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

#define _GNU_SOURCE

#include <arpa/inet.h>
#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.h>
#include <net/if_arp.h>
#include <netinet/in.h>
#include <sched.h>
#include <setjmp.h>
#include <signal.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/mount.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/types.h>
#include <sys/uio.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>

#include <linux/capability.h>
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_tun.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/tcp.h>

unsigned long long procid;

static __thread int skip_segv;
static __thread jmp_buf segv_env;

static void segv_handler(int sig, siginfo_t* info, void* ctx)
{
  uintptr_t addr = (uintptr_t)info->si_addr;
  const uintptr_t prog_start = 1 << 20;
  const uintptr_t prog_end = 100 << 20;
  if (__atomic_load_n(&skip_segv, __ATOMIC_RELAXED) &&
      (addr < prog_start || addr > prog_end)) {
    _longjmp(segv_env, 1);
  }
  exit(sig);
}

static void install_segv_handler(void)
{
  struct sigaction sa;
  memset(&sa, 0, sizeof(sa));
  sa.sa_handler = SIG_IGN;
  syscall(SYS_rt_sigaction, 0x20, &sa, NULL, 8);
  syscall(SYS_rt_sigaction, 0x21, &sa, NULL, 8);
  memset(&sa, 0, sizeof(sa));
  sa.sa_sigaction = segv_handler;
  sa.sa_flags = SA_NODEFER | SA_SIGINFO;
  sigaction(SIGSEGV, &sa, NULL);
  sigaction(SIGBUS, &sa, NULL);
}

#define NONFAILING(...)                                                        \
  {                                                                            \
    __atomic_fetch_add(&skip_segv, 1, __ATOMIC_SEQ_CST);                       \
    if (_setjmp(segv_env) == 0) {                                              \
      __VA_ARGS__;                                                             \
    }                                                                          \
    __atomic_fetch_sub(&skip_segv, 1, __ATOMIC_SEQ_CST);                       \
  }

static void sleep_ms(uint64_t ms)
{
  usleep(ms * 1000);
}

static uint64_t current_time_ms(void)
{
  struct timespec ts;
  if (clock_gettime(CLOCK_MONOTONIC, &ts))
    exit(1);
  return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
}

static void use_temporary_dir(void)
{
  char tmpdir_template[] = "./syzkaller.XXXXXX";
  char* tmpdir = mkdtemp(tmpdir_template);
  if (!tmpdir)
    exit(1);
  if (chmod(tmpdir, 0777))
    exit(1);
  if (chdir(tmpdir))
    exit(1);
}

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)
    exit(1);
  if ((size_t)rv >= size)
    exit(1);
}

#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(bool panic, 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);
  va_end(args);
  rv = system(command);
  if (rv) {
    if (panic)
      exit(1);
  }
}

static int tunfd = -1;
static int tun_frags_enabled;
#define SYZ_TUN_MAX_PACKET_SIZE 1000

#define TUN_IFACE "syz_tun"

#define LOCAL_MAC "aa:aa:aa:aa:aa:aa"
#define REMOTE_MAC "aa:aa:aa:aa:aa:bb"

#define LOCAL_IPV4 "172.20.20.170"
#define REMOTE_IPV4 "172.20.20.187"

#define LOCAL_IPV6 "fe80::aa"
#define REMOTE_IPV6 "fe80::bb"

#define IFF_NAPI 0x0010
#define IFF_NAPI_FRAGS 0x0020

static void initialize_tun(void)
{
  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;
  }
  const int kTunFd = 240;
  if (dup2(tunfd, kTunFd) < 0)
    exit(1);
  close(tunfd);
  tunfd = kTunFd;
  struct ifreq ifr;
  memset(&ifr, 0, sizeof(ifr));
  strncpy(ifr.ifr_name, TUN_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)
      exit(1);
  }
  if (ioctl(tunfd, TUNGETIFF, (void*)&ifr) < 0)
    exit(1);
  tun_frags_enabled = (ifr.ifr_flags & IFF_NAPI_FRAGS) != 0;
  execute_command(0, "sysctl -w net.ipv6.conf.%s.accept_dad=0", TUN_IFACE);
  execute_command(0, "sysctl -w net.ipv6.conf.%s.router_solicitations=0",
                  TUN_IFACE);
  execute_command(1, "ip link set dev %s address %s", TUN_IFACE, LOCAL_MAC);
  execute_command(1, "ip addr add %s/24 dev %s", LOCAL_IPV4, TUN_IFACE);
  execute_command(1, "ip neigh add %s lladdr %s dev %s nud permanent",
                  REMOTE_IPV4, REMOTE_MAC, TUN_IFACE);
  execute_command(0, "ip -6 addr add %s/120 dev %s", LOCAL_IPV6, TUN_IFACE);
  execute_command(0, "ip -6 neigh add %s lladdr %s dev %s nud permanent",
                  REMOTE_IPV6, REMOTE_MAC, TUN_IFACE);
  execute_command(1, "ip link set dev %s up", TUN_IFACE);
}

#define DEV_IPV4 "172.20.20.%d"
#define DEV_IPV6 "fe80::%02hx"
#define DEV_MAC "aa:aa:aa:aa:aa:%02hx"

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);
}
static void initialize_netdevices(void)
{
  unsigned i;
  const char* devtypes[] = {"ip6gretap", "bridge", "vcan", "bond", "team"};
  const char* devnames[] = {"lo",
                            "sit0",
                            "bridge0",
                            "vcan0",
                            "tunl0",
                            "gre0",
                            "gretap0",
                            "ip_vti0",
                            "ip6_vti0",
                            "ip6tnl0",
                            "ip6gre0",
                            "ip6gretap0",
                            "erspan0",
                            "bond0",
                            "veth0",
                            "veth1",
                            "team0",
                            "veth0_to_bridge",
                            "veth1_to_bridge",
                            "veth0_to_bond",
                            "veth1_to_bond",
                            "veth0_to_team",
                            "veth1_to_team"};
  const char* devmasters[] = {"bridge", "bond", "team"};
  for (i = 0; i < sizeof(devtypes) / (sizeof(devtypes[0])); i++)
    execute_command(0, "ip link add dev %s0 type %s", devtypes[i], devtypes[i]);
  execute_command(0, "ip link add type veth");
  for (i = 0; i < sizeof(devmasters) / (sizeof(devmasters[0])); i++) {
    execute_command(
        0, "ip link add name %s_slave_0 type veth peer name veth0_to_%s",
        devmasters[i], devmasters[i]);
    execute_command(
        0, "ip link add name %s_slave_1 type veth peer name veth1_to_%s",
        devmasters[i], devmasters[i]);
    execute_command(0, "ip link set %s_slave_0 master %s0", devmasters[i],
                    devmasters[i]);
    execute_command(0, "ip link set %s_slave_1 master %s0", devmasters[i],
                    devmasters[i]);
    execute_command(0, "ip link set veth0_to_%s up", devmasters[i]);
    execute_command(0, "ip link set veth1_to_%s up", devmasters[i]);
  }
  execute_command(0, "ip link set bridge_slave_0 up");
  execute_command(0, "ip link set bridge_slave_1 up");
  for (i = 0; i < sizeof(devnames) / (sizeof(devnames[0])); i++) {
    char addr[32];
    snprintf_check(addr, sizeof(addr), DEV_IPV4, i + 10);
    execute_command(0, "ip -4 addr add %s/24 dev %s", addr, devnames[i]);
    snprintf_check(addr, sizeof(addr), DEV_IPV6, i + 10);
    execute_command(0, "ip -6 addr add %s/120 dev %s", addr, devnames[i]);
    snprintf_check(addr, sizeof(addr), DEV_MAC, i + 10);
    execute_command(0, "ip link set dev %s address %s", devnames[i], addr);
    execute_command(0, "ip link set dev %s up", devnames[i]);
  }
}

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;
    exit(1);
  }
  return rv;
}

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

static long syz_open_dev(long a0, long a1, long 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;
    NONFAILING(strncpy(buf, (char*)a0, sizeof(buf) - 1));
    buf[sizeof(buf) - 1] = 0;
    while ((hash = strchr(buf, '#'))) {
      *hash = '0' + (char)(a1 % 10);
      a1 /= 10;
    }
    return open(buf, a2, 0);
  }
}

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) {
    int err = errno;
    close(fd);
    errno = err;
    return false;
  }
  close(fd);
  return true;
}

#define XT_TABLE_SIZE 1536
#define XT_MAX_ENTRIES 10

struct xt_counters {
  uint64_t pcnt, bcnt;
};

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;
  void* entrytable[XT_TABLE_SIZE / sizeof(void*)];
};

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[XT_TABLE_SIZE];
};

struct ipt_table_desc {
  const char* name;
  struct ipt_getinfo info;
  struct ipt_replace replace;
};

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

static struct ipt_table_desc ipv6_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)

struct arpt_getinfo {
  char name[32];
  unsigned int valid_hooks;
  unsigned int hook_entry[3];
  unsigned int underflow[3];
  unsigned int num_entries;
  unsigned int size;
};

struct arpt_get_entries {
  char name[32];
  unsigned int size;
  void* entrytable[XT_TABLE_SIZE / sizeof(void*)];
};

struct arpt_replace {
  char name[32];
  unsigned int valid_hooks;
  unsigned int num_entries;
  unsigned int size;
  unsigned int hook_entry[3];
  unsigned int underflow[3];
  unsigned int num_counters;
  struct xt_counters* counters;
  char entrytable[XT_TABLE_SIZE];
};

struct arpt_table_desc {
  const char* name;
  struct arpt_getinfo info;
  struct arpt_replace replace;
};

static struct arpt_table_desc arpt_tables[] = {
    {.name = "filter"},
};

#define ARPT_BASE_CTL 96
#define ARPT_SO_SET_REPLACE (ARPT_BASE_CTL)
#define ARPT_SO_GET_INFO (ARPT_BASE_CTL)
#define ARPT_SO_GET_ENTRIES (ARPT_BASE_CTL + 1)

static void checkpoint_iptables(struct ipt_table_desc* tables, int num_tables,
                                int family, int level)
{
  struct ipt_get_entries entries;
  socklen_t optlen;
  int fd, i;
  fd = socket(family, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
      return;
    }
    exit(1);
  }
  for (i = 0; i < num_tables; i++) {
    struct ipt_table_desc* table = &tables[i];
    strcpy(table->info.name, table->name);
    strcpy(table->replace.name, table->name);
    optlen = sizeof(table->info);
    if (getsockopt(fd, level, IPT_SO_GET_INFO, &table->info, &optlen)) {
      switch (errno) {
      case EPERM:
      case ENOENT:
      case ENOPROTOOPT:
        continue;
      }
      exit(1);
    }
    if (table->info.size > sizeof(table->replace.entrytable))
      exit(1);
    if (table->info.num_entries > XT_MAX_ENTRIES)
      exit(1);
    memset(&entries, 0, sizeof(entries));
    strcpy(entries.name, table->name);
    entries.size = table->info.size;
    optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size;
    if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen))
      exit(1);
    table->replace.valid_hooks = table->info.valid_hooks;
    table->replace.num_entries = table->info.num_entries;
    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, entries.entrytable, table->info.size);
  }
  close(fd);
}

static void reset_iptables(struct ipt_table_desc* tables, int num_tables,
                           int family, int level)
{
  struct xt_counters counters[XT_MAX_ENTRIES];
  struct ipt_get_entries entries;
  struct ipt_getinfo info;
  socklen_t optlen;
  int fd, i;
  fd = socket(family, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
      return;
    }
    exit(1);
  }
  for (i = 0; i < num_tables; i++) {
    struct ipt_table_desc* table = &tables[i];
    if (table->info.valid_hooks == 0)
      continue;
    memset(&info, 0, sizeof(info));
    strcpy(info.name, table->name);
    optlen = sizeof(info);
    if (getsockopt(fd, level, IPT_SO_GET_INFO, &info, &optlen))
      exit(1);
    if (memcmp(&table->info, &info, sizeof(table->info)) == 0) {
      memset(&entries, 0, sizeof(entries));
      strcpy(entries.name, table->name);
      entries.size = table->info.size;
      optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size;
      if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen))
        exit(1);
      if (memcmp(table->replace.entrytable, entries.entrytable,
                 table->info.size) == 0)
        continue;
    }
    table->replace.num_counters = info.num_entries;
    table->replace.counters = counters;
    optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) +
             table->replace.size;
    if (setsockopt(fd, level, IPT_SO_SET_REPLACE, &table->replace, optlen))
      exit(1);
  }
  close(fd);
}

static void checkpoint_arptables(void)
{
  struct arpt_get_entries entries;
  socklen_t optlen;
  unsigned i;
  int fd;
  fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
      return;
    }
    exit(1);
  }
  for (i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) {
    struct arpt_table_desc* table = &arpt_tables[i];
    strcpy(table->info.name, table->name);
    strcpy(table->replace.name, table->name);
    optlen = sizeof(table->info);
    if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &table->info, &optlen)) {
      switch (errno) {
      case EPERM:
      case ENOENT:
      case ENOPROTOOPT:
        continue;
      }
      exit(1);
    }
    if (table->info.size > sizeof(table->replace.entrytable))
      exit(1);
    if (table->info.num_entries > XT_MAX_ENTRIES)
      exit(1);
    memset(&entries, 0, sizeof(entries));
    strcpy(entries.name, table->name);
    entries.size = table->info.size;
    optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size;
    if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen))
      exit(1);
    table->replace.valid_hooks = table->info.valid_hooks;
    table->replace.num_entries = table->info.num_entries;
    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, entries.entrytable, table->info.size);
  }
  close(fd);
}

static void reset_arptables()
{
  struct xt_counters counters[XT_MAX_ENTRIES];
  struct arpt_get_entries entries;
  struct arpt_getinfo info;
  socklen_t optlen;
  unsigned i;
  int fd;
  fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
      return;
    }
    exit(1);
  }
  for (i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) {
    struct arpt_table_desc* table = &arpt_tables[i];
    if (table->info.valid_hooks == 0)
      continue;
    memset(&info, 0, sizeof(info));
    strcpy(info.name, table->name);
    optlen = sizeof(info);
    if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &info, &optlen))
      exit(1);
    if (memcmp(&table->info, &info, sizeof(table->info)) == 0) {
      memset(&entries, 0, sizeof(entries));
      strcpy(entries.name, table->name);
      entries.size = table->info.size;
      optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size;
      if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen))
        exit(1);
      if (memcmp(table->replace.entrytable, entries.entrytable,
                 table->info.size) == 0)
        continue;
    } else {
    }
    table->replace.num_counters = info.num_entries;
    table->replace.counters = counters;
    optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) +
             table->replace.size;
    if (setsockopt(fd, SOL_IP, ARPT_SO_SET_REPLACE, &table->replace, optlen))
      exit(1);
  }
  close(fd);
}

struct ebt_table_desc {
  const char* name;
  struct ebt_replace replace;
  char entrytable[XT_TABLE_SIZE];
};

static struct ebt_table_desc ebt_tables[] = {
    {.name = "filter"}, {.name = "nat"}, {.name = "broute"},
};

static void checkpoint_ebtables(void)
{
  socklen_t optlen;
  unsigned i;
  int fd;
  fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
      return;
    }
    exit(1);
  }
  for (i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) {
    struct ebt_table_desc* table = &ebt_tables[i];
    strcpy(table->replace.name, table->name);
    optlen = sizeof(table->replace);
    if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_INFO, &table->replace,
                   &optlen)) {
      switch (errno) {
      case EPERM:
      case ENOENT:
      case ENOPROTOOPT:
        continue;
      }
      exit(1);
    }
    if (table->replace.entries_size > sizeof(table->entrytable))
      exit(1);
    table->replace.num_counters = 0;
    table->replace.entries = table->entrytable;
    optlen = sizeof(table->replace) + table->replace.entries_size;
    if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_ENTRIES, &table->replace,
                   &optlen))
      exit(1);
  }
  close(fd);
}

static void reset_ebtables()
{
  struct ebt_replace replace;
  char entrytable[XT_TABLE_SIZE];
  socklen_t optlen;
  unsigned i, j, h;
  int fd;
  fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
      return;
    }
    exit(1);
  }
  for (i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) {
    struct ebt_table_desc* table = &ebt_tables[i];
    if (table->replace.valid_hooks == 0)
      continue;
    memset(&replace, 0, sizeof(replace));
    strcpy(replace.name, table->name);
    optlen = sizeof(replace);
    if (getsockopt(fd, SOL_IP, EBT_SO_GET_INFO, &replace, &optlen))
      exit(1);
    replace.num_counters = 0;
    table->replace.entries = 0;
    for (h = 0; h < NF_BR_NUMHOOKS; h++)
      table->replace.hook_entry[h] = 0;
    if (memcmp(&table->replace, &replace, sizeof(table->replace)) == 0) {
      memset(&entrytable, 0, sizeof(entrytable));
      replace.entries = entrytable;
      optlen = sizeof(replace) + replace.entries_size;
      if (getsockopt(fd, SOL_IP, EBT_SO_GET_ENTRIES, &replace, &optlen))
        exit(1);
      if (memcmp(table->entrytable, entrytable, replace.entries_size) == 0)
        continue;
    }
    for (j = 0, h = 0; h < NF_BR_NUMHOOKS; h++) {
      if (table->replace.valid_hooks & (1 << h)) {
        table->replace.hook_entry[h] =
            (struct ebt_entries*)table->entrytable + j;
        j++;
      }
    }
    table->replace.entries = table->entrytable;
    optlen = sizeof(table->replace) + table->replace.entries_size;
    if (setsockopt(fd, SOL_IP, EBT_SO_SET_ENTRIES, &table->replace, optlen))
      exit(1);
  }
  close(fd);
}

static void checkpoint_net_namespace(void)
{
  checkpoint_ebtables();
  checkpoint_arptables();
  checkpoint_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]),
                      AF_INET, SOL_IP);
  checkpoint_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]),
                      AF_INET6, SOL_IPV6);
}

static void reset_net_namespace(void)
{
  reset_ebtables();
  reset_arptables();
  reset_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]),
                 AF_INET, SOL_IP);
  reset_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]),
                 AF_INET6, SOL_IPV6);
}

static void setup_cgroups()
{
  if (mkdir("/syzcgroup", 0777)) {
  }
  if (mkdir("/syzcgroup/unified", 0777)) {
  }
  if (mount("none", "/syzcgroup/unified", "cgroup2", 0, NULL)) {
  }
  if (chmod("/syzcgroup/unified", 0777)) {
  }
  if (!write_file("/syzcgroup/unified/cgroup.subtree_control",
                  "+cpu +memory +io +pids +rdma")) {
  }
  if (mkdir("/syzcgroup/cpu", 0777)) {
  }
  if (mount("none", "/syzcgroup/cpu", "cgroup", 0,
            "cpuset,cpuacct,perf_event,hugetlb")) {
  }
  if (!write_file("/syzcgroup/cpu/cgroup.clone_children", "1")) {
  }
  if (chmod("/syzcgroup/cpu", 0777)) {
  }
  if (mkdir("/syzcgroup/net", 0777)) {
  }
  if (mount("none", "/syzcgroup/net", "cgroup", 0,
            "net_cls,net_prio,devices,freezer")) {
  }
  if (chmod("/syzcgroup/net", 0777)) {
  }
  if (!write_file("/proc/self/oom_score_adj", "-1000")) {
  }
}
static void setup_binfmt_misc()
{
  if (mount(0, "/proc/sys/fs/binfmt_misc", "binfmt_misc", 0, 0)) {
  }
  if (!write_file("/proc/sys/fs/binfmt_misc/register",
                  ":syz0:M:0:\x01::./file0:")) {
  }
  if (!write_file("/proc/sys/fs/binfmt_misc/register",
                  ":syz1:M:1:\x02::./file0:POC")) {
  }
}

static void setup_common()
{
  if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) {
  }
  setup_cgroups();
  setup_binfmt_misc();
}

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 = 160 << 20;
  setrlimit(RLIMIT_AS, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 8 << 20;
  setrlimit(RLIMIT_MEMLOCK, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 136 << 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);
  rlim.rlim_cur = rlim.rlim_max = 256;
  setrlimit(RLIMIT_NOFILE, &rlim);
  if (unshare(CLONE_NEWNS)) {
  }
  if (unshare(CLONE_NEWIPC)) {
  }
  if (unshare(0x02000000)) {
  }
  if (unshare(CLONE_NEWUTS)) {
  }
  if (unshare(CLONE_SYSVSEM)) {
  }
}

int wait_for_loop(int pid)
{
  if (pid < 0)
    exit(1);
  int status = 0;
  while (waitpid(-1, &status, __WALL) != pid) {
  }
  return WEXITSTATUS(status);
}

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))
    exit(1);
  if (!write_file("/proc/self/gid_map", "0 %d 1\n", real_gid))
    exit(1);
  if (unshare(CLONE_NEWNET))
    exit(1);
  initialize_tun();
  initialize_netdevices();
  if (mkdir("./syz-tmp", 0777))
    exit(1);
  if (mount("", "./syz-tmp", "tmpfs", 0, NULL))
    exit(1);
  if (mkdir("./syz-tmp/newroot", 0777))
    exit(1);
  if (mkdir("./syz-tmp/newroot/dev", 0700))
    exit(1);
  unsigned bind_mount_flags = MS_BIND | MS_REC | MS_PRIVATE;
  if (mount("/dev", "./syz-tmp/newroot/dev", NULL, bind_mount_flags, NULL))
    exit(1);
  if (mkdir("./syz-tmp/newroot/proc", 0700))
    exit(1);
  if (mount(NULL, "./syz-tmp/newroot/proc", "proc", 0, NULL))
    exit(1);
  if (mkdir("./syz-tmp/newroot/selinux", 0700))
    exit(1);
  const char* selinux_path = "./syz-tmp/newroot/selinux";
  if (mount("/selinux", selinux_path, NULL, bind_mount_flags, NULL)) {
    if (errno != ENOENT)
      exit(1);
    if (mount("/sys/fs/selinux", selinux_path, NULL, bind_mount_flags, NULL) &&
        errno != ENOENT)
      exit(1);
  }
  if (mkdir("./syz-tmp/newroot/sys", 0700))
    exit(1);
  if (mount("/sys", "./syz-tmp/newroot/sys", 0, bind_mount_flags, NULL))
    exit(1);
  if (mkdir("./syz-tmp/newroot/syzcgroup", 0700))
    exit(1);
  if (mkdir("./syz-tmp/newroot/syzcgroup/unified", 0700))
    exit(1);
  if (mkdir("./syz-tmp/newroot/syzcgroup/cpu", 0700))
    exit(1);
  if (mkdir("./syz-tmp/newroot/syzcgroup/net", 0700))
    exit(1);
  if (mount("/syzcgroup/unified", "./syz-tmp/newroot/syzcgroup/unified", NULL,
            bind_mount_flags, NULL)) {
  }
  if (mount("/syzcgroup/cpu", "./syz-tmp/newroot/syzcgroup/cpu", NULL,
            bind_mount_flags, NULL)) {
  }
  if (mount("/syzcgroup/net", "./syz-tmp/newroot/syzcgroup/net", NULL,
            bind_mount_flags, NULL)) {
  }
  if (mkdir("./syz-tmp/pivot", 0777))
    exit(1);
  if (syscall(SYS_pivot_root, "./syz-tmp", "./syz-tmp/pivot")) {
    if (chdir("./syz-tmp"))
      exit(1);
  } else {
    if (chdir("/"))
      exit(1);
    if (umount2("./pivot", MNT_DETACH))
      exit(1);
  }
  if (chroot("./newroot"))
    exit(1);
  if (chdir("/"))
    exit(1);
  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))
    exit(1);
  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))
    exit(1);
  loop();
  exit(1);
}

#define SYZ_HAVE_SANDBOX_NAMESPACE 1
static int do_sandbox_namespace(void)
{
  int pid;
  setup_common();
  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, 0);
  return wait_for_loop(pid);
}

#define FS_IOC_SETFLAGS _IOW('f', 2, long)
static void remove_dir(const char* dir)
{
  DIR* dp;
  struct dirent* ep;
  int iter = 0;
retry:
  while (umount2(dir, MNT_DETACH) == 0) {
  }
  dp = opendir(dir);
  if (dp == NULL) {
    if (errno == EMFILE) {
      exit(1);
    }
    exit(1);
  }
  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);
    while (umount2(filename, MNT_DETACH) == 0) {
    }
    struct stat st;
    if (lstat(filename, &st))
      exit(1);
    if (S_ISDIR(st.st_mode)) {
      remove_dir(filename);
      continue;
    }
    int i;
    for (i = 0;; i++) {
      if (unlink(filename) == 0)
        break;
      if (errno == EPERM) {
        int fd = open(filename, O_RDONLY);
        if (fd != -1) {
          long flags = 0;
          if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0)
            close(fd);
          continue;
        }
      }
      if (errno == EROFS) {
        break;
      }
      if (errno != EBUSY || i > 100)
        exit(1);
      if (umount2(filename, MNT_DETACH))
        exit(1);
    }
  }
  closedir(dp);
  int i;
  for (i = 0;; i++) {
    if (rmdir(dir) == 0)
      break;
    if (i < 100) {
      if (errno == EPERM) {
        int fd = open(dir, O_RDONLY);
        if (fd != -1) {
          long flags = 0;
          if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0)
            close(fd);
          continue;
        }
      }
      if (errno == EROFS) {
        break;
      }
      if (errno == EBUSY) {
        if (umount2(dir, MNT_DETACH))
          exit(1);
        continue;
      }
      if (errno == ENOTEMPTY) {
        if (iter < 100) {
          iter++;
          goto retry;
        }
      }
    }
    exit(1);
  }
}

static void kill_and_wait(int pid, int* status)
{
  kill(-pid, SIGKILL);
  kill(pid, SIGKILL);
  int i;
  for (i = 0; i < 100; i++) {
    if (waitpid(-1, status, WNOHANG | __WALL) == pid)
      return;
    usleep(1000);
  }
  DIR* dir = opendir("/sys/fs/fuse/connections");
  if (dir) {
    for (;;) {
      struct dirent* ent = readdir(dir);
      if (!ent)
        break;
      if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0)
        continue;
      char abort[300];
      snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort",
               ent->d_name);
      int fd = open(abort, O_WRONLY);
      if (fd == -1) {
        continue;
      }
      if (write(fd, abort, 1) < 0) {
      }
      close(fd);
    }
    closedir(dir);
  } else {
  }
  while (waitpid(-1, status, __WALL) != pid) {
  }
}

#define SYZ_HAVE_SETUP_LOOP 1
static void setup_loop()
{
  int pid = getpid();
  char cgroupdir[64];
  char file[128];
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid);
  if (mkdir(cgroupdir, 0777)) {
  }
  snprintf(file, sizeof(file), "%s/pids.max", cgroupdir);
  if (!write_file(file, "32")) {
  }
  snprintf(file, sizeof(file), "%s/memory.low", cgroupdir);
  if (!write_file(file, "%d", 198 << 20)) {
  }
  snprintf(file, sizeof(file), "%s/memory.high", cgroupdir);
  if (!write_file(file, "%d", 199 << 20)) {
  }
  snprintf(file, sizeof(file), "%s/memory.max", cgroupdir);
  if (!write_file(file, "%d", 200 << 20)) {
  }
  if (!write_file("/proc/self/oom_score_adj", "-1000")) {
  }
  snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
  if (!write_file(file, "%d", pid)) {
  }
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid);
  if (mkdir(cgroupdir, 0777)) {
  }
  snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
  if (!write_file(file, "%d", pid)) {
  }
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid);
  if (mkdir(cgroupdir, 0777)) {
  }
  snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
  if (!write_file(file, "%d", pid)) {
  }
  checkpoint_net_namespace();
}

#define SYZ_HAVE_RESET_LOOP 1
static void reset_loop()
{
  reset_net_namespace();
}

#define SYZ_HAVE_SETUP_TEST 1
static void setup_test()
{
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setpgrp();
  char cgroupdir[64];
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid);
  if (symlink(cgroupdir, "./cgroup")) {
  }
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid);
  if (symlink(cgroupdir, "./cgroup.cpu")) {
  }
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid);
  if (symlink(cgroupdir, "./cgroup.net")) {
  }
  if (!write_file("/proc/self/oom_score_adj", "0")) {
  }
  flush_tun();
}

#define SYZ_HAVE_RESET_TEST 1
static void reset_test()
{
  int fd;
  for (fd = 3; fd < 30; fd++)
    close(fd);
}

static void execute_one(void);

#define WAIT_FLAGS __WALL

static void loop(void)
{
  setup_loop();
  int iter;
  for (iter = 0;; iter++) {
    char cwdbuf[32];
    sprintf(cwdbuf, "./%d", iter);
    if (mkdir(cwdbuf, 0777))
      exit(1);
    reset_loop();
    int pid = fork();
    if (pid < 0)
      exit(1);
    if (pid == 0) {
      if (chdir(cwdbuf))
        exit(1);
      setup_test();
      execute_one();
      reset_test();
      exit(0);
    }
    int status = 0;
    uint64_t start = current_time_ms();
    for (;;) {
      if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
        break;
      sleep_ms(1);
      if (current_time_ms() - start < 5 * 1000)
        continue;
      kill_and_wait(pid, &status);
      break;
    }
    remove_dir(cwdbuf);
  }
}

uint64_t r[2] = {0xffffffffffffffff, 0xffffffffffffffff};

void execute_one(void)
{
  long res = 0;
  NONFAILING(memcpy((void*)0x200000c0, "/dev/loop#", 11));
  res = syz_open_dev(0x200000c0, 0, 0x1100082);
  if (res != -1)
    r[0] = res;
  syscall(__NR_ioctl, r[0], 0x4c01);
  NONFAILING(memcpy((void*)0x20000100, "/dev/loop-control", 18));
  res = syscall(__NR_openat, 0xffffffffffffff9c, 0x20000100, 0, 0);
  if (res != -1)
    r[1] = res;
  syscall(__NR_ioctl, r[1], 0x4c81, 0);
}
int main(void)
{
  syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0);
  install_segv_handler();
  for (procid = 0; procid < 6; procid++) {
    if (fork() == 0) {
      use_temporary_dir();
      do_sandbox_namespace();
    }
  }
  sleep(1000000);
  return 0;
}