Files
ww/test/wcc/758_cgalloc_str_field.c
Hojun-Cho af1549d9c5 selfhost/cmd/wcc: cgalloc str-field store + regression test
wwstage cgalloc N_STRUCTLIT branch emitted MOVQ AX,foff(BX) for every
non-float field. For a str field the cgexpr result is (AX=ptr, BX=len)
and the single MOVQ clobbered BX with the heap pointer, dropping len.
Mirror cmd/w6c/cgen.c:4184-4190: isstrtype branch routes through CX
so BX=len survives. TY_STR only — slice/tagged/fn-pair have the same
gap on both stages (task #23, parked behind Phase 2).

New test/wcc/758_cgalloc_str_field.c is table-driven (6 rows), fails
without the fix under wwstage with predicted exit codes.
2026-05-20 16:51:32 +09:00

224 lines
6.9 KiB
C

/*
* 758_cgalloc_str_field — cgalloc N_STRUCTLIT str-field store (task #22).
*
* Pre-fix: wwstage cgalloc's per-field walk routed str-typed fields
* through the generic `MOVQ (SP), BX ; MOVQ AX, foff(BX)` path, which
* landed only AX (str.ptr) and clobbered BX (str.len) with the heap
* base. str.len silently stayed zero (rt_alloc is MAP_ANON-backed, so
* the slot was zero-init rather than garbage — but still wrong). 990
* and 995 byte-identity didn't catch this because nothing in the
* bootstrapped selfhost source uses `alloc(T { strfield = "..." })!`.
*
* Fix: a str-field-typed branch mirrors cmd/w6c/cgen.c:4184-4190 —
* route the heap base through CX so BX=len survives both stores
* (ptr at foff+0, len at foff+8). Task #23 (slice/tagged/fn-pair
* multi-word fields) is the broader follow-up; this row pins str.
*
* Each row runs the generated binary under cstage and (when present)
* wwstage; the exit code is the regression-catching gate. The cstage
* row is the cross-check oracle.
*
* Byte-identity is intentionally NOT checked here. cgalloc N_STRUCTLIT
* already diverges on two pre-existing axes that 995_self_rebuild
* doesn't exercise because selfhost source uses amalloc, never
* `alloc(T{...})!`:
* - `CALL alloc(SB)` (cstage, via ffi_resolve) vs `CALL rt_alloc(SB)`
* (wwstage, hardcoded symbol).
* - `(BX)` (cstage txt.c omits zero displacement) vs `0(BX)`
* (wwstage emitint(0) is unconditional). The new str branch
* follows the existing float / int branch shape and inherits the
* same formatting; aligning all three with cstage is a separate
* follow-up.
*/
#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[] = {
/* Singleton str field. Pre-fix p.s.len stayed 0; post-fix 5. */
{ "alloc_str_singleton",
"package main;\n"
"import os;\n"
"type holder = struct { s: str };\n"
"fn main() i32 = {\n"
" let p: *holder = alloc(holder { s = \"hello\" })!;\n"
" return p.s.len;\n"
"};\n",
5 },
/* i32 field before str. Verifies field iteration restarts cleanly
* after the str-field branch and that the i32 store path is
* unaffected. Pre-fix: 100 + 0 = 100; post-fix: 100 + 2 = 102. */
{ "alloc_i32_then_str",
"package main;\n"
"import os;\n"
"type holder = struct { n: i32, s: str };\n"
"fn main() i32 = {\n"
" let p: *holder = alloc(holder { n = 100, s = \"hi\" })!;\n"
" return p.n + p.s.len;\n"
"};\n",
102 },
/* str field before i32. Verifies foff>0 routing for the trailing
* i32 store after the str-field branch. Pre-fix: 0 + 7 = 7;
* post-fix: 5 + 7 = 12. */
{ "alloc_str_then_i32",
"package main;\n"
"import os;\n"
"type holder = struct { s: str, n: i32 };\n"
"fn main() i32 = {\n"
" let p: *holder = alloc(holder { s = \"world\", n = 7 })!;\n"
" return p.s.len + p.n;\n"
"};\n",
12 },
/* Two str fields. Pre-fix both lens stayed 0; post-fix 3 + 6 = 9.
* Pins that `fi = nil` advances correctly between str fields. */
{ "alloc_two_str",
"package main;\n"
"import os;\n"
"type holder = struct { a: str, b: str };\n"
"fn main() i32 = {\n"
" let p: *holder = alloc(holder { a = \"foo\", b = \"barbaz\" })!;\n"
" return p.a.len + p.b.len;\n"
"};\n",
9 },
/* Float-then-str-then-int. Pre-fix str.len=0 so result is
* 0 + 10 = 10; post-fix 3 + 10 = 13. Confirms the str-field
* branch slots between the existing float and integer branches
* without disrupting either. */
{ "alloc_f64_str_i32",
"package main;\n"
"import os;\n"
"type holder = struct { f: f64, s: str, n: i32 };\n"
"fn main() i32 = {\n"
" let p: *holder = alloc(holder { f = 1.5f64, s = \"abc\", n = 10 })!;\n"
" return p.s.len + p.n;\n"
"};\n",
13 },
/* Read-back via p.s[i]: confirms str.ptr survived the store
* (foff=0 case) while still pinning str.len. Pre-fix len=0 so
* the loop body never executes; post-fix sum is 'h'+'i' = 209.
* Indexes the string by hand to avoid pulling in stdlib. */
{ "alloc_str_readback",
"package main;\n"
"import os;\n"
"type holder = struct { s: str };\n"
"fn main() i32 = {\n"
" let p: *holder = alloc(holder { s = \"hi\" })!;\n"
" let sum: i32 = 0;\n"
" let i: i32 = 0;\n"
" for (i < p.s.len) {\n"
" sum += p.s[i]: i32;\n"
" i += 1;\n"
" };\n"
" return sum;\n"
"};\n",
209 },
};
/* run_driver — compile r->src via the given driver and exec; return
* the process exit code. Mirror of 703/704. */
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/wcas_%d_%d.ww", getpid(), i);
snprintf(tmpdir, sizeof tmpdir, "/tmp/wcas_%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;
}
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, "cgalloc_str_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,
"cgalloc_str_field[%s][%s]: exit=%d want=%d\n",
drivers[d].name, rows[i].label,
got, rows[i].want);
fail++;
}
}
}
if (fail) {
fprintf(stderr,
"cgalloc_str_field: %d/%d fixtures failed\n",
fail, total);
return 1;
}
printf("cgalloc_str_field: %d/%d ok\n", total, total);
return 0;
}