ww/test/wcc/731_fnret_bare_leaf_shadow.c

/*
 * 731_fnret_bare_leaf_shadow — sentinel for the trio leaf-name
 * pattern's 8th and FINAL leaf: wwstage's bare-leaf fnretlookup
 * (selfhost/cmd/wcc/cgen.ww). Pins bare-leaf `foo()` calls (N_IDENT
 * callee) to a same-module-first walk so cgcall's str-pair shuffle
 * decision fires against the caller's own foo's return type, not
 * another module's same-leaf-name foo sitting at the head of
 * c.fnrets.
 *
 * Pre-fix wwstage's `fnretlookup` walked c.fnrets head-first by
 * fname and returned the FIRST match's rtype. cgcall (cgenexpr.ww
 * cgcall:3249) handed it `calleename` (the bare leaf from an
 * N_IDENT callee) and the head-pick silently picked a sibling
 * module's same-leaf foo. When that sibling foo returned `str`
 * and the caller's own foo returned a scalar (i64 here), the
 * `isstrtype(c, rt)` guard fired against the wrong type and
 * emitted a spurious `MOVQ DX, BX` shuffle after the CALL — the
 * SysV (AX, DX) → ww str (AX, BX) shape — corrupting BX even
 * though the callee never returned an str pair. Every other bare-
 * leaf consumer (taggedcallslot, callsretsize, exprfloatkind,
 * rhstaggedabicall, tuple destructure in cglet / cgmlet, fn-rvalue
 * LEAQ in cgident, cgtryprop/cgtryunw success-shuffle) keys on
 * the same fnretlookup return and was silently miscompiling under
 * the same collision shape.
 *
 * Cstage carries no sister bug: cmd/wcc/check.c N_CALL routes
 * `cexpr(c, n->lhs)` through scope_lookup_prefer for an N_IDENT
 * callee, then cmd/w6c/cgen.c reads the return type from the
 * typed `n->lhs->type`'s TY_FN sig — module-aware via the typed
 * AST, sidestepping any bare-leaf table. Same shape as #4a/#4b/
 * #4c/#4d: cs vs ws diverge on every same-leaf fn return-type
 * collision but no in-tree corpus declares two same-leaf fns
 * with diverging return-type *categories* (str vs scalar, tagged
 * vs not, tuple vs not, float vs int) today, so 995_self_rebuild
 * stays green — the in-corpus leaf collisions (utf8.next vs
 * strings.next, strconv.invalid vs utf8.invalid, etc.) are all
 * routed through the existing fnretlookupmod N_DOT variant and
 * the bare-leaf path never sees them on the present corpus.
 *
 * Eighth and FINAL leaf of the trio graduation (after #27
 * aliaslookup, #28 fnparams *mod*-variant, #31 fnret *mod*-variant,
 * #4a enum, #4b struct, #4c def, #4d fnparams bare-leaf).
 * fnretlookupmod (the N_DOT consumer at cgen.ww:1585) already
 * exists post-#31; this commit graduates only the BARE-LEAF entry
 * point with a same-module-first walk mirroring fnparamslookup's
 * two-pass shape (#4d). Twelve+ bare-leaf callsites consume the
 * graduated lookup uniformly (cgenutil.ww:468/494/611/1428/1674/
 * 2286/2795, cgenexpr.ww:160/204/565/1709/3249, cgenstmt.ww:173/
 * 1017, cgendecl.ww:104) — none are independently re-routed to
 * fnretlookupmod in this commit. The in-tree N_DOT cross-module
 * fn collisions (utf8.next vs strings.next; bytes.hasprefix vs
 * strings.hasprefix and equivalents) all have invariant return
 * shape across the colliding overloads (rune-or-done tagged on
 * both next, bool on both hasprefix), so the consumer behaviour
 * is invariant either way for the N_DOT-feeding sites (e.g. the
 * cgcall:3249 callsite reads callee.kind == N_DOT and feeds the
 * bare leaf — invariant on the present corpus). A future stdlib
 * port introducing a return-category-divergent same-leaf N_DOT
 * collision will need the *mod re-routing — file at that
 * surfacing.
 *
 * Pin: row 1 sentinel-flips the bare-leaf graduation on wwstage —
 * revert the prefer pass and row 1 fails on wwstage (a spurious
 * `MOVQ DX, BX` for the wrong-module str shuffle sneaks in after
 * the CALL). Cstage sees no shuffle either way (typed AST is
 * module-aware). Asserts CALL alpha.foo present inside the right
 * TEXT sym + bad_imm (`MOVQ\tDX, BX`) 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 call */
	const char *want_imm;	/* substring that MUST appear */
	const char *bad_imm;	/* substring that MUST NOT appear */
};

/* Source ordering picks which module's `fn foo` sits at the head of
 * c.fnrets after collectfnrets' head-prepend walk. The LAST `fn foo`
 * in source order ends at the head — that's the leaf-collision the
 * same-module-first walk must beat. Caller is inside alpha; alpha's
 * foo returns i64 (no str shuffle), beta's foo returns str (head-
 * pick would falsely emit MOVQ DX, BX). */
static const struct row rows[] = {
	{ "bare_leaf_same_module",
	  "package gamma;\n"
	  "import alpha;\n"
	  "import beta;\n"
	  "export fn main() i32 = { return 0; };\n"
	  "package alpha;\n"
	  "export fn foo() i64 = { return 0; };\n"
	  "export fn alphacaller() i64 = { return foo(); };\n"
	  "package beta;\n"
	  "export fn foo() str = { return \"x\"; };\n",
	  "TEXT alpha.alphacaller", "CALL\talpha.foo", "MOVQ\tDX, BX" },
};

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/frb_%d_%d.ww", getpid(), i);
	snprintf(out_s, cap, "/tmp/frb_%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 bare-leaf
 * head-walk picking beta's str-returning foo and emitting a spurious
 * MOVQ DX, BX after the CALL to a scalar-returning fn. */
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 foo str-shuffled\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,
			    "fnret_bare_leaf_shadow[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,
			    "fnret_bare_leaf_shadow[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,
			    "fnret_bare_leaf_shadow[%s]: cstage vs wwstage asm differs\n",
			    rows[i].label);
			fail++;
		}

		unlink(cs_path); unlink(ws_path);
	}

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