ww/test/wcc/745_fnret34_modshadow.c

/*
 * 745_fnret34_modshadow — sentinel for task #34 (sub-bug of #4e):
 * wwstage's cgcall return-ABI fixup keyed bare-leaf fnretlookup, not
 * fnretlookupmod. For N_DOT cross-module callees the post-#4e same-
 * module-first walk grabbed the caller-module's same-leaf fn's
 * return type — when that caller-side fn returned `str` and the
 * cross-module callee returned a non-str ([]u8, struct, scalar) the
 * `isstrtype(c, rt)` guard fired against the wrong type and emitted
 * a spurious `MOVQ DX, BX` shuffle after the cross-module CALL
 * (selfhost/cmd/wcc/cgenexpr.ww cgcall return-ABI fixup).
 *
 * Sibling: nodeisslice / nodeisstr N_CALL arms were N_IDENT-only
 * (selfhost/cmd/wcc/cgenutil.ww), so pushargsrev's slice/str word-
 * count fell through to the 1-word natural-push for any cross-
 * module N_DOT call result — dropping `.len` (and `.cap` for
 * slices). Hare's `strings.slice` body
 * (`fromutf8_unsafe(utf8.slice(begin, end))`, ref/hare/strings/
 * iter.ha:75-77) hits both bugs at once because strings.slice
 * itself returns str (str-shuffle phantom on the inner utf8.slice
 * call) AND passes the inner []u8 to a same-module fn (.len/.cap
 * dropped on the push).
 *
 * Cstage carries no sister bug: cmd/w6c/cgen.c reads the return
 * shape from the typed `n->lhs->type` (TY_FN sig), module-aware via
 * the typed AST. Both cgcall's str-shuffle and the slice/str-arg
 * push count come off n->type directly. Mirror of #4e: cstage
 * sidesteps every fnretlookup-keyed bare-leaf table.
 *
 * Pin: row 1 — caller-module exports `fn slice(s: str) str` (same
 * leaf as the cross-module callee, return shape diverges); calls
 * `myutf8.slice(&d)` returning []u8. Pre-fix wwstage emits a phantom
 * `MOVQ DX, BX` after the CALL (and drops the slice 3-word push if
 * the result is consumed as a slice arg). Post-fix the TEXT sym
 * for caller.run carries no `MOVQ DX, BX` between the CALL and the
 * RET. Asserts CALL myutf8.slice present + bad_imm anti-check on
 * each stage plus cs-vs-ws byte-id.
 */
#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 */
};

/* caller.slice (same leaf as myutf8.slice, returns str) lives in the
 * same source so caller's fnret table holds a slice-named fn returning
 * str. caller.run calls the cross-module myutf8.slice (returning []u8).
 * Pre-fix wwstage's cgcall fnretlookup picks caller.slice (same-module-
 * first) and emits a phantom MOVQ DX, BX after the cross-module CALL. */
static const struct row rows[] = {
	{ "cross_module_same_leaf_str_shuffle",
	  "package caller;\n"
	  "import myutf8;\n"
	  "export fn main() i32 = { return 0; };\n"
	  "export fn slice(s: str) str = { return s; };\n"
	  "export fn run() i32 = {\n"
	  "\tlet d: myutf8.decoder;\n"
	  "\td.x = 0;\n"
	  "\tlet s: []u8 = myutf8.slice(&d);\n"
	  "\treturn s.len;\n"
	  "};\n"
	  "package myutf8;\n"
	  "export type decoder = struct { x: i32 };\n"
	  "export fn slice(d: *myutf8.decoder) []u8 = {\n"
	  "\tlet r: []u8;\n"
	  "\tr.ptr = nil: *u8;\n"
	  "\tr.len = d.x;\n"
	  "\tr.cap = d.x;\n"
	  "\treturn r;\n"
	  "};\n",
	  "TEXT caller.run", "CALL\tmyutf8.slice", "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/fr34_%d_%d.ww", getpid(), i);
	snprintf(out_s, cap, "/tmp/fr34_%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, want_imm MUST
 * appear and bad_imm MUST NOT. bad_imm flags pre-fix wwstage str-
 * shuffle firing on a non-str cross-module callee. */
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 str-shuffle phantom fired\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,
			    "fnret34_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,
			    "fnret34_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,
			    "fnret34_modshadow[%s]: cstage vs wwstage asm differs\n",
			    rows[i].label);
			fail++;
		}

		unlink(cs_path); unlink(ws_path);
	}

	if (fail) {
		fprintf(stderr,
		    "fnret34_modshadow: %d/%d fixtures failed\n",
		    fail, total);
		return 1;
	}
	printf("fnret34_modshadow: %d/%d ok\n", total, total);
	return 0;
}