ww/test/wcc/991_w6a_ww.c

/*
 * 991_w6a_ww — phase-10 marker for the ww-side w6a port.
 *
 * Diffs the C-built `w6a` against the ww-built `w6a_ww` on a corpus of
 * .s files. Both must produce byte-identical ELF .o output. The corpus
 * spans:
 *   - rt/X.s              hand-written runtime; small, varied operands
 *   - generated .s        from the existing selfhost cgen pipeline
 *                         (wwdump/w6a/w6l main.s) - large, exercises
 *                         every encoding path w6c emits
 *
 * Any divergence is a port bug in selfhost/cmd/w6a/.
 */
#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;
}

static const char *
absbin(void)
{
	const char *b = getenv("BIN");
	if (!b) b = "out/bin";
	if (b[0] == '/') return b;
	static char buf[2048];
	char cwd[1024];
	if (getcwd(cwd, sizeof cwd) == NULL) return NULL;
	snprintf(buf, sizeof buf, "%s/%s", cwd, b);
	return buf;
}

static int
slurp(const char *path, char **outbuf, size_t *outlen)
{
	FILE *f = fopen(path, "rb");
	if (!f) return -1;
	fseek(f, 0, SEEK_END);
	long n = ftell(f);
	fseek(f, 0, SEEK_SET);
	if (n < 0) { fclose(f); return -1; }
	char *b = malloc((size_t)n + 1);
	if (!b) { fclose(f); return -1; }
	if (fread(b, 1, (size_t)n, f) != (size_t)n) { free(b); fclose(f); return -1; }
	b[n] = '\0';
	fclose(f);
	*outbuf = b;
	*outlen = (size_t)n;
	return 0;
}

static int
diff_one(const char *bin, const char *src)
{
	char co[64], wo[64], cmd[2048];
	snprintf(co, sizeof co, "/tmp/wwa_%d_c.o", getpid());
	snprintf(wo, sizeof wo, "/tmp/wwa_%d_w.o", getpid());

	snprintf(cmd, sizeof cmd, "%s/w6a -o %s %s 2>/dev/null", bin, co, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "w6a_ww FAIL: C w6a errored on %s\n", src);
		unlink(co);
		return -1;
	}
	snprintf(cmd, sizeof cmd, "%s/w6a_ww -o %s %s 2>/dev/null", bin, wo, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "w6a_ww FAIL: ww w6a errored on %s\n", src);
		unlink(co); unlink(wo);
		return -1;
	}
	char *bc = NULL, *bw = NULL;
	size_t nc = 0, nw = 0;
	int rc = 0;
	if (slurp(co, &bc, &nc) < 0 || slurp(wo, &bw, &nw) < 0) {
		fprintf(stderr, "w6a_ww FAIL: cannot read .o for %s\n", src);
		rc = -1;
	} else if (nc != nw || memcmp(bc, bw, nc) != 0) {
		fprintf(stderr, "w6a_ww FAIL: %s — C %zu vs ww %zu bytes\n",
		    src, nc, nw);
		rc = -1;
	}
	free(bc); free(bw);
	unlink(co); unlink(wo);
	return rc;
}

int
main(void)
{
	const char *bin = absbin();
	if (!bin) return 1;

	char cwd[1024];
	if (getcwd(cwd, sizeof cwd) == NULL) return 1;

	const char *files[] = {
		/* hand-written runtime — small, covers MOVQ/LEAQ/CALL/SYSCALL/RET. */
		"rt/start.s",
		"rt/syscall.s",
		"rt/abort.s",
		"rt/alloc.s",
		"rt/streq.s",
		/* generated .s from the existing selfhost stack — large,
		 * exercises every encoding w6c emits (the only way to hit
		 * the long tail of operand shapes). */
		"selfhost/cmd/wwdump/main.s",
		"selfhost/cmd/w6l/main.s",
		"selfhost/cmd/w6a/main.s",
		NULL,
	};
	int fail = 0;
	int n = 0;
	for (int i = 0; files[i]; i++) {
		char p[2048];
		snprintf(p, sizeof p, "%s/%s", cwd, files[i]);
		if (diff_one(bin, p) != 0) fail++;
		n++;
	}
	if (fail) {
		fprintf(stderr, "w6a_ww: %d/%d diff(s) failed\n", fail, n);
		return 1;
	}
	printf("w6a_ww: byte-identical to C w6a on %d corpus files "
	    "(rt/*.s + selfhost generated main.s)\n", n);
	return 0;
}