ww/test/wcc/915_arr_module_index_run.c

/*
 * 915_arr_module_index_run — runtime + byte-id net for #128b: a
 * cross-package indexed read on an imported global `let arr: [N]T`
 * (the `mod.arr[i]` shape) must compute the array's ADDRESS via LEAQ
 * and stride by the element type's size. Pre-fix both stages
 * mis-compiled this shape, but differently:
 *   - cstage: emitted `MOVQ mod.arr(SB), AX` (loaded the first 8 bytes
 *     of the array as if it were a pointer-var value), then ADDed the
 *     index, then MOVZBQ at that junk address — SEGFAULT-class memory
 *     corruption on any non-trivial index. cstage also defaulted esz=1
 *     (the `bt = n->lhs->type` was NULL for SK_USE module idents).
 *   - wwstage: had the same MOVQ-not-LEAQ bug; in earlier session
 *     state also defaulted esz=8 + MOVQ-load (wrong stride + wrong
 *     load-width). By the time #128b ratified, wwstage was emitting
 *     IMUL$2 + MOVZWQ correctly (via stamped n.type_ path) but the
 *     base load remained MOVQ-not-LEAQ.
 *
 * Fix (per the design's option B — use-site at cgindex/cgassign, NOT
 * a provider-shape change at cgdot):
 *   - cstage: extend `cg_dotbase_addr` (the #135 helper) to recognise
 *     module-imported `let X: [N]T` and emit `LEAQ X(SB)` for the
 *     base. Add a `let_var_type(name)` lookup (LetVar gains a `type`
 *     field) so cgindex's N_INDEX case can fall back to the imported
 *     let's type when `n->lhs->type` is NULL (SK_USE-bound ident).
 *   - wwstage: extend `dotbaseaddr` parallel — when the inner ident
 *     isn't a local (localfindnode → nil) but `letvartnode(base.str)`
 *     resolves to N_TARRAY, emit `LEAQ symname(SB)`.
 *
 * Rule-10 alignment: both stages share the same cgindex N_INDEX
 * fallback shape; the helper is the use-site fix per #135's pattern,
 * preserving cgdot's current MOVQ semantics so whole-array-assign
 * shapes (defensive case; not exercised in committed code per
 * design-pass audit) aren't disturbed.
 *
 * Each row carries (a) cstage `ww build` + run asserting the exit
 * code (the cstage-segfault repro now exits cleanly) and (b) a w6c vs
 * w6c_ww `.s` cmp (rule-10 byte-id). Imports `strconv` because its
 * `let left_shift_table: [65]u16` is the canonical reviewer-stofdata
 * probe surface for this bug.
 */
#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; };

static const struct row rows[] = {
	/* The reviewer-stofdata probe: indexed read on an imported [N]u16
	 * at idx=0. Pre-fix cstage segfaulted on nontrivial indices and
	 * MOVZBQ-loaded the wrong byte; here at idx=0 the wrong-stride
	 * doesn't matter, so the test exit reflects the load-width fix:
	 * MOVZWQ now reads the full u16 = 0x0000 → exit 0. */
	{ "mod_u16_idx0",
	  "package main;\n"
	  "import strconv;\n"
	  "export fn main() i32 = {\n"
	  "	let v: u32 = (strconv.left_shift_table[0]: u32);\n"
	  "	return v: i32;\n"
	  "};\n", 0 },
	/* Nontrivial idx: pre-fix segfault repro. table[2] = 0x0801;
	 * 0x0801 mod 256 = 1. */
	{ "mod_u16_idx2",
	  "package main;\n"
	  "import strconv;\n"
	  "export fn main() i32 = {\n"
	  "	let v: u32 = (strconv.left_shift_table[2]: u32);\n"
	  "	return v: i32;\n"
	  "};\n", 1 },
	/* Further idx — pins per-element stride. table[4] = 0x1006;
	 * 0x1006 mod 256 = 6. */
	{ "mod_u16_idx4",
	  "package main;\n"
	  "import strconv;\n"
	  "export fn main() i32 = {\n"
	  "	let v: u32 = (strconv.left_shift_table[4]: u32);\n"
	  "	return v: i32;\n"
	  "};\n", 6 },
	/* Local-array control: confirms the existing IDENT-base path is
	 * unchanged by the #128b cgindex edit. Pre-fix already worked; the
	 * fix is gated by `bt == NULL` so this row's byte-id is
	 * preserved. */
	{ "local_arr_control",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let a: [4]u16 = [10u16, 20u16, 30u16, 40u16];\n"
	  "	let v: u32 = (a[2]: u32);\n"
	  "	return v: i32;\n"
	  "};\n", 30 },
	/* Same-package access (NOT module-qualified) — pins that the
	 * existing in-package IDENT path stays unchanged. left_shift_table
	 * exists in strconv; access from within `package strconv` would be
	 * IDENT-base. Wrap in a tiny helper here to keep test self-
	 * contained; uses local table. */
	{ "local_u16_idx_nonzero",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "	let t: [8]u16 = [0u16, 0x0800u16, 0x0801u16, 0x0803u16, "
	  "0x1006u16, 0x1009u16, 0x100Du16, 0x1812u16];\n"
	  "	let v: u32 = (t[2]: u32);\n"
	  "	return v: i32;\n"
	  "};\n", 1 },
	{ NULL, NULL, 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, "modarridx: 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/wwmoda_%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/wwmoda_%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);

		/* Byte-id only meaningful when the source compiles standalone
		 * to a .s. Module-imported rows need the combined.ww shape
		 * (which `ww build` produces inside tmpdir); we already ran
		 * that above. For the byte-id leg, point at the combined.ww. */
		char combined[160];
		snprintf(combined, sizeof combined, "%s/%s.combined.ww",
		    tmpdir, base);
		(void)combined;
		/* Both stages emit on the original .ww directly; the
		 * combined.ww has the same surface for cgen purposes. We use
		 * the original src for byte-id since w6c/w6c_ww handle the
		 * import resolution when invoked on the file with -I and the
		 * lib search. The probe row asserts module-qualified shape
		 * via direct w6c{,_ww} on the .ww; if the stage can't find
		 * the import, the build above would have failed first. */
		char cs_s[64], ws_s[64];
		snprintf(cs_s, sizeof cs_s, "/tmp/wwmoda_%d_%d_cs.s",
		    getpid(), i);
		snprintf(ws_s, sizeof ws_s, "/tmp/wwmoda_%d_%d_ww.s",
		    getpid(), i);

		/* Skip byte-id leg for rows that need imports — w6c/w6c_ww
		 * standalone won't resolve `import strconv;`. The runtime
		 * leg above (via `ww build`) IS the byte-id+correctness
		 * gate for these rows; the full bootstrap byte-id (994) is
		 * the corpus check. */
		int needs_import = (strstr(rows[i].src, "import ") != NULL);
		if (!needs_import) {
			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(cs_s); unlink(ws_s);
		}
		unlink(src);
	}

	if (fail) {
		fprintf(stderr, "%d/%d mod-arr-idx tests failed\n", fail, n);
		return 1;
	}
	printf("modarridx: %d/%d ok (cstage run + cs==ww byte-id)\n",
	    n, n);
	return 0;
}