ww/test/wwc/992_6l_ww.c

/*
 * 992_6l_ww — phase-10 marker for the ww-side 6l port.
 *
 * Diffs the C-built `6l` against the ww-built `6l_ww` on a corpus of
 * link inputs. Both must produce byte-identical static ELF binaries.
 * The corpus mixes:
 *   - a single .o input (no archive resolution)
 *   - a .o + libwwrt.a link, exercising the SysV `ar` two-pass loader
 *
 * Any divergence is a port bug in selfhost/cmd/6l/.
 */
#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;
}

/* link `inputs` (space-separated, the caller's responsibility to quote)
 * with both linkers, compare bytes. */
static int
diff_one(const char *bin, const char *label, const char *inputs)
{
	char co[64], wo[64], cmd[4096];
	snprintf(co, sizeof co, "/tmp/wwl_%d_c", getpid());
	snprintf(wo, sizeof wo, "/tmp/wwl_%d_w", getpid());

	snprintf(cmd, sizeof cmd, "%s/6l -o %s %s 2>/dev/null", bin, co, inputs);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "6l_ww FAIL: C 6l errored on %s\n", label);
		unlink(co);
		return -1;
	}
	snprintf(cmd, sizeof cmd, "%s/6l_ww -o %s %s 2>/dev/null", bin, wo, inputs);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "6l_ww FAIL: ww 6l errored on %s\n", label);
		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, "6l_ww FAIL: cannot read output for %s\n", label);
		rc = -1;
	} else if (nc != nw || memcmp(bc, bw, nc) != 0) {
		fprintf(stderr, "6l_ww FAIL: %s — C %zu vs ww %zu bytes\n",
		    label, 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;

	struct {
		const char *label;
		const char *inputs_fmt;	/* %s = cwd */
	} cases[] = {
		/* Real bootstrap-style links: every selfhost main.o paired
		 * with libwwrt.a. Exercises both the .o code path and the
		 * archive two-pass loader (rt_alloc / rt_syscall / rt_abort
		 * are pulled from libwwrt.a as undefs are encountered). */
		{ "wwdump+libwwrt",
		  "%s/selfhost/cmd/wwdump/main.o %s/out/lib/libwwrt.a" },
		{ "6a+libwwrt",
		  "%s/selfhost/cmd/6a/main.o %s/out/lib/libwwrt.a" },
		{ "6l+libwwrt",
		  "%s/selfhost/cmd/6l/main.o %s/out/lib/libwwrt.a" },
		{ NULL, NULL },
	};

	int fail = 0;
	int n = 0;
	for (int i = 0; cases[i].label; i++) {
		char inputs[2048];
		snprintf(inputs, sizeof inputs, cases[i].inputs_fmt, cwd, cwd);
		if (diff_one(bin, cases[i].label, inputs) != 0) fail++;
		n++;
	}
	if (fail) {
		fprintf(stderr, "6l_ww: %d/%d diff(s) failed\n", fail, n);
		return 1;
	}
	printf("6l_ww: byte-identical to C 6l on %d corpus links "
	    "(.o + libwwrt.a archive resolution)\n", n);
	return 0;
}