w6c+w6c_ww: store full slice header for struct-literal slice fields (fix #24)

cg_structlit_fill / cgstructlitfill had a TY_STR arm that stored all
three header words (ptr@+0, len@+8, cap@+16) but no TY_SLICE arm, so a
slice field in a struct literal `cl{ items = b, n = .. }` fell through to
the generic scalar tail and stored only the ptr word — the field's .len
and .cap read 0. str fields (the same 24B {ptr,len,cap} shape) worked;
slice fields silently dropped two words.

Both stages emitted IDENTICAL wrong asm, so the 990-997 byte-id gate was
green on both-wrong; runtime readback is the only correctness net. Same
is_str/is_slice discrimination gap as #10 part-b, here in the
struct-literal field-init path.

A slice is the same 24B header shape as str, so widen the str arm's
guard to TY_STR || TY_SLICE (cstage) / isstrtype || isslicetype
(wwstage) and let a slice ride the already-correct 3-word store. The
TAGGED arm stays ordered before it, so a nullable/tagged slice
(TY_TAGGED) still routes to the widener, not the 3-word store.

Test 689 (table-driven, runtime readback + dual-stage asm byte-id):
slice .len/.cap/.ptr, a scalar field beside/before the slice, a slice at
a non-zero field offset, two slice fields, and a str field beside a
slice (str-arm regression pin). 33/33 ok.
This commit is contained in:
2026-06-03 23:51:28 +09:00
parent b6a41ae063
commit c490ed3ec1
6 changed files with 374 additions and 8 deletions

View File

@@ -246,6 +246,7 @@ TESTS = $(BIN)/test_smoke $(BIN)/test_lex $(BIN)/test_parse $(BIN)/test_check \
$(BIN)/test_slice_str_global_zero \ $(BIN)/test_slice_str_global_zero \
$(BIN)/test_slice_literal_global \ $(BIN)/test_slice_literal_global \
$(BIN)/test_global_arr_elem_field \ $(BIN)/test_global_arr_elem_field \
$(BIN)/test_structlit_slice_field \
$(BIN)/test_dot_str_chained_arg \ $(BIN)/test_dot_str_chained_arg \
$(BIN)/test_dot_slice_arg \ $(BIN)/test_dot_slice_arg \
$(BIN)/test_dot_tagged_source \ $(BIN)/test_dot_tagged_source \
@@ -597,6 +598,12 @@ $(BIN)/test_global_arr_elem_field: test/wcc/688_global_arr_elem_field.c $(BIN)/w
$(LIB)/libwwrt.a | $(BIN) $(LIB)/libwwrt.a | $(BIN)
$(CC) $(CFLAGS) -o $@ $< $(CC) $(CFLAGS) -o $@ $<
$(BIN)/test_structlit_slice_field: test/wcc/689_structlit_slice_field.c $(BIN)/ww \
$(BIN)/w6c $(BIN)/w6a $(BIN)/w6l \
$(BIN)/ww_ww $(BIN)/w6c_ww $(BIN)/w6a_ww $(BIN)/w6l_ww \
$(LIB)/libwwrt.a | $(BIN)
$(CC) $(CFLAGS) -o $@ $<
$(BIN)/test_dot_str_chained_arg: test/wcc/692_dot_str_chained_arg.c $(BIN)/ww \ $(BIN)/test_dot_str_chained_arg: test/wcc/692_dot_str_chained_arg.c $(BIN)/ww \
$(BIN)/w6c $(BIN)/w6a $(BIN)/w6l \ $(BIN)/w6c $(BIN)/w6a $(BIN)/w6l \
$(BIN)/ww_ww $(BIN)/w6c_ww $(BIN)/w6a_ww $(BIN)/w6l_ww \ $(BIN)/ww_ww $(BIN)/w6c_ww $(BIN)/w6a_ww $(BIN)/w6l_ww \

View File

@@ -2690,8 +2690,10 @@ cg_structlit_fill(Cg *c, Local **locals_p, Type *lu, Node *lit,
/* str IS []u8: 3-word field (ptr,len,cap). cgexpr leaves /* str IS []u8: 3-word field (ptr,len,cap). cgexpr leaves
* AX/BX/CX; for non-BP modes the dst base goes in DX to dodge * AX/BX/CX; for non-BP modes the dst base goes in DX to dodge
* BX=len / CX=cap (the generic store below reloads BX, which * BX=len / CX=cap (the generic store below reloads BX, which
* would clobber len) (#1/Phase 3). */ * would clobber len) (#1/Phase 3). A slice is the same 24B
if (fu && fu->kind == TY_STR) { * {ptr,len,cap} shape, so it rides this arm; without it the
* generic scalar tail stored only the ptr word (#24). */
if (fu && (fu->kind == TY_STR || fu->kind == TY_SLICE)) {
cgexpr(c, f->lhs, *locals_p); cgexpr(c, f->lhs, *locals_p);
if (mode == DST_BP) { if (mode == DST_BP) {
ins2(c, A_MOVQ, areg(D_AX), ins2(c, A_MOVQ, areg(D_AX),

View File

@@ -19519,12 +19519,15 @@ fn cgstructlitfill(c: *cgen, si: *structinfo, lit: *node,
fi = nil; fi = nil;
} else if (callwhole) { } else if (callwhole) {
fi = nil; fi = nil;
} else if (isstrtype(c, fi.tnode)) { } else if (isstrtype(c, fi.tnode) || isslicetype(c, fi.tnode)) {
// str IS []u8: 3-word field (ptr,len,cap). // str IS []u8: 3-word field (ptr,len,cap).
// cgexpr leaves AX/BX/CX; for non-BP modes // cgexpr leaves AX/BX/CX; for non-BP modes
// the dst base goes in DX to dodge BX=len / // the dst base goes in DX to dodge BX=len /
// CX=cap (the generic store reloads BX, which // CX=cap (the generic store reloads BX, which
// would clobber len) (#1/Phase 3). // would clobber len) (#1/Phase 3). A slice is
// the same 24B {ptr,len,cap} shape, so it rides
// this arm; without it the generic scalar tail
// stored only the ptr word (#24).
cgexpr(c, fieldnode.lhs); cgexpr(c, fieldnode.lhs);
if (mode == 0) { if (mode == 0) {
emitline("\tMOVQ\tAX, "); emitline("\tMOVQ\tAX, ");

View File

@@ -3853,12 +3853,15 @@ fn cgstructlitfill(c: *cgen, si: *structinfo, lit: *node,
fi = nil; fi = nil;
} else if (callwhole) { } else if (callwhole) {
fi = nil; fi = nil;
} else if (isstrtype(c, fi.tnode)) { } else if (isstrtype(c, fi.tnode) || isslicetype(c, fi.tnode)) {
// str IS []u8: 3-word field (ptr,len,cap). // str IS []u8: 3-word field (ptr,len,cap).
// cgexpr leaves AX/BX/CX; for non-BP modes // cgexpr leaves AX/BX/CX; for non-BP modes
// the dst base goes in DX to dodge BX=len / // the dst base goes in DX to dodge BX=len /
// CX=cap (the generic store reloads BX, which // CX=cap (the generic store reloads BX, which
// would clobber len) (#1/Phase 3). // would clobber len) (#1/Phase 3). A slice is
// the same 24B {ptr,len,cap} shape, so it rides
// this arm; without it the generic scalar tail
// stored only the ptr word (#24).
cgexpr(c, fieldnode.lhs); cgexpr(c, fieldnode.lhs);
if (mode == 0) { if (mode == 0) {
emitline("\tMOVQ\tAX, "); emitline("\tMOVQ\tAX, ");

View File

@@ -19519,12 +19519,15 @@ fn cgstructlitfill(c: *cgen, si: *structinfo, lit: *node,
fi = nil; fi = nil;
} else if (callwhole) { } else if (callwhole) {
fi = nil; fi = nil;
} else if (isstrtype(c, fi.tnode)) { } else if (isstrtype(c, fi.tnode) || isslicetype(c, fi.tnode)) {
// str IS []u8: 3-word field (ptr,len,cap). // str IS []u8: 3-word field (ptr,len,cap).
// cgexpr leaves AX/BX/CX; for non-BP modes // cgexpr leaves AX/BX/CX; for non-BP modes
// the dst base goes in DX to dodge BX=len / // the dst base goes in DX to dodge BX=len /
// CX=cap (the generic store reloads BX, which // CX=cap (the generic store reloads BX, which
// would clobber len) (#1/Phase 3). // would clobber len) (#1/Phase 3). A slice is
// the same 24B {ptr,len,cap} shape, so it rides
// this arm; without it the generic scalar tail
// stored only the ptr word (#24).
cgexpr(c, fieldnode.lhs); cgexpr(c, fieldnode.lhs);
if (mode == 0) { if (mode == 0) {
emitline("\tMOVQ\tAX, "); emitline("\tMOVQ\tAX, ");

View File

@@ -0,0 +1,348 @@
/*
* 689_structlit_slice_field — cstage and wwstage agree, byte-for-byte
* and at runtime, that a struct-LITERAL initializer `cl{ items = b, n =
* .. }` with a SLICE field copies the FULL 24B { ptr, len, cap } header
* of that field (task #24).
*
* The bug: cg_structlit_fill / cgstructlitfill had a TY_STR arm that
* stored all three header words (ptr@+0, len@+8, cap@+16), but NO
* TY_SLICE arm — a slice field fell through to the generic scalar tail
* which stored only the ptr word, so the stored .len and .cap read 0.
* str fields (same 24B shape) worked; slice fields silently dropped
* two words. Both stages emitted IDENTICAL wrong asm (the 990-997
* byte-id gate was green on both-wrong), so RUNTIME readback is the
* correctness net. Same is_str/is_slice discrimination gap as #10
* part-b, here in the struct-literal field-init path.
*
* The fix (BOTH stages, converged byte-identical): the str arm's guard
* widens to `TY_STR || TY_SLICE` (cstage) / `isstrtype || isslicetype`
* (wwstage) — a slice rides the existing, already-correct 3-word store.
* The TAGGED arm stays ordered BEFORE it, so a nullable/tagged slice
* (TY_TAGGED) still routes to the widener, not the 3-word store.
*
* Mutation-sanity: the .len and .cap rows fail if the store drops
* either word (the pre-fix 1-word slice store), and the scalar-field
* rows (y.n, y.head) pin that the field beside/before the slice is
* untouched. The str_* rows are a regression pin on the untouched str
* arm.
*
* row | shape | want
* ---------------+------------------------------------------+------
* slice_len | cl{items=b,n=9}; b.len=5; y.items.len | 5
* slice_cap | cl{items=b,n=9}; b.cap=8; y.items.cap | 8
* slice_n | cl{items=b,n=9}; y.n (scalar beside slice)| 9
* slice_ptr | hb[0]=4; cl{items=b,..}; y.items[0] | 4
* off_len | struct{head:i64,s:[]u8}; s @foff 8; | 7
* | s.len=7; y.s.len (pins disp+foff+8 hdr) |
* off_cap | same; s.cap=8; y.s.cap (disp+foff+16) | 8
* off_head | same; head=1; y.head (scalar before slice)| 1
* two_b_len | struct{a:[]u8,b:[]u8}; b @foff 24; | 6
* | b.len=6; y.b.len (2nd slice, non-0 foff) |
* two_b_cap | same; b.cap=8; y.b.cap | 8
* str_name_len | struct{s:[]u8,name:str}; name="hello"; | 5
* | y.name.len (str arm regression pin) |
* str_s_len | same; s.len=3; y.s.len (slice beside str) | 3
*
* The asm-byte-id rows pin the symmetric fix (cstage == wwstage); a
* non-empty diff means one stage missed the new slice arm.
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/wait.h>
static int
runwait(const char *cmd)
{
int rc = system(cmd);
if (rc == -1) return -1;
if (WIFEXITED(rc)) return WEXITSTATUS(rc);
return -1;
}
struct row { const char *label; const char *src; int want; };
static const struct row rows[] = {
{ "slice_len",
"package main;\n"
"type cl = struct { items: []u8, n: i64 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 5; b.cap = 8;\n"
"\tlet y: cl = cl { items = b, n = 9i64 };\n"
"\treturn y.items.len: i32;\n"
"};\n",
5 },
{ "slice_cap",
"package main;\n"
"type cl = struct { items: []u8, n: i64 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 5; b.cap = 8;\n"
"\tlet y: cl = cl { items = b, n = 9i64 };\n"
"\treturn y.items.cap: i32;\n"
"};\n",
8 },
{ "slice_n",
"package main;\n"
"type cl = struct { items: []u8, n: i64 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 5; b.cap = 8;\n"
"\tlet y: cl = cl { items = b, n = 9i64 };\n"
"\treturn y.n: i32;\n"
"};\n",
9 },
{ "slice_ptr",
"package main;\n"
"type cl = struct { items: []u8, n: i64 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8; hb[0] = 4u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 5; b.cap = 8;\n"
"\tlet y: cl = cl { items = b, n = 9i64 };\n"
"\treturn y.items[0]: i32;\n"
"};\n",
4 },
/* slice field at a NON-ZERO field offset (head: i64 @0, s @8).
* Pins disp+foff+8/+16 in the stored header. */
{ "off_len",
"package main;\n"
"type hs = struct { head: i64, s: []u8 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 7; b.cap = 8;\n"
"\tlet y: hs = hs { head = 1i64, s = b };\n"
"\treturn y.s.len: i32;\n"
"};\n",
7 },
{ "off_cap",
"package main;\n"
"type hs = struct { head: i64, s: []u8 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 7; b.cap = 8;\n"
"\tlet y: hs = hs { head = 1i64, s = b };\n"
"\treturn y.s.cap: i32;\n"
"};\n",
8 },
{ "off_head",
"package main;\n"
"type hs = struct { head: i64, s: []u8 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 7; b.cap = 8;\n"
"\tlet y: hs = hs { head = 1i64, s = b };\n"
"\treturn y.head: i32;\n"
"};\n",
1 },
/* two slice fields: a @0, b @24. Pins the 2nd slice's header at a
* non-zero field offset (the 24B stride). */
{ "two_b_len",
"package main;\n"
"type tt = struct { a: []u8, b: []u8 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet p: []u8; p.ptr = &hb[0]; p.len = 3; p.cap = 8;\n"
"\tlet q: []u8; q.ptr = &hb[0]; q.len = 6; q.cap = 8;\n"
"\tlet y: tt = tt { a = p, b = q };\n"
"\treturn y.b.len: i32;\n"
"};\n",
6 },
{ "two_b_cap",
"package main;\n"
"type tt = struct { a: []u8, b: []u8 };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet p: []u8; p.ptr = &hb[0]; p.len = 3; p.cap = 8;\n"
"\tlet q: []u8; q.ptr = &hb[0]; q.len = 6; q.cap = 8;\n"
"\tlet y: tt = tt { a = p, b = q };\n"
"\treturn y.b.cap: i32;\n"
"};\n",
8 },
/* str field beside a slice field — the untouched str arm must still
* store its full header (regression pin). */
{ "str_name_len",
"package main;\n"
"type sn = struct { s: []u8, name: str };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 3; b.cap = 8;\n"
"\tlet y: sn = sn { s = b, name = \"hello\" };\n"
"\treturn y.name.len: i32;\n"
"};\n",
5 },
{ "str_s_len",
"package main;\n"
"type sn = struct { s: []u8, name: str };\n"
"export fn main() i32 = {\n"
"\tlet hb: [8]u8;\n"
"\tlet b: []u8; b.ptr = &hb[0]; b.len = 3; b.cap = 8;\n"
"\tlet y: sn = sn { s = b, name = \"hello\" };\n"
"\treturn y.s.len: i32;\n"
"};\n",
3 },
};
static int
run_driver(const char *driver, const struct row *r, int i)
{
char src[64], tmpdir[64], cmd[1024];
snprintf(src, sizeof src, "/tmp/slf_%d_%d.ww", getpid(), i);
snprintf(tmpdir, sizeof tmpdir, "/tmp/slf_%d_d_%d", getpid(), i);
FILE *f = fopen(src, "wb");
if (!f) return -1;
fputs(r->src, f);
fclose(f);
mkdir(tmpdir, 0755);
snprintf(cmd, sizeof cmd, "cd %s && %s build %s 2>/dev/null",
tmpdir, driver, src);
if (runwait(cmd) != 0) {
fprintf(stderr, "row[%s]: build via %s failed\n",
r->label, driver);
unlink(src); rmdir(tmpdir);
return -1;
}
const char *base = strrchr(src, '/');
base = base ? base + 1 : src;
char outbin[128];
snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
char *dot = strrchr(outbin, '.');
if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
int got = runwait(outbin);
unlink(src); unlink(outbin); rmdir(tmpdir);
return got;
}
/* asm_byte_identical — w6c vs w6c_ww .s for the same source must match.
* Pre-fix BOTH stages dropped len+cap identically (byte-id green on
* both-wrong); the symmetric fix keeps them byte-identical and correct. */
static int
asm_byte_identical(const char *bin, const struct row *r, int i)
{
char src[64], cs[64], ws[64], cmd[1024];
snprintf(src, sizeof src, "/tmp/slf_asm_%d_%d.ww", getpid(), i);
snprintf(cs, sizeof cs, "/tmp/slf_asm_%d_%d_c.s", getpid(), i);
snprintf(ws, sizeof ws, "/tmp/slf_asm_%d_%d_w.s", getpid(), i);
FILE *f = fopen(src, "wb");
if (!f) return -1;
fputs(r->src, f);
fclose(f);
snprintf(cmd, sizeof cmd, "%s/w6c -o %s %s 2>/dev/null", bin, cs, src);
if (runwait(cmd) != 0) {
fprintf(stderr, "row[%s]: w6c errored\n", r->label);
unlink(src);
return -1;
}
snprintf(cmd, sizeof cmd, "%s/w6c_ww -o %s %s 2>/dev/null",
bin, ws, src);
if (runwait(cmd) != 0) {
fprintf(stderr, "row[%s]: w6c_ww errored\n", r->label);
unlink(src); unlink(cs);
return -1;
}
FILE *fc = fopen(cs, "rb");
FILE *fw = fopen(ws, "rb");
int rc = 0;
if (!fc || !fw) {
rc = -1;
} else {
for (;;) {
int a = fgetc(fc);
int b = fgetc(fw);
if (a != b) { rc = -1; break; }
if (a == EOF) break;
}
}
if (fc) fclose(fc);
if (fw) fclose(fw);
if (rc != 0)
fprintf(stderr, "row[%s]: cstage vs wwstage asm differs\n",
r->label);
unlink(src); unlink(cs); unlink(ws);
return rc;
}
int
main(void)
{
const char *bin = getenv("BIN");
if (!bin) bin = "out/bin";
char absbin[1024];
if (bin[0] != '/') {
char cwd[1024];
if (getcwd(cwd, sizeof cwd) == NULL) return 1;
snprintf(absbin, sizeof absbin, "%s/%s", cwd, bin);
bin = absbin;
}
char cdrv[1024];
snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
char wdrv[1024];
snprintf(wdrv, sizeof wdrv, "%s/ww_ww", bin);
struct { const char *name; const char *path; int gated_on_existence; }
drivers[] = {
{ "cstage", cdrv, 0 },
{ "wwstage", wdrv, 1 },
{ NULL, NULL, 0 },
};
int n = (int)(sizeof rows / sizeof rows[0]);
int total = 0, fail = 0;
for (int d = 0; drivers[d].name; d++) {
if (drivers[d].gated_on_existence
&& access(drivers[d].path, X_OK) != 0) {
fprintf(stderr, "structlit_slice_field: skip %s (no %s)\n",
drivers[d].name, drivers[d].path);
continue;
}
for (int i = 0; i < n; i++) {
int got = run_driver(drivers[d].path, &rows[i], i);
total++;
if (got != rows[i].want) {
fprintf(stderr,
"structlit_slice_field[%s][%s]: exit=%d want=%d\n",
drivers[d].name, rows[i].label,
got, rows[i].want);
fail++;
}
}
}
if (access(wdrv, X_OK) == 0) {
for (int i = 0; i < n; i++) {
total++;
if (asm_byte_identical(bin, &rows[i], i) != 0)
fail++;
}
}
if (fail) {
fprintf(stderr,
"structlit_slice_field: %d/%d fixtures failed\n",
fail, total);
return 1;
}
printf("structlit_slice_field: %d/%d ok\n", total, total);
return 0;
}