Hojun-Cho
f4176b8749
wwstage cgmatch hardcoded `spillsz = 24` + unconditional CX write
where cstage emits `slot_size = (su->kind == TY_TAGGED) ? su->size
: 16` with `if (slot_size > 16)` gating. For 1-word-payload variants
like `(*u8 | oserror)` the slot is 16B; wwstage over-allocated and
over-wrote past the receiver's read window.
Factor cgmatch's non-ident scrutinee-type resolution + spill sizing
into matchscrutt + matchspillsz in cgenutil.ww. cgmatch gates CX
write on `spillsz > 16`; R8 gate `> 24` already correct. scanlocals
N_MATCH branch uses the same helpers — scan+emit lockstep.
Test 716: 4 rows × {cstage runtime, wwstage runtime, asm-byte-id}.
Aliased (*u8 | oserror) ok/err arms, raw (*u8 | i64) for hypothesis
breadth, (str | i64) 24B regression guard.
288 lines
8.8 KiB
C
288 lines
8.8 KiB
C
/*
|
|
* 716_match_spill_pointer_payload — wwstage @match_spill scratch slot
|
|
* sized to the scrutinee's tagged-union slot, not a hardcoded 24B
|
|
* default. Surfaced during task #23 (lib/os path *u8 → str migration)
|
|
* where `kpath` originally returned `(*u8 | oserror)`.
|
|
*
|
|
* Pre-fix (#9): cgmatch's non-ident scrutinee spill defaulted spillsz
|
|
* to 24 and only grew it; cgendecl scanlocals mirrored with a hardcoded
|
|
* `total += 24`. For a 1-word-payload tagged union (`(*u8 | oserror)`
|
|
* with `type oserror = !i64`) the actual slot is 16B (tag + one 8B
|
|
* word) — cstage allocated $48 / 16B slot / 2-word ABI (AX=tag, DX),
|
|
* wwstage allocated $64 / 24B slot / 3-word ABI (AX=tag, DX, CX).
|
|
* Frame-size drift broke bootstrap byte-identity the moment any caller
|
|
* matched on such a return.
|
|
*
|
|
* Fix (#9, wwstage-only per rule 10): factor scrutinee-type resolution
|
|
* into matchscrutt; factor slot-size computation into matchspillsz
|
|
* (default 16, mirroring cmd/w6c/cgen.c cgmatch's `slot_size = (su->
|
|
* kind == TY_TAGGED) ? su->size : 16`). cgmatch gates CX write on
|
|
* `spillsz > 16` (R8 gate `> 24` was already correct). scanlocals
|
|
* uses the same helpers so scan + emit stay lockstep.
|
|
*
|
|
* What this test pins:
|
|
* - Asm byte-identity between cstage and wwstage for the canonical
|
|
* `(*u8 | oserror)` shape (aliased !i64) and the raw `(*u8 | i64)`
|
|
* shape — both must produce $48 frame, 16B spill slot, 2-word
|
|
* return ABI.
|
|
* - Runtime: both arms (pointer / error) round-trip the payload
|
|
* correctly through the narrower spill.
|
|
* - 24B-slot regression guard: `(str | i64)` (max payload 16B, slot
|
|
* 24B) still byte-identical post-fix — the gate must keep the CX
|
|
* write for slot_size > 16.
|
|
*
|
|
* NOT covered: raw `(*u8 | !i64)` (no alias) — wwstage's variant-index
|
|
* resolution for the raw N_TBANG-in-union shape has a separate pre-
|
|
* existing tag-emit divergence from cstage (tag=0 vs tag=1) that is
|
|
* orthogonal to the spill-slot sizing fixed by #9. Documented at the
|
|
* probe .ai/probe_tagged_return_pointer_payload.ww.
|
|
*/
|
|
#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[] = {
|
|
/* 1. Canonical `(*u8 | oserror)` (aliased !i64). Pointer arm
|
|
* returns the first byte through a str-literal `.ptr`. Avoiding
|
|
* a top-level `let buf: [16]u8;` sidesteps an orthogonal wwstage
|
|
* DATAW-emit divergence for module-scope uninit `[N]u8`. */
|
|
{ "ptr_payload_aliased_bang_ok",
|
|
"type oserror = !i64;\n"
|
|
"fn kpath(p: str) (*u8 | oserror) = {\n"
|
|
" if (p.len < 0) { return -36i64: oserror; };\n"
|
|
" let s: str = \"A\";\n"
|
|
" return s.ptr;\n"
|
|
"};\n"
|
|
"fn main() i32 = {\n"
|
|
" let q: str = \"x\";\n"
|
|
" match (kpath(q)) {\n"
|
|
" case let e: oserror => return (e: i64): i32;\n"
|
|
" case let p: *u8 => return p[0]: i32;\n"
|
|
" };\n"
|
|
" return 0;\n"
|
|
"};\n",
|
|
65 },
|
|
/* 2. Same shape, error arm: pre-fix the 24B spill clobbered CX
|
|
* (irrelevant tag-only path) and bumped the frame; this row
|
|
* pins the error arm round-trips -36 + 100 = 64. */
|
|
{ "ptr_payload_aliased_bang_err",
|
|
"type oserror = !i64;\n"
|
|
"fn kpath(p: str) (*u8 | oserror) = {\n"
|
|
" if (p.len >= 0) { return -36i64: oserror; };\n"
|
|
" let s: str = \"A\";\n"
|
|
" return s.ptr;\n"
|
|
"};\n"
|
|
"fn main() i32 = {\n"
|
|
" let q: str = \"x\";\n"
|
|
" match (kpath(q)) {\n"
|
|
" case let e: oserror => return ((e: i64): i32) + 100;\n"
|
|
" case let p: *u8 => return p[0]: i32;\n"
|
|
" };\n"
|
|
" return 0;\n"
|
|
"};\n",
|
|
64 },
|
|
/* 3. Raw `(*u8 | i64)` — no alias, no `!`. Hypothesis (b) probe:
|
|
* the spill-slot fix holds regardless of whether the payload is
|
|
* wrapped in a type alias. */
|
|
{ "ptr_payload_raw_i64_ok",
|
|
"fn kpath(p: str) (*u8 | i64) = {\n"
|
|
" if (p.len < 0) { return -36i64; };\n"
|
|
" let s: str = \"Z\";\n"
|
|
" return s.ptr;\n"
|
|
"};\n"
|
|
"fn main() i32 = {\n"
|
|
" let q: str = \"x\";\n"
|
|
" match (kpath(q)) {\n"
|
|
" case let e: i64 => return e: i32;\n"
|
|
" case let p: *u8 => return p[0]: i32;\n"
|
|
" };\n"
|
|
" return 0;\n"
|
|
"};\n",
|
|
90 },
|
|
/* 4. 24B-slot regression guard. `(str | i64)` slot = 8 tag +
|
|
* 16 str = 24. The CX write at slot+16 is required (carries
|
|
* .len for the str arm). Pre-fix this row passed; post-fix the
|
|
* `spillsz > 16` gate must keep CX. Returns s.len for "hello"
|
|
* = 5. */
|
|
{ "str_payload_24B_keeps_cx",
|
|
"fn pick(b: bool) (str | i64) = {\n"
|
|
" if (b) { return \"hello\"; };\n"
|
|
" return 7i64;\n"
|
|
"};\n"
|
|
"fn main() i32 = {\n"
|
|
" match (pick(true)) {\n"
|
|
" case let e: i64 => return (e: i32) + 200;\n"
|
|
" case let s: str => return s.len: i32;\n"
|
|
" };\n"
|
|
" return 0;\n"
|
|
"};\n",
|
|
5 },
|
|
};
|
|
|
|
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/wcmsp_%d_%d.ww", getpid(), i);
|
|
snprintf(tmpdir, sizeof tmpdir, "/tmp/wcmsp_%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",
|
|
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 — pin frame size + spill layout by diffing the
|
|
* w6c vs w6c_ww text output. The whole point of #9 is that wwstage's
|
|
* frame stops bloating for 1-word-payload variants, so the bytes
|
|
* must match (modulo orthogonal divergences — none on these rows). */
|
|
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/wcmsp_asm_%d_%d.ww", getpid(), i);
|
|
snprintf(cs, sizeof cs, "/tmp/wcmsp_asm_%d_%d_c.s", getpid(), i);
|
|
snprintf(ws, sizeof ws, "/tmp/wcmsp_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[512];
|
|
if (bin[0] != '/') {
|
|
char cwd[256];
|
|
if (getcwd(cwd, sizeof cwd) == NULL) return 1;
|
|
snprintf(absbin, sizeof absbin, "%s/%s", cwd, bin);
|
|
bin = absbin;
|
|
}
|
|
|
|
char cdrv[640];
|
|
snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
|
|
char wdrv[640];
|
|
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_spill_pointer_payload: 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_spill_pointer_payload[%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,
|
|
"match_spill_pointer_payload: %d/%d fixtures failed\n",
|
|
fail, total);
|
|
return 1;
|
|
}
|
|
printf("match_spill_pointer_payload: %d/%d ok\n", total, total);
|
|
return 0;
|
|
}
|