tests: link M1 char helpers and check MOVB

2026-11-11 08:53:41 +00:00
1 parent b638ab0fad
commit 755b3cb7b2
@@ -0,0 +1,22 @@
+; char-test.asm -- run the compiled char helpers and publish their results.
+;
+; Appended after char.s so _loadb/_storeb (and every earlier function) keep
+; their linked addresses.  _start calls this instead of calling _second
+; directly, which is the same one-word-size calla; _char_test calls _second
+; and returns its result in A0 so the existing second() marker still works.
+;
+;   storeb(018A8080, 0x81) writes the byte 0x81
+;   loadb(018A8080)        returns the sign-extended 0xFFFFFF81
+	.text
+	.globl	_char_test
+_char_test:
+	calla	_second			; A0 = &arr[1]
+	move	a0, a3			; save it for the second() marker
+	movi	018A8080h, a0		; p = storeb/loadb marker byte
+	movi	81h, a1			; v = 0x81 (low byte stored by MOVB)
+	calla	_storeb
+	calla	_loadb			; A0 is still 018A8080
+	movi	018A8060h, a2
+	move	a0, *a2, 1		; 32-bit loadb marker
+	move	a3, a0			; restore &arr[1]
+	rets
@@ -0,0 +1,2 @@
+int loadb(char *p) { return *p; }
+void storeb(char *p, int v) { *p = v; }
@@ -12,6 +12,8 @@
 #   _load    MOVE *A0, A0, 1 ; RETS 0
 #   _late    ADDI 24, A0 ; RETS 0
 #   _second  MOVI _arr+32, A0 ; RETS 0
+#   _loadb   MOVB *A0, A0 ; RETS 0
+#   _storeb  MOVB A1, *A0 ; RETS 0
 #
 # This verifies the 1987 GSPA assembler's encoding, not a dormant LLVM Inst
 # encoding.  Overridable: M1_COFF DIS34
@@ -121,31 +123,49 @@ ADD=$(get_sym _add)
 LOAD=$(get_sym _load)
 LATE=$(get_sym _late)
 SECOND=$(get_sym _second)
+LOADB=$(get_sym _loadb)
+STOREB=$(get_sym _storeb)
 ADD_HEX=$(printf '%08X' "$ADD")
 LOAD_HEX=$(printf '%08X' "$LOAD")
 LATE_HEX=$(printf '%08X' "$LATE")
 SECOND_HEX=$(printf '%08X' "$SECOND")
+LOADB_HEX=$(printf '%08X' "$LOADB")
+STOREB_HEX=$(printf '%08X' "$STOREB")

 [ "$ADD_HEX" = "018A0240" ] || fail "_add linked at $ADD_HEX, want 018A0240"
 [ "$LOAD_HEX" = "018A0270" ] || fail "_load linked at $LOAD_HEX, want 018A0270"
 [ "$LATE_HEX" = "018A0290" ] || fail "_late linked at $LATE_HEX, want 018A0290"
 [ "$SECOND_HEX" = "018A02C0" ] || fail "_second linked at $SECOND_HEX, want 018A02C0"
+[ "$LOADB_HEX" = "018A0300" ] || fail "_loadb linked at $LOADB_HEX, want 018A0300"
+[ "$STOREB_HEX" = "018A0320" ] || fail "_storeb linked at $STOREB_HEX, want 018A0320"
 echo "   _add=$ADD_HEX _load=$LOAD_HEX _late=$LATE_HEX _second=$SECOND_HEX"
+echo "   _loadb=$LOADB_HEX _storeb=$STOREB_HEX (appended after _second)"

 echo "== disassemble the emitted .text with dis34"
 "$DIS34" -b "$TEXT_HEX" -l -o "$TMP/text.bin" > "$TMP/dis34.txt" 2> "$TMP/dis34.err" \
    || { cat "$TMP/dis34.err" >&2; fail "dis34 failed"; }
 [ -s "$TMP/dis34.txt" ] || fail "dis34 produced no output"

+# match_at FILE DECIMAL_ADDR ERE
+# dis34 -l prints "018a0240:\tadd    a0, a1\t; 4001".  The operand must be
+# followed by optional whitespace and then the comment/end-of-line marker, so
+# "rets 1" cannot satisfy a "rets" pattern.
+match_at() {
+    _file=$1
+    _addr=$2
+    _pat=$3
+    _laddr=$(printf '%08x' "$_addr")
+    grep -Eiq "^${_laddr}:[[:space:]]+${_pat}([[:space:]]*(;|$))" "$_file"
+}
+
 # expect_at LABEL DECIMAL_ADDR EXPECTED_TEXT ERE
-# dis34 -l prints "018a0240:\tadd    a0, a1\t; 4001".
 expect_at() {
    _label=$1
    _addr=$2
    _want=$3
    _pat=$4
    _laddr=$(printf '%08x' "$_addr")
-    if grep -Eiq "^${_laddr}:[[:space:]]+${_pat}([[:space:]]|;|$)" "$TMP/dis34.txt"; then
+    if match_at "$TMP/dis34.txt" "$_addr" "$_pat"; then
        echo "   ok $_label @ 0x$_laddr: $_want"
        return 0
    fi
@@ -191,16 +211,18 @@ expect_label "$SECOND"
 expect_at "_second"     "$SECOND"        "MOVI _arr+32, A0" 'movi[[:space:]]+(0x)?18a9020,[[:space:]]*a0'
 expect_at "_second+48"  $((SECOND + 48)) "RETS 0"            'rets([[:space:]]+0)?'

-# The char helpers are lit-only in M1, so the harness does not link them.
-# If a later harness does, do not silently skip their encoding.
-MOVB_SEEN=0
-for name in _loadb _storeb; do
-    if addr=$(sym_addr "$name"); then
-        MOVB_SEEN=1
-        expect_at "$name" "$addr" "MOVB" 'movb[[:space:]]+'
-    fi
-done
-[ "$MOVB_SEEN" -eq 1 ] \
-    || echo "   movb: no _loadb/_storeb linked (char helpers are lit-only)"
+# Negative control for the RETS operand boundary: "rets 1" must not match.
+printf '018a0260:\trets\t1\t; 0960\n' > "$TMP/rets-neg.txt"
+if match_at "$TMP/rets-neg.txt" $((ADD + 32)) 'rets([[:space:]]+0)?'; then
+    fail "negative control: the RETS pattern accepted 'rets 1'"
+fi
+echo "   ok negative control @ 0x$(printf '%08x' $((ADD + 32))): 'rets 1' rejected"
+
+expect_label "$LOADB"
+expect_at "_loadb"      "$LOADB"        "MOVB *A0, A0"     'movb[[:space:]]+\*a0,[[:space:]]*a0'
+expect_at "_loadb+16"   $((LOADB + 16)) "RETS 0"           'rets([[:space:]]+0)?'
+
+expect_at "_storeb"     "$STOREB"       "MOVB A1, *A0"     'movb[[:space:]]+a1,[[:space:]]*\*a0'
+expect_at "_storeb+16"  $((STOREB + 16)) "RETS 0"          'rets([[:space:]]+0)?'

 echo "M1 dis34 round-trip: PASS"
@@ -7,9 +7,16 @@
 ;   018A8000  add(20, 22)
 ;   018A8020  load(018A8100)
 ;   018A8040  second() == &arr[1]
+;   018A8060  loadb(018A8080) == 0xFFFFFF81 (sign-extended 0x81)
+;   018A8080  storeb(018A8080, 0x81) leaves the byte 0x81
 ;
 ; _late is linked but not called: it is a compile-time check that a surviving
 ; GEP offset is 24 bits, not 192.
+;
+; The char helpers are exercised by _char_test (char-test.asm, appended after
+; the compiled functions).  Calling it here instead of calling _second keeps
+; this entry's size -- and therefore every function's linked address -- the
+; same; _char_test calls _second and returns its result in A0.
 	.text
 	.globl	_start
 _start:
@@ -29,7 +36,8 @@ _start:
 	movi	018A8020h, a2
 	move	a0, *a2, 1

-	calla	_second
+	calla	_char_test
+
 	movi	018A8040h, a2
 	move	a0, *a2, 1

@@ -4,6 +4,8 @@
 -- M1_LOADER_LUA   path to vendor/vt1200/dwt/loader/loader.lua
 -- M1_EXPECT_LOAD  expected load() result (default 0x12345678)
 -- M1_EXPECT_SECOND expected &arr[1] in bits
+-- M1_EXPECT_LOADB expected sign-extended byte load (default 0xFFFFFF81)
+-- M1_EXPECT_STOREB expected byte store (default 0x81)
 --
 -- The marker read runs one frame before loader.lua's inspection/exit frame.

@@ -12,6 +14,8 @@ dofile(os.getenv("M1_LOADER_LUA"))
 local ENDF = tonumber(os.getenv("LOADER_END") or "2700")
 local EXPECT_LOAD = tonumber(os.getenv("M1_EXPECT_LOAD") or "0x12345678")
 local EXPECT_SECOND = tonumber(os.getenv("M1_EXPECT_SECOND") or "0x018A9020")
+local EXPECT_LOADB = tonumber(os.getenv("M1_EXPECT_LOADB") or "0xFFFFFF81")
+local EXPECT_STOREB = tonumber(os.getenv("M1_EXPECT_STOREB") or "0x81")
 local frames = 0
 local checked = false

@@ -23,14 +27,18 @@ emu.register_frame_done(function()
 		local add = prog:read_u32(0x018A8000)
 		local load = prog:read_u32(0x018A8020)
 		local second = prog:read_u32(0x018A8040)
-		print(string.format("M1: add=%d load=0x%08X second=0x%08X",
-			add, load, second))
-		if add == 42 and load == EXPECT_LOAD and second == EXPECT_SECOND then
+		local loadb = prog:read_u32(0x018A8060)
+		local storeb = prog:read_u8(0x018A8080)
+		print(string.format(
+			"M1: add=%d load=0x%08X second=0x%08X loadb=0x%08X storeb=0x%02X",
+			add, load, second, loadb, storeb))
+		if add == 42 and load == EXPECT_LOAD and second == EXPECT_SECOND
+			and loadb == EXPECT_LOADB and storeb == EXPECT_STOREB then
 			print("M1 MAME: PASS")
 		else
 			print(string.format(
-				"M1 MAME: FAIL (want add=42 load=0x%08X second=0x%08X)",
-				EXPECT_LOAD, EXPECT_SECOND))
+				"M1 MAME: FAIL (want add=42 load=0x%08X second=0x%08X loadb=0x%08X storeb=0x%02X)",
+				EXPECT_LOAD, EXPECT_SECOND, EXPECT_LOADB, EXPECT_STOREB))
 		end
 	end
 end, "m1-check")
@@ -3,16 +3,18 @@
 #
 #   scripts/m1/run.sh
 #
-# Compiles four C functions with scripts/tms-clang + llc -O0, assembles and
+# Compiles six C functions with scripts/tms-clang + llc -O0, assembles and
 # links them with the 1987 GSPA/GSPLNK 2.00 under DOSBox, then loads the COFF
 # into MAME through dwt/loader/loader.lua and checks the marker words:
 #
 #   add(20, 22) == 42
 #   load(&word) == 0x12345678
 #   second() == &arr[1] (arr + 32 bits)
+#   loadb(&byte) == 0xFFFFFF81 (sign-extended 0x81)
+#   storeb(&byte, 0x81) leaves the byte 0x81
 #
 # Overridable: TMS_CLANG TMS_OPT TMS_BITADDR TMS_LLC MAME DOSBOX DOSBOX_CONF
-#              SDK_IMG M1_WORK M1_SDK LOADER_AT LOADER_END
+#              SDK_IMG M1_WORK M1_COFF M1_SDK LOADER_AT LOADER_END
 set -eu

 ROOT=$(cd "$(dirname "$0")/../.." && pwd)
@@ -30,6 +32,7 @@ DOSBOX_CONF=${DOSBOX_CONF:-$ROOT/vendor/vt1200/harness/sdk-scratch/dosbox-bench.
 SDK_IMG=${SDK_IMG:-$ROOT/vendor/vt1200/tools/tms34010-sdk/1987-05 TMS34010 SDK/1987-11-06 TMS34010 Simulator-C Tools-ASM Tools.img}

 WORK=${M1_WORK:-$ROOT/build/m1}
+COFF=${M1_COFF:-$WORK/m1.coff}
 SDK=${M1_SDK:-$ROOT/build/m1-sdk}
 ASM=$WORK/asm
 LOADER_LUA=$ROOT/vendor/vt1200/dwt/loader/loader.lua
@@ -47,10 +50,11 @@ for tool in "$TMS_CLANG" "$TMS_OPT" "$TMS_BITADDR" "$TMS_LLC"; do
 done

 mkdir -p "$ASM" "$WORK/evidence" "$WORK/run/nvram" "$WORK/run/cfg"
+mkdir -p "$(dirname "$COFF")"

 echo "== compile and select"
 export TMS_CLANG TMS_OPT TMS_BITADDR
-for name in add load late const_gep; do
+for name in add load late const_gep char; do
    "$ROOT/scripts/tms-clang" -O2 -o "$ASM/$name.ll" "$DIR/$name.c"
    "$TMS_LLC" -march=tms34010 -O0 -filetype=asm \
        "$ASM/$name.ll" -o "$ASM/$name.s" \
@@ -82,7 +86,7 @@ fi

 echo "== assemble and link with GSPA/GSPLNK under DOSBox"
 cat "$DIR/entry.asm" "$ASM/add.s" "$ASM/load.s" "$ASM/late.s" \
-    "$ASM/const_gep.s" > "$SDK/M1.ASM"
+    "$ASM/const_gep.s" "$ASM/char.s" "$DIR/char-test.asm" > "$SDK/M1.ASM"
 # The linker command file must keep CRLF line endings.
 sed 's/\r$//' "$DIR/link.cmd" | sed 's/$/\r/' > "$SDK/M1.CMD"
 rm -f "$SDK/M1.OBJ" "$SDK/M1.OUT" "$SDK/M1.MAP" "$SDK/M1.LST"
@@ -102,7 +106,7 @@ grep -q 'No Errors' "$WORK/m1.lst" \
    || { grep -i -B2 -A2 'error' "$WORK/m1.lst" >&2 || true; fail "GSPA reported errors"; }
 [ -f "$SDK/M1.OUT" ] || fail "GSPLNK produced no M1.OUT"
 sed 's/\r$//' "$SDK/M1.MAP" > "$WORK/m1.map"
-cp "$SDK/M1.OUT" "$WORK/m1.coff"
+cp "$SDK/M1.OUT" "$COFF"
 cp "$SDK/M1.ASM" "$WORK/m1.asm"

 ENTRY=$(awk '$2 == "_start" { print $1; exit }' "$WORK/m1.map")
@@ -133,7 +137,7 @@ echo "== run the COFF in MAME"

 VT1200_SKIP_LEVEL1=1 \
 LOADER_AT="$LOADER_AT" LOADER_END="$LOADER_END" \
-LOADER_BIN="$LOADER_BIN" LOADER_COFF="$WORK/m1.coff" \
+LOADER_BIN="$LOADER_BIN" LOADER_COFF="$COFF" \
 LOADER_OUT="$WORK/evidence" \
 M1_LOADER_LUA="$LOADER_LUA" \
 M1_EXPECT_LOAD=0x12345678 M1_EXPECT_SECOND="$EXPECT_SECOND" \
@@ -5,6 +5,12 @@ set -eu
 ROOT=$(cd "$(dirname "$0")/../../.." && pwd)

 # Always rebuild: a stale build/m1/m1.coff would let an asm-encoding
-# regression pass without ever touching the compiler or assembler.
+# regression pass without ever touching the compiler or assembler.  Keep
+# dis-roundtrip.sh pointed at the file this run produces, including when
+# M1_WORK/M1_COFF are overridden.
+WORK=${M1_WORK:-$ROOT/build/m1}
+M1_COFF=${M1_COFF:-$WORK/m1.coff}
+export M1_COFF
+
 "$ROOT/scripts/m1/run.sh" "$@"
 exec "$ROOT/scripts/m1/dis-roundtrip.sh" "$@"