Files
rea/src/domain/binaryTargetTypes.ts
T
Ariel Fikru Avicennaandgensokyo-dev cab78de506 feat(ghidra): analyze GameCube/Wii DOL executables through Ghidra (#6240)
* feat(domain): parse and validate GameCube/Wii DOL headers

Add a pure parser for the 0x100-byte DOL header (7 text and 11 data
slots, BSS, entry point). Used slots must lie after the header and
inside the file and the 0x80000000..0x81800000 load window; text slots
are 4-byte aligned; sections may not overlap in memory or in the file;
the entry point must be inside a text section. BSS may overlap data
sections, as .sdata/.sdata2 do in shipped DOLs.

Refs #1741

* feat(binary): admit caller-selected GameCube/Wii DOL targets

* feat(ghidra): import GameCube/Wii DOL targets through a section-map pre-script

* test(ghidra): cover DOL launcher arguments, attestation and raw profile digests

* test(ghidra): add the real verify:ghidra:dol lane and DOL docs

* fix(ghidra): read only the DOL header and section ranges instead of the whole file

* test(ghidra): derive DOL lane addresses from readelf and admit Gekko from the install catalog

* fix(ghidra): attest DOL block permissions, space, overlay and load state

* fix(ghidra): keep load-image permissions optional for older inspections

* fix(contracts): accept DOL targets in binary_session output

* fix(ghidra): adapt the DOL lane to the current upstream address schema

Validate DOL load-image coordinates with the upstream observed-address
schema, drop a duplicate import left by the rebase, and re-pin the raw
profile digests to the unmodified upstream resolver.

* fix(ghidra): preserve bridge inventory symbol provenance

* fix(ghidra): align DOL verification with shared workflow contracts

* feat(domain): parse and validate GameCube/Wii DOL headers

Add a pure parser for the 0x100-byte DOL header (7 text and 11 data
slots, BSS, entry point). Used slots must lie after the header and
inside the file and the 0x80000000..0x81800000 load window; text slots
are 4-byte aligned; sections may not overlap in memory or in the file;
the entry point must be inside a text section. BSS may overlap data
sections, as .sdata/.sdata2 do in shipped DOLs.

Refs #1741

* feat(binary): admit caller-selected GameCube/Wii DOL targets

* feat(ghidra): import GameCube/Wii DOL targets through a section-map pre-script

* test(ghidra): cover DOL launcher arguments, attestation and raw profile digests

* test(ghidra): add the real verify:ghidra:dol lane and DOL docs

* fix(ghidra): read only the DOL header and section ranges instead of the whole file

* test(ghidra): derive DOL lane addresses from readelf and admit Gekko from the install catalog

* fix(ghidra): attest DOL block permissions, space, overlay and load state

* fix(ghidra): keep load-image permissions optional for older inspections

* fix(contracts): accept DOL targets in binary_session output

* fix(ghidra): adapt the DOL lane to the current upstream address schema

Validate DOL load-image coordinates with the upstream observed-address
schema, drop a duplicate import left by the rebase, and re-pin the raw
profile digests to the unmodified upstream resolver.

* docs(ghidra): qualify the DOL memory window

* refactor(ghidra): own DOL BSS ranges in the parsed header

* docs(ghidra): record real DOL workflows and task costs

* docs(ghidra): record final DOL integration verification

* fix(mcp): share the native procedure search row contract

* docs(ghidra): record public procedure search verification

---------

Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
2026-10-24 17:56:31 +08:00

280 lines
9.5 KiB
TypeScript

import type { DolHeader } from "./gamecubeDol.js";
import type { ZipPackageFormat } from "./zipPackageFormat.js";
/** Provider-neutral CPU families detected from headers or explicitly selected raw loads. */
export const BINARY_ARCHITECTURES = [
"x86",
"x86_64",
"arm",
"arm64",
"arm64_32",
"mips",
"6502",
"riscv",
"powerpc",
"m68k",
"hexagon",
] as const;
export type BinaryArchitecture = (typeof BINARY_ARCHITECTURES)[number];
/**
* Families admitted only by explicit raw-binary selection. Header detection
* never yields them, so detected targets and Evidence subjects exclude them.
*/
export const RAW_ONLY_ARCHITECTURES = [
"6502",
"m68k",
] as const satisfies readonly BinaryArchitecture[];
export type RawOnlyArchitecture = (typeof RAW_ONLY_ARCHITECTURES)[number];
/**
* ELF header facts for a family whose ISA and ABI are not established by the
* family name alone. Consumers admit a lane from these declarations rather than
* re-reading the header.
*/
export interface ElfFamilyMetadata {
readonly elfClass: 32 | 64;
readonly byteOrder: "little" | "big";
readonly type: number;
readonly flags: number;
}
/** Referenced CodeView debug symbols from a PE debug directory. */
export interface PeCodeViewRecord {
readonly pdbPath: string;
readonly pdbFileName: string;
readonly guid: string | null;
readonly age: number;
}
/** Families whose parsed target variant carries `ElfFamilyMetadata`. */
export const ELF_METADATA_ARCHITECTURES = [
"mips",
"riscv",
"powerpc",
] as const satisfies readonly BinaryArchitecture[];
export type ElfMetadataArchitecture =
(typeof ELF_METADATA_ARCHITECTURES)[number];
/** Families whose ISA and ABI need a separate ELF declaration to be admitted. */
export const isElfMetadataArchitecture = (
architecture: BinaryArchitecture,
): architecture is ElfMetadataArchitecture =>
(ELF_METADATA_ARCHITECTURES as readonly string[]).includes(architecture);
/** Recognized family with no ELF metadata member; the header alone is the fact. */
export type HeaderArchitecture = Exclude<
BinaryArchitecture,
ElfMetadataArchitecture | RawOnlyArchitecture | "hexagon" | "arm64_32"
>;
/** Raw ELF facts; family recognition does not establish ISA or ABI support. */
export interface MipsElfMetadata extends ElfFamilyMetadata {
/** Undefined until inspected; null means no ABI record was observed. */
readonly abiFlags?: MipsAbiFlags | null;
/** Undefined until inspected; null means no GNU attribute section was observed. */
readonly gnuAttributes?: MipsGnuAttributes | null;
/** Unavailable declaration sources; missing records there remain unknown. */
readonly limitations?: readonly string[];
/** Complete dynamic REL declarations, or the reason they could not be inspected. */
readonly sharedLoad?:
| {
readonly status: "complete";
readonly relocationCount: number;
readonly relocationTypes: readonly number[];
readonly symbolRelativeCount: number;
}
| { readonly status: "unavailable"; readonly reason: string };
}
/** Declared fields of the 24-byte MIPS ABI flags record, not inferred semantics. */
export interface MipsAbiFlags {
readonly version: number;
readonly isaLevel: number;
readonly isaRevision: number;
readonly gprSize: number;
readonly cpr1Size: number;
readonly cpr2Size: number;
readonly fpAbi: number;
readonly isaExtension: number;
readonly ases: number;
readonly flags1: number;
readonly flags2: number;
}
/** File-scope GNU object attributes parsed from `SHT_GNU_ATTRIBUTES`. */
export interface MipsGnuAttributes {
/** Tag_GNU_MIPS_ABI_FP; null means this file did not declare the tag. */
readonly fpAbi: number | null;
/** Tag_GNU_MIPS_ABI_MSA vector-argument ABI; null means undeclared. */
readonly msa: number | null;
}
/**
* ELF class and flags retain the width and ABI declarations used by this lane.
* ISA extensions in `.riscv.attributes` are not inspected by this header parser.
*/
export type RiscvElfMetadata = ElfFamilyMetadata;
/** Raw PowerPC declarations; family identity does not select a processor variant. */
export type PowerPcElfMetadata = ElfFamilyMetadata;
/** Byte range of the selected slice inside its universal Mach-O container. */
export interface UniversalMachOSlice {
readonly offset: number;
readonly size: number;
}
interface BinaryTargetIdentity {
readonly path: string;
readonly sourcePath?: string;
/** Info.plist of the app bundle the target was resolved from. */
readonly bundleInfoPlist?: string;
readonly sha256: string;
}
type NonExecutableMetadata = {
readonly architecture?: never;
readonly availableArchitectures?: never;
readonly executableRole?: never;
readonly managed?: never;
};
type ExecutableTarget = BinaryTargetIdentity & {
readonly kind: "executable";
readonly architecture: HeaderArchitecture;
readonly availableArchitectures: readonly HeaderArchitecture[];
};
/**
* Canonical local target identity and provider-neutral file classification.
* Each variant carries only metadata established for that exact file kind.
*/
export type BinaryTarget =
| (BinaryTargetIdentity & {
readonly kind: "executable";
readonly format: "elf";
readonly architecture: "mips";
readonly availableArchitectures: readonly "mips"[];
readonly mips: MipsElfMetadata;
readonly executableRole?: never;
readonly managed?: never;
})
| (BinaryTargetIdentity & {
readonly kind: "executable";
readonly format: "elf";
readonly architecture: "riscv";
readonly availableArchitectures: readonly "riscv"[];
readonly riscv: RiscvElfMetadata;
readonly executableRole?: never;
readonly managed?: never;
})
| (BinaryTargetIdentity & {
readonly kind: "executable";
readonly format: "elf";
readonly architecture: "powerpc";
readonly availableArchitectures: readonly "powerpc"[];
readonly powerpc: PowerPcElfMetadata;
readonly executableRole?: never;
readonly managed?: never;
})
| (BinaryTargetIdentity & {
readonly kind: "executable";
readonly format: "elf";
readonly architecture: "hexagon";
readonly availableArchitectures: readonly "hexagon"[];
readonly executableRole?: never;
readonly managed?: never;
})
| (BinaryTargetIdentity & {
readonly kind: "executable";
readonly format: "mach-o";
readonly architecture: "arm64_32";
readonly availableArchitectures: readonly "arm64_32"[];
readonly universalSlice?: never;
readonly executableRole?: never;
readonly managed?: never;
})
| (ExecutableTarget & {
readonly format: "mach-o" | "elf" | "dos-mz" | "dos-com";
readonly universalSlice?: never;
readonly executableRole?: never;
readonly managed?: never;
})
| (ExecutableTarget & {
readonly format: "mach-o-universal";
/** Selected slice range a provider must analyze instead of the container. */
readonly universalSlice: UniversalMachOSlice;
readonly executableRole?: never;
readonly managed?: never;
})
| (BinaryTargetIdentity & {
readonly kind: "executable";
readonly format: "raw-binary";
readonly architecture: HeaderArchitecture | RawOnlyArchitecture;
readonly availableArchitectures: readonly (
| HeaderArchitecture
| RawOnlyArchitecture
)[];
readonly entryPoint: string;
readonly entryPointSource: string;
readonly executableRole?: never;
readonly managed?: never;
})
| (BinaryTargetIdentity & {
readonly kind: "executable";
readonly format: "gamecube-dol";
/** Fixed by the DOL selection; the header does not carry a CPU family. */
readonly architecture: "powerpc";
readonly availableArchitectures: readonly ["powerpc"];
readonly byteOrder: "big";
readonly bits: 32;
/** Canonical hex entry taken from the DOL header. */
readonly entryPoint: string;
readonly entryPointSource: "dol-header";
/** Validated header: used sections, BSS, and BSS-overlapping data slots. */
readonly dol: DolHeader;
readonly executableRole?: never;
readonly managed?: never;
})
| (ExecutableTarget & {
readonly format: "pe";
/** Original COFF machine; undefined means this header fact is unavailable. */
readonly peMachine?: number;
/** Provider-neutral PE image role observed from COFF characteristics. */
readonly executableRole:
| "application"
| "shared-library"
| "non-executable";
/** Whether the PE declares a non-empty CLI header data-directory entry. */
readonly managed: boolean;
/** Referenced CodeView debug symbols from the PE debug directory, if present. */
readonly codeView?: PeCodeViewRecord;
})
| (BinaryTargetIdentity &
NonExecutableMetadata & {
readonly kind: "database";
readonly format: "analysis-database";
})
| (BinaryTargetIdentity &
NonExecutableMetadata & {
readonly kind: "archive";
readonly format:
| ZipPackageFormat
| "asar"
| "godot-pck"
| "dmg"
| "pkg";
})
| (BinaryTargetIdentity &
NonExecutableMetadata & {
readonly kind: "artifact";
readonly format: "plist" | "javascript" | "source-map";
});
/** Whether an executable target contains a thin or universal Mach-O image. */
export const isMachOFormat = (
format: unknown,
): format is "mach-o" | "mach-o-universal" =>
format === "mach-o" || format === "mach-o-universal";