// https://syzkaller.appspot.com/bug?id=00aefe8e90e2c50f3e60d56bfec186b79f29865c
// autogenerated by syzkaller (https://github.com/google/syzkaller)

#define _GNU_SOURCE

#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.h>
#include <net/if.h>
#include <netinet/in.h>
#include <pthread.h>
#include <sched.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/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/wait.h>
#include <time.h>
#include <unistd.h>

#include <linux/capability.h>
#include <linux/futex.h>
#include <linux/net.h>

static unsigned long long procid;

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 thread_start(void* (*fn)(void*), void* arg)
{
  pthread_t th;
  pthread_attr_t attr;
  pthread_attr_init(&attr);
  pthread_attr_setstacksize(&attr, 128 << 10);
  int i = 0;
  for (; i < 100; i++) {
    if (pthread_create(&th, &attr, fn, arg) == 0) {
      pthread_attr_destroy(&attr);
      return;
    }
    if (errno == EAGAIN) {
      usleep(50);
      continue;
    }
    break;
  }
  exit(1);
}

typedef struct {
  int state;
} event_t;

static void event_init(event_t* ev)
{
  ev->state = 0;
}

static void event_reset(event_t* ev)
{
  ev->state = 0;
}

static void event_set(event_t* ev)
{
  if (ev->state)
    exit(1);
  __atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE);
  syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG, 1000000);
}

static void event_wait(event_t* ev)
{
  while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
    syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0);
}

static int event_isset(event_t* ev)
{
  return __atomic_load_n(&ev->state, __ATOMIC_ACQUIRE);
}

static int event_timedwait(event_t* ev, uint64_t timeout)
{
  uint64_t start = current_time_ms();
  uint64_t now = start;
  for (;;) {
    uint64_t remain = timeout - (now - start);
    struct timespec ts;
    ts.tv_sec = remain / 1000;
    ts.tv_nsec = (remain % 1000) * 1000 * 1000;
    syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, &ts);
    if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
      return 1;
    now = current_time_ms();
    if (now - start > timeout)
      return 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 MAX_FDS 30

#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;
  uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)];
};

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;
  uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)];
};

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;
  uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)];
};

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;
  uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)];
};

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)
{
  int fd = socket(family, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
    case ENOENT:
      return;
    }
    exit(1);
  }
  for (int 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);
    socklen_t 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);
    struct ipt_get_entries entries;
    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)
{
  int fd = socket(family, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
    case ENOENT:
      return;
    }
    exit(1);
  }
  for (int i = 0; i < num_tables; i++) {
    struct ipt_table_desc* table = &tables[i];
    if (table->info.valid_hooks == 0)
      continue;
    struct ipt_getinfo info;
    memset(&info, 0, sizeof(info));
    strcpy(info.name, table->name);
    socklen_t optlen = sizeof(info);
    if (getsockopt(fd, level, IPT_SO_GET_INFO, &info, &optlen))
      exit(1);
    if (memcmp(&table->info, &info, sizeof(table->info)) == 0) {
      struct ipt_get_entries entries;
      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;
    }
    struct xt_counters counters[XT_MAX_ENTRIES];
    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)
{
  int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
    case ENOENT:
      return;
    }
    exit(1);
  }
  for (unsigned 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);
    socklen_t 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);
    struct arpt_get_entries entries;
    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()
{
  int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
    case ENOENT:
      return;
    }
    exit(1);
  }
  for (unsigned 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;
    struct arpt_getinfo info;
    memset(&info, 0, sizeof(info));
    strcpy(info.name, table->name);
    socklen_t 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) {
      struct arpt_get_entries entries;
      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 {
    }
    struct xt_counters counters[XT_MAX_ENTRIES];
    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);
}

#define NF_BR_NUMHOOKS 6
#define EBT_TABLE_MAXNAMELEN 32
#define EBT_CHAIN_MAXNAMELEN 32
#define EBT_BASE_CTL 128
#define EBT_SO_SET_ENTRIES (EBT_BASE_CTL)
#define EBT_SO_GET_INFO (EBT_BASE_CTL)
#define EBT_SO_GET_ENTRIES (EBT_SO_GET_INFO + 1)
#define EBT_SO_GET_INIT_INFO (EBT_SO_GET_ENTRIES + 1)
#define EBT_SO_GET_INIT_ENTRIES (EBT_SO_GET_INIT_INFO + 1)

struct ebt_replace {
  char name[EBT_TABLE_MAXNAMELEN];
  unsigned int valid_hooks;
  unsigned int nentries;
  unsigned int entries_size;
  struct ebt_entries* hook_entry[NF_BR_NUMHOOKS];
  unsigned int num_counters;
  struct ebt_counter* counters;
  char* entries;
};

struct ebt_entries {
  unsigned int distinguisher;
  char name[EBT_CHAIN_MAXNAMELEN];
  unsigned int counter_offset;
  int policy;
  unsigned int nentries;
  char data[0] __attribute__((aligned(__alignof__(struct ebt_replace))));
};

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)
{
  int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
    case ENOENT:
      return;
    }
    exit(1);
  }
  for (size_t 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);
    socklen_t 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()
{
  int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
  if (fd == -1) {
    switch (errno) {
    case EAFNOSUPPORT:
    case ENOPROTOOPT:
    case ENOENT:
      return;
    }
    exit(1);
  }
  for (unsigned 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;
    struct ebt_replace replace;
    memset(&replace, 0, sizeof(replace));
    strcpy(replace.name, table->name);
    socklen_t 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 (unsigned h = 0; h < NF_BR_NUMHOOKS; h++)
      table->replace.hook_entry[h] = 0;
    if (memcmp(&table->replace, &replace, sizeof(table->replace)) == 0) {
      char entrytable[XT_TABLE_SIZE];
      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 (unsigned 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 mount_cgroups(const char* dir, const char** controllers, int count)
{
  if (mkdir(dir, 0777)) {
    return;
  }
  char enabled[128] = {0};
  int i = 0;
  for (; i < count; i++) {
    if (mount("none", dir, "cgroup", 0, controllers[i])) {
      continue;
    }
    umount(dir);
    strcat(enabled, ",");
    strcat(enabled, controllers[i]);
  }
  if (enabled[0] == 0) {
    if (rmdir(dir) && errno != EBUSY)
      exit(1);
    return;
  }
  if (mount("none", dir, "cgroup", 0, enabled + 1)) {
    if (rmdir(dir) && errno != EBUSY)
      exit(1);
  }
  if (chmod(dir, 0777)) {
  }
}

static void mount_cgroups2(const char** controllers, int count)
{
  if (mkdir("/syzcgroup/unified", 0777)) {
    return;
  }
  if (mount("none", "/syzcgroup/unified", "cgroup2", 0, NULL)) {
    if (rmdir("/syzcgroup/unified") && errno != EBUSY)
      exit(1);
    return;
  }
  if (chmod("/syzcgroup/unified", 0777)) {
  }
  int control = open("/syzcgroup/unified/cgroup.subtree_control", O_WRONLY);
  if (control == -1)
    return;
  int i;
  for (i = 0; i < count; i++)
    if (write(control, controllers[i], strlen(controllers[i])) < 0) {
    }
  close(control);
}

static void setup_cgroups()
{
  const char* unified_controllers[] = {"+cpu", "+io", "+pids"};
  const char* net_controllers[] = {"net", "net_prio", "devices", "blkio",
                                   "freezer"};
  const char* cpu_controllers[] = {"cpuset", "cpuacct", "hugetlb", "rlimit",
                                   "memory"};
  if (mkdir("/syzcgroup", 0777)) {
    return;
  }
  mount_cgroups2(unified_controllers,
                 sizeof(unified_controllers) / sizeof(unified_controllers[0]));
  mount_cgroups("/syzcgroup/net", net_controllers,
                sizeof(net_controllers) / sizeof(net_controllers[0]));
  mount_cgroups("/syzcgroup/cpu", cpu_controllers,
                sizeof(cpu_controllers) / sizeof(cpu_controllers[0]));
  write_file("/syzcgroup/cpu/cgroup.clone_children", "1");
  write_file("/syzcgroup/cpu/cpuset.memory_pressure_enabled", "1");
}

static void setup_cgroups_loop()
{
  int pid = getpid();
  char file[128];
  char cgroupdir[64];
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid);
  if (mkdir(cgroupdir, 0777)) {
  }
  snprintf(file, sizeof(file), "%s/pids.max", cgroupdir);
  write_file(file, "32");
  snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
  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);
  write_file(file, "%d", pid);
  snprintf(file, sizeof(file), "%s/memory.soft_limit_in_bytes", cgroupdir);
  write_file(file, "%d", 299 << 20);
  snprintf(file, sizeof(file), "%s/memory.limit_in_bytes", cgroupdir);
  write_file(file, "%d", 300 << 20);
  snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid);
  if (mkdir(cgroupdir, 0777)) {
  }
  snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
  write_file(file, "%d", pid);
}

static void setup_cgroups_test()
{
  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")) {
  }
}

static void initialize_cgroups()
{
  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);
  unsigned bind_mount_flags = MS_BIND | MS_REC | MS_PRIVATE;
  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)) {
  }
}

static void setup_binderfs();
static void setup_fusectl();
static void sandbox_common_mount_tmpfs(void)
{
  write_file("/proc/sys/fs/mount-max", "100000");
  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("syz-proc", "./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 (mount("/sys/kernel/debug", "./syz-tmp/newroot/sys/kernel/debug", NULL,
            bind_mount_flags, NULL) &&
      errno != ENOENT)
    exit(1);
  if (mount("/sys/fs/smackfs", "./syz-tmp/newroot/sys/fs/smackfs", NULL,
            bind_mount_flags, NULL) &&
      errno != ENOENT)
    exit(1);
  if (mount("/proc/sys/fs/binfmt_misc",
            "./syz-tmp/newroot/proc/sys/fs/binfmt_misc", NULL, bind_mount_flags,
            NULL) &&
      errno != ENOENT)
    exit(1);
  initialize_cgroups();
  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);
  setup_binderfs();
  setup_fusectl();
}

static void setup_fusectl()
{
  if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) {
  }
}

static void setup_binderfs()
{
  if (mkdir("/dev/binderfs", 0777)) {
  }
  if (mount("binder", "/dev/binderfs", "binder", 0, NULL)) {
  }
}

static void loop();

static void sandbox_common()
{
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setsid();
  struct rlimit rlim;
  rlim.rlim_cur = rlim.rlim_max = (200 << 20);
  setrlimit(RLIMIT_AS, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 32 << 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 = 128 << 20;
  setrlimit(RLIMIT_CORE, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 256;
  setrlimit(RLIMIT_NOFILE, &rlim);
  if (unshare(CLONE_NEWNS)) {
  }
  if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
  }
  if (unshare(CLONE_NEWIPC)) {
  }
  if (unshare(0x02000000)) {
  }
  if (unshare(CLONE_NEWUTS)) {
  }
  if (unshare(CLONE_SYSVSEM)) {
  }
  typedef struct {
    const char* name;
    const char* value;
  } sysctl_t;
  static const sysctl_t sysctls[] = {
      {"/proc/sys/kernel/shmmax", "16777216"},
      {"/proc/sys/kernel/shmall", "536870912"},
      {"/proc/sys/kernel/shmmni", "1024"},
      {"/proc/sys/kernel/msgmax", "8192"},
      {"/proc/sys/kernel/msgmni", "1024"},
      {"/proc/sys/kernel/msgmnb", "1024"},
      {"/proc/sys/kernel/sem", "1024 1048576 500 1024"},
  };
  unsigned i;
  for (i = 0; i < sizeof(sysctls) / sizeof(sysctls[0]); i++)
    write_file(sysctls[i].name, sysctls[i].value);
}

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

static void drop_caps(void)
{
  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);
  const int drop = (1 << CAP_SYS_PTRACE) | (1 << CAP_SYS_NICE);
  cap_data[0].effective &= ~drop;
  cap_data[0].permitted &= ~drop;
  cap_data[0].inheritable &= ~drop;
  if (syscall(SYS_capset, &cap_hdr, &cap_data))
    exit(1);
}

static int do_sandbox_none(void)
{
  if (unshare(CLONE_NEWPID)) {
  }
  int pid = fork();
  if (pid != 0)
    return wait_for_loop(pid);
  sandbox_common();
  drop_caps();
  if (unshare(CLONE_NEWNET)) {
  }
  write_file("/proc/sys/net/ipv4/ping_group_range", "0 65535");
  sandbox_common_mount_tmpfs();
  loop();
  exit(1);
}

#define FS_IOC_SETFLAGS _IOW('f', 2, long)
static void remove_dir(const char* dir)
{
  int iter = 0;
  DIR* dp = 0;
  const int umount_flags = MNT_FORCE | UMOUNT_NOFOLLOW;

retry:
  while (umount2(dir, umount_flags) == 0) {
  }
  dp = opendir(dir);
  if (dp == NULL) {
    if (errno == EMFILE) {
      exit(1);
    }
    exit(1);
  }
  struct dirent* ep = 0;
  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, umount_flags) == 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, umount_flags))
        exit(1);
    }
  }
  closedir(dp);
  for (int 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, umount_flags))
          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);
  for (int 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) {
  }
}

static void setup_loop()
{
  setup_cgroups_loop();
  checkpoint_net_namespace();
}

static void reset_loop()
{
  reset_net_namespace();
}

static void setup_test()
{
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setpgrp();
  setup_cgroups_test();
  write_file("/proc/self/oom_score_adj", "1000");
  if (symlink("/dev/binderfs", "./binderfs")) {
  }
}

static void close_fds()
{
  for (int fd = 3; fd < MAX_FDS; fd++)
    close(fd);
}

static const char* setup_binfmt_misc()
{
  if (mount(0, "/proc/sys/fs/binfmt_misc", "binfmt_misc", 0, 0) &&
      errno != EBUSY) {
    return NULL;
  }
  if (!write_file("/proc/sys/fs/binfmt_misc/register",
                  ":syz0:M:0:\x01::./file0:") ||
      !write_file("/proc/sys/fs/binfmt_misc/register",
                  ":syz1:M:1:\x02::./file0:POC"))
    return "write(/proc/sys/fs/binfmt_misc/register) failed";
  return NULL;
}

static void setup_sysctl()
{
  int cad_pid = fork();
  if (cad_pid < 0)
    exit(1);
  if (cad_pid == 0) {
    for (;;)
      sleep(100);
  }
  char tmppid[32];
  snprintf(tmppid, sizeof(tmppid), "%d", cad_pid);
  struct {
    const char* name;
    const char* data;
  } files[] = {
      {"/sys/kernel/debug/x86/nmi_longest_ns", "10000000000"},
      {"/proc/sys/kernel/hung_task_check_interval_secs", "20"},
      {"/proc/sys/net/core/bpf_jit_kallsyms", "1"},
      {"/proc/sys/net/core/bpf_jit_harden", "0"},
      {"/proc/sys/kernel/kptr_restrict", "0"},
      {"/proc/sys/kernel/softlockup_all_cpu_backtrace", "1"},
      {"/proc/sys/fs/mount-max", "100"},
      {"/proc/sys/vm/oom_dump_tasks", "0"},
      {"/proc/sys/debug/exception-trace", "0"},
      {"/proc/sys/kernel/printk", "7 4 1 3"},
      {"/proc/sys/kernel/keys/gc_delay", "1"},
      {"/proc/sys/vm/oom_kill_allocating_task", "1"},
      {"/proc/sys/kernel/ctrl-alt-del", "0"},
      {"/proc/sys/kernel/cad_pid", tmppid},
  };
  for (size_t i = 0; i < sizeof(files) / sizeof(files[0]); i++) {
    if (!write_file(files[i].name, files[i].data)) {
    }
  }
  kill(cad_pid, SIGKILL);
  while (waitpid(cad_pid, NULL, 0) != cad_pid)
    ;
}

struct thread_t {
  int created, call;
  event_t ready, done;
};

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

static void* thr(void* arg)
{
  struct thread_t* th = (struct thread_t*)arg;
  for (;;) {
    event_wait(&th->ready);
    event_reset(&th->ready);
    execute_call(th->call);
    __atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED);
    event_set(&th->done);
  }
  return 0;
}

static void execute_one(void)
{
  if (write(1, "executing program\n", sizeof("executing program\n") - 1)) {
  }
  int i, call, thread;
  for (call = 0; call < 5; call++) {
    for (thread = 0; thread < (int)(sizeof(threads) / sizeof(threads[0]));
         thread++) {
      struct thread_t* th = &threads[thread];
      if (!th->created) {
        th->created = 1;
        event_init(&th->ready);
        event_init(&th->done);
        event_set(&th->done);
        thread_start(thr, th);
      }
      if (!event_isset(&th->done))
        continue;
      event_reset(&th->done);
      th->call = call;
      __atomic_fetch_add(&running, 1, __ATOMIC_RELAXED);
      event_set(&th->ready);
      if (call == 2)
        break;
      event_timedwait(&th->done, 50);
      break;
    }
  }
  for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++)
    sleep_ms(1);
  close_fds();
}

static void execute_one(void);

#define WAIT_FLAGS __WALL

static void loop(void)
{
  setup_loop();
  int iter = 0;
  for (;; 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();
      exit(0);
    }
    int status = 0;
    uint64_t start = current_time_ms();
    for (;;) {
      sleep_ms(10);
      if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
        break;
      if (current_time_ms() - start < 5000)
        continue;
      kill_and_wait(pid, &status);
      break;
    }
    remove_dir(cwdbuf);
  }
}

void execute_call(int call)
{
  switch (call) {
  case 0:
    syscall(__NR_mmap, /*addr=*/0ul, /*len=*/0x20009ul, /*prot=*/0xdful,
            /*flags=*/0xeb1ul, /*fd=*/0x401ul, /*off=*/0x8000ul);
    break;
  case 1:
    syscall(__NR_remap_file_pages, /*start=*/0x6a27ul, /*size=*/0x1000ul,
            /*prot=*/0ul, /*pgoff=*/3ul, /*flags=*/4ul);
    break;
  case 2:
    syscall(__NR_mmap, /*addr=*/0ul, /*len=*/8ul, /*prot=*/0xdful,
            /*flags=*/0x9b72ul, /*fd=*/2ul, /*off=*/0x8000ul);
    break;
  case 3:
    memcpy((void*)0x20000080, "./file0\000", 8);
    syscall(__NR_open, /*file=*/0x20000080ul,
            /*flags=O_TRUNC|O_NONBLOCK|O_NOCTTY|O_EXCL|O_CREAT|O_APPEND|0x103d*/
            0x1ffdul, /*mode=S_IWOTH|S_IWGRP*/ 0x12ul);
    break;
  case 4:
    syscall(__NR_write, /*fd=*/3, /*buf=*/0ul, /*count=*/0x100082ul);
    break;
  }
}
int main(void)
{
  syscall(__NR_mmap, /*addr=*/0x1ffff000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0x1000000ul,
          /*prot=PROT_WRITE|PROT_READ|PROT_EXEC*/ 7ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x21000000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  setup_sysctl();
  setup_cgroups();
  const char* reason;
  (void)reason;
  if ((reason = setup_binfmt_misc()))
    printf("the reproducer may not work as expected: binfmt_misc setup failed: "
           "%s\n",
           reason);
  use_temporary_dir();
  do_sandbox_none();
  return 0;
}