ww/test/wcc/735_def_modshadow.c

/*
 * 735_def_modshadow — sentinel for the trio leaf-name pattern's 6th
 * leaf: wwstage's deflookuprhs (selfhost/cmd/wcc/cgen.ww). Pins
 * bare-leaf `MSG.len`/`MSG.ptr` on a `def MSG: str = "..."` constant
 * to a same-module-first walk so the field-fold inlines the caller's
 * own strlit length / address rather than another module's same-leaf-
 * name def sitting at the head of c.defs.
 *
 * Pre-fix wwstage's `deflookuprhs` walked c.defs head-first by dname
 * and returned the FIRST match's drhs. cgdot's str-def `.ptr`/`.len`
 * branch handed it `lhs.str` (the bare leaf from a parsed N_IDENT)
 * and the head-pick silently inlined the wrong-module strlit — a
 * LEAQ of the other module's interned strlit label for `.ptr` and a
 * MOVQ of the other module's byte-length for `.len`. Cstage's
 * symmetric Sdef walk in cmd/w6c/cgen.c (N_DOT `.ptr`/`.len` field
 * fold, off==0 branch) did the same head-first pick. The checker's
 * resolve-side already routes through scope_lookup_prefer (cur,
 * cur_mod, MSG) so the typed Sym is right, but cgen's Sdef table is
 * keyed off the bare-leaf string with no module attribution — cs and
 * ws diverged on every same-leaf def collision but no in-tree corpus
 * declares two same-leaf str defs (same surfacing pattern as #4a
 * enumlookup post-strings and #4b structlookup post-strings: latent
 * until a stdlib port introduces the collision).
 *
 * Sixth leaf of the trio graduation (after #27 aliaslookup, #28
 * fnparams, #31 fnret, #4a enum, #4b struct): defent grows a dmod
 * field, deflookup/deflookuprhs walk same-module-first against
 * c.curmod before the head-walk fallback. Cstage Sdef grows a mod
 * field; the symmetric N_DOT `.ptr`/`.len` field-fold walk gains the
 * matching prefer pass keyed off c->cur_mod via sdef_mod_match. The
 * two other cstage Sdef walks (N_IDENT bare-str-def load, N_DOT
 * module-qualified fallback) stay on head-walk in this commit —
 * both have a pre-existing wwstage byte-id break (wwstage emits a
 * bogus MOVQ <mangled>(SB) symbol load for bare/qualified str-def
 * reference instead of strlit-inline), so a graduating prefer pass
 * on the cstage side alone would not sentinel-flip via the cs-vs-ws
 * byte-id check. Deferred to follow-ups #4c-tail-{bare,modqual} +
 * wwstage str-def symbol-load fix. NO deflookupmod variant — same
 * scope rationale as #4b's structlookup-no-mod (no in-tree consumer
 * for `pkg.def.field`).
 *
 * Pin: row 1 sentinel-flips this commit's new same-module-first walk
 * on BOTH stages — revert the prefer pass and row 1 fails on both
 * cstage and wwstage. Asserts the .len fold lands inside the matching
 * TEXT sym with the want_imm present + bad_imm anti-check on each
 * stage plus cs-vs-ws byte-id per row.
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.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;
	const char *textsym;	/* TEXT sym containing the load */
	const char *want_imm;	/* the immediate that MUST appear */
	const char *bad_imm;	/* the immediate that MUST NOT appear */
};

/* Source orderings pick which module's `def MSG` sits at the head of
 * c.defs / sdefs after the collectdefs / sdef_collect head-prepend
 * walk. The LAST `def MSG = ...` in source order ends at the head —
 * that's the leaf-collision the same-module-first walk must beat.
 *
 * Strlit lengths chosen so neither digit-string is a substring of the
 * other (41 vs 27) and neither aliases a common frame/offset constant
 * the asm emits (0/8/16/24/32/48 etc) — strstr-based needle matching
 * would otherwise spuriously hit "$1" inside "$16," etc. */
static const struct row rows[] = {
	{ "bare_leaf_same_module",
	  "// MODULE: gamma\n"
	  "use alpha;\n"
	  "use beta;\n"
	  "export fn main() i32 = { return 0; };\n"
	  "// MODULE: alpha\n"
	  "def MSG: str = \"alpha_msg_for_modshadow_test_pin_45_AAAAA\";\n"
	  "export fn alphalen() i32 = { return MSG.len: i32; };\n"
	  "// MODULE: beta\n"
	  "def MSG: str = \"beta_msg_short_27_chr_pin_X\";\n",
	  "TEXT alpha.alphalen", "$41,", "$27," },
};

static int
slurp(const char *path, char *buf, size_t cap)
{
	FILE *f = fopen(path, "rb");
	if (!f) return -1;
	size_t n = fread(buf, 1, cap - 1, f);
	fclose(f);
	buf[n] = '\0';
	return (int)n;
}

static int
emit_s(const char *w6c, const struct row *r, int i, char *out_s, size_t cap)
{
	char src[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/dms_%d_%d.ww", getpid(), i);
	snprintf(out_s, cap, "/tmp/dms_%d_%d_%s.s",
	    getpid(), i, w6c[strlen(w6c) - 1] == 'w' ? "ww" : "c");

	FILE *f = fopen(src, "wb");
	if (!f) return -1;
	fputs(r->src, f);
	fclose(f);

	snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null", w6c, out_s, src);
	int rc = runwait(cmd);
	unlink(src);
	return rc;
}

/* Inside the named TEXT sym, before its first RET, the want_imm
 * MUST appear and the bad_imm MUST NOT. bad_imm flags pre-fix
 * head-walk picking the wrong-module MSG's strlit length. */
static int
check_imm(const char *spath, const struct row *r, const char *stage)
{
	char buf[1 << 14];
	if (slurp(spath, buf, sizeof buf) < 0) {
		fprintf(stderr, "row[%s][%s]: cannot read %s\n",
		    r->label, stage, spath);
		return -1;
	}
	const char *fn = strstr(buf, r->textsym);
	if (!fn) {
		fprintf(stderr, "row[%s][%s]: no %s in %s\n",
		    r->label, stage, r->textsym, spath);
		return -1;
	}
	const char *ret = strstr(fn, "\tRET");
	if (!ret) {
		fprintf(stderr, "row[%s][%s]: no RET inside %s\n",
		    r->label, stage, r->textsym);
		return -1;
	}
	const char *good = strstr(fn, r->want_imm);
	if (!good || good >= ret) {
		fprintf(stderr,
		    "row[%s][%s]: want_imm %s missing inside %s\n",
		    r->label, stage, r->want_imm, r->textsym);
		return -1;
	}
	const char *bad = strstr(fn, r->bad_imm);
	if (bad && bad < ret) {
		fprintf(stderr,
		    "row[%s][%s]: bad_imm %s present inside %s — wrong-module MSG\n",
		    r->label, stage, r->bad_imm, r->textsym);
		return -1;
	}
	return 0;
}

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 w6c[640], w6c_ww[640];
	snprintf(w6c, sizeof w6c, "%s/w6c", bin);
	snprintf(w6c_ww, sizeof w6c_ww, "%s/w6c_ww", bin);

	int have_ww = (access(w6c_ww, X_OK) == 0);
	int n = (int)(sizeof rows / sizeof rows[0]);
	int total = 0, fail = 0;

	for (int i = 0; i < n; i++) {
		char cs_path[128], ws_path[128];

		if (emit_s(w6c, &rows[i], i, cs_path, sizeof cs_path) != 0) {
			fprintf(stderr,
			    "def_modshadow[cstage][%s]: w6c failed\n",
			    rows[i].label);
			fail++; total++; continue;
		}
		total++;
		if (check_imm(cs_path, &rows[i], "cstage") != 0) fail++;

		if (!have_ww) { unlink(cs_path); continue; }

		if (emit_s(w6c_ww, &rows[i], i, ws_path, sizeof ws_path) != 0) {
			fprintf(stderr,
			    "def_modshadow[wwstage][%s]: w6c_ww failed\n",
			    rows[i].label);
			fail++; total++;
			unlink(cs_path); continue;
		}
		total++;
		if (check_imm(ws_path, &rows[i], "wwstage") != 0) fail++;

		total++;
		char cmd[512];
		snprintf(cmd, sizeof cmd, "cmp -s %s %s", cs_path, ws_path);
		if (runwait(cmd) != 0) {
			fprintf(stderr,
			    "def_modshadow[%s]: cstage vs wwstage asm differs\n",
			    rows[i].label);
			fail++;
		}

		unlink(cs_path); unlink(ws_path);
	}

	if (fail) {
		fprintf(stderr,
		    "def_modshadow: %d/%d fixtures failed\n", fail, total);
		return 1;
	}
	printf("def_modshadow: %d/%d ok\n", total, total);
	return 0;
}