// https://syzkaller.appspot.com/bug?id=fa407a6613bdd94160cb12d618549a364290e406
// autogenerated by syzkaller (http://github.com/google/syzkaller)

#define _GNU_SOURCE
#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <errno.h>
#include <fcntl.h>
#include <linux/capability.h>
#include <linux/net.h>
#include <netinet/in.h>
#include <sched.h>
#include <signal.h>
#include <signal.h>
#include <stdarg.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdio.h>
#include <sys/mman.h>
#include <sys/mount.h>
#include <sys/mount.h>
#include <sys/prctl.h>
#include <sys/prctl.h>
#include <sys/resource.h>
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/time.h>
#include <sys/time.h>
#include <sys/wait.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>

__attribute__((noreturn)) static void doexit(int status)
{
  volatile unsigned i;
  syscall(__NR_exit_group, status);
  for (i = 0;; i++) {
  }
}
#include <errno.h>
#include <stdarg.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>

const int kFailStatus = 67;
const int kRetryStatus = 69;

static void fail(const char* msg, ...)
{
  int e = errno;
  va_list args;
  va_start(args, msg);
  vfprintf(stderr, msg, args);
  va_end(args);
  fprintf(stderr, " (errno %d)\n", e);
  doexit((e == ENOMEM || e == EAGAIN) ? kRetryStatus : kFailStatus);
}

static void exitf(const char* msg, ...)
{
  int e = errno;
  va_list args;
  va_start(args, msg);
  vfprintf(stderr, msg, args);
  va_end(args);
  fprintf(stderr, " (errno %d)\n", e);
  doexit(kRetryStatus);
}

static uint64_t current_time_ms()
{
  struct timespec ts;

  if (clock_gettime(CLOCK_MONOTONIC, &ts))
    fail("clock_gettime failed");
  return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
}

static void use_temporary_dir()
{
  char tmpdir_template[] = "./syzkaller.XXXXXX";
  char* tmpdir = mkdtemp(tmpdir_template);
  if (!tmpdir)
    fail("failed to mkdtemp");
  if (chmod(tmpdir, 0777))
    fail("failed to chmod");
  if (chdir(tmpdir))
    fail("failed to chdir");
}

static void loop();

static void sandbox_common()
{
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setpgrp();
  setsid();

  struct rlimit rlim;
  rlim.rlim_cur = rlim.rlim_max = 128 << 20;
  setrlimit(RLIMIT_AS, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 8 << 20;
  setrlimit(RLIMIT_MEMLOCK, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 1 << 20;
  setrlimit(RLIMIT_FSIZE, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 1 << 20;
  setrlimit(RLIMIT_STACK, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 0;
  setrlimit(RLIMIT_CORE, &rlim);

#define CLONE_NEWCGROUP 0x02000000

  if (unshare(CLONE_NEWNS)) {
  }
  if (unshare(CLONE_NEWIPC)) {
  }
  if (unshare(CLONE_NEWCGROUP)) {
  }
  if (unshare(CLONE_NEWUTS)) {
  }
  if (unshare(CLONE_SYSVSEM)) {
  }
}

static bool write_file(const char* file, const char* what, ...)
{
  char buf[1024];
  va_list args;
  va_start(args, what);
  vsnprintf(buf, sizeof(buf), what, args);
  va_end(args);
  buf[sizeof(buf) - 1] = 0;
  int len = strlen(buf);

  int fd = open(file, O_WRONLY | O_CLOEXEC);
  if (fd == -1)
    return false;
  if (write(fd, buf, len) != len) {
    close(fd);
    return false;
  }
  close(fd);
  return true;
}

static int real_uid;
static int real_gid;
__attribute__((aligned(64 << 10))) static char sandbox_stack[1 << 20];

static int namespace_sandbox_proc(void* arg)
{
  sandbox_common();

  write_file("/proc/self/setgroups", "deny");
  if (!write_file("/proc/self/uid_map", "0 %d 1\n", real_uid))
    fail("write of /proc/self/uid_map failed");
  if (!write_file("/proc/self/gid_map", "0 %d 1\n", real_gid))
    fail("write of /proc/self/gid_map failed");

  if (unshare(CLONE_NEWNET))
    fail("unshare(CLONE_NEWNET)");

  if (mkdir("./syz-tmp", 0777))
    fail("mkdir(syz-tmp) failed");
  if (mount("", "./syz-tmp", "tmpfs", 0, NULL))
    fail("mount(tmpfs) failed");
  if (mkdir("./syz-tmp/newroot", 0777))
    fail("mkdir failed");
  if (mkdir("./syz-tmp/newroot/dev", 0700))
    fail("mkdir failed");
  unsigned mount_flags = MS_BIND | MS_REC | MS_PRIVATE;
  if (mount("/dev", "./syz-tmp/newroot/dev", NULL, mount_flags, NULL))
    fail("mount(dev) failed");
  if (mkdir("./syz-tmp/newroot/proc", 0700))
    fail("mkdir failed");
  if (mount(NULL, "./syz-tmp/newroot/proc", "proc", 0, NULL))
    fail("mount(proc) failed");
  if (mkdir("./syz-tmp/newroot/selinux", 0700))
    fail("mkdir failed");
  const char* selinux_path = "./syz-tmp/newroot/selinux";
  if (mount("/selinux", selinux_path, NULL, mount_flags, NULL) &&
      mount("/sys/fs/selinux", selinux_path, NULL, mount_flags, NULL))
    fail("mount(selinuxfs) failed");
  if (mkdir("./syz-tmp/pivot", 0777))
    fail("mkdir failed");
  if (syscall(SYS_pivot_root, "./syz-tmp", "./syz-tmp/pivot")) {
    if (chdir("./syz-tmp"))
      fail("chdir failed");
  } else {
    if (chdir("/"))
      fail("chdir failed");
    if (umount2("./pivot", MNT_DETACH))
      fail("umount failed");
  }
  if (chroot("./newroot"))
    fail("chroot failed");
  if (chdir("/"))
    fail("chdir failed");

  struct __user_cap_header_struct cap_hdr = {};
  struct __user_cap_data_struct cap_data[2] = {};
  cap_hdr.version = _LINUX_CAPABILITY_VERSION_3;
  cap_hdr.pid = getpid();
  if (syscall(SYS_capget, &cap_hdr, &cap_data))
    fail("capget failed");
  cap_data[0].effective &= ~(1 << CAP_SYS_PTRACE);
  cap_data[0].permitted &= ~(1 << CAP_SYS_PTRACE);
  cap_data[0].inheritable &= ~(1 << CAP_SYS_PTRACE);
  if (syscall(SYS_capset, &cap_hdr, &cap_data))
    fail("capset failed");

  loop();
  doexit(1);
}

static int do_sandbox_namespace(int executor_pid, bool enable_tun)
{
  int pid;

  real_uid = getuid();
  real_gid = getgid();
  mprotect(sandbox_stack, 4096, PROT_NONE);
  void* arg = (void*)(long)((executor_pid << 1) | enable_tun);
  pid =
      clone(namespace_sandbox_proc, &sandbox_stack[sizeof(sandbox_stack) - 64],
            CLONE_NEWUSER | CLONE_NEWPID, arg);
  if (pid < 0)
    fail("sandbox clone failed");
  return pid;
}

struct ipt_getinfo {
  char name[32];
  unsigned int valid_hooks;
  unsigned int hook_entry[5];
  unsigned int underflow[5];
  unsigned int num_entries;
  unsigned int size;
};

struct ipt_get_entries {
  char name[32];
  unsigned int size;
  unsigned int pad;
  char entrytable[1024];
};

struct xt_counters {
  uint64_t pcnt, bcnt;
};

struct ipt_replace {
  char name[32];
  unsigned int valid_hooks;
  unsigned int num_entries;
  unsigned int size;
  unsigned int hook_entry[5];
  unsigned int underflow[5];
  unsigned int num_counters;
  struct xt_counters* counters;
  char entrytable[1024];
};

struct ipt_table_desc {
  const char* name;
  struct ipt_getinfo info;
  struct ipt_get_entries entries;
  struct ipt_replace replace;
  struct xt_counters counters[10];
};

static struct ipt_table_desc ipv4_tables[] = {
    {.name = "filter"}, {.name = "nat"},      {.name = "mangle"},
    {.name = "raw"},    {.name = "security"},
};

#define IPT_BASE_CTL 64
#define IPT_SO_SET_REPLACE (IPT_BASE_CTL)
#define IPT_SO_GET_INFO (IPT_BASE_CTL)
#define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1)

static void checkpoint_net_namespace(void)
{
  socklen_t optlen;
  unsigned i;
  int fd;

  fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1)
    fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)");
  for (i = 0; i < sizeof(ipv4_tables) / sizeof(ipv4_tables[0]); i++) {
    struct ipt_table_desc* table = &ipv4_tables[i];
    strcpy(table->info.name, table->name);
    strcpy(table->entries.name, table->name);
    strcpy(table->replace.name, table->name);
    optlen = sizeof(table->info);
    if (getsockopt(fd, SOL_IP, IPT_SO_GET_INFO, &table->info, &optlen)) {
      switch (errno) {
      case EPERM:
      case ENOENT:
      case ENOPROTOOPT:
        continue;
      }
      fail("getsockopt(IPT_SO_GET_INFO)");
    }
    if (table->info.size > sizeof(table->entries.entrytable))
      fail("table size is too large: %u", table->info.size);
    if (table->info.num_entries >
        sizeof(table->counters) / sizeof(table->counters[0]))
      fail("too many counters: %u", table->info.num_entries);
    table->entries.size = table->info.size;
    optlen = sizeof(table->entries) - sizeof(table->entries.entrytable) +
             table->info.size;
    if (getsockopt(fd, SOL_IP, IPT_SO_GET_ENTRIES, &table->entries, &optlen))
      fail("getsockopt(IPT_SO_GET_ENTRIES)");
    table->replace.valid_hooks = table->info.valid_hooks;
    table->replace.num_entries = table->info.num_entries;
    table->replace.counters = table->counters;
    table->replace.size = table->info.size;
    memcpy(table->replace.hook_entry, table->info.hook_entry,
           sizeof(table->replace.hook_entry));
    memcpy(table->replace.underflow, table->info.underflow,
           sizeof(table->replace.underflow));
    memcpy(table->replace.entrytable, table->entries.entrytable,
           table->info.size);
  }
  close(fd);
}

static void reset_net_namespace(void)
{
  struct ipt_get_entries entries;
  struct ipt_getinfo info;
  socklen_t optlen;
  unsigned i;
  int fd;

  memset(&info, 0, sizeof(info));
  memset(&entries, 0, sizeof(entries));
  fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1)
    fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)");
  for (i = 0; i < sizeof(ipv4_tables) / sizeof(ipv4_tables[0]); i++) {
    struct ipt_table_desc* table = &ipv4_tables[i];
    if (table->info.valid_hooks == 0)
      continue;
    strcpy(info.name, table->name);
    optlen = sizeof(info);
    if (getsockopt(fd, SOL_IP, IPT_SO_GET_INFO, &info, &optlen))
      fail("getsockopt(IPT_SO_GET_INFO)");
    if (memcmp(&table->info, &info, sizeof(table->info)) == 0) {
      strcpy(entries.name, table->name);
      entries.size = table->info.size;
      optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size;
      if (getsockopt(fd, SOL_IP, IPT_SO_GET_ENTRIES, &entries, &optlen))
        fail("getsockopt(IPT_SO_GET_ENTRIES)");
      if (memcmp(&table->entries, &entries, optlen) == 0)
        continue;
    }
    table->replace.num_counters = info.num_entries;
    optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) +
             table->replace.size;
    if (setsockopt(fd, SOL_IP, IPT_SO_SET_REPLACE, &table->replace, optlen))
      fail("setsockopt(IPT_SO_SET_REPLACE)");
  }
  close(fd);
}

static void remove_dir(const char* dir)
{
  DIR* dp;
  struct dirent* ep;
  int iter = 0;
retry:
  dp = opendir(dir);
  if (dp == NULL) {
    if (errno == EMFILE) {
      exitf("opendir(%s) failed due to NOFILE, exiting", dir);
    }
    exitf("opendir(%s) failed", dir);
  }
  while ((ep = readdir(dp))) {
    if (strcmp(ep->d_name, ".") == 0 || strcmp(ep->d_name, "..") == 0)
      continue;
    char filename[FILENAME_MAX];
    snprintf(filename, sizeof(filename), "%s/%s", dir, ep->d_name);
    struct stat st;
    if (lstat(filename, &st))
      exitf("lstat(%s) failed", filename);
    if (S_ISDIR(st.st_mode)) {
      remove_dir(filename);
      continue;
    }
    int i;
    for (i = 0;; i++) {
      if (unlink(filename) == 0)
        break;
      if (errno == EROFS) {
        break;
      }
      if (errno != EBUSY || i > 100)
        exitf("unlink(%s) failed", filename);
      if (umount2(filename, MNT_DETACH))
        exitf("umount(%s) failed", filename);
    }
  }
  closedir(dp);
  int i;
  for (i = 0;; i++) {
    if (rmdir(dir) == 0)
      break;
    if (i < 100) {
      if (errno == EROFS) {
        break;
      }
      if (errno == EBUSY) {
        if (umount2(dir, MNT_DETACH))
          exitf("umount(%s) failed", dir);
        continue;
      }
      if (errno == ENOTEMPTY) {
        if (iter < 100) {
          iter++;
          goto retry;
        }
      }
    }
    exitf("rmdir(%s) failed", dir);
  }
}

static void test();

void loop()
{
  int iter;
  checkpoint_net_namespace();
  for (iter = 0;; iter++) {
    char cwdbuf[256];
    sprintf(cwdbuf, "./%d", iter);
    if (mkdir(cwdbuf, 0777))
      fail("failed to mkdir");
    int pid = fork();
    if (pid < 0)
      fail("loop fork failed");
    if (pid == 0) {
      prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
      setpgrp();
      if (chdir(cwdbuf))
        fail("failed to chdir");
      test();
      doexit(0);
    }
    int status = 0;
    uint64_t start = current_time_ms();
    for (;;) {
      int res = waitpid(-1, &status, __WALL | WNOHANG);
      if (res == pid)
        break;
      usleep(1000);
      if (current_time_ms() - start > 5 * 1000) {
        kill(-pid, SIGKILL);
        kill(pid, SIGKILL);
        while (waitpid(-1, &status, __WALL) != pid) {
        }
        break;
      }
    }
    remove_dir(cwdbuf);
    reset_net_namespace();
  }
}

uint64_t procid;
void test()
{
  syscall(__NR_unshare, 0x40040000);
}

int main()
{
  char* cwd = get_current_dir_name();
  for (procid = 0; procid < 8; procid++) {
    if (fork() == 0) {
      for (;;) {
        if (chdir(cwd))
          fail("failed to chdir");
        use_temporary_dir();
        int pid = do_sandbox_namespace(procid, false);
        int status = 0;
        while (waitpid(pid, &status, __WALL) != pid) {
        }
      }
    }
  }
  sleep(1000000);
  return 0;
}