diff options
51 files changed, 1840 insertions, 605 deletions
diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index a6f4655a3a..b62877e51c 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -280,16 +280,6 @@ Device options Emulated device options ''''''''''''''''''''''' -``-device virtio-blk,scsi=on|off`` (since 5.0) -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - -The virtio-blk SCSI passthrough feature is a legacy VIRTIO feature. VIRTIO 1.0 -and later do not support it because the virtio-scsi device was introduced for -full SCSI support. Use virtio-scsi instead when SCSI passthrough is required. - -Note this also applies to ``-device virtio-blk-pci,scsi=on|off``, which is an -alias. - ``-device nvme-ns,eui64-default=on|off`` (since 7.1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst index 210a90bee8..eaae82b8a5 100644 --- a/docs/about/removed-features.rst +++ b/docs/about/removed-features.rst @@ -510,6 +510,14 @@ than zero. Removed along with the ``compression`` migration capability. +``-device virtio-blk,scsi=on|off`` (since 9.1) +'''''''''''''''''''''''''''''''''''''''''''''' + +The virtio-blk SCSI passthrough feature is a legacy VIRTIO feature. VIRTIO 1.0 +and later do not support it because the virtio-scsi device was introduced for +full SCSI support. Use virtio-scsi instead when SCSI passthrough is required. + + User-mode emulator command line arguments ----------------------------------------- diff --git a/docs/pci_expander_bridge.txt b/docs/pci_expander_bridge.txt index 36750273bb..540191f5e0 100644 --- a/docs/pci_expander_bridge.txt +++ b/docs/pci_expander_bridge.txt @@ -25,7 +25,7 @@ A detailed command line would be: -object memory-backend-ram,size=1024M,policy=bind,host-nodes=1,id=ram-node1 -numa node,nodeid=1,cpus=1,memdev=ram-node1 -device pxb,id=bridge1,bus=pci.0,numa_node=1,bus_nr=4 -netdev user,id=nd -device e1000,bus=bridge1,addr=0x4,netdev=nd -device pxb,id=bridge2,bus=pci.0,numa_node=0,bus_nr=8 -device e1000,bus=bridge2,addr=0x3 --device pxb,id=bridge3,bus=pci.0,bus_nr=40 -drive if=none,id=drive0,file=[img] -device virtio-blk-pci,drive=drive0,scsi=off,bus=bridge3,addr=1 +-device pxb,id=bridge3,bus=pci.0,bus_nr=40 -drive if=none,id=drive0,file=[img] -device virtio-blk-pci,drive=drive0,bus=bridge3,addr=1 Here you have: - 2 NUMA nodes for the guest, 0 and 1. (both mapped to the same NUMA node in host, but you can and should put it in different host NUMA nodes) diff --git a/docs/specs/tpm.rst b/docs/specs/tpm.rst index 68cb8cf7e6..1ad36ad709 100644 --- a/docs/specs/tpm.rst +++ b/docs/specs/tpm.rst @@ -336,7 +336,7 @@ In case a pSeries machine is emulated, use the following command line: -tpmdev emulator,id=tpm0,chardev=chrtpm \ -device tpm-spapr,tpmdev=tpm0 \ -device spapr-vscsi,id=scsi0,reg=0x00002000 \ - -device virtio-blk-pci,scsi=off,bus=pci.0,addr=0x3,drive=drive-virtio-disk0,id=virtio-disk0 \ + -device virtio-blk-pci,bus=pci.0,addr=0x3,drive=drive-virtio-disk0,id=virtio-disk0 \ -drive file=test.img,format=raw,if=none,id=drive-virtio-disk0 In case an Arm virt machine is emulated, use the following command line: diff --git a/docs/system/i386/amd-memory-encryption.rst b/docs/system/i386/amd-memory-encryption.rst index e9bc142bc1..748f5094ba 100644 --- a/docs/system/i386/amd-memory-encryption.rst +++ b/docs/system/i386/amd-memory-encryption.rst @@ -25,8 +25,8 @@ support for notifying a guest's operating system when certain types of VMEXITs are about to occur. This allows the guest to selectively share information with the hypervisor to satisfy the requested function. -Launching ---------- +Launching (SEV and SEV-ES) +-------------------------- Boot images (such as bios) must be encrypted before a guest can be booted. The ``MEMORY_ENCRYPT_OP`` ioctl provides commands to encrypt the images: ``LAUNCH_START``, @@ -161,6 +161,72 @@ The value of GCTX.LD is If kernel hashes are not used, or SEV-ES is disabled, use empty blobs for ``kernel_hashes_blob`` and ``vmsas_blob`` as needed. +Launching (SEV-SNP) +------------------- +Boot images (such as bios) must be encrypted before a guest can be booted. The +``MEMORY_ENCRYPT_OP`` ioctl provides commands to encrypt the images: +``SNP_LAUNCH_START``, ``SNP_LAUNCH_UPDATE``, and ``SNP_LAUNCH_FINISH``. These +three commands communicate with SEV-SNP firmware to generate a fresh memory +encryption key for the VM, encrypt the boot images for a successful launch. For +more details on the SEV-SNP firmware interfaces used by these commands please +see the SEV-SNP Firmware ABI. + +``SNP_LAUNCH_START`` is called first to create a cryptographic launch context +within the firmware. To create this context, the guest owner must provide a +guest policy and other parameters as described in the SEV-SNP firmware +specification. The launch parameters should be specified as described in the +QAPI schema for the sev-snp-guest object. + +The ``SNP_LAUNCH_START`` uses the following parameters, which can be configured +by the corresponding parameters documented in the QAPI schema for the +'sev-snp-guest' object. + ++--------+-------+----------+-------------------------------------------------+ +| key | type | default | meaning | ++---------------------------+-------------------------------------------------+ +| policy | hex | 0x30000 | a 64-bit guest policy | ++---------------------------+-------------------------------------------------+ +| guest-visible-workarounds | string| 0 | 16-byte base64 encoded string| +| | | | for guest OS visible | +| | | | workarounds. | ++---------------------------+-------------------------------------------------+ + +``SNP_LAUNCH_UPDATE`` encrypts the memory region using the cryptographic context +created via the ``SNP_LAUNCH_START`` command. If required, this command can be +called multiple times to encrypt different memory regions. The command also +calculates the measurement of the memory contents as it encrypts. + +``SNP_LAUNCH_FINISH`` finalizes the guest launch flow. Optionally, while +finalizing the launch the firmware can perform checks on the launch digest +computing through the ``SNP_LAUNCH_UPDATE``. To perform the check the user must +supply the id block, authentication blob and host data that should be included +in the attestation report. See the SEV-SNP spec for further details. + +The ``SNP_LAUNCH_FINISH`` uses the following parameters, which can be configured +by the corresponding parameters documented in the QAPI schema for the +'sev-snp-guest' object. + ++--------------------+-------+----------+-------------------------------------+ +| key | type | default | meaning | ++--------------------+-------+----------+-------------------------------------+ +| id-block | string| none | base64 encoded ID block | ++--------------------+-------+----------+-------------------------------------+ +| id-auth | string| none | base64 encoded authentication | +| | | | information | ++--------------------+-------+----------+-------------------------------------+ +| author-key-enabled | bool | 0 | auth block contains author key | ++--------------------+-------+----------+-------------------------------------+ +| host_data | string| none | host provided data | ++--------------------+-------+----------+-------------------------------------+ + +To launch a SEV-SNP guest (additional parameters are documented in the QAPI +schema for the 'sev-snp-guest' object):: + + # ${QEMU} \ + -machine ...,confidential-guest-support=sev0 \ + -object sev-snp-guest,id=sev0,cbitpos=51,reduced-phys-bits=1 + + Debugging --------- diff --git a/host/include/i386/host/cpuinfo.h b/host/include/i386/host/cpuinfo.h index b89e6d2e55..c1e94d75ce 100644 --- a/host/include/i386/host/cpuinfo.h +++ b/host/include/i386/host/cpuinfo.h @@ -9,14 +9,10 @@ /* Digested version of <cpuid.h> */ #define CPUINFO_ALWAYS (1u << 0) /* so cpuinfo is nonzero */ -#define CPUINFO_CMOV (1u << 1) #define CPUINFO_MOVBE (1u << 2) #define CPUINFO_LZCNT (1u << 3) -#define CPUINFO_POPCNT (1u << 4) #define CPUINFO_BMI1 (1u << 5) #define CPUINFO_BMI2 (1u << 6) -#define CPUINFO_SSE2 (1u << 7) -#define CPUINFO_SSE4 (1u << 8) #define CPUINFO_AVX1 (1u << 9) #define CPUINFO_AVX2 (1u << 10) #define CPUINFO_AVX512F (1u << 11) diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index bb86e65f65..73bdfd6122 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -172,57 +172,6 @@ static void virtio_blk_discard_write_zeroes_complete(void *opaque, int ret) virtio_blk_free_request(req); } -#ifdef __linux__ - -typedef struct { - VirtIOBlockReq *req; - struct sg_io_hdr hdr; -} VirtIOBlockIoctlReq; - -static void virtio_blk_ioctl_complete(void *opaque, int status) -{ - VirtIOBlockIoctlReq *ioctl_req = opaque; - VirtIOBlockReq *req = ioctl_req->req; - VirtIOBlock *s = req->dev; - VirtIODevice *vdev = VIRTIO_DEVICE(s); - struct virtio_scsi_inhdr *scsi; - struct sg_io_hdr *hdr; - - scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base; - - if (status) { - status = VIRTIO_BLK_S_UNSUPP; - virtio_stl_p(vdev, &scsi->errors, 255); - goto out; - } - - hdr = &ioctl_req->hdr; - /* - * From SCSI-Generic-HOWTO: "Some lower level drivers (e.g. ide-scsi) - * clear the masked_status field [hence status gets cleared too, see - * block/scsi_ioctl.c] even when a CHECK_CONDITION or COMMAND_TERMINATED - * status has occurred. However they do set DRIVER_SENSE in driver_status - * field. Also a (sb_len_wr > 0) indicates there is a sense buffer. - */ - if (hdr->status == 0 && hdr->sb_len_wr > 0) { - hdr->status = CHECK_CONDITION; - } - - virtio_stl_p(vdev, &scsi->errors, - hdr->status | (hdr->msg_status << 8) | - (hdr->host_status << 16) | (hdr->driver_status << 24)); - virtio_stl_p(vdev, &scsi->residual, hdr->resid); - virtio_stl_p(vdev, &scsi->sense_len, hdr->sb_len_wr); - virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len); - -out: - virtio_blk_req_complete(req, status); - virtio_blk_free_request(req); - g_free(ioctl_req); -} - -#endif - static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s, VirtQueue *vq) { VirtIOBlockReq *req = virtqueue_pop(vq, sizeof(VirtIOBlockReq)); @@ -233,20 +182,14 @@ static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s, VirtQueue *vq) return req; } -static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req) +static void virtio_blk_handle_scsi(VirtIOBlockReq *req) { - int status = VIRTIO_BLK_S_OK; - struct virtio_scsi_inhdr *scsi = NULL; + int status; + struct virtio_scsi_inhdr *scsi; VirtIOBlock *blk = req->dev; VirtIODevice *vdev = VIRTIO_DEVICE(blk); VirtQueueElement *elem = &req->elem; -#ifdef __linux__ - int i; - VirtIOBlockIoctlReq *ioctl_req; - BlockAIOCB *acb; -#endif - /* * We require at least one output segment each for the virtio_blk_outhdr * and the SCSI command block. @@ -262,95 +205,16 @@ static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req) /* * The scsi inhdr is placed in the second-to-last input segment, just * before the regular inhdr. + * + * Just put anything nonzero so that the ioctl fails in the guest. */ scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base; - - if (!virtio_has_feature(blk->host_features, VIRTIO_BLK_F_SCSI)) { - status = VIRTIO_BLK_S_UNSUPP; - goto fail; - } - - /* - * No support for bidirection commands yet. - */ - if (elem->out_num > 2 && elem->in_num > 3) { - status = VIRTIO_BLK_S_UNSUPP; - goto fail; - } - -#ifdef __linux__ - ioctl_req = g_new0(VirtIOBlockIoctlReq, 1); - ioctl_req->req = req; - ioctl_req->hdr.interface_id = 'S'; - ioctl_req->hdr.cmd_len = elem->out_sg[1].iov_len; - ioctl_req->hdr.cmdp = elem->out_sg[1].iov_base; - ioctl_req->hdr.dxfer_len = 0; - - if (elem->out_num > 2) { - /* - * If there are more than the minimally required 2 output segments - * there is write payload starting from the third iovec. - */ - ioctl_req->hdr.dxfer_direction = SG_DXFER_TO_DEV; - ioctl_req->hdr.iovec_count = elem->out_num - 2; - - for (i = 0; i < ioctl_req->hdr.iovec_count; i++) { - ioctl_req->hdr.dxfer_len += elem->out_sg[i + 2].iov_len; - } - - ioctl_req->hdr.dxferp = elem->out_sg + 2; - - } else if (elem->in_num > 3) { - /* - * If we have more than 3 input segments the guest wants to actually - * read data. - */ - ioctl_req->hdr.dxfer_direction = SG_DXFER_FROM_DEV; - ioctl_req->hdr.iovec_count = elem->in_num - 3; - for (i = 0; i < ioctl_req->hdr.iovec_count; i++) { - ioctl_req->hdr.dxfer_len += elem->in_sg[i].iov_len; - } - - ioctl_req->hdr.dxferp = elem->in_sg; - } else { - /* - * Some SCSI commands don't actually transfer any data. - */ - ioctl_req->hdr.dxfer_direction = SG_DXFER_NONE; - } - - ioctl_req->hdr.sbp = elem->in_sg[elem->in_num - 3].iov_base; - ioctl_req->hdr.mx_sb_len = elem->in_sg[elem->in_num - 3].iov_len; - - acb = blk_aio_ioctl(blk->blk, SG_IO, &ioctl_req->hdr, - virtio_blk_ioctl_complete, ioctl_req); - if (!acb) { - g_free(ioctl_req); - status = VIRTIO_BLK_S_UNSUPP; - goto fail; - } - return -EINPROGRESS; -#else - abort(); -#endif + virtio_stl_p(vdev, &scsi->errors, 255); + status = VIRTIO_BLK_S_UNSUPP; fail: - /* Just put anything nonzero so that the ioctl fails in the guest. */ - if (scsi) { - virtio_stl_p(vdev, &scsi->errors, 255); - } - return status; -} - -static void virtio_blk_handle_scsi(VirtIOBlockReq *req) -{ - int status; - - status = virtio_blk_handle_scsi_req(req); - if (status != -EINPROGRESS) { - virtio_blk_req_complete(req, status); - virtio_blk_free_request(req); - } + virtio_blk_req_complete(req, status); + virtio_blk_free_request(req); } static inline void submit_requests(VirtIOBlock *s, MultiReqBuffer *mrb, @@ -1379,13 +1243,9 @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features, virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY); virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY); virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE); - if (virtio_has_feature(features, VIRTIO_F_VERSION_1)) { - if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_SCSI)) { - error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0"); - return 0; - } - } else { + if (!virtio_has_feature(features, VIRTIO_F_VERSION_1)) { virtio_clear_feature(&features, VIRTIO_F_ANY_LAYOUT); + /* Added for historical reasons, removing it could break migration. */ virtio_add_feature(&features, VIRTIO_BLK_F_SCSI); } @@ -2132,10 +1992,6 @@ static Property virtio_blk_properties[] = { DEFINE_PROP_STRING("serial", VirtIOBlock, conf.serial), DEFINE_PROP_BIT64("config-wce", VirtIOBlock, host_features, VIRTIO_BLK_F_CONFIG_WCE, true), -#ifdef __linux__ - DEFINE_PROP_BIT64("scsi", VirtIOBlock, host_features, - VIRTIO_BLK_F_SCSI, false), -#endif DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0, true), DEFINE_PROP_UINT16("num-queues", VirtIOBlock, conf.num_queues, diff --git a/hw/core/machine.c b/hw/core/machine.c index 8087026b45..77a356f232 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -265,8 +265,6 @@ GlobalProperty hw_compat_2_5[] = { const size_t hw_compat_2_5_len = G_N_ELEMENTS(hw_compat_2_5); GlobalProperty hw_compat_2_4[] = { - /* Optional because the 'scsi' property is Linux-only */ - { "virtio-blk-device", "scsi", "true", .optional = true }, { "e1000", "extra_mac_registers", "off" }, { "virtio-pci", "x-disable-pcie", "on" }, { "virtio-pci", "migrate-extra", "off" }, @@ -1218,7 +1216,7 @@ bool machine_mem_merge(MachineState *machine) bool machine_require_guest_memfd(MachineState *machine) { - return machine->require_guest_memfd; + return machine->cgs && machine->cgs->require_guest_memfd; } static char *cpu_slot_to_string(const CPUArchId *cpu) diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 7b638da7aa..0469af00a7 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -62,6 +62,7 @@ #include "hw/mem/memory-device.h" #include "e820_memory_layout.h" #include "trace.h" +#include "sev.h" #include CONFIG_DEVICES #ifdef CONFIG_XEN_EMU @@ -1022,10 +1023,15 @@ void pc_memory_init(PCMachineState *pcms, pc_system_firmware_init(pcms, rom_memory); option_rom_mr = g_malloc(sizeof(*option_rom_mr)); - memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE, - &error_fatal); - if (pcmc->pci_enabled) { - memory_region_set_readonly(option_rom_mr, true); + if (machine_require_guest_memfd(machine)) { + memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom", + PC_ROM_SIZE, &error_fatal); + } else { + memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE, + &error_fatal); + if (pcmc->pci_enabled) { + memory_region_set_readonly(option_rom_mr, true); + } } memory_region_add_subregion_overlap(rom_memory, PC_ROM_MIN_VGA, diff --git a/hw/i386/pc_sysfw.c b/hw/i386/pc_sysfw.c index ac88ad4eb9..ef80281d28 100644 --- a/hw/i386/pc_sysfw.c +++ b/hw/i386/pc_sysfw.c @@ -40,8 +40,8 @@ #define FLASH_SECTOR_SIZE 4096 -static void pc_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *rom_memory, - MemoryRegion *flash_mem) +static void pc_isa_bios_init(PCMachineState *pcms, MemoryRegion *isa_bios, + MemoryRegion *rom_memory, MemoryRegion *flash_mem) { int isa_bios_size; uint64_t flash_size; @@ -51,8 +51,13 @@ static void pc_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *rom_memory, /* map the last 128KB of the BIOS in ISA space */ isa_bios_size = MIN(flash_size, 128 * KiB); - memory_region_init_ram(isa_bios, NULL, "isa-bios", isa_bios_size, - &error_fatal); + if (machine_require_guest_memfd(MACHINE(pcms))) { + memory_region_init_ram_guest_memfd(isa_bios, NULL, "isa-bios", + isa_bios_size, &error_fatal); + } else { + memory_region_init_ram(isa_bios, NULL, "isa-bios", isa_bios_size, + &error_fatal); + } memory_region_add_subregion_overlap(rom_memory, 0x100000 - isa_bios_size, isa_bios, @@ -65,7 +70,9 @@ static void pc_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *rom_memory, ((uint8_t*)flash_ptr) + (flash_size - isa_bios_size), isa_bios_size); - memory_region_set_readonly(isa_bios, true); + if (!machine_require_guest_memfd(current_machine)) { + memory_region_set_readonly(isa_bios, true); + } } static PFlashCFI01 *pc_pflash_create(PCMachineState *pcms, @@ -148,6 +155,8 @@ static void pc_system_flash_map(PCMachineState *pcms, assert(PC_MACHINE_GET_CLASS(pcms)->pci_enabled); for (i = 0; i < ARRAY_SIZE(pcms->flash); i++) { + hwaddr gpa; + system_flash = pcms->flash[i]; blk = pflash_cfi01_get_blk(system_flash); if (!blk) { @@ -177,11 +186,11 @@ static void pc_system_flash_map(PCMachineState *pcms, } total_size += size; + gpa = 0x100000000ULL - total_size; /* where the flash is mapped */ qdev_prop_set_uint32(DEVICE(system_flash), "num-blocks", size / FLASH_SECTOR_SIZE); sysbus_realize_and_unref(SYS_BUS_DEVICE(system_flash), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(system_flash), 0, - 0x100000000ULL - total_size); + sysbus_mmio_map(SYS_BUS_DEVICE(system_flash), 0, gpa); if (i == 0) { flash_mem = pflash_cfi01_get_memory(system_flash); @@ -189,14 +198,14 @@ static void pc_system_flash_map(PCMachineState *pcms, x86_isa_bios_init(&x86ms->isa_bios, rom_memory, flash_mem, true); } else { - pc_isa_bios_init(&x86ms->isa_bios, rom_memory, flash_mem); + pc_isa_bios_init(pcms, &x86ms->isa_bios, rom_memory, flash_mem); } /* Encrypt the pflash boot ROM */ if (sev_enabled()) { flash_ptr = memory_region_get_ram_ptr(flash_mem); flash_size = memory_region_size(flash_mem); - x86_firmware_configure(flash_ptr, flash_size); + x86_firmware_configure(gpa, flash_ptr, flash_size); } } } @@ -249,7 +258,7 @@ void pc_system_firmware_init(PCMachineState *pcms, pc_system_flash_cleanup_unused(pcms); } -void x86_firmware_configure(void *ptr, int size) +void x86_firmware_configure(hwaddr gpa, void *ptr, int size) { int ret; @@ -260,12 +269,16 @@ void x86_firmware_configure(void *ptr, int size) pc_system_parse_ovmf_flash(ptr, size); if (sev_enabled()) { + + /* Copy the SEV metadata table (if it exists) */ + pc_system_parse_sev_metadata(ptr, size); + ret = sev_es_save_reset_vector(ptr, size); if (ret) { error_report("failed to locate and/or save reset vector"); exit(1); } - sev_encrypt_flash(ptr, size, &error_fatal); + sev_encrypt_flash(gpa, ptr, size, &error_fatal); } } diff --git a/hw/i386/x86-common.c b/hw/i386/x86-common.c index ee9046d9a8..c0c66a0eb5 100644 --- a/hw/i386/x86-common.c +++ b/hw/i386/x86-common.c @@ -1001,8 +1001,13 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware, (bios_size % 65536) != 0) { goto bios_error; } - memory_region_init_ram(&x86ms->bios, NULL, "pc.bios", bios_size, - &error_fatal); + if (machine_require_guest_memfd(MACHINE(x86ms))) { + memory_region_init_ram_guest_memfd(&x86ms->bios, NULL, "pc.bios", + bios_size, &error_fatal); + } else { + memory_region_init_ram(&x86ms->bios, NULL, "pc.bios", + bios_size, &error_fatal); + } if (sev_enabled()) { /* * The concept of a "reset" simply doesn't exist for @@ -1013,7 +1018,7 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware, */ void *ptr = memory_region_get_ram_ptr(&x86ms->bios); load_image_size(filename, ptr, bios_size); - x86_firmware_configure(ptr, bios_size); + x86_firmware_configure(0x100000000ULL - bios_size, ptr, bios_size); } else { memory_region_set_readonly(&x86ms->bios, !isapc_ram_fw); ret = rom_add_file_fixed(bios_name, (uint32_t)(-bios_size), -1); @@ -1023,9 +1028,11 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware, } g_free(filename); - /* map the last 128KB of the BIOS in ISA space */ - x86_isa_bios_init(&x86ms->isa_bios, rom_memory, &x86ms->bios, - !isapc_ram_fw); + if (!machine_require_guest_memfd(MACHINE(x86ms))) { + /* map the last 128KB of the BIOS in ISA space */ + x86_isa_bios_init(&x86ms->isa_bios, rom_memory, &x86ms->bios, + !isapc_ram_fw); + } /* map all the bios at the top of memory */ memory_region_add_subregion(rom_memory, diff --git a/hw/misc/pvpanic-isa.c b/hw/misc/pvpanic-isa.c index ccec50f61b..b4f84c4110 100644 --- a/hw/misc/pvpanic-isa.c +++ b/hw/misc/pvpanic-isa.c @@ -21,7 +21,7 @@ #include "hw/misc/pvpanic.h" #include "qom/object.h" #include "hw/isa/isa.h" -#include "standard-headers/linux/pvpanic.h" +#include "standard-headers/misc/pvpanic.h" #include "hw/acpi/acpi_aml_interface.h" OBJECT_DECLARE_SIMPLE_TYPE(PVPanicISAState, PVPANIC_ISA_DEVICE) diff --git a/hw/misc/pvpanic-pci.c b/hw/misc/pvpanic-pci.c index 83be95d0d2..4d44a881da 100644 --- a/hw/misc/pvpanic-pci.c +++ b/hw/misc/pvpanic-pci.c @@ -21,7 +21,7 @@ #include "hw/misc/pvpanic.h" #include "qom/object.h" #include "hw/pci/pci_device.h" -#include "standard-headers/linux/pvpanic.h" +#include "standard-headers/misc/pvpanic.h" OBJECT_DECLARE_SIMPLE_TYPE(PVPanicPCIState, PVPANIC_PCI_DEVICE) diff --git a/hw/misc/pvpanic.c b/hw/misc/pvpanic.c index 1540e9091a..80289ecf5f 100644 --- a/hw/misc/pvpanic.c +++ b/hw/misc/pvpanic.c @@ -21,7 +21,7 @@ #include "hw/qdev-properties.h" #include "hw/misc/pvpanic.h" #include "qom/object.h" -#include "standard-headers/linux/pvpanic.h" +#include "standard-headers/misc/pvpanic.h" static void handle_event(int event) { diff --git a/include/exec/confidential-guest-support.h b/include/exec/confidential-guest-support.h index e5b188cffb..02dc4e518f 100644 --- a/include/exec/confidential-guest-support.h +++ b/include/exec/confidential-guest-support.h @@ -32,6 +32,11 @@ struct ConfidentialGuestSupport { Object parent; /* + * True if the machine should use guest_memfd for RAM. + */ + bool require_guest_memfd; + + /* * ready: flag set by CGS initialization code once it's ready to * start executing instructions in a potentially-secure * guest diff --git a/include/exec/memory.h b/include/exec/memory.h index 9cdd64e9c6..1be58f694c 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -1638,6 +1638,12 @@ bool memory_region_init_ram(MemoryRegion *mr, uint64_t size, Error **errp); +bool memory_region_init_ram_guest_memfd(MemoryRegion *mr, + Object *owner, + const char *name, + uint64_t size, + Error **errp); + /** * memory_region_init_rom: Initialize a ROM memory region. * diff --git a/include/hw/boards.h b/include/hw/boards.h index 2fa800f11a..73ad319d7d 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -375,7 +375,6 @@ struct MachineState { char *dt_compatible; bool dump_guest_core; bool mem_merge; - bool require_guest_memfd; bool usb; bool usb_disabled; char *firmware; diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index ad9c3d9ba8..ca7904ac2c 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -164,6 +164,34 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level); #define PCI_HOST_ABOVE_4G_MEM_SIZE "above-4g-mem-size" #define PCI_HOST_PROP_SMM_RANGES "smm-ranges" +typedef enum { + SEV_DESC_TYPE_UNDEF, + /* The section contains the region that must be validated by the VMM. */ + SEV_DESC_TYPE_SNP_SEC_MEM, + /* The section contains the SNP secrets page */ + SEV_DESC_TYPE_SNP_SECRETS, + /* The section contains address that can be used as a CPUID page */ + SEV_DESC_TYPE_CPUID, + /* The section contains the region for kernel hashes for measured direct boot */ + SEV_DESC_TYPE_SNP_KERNEL_HASHES = 0x10, + +} ovmf_sev_metadata_desc_type; + +typedef struct __attribute__((__packed__)) OvmfSevMetadataDesc { + uint32_t base; + uint32_t len; + ovmf_sev_metadata_desc_type type; +} OvmfSevMetadataDesc; + +typedef struct __attribute__((__packed__)) OvmfSevMetadata { + uint8_t signature[4]; + uint32_t len; + uint32_t version; + uint32_t num_desc; + OvmfSevMetadataDesc descs[]; +} OvmfSevMetadata; + +OvmfSevMetadata *pc_system_get_ovmf_sev_metadata_ptr(void); void pc_pci_as_mapping_init(MemoryRegion *system_memory, MemoryRegion *pci_address_space); diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h index b006f16b8d..d43cb3908e 100644 --- a/include/hw/i386/x86.h +++ b/include/hw/i386/x86.h @@ -154,6 +154,6 @@ void ioapic_init_gsi(GSIState *gsi_state, Object *parent); DeviceState *ioapic_init_secondary(GSIState *gsi_state); /* pc_sysfw.c */ -void x86_firmware_configure(void *ptr, int size); +void x86_firmware_configure(hwaddr gpa, void *ptr, int size); #endif diff --git a/include/standard-headers/linux/kvm_para.h b/include/standard-headers/linux/kvm_para.h new file mode 100644 index 0000000000..015c166302 --- /dev/null +++ b/include/standard-headers/linux/kvm_para.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_KVM_PARA_H +#define __LINUX_KVM_PARA_H + +/* + * This header file provides a method for making a hypercall to the host + * Architectures should define: + * - kvm_hypercall0, kvm_hypercall1... + * - kvm_arch_para_features + * - kvm_para_available + */ + +/* Return values for hypercalls */ +#define KVM_ENOSYS 1000 +#define KVM_EFAULT EFAULT +#define KVM_EINVAL EINVAL +#define KVM_E2BIG E2BIG +#define KVM_EPERM EPERM +#define KVM_EOPNOTSUPP 95 + +#define KVM_HC_VAPIC_POLL_IRQ 1 +#define KVM_HC_MMU_OP 2 +#define KVM_HC_FEATURES 3 +#define KVM_HC_PPC_MAP_MAGIC_PAGE 4 +#define KVM_HC_KICK_CPU 5 +#define KVM_HC_MIPS_GET_CLOCK_FREQ 6 +#define KVM_HC_MIPS_EXIT_VM 7 +#define KVM_HC_MIPS_CONSOLE_OUTPUT 8 +#define KVM_HC_CLOCK_PAIRING 9 +#define KVM_HC_SEND_IPI 10 +#define KVM_HC_SCHED_YIELD 11 +#define KVM_HC_MAP_GPA_RANGE 12 + +/* + * hypercalls use architecture specific + */ + +#endif /* __LINUX_KVM_PARA_H */ diff --git a/include/standard-headers/linux/pvpanic.h b/include/standard-headers/misc/pvpanic.h index 54b7485390..54b7485390 100644 --- a/include/standard-headers/linux/pvpanic.h +++ b/include/standard-headers/misc/pvpanic.h diff --git a/linux-headers/asm-loongarch/kvm.h b/linux-headers/asm-loongarch/kvm.h index 109785922c..f9abef3823 100644 --- a/linux-headers/asm-loongarch/kvm.h +++ b/linux-headers/asm-loongarch/kvm.h @@ -17,6 +17,8 @@ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_DIRTY_LOG_PAGE_OFFSET 64 +#define KVM_GUESTDBG_USE_SW_BP 0x00010000 + /* * for KVM_GET_REGS and KVM_SET_REGS */ @@ -72,6 +74,8 @@ struct kvm_fpu { #define KVM_REG_LOONGARCH_COUNTER (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 1) #define KVM_REG_LOONGARCH_VCPU_RESET (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 2) +/* Debugging: Special instruction for software breakpoint */ +#define KVM_REG_LOONGARCH_DEBUG_INST (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 3) #define LOONGARCH_REG_SHIFT 3 #define LOONGARCH_REG_64(TYPE, REG) (TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT)) diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h index b1c503c295..e878e7cc39 100644 --- a/linux-headers/asm-riscv/kvm.h +++ b/linux-headers/asm-riscv/kvm.h @@ -167,6 +167,7 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_ZFA, KVM_RISCV_ISA_EXT_ZTSO, KVM_RISCV_ISA_EXT_ZACAS, + KVM_RISCV_ISA_EXT_SSCOFPMF, KVM_RISCV_ISA_EXT_MAX, }; diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index 31c95c2dfe..1c8f918234 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -695,6 +695,11 @@ enum sev_cmd_id { /* Second time is the charm; improved versions of the above ioctls. */ KVM_SEV_INIT2, + /* SNP-specific commands */ + KVM_SEV_SNP_LAUNCH_START = 100, + KVM_SEV_SNP_LAUNCH_UPDATE, + KVM_SEV_SNP_LAUNCH_FINISH, + KVM_SEV_NR_MAX, }; @@ -709,7 +714,9 @@ struct kvm_sev_cmd { struct kvm_sev_init { __u64 vmsa_features; __u32 flags; - __u32 pad[9]; + __u16 ghcb_version; + __u16 pad1; + __u32 pad2[8]; }; struct kvm_sev_launch_start { @@ -820,6 +827,48 @@ struct kvm_sev_receive_update_data { __u32 pad2; }; +struct kvm_sev_snp_launch_start { + __u64 policy; + __u8 gosvw[16]; + __u16 flags; + __u8 pad0[6]; + __u64 pad1[4]; +}; + +/* Kept in sync with firmware values for simplicity. */ +#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1 +#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3 +#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4 +#define KVM_SEV_SNP_PAGE_TYPE_SECRETS 0x5 +#define KVM_SEV_SNP_PAGE_TYPE_CPUID 0x6 + +struct kvm_sev_snp_launch_update { + __u64 gfn_start; + __u64 uaddr; + __u64 len; + __u8 type; + __u8 pad0; + __u16 flags; + __u32 pad1; + __u64 pad2[4]; +}; + +#define KVM_SEV_SNP_ID_BLOCK_SIZE 96 +#define KVM_SEV_SNP_ID_AUTH_SIZE 4096 +#define KVM_SEV_SNP_FINISH_DATA_SIZE 32 + +struct kvm_sev_snp_launch_finish { + __u64 id_block_uaddr; + __u64 id_auth_uaddr; + __u8 id_block_en; + __u8 auth_key_en; + __u8 vcek_disabled; + __u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE]; + __u8 pad0[3]; + __u16 flags; + __u64 pad1[4]; +}; + #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) @@ -870,5 +919,6 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SW_PROTECTED_VM 1 #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 +#define KVM_X86_SNP_VM 4 #endif /* _ASM_X86_KVM_H */ diff --git a/linux-headers/asm-x86/kvm_para.h b/linux-headers/asm-x86/kvm_para.h new file mode 100644 index 0000000000..1d3e0e0b07 --- /dev/null +++ b/linux-headers/asm-x86/kvm_para.h @@ -0,0 +1 @@ +#include "standard-headers/asm-x86/kvm_para.h" diff --git a/linux-headers/linux/kvm_para.h b/linux-headers/linux/kvm_para.h new file mode 100644 index 0000000000..6a1e672259 --- /dev/null +++ b/linux-headers/linux/kvm_para.h @@ -0,0 +1,2 @@ +#include "standard-headers/linux/kvm_para.h" +#include <asm/kvm_para.h> diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index bea6973906..b95dd84eef 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -179,12 +179,6 @@ /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) -/* Get the count of all virtqueues */ -#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) - -/* Get the number of virtqueue groups. */ -#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) - /* Get the number of address spaces. */ #define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) @@ -228,10 +222,17 @@ #define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \ struct vhost_vring_state) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + /* 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, \ +#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x82, \ struct vhost_vring_state) #endif diff --git a/meson.build b/meson.build index 6386607144..d80203f1cd 100644 --- a/meson.build +++ b/meson.build @@ -336,9 +336,13 @@ if host_arch == 'i386' and not cc.links(''' qemu_common_flags = ['-march=i486'] + qemu_common_flags endif -# ??? Only extremely old AMD cpus do not have cmpxchg16b. -# If we truly care, we should simply detect this case at -# runtime and generate the fallback to serial emulation. +# Assume x86-64-v2 (minus CMPXCHG16B for 32-bit code) +if host_arch == 'i386' + qemu_common_flags = ['-mfpmath=sse'] + qemu_common_flags +endif +if host_arch in ['i386', 'x86_64'] + qemu_common_flags = ['-mpopcnt', '-msse4.2'] + qemu_common_flags +endif if host_arch == 'x86_64' qemu_common_flags = ['-mcx16'] + qemu_common_flags endif diff --git a/qapi/misc-target.json b/qapi/misc-target.json index 4e0a6492a9..2d7d4d89bd 100644 --- a/qapi/misc-target.json +++ b/qapi/misc-target.json @@ -48,6 +48,50 @@ 'if': 'TARGET_I386' } ## +# @SevGuestType: +# +# An enumeration indicating the type of SEV guest being run. +# +# @sev: The guest is a legacy SEV or SEV-ES guest. +# +# @sev-snp: The guest is an SEV-SNP guest. +# +# Since: 6.2 +## +{ 'enum': 'SevGuestType', + 'data': [ 'sev', 'sev-snp' ], + 'if': 'TARGET_I386' } + +## +# @SevGuestInfo: +# +# Information specific to legacy SEV/SEV-ES guests. +# +# @policy: SEV policy value +# +# @handle: SEV firmware handle +# +# Since: 2.12 +## +{ 'struct': 'SevGuestInfo', + 'data': { 'policy': 'uint32', + 'handle': 'uint32' }, + 'if': 'TARGET_I386' } + +## +# @SevSnpGuestInfo: +# +# Information specific to SEV-SNP guests. +# +# @snp-policy: SEV-SNP policy value +# +# Since: 9.1 +## +{ 'struct': 'SevSnpGuestInfo', + 'data': { 'snp-policy': 'uint64' }, + 'if': 'TARGET_I386' } + +## # @SevInfo: # # Information about Secure Encrypted Virtualization (SEV) support @@ -60,25 +104,25 @@ # # @build-id: SEV FW build id # -# @policy: SEV policy value -# # @state: SEV guest state # -# @handle: SEV firmware handle +# @sev-type: Type of SEV guest being run # # Since: 2.12 ## -{ 'struct': 'SevInfo', - 'data': { 'enabled': 'bool', - 'api-major': 'uint8', - 'api-minor' : 'uint8', - 'build-id' : 'uint8', - 'policy' : 'uint32', - 'state' : 'SevState', - 'handle' : 'uint32' - }, - 'if': 'TARGET_I386' -} +{ 'union': 'SevInfo', + 'base': { 'enabled': 'bool', + 'api-major': 'uint8', + 'api-minor' : 'uint8', + 'build-id' : 'uint8', + 'state' : 'SevState', + 'sev-type' : 'SevGuestType' }, + 'discriminator': 'sev-type', + 'data': { + 'sev': 'SevGuestInfo', + 'sev-snp': 'SevSnpGuestInfo' }, + 'if': 'TARGET_I386' } + ## # @query-sev: diff --git a/qapi/qom.json b/qapi/qom.json index 38dde6d785..8bd299265e 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -875,20 +875,12 @@ 'data': { '*filename': 'str' } } ## -# @SevGuestProperties: +# @SevCommonProperties: # -# Properties for sev-guest objects. +# Properties common to objects that are derivatives of sev-common. # # @sev-device: SEV device to use (default: "/dev/sev") # -# @dh-cert-file: guest owners DH certificate (encoded with base64) -# -# @session-file: guest owners session parameters (encoded with base64) -# -# @policy: SEV policy value (default: 0x1) -# -# @handle: SEV firmware handle (default: 0) -# # @cbitpos: C-bit location in page table entry (default: 0) # # @reduced-phys-bits: number of bits in physical addresses that become @@ -898,6 +890,27 @@ # designated guest firmware page for measured boot with -kernel # (default: false) (since 6.2) # +# Since: 9.1 +## +{ 'struct': 'SevCommonProperties', + 'data': { '*sev-device': 'str', + '*cbitpos': 'uint32', + 'reduced-phys-bits': 'uint32', + '*kernel-hashes': 'bool' } } + +## +# @SevGuestProperties: +# +# Properties for sev-guest objects. +# +# @dh-cert-file: guest owners DH certificate (encoded with base64) +# +# @session-file: guest owners session parameters (encoded with base64) +# +# @policy: SEV policy value (default: 0x1) +# +# @handle: SEV firmware handle (default: 0) +# # @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 @@ -909,17 +922,70 @@ # Since: 2.12 ## { 'struct': 'SevGuestProperties', - 'data': { '*sev-device': 'str', - '*dh-cert-file': 'str', + 'base': 'SevCommonProperties', + 'data': { '*dh-cert-file': 'str', '*session-file': 'str', '*policy': 'uint32', '*handle': 'uint32', - '*cbitpos': 'uint32', - 'reduced-phys-bits': 'uint32', - '*kernel-hashes': 'bool', '*legacy-vm-type': 'bool' } } ## +# @SevSnpGuestProperties: +# +# Properties for sev-snp-guest objects. Most of these are direct +# arguments for the KVM_SNP_* interfaces documented in the Linux +# kernel source under +# Documentation/arch/x86/amd-memory-encryption.rst, which are in turn +# closely coupled with the SNP_INIT/SNP_LAUNCH_* firmware commands +# documented in the SEV-SNP Firmware ABI Specification (Rev 0.9). +# +# More usage information is also available in the QEMU source tree +# under docs/amd-memory-encryption. +# +# @policy: the 'POLICY' parameter to the SNP_LAUNCH_START command, as +# defined in the SEV-SNP firmware ABI (default: 0x30000) +# +# @guest-visible-workarounds: 16-byte, base64-encoded blob to report +# hypervisor-defined workarounds, corresponding to the 'GOSVW' +# parameter of the SNP_LAUNCH_START command defined in the SEV-SNP +# firmware ABI (default: all-zero) +# +# @id-block: 96-byte, base64-encoded blob to provide the 'ID Block' +# structure for the SNP_LAUNCH_FINISH command defined in the +# SEV-SNP firmware ABI (default: all-zero) +# +# @id-auth: 4096-byte, base64-encoded blob to provide the 'ID +# Authentication Information Structure' for the SNP_LAUNCH_FINISH +# command defined in the SEV-SNP firmware ABI (default: all-zero) +# +# @author-key-enabled: true if 'id-auth' blob contains the 'AUTHOR_KEY' +# field defined SEV-SNP firmware ABI (default: false) +# +# @host-data: 32-byte, base64-encoded, user-defined blob to provide to +# the guest, as documented for the 'HOST_DATA' parameter of the +# SNP_LAUNCH_FINISH command in the SEV-SNP firmware ABI (default: +# all-zero) +# +# @vcek-disabled: Guests are by default allowed to choose between VLEK +# (Versioned Loaded Endorsement Key) or VCEK (Versioned Chip +# Endorsement Key) when requesting attestation reports from +# firmware. Set this to true to disable the use of VCEK. +# (default: false) (since: 9.1) +# +# Since: 9.1 +## +{ 'struct': 'SevSnpGuestProperties', + 'base': 'SevCommonProperties', + 'data': { + '*policy': 'uint64', + '*guest-visible-workarounds': 'str', + '*id-block': 'str', + '*id-auth': 'str', + '*author-key-enabled': 'bool', + '*host-data': 'str', + '*vcek-disabled': 'bool' } } + +## # @ThreadContextProperties: # # Properties for thread context objects. @@ -997,6 +1063,7 @@ { 'name': 'secret_keyring', 'if': 'CONFIG_SECRET_KEYRING' }, 'sev-guest', + 'sev-snp-guest', 'thread-context', 's390-pv-guest', 'throttle-group', @@ -1067,6 +1134,7 @@ 'secret_keyring': { 'type': 'SecretKeyringProperties', 'if': 'CONFIG_SECRET_KEYRING' }, 'sev-guest': 'SevGuestProperties', + 'sev-snp-guest': 'SevSnpGuestProperties', 'thread-context': 'ThreadContextProperties', 'throttle-group': 'ThrottleGroupProperties', 'tls-creds-anon': 'TlsCredsAnonProperties', diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index 23afe8c08a..c34ac6454e 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -63,6 +63,7 @@ cp_portable() { -e 'linux/kernel' \ -e 'linux/sysinfo' \ -e 'asm/setup_data.h' \ + -e 'asm/kvm_para.h' \ > /dev/null then echo "Unexpected #include in input file $f". @@ -70,6 +71,15 @@ cp_portable() { fi header=$(basename "$f"); + + if test -z "$arch"; then + # Let users of include/standard-headers/linux/ headers pick the + # asm-* header that they care about + arch_cmd='/<asm\/\([^>]*\)>/d' + else + arch_cmd='s/<asm\/\([^>]*\)>/"standard-headers\/asm-'$arch'\/\1"/' + fi + sed -e 's/__aligned_u64/__u64 __attribute__((aligned(8)))/g' \ -e 's/__u\([0-9][0-9]*\)/uint\1_t/g' \ -e 's/u\([0-9][0-9]*\)/uint\1_t/g' \ @@ -78,7 +88,7 @@ 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/<linux\/\([^>]*\)>/"standard-headers\/linux\/\1"/' \ - -e 's/<asm\/\([^>]*\)>/"standard-headers\/asm-'$arch'\/\1"/' \ + -e "$arch_cmd" \ -e 's/__bitwise//' \ -e 's/__attribute__((packed))/QEMU_PACKED/' \ -e 's/__inline__/inline/' \ @@ -118,7 +128,14 @@ for arch in $ARCHLIST; do rm -rf "$output/linux-headers/asm-$arch" mkdir -p "$output/linux-headers/asm-$arch" for header in kvm.h unistd.h bitsperlong.h mman.h; do - cp "$hdrdir/include/asm/$header" "$output/linux-headers/asm-$arch" + if test -f "$hdrdir/include/asm/$header"; then + cp "$hdrdir/include/asm/$header" "$output/linux-headers/asm-$arch" + elif test -f "$hdrdir/include/asm-generic/$header"; then + # not installed as <asm/$header>, but used as such in kernel sources + cat <<EOF >$output/linux-headers/asm-$arch/$header +#include <asm-generic/$header> +EOF + fi done if [ $arch = mips ]; then @@ -151,7 +168,12 @@ for arch in $ARCHLIST; do cp "$hdrdir/include/asm/unistd_32.h" "$output/linux-headers/asm-x86/" cp "$hdrdir/include/asm/unistd_x32.h" "$output/linux-headers/asm-x86/" cp "$hdrdir/include/asm/unistd_64.h" "$output/linux-headers/asm-x86/" + cp_portable "$hdrdir/include/asm/kvm_para.h" "$output/include/standard-headers/asm-$arch" + cat <<EOF >$output/linux-headers/asm-$arch/kvm_para.h +#include "standard-headers/asm-$arch/kvm_para.h" +EOF + # Remove everything except the macros from bootparam.h avoiding the # unnecessary import of several video/ist/etc headers sed -e '/__ASSEMBLY__/,/__ASSEMBLY__/d' \ @@ -201,6 +223,10 @@ if [ -d "$linux/LICENSES" ]; then done fi +cat <<EOF >$output/linux-headers/linux/kvm_para.h +#include "standard-headers/linux/kvm_para.h" +#include <asm/kvm_para.h> +EOF cat <<EOF >$output/linux-headers/linux/virtio_config.h #include "standard-headers/linux/virtio_config.h" EOF @@ -223,11 +249,14 @@ for i in "$hdrdir"/include/linux/*virtio*.h \ "$hdrdir/include/linux/ethtool.h" \ "$hdrdir/include/linux/const.h" \ "$hdrdir/include/linux/kernel.h" \ + "$hdrdir/include/linux/kvm_para.h" \ "$hdrdir/include/linux/vhost_types.h" \ - "$hdrdir/include/linux/sysinfo.h" \ - "$hdrdir/include/misc/pvpanic.h"; do + "$hdrdir/include/linux/sysinfo.h"; do cp_portable "$i" "$output/include/standard-headers/linux" done +mkdir -p "$output/include/standard-headers/misc" +cp_portable "$hdrdir/include/misc/pvpanic.h" \ + "$output/include/standard-headers/misc" mkdir -p "$output/include/standard-headers/drm" cp_portable "$hdrdir/include/drm/drm_fourcc.h" \ "$output/include/standard-headers/drm" diff --git a/system/memory.c b/system/memory.c index 9540caa8a1..74cd73ebc7 100644 --- a/system/memory.c +++ b/system/memory.c @@ -3649,6 +3649,30 @@ bool memory_region_init_ram(MemoryRegion *mr, return true; } +bool memory_region_init_ram_guest_memfd(MemoryRegion *mr, + Object *owner, + const char *name, + uint64_t size, + Error **errp) +{ + DeviceState *owner_dev; + + if (!memory_region_init_ram_flags_nomigrate(mr, owner, name, size, + RAM_GUEST_MEMFD, errp)) { + return false; + } + /* This will assert if owner is neither NULL nor a DeviceState. + * We only want the owner here for the purposes of defining a + * unique name for migration. TODO: Ideally we should implement + * a naming scheme for Objects which are not DeviceStates, in + * which case we can relax this restriction. + */ + owner_dev = DEVICE(owner); + vmstate_register_ram(mr, owner_dev); + + return true; +} + bool memory_region_init_rom(MemoryRegion *mr, Object *owner, const char *name, diff --git a/target/i386/cpu.c b/target/i386/cpu.c index bc2dceb647..914bef442c 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -6979,6 +6979,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, if (sev_enabled()) { *eax = 0x2; *eax |= sev_es_enabled() ? 0x8 : 0; + *eax |= sev_snp_enabled() ? 0x10 : 0; *ebx = sev_get_cbit_position() & 0x3f; /* EBX[5:0] */ *ebx |= (sev_get_reduced_phys_bits() & 0x3f) << 6; /* EBX[11:6] */ } diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 82ebddada1..0852ed077f 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -21,6 +21,7 @@ #include <sys/syscall.h> #include <linux/kvm.h> +#include <linux/kvm_para.h> #include "standard-headers/asm-x86/kvm_para.h" #include "hw/xen/interface/arch-x86/cpuid.h" @@ -167,6 +168,7 @@ static const char *vm_type_name[] = { [KVM_X86_DEFAULT_VM] = "default", [KVM_X86_SEV_VM] = "SEV", [KVM_X86_SEV_ES_VM] = "SEV-ES", + [KVM_X86_SNP_VM] = "SEV-SNP", }; bool kvm_is_vm_type_supported(int type) @@ -208,6 +210,13 @@ int kvm_get_vm_type(MachineState *ms) return kvm_type; } +bool kvm_enable_hypercall(uint64_t enable_mask) +{ + KVMState *s = KVM_STATE(current_accel()); + + return !kvm_vm_enable_cap(s, KVM_CAP_EXIT_HYPERCALL, 0, enable_mask); +} + bool kvm_has_smm(void) { return kvm_vm_check_extension(kvm_state, KVM_CAP_X86_SMM); @@ -5321,6 +5330,50 @@ static bool host_supports_vmx(void) return ecx & CPUID_EXT_VMX; } +/* + * Currently the handling here only supports use of KVM_HC_MAP_GPA_RANGE + * to service guest-initiated memory attribute update requests so that + * KVM_SET_MEMORY_ATTRIBUTES can update whether or not a page should be + * backed by the private memory pool provided by guest_memfd, and as such + * is only applicable to guest_memfd-backed guests (e.g. SNP/TDX). + * + * Other other use-cases for KVM_HC_MAP_GPA_RANGE, such as for SEV live + * migration, are not implemented here currently. + * + * For the guest_memfd use-case, these exits will generally be synthesized + * by KVM based on platform-specific hypercalls, like GHCB requests in the + * case of SEV-SNP, and not issued directly within the guest though the + * KVM_HC_MAP_GPA_RANGE hypercall. So in this case, KVM_HC_MAP_GPA_RANGE is + * not actually advertised to guests via the KVM CPUID feature bit, as + * opposed to SEV live migration where it would be. Since it is unlikely the + * SEV live migration use-case would be useful for guest-memfd backed guests, + * because private/shared page tracking is already provided through other + * means, these 2 use-cases should be treated as being mutually-exclusive. + */ +static int kvm_handle_hc_map_gpa_range(struct kvm_run *run) +{ + uint64_t gpa, size, attributes; + + if (!machine_require_guest_memfd(current_machine)) + return -EINVAL; + + gpa = run->hypercall.args[0]; + size = run->hypercall.args[1] * TARGET_PAGE_SIZE; + attributes = run->hypercall.args[2]; + + trace_kvm_hc_map_gpa_range(gpa, size, attributes, run->hypercall.flags); + + return kvm_convert_memory(gpa, size, attributes & KVM_MAP_GPA_RANGE_ENCRYPTED); +} + +static int kvm_handle_hypercall(struct kvm_run *run) +{ + if (run->hypercall.nr == KVM_HC_MAP_GPA_RANGE) + return kvm_handle_hc_map_gpa_range(run); + + return -EINVAL; +} + #define VMX_INVALID_GUEST_STATE 0x80000021 int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) @@ -5415,6 +5468,9 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) ret = kvm_xen_handle_exit(cpu, &run->xen); break; #endif + case KVM_EXIT_HYPERCALL: + ret = kvm_handle_hypercall(run); + break; default: fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason); ret = -1; diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h index 6b44844d95..34fc60774b 100644 --- a/target/i386/kvm/kvm_i386.h +++ b/target/i386/kvm/kvm_i386.h @@ -33,6 +33,7 @@ bool kvm_has_smm(void); bool kvm_enable_x2apic(void); bool kvm_hv_vpindex_settable(void); +bool kvm_enable_hypercall(uint64_t enable_mask); bool kvm_enable_sgx_provisioning(KVMState *s); bool kvm_hyperv_expand_features(X86CPU *cpu, Error **errp); diff --git a/target/i386/kvm/trace-events b/target/i386/kvm/trace-events index b365a8e8e2..74a6234ff7 100644 --- a/target/i386/kvm/trace-events +++ b/target/i386/kvm/trace-events @@ -5,6 +5,7 @@ kvm_x86_fixup_msi_error(uint32_t gsi) "VT-d failed to remap interrupt for GSI %" kvm_x86_add_msi_route(int virq) "Adding route entry for virq %d" kvm_x86_remove_msi_route(int virq) "Removing route entry for virq %d" kvm_x86_update_msi_routes(int num) "Updated %d MSI routes" +kvm_hc_map_gpa_range(uint64_t gpa, uint64_t size, uint64_t attributes, uint64_t flags) "gpa 0x%" PRIx64 " size 0x%" PRIx64 " attributes 0x%" PRIx64 " flags 0x%" PRIx64 # xen-emu.c kvm_xen_hypercall(int cpu, uint8_t cpl, uint64_t input, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t ret) "xen_hypercall: cpu %d cpl %d input %" PRIu64 " a0 0x%" PRIx64 " a1 0x%" PRIx64 " a2 0x%" PRIx64" ret 0x%" PRIx64 diff --git a/target/i386/sev-sysemu-stub.c b/target/i386/sev-sysemu-stub.c index 96e1c15cc3..d5bf886e79 100644 --- a/target/i386/sev-sysemu-stub.c +++ b/target/i386/sev-sysemu-stub.c @@ -42,7 +42,7 @@ void qmp_sev_inject_launch_secret(const char *packet_header, const char *secret, error_setg(errp, "SEV is not available in this QEMU"); } -int sev_encrypt_flash(uint8_t *ptr, uint64_t len, Error **errp) +int sev_encrypt_flash(hwaddr gpa, uint8_t *ptr, uint64_t len, Error **errp) { g_assert_not_reached(); } @@ -67,3 +67,7 @@ void hmp_info_sev(Monitor *mon, const QDict *qdict) { monitor_printf(mon, "SEV is not available in this QEMU\n"); } + +void pc_system_parse_sev_metadata(uint8_t *flash_ptr, size_t flash_size) +{ +} diff --git a/target/i386/sev.c b/target/i386/sev.c index d30b68c11e..004c667ac1 100644 --- a/target/i386/sev.c +++ b/target/i386/sev.c @@ -14,6 +14,7 @@ #include "qemu/osdep.h" #include <linux/kvm.h> +#include <linux/kvm_para.h> #include <linux/psp-sev.h> #include <sys/ioctl.h> @@ -39,96 +40,143 @@ #include "confidential-guest.h" #include "hw/i386/pc.h" #include "exec/address-spaces.h" +#include "qemu/queue.h" -#define TYPE_SEV_GUEST "sev-guest" -OBJECT_DECLARE_SIMPLE_TYPE(SevGuestState, SEV_GUEST) +OBJECT_DECLARE_TYPE(SevCommonState, SevCommonStateClass, SEV_COMMON) +OBJECT_DECLARE_TYPE(SevGuestState, SevCommonStateClass, SEV_GUEST) +OBJECT_DECLARE_TYPE(SevSnpGuestState, SevCommonStateClass, SEV_SNP_GUEST) +/* hard code sha256 digest size */ +#define HASH_SIZE 32 -/** - * SevGuestState: - * - * The SevGuestState object is used for creating and managing a SEV - * guest. - * - * # $QEMU \ - * -object sev-guest,id=sev0 \ - * -machine ...,memory-encryption=sev0 +typedef struct QEMU_PACKED SevHashTableEntry { + QemuUUID guid; + uint16_t len; + uint8_t hash[HASH_SIZE]; +} SevHashTableEntry; + +typedef struct QEMU_PACKED SevHashTable { + QemuUUID guid; + uint16_t len; + SevHashTableEntry cmdline; + SevHashTableEntry initrd; + SevHashTableEntry kernel; +} SevHashTable; + +/* + * Data encrypted by sev_encrypt_flash() must be padded to a multiple of + * 16 bytes. */ -struct SevGuestState { +typedef struct QEMU_PACKED PaddedSevHashTable { + SevHashTable ht; + uint8_t padding[ROUND_UP(sizeof(SevHashTable), 16) - sizeof(SevHashTable)]; +} PaddedSevHashTable; + +QEMU_BUILD_BUG_ON(sizeof(PaddedSevHashTable) % 16 != 0); + +#define SEV_INFO_BLOCK_GUID "00f771de-1a7e-4fcb-890e-68c77e2fb44e" +typedef struct __attribute__((__packed__)) SevInfoBlock { + /* SEV-ES Reset Vector Address */ + uint32_t reset_addr; +} SevInfoBlock; + +#define SEV_HASH_TABLE_RV_GUID "7255371f-3a3b-4b04-927b-1da6efa8d454" +typedef struct QEMU_PACKED SevHashTableDescriptor { + /* SEV hash table area guest address */ + uint32_t base; + /* SEV hash table area size (in bytes) */ + uint32_t size; +} SevHashTableDescriptor; + +struct SevCommonState { X86ConfidentialGuest parent_obj; int kvm_type; /* configuration parameters */ char *sev_device; - uint32_t policy; - char *dh_cert_file; - char *session_file; uint32_t cbitpos; uint32_t reduced_phys_bits; bool kernel_hashes; - bool legacy_vm_type; /* runtime state */ - uint32_t handle; uint8_t api_major; uint8_t api_minor; uint8_t build_id; int sev_fd; SevState state; - gchar *measurement; uint32_t reset_cs; uint32_t reset_ip; bool reset_data_valid; }; -#define DEFAULT_GUEST_POLICY 0x1 /* disable debug */ -#define DEFAULT_SEV_DEVICE "/dev/sev" +struct SevCommonStateClass { + X86ConfidentialGuestClass parent_class; + + /* public */ + bool (*build_kernel_loader_hashes)(SevCommonState *sev_common, + SevHashTableDescriptor *area, + SevKernelLoaderContext *ctx, + Error **errp); + int (*launch_start)(SevCommonState *sev_common); + void (*launch_finish)(SevCommonState *sev_common); + int (*launch_update_data)(SevCommonState *sev_common, hwaddr gpa, uint8_t *ptr, uint64_t len); + int (*kvm_init)(ConfidentialGuestSupport *cgs, Error **errp); +}; -#define SEV_INFO_BLOCK_GUID "00f771de-1a7e-4fcb-890e-68c77e2fb44e" -typedef struct __attribute__((__packed__)) SevInfoBlock { - /* SEV-ES Reset Vector Address */ - uint32_t reset_addr; -} SevInfoBlock; +/** + * SevGuestState: + * + * The SevGuestState object is used for creating and managing a SEV + * guest. + * + * # $QEMU \ + * -object sev-guest,id=sev0 \ + * -machine ...,memory-encryption=sev0 + */ +struct SevGuestState { + SevCommonState parent_obj; + gchar *measurement; -#define SEV_HASH_TABLE_RV_GUID "7255371f-3a3b-4b04-927b-1da6efa8d454" -typedef struct QEMU_PACKED SevHashTableDescriptor { - /* SEV hash table area guest address */ - uint32_t base; - /* SEV hash table area size (in bytes) */ - uint32_t size; -} SevHashTableDescriptor; + /* configuration parameters */ + uint32_t handle; + uint32_t policy; + char *dh_cert_file; + char *session_file; + bool legacy_vm_type; +}; -/* hard code sha256 digest size */ -#define HASH_SIZE 32 +struct SevSnpGuestState { + SevCommonState parent_obj; -typedef struct QEMU_PACKED SevHashTableEntry { - QemuUUID guid; - uint16_t len; - uint8_t hash[HASH_SIZE]; -} SevHashTableEntry; + /* configuration parameters */ + char *guest_visible_workarounds; + char *id_block; + char *id_auth; + char *host_data; -typedef struct QEMU_PACKED SevHashTable { - QemuUUID guid; - uint16_t len; - SevHashTableEntry cmdline; - SevHashTableEntry initrd; - SevHashTableEntry kernel; -} SevHashTable; + struct kvm_sev_snp_launch_start kvm_start_conf; + struct kvm_sev_snp_launch_finish kvm_finish_conf; -/* - * Data encrypted by sev_encrypt_flash() must be padded to a multiple of - * 16 bytes. - */ -typedef struct QEMU_PACKED PaddedSevHashTable { - SevHashTable ht; - uint8_t padding[ROUND_UP(sizeof(SevHashTable), 16) - sizeof(SevHashTable)]; -} PaddedSevHashTable; + uint32_t kernel_hashes_offset; + PaddedSevHashTable *kernel_hashes_data; +}; -QEMU_BUILD_BUG_ON(sizeof(PaddedSevHashTable) % 16 != 0); +#define DEFAULT_GUEST_POLICY 0x1 /* disable debug */ +#define DEFAULT_SEV_DEVICE "/dev/sev" +#define DEFAULT_SEV_SNP_POLICY 0x30000 + +typedef struct SevLaunchUpdateData { + QTAILQ_ENTRY(SevLaunchUpdateData) next; + hwaddr gpa; + void *hva; + uint64_t len; + int type; +} SevLaunchUpdateData; + +static QTAILQ_HEAD(, SevLaunchUpdateData) launch_update; -static SevGuestState *sev_guest; static Error *sev_mig_blocker; static const char *const sev_fw_errlist[] = { @@ -161,6 +209,36 @@ static const char *const sev_fw_errlist[] = { #define SEV_FW_MAX_ERROR ARRAY_SIZE(sev_fw_errlist) +/* <linux/kvm.h> doesn't expose this, so re-use the max from kvm.c */ +#define KVM_MAX_CPUID_ENTRIES 100 + +typedef struct KvmCpuidInfo { + struct kvm_cpuid2 cpuid; + struct kvm_cpuid_entry2 entries[KVM_MAX_CPUID_ENTRIES]; +} KvmCpuidInfo; + +#define SNP_CPUID_FUNCTION_MAXCOUNT 64 +#define SNP_CPUID_FUNCTION_UNKNOWN 0xFFFFFFFF + +typedef struct { + uint32_t eax_in; + uint32_t ecx_in; + uint64_t xcr0_in; + uint64_t xss_in; + uint32_t eax; + uint32_t ebx; + uint32_t ecx; + uint32_t edx; + uint64_t reserved; +} __attribute__((packed)) SnpCpuidFunc; + +typedef struct { + uint32_t count; + uint32_t reserved1; + uint64_t reserved2; + SnpCpuidFunc entries[SNP_CPUID_FUNCTION_MAXCOUNT]; +} __attribute__((packed)) SnpCpuidInfo; + static int sev_ioctl(int fd, int cmd, void *data, int *error) { @@ -209,21 +287,21 @@ fw_error_to_str(int code) } static bool -sev_check_state(const SevGuestState *sev, SevState state) +sev_check_state(const SevCommonState *sev_common, SevState state) { - assert(sev); - return sev->state == state ? true : false; + assert(sev_common); + return sev_common->state == state ? true : false; } static void -sev_set_guest_state(SevGuestState *sev, SevState new_state) +sev_set_guest_state(SevCommonState *sev_common, SevState new_state) { assert(new_state < SEV_STATE__MAX); - assert(sev); + assert(sev_common); - trace_kvm_sev_change_state(SevState_str(sev->state), + trace_kvm_sev_change_state(SevState_str(sev_common->state), SevState_str(new_state)); - sev->state = new_state; + sev_common->state = new_state; } static void @@ -290,121 +368,72 @@ static struct RAMBlockNotifier sev_ram_notifier = { .ram_block_removed = sev_ram_block_removed, }; -static void -sev_guest_finalize(Object *obj) -{ -} - -static char * -sev_guest_get_session_file(Object *obj, Error **errp) -{ - SevGuestState *s = SEV_GUEST(obj); - - return s->session_file ? g_strdup(s->session_file) : NULL; -} - -static void -sev_guest_set_session_file(Object *obj, const char *value, Error **errp) -{ - SevGuestState *s = SEV_GUEST(obj); - - s->session_file = g_strdup(value); -} - -static char * -sev_guest_get_dh_cert_file(Object *obj, Error **errp) -{ - SevGuestState *s = SEV_GUEST(obj); - - return g_strdup(s->dh_cert_file); -} - -static void -sev_guest_set_dh_cert_file(Object *obj, const char *value, Error **errp) -{ - SevGuestState *s = SEV_GUEST(obj); - - s->dh_cert_file = g_strdup(value); -} - -static char * -sev_guest_get_sev_device(Object *obj, Error **errp) -{ - SevGuestState *sev = SEV_GUEST(obj); - - return g_strdup(sev->sev_device); -} - -static void -sev_guest_set_sev_device(Object *obj, const char *value, Error **errp) -{ - SevGuestState *sev = SEV_GUEST(obj); - - sev->sev_device = g_strdup(value); -} - -static bool sev_guest_get_kernel_hashes(Object *obj, Error **errp) -{ - SevGuestState *sev = SEV_GUEST(obj); - - return sev->kernel_hashes; -} - -static void sev_guest_set_kernel_hashes(Object *obj, bool value, Error **errp) +bool +sev_enabled(void) { - SevGuestState *sev = SEV_GUEST(obj); + ConfidentialGuestSupport *cgs = MACHINE(qdev_get_machine())->cgs; - sev->kernel_hashes = value; -} - -static bool sev_guest_get_legacy_vm_type(Object *obj, Error **errp) -{ - return SEV_GUEST(obj)->legacy_vm_type; -} - -static void sev_guest_set_legacy_vm_type(Object *obj, bool value, Error **errp) -{ - SEV_GUEST(obj)->legacy_vm_type = value; + return !!object_dynamic_cast(OBJECT(cgs), TYPE_SEV_COMMON); } bool -sev_enabled(void) +sev_snp_enabled(void) { - return !!sev_guest; + ConfidentialGuestSupport *cgs = MACHINE(qdev_get_machine())->cgs; + + return !!object_dynamic_cast(OBJECT(cgs), TYPE_SEV_SNP_GUEST); } bool sev_es_enabled(void) { - return sev_enabled() && (sev_guest->policy & SEV_POLICY_ES); + ConfidentialGuestSupport *cgs = MACHINE(qdev_get_machine())->cgs; + + return sev_snp_enabled() || + (sev_enabled() && SEV_GUEST(cgs)->policy & SEV_POLICY_ES); } uint32_t sev_get_cbit_position(void) { - return sev_guest ? sev_guest->cbitpos : 0; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); + + return sev_common ? sev_common->cbitpos : 0; } uint32_t sev_get_reduced_phys_bits(void) { - return sev_guest ? sev_guest->reduced_phys_bits : 0; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); + + return sev_common ? sev_common->reduced_phys_bits : 0; } static SevInfo *sev_get_info(void) { SevInfo *info; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); info = g_new0(SevInfo, 1); info->enabled = sev_enabled(); if (info->enabled) { - info->api_major = sev_guest->api_major; - info->api_minor = sev_guest->api_minor; - info->build_id = sev_guest->build_id; - info->policy = sev_guest->policy; - info->state = sev_guest->state; - info->handle = sev_guest->handle; + info->api_major = sev_common->api_major; + info->api_minor = sev_common->api_minor; + info->build_id = sev_common->build_id; + info->state = sev_common->state; + + if (sev_snp_enabled()) { + info->sev_type = SEV_GUEST_TYPE_SEV_SNP; + info->u.sev_snp.snp_policy = + object_property_get_uint(OBJECT(sev_common), "policy", NULL); + } else { + info->sev_type = SEV_GUEST_TYPE_SEV; + info->u.sev.handle = SEV_GUEST(sev_common)->handle; + info->u.sev.policy = + (uint32_t)object_property_get_uint(OBJECT(sev_common), + "policy", NULL); + } } return info; @@ -427,20 +456,33 @@ void hmp_info_sev(Monitor *mon, const QDict *qdict) { SevInfo *info = sev_get_info(); - if (info && info->enabled) { - monitor_printf(mon, "handle: %d\n", info->handle); - monitor_printf(mon, "state: %s\n", SevState_str(info->state)); - monitor_printf(mon, "build: %d\n", info->build_id); - monitor_printf(mon, "api version: %d.%d\n", - info->api_major, info->api_minor); + if (!info || !info->enabled) { + monitor_printf(mon, "SEV is not enabled\n"); + goto out; + } + + monitor_printf(mon, "SEV type: %s\n", SevGuestType_str(info->sev_type)); + monitor_printf(mon, "state: %s\n", SevState_str(info->state)); + monitor_printf(mon, "build: %d\n", info->build_id); + monitor_printf(mon, "api version: %d.%d\n", info->api_major, + info->api_minor); + + if (sev_snp_enabled()) { monitor_printf(mon, "debug: %s\n", - info->policy & SEV_POLICY_NODBG ? "off" : "on"); - monitor_printf(mon, "key-sharing: %s\n", - info->policy & SEV_POLICY_NOKS ? "off" : "on"); + info->u.sev_snp.snp_policy & SEV_SNP_POLICY_DBG ? "on" + : "off"); + monitor_printf(mon, "SMT allowed: %s\n", + info->u.sev_snp.snp_policy & SEV_SNP_POLICY_SMT ? "on" + : "off"); } else { - monitor_printf(mon, "SEV is not enabled\n"); + monitor_printf(mon, "handle: %d\n", info->u.sev.handle); + monitor_printf(mon, "debug: %s\n", + info->u.sev.policy & SEV_POLICY_NODBG ? "off" : "on"); + monitor_printf(mon, "key-sharing: %s\n", + info->u.sev.policy & SEV_POLICY_NOKS ? "off" : "on"); } +out: qapi_free_SevInfo(info); } @@ -530,6 +572,8 @@ static SevCapability *sev_get_capabilities(Error **errp) size_t pdh_len = 0, cert_chain_len = 0, cpu0_id_len = 0; uint32_t ebx; int fd; + SevCommonState *sev_common; + char *sev_device; if (!kvm_enabled()) { error_setg(errp, "KVM not enabled"); @@ -540,12 +584,21 @@ static SevCapability *sev_get_capabilities(Error **errp) return NULL; } - fd = open(DEFAULT_SEV_DEVICE, O_RDWR); + sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); + if (!sev_common) { + error_setg(errp, "SEV is not configured"); + } + + sev_device = object_property_get_str(OBJECT(sev_common), "sev-device", + &error_abort); + fd = open(sev_device, O_RDWR); if (fd < 0) { error_setg_errno(errp, errno, "SEV: Failed to open %s", DEFAULT_SEV_DEVICE); + g_free(sev_device); return NULL; } + g_free(sev_device); if (sev_get_pdh_info(fd, &pdh_data, &pdh_len, &cert_chain_data, &cert_chain_len, errp)) { @@ -583,12 +636,44 @@ SevCapability *qmp_query_sev_capabilities(Error **errp) return sev_get_capabilities(errp); } +static OvmfSevMetadata *ovmf_sev_metadata_table; + +#define OVMF_SEV_META_DATA_GUID "dc886566-984a-4798-A75e-5585a7bf67cc" +typedef struct __attribute__((__packed__)) OvmfSevMetadataOffset { + uint32_t offset; +} OvmfSevMetadataOffset; + +OvmfSevMetadata *pc_system_get_ovmf_sev_metadata_ptr(void) +{ + return ovmf_sev_metadata_table; +} + +void pc_system_parse_sev_metadata(uint8_t *flash_ptr, size_t flash_size) +{ + OvmfSevMetadata *metadata; + OvmfSevMetadataOffset *data; + + if (!pc_system_ovmf_table_find(OVMF_SEV_META_DATA_GUID, (uint8_t **)&data, + NULL)) { + return; + } + + metadata = (OvmfSevMetadata *)(flash_ptr + flash_size - data->offset); + if (memcmp(metadata->signature, "ASEV", 4) != 0 || + metadata->len < sizeof(OvmfSevMetadata) || + metadata->len > flash_size - data->offset) { + return; + } + + ovmf_sev_metadata_table = g_memdup2(metadata, metadata->len); +} + static SevAttestationReport *sev_get_attestation_report(const char *mnonce, Error **errp) { struct kvm_sev_attestation_report input = {}; SevAttestationReport *report = NULL; - SevGuestState *sev = sev_guest; + SevCommonState *sev_common; g_autofree guchar *data = NULL; g_autofree guchar *buf = NULL; gsize len; @@ -613,8 +698,10 @@ static SevAttestationReport *sev_get_attestation_report(const char *mnonce, return NULL; } + sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); + /* Query the report length */ - ret = sev_ioctl(sev->sev_fd, KVM_SEV_GET_ATTESTATION_REPORT, + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_GET_ATTESTATION_REPORT, &input, &err); if (ret < 0) { if (err != SEV_RET_INVALID_LEN) { @@ -630,7 +717,7 @@ static SevAttestationReport *sev_get_attestation_report(const char *mnonce, memcpy(input.mnonce, buf, sizeof(input.mnonce)); /* Query the report */ - ret = sev_ioctl(sev->sev_fd, KVM_SEV_GET_ATTESTATION_REPORT, + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_GET_ATTESTATION_REPORT, &input, &err); if (ret) { error_setg_errno(errp, errno, "SEV: Failed to get attestation report" @@ -670,26 +757,56 @@ sev_read_file_base64(const char *filename, guchar **data, gsize *len) } static int -sev_launch_start(SevGuestState *sev) +sev_snp_launch_start(SevCommonState *sev_common) +{ + int fw_error, rc; + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(sev_common); + struct kvm_sev_snp_launch_start *start = &sev_snp_guest->kvm_start_conf; + + trace_kvm_sev_snp_launch_start(start->policy, + sev_snp_guest->guest_visible_workarounds); + + if (!kvm_enable_hypercall(BIT_ULL(KVM_HC_MAP_GPA_RANGE))) { + return 1; + } + + rc = sev_ioctl(sev_common->sev_fd, KVM_SEV_SNP_LAUNCH_START, + start, &fw_error); + if (rc < 0) { + error_report("%s: SNP_LAUNCH_START ret=%d fw_error=%d '%s'", + __func__, rc, fw_error, fw_error_to_str(fw_error)); + return 1; + } + + QTAILQ_INIT(&launch_update); + + sev_set_guest_state(sev_common, SEV_STATE_LAUNCH_UPDATE); + + return 0; +} + +static int +sev_launch_start(SevCommonState *sev_common) { gsize sz; int ret = 1; int fw_error, rc; + SevGuestState *sev_guest = SEV_GUEST(sev_common); struct kvm_sev_launch_start start = { - .handle = sev->handle, .policy = sev->policy + .handle = sev_guest->handle, .policy = sev_guest->policy }; guchar *session = NULL, *dh_cert = NULL; - if (sev->session_file) { - if (sev_read_file_base64(sev->session_file, &session, &sz) < 0) { + if (sev_guest->session_file) { + if (sev_read_file_base64(sev_guest->session_file, &session, &sz) < 0) { goto out; } start.session_uaddr = (unsigned long)session; start.session_len = sz; } - if (sev->dh_cert_file) { - if (sev_read_file_base64(sev->dh_cert_file, &dh_cert, &sz) < 0) { + if (sev_guest->dh_cert_file) { + if (sev_read_file_base64(sev_guest->dh_cert_file, &dh_cert, &sz) < 0) { goto out; } start.dh_uaddr = (unsigned long)dh_cert; @@ -697,15 +814,15 @@ sev_launch_start(SevGuestState *sev) } trace_kvm_sev_launch_start(start.policy, session, dh_cert); - rc = sev_ioctl(sev->sev_fd, KVM_SEV_LAUNCH_START, &start, &fw_error); + rc = sev_ioctl(sev_common->sev_fd, KVM_SEV_LAUNCH_START, &start, &fw_error); if (rc < 0) { error_report("%s: LAUNCH_START ret=%d fw_error=%d '%s'", __func__, ret, fw_error, fw_error_to_str(fw_error)); goto out; } - sev_set_guest_state(sev, SEV_STATE_LAUNCH_UPDATE); - sev->handle = start.handle; + sev_set_guest_state(sev_common, SEV_STATE_LAUNCH_UPDATE); + sev_guest->handle = start.handle; ret = 0; out: @@ -714,8 +831,118 @@ out: return ret; } +static void +sev_snp_cpuid_report_mismatches(SnpCpuidInfo *old, + SnpCpuidInfo *new) +{ + size_t i; + + if (old->count != new->count) { + error_report("SEV-SNP: CPUID validation failed due to count mismatch," + "provided: %d, expected: %d", old->count, new->count); + return; + } + + for (i = 0; i < old->count; i++) { + SnpCpuidFunc *old_func, *new_func; + + old_func = &old->entries[i]; + new_func = &new->entries[i]; + + if (memcmp(old_func, new_func, sizeof(SnpCpuidFunc))) { + error_report("SEV-SNP: CPUID validation failed for function 0x%x, index: 0x%x" + "provided: eax:0x%08x, ebx: 0x%08x, ecx: 0x%08x, edx: 0x%08x" + "expected: eax:0x%08x, ebx: 0x%08x, ecx: 0x%08x, edx: 0x%08x", + old_func->eax_in, old_func->ecx_in, + old_func->eax, old_func->ebx, old_func->ecx, old_func->edx, + new_func->eax, new_func->ebx, new_func->ecx, new_func->edx); + } + } +} + +static const char * +snp_page_type_to_str(int type) +{ + switch (type) { + case KVM_SEV_SNP_PAGE_TYPE_NORMAL: return "Normal"; + case KVM_SEV_SNP_PAGE_TYPE_ZERO: return "Zero"; + case KVM_SEV_SNP_PAGE_TYPE_UNMEASURED: return "Unmeasured"; + case KVM_SEV_SNP_PAGE_TYPE_SECRETS: return "Secrets"; + case KVM_SEV_SNP_PAGE_TYPE_CPUID: return "Cpuid"; + default: return "unknown"; + } +} + +static int +sev_snp_launch_update(SevSnpGuestState *sev_snp_guest, + SevLaunchUpdateData *data) +{ + int ret, fw_error; + SnpCpuidInfo snp_cpuid_info; + struct kvm_sev_snp_launch_update update = {0}; + + if (!data->hva || !data->len) { + error_report("SNP_LAUNCH_UPDATE called with invalid address" + "/ length: %p / %lx", + data->hva, data->len); + return 1; + } + + if (data->type == KVM_SEV_SNP_PAGE_TYPE_CPUID) { + /* Save a copy for comparison in case the LAUNCH_UPDATE fails */ + memcpy(&snp_cpuid_info, data->hva, sizeof(snp_cpuid_info)); + } + + update.uaddr = (__u64)(unsigned long)data->hva; + update.gfn_start = data->gpa >> TARGET_PAGE_BITS; + update.len = data->len; + update.type = data->type; + + /* + * KVM_SEV_SNP_LAUNCH_UPDATE requires that GPA ranges have the private + * memory attribute set in advance. + */ + ret = kvm_set_memory_attributes_private(data->gpa, data->len); + if (ret) { + error_report("SEV-SNP: failed to configure initial" + "private guest memory"); + goto out; + } + + while (update.len || ret == -EAGAIN) { + trace_kvm_sev_snp_launch_update(update.uaddr, update.gfn_start << + TARGET_PAGE_BITS, update.len, + snp_page_type_to_str(update.type)); + + ret = sev_ioctl(SEV_COMMON(sev_snp_guest)->sev_fd, + KVM_SEV_SNP_LAUNCH_UPDATE, + &update, &fw_error); + if (ret && ret != -EAGAIN) { + error_report("SNP_LAUNCH_UPDATE ret=%d fw_error=%d '%s'", + ret, fw_error, fw_error_to_str(fw_error)); + + if (data->type == KVM_SEV_SNP_PAGE_TYPE_CPUID) { + sev_snp_cpuid_report_mismatches(&snp_cpuid_info, data->hva); + error_report("SEV-SNP: failed update CPUID page"); + } + break; + } + } + +out: + if (!ret && update.gfn_start << TARGET_PAGE_BITS != data->gpa + data->len) { + error_report("SEV-SNP: expected update of GPA range %lx-%lx," + "got GPA range %lx-%llx", + data->gpa, data->gpa + data->len, data->gpa, + update.gfn_start << TARGET_PAGE_BITS); + ret = -EIO; + } + + return ret; +} + static int -sev_launch_update_data(SevGuestState *sev, uint8_t *addr, uint64_t len) +sev_launch_update_data(SevCommonState *sev_common, hwaddr gpa, uint8_t *addr, uint64_t len) { int ret, fw_error; struct kvm_sev_launch_update_data update; @@ -727,7 +954,7 @@ sev_launch_update_data(SevGuestState *sev, uint8_t *addr, uint64_t len) update.uaddr = (uintptr_t)addr; update.len = len; trace_kvm_sev_launch_update_data(addr, len); - ret = sev_ioctl(sev->sev_fd, KVM_SEV_LAUNCH_UPDATE_DATA, + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_LAUNCH_UPDATE_DATA, &update, &fw_error); if (ret) { error_report("%s: LAUNCH_UPDATE ret=%d fw_error=%d '%s'", @@ -738,11 +965,12 @@ sev_launch_update_data(SevGuestState *sev, uint8_t *addr, uint64_t len) } static int -sev_launch_update_vmsa(SevGuestState *sev) +sev_launch_update_vmsa(SevGuestState *sev_guest) { int ret, fw_error; - ret = sev_ioctl(sev->sev_fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL, &fw_error); + ret = sev_ioctl(SEV_COMMON(sev_guest)->sev_fd, KVM_SEV_LAUNCH_UPDATE_VMSA, + NULL, &fw_error); if (ret) { error_report("%s: LAUNCH_UPDATE_VMSA ret=%d fw_error=%d '%s'", __func__, ret, fw_error, fw_error_to_str(fw_error)); @@ -754,18 +982,19 @@ sev_launch_update_vmsa(SevGuestState *sev) static void sev_launch_get_measure(Notifier *notifier, void *unused) { - SevGuestState *sev = sev_guest; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); + SevGuestState *sev_guest = SEV_GUEST(sev_common); int ret, error; g_autofree guchar *data = NULL; struct kvm_sev_launch_measure measurement = {}; - if (!sev_check_state(sev, SEV_STATE_LAUNCH_UPDATE)) { + if (!sev_check_state(sev_common, SEV_STATE_LAUNCH_UPDATE)) { return; } if (sev_es_enabled()) { /* measure all the VM save areas before getting launch_measure */ - ret = sev_launch_update_vmsa(sev); + ret = sev_launch_update_vmsa(sev_guest); if (ret) { exit(1); } @@ -773,7 +1002,7 @@ sev_launch_get_measure(Notifier *notifier, void *unused) } /* query the measurement blob length */ - ret = sev_ioctl(sev->sev_fd, KVM_SEV_LAUNCH_MEASURE, + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_LAUNCH_MEASURE, &measurement, &error); if (!measurement.len) { error_report("%s: LAUNCH_MEASURE ret=%d fw_error=%d '%s'", @@ -785,7 +1014,7 @@ sev_launch_get_measure(Notifier *notifier, void *unused) measurement.uaddr = (unsigned long)data; /* get the measurement blob */ - ret = sev_ioctl(sev->sev_fd, KVM_SEV_LAUNCH_MEASURE, + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_LAUNCH_MEASURE, &measurement, &error); if (ret) { error_report("%s: LAUNCH_MEASURE ret=%d fw_error=%d '%s'", @@ -793,17 +1022,21 @@ sev_launch_get_measure(Notifier *notifier, void *unused) return; } - sev_set_guest_state(sev, SEV_STATE_LAUNCH_SECRET); + sev_set_guest_state(sev_common, SEV_STATE_LAUNCH_SECRET); /* encode the measurement value and emit the event */ - sev->measurement = g_base64_encode(data, measurement.len); - trace_kvm_sev_launch_measurement(sev->measurement); + sev_guest->measurement = g_base64_encode(data, measurement.len); + trace_kvm_sev_launch_measurement(sev_guest->measurement); } static char *sev_get_launch_measurement(void) { + ConfidentialGuestSupport *cgs = MACHINE(qdev_get_machine())->cgs; + SevGuestState *sev_guest = + (SevGuestState *)object_dynamic_cast(OBJECT(cgs), TYPE_SEV_GUEST); + if (sev_guest && - sev_guest->state >= SEV_STATE_LAUNCH_SECRET) { + SEV_COMMON(sev_guest)->state >= SEV_STATE_LAUNCH_SECRET) { return g_strdup(sev_guest->measurement); } @@ -832,19 +1065,20 @@ static Notifier sev_machine_done_notify = { }; static void -sev_launch_finish(SevGuestState *sev) +sev_launch_finish(SevCommonState *sev_common) { int ret, error; trace_kvm_sev_launch_finish(); - ret = sev_ioctl(sev->sev_fd, KVM_SEV_LAUNCH_FINISH, 0, &error); + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_LAUNCH_FINISH, 0, + &error); if (ret) { error_report("%s: LAUNCH_FINISH ret=%d fw_error=%d '%s'", __func__, ret, error, fw_error_to_str(error)); exit(1); } - sev_set_guest_state(sev, SEV_STATE_RUNNING); + sev_set_guest_state(sev_common, SEV_STATE_RUNNING); /* add migration blocker */ error_setg(&sev_mig_blocker, @@ -852,55 +1086,293 @@ sev_launch_finish(SevGuestState *sev) migrate_add_blocker(&sev_mig_blocker, &error_fatal); } +static int +snp_launch_update_data(uint64_t gpa, void *hva, + uint32_t len, int type) +{ + SevLaunchUpdateData *data; + + data = g_new0(SevLaunchUpdateData, 1); + data->gpa = gpa; + data->hva = hva; + data->len = len; + data->type = type; + + QTAILQ_INSERT_TAIL(&launch_update, data, next); + + return 0; +} + +static int +sev_snp_launch_update_data(SevCommonState *sev_common, hwaddr gpa, + uint8_t *ptr, uint64_t len) +{ + int ret = snp_launch_update_data(gpa, ptr, len, + KVM_SEV_SNP_PAGE_TYPE_NORMAL); + return ret; +} + +static int +sev_snp_cpuid_info_fill(SnpCpuidInfo *snp_cpuid_info, + const KvmCpuidInfo *kvm_cpuid_info) +{ + size_t i; + + if (kvm_cpuid_info->cpuid.nent > SNP_CPUID_FUNCTION_MAXCOUNT) { + error_report("SEV-SNP: CPUID entry count (%d) exceeds max (%d)", + kvm_cpuid_info->cpuid.nent, SNP_CPUID_FUNCTION_MAXCOUNT); + return -1; + } + + memset(snp_cpuid_info, 0, sizeof(*snp_cpuid_info)); + + for (i = 0; i < kvm_cpuid_info->cpuid.nent; i++) { + const struct kvm_cpuid_entry2 *kvm_cpuid_entry; + SnpCpuidFunc *snp_cpuid_entry; + + kvm_cpuid_entry = &kvm_cpuid_info->entries[i]; + snp_cpuid_entry = &snp_cpuid_info->entries[i]; + + snp_cpuid_entry->eax_in = kvm_cpuid_entry->function; + if (kvm_cpuid_entry->flags == KVM_CPUID_FLAG_SIGNIFCANT_INDEX) { + snp_cpuid_entry->ecx_in = kvm_cpuid_entry->index; + } + snp_cpuid_entry->eax = kvm_cpuid_entry->eax; + snp_cpuid_entry->ebx = kvm_cpuid_entry->ebx; + snp_cpuid_entry->ecx = kvm_cpuid_entry->ecx; + snp_cpuid_entry->edx = kvm_cpuid_entry->edx; + + /* + * Guest kernels will calculate EBX themselves using the 0xD + * subfunctions corresponding to the individual XSAVE areas, so only + * encode the base XSAVE size in the initial leaves, corresponding + * to the initial XCR0=1 state. + */ + if (snp_cpuid_entry->eax_in == 0xD && + (snp_cpuid_entry->ecx_in == 0x0 || snp_cpuid_entry->ecx_in == 0x1)) { + snp_cpuid_entry->ebx = 0x240; + snp_cpuid_entry->xcr0_in = 1; + snp_cpuid_entry->xss_in = 0; + } + } + + snp_cpuid_info->count = i; + + return 0; +} + +static int +snp_launch_update_cpuid(uint32_t cpuid_addr, void *hva, uint32_t cpuid_len) +{ + KvmCpuidInfo kvm_cpuid_info = {0}; + SnpCpuidInfo snp_cpuid_info; + CPUState *cs = first_cpu; + int ret; + uint32_t i = 0; + + assert(sizeof(snp_cpuid_info) <= cpuid_len); + + /* get the cpuid list from KVM */ + do { + kvm_cpuid_info.cpuid.nent = ++i; + ret = kvm_vcpu_ioctl(cs, KVM_GET_CPUID2, &kvm_cpuid_info); + } while (ret == -E2BIG); + + if (ret) { + error_report("SEV-SNP: unable to query CPUID values for CPU: '%s'", + strerror(-ret)); + return 1; + } + + ret = sev_snp_cpuid_info_fill(&snp_cpuid_info, &kvm_cpuid_info); + if (ret) { + error_report("SEV-SNP: failed to generate CPUID table information"); + return 1; + } + + memcpy(hva, &snp_cpuid_info, sizeof(snp_cpuid_info)); + + return snp_launch_update_data(cpuid_addr, hva, cpuid_len, + KVM_SEV_SNP_PAGE_TYPE_CPUID); +} + +static int +snp_launch_update_kernel_hashes(SevSnpGuestState *sev_snp, uint32_t addr, + void *hva, uint32_t len) +{ + int type = KVM_SEV_SNP_PAGE_TYPE_ZERO; + if (sev_snp->parent_obj.kernel_hashes) { + assert(sev_snp->kernel_hashes_data); + assert((sev_snp->kernel_hashes_offset + + sizeof(*sev_snp->kernel_hashes_data)) <= len); + memset(hva, 0, len); + memcpy(hva + sev_snp->kernel_hashes_offset, sev_snp->kernel_hashes_data, + sizeof(*sev_snp->kernel_hashes_data)); + type = KVM_SEV_SNP_PAGE_TYPE_NORMAL; + } + return snp_launch_update_data(addr, hva, len, type); +} + +static int +snp_metadata_desc_to_page_type(int desc_type) +{ + switch (desc_type) { + /* Add the umeasured prevalidated pages as a zero page */ + case SEV_DESC_TYPE_SNP_SEC_MEM: return KVM_SEV_SNP_PAGE_TYPE_ZERO; + case SEV_DESC_TYPE_SNP_SECRETS: return KVM_SEV_SNP_PAGE_TYPE_SECRETS; + case SEV_DESC_TYPE_CPUID: return KVM_SEV_SNP_PAGE_TYPE_CPUID; + default: + return KVM_SEV_SNP_PAGE_TYPE_ZERO; + } +} + +static void +snp_populate_metadata_pages(SevSnpGuestState *sev_snp, + OvmfSevMetadata *metadata) +{ + OvmfSevMetadataDesc *desc; + int type, ret, i; + void *hva; + MemoryRegion *mr = NULL; + + for (i = 0; i < metadata->num_desc; i++) { + desc = &metadata->descs[i]; + + type = snp_metadata_desc_to_page_type(desc->type); + + hva = gpa2hva(&mr, desc->base, desc->len, NULL); + if (!hva) { + error_report("%s: Failed to get HVA for GPA 0x%x sz 0x%x", + __func__, desc->base, desc->len); + exit(1); + } + + if (type == KVM_SEV_SNP_PAGE_TYPE_CPUID) { + ret = snp_launch_update_cpuid(desc->base, hva, desc->len); + } else if (desc->type == SEV_DESC_TYPE_SNP_KERNEL_HASHES) { + ret = snp_launch_update_kernel_hashes(sev_snp, desc->base, hva, + desc->len); + } else { + ret = snp_launch_update_data(desc->base, hva, desc->len, type); + } + + if (ret) { + error_report("%s: Failed to add metadata page gpa 0x%x+%x type %d", + __func__, desc->base, desc->len, desc->type); + exit(1); + } + } +} + +static void +sev_snp_launch_finish(SevCommonState *sev_common) +{ + int ret, error; + Error *local_err = NULL; + OvmfSevMetadata *metadata; + SevLaunchUpdateData *data; + SevSnpGuestState *sev_snp = SEV_SNP_GUEST(sev_common); + struct kvm_sev_snp_launch_finish *finish = &sev_snp->kvm_finish_conf; + + /* + * To boot the SNP guest, the hypervisor is required to populate the CPUID + * and Secrets page before finalizing the launch flow. The location of + * the secrets and CPUID page is available through the OVMF metadata GUID. + */ + metadata = pc_system_get_ovmf_sev_metadata_ptr(); + if (metadata == NULL) { + error_report("%s: Failed to locate SEV metadata header", __func__); + exit(1); + } + + /* Populate all the metadata pages */ + snp_populate_metadata_pages(sev_snp, metadata); + + QTAILQ_FOREACH(data, &launch_update, next) { + ret = sev_snp_launch_update(sev_snp, data); + if (ret) { + exit(1); + } + } + + trace_kvm_sev_snp_launch_finish(sev_snp->id_block, sev_snp->id_auth, + sev_snp->host_data); + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_SNP_LAUNCH_FINISH, + finish, &error); + if (ret) { + error_report("SNP_LAUNCH_FINISH ret=%d fw_error=%d '%s'", + ret, error, fw_error_to_str(error)); + exit(1); + } + + kvm_mark_guest_state_protected(); + sev_set_guest_state(sev_common, SEV_STATE_RUNNING); + + /* add migration blocker */ + error_setg(&sev_mig_blocker, + "SEV-SNP: Migration is not implemented"); + ret = migrate_add_blocker(&sev_mig_blocker, &local_err); + if (local_err) { + error_report_err(local_err); + error_free(sev_mig_blocker); + exit(1); + } +} + + static void sev_vm_state_change(void *opaque, bool running, RunState state) { - SevGuestState *sev = opaque; + SevCommonState *sev_common = opaque; + SevCommonStateClass *klass = SEV_COMMON_GET_CLASS(opaque); if (running) { - if (!sev_check_state(sev, SEV_STATE_RUNNING)) { - sev_launch_finish(sev); + if (!sev_check_state(sev_common, SEV_STATE_RUNNING)) { + klass->launch_finish(sev_common); } } } static int sev_kvm_type(X86ConfidentialGuest *cg) { - SevGuestState *sev = SEV_GUEST(cg); + SevCommonState *sev_common = SEV_COMMON(cg); + SevGuestState *sev_guest = SEV_GUEST(sev_common); int kvm_type; - if (sev->kvm_type != -1) { + if (sev_common->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; + kvm_type = (sev_guest->policy & SEV_POLICY_ES) ? + KVM_X86_SEV_ES_VM : KVM_X86_SEV_VM; + if (kvm_is_vm_type_supported(kvm_type) && !sev_guest->legacy_vm_type) { + sev_common->kvm_type = kvm_type; } else { - sev->kvm_type = KVM_X86_DEFAULT_VM; + sev_common->kvm_type = KVM_X86_DEFAULT_VM; } out: - return sev->kvm_type; + return sev_common->kvm_type; } -static int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) +static int sev_snp_kvm_type(X86ConfidentialGuest *cg) +{ + return KVM_X86_SNP_VM; +} + +static int sev_common_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 = {}; + SevCommonState *sev_common = SEV_COMMON(cgs); + SevCommonStateClass *klass = SEV_COMMON_GET_CLASS(cgs); + X86ConfidentialGuestClass *x86_klass = + X86_CONFIDENTIAL_GUEST_GET_CLASS(cgs); - ret = ram_block_discard_disable(true); - if (ret) { - error_report("%s: cannot disable RAM discard", __func__); - return -1; - } - - sev_guest = sev; - sev->state = SEV_STATE_UNINIT; + sev_common->state = SEV_STATE_UNINIT; host_cpuid(0x8000001F, 0, NULL, &ebx, NULL, NULL); host_cbitpos = ebx & 0x3f; @@ -910,10 +1382,10 @@ static int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) * register of CPUID 0x8000001F. No need to verify the range as the * comparison against the host value accomplishes that. */ - if (host_cbitpos != sev->cbitpos) { + if (host_cbitpos != sev_common->cbitpos) { error_setg(errp, "%s: cbitpos check failed, host '%d' requested '%d'", - __func__, host_cbitpos, sev->cbitpos); - goto err; + __func__, host_cbitpos, sev_common->cbitpos); + return -1; } /* @@ -921,96 +1393,153 @@ static int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) * the EBX register of CPUID 0x8000001F, so verify the supplied value * is in the range of 1 to 63. */ - if (sev->reduced_phys_bits < 1 || sev->reduced_phys_bits > 63) { + if (sev_common->reduced_phys_bits < 1 || + sev_common->reduced_phys_bits > 63) { error_setg(errp, "%s: reduced_phys_bits check failed," " it should be in the range of 1 to 63, requested '%d'", - __func__, sev->reduced_phys_bits); - goto err; + __func__, sev_common->reduced_phys_bits); + return -1; } - devname = object_property_get_str(OBJECT(sev), "sev-device", NULL); - sev->sev_fd = open(devname, O_RDWR); - if (sev->sev_fd < 0) { + devname = object_property_get_str(OBJECT(sev_common), "sev-device", NULL); + sev_common->sev_fd = open(devname, O_RDWR); + if (sev_common->sev_fd < 0) { error_setg(errp, "%s: Failed to open %s '%s'", __func__, devname, strerror(errno)); g_free(devname); - goto err; + return -1; } g_free(devname); - ret = sev_platform_ioctl(sev->sev_fd, SEV_PLATFORM_STATUS, &status, + ret = sev_platform_ioctl(sev_common->sev_fd, SEV_PLATFORM_STATUS, &status, &fw_error); if (ret) { error_setg(errp, "%s: failed to get platform status ret=%d " "fw_error='%d: %s'", __func__, ret, fw_error, fw_error_to_str(fw_error)); - goto err; + return -1; } - sev->build_id = status.build; - sev->api_major = status.api_major; - sev->api_minor = status.api_minor; + sev_common->build_id = status.build; + sev_common->api_major = status.api_major; + sev_common->api_minor = status.api_minor; if (sev_es_enabled()) { if (!kvm_kernel_irqchip_allowed()) { - error_report("%s: SEV-ES guests require in-kernel irqchip support", - __func__); - goto err; + error_setg(errp, "%s: SEV-ES guests require in-kernel irqchip" + "support", __func__); + return -1; } + } + if (sev_es_enabled() && !sev_snp_enabled()) { if (!(status.flags & SEV_STATUS_FLAGS_CONFIG_ES)) { - error_report("%s: guest policy requires SEV-ES, but " + error_setg(errp, "%s: guest policy requires SEV-ES, but " "host SEV-ES support unavailable", __func__); - goto err; + return -1; } } trace_kvm_sev_init(); - if (sev_kvm_type(X86_CONFIDENTIAL_GUEST(sev)) == KVM_X86_DEFAULT_VM) { + if (x86_klass->kvm_type(X86_CONFIDENTIAL_GUEST(sev_common)) == 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); + ret = sev_ioctl(sev_common->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); + ret = sev_ioctl(sev_common->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)); - goto err; + return -1; } - ret = sev_launch_start(sev); + ret = klass->launch_start(sev_common); + if (ret) { error_setg(errp, "%s: failed to create encryption context", __func__); - goto err; + return -1; + } + + if (klass->kvm_init && klass->kvm_init(cgs, errp)) { + return -1; } + qemu_add_vm_change_state_handler(sev_vm_state_change, sev_common); + + cgs->ready = true; + + return 0; +} + +static int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) +{ + int ret; + + /* + * SEV/SEV-ES rely on pinned memory to back guest RAM so discarding + * isn't actually possible. With SNP, only guest_memfd pages are used + * for private guest memory, so discarding of shared memory is still + * possible.. + */ + ret = ram_block_discard_disable(true); + if (ret) { + error_setg(errp, "%s: cannot disable RAM discard", __func__); + return -1; + } + + /* + * SEV uses these notifiers to register/pin pages prior to guest use, + * but SNP relies on guest_memfd for private pages, which has its + * own internal mechanisms for registering/pinning private memory. + */ ram_block_notifier_add(&sev_ram_notifier); + + /* + * The machine done notify event is used for SEV guests to get the + * measurement of the encrypted images. When SEV-SNP is enabled, the + * measurement is part of the guest attestation process where it can + * be collected without any reliance on the VMM. So skip registering + * the notifier for SNP in favor of using guest attestation instead. + */ qemu_add_machine_init_done_notifier(&sev_machine_done_notify); - qemu_add_vm_change_state_handler(sev_vm_state_change, sev); - cgs->ready = true; + return 0; +} + +static int sev_snp_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + X86MachineState *x86ms = X86_MACHINE(ms); + + if (x86ms->smm == ON_OFF_AUTO_AUTO) { + x86ms->smm = ON_OFF_AUTO_OFF; + } else if (x86ms->smm == ON_OFF_AUTO_ON) { + error_setg(errp, "SEV-SNP does not support SMM."); + return -1; + } return 0; -err: - sev_guest = NULL; - ram_block_discard_disable(false); - return -1; } int -sev_encrypt_flash(uint8_t *ptr, uint64_t len, Error **errp) +sev_encrypt_flash(hwaddr gpa, uint8_t *ptr, uint64_t len, Error **errp) { - if (!sev_guest) { + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); + SevCommonStateClass *klass = SEV_COMMON_GET_CLASS(sev_common); + + if (!sev_common) { return 0; } /* if SEV is in update state then encrypt the data else do nothing */ - if (sev_check_state(sev_guest, SEV_STATE_LAUNCH_UPDATE)) { - int ret = sev_launch_update_data(sev_guest, ptr, len); + if (sev_check_state(sev_common, SEV_STATE_LAUNCH_UPDATE)) { + int ret; + + ret = klass->launch_update_data(sev_common, gpa, ptr, len); if (ret < 0) { error_setg(errp, "SEV: Failed to encrypt pflash rom"); return ret; @@ -1030,16 +1559,17 @@ int sev_inject_launch_secret(const char *packet_hdr, const char *secret, void *hva; gsize hdr_sz = 0, data_sz = 0; MemoryRegion *mr = NULL; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); - if (!sev_guest) { + if (!sev_common) { error_setg(errp, "SEV not enabled for guest"); return 1; } /* secret can be injected only in this state */ - if (!sev_check_state(sev_guest, SEV_STATE_LAUNCH_SECRET)) { + if (!sev_check_state(sev_common, SEV_STATE_LAUNCH_SECRET)) { error_setg(errp, "SEV: Not in correct state. (LSECRET) %x", - sev_guest->state); + sev_common->state); return 1; } @@ -1073,7 +1603,7 @@ int sev_inject_launch_secret(const char *packet_hdr, const char *secret, trace_kvm_sev_launch_secret(gpa, input.guest_uaddr, input.trans_uaddr, input.trans_len); - ret = sev_ioctl(sev_guest->sev_fd, KVM_SEV_LAUNCH_SECRET, + ret = sev_ioctl(sev_common->sev_fd, KVM_SEV_LAUNCH_SECRET, &input, &error); if (ret) { error_setg(errp, "SEV: failed to inject secret ret=%d fw_error=%d '%s'", @@ -1180,9 +1710,10 @@ void sev_es_set_reset_vector(CPUState *cpu) { X86CPU *x86; CPUX86State *env; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); /* Only update if we have valid reset information */ - if (!sev_guest || !sev_guest->reset_data_valid) { + if (!sev_common || !sev_common->reset_data_valid) { return; } @@ -1194,11 +1725,11 @@ void sev_es_set_reset_vector(CPUState *cpu) x86 = X86_CPU(cpu); env = &x86->env; - cpu_x86_load_seg_cache(env, R_CS, 0xf000, sev_guest->reset_cs, 0xffff, + cpu_x86_load_seg_cache(env, R_CS, 0xf000, sev_common->reset_cs, 0xffff, DESC_P_MASK | DESC_S_MASK | DESC_CS_MASK | DESC_R_MASK | DESC_A_MASK); - env->eip = sev_guest->reset_ip; + env->eip = sev_common->reset_ip; } int sev_es_save_reset_vector(void *flash_ptr, uint64_t flash_size) @@ -1206,6 +1737,7 @@ int sev_es_save_reset_vector(void *flash_ptr, uint64_t flash_size) CPUState *cpu; uint32_t addr; int ret; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); if (!sev_es_enabled()) { return 0; @@ -1219,9 +1751,9 @@ int sev_es_save_reset_vector(void *flash_ptr, uint64_t flash_size) } if (addr) { - sev_guest->reset_cs = addr & 0xffff0000; - sev_guest->reset_ip = addr & 0x0000ffff; - sev_guest->reset_data_valid = true; + sev_common->reset_cs = addr & 0xffff0000; + sev_common->reset_ip = addr & 0x0000ffff; + sev_common->reset_data_valid = true; CPU_FOREACH(cpu) { sev_es_set_reset_vector(cpu); @@ -1249,44 +1781,16 @@ static const QemuUUID sev_cmdline_entry_guid = { 0x4d, 0x36, 0xab, 0x2a) }; -/* - * Add the hashes of the linux kernel/initrd/cmdline to an encrypted guest page - * which is included in SEV's initial memory measurement. - */ -bool sev_add_kernel_loader_hashes(SevKernelLoaderContext *ctx, Error **errp) +static bool build_kernel_loader_hashes(PaddedSevHashTable *padded_ht, + SevKernelLoaderContext *ctx, + Error **errp) { - uint8_t *data; - SevHashTableDescriptor *area; SevHashTable *ht; - PaddedSevHashTable *padded_ht; uint8_t cmdline_hash[HASH_SIZE]; uint8_t initrd_hash[HASH_SIZE]; uint8_t kernel_hash[HASH_SIZE]; uint8_t *hashp; size_t hash_len = HASH_SIZE; - hwaddr mapped_len = sizeof(*padded_ht); - MemTxAttrs attrs = { 0 }; - bool ret = true; - - /* - * Only add the kernel hashes if the sev-guest configuration explicitly - * stated kernel-hashes=on. - */ - if (!sev_guest->kernel_hashes) { - return false; - } - - if (!pc_system_ovmf_table_find(SEV_HASH_TABLE_RV_GUID, &data, NULL)) { - error_setg(errp, "SEV: kernel specified but guest firmware " - "has no hashes table GUID"); - return false; - } - area = (SevHashTableDescriptor *)data; - if (!area->base || area->size < sizeof(PaddedSevHashTable)) { - error_setg(errp, "SEV: guest firmware hashes table area is invalid " - "(base=0x%x size=0x%x)", area->base, area->size); - return false; - } /* * Calculate hash of kernel command-line with the terminating null byte. If @@ -1323,16 +1827,6 @@ bool sev_add_kernel_loader_hashes(SevKernelLoaderContext *ctx, Error **errp) } assert(hash_len == HASH_SIZE); - /* - * Populate the hashes table in the guest's memory at the OVMF-designated - * area for the SEV hashes table - */ - padded_ht = address_space_map(&address_space_memory, area->base, - &mapped_len, true, attrs); - if (!padded_ht || mapped_len != sizeof(*padded_ht)) { - error_setg(errp, "SEV: cannot map hashes table guest memory area"); - return false; - } ht = &padded_ht->ht; ht->guid = sev_hash_table_header_guid; @@ -1353,7 +1847,52 @@ bool sev_add_kernel_loader_hashes(SevKernelLoaderContext *ctx, Error **errp) /* zero the excess data so the measurement can be reliably calculated */ memset(padded_ht->padding, 0, sizeof(padded_ht->padding)); - if (sev_encrypt_flash((uint8_t *)padded_ht, sizeof(*padded_ht), errp) < 0) { + return true; +} + +static bool sev_snp_build_kernel_loader_hashes(SevCommonState *sev_common, + SevHashTableDescriptor *area, + SevKernelLoaderContext *ctx, + Error **errp) +{ + /* + * SNP: Populate the hashes table in an area that later in + * snp_launch_update_kernel_hashes() will be copied to the guest memory + * and encrypted. + */ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(sev_common); + sev_snp_guest->kernel_hashes_offset = area->base & ~TARGET_PAGE_MASK; + sev_snp_guest->kernel_hashes_data = g_new0(PaddedSevHashTable, 1); + return build_kernel_loader_hashes(sev_snp_guest->kernel_hashes_data, ctx, errp); +} + +static bool sev_build_kernel_loader_hashes(SevCommonState *sev_common, + SevHashTableDescriptor *area, + SevKernelLoaderContext *ctx, + Error **errp) +{ + PaddedSevHashTable *padded_ht; + hwaddr mapped_len = sizeof(*padded_ht); + MemTxAttrs attrs = { 0 }; + bool ret = true; + + /* + * Populate the hashes table in the guest's memory at the OVMF-designated + * area for the SEV hashes table + */ + padded_ht = address_space_map(&address_space_memory, area->base, + &mapped_len, true, attrs); + if (!padded_ht || mapped_len != sizeof(*padded_ht)) { + error_setg(errp, "SEV: cannot map hashes table guest memory area"); + return false; + } + + if (build_kernel_loader_hashes(padded_ht, ctx, errp)) { + if (sev_encrypt_flash(area->base, (uint8_t *)padded_ht, + sizeof(*padded_ht), errp) < 0) { + ret = false; + } + } else { ret = false; } @@ -1363,20 +1902,162 @@ bool sev_add_kernel_loader_hashes(SevKernelLoaderContext *ctx, Error **errp) return ret; } +/* + * Add the hashes of the linux kernel/initrd/cmdline to an encrypted guest page + * which is included in SEV's initial memory measurement. + */ +bool sev_add_kernel_loader_hashes(SevKernelLoaderContext *ctx, Error **errp) +{ + uint8_t *data; + SevHashTableDescriptor *area; + SevCommonState *sev_common = SEV_COMMON(MACHINE(qdev_get_machine())->cgs); + SevCommonStateClass *klass = SEV_COMMON_GET_CLASS(sev_common); + + /* + * Only add the kernel hashes if the sev-guest configuration explicitly + * stated kernel-hashes=on. + */ + if (!sev_common->kernel_hashes) { + return false; + } + + if (!pc_system_ovmf_table_find(SEV_HASH_TABLE_RV_GUID, &data, NULL)) { + error_setg(errp, "SEV: kernel specified but guest firmware " + "has no hashes table GUID"); + return false; + } + + area = (SevHashTableDescriptor *)data; + if (!area->base || area->size < sizeof(PaddedSevHashTable)) { + error_setg(errp, "SEV: guest firmware hashes table area is invalid " + "(base=0x%x size=0x%x)", area->base, area->size); + return false; + } + + return klass->build_kernel_loader_hashes(sev_common, area, ctx, errp); +} + +static char * +sev_common_get_sev_device(Object *obj, Error **errp) +{ + return g_strdup(SEV_COMMON(obj)->sev_device); +} + static void -sev_guest_class_init(ObjectClass *oc, void *data) +sev_common_set_sev_device(Object *obj, const char *value, Error **errp) +{ + SEV_COMMON(obj)->sev_device = g_strdup(value); +} + +static bool sev_common_get_kernel_hashes(Object *obj, Error **errp) +{ + return SEV_COMMON(obj)->kernel_hashes; +} + +static void sev_common_set_kernel_hashes(Object *obj, bool value, Error **errp) +{ + SEV_COMMON(obj)->kernel_hashes = value; +} + +static void +sev_common_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; + klass->kvm_init = sev_common_kvm_init; object_class_property_add_str(oc, "sev-device", - sev_guest_get_sev_device, - sev_guest_set_sev_device); + sev_common_get_sev_device, + sev_common_set_sev_device); object_class_property_set_description(oc, "sev-device", "SEV device to use"); + object_class_property_add_bool(oc, "kernel-hashes", + sev_common_get_kernel_hashes, + sev_common_set_kernel_hashes); + object_class_property_set_description(oc, "kernel-hashes", + "add kernel hashes to guest firmware for measured Linux boot"); +} + +static void +sev_common_instance_init(Object *obj) +{ + SevCommonState *sev_common = SEV_COMMON(obj); + + sev_common->kvm_type = -1; + + sev_common->sev_device = g_strdup(DEFAULT_SEV_DEVICE); + + object_property_add_uint32_ptr(obj, "cbitpos", &sev_common->cbitpos, + OBJ_PROP_FLAG_READWRITE); + object_property_add_uint32_ptr(obj, "reduced-phys-bits", + &sev_common->reduced_phys_bits, + OBJ_PROP_FLAG_READWRITE); +} + +/* sev guest info common to sev/sev-es/sev-snp */ +static const TypeInfo sev_common_info = { + .parent = TYPE_X86_CONFIDENTIAL_GUEST, + .name = TYPE_SEV_COMMON, + .instance_size = sizeof(SevCommonState), + .instance_init = sev_common_instance_init, + .class_size = sizeof(SevCommonStateClass), + .class_init = sev_common_class_init, + .abstract = true, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static char * +sev_guest_get_dh_cert_file(Object *obj, Error **errp) +{ + return g_strdup(SEV_GUEST(obj)->dh_cert_file); +} + +static void +sev_guest_set_dh_cert_file(Object *obj, const char *value, Error **errp) +{ + SEV_GUEST(obj)->dh_cert_file = g_strdup(value); +} + +static char * +sev_guest_get_session_file(Object *obj, Error **errp) +{ + SevGuestState *sev_guest = SEV_GUEST(obj); + + return sev_guest->session_file ? g_strdup(sev_guest->session_file) : NULL; +} + +static void +sev_guest_set_session_file(Object *obj, const char *value, Error **errp) +{ + SEV_GUEST(obj)->session_file = g_strdup(value); +} + +static bool sev_guest_get_legacy_vm_type(Object *obj, Error **errp) +{ + return SEV_GUEST(obj)->legacy_vm_type; +} + +static void sev_guest_set_legacy_vm_type(Object *obj, bool value, Error **errp) +{ + SEV_GUEST(obj)->legacy_vm_type = value; +} + +static void +sev_guest_class_init(ObjectClass *oc, void *data) +{ + SevCommonStateClass *klass = SEV_COMMON_CLASS(oc); + X86ConfidentialGuestClass *x86_klass = X86_CONFIDENTIAL_GUEST_CLASS(oc); + + klass->build_kernel_loader_hashes = sev_build_kernel_loader_hashes; + klass->launch_start = sev_launch_start; + klass->launch_finish = sev_launch_finish; + klass->launch_update_data = sev_launch_update_data; + klass->kvm_init = sev_kvm_init; + x86_klass->kvm_type = sev_kvm_type; + object_class_property_add_str(oc, "dh-cert-file", sev_guest_get_dh_cert_file, sev_guest_set_dh_cert_file); @@ -1387,11 +2068,6 @@ sev_guest_class_init(ObjectClass *oc, void *data) 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); @@ -1402,42 +2078,281 @@ sev_guest_class_init(ObjectClass *oc, void *data) static void sev_guest_instance_init(Object *obj) { - SevGuestState *sev = SEV_GUEST(obj); - - sev->kvm_type = -1; + SevGuestState *sev_guest = 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, + sev_guest->policy = DEFAULT_GUEST_POLICY; + object_property_add_uint32_ptr(obj, "handle", &sev_guest->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, + object_property_add_uint32_ptr(obj, "policy", &sev_guest->policy, OBJ_PROP_FLAG_READWRITE); object_apply_compat_props(obj); } -/* sev guest info */ +/* guest info specific sev/sev-es */ static const TypeInfo sev_guest_info = { - .parent = TYPE_X86_CONFIDENTIAL_GUEST, + .parent = TYPE_SEV_COMMON, .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 }, - { } + .class_init = sev_guest_class_init, +}; + +static void +sev_snp_guest_get_policy(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + visit_type_uint64(v, name, + (uint64_t *)&SEV_SNP_GUEST(obj)->kvm_start_conf.policy, + errp); +} + +static void +sev_snp_guest_set_policy(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + visit_type_uint64(v, name, + (uint64_t *)&SEV_SNP_GUEST(obj)->kvm_start_conf.policy, + errp); +} + +static char * +sev_snp_guest_get_guest_visible_workarounds(Object *obj, Error **errp) +{ + return g_strdup(SEV_SNP_GUEST(obj)->guest_visible_workarounds); +} + +static void +sev_snp_guest_set_guest_visible_workarounds(Object *obj, const char *value, + Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + struct kvm_sev_snp_launch_start *start = &sev_snp_guest->kvm_start_conf; + g_autofree guchar *blob; + gsize len; + + g_free(sev_snp_guest->guest_visible_workarounds); + + /* store the base64 str so we don't need to re-encode in getter */ + sev_snp_guest->guest_visible_workarounds = g_strdup(value); + + blob = qbase64_decode(sev_snp_guest->guest_visible_workarounds, + -1, &len, errp); + if (!blob) { + return; } + + if (len != sizeof(start->gosvw)) { + error_setg(errp, "parameter length of %lu exceeds max of %lu", + len, sizeof(start->gosvw)); + return; + } + + memcpy(start->gosvw, blob, len); +} + +static char * +sev_snp_guest_get_id_block(Object *obj, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + return g_strdup(sev_snp_guest->id_block); +} + +static void +sev_snp_guest_set_id_block(Object *obj, const char *value, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + struct kvm_sev_snp_launch_finish *finish = &sev_snp_guest->kvm_finish_conf; + gsize len; + + g_free(sev_snp_guest->id_block); + g_free((guchar *)finish->id_block_uaddr); + + /* store the base64 str so we don't need to re-encode in getter */ + sev_snp_guest->id_block = g_strdup(value); + + finish->id_block_uaddr = + (uint64_t)qbase64_decode(sev_snp_guest->id_block, -1, &len, errp); + + if (!finish->id_block_uaddr) { + return; + } + + if (len != KVM_SEV_SNP_ID_BLOCK_SIZE) { + error_setg(errp, "parameter length of %lu not equal to %u", + len, KVM_SEV_SNP_ID_BLOCK_SIZE); + return; + } + + finish->id_block_en = (len) ? 1 : 0; +} + +static char * +sev_snp_guest_get_id_auth(Object *obj, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + return g_strdup(sev_snp_guest->id_auth); +} + +static void +sev_snp_guest_set_id_auth(Object *obj, const char *value, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + struct kvm_sev_snp_launch_finish *finish = &sev_snp_guest->kvm_finish_conf; + gsize len; + + g_free(sev_snp_guest->id_auth); + g_free((guchar *)finish->id_auth_uaddr); + + /* store the base64 str so we don't need to re-encode in getter */ + sev_snp_guest->id_auth = g_strdup(value); + + finish->id_auth_uaddr = + (uint64_t)qbase64_decode(sev_snp_guest->id_auth, -1, &len, errp); + + if (!finish->id_auth_uaddr) { + return; + } + + if (len > KVM_SEV_SNP_ID_AUTH_SIZE) { + error_setg(errp, "parameter length:ID_AUTH %lu exceeds max of %u", + len, KVM_SEV_SNP_ID_AUTH_SIZE); + return; + } +} + +static bool +sev_snp_guest_get_author_key_enabled(Object *obj, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + return !!sev_snp_guest->kvm_finish_conf.auth_key_en; +} + +static void +sev_snp_guest_set_author_key_enabled(Object *obj, bool value, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + sev_snp_guest->kvm_finish_conf.auth_key_en = value; +} + +static bool +sev_snp_guest_get_vcek_disabled(Object *obj, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + return !!sev_snp_guest->kvm_finish_conf.vcek_disabled; +} + +static void +sev_snp_guest_set_vcek_disabled(Object *obj, bool value, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + sev_snp_guest->kvm_finish_conf.vcek_disabled = value; +} + +static char * +sev_snp_guest_get_host_data(Object *obj, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + return g_strdup(sev_snp_guest->host_data); +} + +static void +sev_snp_guest_set_host_data(Object *obj, const char *value, Error **errp) +{ + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + struct kvm_sev_snp_launch_finish *finish = &sev_snp_guest->kvm_finish_conf; + g_autofree guchar *blob; + gsize len; + + g_free(sev_snp_guest->host_data); + + /* store the base64 str so we don't need to re-encode in getter */ + sev_snp_guest->host_data = g_strdup(value); + + blob = qbase64_decode(sev_snp_guest->host_data, -1, &len, errp); + + if (!blob) { + return; + } + + if (len != sizeof(finish->host_data)) { + error_setg(errp, "parameter length of %lu not equal to %lu", + len, sizeof(finish->host_data)); + return; + } + + memcpy(finish->host_data, blob, len); +} + +static void +sev_snp_guest_class_init(ObjectClass *oc, void *data) +{ + SevCommonStateClass *klass = SEV_COMMON_CLASS(oc); + X86ConfidentialGuestClass *x86_klass = X86_CONFIDENTIAL_GUEST_CLASS(oc); + + klass->build_kernel_loader_hashes = sev_snp_build_kernel_loader_hashes; + klass->launch_start = sev_snp_launch_start; + klass->launch_finish = sev_snp_launch_finish; + klass->launch_update_data = sev_snp_launch_update_data; + klass->kvm_init = sev_snp_kvm_init; + x86_klass->kvm_type = sev_snp_kvm_type; + + object_class_property_add(oc, "policy", "uint64", + sev_snp_guest_get_policy, + sev_snp_guest_set_policy, NULL, NULL); + object_class_property_add_str(oc, "guest-visible-workarounds", + sev_snp_guest_get_guest_visible_workarounds, + sev_snp_guest_set_guest_visible_workarounds); + object_class_property_add_str(oc, "id-block", + sev_snp_guest_get_id_block, + sev_snp_guest_set_id_block); + object_class_property_add_str(oc, "id-auth", + sev_snp_guest_get_id_auth, + sev_snp_guest_set_id_auth); + object_class_property_add_bool(oc, "author-key-enabled", + sev_snp_guest_get_author_key_enabled, + sev_snp_guest_set_author_key_enabled); + object_class_property_add_bool(oc, "vcek-required", + sev_snp_guest_get_vcek_disabled, + sev_snp_guest_set_vcek_disabled); + object_class_property_add_str(oc, "host-data", + sev_snp_guest_get_host_data, + sev_snp_guest_set_host_data); +} + +static void +sev_snp_guest_instance_init(Object *obj) +{ + ConfidentialGuestSupport *cgs = CONFIDENTIAL_GUEST_SUPPORT(obj); + SevSnpGuestState *sev_snp_guest = SEV_SNP_GUEST(obj); + + cgs->require_guest_memfd = true; + + /* default init/start/finish params for kvm */ + sev_snp_guest->kvm_start_conf.policy = DEFAULT_SEV_SNP_POLICY; +} + +/* guest info specific to sev-snp */ +static const TypeInfo sev_snp_guest_info = { + .parent = TYPE_SEV_COMMON, + .name = TYPE_SEV_SNP_GUEST, + .instance_size = sizeof(SevSnpGuestState), + .class_init = sev_snp_guest_class_init, + .instance_init = sev_snp_guest_instance_init, }; static void sev_register_types(void) { + type_register_static(&sev_common_info); type_register_static(&sev_guest_info); + type_register_static(&sev_snp_guest_info); } type_init(sev_register_types); diff --git a/target/i386/sev.h b/target/i386/sev.h index 9e10d09539..858005a119 100644 --- a/target/i386/sev.h +++ b/target/i386/sev.h @@ -20,6 +20,10 @@ #include "exec/confidential-guest-support.h" +#define TYPE_SEV_COMMON "sev-common" +#define TYPE_SEV_GUEST "sev-guest" +#define TYPE_SEV_SNP_GUEST "sev-snp-guest" + #define SEV_POLICY_NODBG 0x1 #define SEV_POLICY_NOKS 0x2 #define SEV_POLICY_ES 0x4 @@ -27,6 +31,9 @@ #define SEV_POLICY_DOMAIN 0x10 #define SEV_POLICY_SEV 0x20 +#define SEV_SNP_POLICY_SMT 0x10000 +#define SEV_SNP_POLICY_DBG 0x80000 + typedef struct SevKernelLoaderContext { char *setup_data; size_t setup_size; @@ -41,20 +48,24 @@ typedef struct SevKernelLoaderContext { #ifdef CONFIG_SEV bool sev_enabled(void); bool sev_es_enabled(void); +bool sev_snp_enabled(void); #else #define sev_enabled() 0 #define sev_es_enabled() 0 +#define sev_snp_enabled() 0 #endif uint32_t sev_get_cbit_position(void); uint32_t sev_get_reduced_phys_bits(void); bool sev_add_kernel_loader_hashes(SevKernelLoaderContext *ctx, Error **errp); -int sev_encrypt_flash(uint8_t *ptr, uint64_t len, Error **errp); +int sev_encrypt_flash(hwaddr gpa, uint8_t *ptr, uint64_t len, Error **errp); int sev_inject_launch_secret(const char *hdr, const char *secret, uint64_t gpa, Error **errp); int sev_es_save_reset_vector(void *flash_ptr, uint64_t flash_size); void sev_es_set_reset_vector(CPUState *cpu); +void pc_system_parse_sev_metadata(uint8_t *flash_ptr, size_t flash_size); + #endif diff --git a/target/i386/tcg/decode-new.c.inc b/target/i386/tcg/decode-new.c.inc index 27dc1bb146..0ff0866e8f 100644 --- a/target/i386/tcg/decode-new.c.inc +++ b/target/i386/tcg/decode-new.c.inc @@ -202,6 +202,7 @@ #define avx_movx .special = X86_SPECIAL_AVXExtMov, #define sextT0 .special = X86_SPECIAL_SExtT0, #define zextT0 .special = X86_SPECIAL_ZExtT0, +#define op0_Mw .special = X86_SPECIAL_Op0_Mw, #define vex1 .vex_class = 1, #define vex1_rep3 .vex_class = 1, .vex_special = X86_VEX_REPScalar, @@ -1576,9 +1577,10 @@ static const X86OpEntry opcodes_root[256] = { [0x89] = X86_OP_ENTRY3(MOV, E,v, G,v, None, None), [0x8A] = X86_OP_ENTRY3(MOV, G,b, E,b, None, None), [0x8B] = X86_OP_ENTRY3(MOV, G,v, E,v, None, None), - [0x8C] = X86_OP_ENTRY3(MOV, E,v, S,w, None, None), + /* Missing in Table A-2: memory destination is always 16-bit. */ + [0x8C] = X86_OP_ENTRY3(MOV, E,v, S,w, None, None, op0_Mw), [0x8D] = X86_OP_ENTRY3(LEA, G,v, M,v, None, None, noseg), - [0x8E] = X86_OP_ENTRY3(MOV, S,w, E,v, None, None), + [0x8E] = X86_OP_ENTRY3(MOV, S,w, E,w, None, None), [0x8F] = X86_OP_GROUPw(group1A, E,v), [0x98] = X86_OP_ENTRY1(CBW, 0,v), /* rAX */ @@ -2041,9 +2043,9 @@ static bool has_cpuid_feature(DisasContext *s, X86CPUIDFeature cpuid) case X86_FEAT_PCLMULQDQ: return (s->cpuid_ext_features & CPUID_EXT_PCLMULQDQ); case X86_FEAT_SSE: - return (s->cpuid_ext_features & CPUID_SSE); + return (s->cpuid_features & CPUID_SSE); case X86_FEAT_SSE2: - return (s->cpuid_ext_features & CPUID_SSE2); + return (s->cpuid_features & CPUID_SSE2); case X86_FEAT_SSE3: return (s->cpuid_ext_features & CPUID_EXT_SSE3); case X86_FEAT_SSSE3: @@ -2514,6 +2516,13 @@ static void disas_insn(DisasContext *s, CPUState *cpu) s->override = -1; break; + case X86_SPECIAL_Op0_Mw: + assert(decode.op[0].unit == X86_OP_INT); + if (decode.op[0].has_ea) { + decode.op[0].ot = MO_16; + } + break; + default: break; } diff --git a/target/i386/tcg/decode-new.h b/target/i386/tcg/decode-new.h index 51ef0e621b..1f90cf9640 100644 --- a/target/i386/tcg/decode-new.h +++ b/target/i386/tcg/decode-new.h @@ -203,6 +203,9 @@ typedef enum X86InsnSpecial { /* When loaded into s->T0, register operand 1 is zero/sign extended. */ X86_SPECIAL_SExtT0, X86_SPECIAL_ZExtT0, + + /* Memory operand size of MOV from segment register is MO_16 */ + X86_SPECIAL_Op0_Mw, } X86InsnSpecial; /* diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index e322293371..e1b850f3fc 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -3142,6 +3142,11 @@ void helper_xsetbv(CPUX86State *env, uint32_t ecx, uint64_t mask) goto do_gpf; } + /* SSE can be disabled, but only if AVX is disabled too. */ + if ((mask & (XSTATE_SSE_MASK | XSTATE_YMM_MASK)) == XSTATE_YMM_MASK) { + goto do_gpf; + } + /* Disallow enabling unimplemented features. */ cpu_x86_cpuid(env, 0x0d, 0, &ena_lo, &dummy, &dummy, &ena_hi); ena = ((uint64_t)ena_hi << 32) | ena_lo; diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index 6dedfe94c0..0486ab6911 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -3199,7 +3199,7 @@ static void disas_insn_old(DisasContext *s, CPUState *cpu, int b) goto illegal_op; } if (s->prefix & PREFIX_REPZ) { - if (!(s->cpuid_ext_features & CPUID_7_0_ECX_RDPID)) { + if (!(s->cpuid_7_0_ecx_features & CPUID_7_0_ECX_RDPID)) { goto illegal_op; } gen_helper_rdpid(s->T0, tcg_env); diff --git a/target/i386/trace-events b/target/i386/trace-events index 2cd8726eeb..06b44ead2e 100644 --- a/target/i386/trace-events +++ b/target/i386/trace-events @@ -11,3 +11,6 @@ kvm_sev_launch_measurement(const char *value) "data %s" kvm_sev_launch_finish(void) "" kvm_sev_launch_secret(uint64_t hpa, uint64_t hva, uint64_t secret, int len) "hpa 0x%" PRIx64 " hva 0x%" PRIx64 " data 0x%" PRIx64 " len %d" kvm_sev_attestation_report(const char *mnonce, const char *data) "mnonce %s data %s" +kvm_sev_snp_launch_start(uint64_t policy, char *gosvw) "policy 0x%" PRIx64 " gosvw %s" +kvm_sev_snp_launch_update(uint64_t src, uint64_t gpa, uint64_t len, const char *type) "src 0x%" PRIx64 " gpa 0x%" PRIx64 " len 0x%" PRIx64 " (%s page)" +kvm_sev_snp_launch_finish(char *id_block, char *id_auth, char *host_data) "id_block %s id_auth %s host_data %s" diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index 59235b4f38..9a54ef7f8d 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -157,12 +157,6 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot) #define SOFTMMU_RESERVE_REGS \ (tcg_use_softmmu ? (1 << TCG_REG_L0) | (1 << TCG_REG_L1) : 0) -/* For 64-bit, we always know that CMOV is available. */ -#if TCG_TARGET_REG_BITS == 64 -# define have_cmov true -#else -# define have_cmov (cpuinfo & CPUINFO_CMOV) -#endif #define have_bmi2 (cpuinfo & CPUINFO_BMI2) #define have_lzcnt (cpuinfo & CPUINFO_LZCNT) @@ -1815,14 +1809,7 @@ static void tcg_out_setcond2(TCGContext *s, const TCGArg *args, static void tcg_out_cmov(TCGContext *s, int jcc, int rexw, TCGReg dest, TCGReg v1) { - if (have_cmov) { - tcg_out_modrm(s, OPC_CMOVCC | jcc | rexw, dest, v1); - } else { - TCGLabel *over = gen_new_label(); - tcg_out_jxx(s, jcc ^ 1, over, 1); - tcg_out_mov(s, TCG_TYPE_I32, dest, v1); - tcg_out_label(s, over); - } + tcg_out_modrm(s, OPC_CMOVCC | jcc | rexw, dest, v1); } static void tcg_out_movcond(TCGContext *s, int rexw, TCGCond cond, diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h index 2f67a97e05..ecc6982728 100644 --- a/tcg/i386/tcg-target.h +++ b/tcg/i386/tcg-target.h @@ -111,7 +111,6 @@ typedef enum { #endif #define have_bmi1 (cpuinfo & CPUINFO_BMI1) -#define have_popcnt (cpuinfo & CPUINFO_POPCNT) #define have_avx1 (cpuinfo & CPUINFO_AVX1) #define have_avx2 (cpuinfo & CPUINFO_AVX2) #define have_movbe (cpuinfo & CPUINFO_MOVBE) @@ -143,7 +142,7 @@ typedef enum { #define TCG_TARGET_HAS_nor_i32 0 #define TCG_TARGET_HAS_clz_i32 1 #define TCG_TARGET_HAS_ctz_i32 1 -#define TCG_TARGET_HAS_ctpop_i32 have_popcnt +#define TCG_TARGET_HAS_ctpop_i32 1 #define TCG_TARGET_HAS_deposit_i32 1 #define TCG_TARGET_HAS_extract_i32 1 #define TCG_TARGET_HAS_sextract_i32 1 @@ -178,7 +177,7 @@ typedef enum { #define TCG_TARGET_HAS_nor_i64 0 #define TCG_TARGET_HAS_clz_i64 1 #define TCG_TARGET_HAS_ctz_i64 1 -#define TCG_TARGET_HAS_ctpop_i64 have_popcnt +#define TCG_TARGET_HAS_ctpop_i64 1 #define TCG_TARGET_HAS_deposit_i64 1 #define TCG_TARGET_HAS_extract_i64 1 #define TCG_TARGET_HAS_sextract_i64 0 diff --git a/tests/avocado/intel_iommu.py b/tests/avocado/intel_iommu.py index f04ee1cf9d..09e694bd40 100644 --- a/tests/avocado/intel_iommu.py +++ b/tests/avocado/intel_iommu.py @@ -32,7 +32,7 @@ class IntelIOMMU(LinuxTest): def set_up_boot(self): path = self.download_boot() - self.vm.add_args('-device', 'virtio-blk-pci,bus=pcie.0,scsi=off,' + + self.vm.add_args('-device', 'virtio-blk-pci,bus=pcie.0,' + 'drive=drv0,id=virtio-disk0,bootindex=1,' 'werror=stop,rerror=stop' + self.IOMMU_ADDON) self.vm.add_args('-device', 'virtio-gpu-pci' + self.IOMMU_ADDON) diff --git a/tests/avocado/smmu.py b/tests/avocado/smmu.py index 21ff030ca7..4ebfa7128c 100644 --- a/tests/avocado/smmu.py +++ b/tests/avocado/smmu.py @@ -32,7 +32,7 @@ class SMMU(LinuxTest): def set_up_boot(self): path = self.download_boot() - self.vm.add_args('-device', 'virtio-blk-pci,bus=pcie.0,scsi=off,' + + self.vm.add_args('-device', 'virtio-blk-pci,bus=pcie.0,' + 'drive=drv0,id=virtio-disk0,bootindex=1,' 'werror=stop,rerror=stop' + self.IOMMU_ADDON) self.vm.add_args('-drive', diff --git a/tests/avocado/tuxrun_baselines.py b/tests/avocado/tuxrun_baselines.py index a936a3b780..736e4aa289 100644 --- a/tests/avocado/tuxrun_baselines.py +++ b/tests/avocado/tuxrun_baselines.py @@ -235,7 +235,7 @@ class TuxRunBaselineTest(QemuSystemTest): self.vm.add_args('-drive', 'file=' + qcow2.name + ',format=qcow2,if=none,id=' 'drive-virtio-disk1', - '-device', 'virtio-blk-pci,scsi=off,bus=pci.0,' + '-device', 'virtio-blk-pci,bus=pci.0,' 'addr=0xb,drive=drive-virtio-disk1,id=virtio-disk1' ',bootindex=2') self.common_tuxrun(csums=sums, drive="scsi-hd") diff --git a/util/bufferiszero.c b/util/bufferiszero.c index 74864f7b78..11c080e02c 100644 --- a/util/bufferiszero.c +++ b/util/bufferiszero.c @@ -188,14 +188,14 @@ static biz_accel_fn const accel_table[] = { static unsigned best_accel(void) { +#ifdef CONFIG_AVX2_OPT unsigned info = cpuinfo_init(); -#ifdef CONFIG_AVX2_OPT if (info & CPUINFO_AVX2) { return 2; } #endif - return info & CPUINFO_SSE2 ? 1 : 0; + return 1; } #elif defined(__aarch64__) && defined(__ARM_NEON) diff --git a/util/cpuinfo-i386.c b/util/cpuinfo-i386.c index 9fddb18303..8f2694d88f 100644 --- a/util/cpuinfo-i386.c +++ b/util/cpuinfo-i386.c @@ -34,15 +34,11 @@ unsigned __attribute__((constructor)) cpuinfo_init(void) if (max >= 1) { __cpuid(1, a, b, c, d); - info |= (d & bit_CMOV ? CPUINFO_CMOV : 0); - info |= (d & bit_SSE2 ? CPUINFO_SSE2 : 0); - info |= (c & bit_SSE4_1 ? CPUINFO_SSE4 : 0); info |= (c & bit_MOVBE ? CPUINFO_MOVBE : 0); - info |= (c & bit_POPCNT ? CPUINFO_POPCNT : 0); info |= (c & bit_PCLMUL ? CPUINFO_PCLMUL : 0); - /* Our AES support requires PSHUFB as well. */ - info |= ((c & bit_AES) && (c & bit_SSSE3) ? CPUINFO_AES : 0); + /* NOTE: our AES support requires SSSE3 (PSHUFB) as well. */ + info |= (c & bit_AES) ? CPUINFO_AES : 0; /* For AVX features, we must check available and usable. */ if ((c & bit_AVX) && (c & bit_OSXSAVE)) { |