Files
ww/test/wcc/949_dotbase_addr_slice_run.c
Hojun-Cho d8aaa54b41 wwstage: sign-extend signed-narrow struct-array-field element load via N_DOT base (#255)
The cgindex N_DOT-base arm set esz from the checker-stamped element
tinfo but skipped signedness, so loadopsz saw signed_elem=false and
emitted MOVL/MOVZ* (zero-extend) where cstage's fldloadop reads
signedness from the element type and emits MOVSXD/MOVSWQ/MOVSBQ. A
negative i8/i16/i32 read of `x.o[k]` (struct `[N]T` field) round-tripped
with the wrong upper bits — silent cs!=ww, byte-id-blind since bootstrap
never indexes signed-narrow struct array-fields.

Mirror the sibling N_INDEX-base arm: signed_elem = typeissigned(dt).
loadopsz already keys on (signed,sz), so this closes all three narrow
widths at once. Pure wwstage-up; cstage unchanged.

949 gains nload_i32/i16/i8 negative-read rows (run + cs==ww byte-id).
combined.ww regen'd for w6c + wwdump (the cgen embedders).
2026-06-02 04:07:42 +09:00

506 lines
16 KiB
C

/*
* 949_dotbase_addr_slice_run — runtime + byte-id net for the array-
* field-base-address family: #252 (the addr-of + slice SIBLING of #135)
* and #253 (the CHAINED-base close-out). 949_dotbase_arr_run covers the
* single-level read/write index path.
*
* #252: taking `&x.o[i]` (address-of an element) or slicing
* `x.o[lo:hi]` / `x.o[lo:]` of a struct's `[N]T`-typed FIELD computed
* the field's VALUE as the base address instead of its ADDRESS: cgen
* emitted `MOVL off(BP),AX` (load the field's first 8 bytes as a
* pointer) where it must emit `LEAQ off(BP),AX` (the field's address)
* -> garbage pointer -> SEGFAULT. The index read/write path was fixed
* in #135; the addr-of N_INDEX "complex base" arm and the N_SLICE base
* arm still fell to the generic cgexpr(base) auto-deref.
*
* #253: the same family with a CHAINED base — the inner is itself an
* N_DOT (`o.p.m[i]` / `o.i.m[i]` / `o.a.b.m[i]`), not a bare ident.
* `cg_dotbase_addr` / `dotbaseaddr` rejected a non-ident inner, so the
* caller fell to cgexpr(base) which auto-derefs the array field's first
* 8 bytes AS a pointer -> garbage base -> SEGFAULT (base64 fillobuf
* `s.enc.encmap[...]` blocker). The fix recovers the container base via
* the dot-chain spine (`cg_dotchain_addr` / `dotchainaddr`): the pointer
* VALUE of inner when inner is a *struct, else the ADDRESS of inner,
* then adds the field offset. One helper extension per stage closes the
* whole family — every op (index r/w, addr-of, slice, compound) routes
* through the same helper. cs==ww BOTH stages broken identically
* pre-fix (gate-blind, pure correctness — not a byte-id divergence).
*
* Byte-id rows (cstage `ww build` + run for exit code; w6c vs w6c_ww
* `.s` cmp for rule-10 byte-id):
* #252 (bare-ident base):
* - addr_local_u8 &x.o[1] on a local value-struct, *p read → 66
* - addr_ptr_u8 &x.o[2] via a *struct param, *p read → 77
* - addr_i32 &x.o[2] on [4]i32 field, *p read (esz=4) → 88
* - slice_u8_expl x.o[1:4] explicit hi, s[0] read → 66
* - slice_u8_dflthi x.o[1:] default hi, s[0] read → 66
* - slice_ptr_u8 x.o[1:4] via a *struct param, s[0] read → 66
* - slice_i32_expl [4]i32 field x.o[1:3], s[1] read (esz=4) → 88
* - slice_i32_dflt [4]i32 field x.o[1:], s[2] read (esz=4) → 55
* - control_bare bare-local [4]u8 &a[1] write + a[1:4] read → 44
* #253 (chained base — *struct-field-pointer / deeper / non-u8):
* - chain_ptr_rd o.p.m[1] read (p:*inner field) → 66
* - chain_ptr_wr o.p.m[2] write, read back via a.m[2] → 77
* - chain_ptr_addr &o.p.m[2] then *q read → 55
* - chain_ptr_sl_e o.p.m[1:4] explicit hi, s[0] → 66
* - chain_ptr_sl_d o.p.m[1:] default hi, s[0] → 66
* - chain_ptr_comp o.p.m[1] += v compound → 66
* - chain_deep_lf o.a.b.m[1] read (a value, b:*inner leaf) → 66
* - chain_triple o.p.q.m[1] read (two ptr links: dotchain → 66
* internal deref, pointer-only structs)
* - chain_tri_comp o.p.q.m[1] += v through the triple chain → 66
* - chain_i32_addr &o.p.m[2] on [4]i32 (esz=4 stride) → 88
* - chain_i32_slice o.p.m[1:3] on [4]i32, s[1] (esz=4) → 88
* - ctrl_ptr_rd p.m[1] read via *e param (control) → 66
* - ctrl_local_rd x.m[1] read, value-local field (control) → 66
*
* Run-only rows (byteid=0): the chained VALUE-container arm (`o.i.m`,
* inner is a value nested struct). These exercise the same fixed helper
* and run correctly, but a value nested-struct instance trips two
* orthogonal pre-existing cs!=ww divergences unrelated to #253 — bare-
* let zero-init policy (wwstage emits an extra `MOVQ $0,off(BP)`) and
* global DATAW byte count (wwstage over-emits) — so the rule-10 byte-id
* gate can't apply here until those are fixed (#254). (A third, the
* signed-narrow index-fallback element-LOAD opcode, was #255 — now
* fixed; these u8 rows never hit it anyway.) Run correctness alone
* proves the #253 segfault is gone for this cell.
* - chain_val_rd o.i.m[1] read (i value nested) → 66
* - chain_val_addr &o.i.m[2] then *q read → 55
* - chain_val_slice o.i.m[1:4], s[0] → 66
* - chain_deep_val o.a.b.m[1] read, full value chain → 66
*
* The bare-local control asserts the N_IDENT base paths still emit
* correct code; the non-u8 rows assert the esz stride extension is
* wired (not silently esz=1).
*/
#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_exit; int byteid; };
static const struct row rows[] = {
{ "addr_local_u8",
"package main;\n"
"type e = struct { o: [4]u8 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[1] = 66u8;\n"
" let p: *u8 = &x.o[1];\n"
" return (*p): i32;\n"
"};\n", 66, 1 },
{ "addr_ptr_u8",
"package main;\n"
"type e = struct { o: [4]u8 };\n"
"fn rd(x: *e) u8 = { let p: *u8 = &x.o[2]; return *p; };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[2] = 77u8;\n"
" return rd(&x): i32;\n"
"};\n", 77, 1 },
{ "addr_i32",
"package main;\n"
"type e = struct { o: [4]i32 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[2] = 88;\n"
" let p: *i32 = &x.o[2];\n"
" return *p;\n"
"};\n", 88, 1 },
{ "slice_u8_expl",
"package main;\n"
"type e = struct { o: [4]u8 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[1] = 66u8;\n"
" let s: []u8 = x.o[1:4];\n"
" return s[0]: i32;\n"
"};\n", 66, 1 },
{ "slice_u8_dflthi",
"package main;\n"
"type e = struct { o: [4]u8 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[1] = 66u8;\n"
" let s: []u8 = x.o[1:];\n"
" return s[0]: i32;\n"
"};\n", 66, 1 },
{ "slice_ptr_u8",
"package main;\n"
"type e = struct { o: [4]u8 };\n"
"fn sl(x: *e) u8 = { let s: []u8 = x.o[1:4]; return s[0]; };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[1] = 66u8;\n"
" return sl(&x): i32;\n"
"};\n", 66, 1 },
{ "slice_i32_expl",
"package main;\n"
"type e = struct { o: [4]i32 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[1] = 99;\n"
" x.o[2] = 88;\n"
" let s: []i32 = x.o[1:3];\n"
" return s[1];\n"
"};\n", 88, 1 },
{ "slice_i32_dflt",
"package main;\n"
"type e = struct { o: [4]i32 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[3] = 55;\n"
" let s: []i32 = x.o[1:];\n"
" return s[2];\n"
"};\n", 55, 1 },
{ "control_bare",
"package main;\n"
"export fn main() i32 = {\n"
" let a: [4]u8;\n"
" a[2] = 44u8;\n"
" let p: *u8 = &a[1];\n"
" *p = 33u8;\n"
" let s: []u8 = a[1:4];\n"
" return s[1]: i32;\n"
"};\n", 44, 1 },
/* #253 chained-base rows. inner/outer types declared per-row so
* each source is self-contained. */
{ "chain_ptr_rd",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outer = struct { p: *inner };\n"
"export fn main() i32 = {\n"
" let a: inner; a.m[1] = 66u8;\n"
" let o: outer; o.p = &a;\n"
" return o.p.m[1]: i32;\n"
"};\n", 66, 1 },
{ "chain_ptr_wr",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outer = struct { p: *inner };\n"
"export fn main() i32 = {\n"
" let a: inner;\n"
" let o: outer; o.p = &a;\n"
" o.p.m[2] = 77u8;\n"
" return a.m[2]: i32;\n"
"};\n", 77, 1 },
{ "chain_ptr_addr",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outer = struct { p: *inner };\n"
"export fn main() i32 = {\n"
" let a: inner; a.m[2] = 55u8;\n"
" let o: outer; o.p = &a;\n"
" let q: *u8 = &o.p.m[2];\n"
" return (*q): i32;\n"
"};\n", 55, 1 },
{ "chain_ptr_sl_e",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outer = struct { p: *inner };\n"
"export fn main() i32 = {\n"
" let a: inner; a.m[1] = 66u8;\n"
" let o: outer; o.p = &a;\n"
" let s: []u8 = o.p.m[1:4];\n"
" return s[0]: i32;\n"
"};\n", 66, 1 },
{ "chain_ptr_sl_d",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outer = struct { p: *inner };\n"
"export fn main() i32 = {\n"
" let a: inner; a.m[1] = 66u8;\n"
" let o: outer; o.p = &a;\n"
" let s: []u8 = o.p.m[1:];\n"
" return s[0]: i32;\n"
"};\n", 66, 1 },
{ "chain_ptr_comp",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outer = struct { p: *inner };\n"
"export fn main() i32 = {\n"
" let a: inner; a.m[1] = 60u8;\n"
" let o: outer; o.p = &a;\n"
" o.p.m[1] += 6u8;\n"
" return o.p.m[1]: i32;\n"
"};\n", 66, 1 },
{ "chain_deep_lf",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type mid = struct { b: *inner };\n"
"type top = struct { a: mid };\n"
"export fn main() i32 = {\n"
" let z: inner; z.m[1] = 66u8;\n"
" let o: top; o.a.b = &z;\n"
" return o.a.b.m[1]: i32;\n"
"};\n", 66, 1 },
{ "chain_triple",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type amid = struct { q: *inner };\n"
"type otop = struct { p: *amid };\n"
"export fn main() i32 = {\n"
" let z: inner; z.m[1] = 66u8;\n"
" let aa: amid; aa.q = &z;\n"
" let o: otop; o.p = &aa;\n"
" return o.p.q.m[1]: i32;\n"
"};\n", 66, 1 },
{ "chain_tri_comp",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type amid = struct { q: *inner };\n"
"type otop = struct { p: *amid };\n"
"export fn main() i32 = {\n"
" let z: inner; z.m[1] = 60u8;\n"
" let aa: amid; aa.q = &z;\n"
" let o: otop; o.p = &aa;\n"
" o.p.q.m[1] += 6u8;\n"
" return o.p.q.m[1]: i32;\n"
"};\n", 66, 1 },
{ "chain_i32_addr",
"package main;\n"
"type inneri = struct { m: [4]i32 };\n"
"type outeri = struct { p: *inneri };\n"
"export fn main() i32 = {\n"
" let a: inneri; a.m[2] = 88;\n"
" let o: outeri; o.p = &a;\n"
" let q: *i32 = &o.p.m[2];\n"
" return *q;\n"
"};\n", 88, 1 },
{ "chain_i32_slice",
"package main;\n"
"type inneri = struct { m: [4]i32 };\n"
"type outeri = struct { p: *inneri };\n"
"export fn main() i32 = {\n"
" let a: inneri; a.m[1] = 99; a.m[2] = 88;\n"
" let o: outeri; o.p = &a;\n"
" let s: []i32 = o.p.m[1:3];\n"
" return s[1];\n"
"};\n", 88, 1 },
{ "ctrl_ptr_rd",
"package main;\n"
"type e = struct { m: [4]u8 };\n"
"fn rd(p: *e) u8 = { return p.m[1]; };\n"
"export fn main() i32 = {\n"
" let x: e; x.m[1] = 66u8;\n"
" return rd(&x): i32;\n"
"};\n", 66, 1 },
{ "ctrl_local_rd",
"package main;\n"
"type e = struct { m: [4]u8 };\n"
"export fn main() i32 = {\n"
" let x: e; x.m[1] = 66u8;\n"
" return x.m[1]: i32;\n"
"};\n", 66, 1 },
/* #255 signed-narrow N_DOT-base index read. Reading x.o[k] of a
* [N]i32/i16/i8 struct field via the N_DOT-base index fallback must
* sign-extend the narrow element (loadopsz keys on (signed,sz) →
* MOVSXD/MOVSWQ/MOVSBQ); pre-fix wwstage left signedness unset and
* emitted MOVL/MOVZ* (zero-extend) where cstage emits MOVS* — a
* byte-id divergence bootstrap never indexes, so these rows ARE the
* net. Negative round-trip (-5 → exit 251 = 256-5). */
{ "nload_i32",
"package main;\n"
"type e = struct { o: [4]i32 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[2] = -5;\n"
" let v: i32 = x.o[2];\n"
" return v;\n"
"};\n", 251, 1 },
{ "nload_i16",
"package main;\n"
"type e = struct { o: [4]i16 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[2] = -5i16;\n"
" let v: i16 = x.o[2];\n"
" return v: i32;\n"
"};\n", 251, 1 },
{ "nload_i8",
"package main;\n"
"type e = struct { o: [4]i8 };\n"
"export fn main() i32 = {\n"
" let x: e;\n"
" x.o[2] = -5i8;\n"
" let v: i8 = x.o[2];\n"
" return v: i32;\n"
"};\n", 251, 1 },
/* #253 chained VALUE-container arm (o.i.m). Run-only (byteid=0):
* a value nested-struct instance trips orthogonal pre-existing
* cs!=ww emission divergences (see header). The fixed helper runs
* these correctly — the segfault is gone. */
{ "chain_val_rd",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outv = struct { i: inner };\n"
"export fn main() i32 = {\n"
" let o: outv; o.i.m[1] = 66u8;\n"
" return o.i.m[1]: i32;\n"
"};\n", 66, 0 },
{ "chain_val_addr",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outv = struct { i: inner };\n"
"export fn main() i32 = {\n"
" let o: outv; o.i.m[2] = 55u8;\n"
" let q: *u8 = &o.i.m[2];\n"
" return (*q): i32;\n"
"};\n", 55, 0 },
{ "chain_val_slice",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type outv = struct { i: inner };\n"
"export fn main() i32 = {\n"
" let o: outv; o.i.m[1] = 66u8;\n"
" let s: []u8 = o.i.m[1:4];\n"
" return s[0]: i32;\n"
"};\n", 66, 0 },
{ "chain_deep_val",
"package main;\n"
"type inner = struct { m: [4]u8 };\n"
"type mid = struct { b: inner };\n"
"type top = struct { a: mid };\n"
"export fn main() i32 = {\n"
" let o: top; o.a.b.m[1] = 66u8;\n"
" return o.a.b.m[1]: i32;\n"
"};\n", 66, 0 },
{ NULL, NULL, 0, 0 }
};
static int
slurp_eq(const char *a, const char *b)
{
FILE *fa = fopen(a, "rb");
FILE *fb = fopen(b, "rb");
if (!fa || !fb) { if (fa) fclose(fa); if (fb) fclose(fb); return -1; }
int rc = 0;
for (;;) {
int ca = fgetc(fa);
int cb = fgetc(fb);
if (ca != cb) { rc = -1; break; }
if (ca == EOF) break;
}
fclose(fa); fclose(fb);
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 w6c[1100], w6c_ww[1100];
snprintf(w6c, sizeof w6c, "%s/w6c", bin);
snprintf(w6c_ww, sizeof w6c_ww, "%s/w6c_ww", bin);
if (access(w6c_ww, X_OK) != 0) {
fprintf(stderr, "dotbaseaddr: w6c_ww missing — cannot run the "
"cs==ww byte-id gate (the whole point of this test)\n");
return 1;
}
int n = 0, fail = 0;
for (int i = 0; rows[i].src; i++, n++) {
char src[64];
snprintf(src, sizeof src, "/tmp/wwdbs_%d_%d.ww", getpid(), i);
FILE *f = fopen(src, "wb");
if (f == NULL) { fail++; continue; }
fputs(rows[i].src, f);
fclose(f);
char tmpdir[64];
snprintf(tmpdir, sizeof tmpdir, "/tmp/wwdbs_%d_d_%d",
getpid(), i);
mkdir(tmpdir, 0755);
char cmd[2048];
snprintf(cmd, sizeof cmd, "cd %s && %s/ww build %s",
tmpdir, bin, src);
if (runwait(cmd) != 0) {
fprintf(stderr, "row[%s]: cstage build failed\n",
rows[i].label);
fail++;
unlink(src); rmdir(tmpdir);
continue;
}
char outbin[128];
const char *base = strrchr(src, '/');
base = base ? base + 1 : src;
snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
char *dot = strrchr(outbin, '.');
if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
int got = runwait(outbin);
if (got != rows[i].want_exit) {
fprintf(stderr, "row[%s]: cstage exit %d, want %d\n",
rows[i].label, got, rows[i].want_exit);
fail++;
}
unlink(outbin); rmdir(tmpdir);
if (!rows[i].byteid) {
/* Run-only row — byte-id blocked by an orthogonal
* pre-existing cs!=ww divergence (see header). */
unlink(src);
continue;
}
char cs_s[64], ws_s[64];
snprintf(cs_s, sizeof cs_s, "/tmp/wwdbs_%d_%d_cs.s",
getpid(), i);
snprintf(ws_s, sizeof ws_s, "/tmp/wwdbs_%d_%d_ww.s",
getpid(), i);
snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null",
w6c, cs_s, src);
if (runwait(cmd) != 0) {
fprintf(stderr, "row[%s]: w6c failed\n", rows[i].label);
fail++; unlink(src); continue;
}
snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null",
w6c_ww, ws_s, src);
if (runwait(cmd) != 0) {
fprintf(stderr, "row[%s]: w6c_ww failed\n",
rows[i].label);
fail++; unlink(src); unlink(cs_s); continue;
}
if (slurp_eq(cs_s, ws_s) != 0) {
fprintf(stderr,
"row[%s]: cstage/wwstage .s DIFFER (rule-10 "
"byte-id violation)\n", rows[i].label);
fail++;
}
unlink(src); unlink(cs_s); unlink(ws_s);
}
if (fail) {
fprintf(stderr, "%d/%d dotbase-addr-slice tests failed\n",
fail, n);
return 1;
}
printf("dotbaseaddr: %d/%d ok (cstage run + cs==ww byte-id)\n",
n, n);
return 0;
}