Files
ww/test/wcc/695_match_bind_struct.c
Hojun-Cho ce3a25a0b4 test: contain sepwork scratch per-driver tmpdir, fix /tmp+in-repo leak (#8)
The wcc test drivers ran `ww build <bare-/tmp src>` with no -o, so the
compiler's <stem>.sepwork scratch landed beside the source and was never
cleaned: unbounded /tmp growth (2195 stale dirs observed) that fills tmpfs
and fabricates phantom test failures + silent harness aborts, and for
in-repo fixture builds leaked .sepwork into the tracked tree.

Each leaking build now writes its source + output inside a per-invocation
tmpdir, passes -o <tmpdir>/<stem> so the .sepwork lands inside it, and
rm -rf's the tmpdir on every exit path -- including fopen-fail and the
expected-fail reject builds (scratch is mkdir'd before the build can fail).
`ww run` and explicit-`-o`/byte-id helpers are left as-is; the 990/993
byte-id comparison logic is byte-for-byte unchanged.

Two items filed separately (this commit holds the no-Makefile / no-main.c
rail):
- #13: a stale <src>.s byte-id readback (749) silently no-ops since
  separate-compile emits .s to <ostem>.sepwork/__root.s; documented inline.
- #14: build-system Makefile recipes build selfhost/cmd/*/main.ww with no
  -o and leak main.sepwork in-tree (bounded, gitignored; own commit).

One concern -- sepwork leak hygiene -- across 228 drivers; uniform
transform applied per-file and two-round reviewed. make test: all 402
passed, zero net-new /tmp scratch, zero test-driven in-repo .sepwork.
2026-06-22 23:29:39 +09:00

298 lines
10 KiB
C

/*
* 695_match_bind_struct — `case let v: T => ...` where T is a TY_STRUCT
* variant of a tagged-union scrutinee. wwstage's cgmatch (and the
* matching scanlocals frame pre-scan) hardcoded the bind-slot size to
*
* str -> 16
* []T -> 24
* else -> 8
*
* so a struct variant collapsed to a single 8B word: only the first
* quadword reached the per-arm bind slot, and (worse) the prologue's
* SUBQ underbooked the frame, so localalloc at emit time then ran the
* SP cursor off the bottom of the function's frame and the bind's
* subsequent stores smashed whatever was past it.
*
* cstage cgen.c is fine: the else-branch falls through to
* `bsz = (int)bu->size` and the SP cursor / cg_frame counter both
* ride the same `bu->size`. Worker-28 noted this while landing #28,
* and a reread of cstage's cgmatch (cgen.c ~3998-4017) and stack-
* frame setup confirms — no cstage mirror needed.
*
* Closed in task #31 by:
* - selfhost/cmd/wcc/cgenexpr.ww: cgmatch bsz table replaced with
* `slotsize(c, pat)`. slotsize already covers N_TNAME named struct
* (returns si.totsize), str (16), []T (24), aliases, tuples, and
* primitives (8). Defensive nwords = (bsz + 7) / 8 mirrors cstage.
* - selfhost/cmd/wcc/cgendecl.ww: scanlocals N_MCASE pre-scan
* mirrored — must agree with cgmatch's bind-slot size so the
* prologue SUBQ reserves enough frame.
* - selfhost/cmd/{w6c,wwdump}/main.combined.ww: combined-file mirrors
* of both sites kept in lockstep.
*
* Coverage — seven rows: four structurally distinct TY_STRUCT shapes
* plus three negative controls. The 3xi64 headline repro, a 4-i64
* struct via let-init scrutinee (exercise > 24B payload, so the
* historical 24-cap doesn't quietly pass), a mixed-quadword struct
* with i32 alignment + i64 tail (size still pads to a multiple of 8),
* str/slice/i32 negative controls (the existing sized paths must not
* regress), and a direct `let x: tag = (pair{...}: tag);` scrutinee
* (different from `match (h.e)` — exercises cglet's tagged-init
* route to the same bind site).
*/
#include <stdio.h>
#include <stdlib.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[] = {
/* Headline repro. 3xi64 = 24B struct as a tagged-union variant.
* Bind copies all three quadwords; sum to 31. Pre-fix only v.x
* reached the bind and v.y/v.z were uninitialized stack — exit
* was nondeterministic but never 0. */
{ "pair_3xi64",
"type pair = struct { x: i64, y: i64, z: i64 };\n"
"type tag = (pair | i32);\n"
"type holder = struct { e: tag, mark: i32 };\n"
"fn main() i32 = {\n"
" let h: holder;\n"
" h.mark = 99;\n"
" let p: pair = pair { x = 7i64, y = 11i64, z = 13i64 };\n"
" h.e = (p: tag);\n"
" match (h.e) {\n"
" case let v: pair => {\n"
" let s: i64 = v.x + v.y + v.z;\n"
" if (s != 31i64) { return 1; };\n"
" return 0;\n"
" };\n"
" case let z: i32 => { return 2; };\n"
" };\n"
"};\n",
0 },
/* 4xi64 = 32B struct payload, exercising a >24B bind copy via the
* direct-let-init scrutinee shape (`match (x)` over an ident,
* bypassing the N_DOT spill path). Hardcoding a 24B cap (an
* obvious fix-sketch hack — "if struct then 24") would drop
* v.d and the sum would miss 24, returning 1 not 0.
*
* The N_DOT route through `match (h.t)` for a 32B-payload variant
* is a separate, unrelated gap: cgmatch's scrut spill only writes
* AX/DX/CX/R8 (4 registers, one of which is the tag), so the 4th
* payload quadword is dropped at spill time — not at bind time.
* Cstage sidesteps this with a direct-field addressing special-
* case in cgmatch (cgen.c ~3858-3876) that skips the spill
* entirely; wwstage lacks that path. Filing that as a follow-up;
* the let-init scrutinee already exercises the bind size for
* payloads > 24B without entangling the two bugs. */
{ "wide_4xi64_letinit",
"type wide = struct { a: i64, b: i64, c: i64, d: i64 };\n"
"type tag = (wide | i32);\n"
"fn main() i32 = {\n"
" let x: tag = (wide { a = 1i64, b = 2i64, c = 4i64,\n"
" d = 24i64 }: tag);\n"
" match (x) {\n"
" case let v: wide => {\n"
" let s: i64 = v.a + v.b + v.c + v.d;\n"
" if (s != 31i64) { return 1; };\n"
" return 0;\n"
" };\n"
" case let z: i32 => { return 2; };\n"
" };\n"
"};\n",
0 },
/* Mixed-quadword: i32+i32+i64+i64. registerstruct packs the two
* i32s into one quadword (x@0, y@4, z@8, w@16), totsize = 24
* (after the trailing pad-to-8). Bind must copy all three
* quadwords; reading w must see the right value. */
{ "mixed_i32_i32_i64_i64",
"type mix = struct { x: i32, y: i32, z: i64, w: i64 };\n"
"type tag = (mix | i32);\n"
"type holder = struct { t: tag, mark: i32 };\n"
"fn main() i32 = {\n"
" let h: holder;\n"
" h.mark = 99;\n"
" let m: mix = mix { x = 3, y = 5, z = 11i64, w = 12i64 };\n"
" h.t = (m: tag);\n"
" match (h.t) {\n"
" case let v: mix => {\n"
" if (v.x != 3) { return 10; };\n"
" if (v.y != 5) { return 11; };\n"
" if (v.z != 11i64) { return 12; };\n"
" if (v.w != 12i64) { return 13; };\n"
" return 0;\n"
" };\n"
" case let z: i32 => { return 2; };\n"
" };\n"
"};\n",
0 },
/* Negative control: str variant in (str | pair). Pins that the
* fix didn't shadow the existing 16B str bind. */
{ "str_neg_control",
"type pair = struct { x: i64, y: i64, z: i64 };\n"
"type tag = (str | pair);\n"
"type holder = struct { e: tag, mark: i32 };\n"
"fn main() i32 = {\n"
" let h: holder;\n"
" h.mark = 99;\n"
" h.e = (\"hello\": tag);\n"
" match (h.e) {\n"
" case let s: str => { return s.len: i32; };\n"
" case let v: pair => { return -1; };\n"
" };\n"
"};\n",
5 },
/* Negative control: []u8 variant in ([]u8 | pair). Pins 24B slice
* bind. */
{ "slice_neg_control",
"type pair = struct { x: i64, y: i64, z: i64 };\n"
"type tag = ([]u8 | pair);\n"
"type holder = struct { e: tag, mark: i32 };\n"
"fn main() i32 = {\n"
" let raw: [8]u8;\n"
" raw[0] = 1u8; raw[1] = 2u8; raw[2] = 3u8;\n"
" let h: holder;\n"
" h.mark = 99;\n"
" h.e = (raw[0:3]: tag);\n"
" match (h.e) {\n"
" case let v: []u8 => {\n"
" if (v.cap != 8) { return 20; };\n"
" return v.len: i32;\n"
" };\n"
" case let p: pair => { return -1; };\n"
" };\n"
"};\n",
3 },
/* Negative control: primitive i32 variant — pins the 8B fall-
* through. */
{ "i32_neg_control",
"type pair = struct { x: i64, y: i64, z: i64 };\n"
"type tag = (pair | i32);\n"
"type holder = struct { e: tag, mark: i32 };\n"
"fn main() i32 = {\n"
" let h: holder;\n"
" h.mark = 99;\n"
" h.e = (42i32: tag);\n"
" match (h.e) {\n"
" case let v: pair => { return -1; };\n"
" case let z: i32 => { return z; };\n"
" };\n"
"};\n",
42 },
/* Direct `let x: tag = (struct: tag);` scrutinee — different
* write site than the holder-field assign route, but the bind
* read-side hits the same cgmatch table. Pins the let-init
* shape. */
{ "letinit_direct_scrutinee",
"type pair = struct { x: i64, y: i64, z: i64 };\n"
"type tag = (pair | i32);\n"
"fn main() i32 = {\n"
" let x: tag = (pair { x = 7i64, y = 11i64, z = 13i64 }: tag);\n"
" match (x) {\n"
" case let v: pair => {\n"
" let s: i64 = v.x + v.y + v.z;\n"
" if (s != 31i64) { return 1; };\n"
" return 0;\n"
" };\n"
" case let z: i32 => { return 2; };\n"
" };\n"
"};\n",
0 },
};
static int
run_driver(const char *driver, const struct row *r, int i)
{
char src[128], tmpdir[64], outbin[128], rmcmd[160], cmd[1024];
snprintf(tmpdir, sizeof tmpdir, "/tmp/wmbs_%d_d_%d", getpid(), i);
mkdir(tmpdir, 0755);
snprintf(src, sizeof src, "%s/wmbs_%d_%d.ww", tmpdir, getpid(), i);
snprintf(outbin, sizeof outbin, "%s/wmbs_%d_%d", tmpdir, getpid(), i);
snprintf(rmcmd, sizeof rmcmd, "rm -rf %s", tmpdir);
FILE *f = fopen(src, "wb");
if (!f) { runwait(rmcmd); return -1; }
fputs(r->src, f);
fclose(f);
snprintf(cmd, sizeof cmd, "%s build -o %s %s",
driver, outbin, src);
if (runwait(cmd) != 0) {
fprintf(stderr, "row[%s]: build via %s failed\n",
r->label, driver);
runwait(rmcmd);
return -1;
}
int got = runwait(outbin);
runwait(rmcmd);
return got;
}
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, "match_bind_struct: 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,
"match_bind_struct[%s][%s]: exit=%d want=%d\n",
drivers[d].name, rows[i].label,
got, rows[i].want);
fail++;
}
}
}
if (fail) {
fprintf(stderr,
"match_bind_struct: %d/%d fixtures failed\n", fail, total);
return 1;
}
printf("match_bind_struct: %d/%d ok\n", total, total);
return 0;
}