// https://syzkaller.appspot.com/bug?id=578218eb5c779ebb43db291994cb99ee3b040681
// autogenerated by syzkaller (http://github.com/google/syzkaller)

#define _GNU_SOURCE
#include <arpa/inet.h>
#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <errno.h>
#include <errno.h>
#include <fcntl.h>
#include <fcntl.h>
#include <fcntl.h>
#include <linux/capability.h>
#include <linux/futex.h>
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_tun.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <net/if_arp.h>
#include <pthread.h>
#include <sched.h>
#include <signal.h>
#include <signal.h>
#include <stdarg.h>
#include <stdarg.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdio.h>
#include <stdio.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.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/stat.h>
#include <sys/stat.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/time.h>
#include <sys/time.h>
#include <sys/uio.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 vsnprintf_check(char* str, size_t size, const char* format,
                            va_list args)
{
  int rv;

  rv = vsnprintf(str, size, format, args);
  if (rv < 0)
    fail("tun: snprintf failed");
  if ((size_t)rv >= size)
    fail("tun: string '%s...' doesn't fit into buffer", str);
}

static void snprintf_check(char* str, size_t size, const char* format, ...)
{
  va_list args;

  va_start(args, format);
  vsnprintf_check(str, size, format, args);
  va_end(args);
}

#define COMMAND_MAX_LEN 128
#define PATH_PREFIX                                                            \
  "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin "
#define PATH_PREFIX_LEN (sizeof(PATH_PREFIX) - 1)

static void execute_command(const char* format, ...)
{
  va_list args;
  char command[PATH_PREFIX_LEN + COMMAND_MAX_LEN];
  int rv;

  va_start(args, format);
  memcpy(command, PATH_PREFIX, PATH_PREFIX_LEN);
  vsnprintf_check(command + PATH_PREFIX_LEN, COMMAND_MAX_LEN, format, args);
  rv = system(command);
  if (rv != 0)
    fail("tun: command \"%s\" failed with code %d", &command[0], rv);

  va_end(args);
}

static int tunfd = -1;
static int tun_frags_enabled;

#define SYZ_TUN_MAX_PACKET_SIZE 1000

#define MAX_PIDS 32
#define ADDR_MAX_LEN 32

#define LOCAL_MAC "aa:aa:aa:aa:aa:%02hx"
#define REMOTE_MAC "bb:bb:bb:bb:bb:%02hx"

#define LOCAL_IPV4 "172.20.%d.170"
#define REMOTE_IPV4 "172.20.%d.187"

#define LOCAL_IPV6 "fe80::%02hxaa"
#define REMOTE_IPV6 "fe80::%02hxbb"

#define IFF_NAPI 0x0010
#define IFF_NAPI_FRAGS 0x0020

static void initialize_tun(uint64_t pid)
{
  if (pid >= MAX_PIDS)
    fail("tun: no more than %d executors", MAX_PIDS);
  int id = pid;

  tunfd = open("/dev/net/tun", O_RDWR | O_NONBLOCK);
  if (tunfd == -1) {
    printf("tun: can't open /dev/net/tun: please enable CONFIG_TUN=y\n");
    printf("otherwise fuzzing or reproducing might not work as intended\n");
    return;
  }

  char iface[IFNAMSIZ];
  snprintf_check(iface, sizeof(iface), "syz%d", id);

  struct ifreq ifr;
  memset(&ifr, 0, sizeof(ifr));
  strncpy(ifr.ifr_name, iface, IFNAMSIZ);
  ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_NAPI | IFF_NAPI_FRAGS;
  if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0) {
    ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
    if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0)
      fail("tun: ioctl(TUNSETIFF) failed");
  }
  if (ioctl(tunfd, TUNGETIFF, (void*)&ifr) < 0)
    fail("tun: ioctl(TUNGETIFF) failed");
  tun_frags_enabled = (ifr.ifr_flags & IFF_NAPI_FRAGS) != 0;

  char local_mac[ADDR_MAX_LEN];
  snprintf_check(local_mac, sizeof(local_mac), LOCAL_MAC, id);
  char remote_mac[ADDR_MAX_LEN];
  snprintf_check(remote_mac, sizeof(remote_mac), REMOTE_MAC, id);

  char local_ipv4[ADDR_MAX_LEN];
  snprintf_check(local_ipv4, sizeof(local_ipv4), LOCAL_IPV4, id);
  char remote_ipv4[ADDR_MAX_LEN];
  snprintf_check(remote_ipv4, sizeof(remote_ipv4), REMOTE_IPV4, id);

  char local_ipv6[ADDR_MAX_LEN];
  snprintf_check(local_ipv6, sizeof(local_ipv6), LOCAL_IPV6, id);
  char remote_ipv6[ADDR_MAX_LEN];
  snprintf_check(remote_ipv6, sizeof(remote_ipv6), REMOTE_IPV6, id);

  execute_command("sysctl -w net.ipv6.conf.%s.accept_dad=0", iface);

  execute_command("sysctl -w net.ipv6.conf.%s.router_solicitations=0", iface);

  execute_command("ip link set dev %s address %s", iface, local_mac);
  execute_command("ip addr add %s/24 dev %s", local_ipv4, iface);
  execute_command("ip -6 addr add %s/120 dev %s", local_ipv6, iface);
  execute_command("ip neigh add %s lladdr %s dev %s nud permanent", remote_ipv4,
                  remote_mac, iface);
  execute_command("ip -6 neigh add %s lladdr %s dev %s nud permanent",
                  remote_ipv6, remote_mac, iface);
  execute_command("ip link set dev %s up", iface);
}

static void setup_tun(uint64_t pid, bool enable_tun)
{
  if (enable_tun)
    initialize_tun(pid);
}

static int read_tun(char* data, int size)
{
  if (tunfd < 0)
    return -1;

  int rv = read(tunfd, data, size);
  if (rv < 0) {
    if (errno == EAGAIN)
      return -1;
    if (errno == EBADFD)
      return -1;
    fail("tun: read failed with %d", rv);
  }
  return rv;
}

static void flush_tun()
{
  char data[SYZ_TUN_MAX_PACKET_SIZE];
  while (read_tun(&data[0], sizeof(data)) != -1)
    ;
}

static uintptr_t syz_open_dev(uintptr_t a0, uintptr_t a1, uintptr_t a2)
{
  if (a0 == 0xc || a0 == 0xb) {
    char buf[128];
    sprintf(buf, "/dev/%s/%d:%d", a0 == 0xc ? "char" : "block", (uint8_t)a1,
            (uint8_t)a2);
    return open(buf, O_RDWR, 0);
  } else {
    char buf[1024];
    char* hash;
    strncpy(buf, (char*)a0, sizeof(buf));
    buf[sizeof(buf) - 1] = 0;
    while ((hash = strchr(buf, '#'))) {
      *hash = '0' + (char)(a1 % 10);
      a1 /= 10;
    }
    return open(buf, a2, 0);
  }
}

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

  unshare(CLONE_NEWNS);
  unshare(CLONE_NEWIPC);
  unshare(CLONE_NEWCGROUP);
  unshare(CLONE_NEWNET);
  unshare(CLONE_NEWUTS);
  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 (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");
  if (mount("/dev", "./syz-tmp/newroot/dev", NULL,
            MS_BIND | MS_REC | MS_PRIVATE, 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/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;

  setup_tun(executor_pid, enable_tun);

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

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;
  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");
      flush_tun();
      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);
  }
}

struct thread_t {
  int created, running, call;
  pthread_t th;
};

static struct thread_t threads[16];
static void execute_call(int call);
static int running;
static int collide;

static void* thr(void* arg)
{
  struct thread_t* th = (struct thread_t*)arg;
  for (;;) {
    while (!__atomic_load_n(&th->running, __ATOMIC_ACQUIRE))
      syscall(SYS_futex, &th->running, FUTEX_WAIT, 0, 0);
    execute_call(th->call);
    __atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED);
    __atomic_store_n(&th->running, 0, __ATOMIC_RELEASE);
    syscall(SYS_futex, &th->running, FUTEX_WAKE);
  }
  return 0;
}

static void execute(int num_calls)
{
  int call, thread;
  running = 0;
  for (call = 0; call < num_calls; call++) {
    for (thread = 0; thread < sizeof(threads) / sizeof(threads[0]); thread++) {
      struct thread_t* th = &threads[thread];
      if (!th->created) {
        th->created = 1;
        pthread_attr_t attr;
        pthread_attr_init(&attr);
        pthread_attr_setstacksize(&attr, 128 << 10);
        pthread_create(&th->th, &attr, thr, th);
      }
      if (!__atomic_load_n(&th->running, __ATOMIC_ACQUIRE)) {
        th->call = call;
        __atomic_fetch_add(&running, 1, __ATOMIC_RELAXED);
        __atomic_store_n(&th->running, 1, __ATOMIC_RELEASE);
        syscall(SYS_futex, &th->running, FUTEX_WAKE);
        if (collide && call % 2)
          break;
        struct timespec ts;
        ts.tv_sec = 0;
        ts.tv_nsec = 20 * 1000 * 1000;
        syscall(SYS_futex, &th->running, FUTEX_WAIT, 1, &ts);
        if (running)
          usleep((call == num_calls - 1) ? 10000 : 1000);
        break;
      }
    }
  }
}

#ifndef __NR_openat
#define __NR_openat 295
#endif
#ifndef __NR_mmap
#define __NR_mmap 192
#endif
#ifndef __NR_ioctl
#define __NR_ioctl 54
#endif
#undef __NR_mmap
#define __NR_mmap __NR_mmap2

long r[2];
uint64_t procid;
void execute_call(int call)
{
  switch (call) {
  case 0:
    syscall(__NR_mmap, 0x20000000, 0xfff000, 3, 0x32, -1, 0);
    break;
  case 1:
    memcpy((void*)0x209f1ff5, "/dev/loop#", 11);
    r[0] = syz_open_dev(0x209f1ff5, 0, 0x101086);
    break;
  case 2:
    syscall(__NR_ioctl, r[0], 0x4c01);
    break;
  case 3:
    syscall(__NR_ioctl, -1, 0x4c00, -1);
    break;
  case 4:
    memcpy((void*)0x2066e000, "/dev/loop-control", 18);
    r[1] = syscall(__NR_openat, 0xffffff9c, 0x2066e000, 0, 0);
    break;
  case 5:
    syscall(__NR_ioctl, r[1], 0x4c81, 0);
    break;
  }
}

void test()
{
  memset(r, -1, sizeof(r));
  execute(6);
  collide = 1;
  execute(6);
}

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, true);
        int status = 0;
        while (waitpid(pid, &status, __WALL) != pid) {
        }
      }
    }
  }
  sleep(1000000);
  return 0;
}