ww/test/wcc/822_struct_global_byval_arg.c

/*
 * 822_struct_global_byval_arg — a module-global struct passed BY VALUE to
 * a fn (`let g: pt = pt{...}; take(g)`) was silently miscompiled, mirror-
 * opposite on the two stages (task #150, the off==0 localfind footgun /
 * GAP-A.ptr / #231 family):
 *
 *   - cstage (cmd/w6c/cgen.c by-value struct-IDENT call-arg arm): localfind
 *     of a global returns 0, so the BP loads read the stack FRAME, never
 *     `LEAQ main.g(SB)` → garbage (ken saw 104, not the field sum).
 *   - wwstage (selfhost cgenexpr/cgenutil pushargsrev struct arm): the
 *     ≤16B-struct ident with no local slot fell past the local fast path
 *     AND was excluded from the #271 aggregate arm (structident), landing
 *     on the scalar single-PUSHQ default — ONE word for a 2-word struct,
 *     so the callee's word1 read stack garbage (silent field-drop).
 *
 * The fix (ONE both-stage cgen commit, converged byte-IDENTICAL): when the
 * struct-arg operand is a module-global (off==0 && let_islet||def_isstructdef),
 * resolve the global base into BX via `LEAQ name(SB)` and copy ALL
 * eightbytes (`MOVQ off(BX),AX; PUSHQ`) high→low — the #129-A.2 struct-
 * global access shape. The LOCAL path (off!=0) is untouched.
 *
 *   row         | shape                                          | want
 *   ------------+------------------------------------------------+------
 *   two_field   | let g:pt{a:int,b:int}=pt{a=5,b=9}; take(g)     | 14
 *   narrow_mix  | let g:struct{a:i32,b:i32,c:int}; sum           | 6
 *   three_word  | let g:struct{a,b,c:int} (24B, #271 arm); sum   | 7
 *   ctrl_local  | LOCAL struct arg (off!=0, unchanged, byte-id)  | 14
 *
 * two_field / narrow_mix are the mutation-sane rows: pre-fix cstage reads
 * the frame (garbage) and wwstage drops word1. three_word confirms the >16B
 * #271 aggregate arm already handles a struct global (let_islet base).
 * ctrl_local guards the unchanged local-struct path. A byte-id row pins
 * cstage==wwstage `.s` for each source — the convergence the fix delivers.
 *
 * Explicit-typed globals ONLY (`let g: pt = ...`): an inferred `let g =
 * pt{}` would loud via the separate checker Bug 1 (#18) and mask #150.
 */
#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[] = {
	/* two_field — THE regression pin: 2-field 16B struct global by value.
	 * Pre-fix cstage reads the frame (garbage), wwstage drops field b. */
	{ "two_field",
	  "package main;\n"
	  "type pt = struct { a: int, b: int };\n"
	  "let g: pt = pt { a = 5, b = 9 };\n"
	  "fn take(x: pt) int = { return x.a + x.b; };\n"
	  "export fn main() i32 = { return take(g): i32; };\n",
	  14 },

	/* narrow_mix — i32/i32/int packs two narrow fields into eightbyte 0,
	 * int into eightbyte 1; 16B → the struct-ident fast arm (the fix). */
	{ "narrow_mix",
	  "package main;\n"
	  "type pt = struct { a: i32, b: i32, c: int };\n"
	  "let g: pt = pt { a = 1, b = 2, c = 3 };\n"
	  "fn take(x: pt) int = { return (x.a: int) + (x.b: int) + x.c; };\n"
	  "export fn main() i32 = { return take(g): i32; };\n",
	  6 },

	/* three_word — 24B struct global (>16B) routes through the #271
	 * aggregate arm; confirms the global base (let_islet) is honoured. */
	{ "three_word",
	  "package main;\n"
	  "type pt = struct { a: int, b: int, c: int };\n"
	  "let g: pt = pt { a = 1, b = 2, c = 4 };\n"
	  "fn take(x: pt) int = { return x.a + x.b + x.c; };\n"
	  "export fn main() i32 = { return take(g): i32; };\n",
	  7 },

	/* ctrl_local — a LOCAL struct arg (off!=0). cgen unchanged; pins the
	 * local-struct push path stays byte-id (no regress). */
	{ "ctrl_local",
	  "package main;\n"
	  "type pt = struct { a: int, b: int };\n"
	  "fn take(x: pt) int = { return x.a + x.b; };\n"
	  "export fn main() i32 = {\n"
	  "\tlet g: pt = pt { a = 5, b = 9 };\n"
	  "\treturn take(g): i32;\n"
	  "};\n",
	  14 },
};

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/sga_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/sga_%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 2>/dev/null",
	    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;
}

/* asm_byte_identical — w6c vs w6c_ww .s for the same source must match. */
static int
asm_byte_identical(const char *bin, const struct row *r, int i)
{
	char src[64], cs[64], ws[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/sga_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/sga_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/sga_asm_%d_%d_w.s", getpid(), i);

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

	snprintf(cmd, sizeof cmd, "%s/w6c -o %s %s 2>/dev/null", bin, cs, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c errored\n", r->label);
		unlink(src);
		return -1;
	}
	snprintf(cmd, sizeof cmd, "%s/w6c_ww -o %s %s 2>/dev/null",
	    bin, ws, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c_ww errored\n", r->label);
		unlink(src); unlink(cs);
		return -1;
	}

	FILE *fc = fopen(cs, "rb");
	FILE *fw = fopen(ws, "rb");
	int rc = 0;
	if (!fc || !fw) {
		rc = -1;
	} else {
		for (;;) {
			int a = fgetc(fc);
			int b = fgetc(fw);
			if (a != b) { rc = -1; break; }
			if (a == EOF) break;
		}
	}
	if (fc) fclose(fc);
	if (fw) fclose(fw);
	if (rc != 0)
		fprintf(stderr, "row[%s]: cstage vs wwstage asm differs\n",
		    r->label);
	unlink(src); unlink(cs); unlink(ws);
	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 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, "struct_global_byval_arg: 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,
				    "struct_global_byval_arg[%s][%s]: exit=%d want=%d\n",
				    drivers[d].name, rows[i].label,
				    got, rows[i].want);
				fail++;
			}
		}
	}

	if (access(wdrv, X_OK) == 0) {
		for (int i = 0; i < n; i++) {
			total++;
			if (asm_byte_identical(bin, &rows[i], i) != 0)
				fail++;
		}
	}

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