Christopher Williams
2000cc4101
Matching conventions require a duplicate check before registering, because a shared body is matched once and registered once per address. Phase 6 did that check by hand and found one 12-byte pair. tools/sf3_dupes now hashes every derived extent body and groups exact duplicates. Results: 2284 extents, 65 multi-address groups, 2104 singletons. Only 10 groups contain code (24 addresses, all exact-graded); 55 are all-zero bodies. The hand-found pair 0x800262E0/0x800262EC is reproduced as g0002, which is the check that the census measures what it claims. The largest real groups are 712 bytes (0x8001084C/0x800189E8) and 436 bytes. The zero groups are a real finding: 252 extents have all-zero bodies, 245 inside the zero band 0x80147000..0x80170000. The cause is the inventory's jal grade, which decodes every word as an instruction -- in a data region a word with opcode 3 is graded as a call whose target lands in the zero band. The census flags those groups rather than hiding them, and the worklist must exclude degenerate bodies. The census is tracked rather than ignored as the plan said, because it holds addresses, sizes and grades only (the same class as the tracked inventory and extents tables) and the worklist must be reproducible from tracked inputs. The content hash is computed and never written.
126 lines
4.2 KiB
Makefile
126 lines
4.2 KiB
Makefile
# Phase 3 all-assembly baseline orchestration.
|
|
# All original and generated ROM-derived inputs/outputs remain ignored.
|
|
|
|
SHELL := /usr/bin/bash
|
|
|
|
EXE := extracted/SCUS_946.40;1
|
|
MANIFEST := extracted/MANIFEST.tsv
|
|
SPLAT := tools/splat/.venv/bin/splat
|
|
AS := tools/mipsel-none-elf-binutils/prefix/usr/bin/mipsel-none-elf-as
|
|
LD := tools/mipsel-none-elf-binutils/prefix/usr/bin/mipsel-none-elf-ld
|
|
OBJCOPY := tools/mipsel-none-elf-binutils/prefix/usr/bin/mipsel-none-elf-objcopy
|
|
|
|
ASM_ROOT := asm
|
|
SPLAT_CONFIG := $(ASM_ROOT)/scus_946_40.yaml
|
|
SPLAT_OUTPUT := $(ASM_ROOT)/generated
|
|
LINKER_SCRIPT := $(ASM_ROOT)/scus_946_40.ld
|
|
BUILD := build
|
|
ELF := $(BUILD)/scus_946_40.elf
|
|
REBUILT := $(BUILD)/scus_946_40.rebuilt
|
|
INPUT_REPORT := .run/p3-exe-info.tsv
|
|
|
|
# Phase 5 ordered code build: C regions listed in the tracked registry are
|
|
# compiled with the identified toolchain and linked in address order between
|
|
# data fallbacks taken from the original executable. An empty registry
|
|
# reproduces the all-payload data baseline exactly.
|
|
REGIONS := config/regions.tsv
|
|
SYMBOLS := config/symbols.tsv
|
|
INVENTORY := config/function_inventory.tsv
|
|
EXTENTS := config/function_extents.tsv
|
|
DUPES := config/duplicate_bodies.tsv
|
|
MATCH := tools/sf3_match
|
|
EXTENTS_TOOL := tools/sf3_extents
|
|
DUPES_TOOL := tools/sf3_dupes
|
|
CODE_OUT := build/code
|
|
EXPECTED_SHA1 := e173426c157384ebf1b6caf8c6fea18a85a14af9
|
|
|
|
.PHONY: all validate split assemble link binary code gate extents extents-verify dupes test check clean
|
|
|
|
all: binary
|
|
|
|
validate:
|
|
@test -f "$(EXE)"
|
|
@test -f "$(MANIFEST)"
|
|
@mkdir -p .run
|
|
@./tools/sf3_extract psx-exe-info "$(EXE)" "$(MANIFEST)" > "$(INPUT_REPORT)"
|
|
|
|
split: validate
|
|
@test -f "$(SPLAT)"
|
|
@test -f "$(SPLAT_CONFIG)"
|
|
@cd "$(ASM_ROOT)" && ../"$(SPLAT)" split "$$(basename "$(SPLAT_CONFIG)")" --disassemble-all
|
|
|
|
assemble: split
|
|
@test -d "$(SPLAT_OUTPUT)" && test ! -L "$(SPLAT_OUTPUT)"
|
|
@test -f "$(AS)"
|
|
@test ! -L "$(BUILD)"
|
|
@mkdir -p "$(BUILD)"
|
|
@while IFS= read -r source; do \
|
|
rel="$${source#$(ASM_ROOT)/}"; \
|
|
object="$(BUILD)/$${rel}.o"; \
|
|
mkdir -p "$$(dirname "$$object")"; \
|
|
"$(AS)" -march=r3000 -G0 -I "$(ASM_ROOT)/include" -o "$$object" "$$source"; \
|
|
done < <(find "$(SPLAT_OUTPUT)" -type f -name '*.s' -print | sort)
|
|
|
|
link: assemble
|
|
@test -f "$(LINKER_SCRIPT)"
|
|
@test -f "$(LD)"
|
|
@rm -f "$(ELF)"
|
|
@"$(LD)" -T "$(LINKER_SCRIPT)" -o "$(ELF)"
|
|
|
|
binary: link
|
|
@test -f "$(OBJCOPY)"
|
|
@rm -f "$(REBUILT)"
|
|
@"$(OBJCOPY)" -O binary "$(ELF)" "$(REBUILT)"
|
|
|
|
# Ordered code build and full-binary gate (Phase 5). `code` builds only;
|
|
# `gate` builds and then requires the whole executable to be byte-identical.
|
|
code: validate
|
|
@test -f "$(MATCH)"
|
|
@test -f "$(REGIONS)"
|
|
@test -f "$(SYMBOLS)"
|
|
@rm -rf "$(CODE_OUT)"
|
|
@"$(MATCH)" build --exe "$(EXE)" --regions "$(REGIONS)" --symbols "$(SYMBOLS)" --out "$(CODE_OUT)"
|
|
|
|
gate: validate
|
|
@test -f "$(MATCH)"
|
|
@test -f "$(REGIONS)"
|
|
@test -f "$(SYMBOLS)"
|
|
@rm -rf "$(CODE_OUT)"
|
|
@"$(MATCH)" gate --exe "$(EXE)" --regions "$(REGIONS)" --symbols "$(SYMBOLS)" --out "$(CODE_OUT)" \
|
|
--expect-sha1 "$(EXPECTED_SHA1)"
|
|
|
|
# Function extents (Phase 7). `extents` regenerates the tracked table from the
|
|
# inventory; `extents-verify` re-derives it and requires every registered region
|
|
# to agree, so a region can never silently disagree with the derived extent.
|
|
extents: validate
|
|
@test -f "$(EXTENTS_TOOL)"
|
|
@test -f "$(INVENTORY)"
|
|
@"$(EXTENTS_TOOL)" scan --exe "$(EXE)" --inventory "$(INVENTORY)" --out "$(EXTENTS)" --force
|
|
|
|
extents-verify: validate
|
|
@test -f "$(EXTENTS_TOOL)"
|
|
@test -f "$(INVENTORY)"
|
|
@test -f "$(EXTENTS)"
|
|
@"$(EXTENTS_TOOL)" verify --exe "$(EXE)" --inventory "$(INVENTORY)" \
|
|
--extents "$(EXTENTS)" --regions "$(REGIONS)"
|
|
|
|
# Duplicate-body census (Phase 7): groups byte-identical bodies so a shared body
|
|
# is matched once and registered once per address.
|
|
dupes: validate
|
|
@test -f "$(DUPES_TOOL)"
|
|
@test -f "$(EXTENTS)"
|
|
@"$(DUPES_TOOL)" census --exe "$(EXE)" --extents "$(EXTENTS)" --out "$(DUPES)" --force
|
|
|
|
# Verification gates. `test` is synthetic-only and needs no game input;
|
|
# `check` adds the extents check and the full-binary byte gate (which do).
|
|
test:
|
|
@PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s tools/tests
|
|
|
|
check: test extents-verify gate
|
|
|
|
clean:
|
|
@if test -e "$(BUILD)"; then \
|
|
test -d "$(BUILD)" && test ! -L "$(BUILD)"; \
|
|
rm -rf "$(BUILD)"; \
|
|
fi
|