ww/test/wcc/995_self_rebuild.c

/*
 * 995_self_rebuild — the wwstage rebuilds itself.
 *
 * Drives ww_ww (the ww-side driver, which shells to w6c_ww/w6a_ww/w6l_ww)
 * over each wwstage tool's source and diffs the result byte-for-byte
 * against the cstage-built binary in $BIN. A green run means the
 * toolchain can recompile itself without touching cc, modulo the
 * cold-start binary — which is the v1.0 lock from PLAN.md.
 *
 * This is stricter than `make bootstrap`: that loop only proves the
 * wwdump cgen self-stabilises; this proves every wwstage tool round-
 * trips through the wwstage pipeline.
 *
 * The five tool builds run concurrently: fork() per tool, parent
 * collects each pid with waitpid() and then byte-compares. Wall drops
 * from sum(builds) to max(builds).
 */
#include <stdio.h>
#include <stdlib.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_eq(const char *a, const char *b)
{
	FILE *fa = fopen(a, "rb");
	FILE *fb = fopen(b, "rb");
	if (!fa || !fb) {
		if (fa) fclose(fa);
		if (fb) fclose(fb);
		return -1;
	}
	int rc = 0;
	for (;;) {
		int ca = fgetc(fa);
		int cb = fgetc(fb);
		if (ca != cb) { rc = -1; break; }
		if (ca == EOF) break;
	}
	fclose(fa); fclose(fb);
	return rc;
}

/* Each tool builds via `ww_ww build -I <local> -I lib/ww -I selfhost/cmd/wcc src`.
 * lib/ww holds the language introspection (lex/tok/ast/parse/typ/sym);
 * selfhost/cmd/wcc holds the compiler internals (mem/check/cgen*).
 * Dotted `import encoding.utf8;` finds lib/encoding/utf8/ via the
 * driver's default srclib path post-task-#22 dir-enum.
 * Some tools have a local module dir (w6a, w6l with sibling .ww files).
 * inc_local is "" for tools without one (w6c, ww, wwdump).
 */
struct buildjob {
	const char *tool;
	const char *src_rel;
	const char *inc_local;
	char workdir[64];
	pid_t pid;
};

/* Fork a child that runs the `ww_ww build` for this tool. The child
 * inherits no concurrent siblings — system() spawns a fresh /bin/sh -c.
 * stderr lands in <workdir>/build.err so concurrent builds don't merge
 * their diagnostics. */
static int
spawn_build(const char *bin, const char *cwd, struct buildjob *j)
{
	snprintf(j->workdir, sizeof j->workdir, "/tmp/wwsr_%d_%s",
	    getpid(), j->tool);
	char setup[256];
	snprintf(setup, sizeof setup, "rm -rf %s && mkdir -p %s",
	    j->workdir, j->workdir);
	if (runwait(setup) != 0) return -1;

	char cmd[4096];
	if (j->inc_local && j->inc_local[0]) {
		snprintf(cmd, sizeof cmd,
		    "cd %s && timeout 180 %s/ww_ww build -I %s/%s "
		    "-I %s/lib/ww -I %s/lib/ww/lex -I %s/lib/ww/parse "
		    "-I %s/selfhost/cmd/wcc %s/%s >/dev/null 2>%s/build.err",
		    j->workdir, bin, cwd, j->inc_local,
		    cwd, cwd, cwd, cwd, cwd, j->src_rel, j->workdir);
	} else {
		snprintf(cmd, sizeof cmd,
		    "cd %s && timeout 180 %s/ww_ww build "
		    "-I %s/lib/ww -I %s/lib/ww/lex -I %s/lib/ww/parse "
		    "-I %s/selfhost/cmd/wcc %s/%s >/dev/null 2>%s/build.err",
		    j->workdir, bin, cwd, cwd, cwd, cwd, cwd, j->src_rel, j->workdir);
	}

	pid_t p = fork();
	if (p < 0) return -1;
	if (p == 0) {
		int rc = system(cmd);
		if (rc == -1) _exit(1);
		_exit(WIFEXITED(rc) ? WEXITSTATUS(rc) : 1);
	}
	j->pid = p;
	return 0;
}

/* Reap one job, byte-diff rebuilt vs canonical, replay captured stderr
 * on build failure, rm workdir. Returns 0 on byte-match, -1 otherwise. */
static int
collect_build(const char *bin, struct buildjob *j)
{
	int rc = 0;
	int status;
	if (waitpid(j->pid, &status, 0) < 0) {
		fprintf(stderr, "self-rebuild FAIL: waitpid %s\n", j->tool);
		rc = -1;
	} else if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) {
		fprintf(stderr, "self-rebuild FAIL: ww_ww build errored on %s\n",
		    j->tool);
		/* Replay the captured stderr so the failure is diagnosable. */
		char errpath[256];
		snprintf(errpath, sizeof errpath, "%s/build.err", j->workdir);
		FILE *f = fopen(errpath, "r");
		if (f) {
			char buf[1024];
			while (fgets(buf, sizeof buf, f))
				fputs(buf, stderr);
			fclose(f);
		}
		rc = -1;
	} else {
		char rebuilt[256], canonical[256];
		snprintf(rebuilt,   sizeof rebuilt,   "%s/main", j->workdir);
		snprintf(canonical, sizeof canonical, "%s/%s_ww", bin, j->tool);
		rc = slurp_eq(rebuilt, canonical);
		if (rc != 0) {
			fprintf(stderr, "self-rebuild FAIL: %s rebuilt != cstage %s\n",
			    j->tool, canonical);
		}
	}

	char cleanup[128];
	snprintf(cleanup, sizeof cleanup, "rm -rf %s", j->workdir);
	runwait(cleanup);
	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 buildjob jobs[] = {
		{ "w6c",    "selfhost/cmd/w6c/main.ww",    "",                  {0}, 0 },
		{ "w6a",    "selfhost/cmd/w6a/main.ww",    "selfhost/cmd/w6a",  {0}, 0 },
		{ "w6l",    "selfhost/cmd/w6l/main.ww",    "selfhost/cmd/w6l",  {0}, 0 },
		{ "ww",     "selfhost/cmd/ww/main.ww",     "",                  {0}, 0 },
		{ "wwdump", "selfhost/cmd/wwdump/main.ww", "",                  {0}, 0 },
	};
	const int n = (int)(sizeof jobs / sizeof jobs[0]);

	int spawned = 0;
	for (int i = 0; i < n; i++) {
		if (spawn_build(bin, cwd, &jobs[i]) != 0) {
			fprintf(stderr, "self-rebuild FAIL: spawn %s\n", jobs[i].tool);
			jobs[i].pid = 0;
		} else {
			spawned++;
		}
	}

	int fail = n - spawned;
	for (int i = 0; i < n; i++) {
		if (jobs[i].pid == 0) continue;
		if (collect_build(bin, &jobs[i]) != 0)
			fail++;
	}

	if (fail) {
		fprintf(stderr, "self-rebuild: %d/%d tool(s) diverged\n", fail, n);
		return 1;
	}
	printf("self-rebuild: %d wwstage tool(s) round-trip byte-identical "
	    "through ww_ww + w6c_ww + w6a_ww + w6l_ww\n", n);
	return 0;
}