Confine restricted engines before launch and preserve the reader recovery baseline

2026-10-07 20:47:53 -07:00
parent dbd159be70
commit b5046ad680
8 changed files with 338 additions and 32 deletions
@@ -0,0 +1,77 @@
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+/* Trusted, single-process admission gate. The supervisor charges this PID to
+ * its engine cgroup before releasing stdin. All subsequently created namespace
+ * helpers and threads inherit that charge. No authored code runs here. */
+static void fail(const char *message) {
+  fprintf(stderr, "RESTRICTED_SANDBOX: %s\n", message);
+  exit(125);
+}
+
+int main(int argc, char **argv) {
+  struct stat info;
+  if (argc != 2 || argv[1][0] != '/' || strstr(argv[1], "/../") ||
+      lstat(argv[1], &info) || !S_ISDIR(info.st_mode) ||
+      info.st_uid != getuid() || (info.st_mode & 077))
+    fail("invalid engine directory");
+  char gate;
+  if (read(STDIN_FILENO, &gate, 1) != 1 || gate != 1)
+    fail("engine admission was not released");
+  int input = open("/dev/null", O_RDONLY);
+  if (input < 0 || dup2(input, STDIN_FILENO) < 0)
+    fail("stdin");
+  close(input);
+  int filter = open(SANDBOX_FILTER, O_RDONLY);
+  if (filter < 0)
+    fail("seccomp filter");
+  char filter_fd[32];
+  snprintf(filter_fd, sizeof(filter_fd), "%d", filter);
+  char *args[4096];
+  size_t count = 0;
+#define ARG(value) args[count++] = (value)
+  ARG(SANDBOX_BWRAP);
+  ARG("--unshare-all");
+  ARG("--unshare-user");
+  ARG("--die-with-parent");
+  ARG("--disable-userns");
+  ARG("--assert-userns-disabled");
+  ARG("--cap-drop"); ARG("ALL");
+  ARG("--hostname"); ARG("quixos-restricted");
+  ARG("--clearenv");
+  ARG("--setenv"); ARG("TZ"); ARG("UTC");
+  ARG("--setenv"); ARG("LANG"); ARG("C.UTF-8");
+  FILE *closure = fopen(SANDBOX_CLOSURE, "r");
+  if (!closure)
+    fail("runtime closure");
+  char *line = NULL;
+  size_t capacity = 0;
+  while (getline(&line, &capacity, closure) >= 0) {
+    line[strcspn(line, "\n")] = 0;
+    if (strncmp(line, "/nix/store/", 11) || strchr(line, ' ') || count > 4000)
+      fail("runtime closure entry");
+    char *path = strdup(line);
+    if (!path)
+      fail("runtime closure allocation");
+    ARG("--ro-bind"); ARG(path); ARG(path);
+  }
+  fclose(closure);
+  free(line);
+  ARG("--proc"); ARG("/proc");
+  ARG("--dev"); ARG("/dev");
+  ARG("--tmpfs"); ARG("/tmp");
+  ARG("--bind"); ARG(argv[1]); ARG(argv[1]);
+  ARG("--chdir"); ARG(argv[1]);
+  ARG("--seccomp"); ARG(filter_fd);
+  ARG("--"); ARG(SANDBOX_EXECUTABLE);
+  ARG("serve"); ARG("--experimental"); ARG("config.capnp");
+  ARG(NULL);
+  execv(SANDBOX_BWRAP, args);
+  fail("bubblewrap failed");
+}