test'] : []) + \ ['arm-cpu-features', @@ -269,7 +269,7 @@ foreach dir : target_dirs qtest_emulator = emulators['qemu-system-' + target_base] target_qtests = get_variable('qtests_' + target_base, []) + qtests_generic - test_deps = [] + test_deps = roms qtest_env = environment() if have_tools qtest_env.set('QTEST_QEMU_IMG', './qemu-img') diff --git a/tests/qtest/qmp-cmd-test.c b/tests/qtest/qmp-cmd-test.c index c98b78d033..1af2f74c28 100644 --- a/tests/qtest/qmp-cmd-test.c +++ b/tests/qtest/qmp-cmd-test.c @@ -100,6 +100,8 @@ static bool query_is_ignored(const char *cmd) /* Success depends on Host or Hypervisor SEV support */ "query-sev", "query-sev-capabilities", + "query-sgx", + "query-sgx-capabilities", NULL }; int i; diff --git a/util/qemu-sockets.c b/util/qemu-sockets.c index 72216ef980..0585e7a629 100644 --- a/util/qemu-sockets.c +++ b/util/qemu-sockets.c @@ -278,7 +278,7 @@ static int inet_listen_saddr(InetSocketAddress *saddr, /* create socket + bind/listen */ for (e = res; e != NULL; e = e->ai_next) { -#ifdef IPPROTO_MPTCP +#ifdef HAVE_IPPROTO_MPTCP if (saddr->has_mptcp && saddr->mptcp) { e->ai_protocol = IPPROTO_MPTCP; } @@ -462,7 +462,7 @@ int inet_connect_saddr(InetSocketAddress *saddr, Error **errp) error_free(local_err); local_err = NULL; -#ifdef IPPROTO_MPTCP +#ifdef HAVE_IPPROTO_MPTCP if (saddr->has_mptcp && saddr->mptcp) { e->ai_protocol = IPPROTO_MPTCP; } @@ -699,7 +699,7 @@ int inet_parse(InetSocketAddress *addr, const char *str, Error **errp) } addr->has_keep_alive = true; } -#ifdef IPPROTO_MPTCP +#ifdef HAVE_IPPROTO_MPTCP begin = strstr(optstr, ",mptcp"); if (begin) { if (inet_parse_flag("mptcp", begin + strlen(",mptcp"), |