Christopher Williams
228ad953e4
Worker D found it while sweeping the GTE batch, refused to spend spellings on it, and reported it rather than grinding. I re-derived the conclusion from the bytes before acting: its first instruction is lw t0,0(t5) (0x8DA80000) and $13 is written ZERO times in the whole 72-byte extent, so t5 is read but never established and the extent is the tail of a larger function. The already-excluded 0x800C3490 has the identical signature (also zero writes to $13). That gives the fragment class a CHECKABLE predicate instead of a vibe: 'a caller-saved temporary ($8-$15) is READ before any instruction in the extent WRITES it.' It is sound because $8-$15 are never incoming o32 arguments and no compiler emits a read of an uninitialised temporary. It is not yet an automatic triage rule -- that needs a fail-first test, so it is recorded as an open item rather than half-implemented at the context cap. Until then fragments are caught by a worker reading the row, which has now cost two workers a reading budget each. Excluded rather than left in the dispatch files: 0x800C3490 was re-identified twice by two separate workers before this.
175 lines
7.3 KiB
Makefile
175 lines
7.3 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 := $(BUILD)/scus_946_40.rebuilt
|
|
INPUT_REPORT := .run/p3-exe-info.tsv
|
|
|
|
# Phase 5 ordered code build: C regions listed in the tracked registry are
|
|
# compiled with the identified toolchain and linked in address order between
|
|
# data fallbacks taken from the original executable. An empty registry
|
|
# reproduces the all-payload data baseline exactly.
|
|
REGIONS := config/regions.tsv
|
|
SYMBOLS := config/symbols.tsv
|
|
INVENTORY := config/function_inventory.tsv
|
|
EXTENTS := config/function_extents.tsv
|
|
DUPES := config/duplicate_bodies.tsv
|
|
NEGATIVES := config/near_match_negatives.tsv
|
|
WORKLIST := config/match_worklist.tsv
|
|
MATCH := tools/sf3_match
|
|
EXTENTS_TOOL := tools/sf3_extents
|
|
DUPES_TOOL := tools/sf3_dupes
|
|
TRIAGE_TOOL := tools/sf3_triage
|
|
CODE_OUT := build/code
|
|
EXPECTED_SHA1 := e173426c157384ebf1b6caf8c6fea18a85a14af9
|
|
|
|
.PHONY: all validate split assemble link binary code gate extents extents-verify dupes worklist test check clean
|
|
|
|
all: binary
|
|
|
|
validate:
|
|
@test -f "$(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
|
|
|
|
# Ranked match worklist (Phase 7). The --exclude addresses are recorded
|
|
# near-misses or known-bad rows deferred by developer direction; naming them here
|
|
# keeps the exclusion visible instead of burying it in the tool.
|
|
# 0x8010080C was added in Phase 10 as a FALSE EXTENT START (worker C): its first
|
|
# instruction is `beq s0,zero` with s0 never written in range, and the walk split
|
|
# one real 252-byte function (0x801007E0..0x801008DC) at a spurious `jal`-target
|
|
# boundary. It is now caught earlier by sf3_triage's general `restores_unsaved`
|
|
# rule (worker A's independent scan re-derived the same row from a different
|
|
# signal), so this row is retained only as the provenance record for that defect.
|
|
#
|
|
# 0x800C3490 was added in Phase 12 as a FRAGMENT, not a function (cookbook 114,
|
|
# found by worker A and re-confirmed by the coordinator against the registry). It
|
|
# starts mid-expression, its body is a SHARED TAIL (`addiu sp,sp,48; jr ra`) that
|
|
# also appears at 0x800C3470-0x800C348C, and it cannot be matched standalone. The
|
|
# extents table still grades it `exact` with `term=jr_ra`, because the boundary walk
|
|
# sees a well-formed terminal -- so the tool cannot catch this one. Excluded rather
|
|
# than left in the dispatch files, where it costs every fresh-band worker a reading
|
|
# budget before it is recognised again. Worker A identified it for the second time in
|
|
# Phase 12 and skipped it rather than spending that budget.
|
|
#
|
|
# 0x8001DC20 was added in Phase 12 as the SECOND instance of the same class, and it
|
|
# gives the class a CHECKABLE predicate instead of a vibe. Its first instruction is
|
|
# `lw t0,0(t5)` (0x8DA80000) and **$13 is written ZERO times in the whole 72-byte
|
|
# extent** -- t5 is read but never established, so the extent is the tail of a larger
|
|
# function. Worker D found it and refused to spend GTE spellings on it; the
|
|
# coordinator re-derived the same conclusion from the bytes before excluding it, so
|
|
# this row is a two-worker confirmation like 0x800C3490 is.
|
|
# The general predicate -- "a caller-saved temporary ($8-$15) is READ before any
|
|
# instruction in the extent WRITES it" -- holds for BOTH rows (`0x800C3490` also
|
|
# writes $13 zero times) and is sound, because $8-$15 are never incoming o32
|
|
# arguments and no compiler emits a read of an uninitialised temporary. It is NOT
|
|
# yet implemented as an automatic triage rule; until it is, fragments are caught by
|
|
# a worker reading the row. See the Phase 12 ledger for that open item.
|
|
worklist: validate
|
|
@test -f "$(TRIAGE_TOOL)"
|
|
@test -f "$(EXTENTS)"
|
|
@test -f "$(DUPES)"
|
|
@"$(TRIAGE_TOOL)" plan --exe "$(EXE)" --extents "$(EXTENTS)" --inventory "$(INVENTORY)" \
|
|
--census "$(DUPES)" --regions "$(REGIONS)" --negatives "$(NEGATIVES)" \
|
|
--exclude 0x8005DEF8 --exclude 0x800F3160 \
|
|
--exclude 0x80108034 --exclude 0x8010804C \
|
|
--exclude 0x80012A10 --exclude 0x80012AE0 \
|
|
--exclude 0x80012CFC --exclude 0x80012B20 \
|
|
--exclude 0x8008A198 --exclude 0x8010080C \
|
|
--exclude 0x800C3490 --exclude 0x8001DC20 --out "$(WORKLIST)" --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
|