diff options
| author | Stefan Hajnoczi <stefanha@redhat.com> | 2025-06-21 10:00:46 -0400 |
|---|---|---|
| committer | Stefan Hajnoczi <stefanha@redhat.com> | 2025-06-21 10:00:46 -0400 |
| commit | 43ba160cb4bbb193560eb0d2d7decc4b5fc599fe (patch) | |
| tree | 2a12561d9da7a4bee1ad5279fe8dd10f4432d74a | |
| parent | 6e1571533fd92bec67e5ab9b1dd1e15032925757 (diff) | |
| parent | 40da501d8989913935660dc24953ece02c9e98b8 (diff) | |
| download | focaccia-qemu-43ba160cb4bbb193560eb0d2d7decc4b5fc599fe.tar.gz focaccia-qemu-43ba160cb4bbb193560eb0d2d7decc4b5fc599fe.zip | |
Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging
* cleanups for distributed DTB files * scripts/meson-buildoptions: Sort coroutine_backend choices lexicographically * rust/qemu-api: Add initial logging support : rust: pl011: Implement logging * target/i386: fix Win98 * meson: cleanup win32 library detection * rust: safe(r) instance_init * rust: prepare for multiple bindgen invocations * rust: fix new warning * target/i386: Warn about why CPUID_EXT_PDCM is not available * target/i386: small TDX fixes and clarifications * target/i386: support for TDX quote generation # -----BEGIN PGP SIGNATURE----- # # iQFIBAABCgAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmhVRWsUHHBib256aW5p # QHJlZGhhdC5jb20ACgkQv/vSX3jHroOyDQf/YqX2jTZbC4jXdHZT6YiDlYPX9MPx # emFX0S+30X5zNuGYUQufKHEJWshMtklB1seUTQathOPaNeCFK13lY4m1CRbhbrMs # 3iG4ZQf5V+YTuB+JuE8KfclJeAPXDTnIc2uJbtXErIsPBeEGYZelFLnO5HLiMsY3 # iX9S2hSkjvjlikFv/m9ebg9SMP3+/ZunQMZxsDwgb7U3uqtuZagCJTWz0xTHHHxV # Ko5OPA0kIydm0NnlHs2DsF1mivmYSSIfBnxg4KXgmJxd3gNGd9SemBQOwYU68x0T # R3GzI6NLgdP/3mKOsxpM6hFiXBp84eT6zghpdqK5zQFidgz935EXP5WjvQ== # =ttQr # -----END PGP SIGNATURE----- # gpg: Signature made Fri 20 Jun 2025 07:26:35 EDT # gpg: using RSA key F13338574B662389866C7682BFFBD25F78C7AE83 # gpg: issuer "pbonzini@redhat.com" # gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full] # gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" [full] # Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4 E2F7 7E15 100C CD36 69B1 # Subkey fingerprint: F133 3857 4B66 2389 866C 7682 BFFB D25F 78C7 AE83 * tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (24 commits) i386/tdx: handle TDG.VP.VMCALL<GetQuote> i386/tdx: handle TDG.VP.VMCALL<GetTdVmCallInfo> update Linux headers to v6.16-rc3 i386/tdx: Clarify the error message of mrconfigid/mrowner/mrownerconfig i386/tdx: Fix the typo of the comment of struct TdxGuest i386/cpu: Rename enable_cpuid_0x1f to force_cpuid_0x1f i386/tdx: Error and exit when named cpu model is requested i386/cpu: Warn about why CPUID_EXT_PDCM is not available i386/cpu: Move adjustment of CPUID_EXT_PDCM before feature_dependencies[] check rust: hpet: fix new warning rust: pl011: Add missing logging to match C version rust: pl011: Implement logging rust/qemu-api: Add initial logging support based on C API rust: move rust.bindgen to qemu-api crate rust: prepare variable definitions for multiple bindgen invocations rust: qom: change instance_init to take a ParentInit<> rust: qom: make ParentInit lifetime-invariant rust: qom: introduce ParentInit rust: hpet: fully initialize object during instance_init rust: qemu_api: introduce MaybeUninit field projection ... Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
42 files changed, 1340 insertions, 233 deletions
diff --git a/docs/devel/rust.rst b/docs/devel/rust.rst index 47e9677fcb..dc8c44109e 100644 --- a/docs/devel/rust.rst +++ b/docs/devel/rust.rst @@ -162,6 +162,7 @@ module status ``errno`` complete ``error`` stable ``irq`` complete +``log`` proof of concept ``memory`` stable ``module`` complete ``qdev`` stable diff --git a/hw/arm/boot.c b/hw/arm/boot.c index 3c93d87985..becd827af1 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -527,7 +527,7 @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, if (binfo->dtb_filename) { char *filename; - filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, binfo->dtb_filename); + filename = qemu_find_file(QEMU_FILE_TYPE_DTB, binfo->dtb_filename); if (!filename) { fprintf(stderr, "Couldn't open dtb file %s\n", binfo->dtb_filename); goto fail; diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c index 6899802bed..723c97fad2 100644 --- a/hw/ppc/e500.c +++ b/hw/ppc/e500.c @@ -408,7 +408,7 @@ static int ppce500_load_device_tree(PPCE500MachineState *pms, if (dtb_file) { char *filename; - filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, dtb_file); + filename = qemu_find_file(QEMU_FILE_TYPE_DTB, dtb_file); if (!filename) { goto out; } diff --git a/include/standard-headers/asm-x86/setup_data.h b/include/standard-headers/asm-x86/setup_data.h index a483d72f42..2e446c1d85 100644 --- a/include/standard-headers/asm-x86/setup_data.h +++ b/include/standard-headers/asm-x86/setup_data.h @@ -13,7 +13,8 @@ #define SETUP_CC_BLOB 7 #define SETUP_IMA 8 #define SETUP_RNG_SEED 9 -#define SETUP_ENUM_MAX SETUP_RNG_SEED +#define SETUP_KEXEC_KHO 10 +#define SETUP_ENUM_MAX SETUP_KEXEC_KHO #define SETUP_INDIRECT (1<<31) #define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) @@ -78,6 +79,16 @@ struct ima_setup_data { uint64_t size; } QEMU_PACKED; +/* + * Locations of kexec handover metadata + */ +struct kho_data { + uint64_t fdt_addr; + uint64_t fdt_size; + uint64_t scratch_addr; + uint64_t scratch_size; +} QEMU_PACKED; + #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_SETUP_DATA_H */ diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index a8b759dcbc..c8309d378b 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -421,6 +421,7 @@ extern "C" { #define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09 #define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a #define DRM_FORMAT_MOD_VENDOR_MTK 0x0b +#define DRM_FORMAT_MOD_VENDOR_APPLE 0x0c /* add more to the end as needed */ @@ -1494,6 +1495,50 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) #define DRM_FORMAT_MOD_MTK_16L_32S_TILE DRM_FORMAT_MOD_MTK(MTK_FMT_MOD_TILE_16L32S) /* + * Apple GPU-tiled layouts. + * + * Apple GPUs support nonlinear tilings with optional lossless compression. + * + * GPU-tiled images are divided into 16KiB tiles: + * + * Bytes per pixel Tile size + * --------------- --------- + * 1 128x128 + * 2 128x64 + * 4 64x64 + * 8 64x32 + * 16 32x32 + * + * Tiles are raster-order. Pixels within a tile are interleaved (Morton order). + * + * Compressed images pad the body to 128-bytes and are immediately followed by a + * metadata section. The metadata section rounds the image dimensions to + * powers-of-two and contains 8 bytes for each 16x16 compression subtile. + * Subtiles are interleaved (Morton order). + * + * All images are 128-byte aligned. + * + * These layouts fundamentally do not have meaningful strides. No matter how we + * specify strides for these layouts, userspace unaware of Apple image layouts + * will be unable to use correctly the specified stride for any purpose. + * Userspace aware of the image layouts do not use strides. The most "correct" + * convention would be setting the image stride to 0. Unfortunately, some + * software assumes the stride is at least (width * bytes per pixel). We + * therefore require that stride equals (width * bytes per pixel). Since the + * stride is arbitrary here, we pick the simplest convention. + * + * Although containing two sections, compressed image layouts are treated in + * software as a single plane. This is modelled after AFBC, a similar + * scheme. Attempting to separate the sections to be "explicit" in DRM would + * only generate more confusion, as software does not treat the image this way. + * + * For detailed information on the hardware image layouts, see + * https://docs.mesa3d.org/drivers/asahi.html#image-layouts + */ +#define DRM_FORMAT_MOD_APPLE_GPU_TILED fourcc_mod_code(APPLE, 1) +#define DRM_FORMAT_MOD_APPLE_GPU_TILED_COMPRESSED fourcc_mod_code(APPLE, 2) + +/* * AMD modifiers * * Memory layout: diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index 5d1ad5fdea..cef0d207a6 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -2295,71 +2295,75 @@ static inline int ethtool_validate_duplex(uint8_t duplex) #define RXH_XFRM_SYM_OR_XOR (1 << 1) #define RXH_XFRM_NO_CHANGE 0xff -/* L2-L4 network traffic flow types */ -#define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ -#define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ -#define SCTP_V4_FLOW 0x03 /* hash or spec (sctp_ip4_spec) */ -#define AH_ESP_V4_FLOW 0x04 /* hash only */ -#define TCP_V6_FLOW 0x05 /* hash or spec (tcp_ip6_spec; nfc only) */ -#define UDP_V6_FLOW 0x06 /* hash or spec (udp_ip6_spec; nfc only) */ -#define SCTP_V6_FLOW 0x07 /* hash or spec (sctp_ip6_spec; nfc only) */ -#define AH_ESP_V6_FLOW 0x08 /* hash only */ -#define AH_V4_FLOW 0x09 /* hash or spec (ah_ip4_spec) */ -#define ESP_V4_FLOW 0x0a /* hash or spec (esp_ip4_spec) */ -#define AH_V6_FLOW 0x0b /* hash or spec (ah_ip6_spec; nfc only) */ -#define ESP_V6_FLOW 0x0c /* hash or spec (esp_ip6_spec; nfc only) */ -#define IPV4_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */ -#define IP_USER_FLOW IPV4_USER_FLOW -#define IPV6_USER_FLOW 0x0e /* spec only (usr_ip6_spec; nfc only) */ -#define IPV4_FLOW 0x10 /* hash only */ -#define IPV6_FLOW 0x11 /* hash only */ -#define ETHER_FLOW 0x12 /* spec only (ether_spec) */ - -/* Used for GTP-U IPv4 and IPv6. - * The format of GTP packets only includes - * elements such as TEID and GTP version. - * It is primarily intended for data communication of the UE. - */ -#define GTPU_V4_FLOW 0x13 /* hash only */ -#define GTPU_V6_FLOW 0x14 /* hash only */ - -/* Use for GTP-C IPv4 and v6. - * The format of these GTP packets does not include TEID. - * Primarily expected to be used for communication - * to create sessions for UE data communication, - * commonly referred to as CSR (Create Session Request). - */ -#define GTPC_V4_FLOW 0x15 /* hash only */ -#define GTPC_V6_FLOW 0x16 /* hash only */ - -/* Use for GTP-C IPv4 and v6. - * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. - * After session creation, it becomes this packet. - * This is mainly used for requests to realize UE handover. - */ -#define GTPC_TEID_V4_FLOW 0x17 /* hash only */ -#define GTPC_TEID_V6_FLOW 0x18 /* hash only */ - -/* Use for GTP-U and extended headers for the PSC (PDU Session Container). - * The format of these GTP packets includes TEID and QFI. - * In 5G communication using UPF (User Plane Function), - * data communication with this extended header is performed. - */ -#define GTPU_EH_V4_FLOW 0x19 /* hash only */ -#define GTPU_EH_V6_FLOW 0x1a /* hash only */ - -/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. - * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by - * UL/DL included in the PSC. - * There are differences in the data included based on Downlink/Uplink, - * and can be used to distinguish packets. - * The functions described so far are useful when you want to - * handle communication from the mobile network in UPF, PGW, etc. - */ -#define GTPU_UL_V4_FLOW 0x1b /* hash only */ -#define GTPU_UL_V6_FLOW 0x1c /* hash only */ -#define GTPU_DL_V4_FLOW 0x1d /* hash only */ -#define GTPU_DL_V6_FLOW 0x1e /* hash only */ +enum { + /* L2-L4 network traffic flow types */ + TCP_V4_FLOW = 0x01, /* hash or spec (tcp_ip4_spec) */ + UDP_V4_FLOW = 0x02, /* hash or spec (udp_ip4_spec) */ + SCTP_V4_FLOW = 0x03, /* hash or spec (sctp_ip4_spec) */ + AH_ESP_V4_FLOW = 0x04, /* hash only */ + TCP_V6_FLOW = 0x05, /* hash or spec (tcp_ip6_spec; nfc only) */ + UDP_V6_FLOW = 0x06, /* hash or spec (udp_ip6_spec; nfc only) */ + SCTP_V6_FLOW = 0x07, /* hash or spec (sctp_ip6_spec; nfc only) */ + AH_ESP_V6_FLOW = 0x08, /* hash only */ + AH_V4_FLOW = 0x09, /* hash or spec (ah_ip4_spec) */ + ESP_V4_FLOW = 0x0a, /* hash or spec (esp_ip4_spec) */ + AH_V6_FLOW = 0x0b, /* hash or spec (ah_ip6_spec; nfc only) */ + ESP_V6_FLOW = 0x0c, /* hash or spec (esp_ip6_spec; nfc only) */ + IPV4_USER_FLOW = 0x0d, /* spec only (usr_ip4_spec) */ + IP_USER_FLOW = IPV4_USER_FLOW, + IPV6_USER_FLOW = 0x0e, /* spec only (usr_ip6_spec; nfc only) */ + IPV4_FLOW = 0x10, /* hash only */ + IPV6_FLOW = 0x11, /* hash only */ + ETHER_FLOW = 0x12, /* spec only (ether_spec) */ + + /* Used for GTP-U IPv4 and IPv6. + * The format of GTP packets only includes + * elements such as TEID and GTP version. + * It is primarily intended for data communication of the UE. + */ + GTPU_V4_FLOW = 0x13, /* hash only */ + GTPU_V6_FLOW = 0x14, /* hash only */ + + /* Use for GTP-C IPv4 and v6. + * The format of these GTP packets does not include TEID. + * Primarily expected to be used for communication + * to create sessions for UE data communication, + * commonly referred to as CSR (Create Session Request). + */ + GTPC_V4_FLOW = 0x15, /* hash only */ + GTPC_V6_FLOW = 0x16, /* hash only */ + + /* Use for GTP-C IPv4 and v6. + * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. + * After session creation, it becomes this packet. + * This is mainly used for requests to realize UE handover. + */ + GTPC_TEID_V4_FLOW = 0x17, /* hash only */ + GTPC_TEID_V6_FLOW = 0x18, /* hash only */ + + /* Use for GTP-U and extended headers for the PSC (PDU Session Container). + * The format of these GTP packets includes TEID and QFI. + * In 5G communication using UPF (User Plane Function), + * data communication with this extended header is performed. + */ + GTPU_EH_V4_FLOW = 0x19, /* hash only */ + GTPU_EH_V6_FLOW = 0x1a, /* hash only */ + + /* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. + * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by + * UL/DL included in the PSC. + * There are differences in the data included based on Downlink/Uplink, + * and can be used to distinguish packets. + * The functions described so far are useful when you want to + * handle communication from the mobile network in UPF, PGW, etc. + */ + GTPU_UL_V4_FLOW = 0x1b, /* hash only */ + GTPU_UL_V6_FLOW = 0x1c, /* hash only */ + GTPU_DL_V4_FLOW = 0x1d, /* hash only */ + GTPU_DL_V6_FLOW = 0x1e, /* hash only */ + + __FLOW_TYPE_COUNT, +}; /* Flag to enable additional fields in struct ethtool_rx_flow_spec */ #define FLOW_EXT 0x80000000 diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h index a2b5815d89..d8b2fd67e1 100644 --- a/include/standard-headers/linux/fuse.h +++ b/include/standard-headers/linux/fuse.h @@ -232,6 +232,9 @@ * * 7.43 * - add FUSE_REQUEST_TIMEOUT + * + * 7.44 + * - add FUSE_NOTIFY_INC_EPOCH */ #ifndef _LINUX_FUSE_H @@ -263,7 +266,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 43 +#define FUSE_KERNEL_MINOR_VERSION 44 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -667,6 +670,7 @@ enum fuse_notify_code { FUSE_NOTIFY_RETRIEVE = 5, FUSE_NOTIFY_DELETE = 6, FUSE_NOTIFY_RESEND = 7, + FUSE_NOTIFY_INC_EPOCH = 8, FUSE_NOTIFY_CODE_MAX, }; diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index 09ba0ad878..a82ff795e0 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -925,7 +925,8 @@ #define SW_MUTE_DEVICE 0x0e /* set = device disabled */ #define SW_PEN_INSERTED 0x0f /* set = pen inserted */ #define SW_MACHINE_COVER 0x10 /* set = cover closed */ -#define SW_MAX_ 0x10 +#define SW_USB_INSERT 0x11 /* set = USB audio device connected */ +#define SW_MAX_ 0x11 #define SW_CNT (SW_MAX_+1) /* diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index ba326710f9..a3a3e942de 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -750,7 +750,8 @@ #define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ -#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE +#define PCI_EXT_CAP_ID_PL_64GT 0x31 /* Physical Layer 64.0 GT/s */ +#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_64GT #define PCI_EXT_CAP_DSN_SIZEOF 12 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 @@ -1144,12 +1145,21 @@ #define PCI_DLF_CAP 0x04 /* Capabilities Register */ #define PCI_DLF_EXCHANGE_ENABLE 0x80000000 /* Data Link Feature Exchange Enable */ +/* Secondary PCIe Capability 8.0 GT/s */ +#define PCI_SECPCI_LE_CTRL 0x0c /* Lane Equalization Control Register */ + /* Physical Layer 16.0 GT/s */ #define PCI_PL_16GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ #define PCI_PL_16GT_LE_CTRL_DSP_TX_PRESET_MASK 0x0000000F #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0 #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4 +/* Physical Layer 32.0 GT/s */ +#define PCI_PL_32GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ + +/* Physical Layer 64.0 GT/s */ +#define PCI_PL_64GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ + /* Native PCIe Enclosure Management */ #define PCI_NPEM_CAP 0x04 /* NPEM capability register */ #define PCI_NPEM_CAP_CAPABLE 0x00000001 /* NPEM Capable */ diff --git a/include/standard-headers/linux/virtio_gpu.h b/include/standard-headers/linux/virtio_gpu.h index 6459fdb9fb..00cd3f04af 100644 --- a/include/standard-headers/linux/virtio_gpu.h +++ b/include/standard-headers/linux/virtio_gpu.h @@ -309,8 +309,9 @@ struct virtio_gpu_cmd_submit { #define VIRTIO_GPU_CAPSET_VIRGL 1 #define VIRTIO_GPU_CAPSET_VIRGL2 2 -/* 3 is reserved for gfxstream */ +#define VIRTIO_GPU_CAPSET_GFXSTREAM_VULKAN 3 #define VIRTIO_GPU_CAPSET_VENUS 4 +#define VIRTIO_GPU_CAPSET_CROSS_DOMAIN 5 #define VIRTIO_GPU_CAPSET_DRM 6 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ diff --git a/include/standard-headers/linux/virtio_pci.h b/include/standard-headers/linux/virtio_pci.h index 91fec6f502..09e964e6ee 100644 --- a/include/standard-headers/linux/virtio_pci.h +++ b/include/standard-headers/linux/virtio_pci.h @@ -246,6 +246,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_ADMIN_CMD_LIST_USE 0x1 /* Admin command group type. */ +#define VIRTIO_ADMIN_GROUP_TYPE_SELF 0x0 #define VIRTIO_ADMIN_GROUP_TYPE_SRIOV 0x1 /* Transitional device admin command. */ diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index 4e6aff08df..f4d9baafa1 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -419,10 +419,11 @@ enum { /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 -#define KVM_ARM_VCPU_PMU_V3_IRQ 0 -#define KVM_ARM_VCPU_PMU_V3_INIT 1 -#define KVM_ARM_VCPU_PMU_V3_FILTER 2 -#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3 +#define KVM_ARM_VCPU_PMU_V3_IRQ 0 +#define KVM_ARM_VCPU_PMU_V3_INIT 1 +#define KVM_ARM_VCPU_PMU_V3_FILTER 2 +#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3 +#define KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS 4 #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index 7fb57ccb2a..cd275ae76d 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -843,6 +843,7 @@ struct kvm_sev_snp_launch_start { }; /* Kept in sync with firmware values for simplicity. */ +#define KVM_SEV_PAGE_TYPE_INVALID 0x0 #define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1 #define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3 #define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4 diff --git a/linux-headers/linux/bits.h b/linux-headers/linux/bits.h index 58596d18f4..9243f38975 100644 --- a/linux-headers/linux/bits.h +++ b/linux-headers/linux/bits.h @@ -4,9 +4,9 @@ #ifndef _LINUX_BITS_H #define _LINUX_BITS_H -#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) -#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) #define __GENMASK_U128(h, l) \ ((_BIT128((h)) << 1) - (_BIT128(l))) diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index 99cc82a275..0690743944 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -178,6 +178,7 @@ struct kvm_xen_exit { #define KVM_EXIT_NOTIFY 37 #define KVM_EXIT_LOONGARCH_IOCSR 38 #define KVM_EXIT_MEMORY_FAULT 39 +#define KVM_EXIT_TDX 40 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -439,6 +440,27 @@ struct kvm_run { __u64 gpa; __u64 size; } memory_fault; + /* KVM_EXIT_TDX */ + struct { + __u64 flags; + __u64 nr; + union { + struct { + __u64 ret; + __u64 data[5]; + } unknown; + struct { + __u64 ret; + __u64 gpa; + __u64 size; + } get_quote; + struct { + __u64 ret; + __u64 leaf; + __u64 r11, r12, r13, r14; + } get_tdvmcall_info; + }; + } tdx; /* Fix the size of the union. */ char padding[256]; }; @@ -923,6 +945,9 @@ struct kvm_enable_cap { #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 #define KVM_CAP_X86_GUEST_MODE 238 #define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239 +#define KVM_CAP_ARM_EL2 240 +#define KVM_CAP_ARM_EL2_E2H0 241 +#define KVM_CAP_RISCV_MP_STATE_RESET 242 struct kvm_irq_routing_irqchip { __u32 irqchip; diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index b95dd84eef..d4b3e2ae13 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -28,10 +28,10 @@ /* Set current process as the (exclusive) owner of this file descriptor. This * must be called before any other vhost command. Further calls to - * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */ + * VHOST_SET_OWNER fail until VHOST_RESET_OWNER is called. */ #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01) /* Give up ownership, and reset the device to default values. - * Allows subsequent call to VHOST_OWNER_SET to succeed. */ + * Allows subsequent call to VHOST_SET_OWNER to succeed. */ #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02) /* Set up/modify memory layout */ diff --git a/meson.build b/meson.build index 34729c2a3d..4676908dbb 100644 --- a/meson.build +++ b/meson.build @@ -843,15 +843,12 @@ host_dsosuf = '.so' if host_os == 'windows' midl = find_program('midl', required: false) widl = find_program('widl', required: false) - pathcch = cc.find_library('pathcch') - synchronization = cc.find_library('Synchronization', required: false) - if not synchronization.found() - # The library name is lowercase on mingw - synchronization = cc.find_library('synchronization', required: true) - endif - socket = cc.find_library('ws2_32') - winmm = cc.find_library('winmm') + # MinGW uses lowercase for library names + pathcch = cc.find_library('pathcch', required: true) + synchronization = cc.find_library('synchronization', required: true) + socket = cc.find_library('ws2_32', required: true) + winmm = cc.find_library('winmm', required: true) win = import('windows') version_res = win.compile_resources('version.rc', @@ -4203,10 +4200,11 @@ foreach target_base_arch, config_base_arch : config_base_arch_mak endforeach if have_rust + bindings_incdir = include_directories('.', 'include') # We would like to use --generate-cstr, but it is only available # starting with bindgen 0.66.0. The oldest supported versions # is 0.60.x (Debian 12 has 0.60.1) which introduces --allowlist-file. - bindgen_args = [ + bindgen_args_common = [ '--disable-header-comment', '--raw-line', '// @generated', '--ctypes-prefix', 'std::os::raw', @@ -4222,59 +4220,20 @@ if have_rust ] if not rustfmt.found() if bindgen.version().version_compare('<0.65.0') - bindgen_args += ['--no-rustfmt-bindings'] + bindgen_args_common += ['--no-rustfmt-bindings'] else - bindgen_args += ['--formatter', 'none'] + bindgen_args_common += ['--formatter', 'none'] endif endif if bindgen.version().version_compare('>=0.66.0') - bindgen_args += ['--rust-target', '1.59'] + bindgen_args_common += ['--rust-target', '1.59'] endif if bindgen.version().version_compare('<0.61.0') # default in 0.61+ - bindgen_args += ['--size_t-is-usize'] + bindgen_args_common += ['--size_t-is-usize'] else - bindgen_args += ['--merge-extern-blocks'] - endif - c_enums = [ - 'DeviceCategory', - 'GpioPolarity', - 'MachineInitPhase', - 'MemoryDeviceInfoKind', - 'MigrationPolicy', - 'MigrationPriority', - 'QEMUChrEvent', - 'QEMUClockType', - 'ResetType', - 'device_endian', - 'module_init_type', - ] - foreach enum : c_enums - bindgen_args += ['--rustified-enum', enum] - endforeach - c_bitfields = [ - 'ClockEvent', - 'VMStateFlags', - ] - foreach enum : c_bitfields - bindgen_args += ['--bitfield-enum', enum] - endforeach - - # TODO: Remove this comment when the clang/libclang mismatch issue is solved. - # - # Rust bindings generation with `bindgen` might fail in some cases where the - # detected `libclang` does not match the expected `clang` version/target. In - # this case you must pass the path to `clang` and `libclang` to your build - # command invocation using the environment variables CLANG_PATH and - # LIBCLANG_PATH - bindings_rs = rust.bindgen( - input: 'rust/wrapper.h', - dependencies: common_ss.all_dependencies(), - output: 'bindings.inc.rs', - include_directories: include_directories('.', 'include'), - bindgen_version: ['>=0.60.0'], - args: bindgen_args, - ) + bindgen_args_common += ['--merge-extern-blocks'] + endif subdir('rust') endif diff --git a/pc-bios/dtb/meson.build b/pc-bios/dtb/meson.build index 7a71835bca..993032949f 100644 --- a/pc-bios/dtb/meson.build +++ b/pc-bios/dtb/meson.build @@ -9,7 +9,7 @@ dtc = find_program('dtc', required: false) if dtc.found() foreach out : dtbs f = fs.replace_suffix(out, '.dts') - custom_target(f, + custom_target(out, build_by_default: have_system, input: files(f), output: out, diff --git a/qapi/qom.json b/qapi/qom.json index 3e8debf78c..b133b06447 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -1071,6 +1071,11 @@ # e.g., specific to the workload rather than the run-time or OS # (base64 encoded SHA384 digest). Defaults to all zeros. # +# @quote-generation-socket: socket address for Quote Generation +# Service (QGS). QGS is a daemon running on the host. Without +# it, the guest will not be able to get a TD quote for +# attestation. +# # Since: 10.1 ## { 'struct': 'TdxGuestProperties', @@ -1078,7 +1083,8 @@ '*sept-ve-disable': 'bool', '*mrconfigid': 'str', '*mrowner': 'str', - '*mrownerconfig': 'str' } } + '*mrownerconfig': 'str', + '*quote-generation-socket': 'SocketAddress' } } ## # @ThreadContextProperties: diff --git a/rust/hw/char/pl011/src/device.rs b/rust/hw/char/pl011/src/device.rs index be8387f6f2..5b53f2649f 100644 --- a/rust/hw/char/pl011/src/device.rs +++ b/rust/hw/char/pl011/src/device.rs @@ -2,18 +2,21 @@ // Author(s): Manos Pitsidianakis <manos.pitsidianakis@linaro.org> // SPDX-License-Identifier: GPL-2.0-or-later -use std::{ffi::CStr, mem::size_of, ptr::addr_of_mut}; +use std::{ffi::CStr, mem::size_of}; use qemu_api::{ chardev::{CharBackend, Chardev, Event}, impl_vmstate_forward, irq::{IRQState, InterruptSource}, + log::Log, + log_mask_ln, memory::{hwaddr, MemoryRegion, MemoryRegionOps, MemoryRegionOpsBuilder}, prelude::*, qdev::{Clock, ClockEvent, DeviceImpl, DeviceState, Property, ResetType, ResettablePhasesImpl}, - qom::{ObjectImpl, Owned, ParentField}, + qom::{ObjectImpl, Owned, ParentField, ParentInit}, static_assert, sysbus::{SysBusDevice, SysBusDeviceImpl}, + uninit_field_mut, vmstate::VMStateDescription, }; @@ -163,7 +166,7 @@ impl PL011Impl for PL011State { impl ObjectImpl for PL011State { type ParentType = SysBusDevice; - const INSTANCE_INIT: Option<unsafe fn(&mut Self)> = Some(Self::init); + const INSTANCE_INIT: Option<unsafe fn(ParentInit<Self>)> = Some(Self::init); const INSTANCE_POST_INIT: Option<fn(&Self)> = Some(Self::post_init); const CLASS_INIT: fn(&mut Self::Class) = Self::Class::class_init::<Self>; } @@ -275,8 +278,7 @@ impl PL011Registers { DMACR => { self.dmacr = value; if value & 3 > 0 { - // qemu_log_mask(LOG_UNIMP, "pl011: DMA not implemented\n"); - eprintln!("pl011: DMA not implemented"); + log_mask_ln!(Log::Unimp, "pl011: DMA not implemented"); } } } @@ -303,6 +305,12 @@ impl PL011Registers { } fn write_data_register(&mut self, value: u32) -> bool { + if !self.control.enable_uart() { + log_mask_ln!(Log::GuestError, "PL011 data written to disabled UART"); + } + if !self.control.enable_transmit() { + log_mask_ln!(Log::GuestError, "PL011 data written to disabled TX UART"); + } // interrupts always checked let _ = self.loopback_tx(value.into()); self.int_level |= Interrupt::TX; @@ -488,7 +496,7 @@ impl PL011State { /// `PL011State` type. It must not be called more than once on the same /// location/instance. All its fields are expected to hold uninitialized /// values with the sole exception of `parent_obj`. - unsafe fn init(&mut self) { + unsafe fn init(mut this: ParentInit<Self>) { static PL011_OPS: MemoryRegionOps<PL011State> = MemoryRegionOpsBuilder::<PL011State>::new() .read(&PL011State::read) .write(&PL011State::write) @@ -496,28 +504,23 @@ impl PL011State { .impl_sizes(4, 4) .build(); - // SAFETY: - // - // self and self.iomem are guaranteed to be valid at this point since callers - // must make sure the `self` reference is valid. + // SAFETY: this and this.iomem are guaranteed to be valid at this point MemoryRegion::init_io( - unsafe { &mut *addr_of_mut!(self.iomem) }, - addr_of_mut!(*self), + &mut uninit_field_mut!(*this, iomem), &PL011_OPS, "pl011", 0x1000, ); - self.regs = Default::default(); + uninit_field_mut!(*this, regs).write(Default::default()); - // SAFETY: - // - // self.clock is not initialized at this point; but since `Owned<_>` is - // not Drop, we can overwrite the undefined value without side effects; - // it's not sound but, because for all PL011State instances are created - // by QOM code which calls this function to initialize the fields, at - // leastno code is able to access an invalid self.clock value. - self.clock = self.init_clock_in("clk", &Self::clock_update, ClockEvent::ClockUpdate); + let clock = DeviceState::init_clock_in( + &mut this, + "clk", + &Self::clock_update, + ClockEvent::ClockUpdate, + ); + uninit_field_mut!(*this, clock).write(clock); } const fn clock_update(&self, _event: ClockEvent) { @@ -538,7 +541,7 @@ impl PL011State { u64::from(device_id[(offset - 0xfe0) >> 2]) } Err(_) => { - // qemu_log_mask(LOG_GUEST_ERROR, "pl011_read: Bad offset 0x%x\n", (int)offset); + log_mask_ln!(Log::GuestError, "PL011State::read: Bad offset {offset}"); 0 } Ok(field) => { @@ -570,7 +573,10 @@ impl PL011State { .borrow_mut() .write(field, value as u32, &self.char_backend); } else { - eprintln!("write bad offset {offset} value {value}"); + log_mask_ln!( + Log::GuestError, + "PL011State::write: Bad offset {offset} value {value}" + ); } if update_irq { self.update(); diff --git a/rust/hw/timer/hpet/src/device.rs b/rust/hw/timer/hpet/src/device.rs index 735b2fbef7..acf7251029 100644 --- a/rust/hw/timer/hpet/src/device.rs +++ b/rust/hw/timer/hpet/src/device.rs @@ -4,6 +4,7 @@ use std::{ ffi::{c_int, c_void, CStr}, + mem::MaybeUninit, pin::Pin, ptr::{addr_of_mut, null_mut, NonNull}, slice::from_ref, @@ -20,11 +21,12 @@ use qemu_api::{ hwaddr, MemoryRegion, MemoryRegionOps, MemoryRegionOpsBuilder, MEMTXATTRS_UNSPECIFIED, }, prelude::*, - qdev::{DeviceImpl, DeviceMethods, DeviceState, Property, ResetType, ResettablePhasesImpl}, - qom::{ObjectImpl, ObjectType, ParentField}, + qdev::{DeviceImpl, DeviceState, Property, ResetType, ResettablePhasesImpl}, + qom::{ObjectImpl, ObjectType, ParentField, ParentInit}, qom_isa, sysbus::{SysBusDevice, SysBusDeviceImpl}, timer::{Timer, CLOCK_VIRTUAL, NANOSECONDS_PER_SECOND}, + uninit_field_mut, vmstate::VMStateDescription, vmstate_fields, vmstate_of, vmstate_struct, vmstate_subsections, vmstate_validate, zeroable::Zeroable, @@ -212,13 +214,13 @@ pub struct HPETTimer { } impl HPETTimer { - fn init(&mut self, index: u8, state: &HPETState) { - *self = HPETTimer { + fn new(index: u8, state: *const HPETState) -> HPETTimer { + HPETTimer { index, // SAFETY: the HPETTimer will only be used after the timer // is initialized below. qemu_timer: unsafe { Timer::new() }, - state: NonNull::new((state as *const HPETState).cast_mut()).unwrap(), + state: NonNull::new(state.cast_mut()).unwrap(), config: 0, cmp: 0, fsb: 0, @@ -226,19 +228,15 @@ impl HPETTimer { period: 0, wrap_flag: 0, last: 0, - }; + } + } + fn init_timer_with_cell(cell: &BqlRefCell<Self>) { + let mut timer = cell.borrow_mut(); // SAFETY: HPETTimer is only used as part of HPETState, which is // always pinned. - let qemu_timer = unsafe { Pin::new_unchecked(&mut self.qemu_timer) }; - qemu_timer.init_full( - None, - CLOCK_VIRTUAL, - Timer::NS, - 0, - timer_handler, - &state.timers[self.index as usize], - ) + let qemu_timer = unsafe { Pin::new_unchecked(&mut timer.qemu_timer) }; + qemu_timer.init_full(None, CLOCK_VIRTUAL, Timer::NS, 0, timer_handler, cell); } fn get_state(&self) -> &HPETState { @@ -607,9 +605,18 @@ impl HPETState { } } - fn init_timer(&self) { - for (index, timer) in self.timers.iter().enumerate() { - timer.borrow_mut().init(index.try_into().unwrap(), self); + fn init_timers(this: &mut MaybeUninit<Self>) { + let state = this.as_ptr(); + for index in 0..HPET_MAX_TIMERS { + let mut timer = uninit_field_mut!(*this, timers[index]); + + // Initialize in two steps, to avoid calling Timer::init_full on a + // temporary that can be moved. + let timer = timer.write(BqlRefCell::new(HPETTimer::new( + index.try_into().unwrap(), + state, + ))); + HPETTimer::init_timer_with_cell(timer); } } @@ -690,7 +697,7 @@ impl HPETState { .set(self.counter.get().deposit(shift, len, val)); } - unsafe fn init(&mut self) { + unsafe fn init(mut this: ParentInit<Self>) { static HPET_RAM_OPS: MemoryRegionOps<HPETState> = MemoryRegionOpsBuilder::<HPETState>::new() .read(&HPETState::read) @@ -700,16 +707,14 @@ impl HPETState { .impl_sizes(4, 8) .build(); - // SAFETY: - // self and self.iomem are guaranteed to be valid at this point since callers - // must make sure the `self` reference is valid. MemoryRegion::init_io( - unsafe { &mut *addr_of_mut!(self.iomem) }, - addr_of_mut!(*self), + &mut uninit_field_mut!(*this, iomem), &HPET_RAM_OPS, "hpet", HPET_REG_SPACE_LEN, ); + + Self::init_timers(&mut this); } fn post_init(&self) { @@ -731,7 +736,6 @@ impl HPETState { self.hpet_id.set(HPETFwConfig::assign_hpet_id()?); - self.init_timer(); // 64-bit General Capabilities and ID Register; LegacyReplacementRoute. self.capability.set( HPET_CAP_REV_ID_VALUE << HPET_CAP_REV_ID_SHIFT | @@ -767,7 +771,7 @@ impl HPETState { self.rtc_irq_level.set(0); } - fn decode(&self, mut addr: hwaddr, size: u32) -> HPETAddrDecode { + fn decode(&self, mut addr: hwaddr, size: u32) -> HPETAddrDecode<'_> { let shift = ((addr & 4) * 8) as u32; let len = std::cmp::min(size * 8, 64 - shift); @@ -892,7 +896,7 @@ unsafe impl ObjectType for HPETState { impl ObjectImpl for HPETState { type ParentType = SysBusDevice; - const INSTANCE_INIT: Option<unsafe fn(&mut Self)> = Some(Self::init); + const INSTANCE_INIT: Option<unsafe fn(ParentInit<Self>)> = Some(Self::init); const INSTANCE_POST_INIT: Option<fn(&Self)> = Some(Self::post_init); const CLASS_INIT: fn(&mut Self::Class) = Self::Class::class_init::<Self>; } diff --git a/rust/meson.build b/rust/meson.build index 99ae7956cd..331f11b7e7 100644 --- a/rust/meson.build +++ b/rust/meson.build @@ -20,6 +20,8 @@ proc_macro2_rs_native = dependency('proc-macro2-1-rs', native: true) qemuutil_rs = qemuutil.partial_dependency(link_args: true, links: true) +genrs = [] + subdir('qemu-api-macros') subdir('bits') subdir('qemu-api') @@ -33,5 +35,5 @@ if cargo.found() command: [config_host['MESON'], 'devenv', '--workdir', '@CURRENT_SOURCE_DIR@', cargo, 'fmt'], - depends: bindings_rs) + depends: genrs) endif diff --git a/rust/qemu-api/build.rs b/rust/qemu-api/build.rs index 1e720641d2..7849486c1b 100644 --- a/rust/qemu-api/build.rs +++ b/rust/qemu-api/build.rs @@ -14,7 +14,7 @@ fn main() -> Result<()> { let path = env::var("MESON_BUILD_ROOT") .unwrap_or_else(|_| format!("{}/src", env!("CARGO_MANIFEST_DIR"))); - let file = format!("{path}/bindings.inc.rs"); + let file = format!("{path}/rust/qemu-api/bindings.inc.rs"); let file = Path::new(&file); if !Path::new(&file).exists() { panic!(concat!( diff --git a/rust/qemu-api/meson.build b/rust/qemu-api/meson.build index cac8595a14..a090297c45 100644 --- a/rust/qemu-api/meson.build +++ b/rust/qemu-api/meson.build @@ -7,6 +7,47 @@ if get_option('debug_mutex') _qemu_api_cfg += ['--cfg', 'feature="debug_cell"'] endif +c_enums = [ + 'DeviceCategory', + 'GpioPolarity', + 'MachineInitPhase', + 'MemoryDeviceInfoKind', + 'MigrationPolicy', + 'MigrationPriority', + 'QEMUChrEvent', + 'QEMUClockType', + 'ResetType', + 'device_endian', + 'module_init_type', +] +_qemu_api_bindgen_args = [] +foreach enum : c_enums + _qemu_api_bindgen_args += ['--rustified-enum', enum] +endforeach +c_bitfields = [ + 'ClockEvent', + 'VMStateFlags', +] +foreach enum : c_bitfields + _qemu_api_bindgen_args += ['--bitfield-enum', enum] +endforeach + +# TODO: Remove this comment when the clang/libclang mismatch issue is solved. +# +# Rust bindings generation with `bindgen` might fail in some cases where the +# detected `libclang` does not match the expected `clang` version/target. In +# this case you must pass the path to `clang` and `libclang` to your build +# command invocation using the environment variables CLANG_PATH and +# LIBCLANG_PATH +_qemu_api_bindings_inc_rs = rust.bindgen( + input: 'wrapper.h', + dependencies: common_ss.all_dependencies(), + output: 'bindings.inc.rs', + include_directories: bindings_incdir, + bindgen_version: ['>=0.60.0'], + args: bindgen_args_common + _qemu_api_bindgen_args, + ) + _qemu_api_rs = static_library( 'qemu_api', structured_sources( @@ -21,6 +62,7 @@ _qemu_api_rs = static_library( 'src/errno.rs', 'src/error.rs', 'src/irq.rs', + 'src/log.rs', 'src/memory.rs', 'src/module.rs', 'src/prelude.rs', @@ -28,10 +70,11 @@ _qemu_api_rs = static_library( 'src/qom.rs', 'src/sysbus.rs', 'src/timer.rs', + 'src/uninit.rs', 'src/vmstate.rs', 'src/zeroable.rs', ], - {'.' : bindings_rs}, + {'.' : _qemu_api_bindings_inc_rs}, ), override_options: ['rust_std=2021', 'build.rust_std=2021'], rust_abi: 'rust', diff --git a/rust/qemu-api/src/lib.rs b/rust/qemu-api/src/lib.rs index 93902fc94b..86dcd8ef17 100644 --- a/rust/qemu-api/src/lib.rs +++ b/rust/qemu-api/src/lib.rs @@ -21,12 +21,14 @@ pub mod chardev; pub mod errno; pub mod error; pub mod irq; +pub mod log; pub mod memory; pub mod module; pub mod qdev; pub mod qom; pub mod sysbus; pub mod timer; +pub mod uninit; pub mod vmstate; pub mod zeroable; diff --git a/rust/qemu-api/src/log.rs b/rust/qemu-api/src/log.rs new file mode 100644 index 0000000000..d6c3d6c1b6 --- /dev/null +++ b/rust/qemu-api/src/log.rs @@ -0,0 +1,73 @@ +// Copyright 2025 Bernhard Beschow <shentey@gmail.com> +// SPDX-License-Identifier: GPL-2.0-or-later + +//! Bindings for QEMU's logging infrastructure + +#[repr(u32)] +/// Represents specific error categories within QEMU's logging system. +/// +/// The `Log` enum provides a Rust abstraction for logging errors, corresponding +/// to a subset of the error categories defined in the C implementation. +pub enum Log { + /// Log invalid access caused by the guest. + /// Corresponds to `LOG_GUEST_ERROR` in the C implementation. + GuestError = crate::bindings::LOG_GUEST_ERROR, + + /// Log guest access of unimplemented functionality. + /// Corresponds to `LOG_UNIMP` in the C implementation. + Unimp = crate::bindings::LOG_UNIMP, +} + +/// A macro to log messages conditionally based on a provided mask. +/// +/// The `log_mask_ln` macro checks whether the given mask matches the current +/// log level and, if so, formats and logs the message. It is the Rust +/// counterpart of the `qemu_log_mask()` macro in the C implementation. +/// +/// # Parameters +/// +/// - `$mask`: A log level mask. This should be a variant of the `Log` enum. +/// - `$fmt`: A format string following the syntax and rules of the `format!` +/// macro. It specifies the structure of the log message. +/// - `$args`: Optional arguments to be interpolated into the format string. +/// +/// # Example +/// +/// ``` +/// use qemu_api::{log::Log, log_mask_ln}; +/// +/// let error_address = 0xbad; +/// log_mask_ln!(Log::GuestError, "Address 0x{error_address:x} out of range"); +/// ``` +/// +/// It is also possible to use printf-style formatting, as well as having a +/// trailing `,`: +/// +/// ``` +/// use qemu_api::{log::Log, log_mask_ln}; +/// +/// let error_address = 0xbad; +/// log_mask_ln!( +/// Log::GuestError, +/// "Address 0x{:x} out of range", +/// error_address, +/// ); +/// ``` +#[macro_export] +macro_rules! log_mask_ln { + ($mask:expr, $fmt:tt $($args:tt)*) => {{ + // Type assertion to enforce type `Log` for $mask + let _: Log = $mask; + + if unsafe { + (::qemu_api::bindings::qemu_loglevel & ($mask as std::os::raw::c_int)) != 0 + } { + let formatted_string = format!("{}\n", format_args!($fmt $($args)*)); + let c_string = std::ffi::CString::new(formatted_string).unwrap(); + + unsafe { + ::qemu_api::bindings::qemu_log(c_string.as_ptr()); + } + } + }}; +} diff --git a/rust/qemu-api/src/memory.rs b/rust/qemu-api/src/memory.rs index 9ef2694bd6..e40fad6cf1 100644 --- a/rust/qemu-api/src/memory.rs +++ b/rust/qemu-api/src/memory.rs @@ -16,6 +16,7 @@ use crate::{ callbacks::FnCall, cell::Opaque, prelude::*, + uninit::MaybeUninitField, zeroable::Zeroable, }; @@ -147,7 +148,7 @@ impl MemoryRegion { #[inline(always)] unsafe fn do_init_io( slot: *mut bindings::MemoryRegion, - owner: *mut Object, + owner: *mut bindings::Object, ops: &'static bindings::MemoryRegionOps, name: &'static str, size: u64, @@ -156,7 +157,7 @@ impl MemoryRegion { let cstr = CString::new(name).unwrap(); memory_region_init_io( slot, - owner.cast::<bindings::Object>(), + owner, ops, owner.cast::<c_void>(), cstr.as_ptr(), @@ -166,16 +167,15 @@ impl MemoryRegion { } pub fn init_io<T: IsA<Object>>( - &mut self, - owner: *mut T, + this: &mut MaybeUninitField<'_, T, Self>, ops: &'static MemoryRegionOps<T>, name: &'static str, size: u64, ) { unsafe { Self::do_init_io( - self.0.as_mut_ptr(), - owner.cast::<Object>(), + this.as_mut_ptr().cast(), + MaybeUninitField::parent_mut(this).cast(), &ops.0, name, size, diff --git a/rust/qemu-api/src/prelude.rs b/rust/qemu-api/src/prelude.rs index 43bfcd5fca..8f9e23ee2c 100644 --- a/rust/qemu-api/src/prelude.rs +++ b/rust/qemu-api/src/prelude.rs @@ -11,6 +11,8 @@ pub use crate::cell::BqlRefCell; pub use crate::errno; +pub use crate::log_mask_ln; + pub use crate::qdev::DeviceMethods; pub use crate::qom::InterfaceType; diff --git a/rust/qemu-api/src/qdev.rs b/rust/qemu-api/src/qdev.rs index 0610959f46..36f02fb57d 100644 --- a/rust/qemu-api/src/qdev.rs +++ b/rust/qemu-api/src/qdev.rs @@ -19,7 +19,7 @@ use crate::{ error::{Error, Result}, irq::InterruptSource, prelude::*, - qom::{ObjectClass, ObjectImpl, Owned}, + qom::{ObjectClass, ObjectImpl, Owned, ParentInit}, vmstate::VMStateDescription, }; @@ -247,15 +247,9 @@ unsafe impl ObjectType for DeviceState { } qom_isa!(DeviceState: Object); -/// Trait for methods exposed by the [`DeviceState`] class. The methods can be -/// called on all objects that have the trait `IsA<DeviceState>`. -/// -/// The trait should only be used through the blanket implementation, -/// which guarantees safety via `IsA`. -pub trait DeviceMethods: ObjectDeref -where - Self::Target: IsA<DeviceState>, -{ +/// Initialization methods take a [`ParentInit`] and can be called as +/// associated functions. +impl DeviceState { /// Add an input clock named `name`. Invoke the callback with /// `self` as the first parameter for the events that are requested. /// @@ -266,12 +260,15 @@ where /// which Rust code has a reference to a child object) it would be /// possible for this function to return a `&Clock` too. #[inline] - fn init_clock_in<F: for<'a> FnCall<(&'a Self::Target, ClockEvent)>>( - &self, + pub fn init_clock_in<T: DeviceImpl, F: for<'a> FnCall<(&'a T, ClockEvent)>>( + this: &mut ParentInit<T>, name: &str, _cb: &F, events: ClockEvent, - ) -> Owned<Clock> { + ) -> Owned<Clock> + where + T::ParentType: IsA<DeviceState>, + { fn do_init_clock_in( dev: &DeviceState, name: &str, @@ -287,10 +284,10 @@ where unsafe { let cstr = CString::new(name).unwrap(); let clk = bindings::qdev_init_clock_in( - dev.as_mut_ptr(), + dev.0.as_mut_ptr(), cstr.as_ptr(), cb, - dev.as_void_ptr(), + dev.0.as_void_ptr(), events.0, ); @@ -307,12 +304,12 @@ where // SAFETY: the opaque is "this", which is indeed a pointer to T F::call((unsafe { &*(opaque.cast::<T>()) }, event)) } - Some(rust_clock_cb::<Self::Target, F>) + Some(rust_clock_cb::<T, F>) } else { None }; - do_init_clock_in(self.upcast(), name, cb, events) + do_init_clock_in(unsafe { this.upcast_mut() }, name, cb, events) } /// Add an output clock named `name`. @@ -324,16 +321,30 @@ where /// which Rust code has a reference to a child object) it would be /// possible for this function to return a `&Clock` too. #[inline] - fn init_clock_out(&self, name: &str) -> Owned<Clock> { + pub fn init_clock_out<T: DeviceImpl>(this: &mut ParentInit<T>, name: &str) -> Owned<Clock> + where + T::ParentType: IsA<DeviceState>, + { unsafe { let cstr = CString::new(name).unwrap(); - let clk = bindings::qdev_init_clock_out(self.upcast().as_mut_ptr(), cstr.as_ptr()); + let dev: &mut DeviceState = this.upcast_mut(); + let clk = bindings::qdev_init_clock_out(dev.0.as_mut_ptr(), cstr.as_ptr()); let clk: &Clock = Clock::from_raw(clk); Owned::from(clk) } } +} +/// Trait for methods exposed by the [`DeviceState`] class. The methods can be +/// called on all objects that have the trait `IsA<DeviceState>`. +/// +/// The trait should only be used through the blanket implementation, +/// which guarantees safety via `IsA`. +pub trait DeviceMethods: ObjectDeref +where + Self::Target: IsA<DeviceState>, +{ fn prop_set_chr(&self, propname: &str, chr: &Owned<Chardev>) { assert!(bql_locked()); let c_propname = CString::new(propname).unwrap(); diff --git a/rust/qemu-api/src/qom.rs b/rust/qemu-api/src/qom.rs index 14f98fee60..e20ee014cb 100644 --- a/rust/qemu-api/src/qom.rs +++ b/rust/qemu-api/src/qom.rs @@ -95,7 +95,8 @@ use std::{ ffi::{c_void, CStr}, fmt, - mem::ManuallyDrop, + marker::PhantomData, + mem::{ManuallyDrop, MaybeUninit}, ops::{Deref, DerefMut}, ptr::NonNull, }; @@ -206,13 +207,190 @@ impl<T: fmt::Display + ObjectType> fmt::Display for ParentField<T> { } } +/// This struct knows that the superclasses of the object have already been +/// initialized. +/// +/// The declaration of `ParentInit` is.. *"a kind of magic"*. It uses a +/// technique that is found in several crates, the main ones probably being +/// `ghost-cell` (in fact it was introduced by the [`GhostCell` paper](https://plv.mpi-sws.org/rustbelt/ghostcell/)) +/// and `generativity`. +/// +/// The `PhantomData` makes the `ParentInit` type *invariant* with respect to +/// the lifetime argument `'init`. This, together with the `for<'...>` in +/// `[ParentInit::with]`, block any attempt of the compiler to be creative when +/// operating on types of type `ParentInit` and to extend their lifetimes. In +/// particular, it ensures that the `ParentInit` cannot be made to outlive the +/// `rust_instance_init()` function that creates it, and therefore that the +/// `&'init T` reference is valid. +/// +/// This implementation of the same concept, without the QOM baggage, can help +/// understanding the effect: +/// +/// ``` +/// use std::marker::PhantomData; +/// +/// #[derive(PartialEq, Eq)] +/// pub struct Jail<'closure, T: Copy>(&'closure T, PhantomData<fn(&'closure ()) -> &'closure ()>); +/// +/// impl<'closure, T: Copy> Jail<'closure, T> { +/// fn get(&self) -> T { +/// *self.0 +/// } +/// +/// #[inline] +/// fn with<U>(v: T, f: impl for<'id> FnOnce(Jail<'id, T>) -> U) -> U { +/// let parent_init = Jail(&v, PhantomData); +/// f(parent_init) +/// } +/// } +/// ``` +/// +/// It's impossible to escape the `Jail`; `token1` cannot be moved out of the +/// closure: +/// +/// ```ignore +/// let x = 42; +/// let escape = Jail::with(&x, |token1| { +/// println!("{}", token1.get()); +/// // fails to compile... +/// token1 +/// }); +/// // ... so you cannot do this: +/// println!("{}", escape.get()); +/// ``` +/// +/// Likewise, in the QOM case the `ParentInit` cannot be moved out of +/// `instance_init()`. Without this trick it would be possible to stash a +/// `ParentInit` and use it later to access uninitialized memory. +/// +/// Here is another example, showing how separately-created "identities" stay +/// isolated: +/// +/// ```ignore +/// impl<'closure, T: Copy> Clone for Jail<'closure, T> { +/// fn clone(&self) -> Jail<'closure, T> { +/// Jail(self.0, PhantomData) +/// } +/// } +/// +/// fn main() { +/// Jail::with(42, |token1| { +/// // this works and returns true: the clone has the same "identity" +/// println!("{}", token1 == token1.clone()); +/// Jail::with(42, |token2| { +/// // here the outer token remains accessible... +/// println!("{}", token1.get()); +/// // ... but the two are separate: this fails to compile: +/// println!("{}", token1 == token2); +/// }); +/// }); +/// } +/// ``` +pub struct ParentInit<'init, T>( + &'init mut MaybeUninit<T>, + PhantomData<fn(&'init ()) -> &'init ()>, +); + +impl<'init, T> ParentInit<'init, T> { + #[inline] + pub fn with(obj: &'init mut MaybeUninit<T>, f: impl for<'id> FnOnce(ParentInit<'id, T>)) { + let parent_init = ParentInit(obj, PhantomData); + f(parent_init) + } +} + +impl<T: ObjectType> ParentInit<'_, T> { + /// Return the receiver as a mutable raw pointer to Object. + /// + /// # Safety + /// + /// Fields beyond `Object` could be uninitialized and it's your + /// responsibility to avoid that they're used when the pointer is + /// dereferenced, either directly or through a cast. + pub fn as_object_mut_ptr(&self) -> *mut bindings::Object { + self.as_object_ptr().cast_mut() + } + + /// Return the receiver as a mutable raw pointer to Object. + /// + /// # Safety + /// + /// Fields beyond `Object` could be uninitialized and it's your + /// responsibility to avoid that they're used when the pointer is + /// dereferenced, either directly or through a cast. + pub fn as_object_ptr(&self) -> *const bindings::Object { + self.0.as_ptr().cast() + } +} + +impl<'a, T: ObjectImpl> ParentInit<'a, T> { + /// Convert from a derived type to one of its parent types, which + /// have already been initialized. + /// + /// # Safety + /// + /// Structurally this is always a safe operation; the [`IsA`] trait + /// provides static verification trait that `Self` dereferences to `U` or + /// a child of `U`, and only parent types of `T` are allowed. + /// + /// However, while the fields of the resulting reference are initialized, + /// calls might use uninitialized fields of the subclass. It is your + /// responsibility to avoid this. + pub unsafe fn upcast<U: ObjectType>(&self) -> &'a U + where + T::ParentType: IsA<U>, + { + // SAFETY: soundness is declared via IsA<U>, which is an unsafe trait; + // the parent has been initialized before `instance_init `is called + unsafe { &*(self.0.as_ptr().cast::<U>()) } + } + + /// Convert from a derived type to one of its parent types, which + /// have already been initialized. + /// + /// # Safety + /// + /// Structurally this is always a safe operation; the [`IsA`] trait + /// provides static verification trait that `Self` dereferences to `U` or + /// a child of `U`, and only parent types of `T` are allowed. + /// + /// However, while the fields of the resulting reference are initialized, + /// calls might use uninitialized fields of the subclass. It is your + /// responsibility to avoid this. + pub unsafe fn upcast_mut<U: ObjectType>(&mut self) -> &'a mut U + where + T::ParentType: IsA<U>, + { + // SAFETY: soundness is declared via IsA<U>, which is an unsafe trait; + // the parent has been initialized before `instance_init `is called + unsafe { &mut *(self.0.as_mut_ptr().cast::<U>()) } + } +} + +impl<T> Deref for ParentInit<'_, T> { + type Target = MaybeUninit<T>; + + fn deref(&self) -> &Self::Target { + self.0 + } +} + +impl<T> DerefMut for ParentInit<'_, T> { + fn deref_mut(&mut self) -> &mut Self::Target { + self.0 + } +} + unsafe extern "C" fn rust_instance_init<T: ObjectImpl>(obj: *mut bindings::Object) { - let mut state = NonNull::new(obj).unwrap().cast::<T>(); + let mut state = NonNull::new(obj).unwrap().cast::<MaybeUninit<T>>(); + // SAFETY: obj is an instance of T, since rust_instance_init<T> // is called from QOM core as the instance_init function // for class T unsafe { - T::INSTANCE_INIT.unwrap()(state.as_mut()); + ParentInit::with(state.as_mut(), |parent_init| { + T::INSTANCE_INIT.unwrap()(parent_init); + }); } } @@ -479,7 +657,7 @@ pub trait ObjectImpl: ObjectType + IsA<Object> { /// /// FIXME: The argument is not really a valid reference. `&mut /// MaybeUninit<Self>` would be a better description. - const INSTANCE_INIT: Option<unsafe fn(&mut Self)> = None; + const INSTANCE_INIT: Option<unsafe fn(ParentInit<Self>)> = None; /// Function that is called to finish initialization of an object, once /// `INSTANCE_INIT` functions have been called. diff --git a/rust/qemu-api/src/uninit.rs b/rust/qemu-api/src/uninit.rs new file mode 100644 index 0000000000..04123b4ae9 --- /dev/null +++ b/rust/qemu-api/src/uninit.rs @@ -0,0 +1,85 @@ +//! Access fields of a [`MaybeUninit`] + +use std::{ + mem::MaybeUninit, + ops::{Deref, DerefMut}, +}; + +pub struct MaybeUninitField<'a, T, U> { + parent: &'a mut MaybeUninit<T>, + child: *mut U, +} + +impl<'a, T, U> MaybeUninitField<'a, T, U> { + #[doc(hidden)] + pub fn new(parent: &'a mut MaybeUninit<T>, child: *mut U) -> Self { + MaybeUninitField { parent, child } + } + + /// Return a constant pointer to the containing object of the field. + /// + /// Because the `MaybeUninitField` remembers the containing object, + /// it is possible to use it in foreign APIs that initialize the + /// child. + pub fn parent(f: &Self) -> *const T { + f.parent.as_ptr() + } + + /// Return a mutable pointer to the containing object. + /// + /// Because the `MaybeUninitField` remembers the containing object, + /// it is possible to use it in foreign APIs that initialize the + /// child. + pub fn parent_mut(f: &mut Self) -> *mut T { + f.parent.as_mut_ptr() + } +} + +impl<'a, T, U> Deref for MaybeUninitField<'a, T, U> { + type Target = MaybeUninit<U>; + + fn deref(&self) -> &MaybeUninit<U> { + // SAFETY: self.child was obtained by dereferencing a valid mutable + // reference; the content of the memory may be invalid or uninitialized + // but MaybeUninit<_> makes no assumption on it + unsafe { &*(self.child.cast()) } + } +} + +impl<'a, T, U> DerefMut for MaybeUninitField<'a, T, U> { + fn deref_mut(&mut self) -> &mut MaybeUninit<U> { + // SAFETY: self.child was obtained by dereferencing a valid mutable + // reference; the content of the memory may be invalid or uninitialized + // but MaybeUninit<_> makes no assumption on it + unsafe { &mut *(self.child.cast()) } + } +} + +/// ``` +/// #[derive(Debug)] +/// struct S { +/// x: u32, +/// y: u32, +/// } +/// +/// # use std::mem::MaybeUninit; +/// # use qemu_api::{assert_match, uninit_field_mut}; +/// +/// let mut s: MaybeUninit<S> = MaybeUninit::zeroed(); +/// uninit_field_mut!(s, x).write(5); +/// let s = unsafe { s.assume_init() }; +/// assert_match!(s, S { x: 5, y: 0 }); +/// ``` +#[macro_export] +macro_rules! uninit_field_mut { + ($container:expr, $($field:tt)+) => {{ + let container__: &mut ::std::mem::MaybeUninit<_> = &mut $container; + let container_ptr__ = container__.as_mut_ptr(); + + // SAFETY: the container is not used directly, only through a MaybeUninit<>, + // so the safety is delegated to the caller and to final invocation of + // assume_init() + let target__ = unsafe { std::ptr::addr_of_mut!((*container_ptr__).$($field)+) }; + $crate::uninit::MaybeUninitField::new(container__, target__) + }}; +} diff --git a/rust/wrapper.h b/rust/qemu-api/wrapper.h index 6060d3ba1a..15a1b19847 100644 --- a/rust/wrapper.h +++ b/rust/qemu-api/wrapper.h @@ -48,6 +48,8 @@ typedef enum memory_order { #endif /* __CLANG_STDATOMIC_H */ #include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/log-for-trace.h" #include "qemu/module.h" #include "qemu-io.h" #include "system/system.h" diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 40aefb38f6..0d35e95430 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -7349,9 +7349,6 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, if (threads_per_pkg > 1) { *ebx |= threads_per_pkg << 16; } - if (!cpu->enable_pmu) { - *ecx &= ~CPUID_EXT_PDCM; - } break; case 2: /* cache info: needed for Pentium Pro compatibility */ @@ -8341,6 +8338,13 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) } } + if (!cpu->enable_pmu) { + mark_unavailable_features(cpu, FEAT_1_ECX, + env->user_features[FEAT_1_ECX] & CPUID_EXT_PDCM, + "This feature is not available due to PMU being disabled"); + env->features[FEAT_1_ECX] &= ~CPUID_EXT_PDCM; + } + for (i = 0; i < ARRAY_SIZE(feature_dependencies); i++) { FeatureDep *d = &feature_dependencies[i]; if (!(env->features[d->from.index] & d->from.mask)) { diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 5910dcf74d..51e10139df 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -2269,7 +2269,7 @@ struct ArchCPU { bool enable_cpuid_0xb; /* Force to enable cpuid 0x1f */ - bool enable_cpuid_0x1f; + bool force_cpuid_0x1f; /* Enable auto level-increase for all CPUID leaves */ bool full_cpuid_auto_level; @@ -2539,7 +2539,7 @@ void mark_forced_on_features(X86CPU *cpu, FeatureWord w, uint64_t mask, static inline bool x86_has_cpuid_0x1f(X86CPU *cpu) { - return cpu->enable_cpuid_0x1f || + return cpu->force_cpuid_0x1f || x86_has_extended_topo(cpu->env.avail_cpu_topo); } diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 56a6b9b638..234878c613 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -6170,6 +6170,21 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) break; } break; + case KVM_EXIT_TDX: + /* + * run->tdx is already set up for the case where userspace + * does not handle the TDVMCALL. + */ + switch (run->tdx.nr) { + case TDVMCALL_GET_QUOTE: + tdx_handle_get_quote(cpu, run); + break; + case TDVMCALL_GET_TD_VM_CALL_INFO: + tdx_handle_get_tdvmcall_info(cpu, run); + break; + } + ret = 0; + break; default: fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason); ret = -1; diff --git a/target/i386/kvm/meson.build b/target/i386/kvm/meson.build index 3f44cdedb7..2675bf8902 100644 --- a/target/i386/kvm/meson.build +++ b/target/i386/kvm/meson.build @@ -8,7 +8,7 @@ i386_kvm_ss.add(files( i386_kvm_ss.add(when: 'CONFIG_XEN_EMU', if_true: files('xen-emu.c')) -i386_kvm_ss.add(when: 'CONFIG_TDX', if_true: files('tdx.c'), if_false: files('tdx-stub.c')) +i386_kvm_ss.add(when: 'CONFIG_TDX', if_true: files('tdx.c', 'tdx-quote-generator.c'), if_false: files('tdx-stub.c')) i386_system_ss.add(when: 'CONFIG_HYPERV', if_true: files('hyperv.c'), if_false: files('hyperv-stub.c')) diff --git a/target/i386/kvm/tdx-quote-generator.c b/target/i386/kvm/tdx-quote-generator.c new file mode 100644 index 0000000000..f59715f617 --- /dev/null +++ b/target/i386/kvm/tdx-quote-generator.c @@ -0,0 +1,300 @@ +/* + * QEMU TDX Quote Generation Support + * + * Copyright (c) 2025 Intel Corporation + * + * Author: + * Xiaoyao Li <xiaoyao.li@intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "qapi/qapi-visit-sockets.h" + +#include "tdx-quote-generator.h" + +#define QGS_MSG_LIB_MAJOR_VER 1 +#define QGS_MSG_LIB_MINOR_VER 1 + +typedef enum _qgs_msg_type_t { + GET_QUOTE_REQ = 0, + GET_QUOTE_RESP = 1, + GET_COLLATERAL_REQ = 2, + GET_COLLATERAL_RESP = 3, + GET_PLATFORM_INFO_REQ = 4, + GET_PLATFORM_INFO_RESP = 5, + QGS_MSG_TYPE_MAX +} qgs_msg_type_t; + +typedef struct _qgs_msg_header_t { + uint16_t major_version; + uint16_t minor_version; + uint32_t type; + uint32_t size; // size of the whole message, include this header, in byte + uint32_t error_code; // used in response only +} qgs_msg_header_t; + +typedef struct _qgs_msg_get_quote_req_t { + qgs_msg_header_t header; // header.type = GET_QUOTE_REQ + uint32_t report_size; // cannot be 0 + uint32_t id_list_size; // length of id_list, in byte, can be 0 +} qgs_msg_get_quote_req_t; + +typedef struct _qgs_msg_get_quote_resp_s { + qgs_msg_header_t header; // header.type = GET_QUOTE_RESP + uint32_t selected_id_size; // can be 0 in case only one id is sent in request + uint32_t quote_size; // length of quote_data, in byte + uint8_t id_quote[]; // selected id followed by quote +} qgs_msg_get_quote_resp_t; + +#define HEADER_SIZE 4 + +static uint32_t decode_header(const char *buf, size_t len) { + if (len < HEADER_SIZE) { + return 0; + } + uint32_t msg_size = 0; + for (uint32_t i = 0; i < HEADER_SIZE; ++i) { + msg_size = msg_size * 256 + (buf[i] & 0xFF); + } + return msg_size; +} + +static void encode_header(char *buf, size_t len, uint32_t size) { + assert(len >= HEADER_SIZE); + buf[0] = ((size >> 24) & 0xFF); + buf[1] = ((size >> 16) & 0xFF); + buf[2] = ((size >> 8) & 0xFF); + buf[3] = (size & 0xFF); +} + +static void tdx_generate_quote_cleanup(TdxGenerateQuoteTask *task) +{ + timer_del(&task->timer); + + g_source_remove(task->watch); + qio_channel_close(QIO_CHANNEL(task->sioc), NULL); + object_unref(OBJECT(task->sioc)); + + task->completion(task); +} + +static gboolean tdx_get_quote_read(QIOChannel *ioc, GIOCondition condition, + gpointer opaque) +{ + TdxGenerateQuoteTask *task = opaque; + Error *err = NULL; + int ret; + + ret = qio_channel_read(ioc, task->receive_buf + task->receive_buf_received, + task->payload_len - task->receive_buf_received, &err); + if (ret < 0) { + if (ret == QIO_CHANNEL_ERR_BLOCK) { + return G_SOURCE_CONTINUE; + } else { + error_report_err(err); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + } + + if (ret == 0) { + error_report("End of file before reply received"); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + + task->receive_buf_received += ret; + if (task->receive_buf_received >= HEADER_SIZE) { + uint32_t len = decode_header(task->receive_buf, + task->receive_buf_received); + if (len == 0 || + len > (task->payload_len - HEADER_SIZE)) { + error_report("Message len %u must be non-zero & less than %zu", + len, (task->payload_len - HEADER_SIZE)); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + + /* Now we know the size, shrink to fit */ + task->payload_len = HEADER_SIZE + len; + task->receive_buf = g_renew(char, + task->receive_buf, + task->payload_len); + } + + if (task->receive_buf_received >= (sizeof(qgs_msg_header_t) + HEADER_SIZE)) { + qgs_msg_header_t *hdr = (qgs_msg_header_t *)(task->receive_buf + HEADER_SIZE); + if (hdr->major_version != QGS_MSG_LIB_MAJOR_VER || + hdr->minor_version != QGS_MSG_LIB_MINOR_VER) { + error_report("Invalid QGS message header version %d.%d", + hdr->major_version, + hdr->minor_version); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + if (hdr->type != GET_QUOTE_RESP) { + error_report("Invalid QGS message type %d", + hdr->type); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + if (hdr->size > (task->payload_len - HEADER_SIZE)) { + error_report("QGS message size %d exceeds payload capacity %zu", + hdr->size, task->payload_len); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + if (hdr->error_code != 0) { + error_report("QGS message error code %d", + hdr->error_code); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + } + if (task->receive_buf_received >= (sizeof(qgs_msg_get_quote_resp_t) + HEADER_SIZE)) { + qgs_msg_get_quote_resp_t *msg = (qgs_msg_get_quote_resp_t *)(task->receive_buf + HEADER_SIZE); + if (msg->selected_id_size != 0) { + error_report("QGS message selected ID was %d not 0", + msg->selected_id_size); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + + if ((task->payload_len - HEADER_SIZE - sizeof(qgs_msg_get_quote_resp_t)) != + msg->quote_size) { + error_report("QGS quote size %d should be %zu", + msg->quote_size, + (task->payload_len - sizeof(qgs_msg_get_quote_resp_t))); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + goto end; + } + } + + if (task->receive_buf_received == task->payload_len) { + size_t strip = HEADER_SIZE + sizeof(qgs_msg_get_quote_resp_t); + memmove(task->receive_buf, + task->receive_buf + strip, + task->receive_buf_received - strip); + task->receive_buf_received -= strip; + task->status_code = TDX_VP_GET_QUOTE_SUCCESS; + goto end; + } + + return G_SOURCE_CONTINUE; + +end: + tdx_generate_quote_cleanup(task); + return G_SOURCE_REMOVE; +} + +static gboolean tdx_send_report(QIOChannel *ioc, GIOCondition condition, + gpointer opaque) +{ + TdxGenerateQuoteTask *task = opaque; + Error *err = NULL; + int ret; + + ret = qio_channel_write(ioc, task->send_data + task->send_data_sent, + task->send_data_size - task->send_data_sent, &err); + if (ret < 0) { + if (ret == QIO_CHANNEL_ERR_BLOCK) { + ret = 0; + } else { + error_report_err(err); + task->status_code = TDX_VP_GET_QUOTE_ERROR; + tdx_generate_quote_cleanup(task); + goto end; + } + } + task->send_data_sent += ret; + + if (task->send_data_sent == task->send_data_size) { + task->watch = qio_channel_add_watch(QIO_CHANNEL(task->sioc), G_IO_IN, + tdx_get_quote_read, task, NULL); + goto end; + } + + return G_SOURCE_CONTINUE; + +end: + return G_SOURCE_REMOVE; +} + +static void tdx_quote_generator_connected(QIOTask *qio_task, gpointer opaque) +{ + TdxGenerateQuoteTask *task = opaque; + Error *err = NULL; + int ret; + + ret = qio_task_propagate_error(qio_task, &err); + if (ret) { + error_report_err(err); + task->status_code = TDX_VP_GET_QUOTE_QGS_UNAVAILABLE; + tdx_generate_quote_cleanup(task); + return; + } + + task->watch = qio_channel_add_watch(QIO_CHANNEL(task->sioc), G_IO_OUT, + tdx_send_report, task, NULL); +} + +#define TRANSACTION_TIMEOUT 30000 + +static void getquote_expired(void *opaque) +{ + TdxGenerateQuoteTask *task = opaque; + + task->status_code = TDX_VP_GET_QUOTE_ERROR; + tdx_generate_quote_cleanup(task); +} + +static void setup_get_quote_timer(TdxGenerateQuoteTask *task) +{ + int64_t time; + + timer_init_ms(&task->timer, QEMU_CLOCK_VIRTUAL, getquote_expired, task); + time = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL); + timer_mod(&task->timer, time + TRANSACTION_TIMEOUT); +} + +void tdx_generate_quote(TdxGenerateQuoteTask *task, + SocketAddress *qg_sock_addr) +{ + QIOChannelSocket *sioc; + qgs_msg_get_quote_req_t msg; + + /* Prepare a QGS message prelude */ + msg.header.major_version = QGS_MSG_LIB_MAJOR_VER; + msg.header.minor_version = QGS_MSG_LIB_MINOR_VER; + msg.header.type = GET_QUOTE_REQ; + msg.header.size = sizeof(msg) + task->send_data_size; + msg.header.error_code = 0; + msg.report_size = task->send_data_size; + msg.id_list_size = 0; + + /* Make room to add the QGS message prelude */ + task->send_data = g_renew(char, + task->send_data, + task->send_data_size + sizeof(msg) + HEADER_SIZE); + memmove(task->send_data + sizeof(msg) + HEADER_SIZE, + task->send_data, + task->send_data_size); + memcpy(task->send_data + HEADER_SIZE, + &msg, + sizeof(msg)); + encode_header(task->send_data, HEADER_SIZE, task->send_data_size + sizeof(msg)); + task->send_data_size += sizeof(msg) + HEADER_SIZE; + + sioc = qio_channel_socket_new(); + task->sioc = sioc; + + setup_get_quote_timer(task); + + qio_channel_socket_connect_async(sioc, qg_sock_addr, + tdx_quote_generator_connected, task, + NULL, NULL); +} diff --git a/target/i386/kvm/tdx-quote-generator.h b/target/i386/kvm/tdx-quote-generator.h new file mode 100644 index 0000000000..3bd9b8ef33 --- /dev/null +++ b/target/i386/kvm/tdx-quote-generator.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef QEMU_I386_TDX_QUOTE_GENERATOR_H +#define QEMU_I386_TDX_QUOTE_GENERATOR_H + +#include "qom/object_interfaces.h" +#include "io/channel-socket.h" +#include "exec/hwaddr.h" + +#define TDX_GET_QUOTE_STRUCTURE_VERSION 1ULL + +#define TDX_VP_GET_QUOTE_SUCCESS 0ULL +#define TDX_VP_GET_QUOTE_IN_FLIGHT (-1ULL) +#define TDX_VP_GET_QUOTE_ERROR 0x8000000000000000ULL +#define TDX_VP_GET_QUOTE_QGS_UNAVAILABLE 0x8000000000000001ULL + +/* Limit to avoid resource starvation. */ +#define TDX_GET_QUOTE_MAX_BUF_LEN (128 * 1024) +#define TDX_MAX_GET_QUOTE_REQUEST 16 + +#define TDX_GET_QUOTE_HDR_SIZE 24 + +/* Format of pages shared with guest. */ +struct tdx_get_quote_header { + /* Format version: must be 1 in little endian. */ + uint64_t structure_version; + + /* + * GetQuote status code in little endian: + * Guest must set error_code to 0 to avoid information leak. + * Qemu sets this before interrupting guest. + */ + uint64_t error_code; + + /* + * in-message size in little endian: The message will follow this header. + * The in-message will be send to QGS. + */ + uint32_t in_len; + + /* + * out-message size in little endian: + * On request, out_len must be zero to avoid information leak. + * On return, message size from QGS. Qemu overwrites this field. + * The message will follows this header. The in-message is overwritten. + */ + uint32_t out_len; + + /* + * Message buffer follows. + * Guest sets message that will be send to QGS. If out_len > in_len, guest + * should zero remaining buffer to avoid information leak. + * Qemu overwrites this buffer with a message returned from QGS. + */ +}; + +typedef struct TdxGenerateQuoteTask { + hwaddr buf_gpa; + hwaddr payload_gpa; + uint64_t payload_len; + + char *send_data; + uint64_t send_data_size; + uint64_t send_data_sent; + + char *receive_buf; + uint64_t receive_buf_received; + + uint64_t status_code; + struct tdx_get_quote_header hdr; + + QIOChannelSocket *sioc; + guint watch; + QEMUTimer timer; + + void (*completion)(struct TdxGenerateQuoteTask *task); + void *opaque; +} TdxGenerateQuoteTask; + +void tdx_generate_quote(TdxGenerateQuoteTask *task, SocketAddress *qg_sock_addr); + +#endif /* QEMU_I386_TDX_QUOTE_GENERATOR_H */ diff --git a/target/i386/kvm/tdx-stub.c b/target/i386/kvm/tdx-stub.c index 720a4ff046..76fee49eff 100644 --- a/target/i386/kvm/tdx-stub.c +++ b/target/i386/kvm/tdx-stub.c @@ -18,3 +18,11 @@ int tdx_handle_report_fatal_error(X86CPU *cpu, struct kvm_run *run) { return -EINVAL; } + +void tdx_handle_get_quote(X86CPU *cpu, struct kvm_run *run) +{ +} + +void tdx_handle_get_tdvmcall_info(X86CPU *cpu, struct kvm_run *run) +{ +} diff --git a/target/i386/kvm/tdx.c b/target/i386/kvm/tdx.c index 820ca3614e..e809e4b2df 100644 --- a/target/i386/kvm/tdx.c +++ b/target/i386/kvm/tdx.c @@ -14,12 +14,14 @@ #include "qemu/base64.h" #include "qemu/mmap-alloc.h" #include "qapi/error.h" +#include "qapi/qapi-visit-sockets.h" #include "qom/object_interfaces.h" #include "crypto/hash.h" #include "system/kvm_int.h" #include "system/runstate.h" #include "system/system.h" #include "system/ramblock.h" +#include "system/address-spaces.h" #include <linux/kvm_para.h> @@ -32,6 +34,7 @@ #include "hw/i386/tdvf-hob.h" #include "kvm_i386.h" #include "tdx.h" +#include "tdx-quote-generator.h" #include "standard-headers/asm-x86/kvm_para.h" @@ -739,14 +742,20 @@ static int tdx_kvm_type(X86ConfidentialGuest *cg) static void tdx_cpu_instance_init(X86ConfidentialGuest *cg, CPUState *cpu) { + X86CPUClass *xcc = X86_CPU_GET_CLASS(cpu); X86CPU *x86cpu = X86_CPU(cpu); + if (xcc->model) { + error_report("Named cpu model is not supported for TDX yet!"); + exit(1); + } + object_property_set_bool(OBJECT(cpu), "pmu", false, &error_abort); /* invtsc is fixed1 for TD guest */ object_property_set_bool(OBJECT(cpu), "invtsc", true, &error_abort); - x86cpu->enable_cpuid_0x1f = true; + x86cpu->force_cpuid_0x1f = true; } static uint32_t tdx_adjust_cpuid_features(X86ConfidentialGuest *cg, @@ -1026,7 +1035,9 @@ int tdx_pre_create_vcpu(CPUState *cpu, Error **errp) return -1; } if (data_len != QCRYPTO_HASH_DIGEST_LEN_SHA384) { - error_setg(errp, "TDX: failed to decode mrconfigid"); + error_setg(errp, "TDX 'mrconfigid' sha384 digest was %ld bytes, " + "expected %d bytes", data_len, + QCRYPTO_HASH_DIGEST_LEN_SHA384); return -1; } memcpy(init_vm->mrconfigid, data, data_len); @@ -1039,7 +1050,9 @@ int tdx_pre_create_vcpu(CPUState *cpu, Error **errp) return -1; } if (data_len != QCRYPTO_HASH_DIGEST_LEN_SHA384) { - error_setg(errp, "TDX: failed to decode mrowner"); + error_setg(errp, "TDX 'mrowner' sha384 digest was %ld bytes, " + "expected %d bytes", data_len, + QCRYPTO_HASH_DIGEST_LEN_SHA384); return -1; } memcpy(init_vm->mrowner, data, data_len); @@ -1052,7 +1065,9 @@ int tdx_pre_create_vcpu(CPUState *cpu, Error **errp) return -1; } if (data_len != QCRYPTO_HASH_DIGEST_LEN_SHA384) { - error_setg(errp, "TDX: failed to decode mrownerconfig"); + error_setg(errp, "TDX 'mrownerconfig' sha384 digest was %ld bytes, " + "expected %d bytes", data_len, + QCRYPTO_HASH_DIGEST_LEN_SHA384); return -1; } memcpy(init_vm->mrownerconfig, data, data_len); @@ -1108,6 +1123,151 @@ int tdx_parse_tdvf(void *flash_ptr, int size) return tdvf_parse_metadata(&tdx_guest->tdvf, flash_ptr, size); } +static void tdx_get_quote_completion(TdxGenerateQuoteTask *task) +{ + TdxGuest *tdx = task->opaque; + int ret; + + /* Maintain the number of in-flight requests. */ + qemu_mutex_lock(&tdx->lock); + tdx->num--; + qemu_mutex_unlock(&tdx->lock); + + if (task->status_code == TDX_VP_GET_QUOTE_SUCCESS) { + ret = address_space_write(&address_space_memory, task->payload_gpa, + MEMTXATTRS_UNSPECIFIED, task->receive_buf, + task->receive_buf_received); + if (ret != MEMTX_OK) { + error_report("TDX: get-quote: failed to write quote data."); + } else { + task->hdr.out_len = cpu_to_le64(task->receive_buf_received); + } + } + task->hdr.error_code = cpu_to_le64(task->status_code); + + /* Publish the response contents before marking this request completed. */ + smp_wmb(); + ret = address_space_write(&address_space_memory, task->buf_gpa, + MEMTXATTRS_UNSPECIFIED, &task->hdr, + TDX_GET_QUOTE_HDR_SIZE); + if (ret != MEMTX_OK) { + error_report("TDX: get-quote: failed to update GetQuote header."); + } + + g_free(task->send_data); + g_free(task->receive_buf); + g_free(task); + object_unref(tdx); +} + +void tdx_handle_get_quote(X86CPU *cpu, struct kvm_run *run) +{ + TdxGenerateQuoteTask *task; + struct tdx_get_quote_header hdr; + hwaddr buf_gpa = run->tdx.get_quote.gpa; + uint64_t buf_len = run->tdx.get_quote.size; + + QEMU_BUILD_BUG_ON(sizeof(struct tdx_get_quote_header) != TDX_GET_QUOTE_HDR_SIZE); + + run->tdx.get_quote.ret = TDG_VP_VMCALL_INVALID_OPERAND; + + if (buf_len == 0) { + return; + } + + if (!QEMU_IS_ALIGNED(buf_gpa, 4096) || !QEMU_IS_ALIGNED(buf_len, 4096)) { + run->tdx.get_quote.ret = TDG_VP_VMCALL_ALIGN_ERROR; + return; + } + + if (address_space_read(&address_space_memory, buf_gpa, MEMTXATTRS_UNSPECIFIED, + &hdr, TDX_GET_QUOTE_HDR_SIZE) != MEMTX_OK) { + error_report("TDX: get-quote: failed to read GetQuote header."); + return; + } + + if (le64_to_cpu(hdr.structure_version) != TDX_GET_QUOTE_STRUCTURE_VERSION) { + return; + } + + /* Only safe-guard check to avoid too large buffer size. */ + if (buf_len > TDX_GET_QUOTE_MAX_BUF_LEN || + le32_to_cpu(hdr.in_len) > buf_len - TDX_GET_QUOTE_HDR_SIZE) { + return; + } + + if (!tdx_guest->qg_sock_addr) { + hdr.error_code = cpu_to_le64(TDX_VP_GET_QUOTE_QGS_UNAVAILABLE); + if (address_space_write(&address_space_memory, buf_gpa, + MEMTXATTRS_UNSPECIFIED, + &hdr, TDX_GET_QUOTE_HDR_SIZE) != MEMTX_OK) { + error_report("TDX: failed to update GetQuote header."); + return; + } + run->tdx.get_quote.ret = TDG_VP_VMCALL_SUCCESS; + return; + } + + qemu_mutex_lock(&tdx_guest->lock); + if (tdx_guest->num >= TDX_MAX_GET_QUOTE_REQUEST) { + qemu_mutex_unlock(&tdx_guest->lock); + run->tdx.get_quote.ret = TDG_VP_VMCALL_RETRY; + return; + } + tdx_guest->num++; + qemu_mutex_unlock(&tdx_guest->lock); + + task = g_new(TdxGenerateQuoteTask, 1); + task->buf_gpa = buf_gpa; + task->payload_gpa = buf_gpa + TDX_GET_QUOTE_HDR_SIZE; + task->payload_len = buf_len - TDX_GET_QUOTE_HDR_SIZE; + task->hdr = hdr; + task->completion = tdx_get_quote_completion; + + task->send_data_size = le32_to_cpu(hdr.in_len); + task->send_data = g_malloc(task->send_data_size); + task->send_data_sent = 0; + + if (address_space_read(&address_space_memory, task->payload_gpa, + MEMTXATTRS_UNSPECIFIED, task->send_data, + task->send_data_size) != MEMTX_OK) { + goto out_free; + } + + /* Mark the buffer in-flight. */ + hdr.error_code = cpu_to_le64(TDX_VP_GET_QUOTE_IN_FLIGHT); + if (address_space_write(&address_space_memory, buf_gpa, + MEMTXATTRS_UNSPECIFIED, + &hdr, TDX_GET_QUOTE_HDR_SIZE) != MEMTX_OK) { + goto out_free; + } + + task->receive_buf = g_malloc0(task->payload_len); + task->receive_buf_received = 0; + task->opaque = tdx_guest; + + object_ref(tdx_guest); + tdx_generate_quote(task, tdx_guest->qg_sock_addr); + run->tdx.get_quote.ret = TDG_VP_VMCALL_SUCCESS; + return; + +out_free: + g_free(task->send_data); + g_free(task); +} + +void tdx_handle_get_tdvmcall_info(X86CPU *cpu, struct kvm_run *run) +{ + if (run->tdx.get_tdvmcall_info.leaf != 1) { + return; + } + + run->tdx.get_tdvmcall_info.r11 = TDG_VP_VMCALL_SUBFUNC_GET_QUOTE; + run->tdx.get_tdvmcall_info.r12 = 0; + run->tdx.get_tdvmcall_info.r13 = 0; + run->tdx.get_tdvmcall_info.r14 = 0; +} + static void tdx_panicked_on_fatal_error(X86CPU *cpu, uint64_t error_code, char *message, uint64_t gpa) { @@ -1239,6 +1399,37 @@ static void tdx_guest_set_mrownerconfig(Object *obj, const char *value, Error ** tdx->mrownerconfig = g_strdup(value); } +static void tdx_guest_get_qgs(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + TdxGuest *tdx = TDX_GUEST(obj); + + if (!tdx->qg_sock_addr) { + error_setg(errp, "quote-generation-socket is not set"); + return; + } + visit_type_SocketAddress(v, name, &tdx->qg_sock_addr, errp); +} + +static void tdx_guest_set_qgs(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + TdxGuest *tdx = TDX_GUEST(obj); + SocketAddress *sock = NULL; + + if (!visit_type_SocketAddress(v, name, &sock, errp)) { + return; + } + + if (tdx->qg_sock_addr) { + qapi_free_SocketAddress(tdx->qg_sock_addr); + } + + tdx->qg_sock_addr = sock; +} + /* tdx guest */ OBJECT_DEFINE_TYPE_WITH_INTERFACES(TdxGuest, tdx_guest, @@ -1270,6 +1461,13 @@ static void tdx_guest_init(Object *obj) object_property_add_str(obj, "mrownerconfig", tdx_guest_get_mrownerconfig, tdx_guest_set_mrownerconfig); + + object_property_add(obj, "quote-generation-socket", "SocketAddress", + tdx_guest_get_qgs, + tdx_guest_set_qgs, + NULL, NULL); + + qemu_mutex_init(&tdx->lock); } static void tdx_guest_finalize(Object *obj) diff --git a/target/i386/kvm/tdx.h b/target/i386/kvm/tdx.h index 04b5afe199..35a09c19c5 100644 --- a/target/i386/kvm/tdx.h +++ b/target/i386/kvm/tdx.h @@ -11,6 +11,8 @@ #include "cpu.h" #include "hw/i386/tdvf.h" +#include "tdx-quote-generator.h" + #define TYPE_TDX_GUEST "tdx-guest" #define TDX_GUEST(obj) OBJECT_CHECK(TdxGuest, (obj), TYPE_TDX_GUEST) @@ -21,6 +23,17 @@ typedef struct TdxGuestClass { /* TDX requires bus frequency 25MHz */ #define TDX_APIC_BUS_CYCLES_NS 40 +#define TDVMCALL_GET_TD_VM_CALL_INFO 0x10000 +#define TDVMCALL_GET_QUOTE 0x10002 + +#define TDG_VP_VMCALL_SUCCESS 0x0000000000000000ULL +#define TDG_VP_VMCALL_RETRY 0x0000000000000001ULL +#define TDG_VP_VMCALL_INVALID_OPERAND 0x8000000000000000ULL +#define TDG_VP_VMCALL_GPA_INUSE 0x8000000000000001ULL +#define TDG_VP_VMCALL_ALIGN_ERROR 0x8000000000000002ULL + +#define TDG_VP_VMCALL_SUBFUNC_GET_QUOTE 0x0000000000000001ULL + enum TdxRamType { TDX_RAM_UNACCEPTED, TDX_RAM_ADDED, @@ -40,15 +53,19 @@ typedef struct TdxGuest { bool initialized; uint64_t attributes; /* TD attributes */ uint64_t xfam; - char *mrconfigid; /* base64 encoded sha348 digest */ - char *mrowner; /* base64 encoded sha348 digest */ - char *mrownerconfig; /* base64 encoded sha348 digest */ + char *mrconfigid; /* base64 encoded sha384 digest */ + char *mrowner; /* base64 encoded sha384 digest */ + char *mrownerconfig; /* base64 encoded sha384 digest */ MemoryRegion *tdvf_mr; TdxFirmware tdvf; uint32_t nr_ram_entries; TdxRamEntry *ram_entries; + + /* GetQuote */ + SocketAddress *qg_sock_addr; + int num; } TdxGuest; #ifdef CONFIG_TDX @@ -61,5 +78,7 @@ int tdx_pre_create_vcpu(CPUState *cpu, Error **errp); void tdx_set_tdvf_region(MemoryRegion *tdvf_mr); int tdx_parse_tdvf(void *flash_ptr, int size); int tdx_handle_report_fatal_error(X86CPU *cpu, struct kvm_run *run); +void tdx_handle_get_quote(X86CPU *cpu, struct kvm_run *run); +void tdx_handle_get_tdvmcall_info(X86CPU *cpu, struct kvm_run *run); #endif /* QEMU_I386_TDX_H */ diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index 0fcddc2ec0..0cb87d0201 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -2033,8 +2033,11 @@ static void gen_movl_seg(DisasContext *s, X86Seg seg_reg, TCGv src, bool inhibit tcg_gen_trunc_tl_i32(sel, src); gen_helper_load_seg(tcg_env, tcg_constant_i32(seg_reg), sel); - /* For move to DS/ES/SS, the addseg or ss32 flags may change. */ - if (CODE32(s) && seg_reg < R_FS) { + /* + * For moves to SS, the SS32 flag may change. For CODE32 only, changes + * to SS, DS and ES may change the ADDSEG flags. + */ + if (seg_reg == R_SS || (CODE32(s) && seg_reg < R_FS)) { s->base.is_jmp = DISAS_EOB_NEXT; } } else { |