// https://syzkaller.appspot.com/bug?id=a49e7e08ec7a7085519264dc34c249be65d0a17a
// autogenerated by syzkaller (https://github.com/google/syzkaller)

#define _GNU_SOURCE

#include <endian.h>
#include <errno.h>
#include <pthread.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <time.h>
#include <unistd.h>

#include <linux/futex.h>

#ifndef __NR_io_uring_setup
#define __NR_io_uring_setup 425
#endif
#ifndef __NR_userfaultfd
#define __NR_userfaultfd 323
#endif

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 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;
  }
}

#define SIZEOF_IO_URING_SQE 64
#define SIZEOF_IO_URING_CQE 16
#define SQ_HEAD_OFFSET 0
#define SQ_TAIL_OFFSET 64
#define SQ_RING_MASK_OFFSET 256
#define SQ_RING_ENTRIES_OFFSET 264
#define SQ_FLAGS_OFFSET 276
#define SQ_DROPPED_OFFSET 272
#define CQ_HEAD_OFFSET 128
#define CQ_TAIL_OFFSET 192
#define CQ_RING_MASK_OFFSET 260
#define CQ_RING_ENTRIES_OFFSET 268
#define CQ_RING_OVERFLOW_OFFSET 284
#define CQ_FLAGS_OFFSET 280
#define CQ_CQES_OFFSET 320

struct io_sqring_offsets {
  uint32_t head;
  uint32_t tail;
  uint32_t ring_mask;
  uint32_t ring_entries;
  uint32_t flags;
  uint32_t dropped;
  uint32_t array;
  uint32_t resv1;
  uint64_t resv2;
};

struct io_cqring_offsets {
  uint32_t head;
  uint32_t tail;
  uint32_t ring_mask;
  uint32_t ring_entries;
  uint32_t overflow;
  uint32_t cqes;
  uint64_t resv[2];
};

struct io_uring_params {
  uint32_t sq_entries;
  uint32_t cq_entries;
  uint32_t flags;
  uint32_t sq_thread_cpu;
  uint32_t sq_thread_idle;
  uint32_t features;
  uint32_t resv[4];
  struct io_sqring_offsets sq_off;
  struct io_cqring_offsets cq_off;
};

#define IORING_OFF_SQ_RING 0
#define IORING_OFF_SQES 0x10000000ULL
#define IORING_SETUP_SQE128 (1U << 10)
#define IORING_SETUP_CQE32 (1U << 11)

static long syz_io_uring_setup(volatile long a0, volatile long a1,
                               volatile long a2, volatile long a3)
{
  uint32_t entries = (uint32_t)a0;
  struct io_uring_params* setup_params = (struct io_uring_params*)a1;
  void** ring_ptr_out = (void**)a2;
  void** sqes_ptr_out = (void**)a3;
  setup_params->flags &= ~(IORING_SETUP_CQE32 | IORING_SETUP_SQE128);
  uint32_t fd_io_uring = syscall(__NR_io_uring_setup, entries, setup_params);
  uint32_t sq_ring_sz =
      setup_params->sq_off.array + setup_params->sq_entries * sizeof(uint32_t);
  uint32_t cq_ring_sz = setup_params->cq_off.cqes +
                        setup_params->cq_entries * SIZEOF_IO_URING_CQE;
  uint32_t ring_sz = sq_ring_sz > cq_ring_sz ? sq_ring_sz : cq_ring_sz;
  *ring_ptr_out =
      mmap(0, ring_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
           fd_io_uring, IORING_OFF_SQ_RING);
  uint32_t sqes_sz = setup_params->sq_entries * SIZEOF_IO_URING_SQE;
  *sqes_ptr_out = mmap(0, sqes_sz, PROT_READ | PROT_WRITE,
                       MAP_SHARED | MAP_POPULATE, fd_io_uring, IORING_OFF_SQES);
  uint32_t* array =
      (uint32_t*)((uintptr_t)*ring_ptr_out + setup_params->sq_off.array);
  for (uint32_t index = 0; index < entries; index++)
    array[index] = index;
  return fd_io_uring;
}

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 loop(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);
      event_timedwait(&th->done, 50);
      break;
    }
  }
  for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++)
    sleep_ms(1);
}

uint64_t r[1] = {0xffffffffffffffff};

void execute_call(int call)
{
  intptr_t res = 0;
  switch (call) {
  case 0:
    res = syscall(__NR_userfaultfd,
                  /*flags=UFFD_USER_MODE_ONLY|O_CLOEXEC*/ 0x80001ul);
    if (res != -1)
      r[0] = res;
    break;
  case 1:
    *(uint64_t*)0x20000140 = 0xaa;
    *(uint64_t*)0x20000148 = 0;
    *(uint64_t*)0x20000150 = 0;
    syscall(__NR_ioctl, /*fd=*/r[0], /*cmd=*/0xc018aa3f, /*arg=*/0x20000140ul);
    break;
  case 2:
    *(uint64_t*)0x20000080 = 0x200e2000;
    *(uint64_t*)0x20000088 = 0xc00000;
    *(uint64_t*)0x20000090 = 3;
    *(uint64_t*)0x20000098 = 0;
    syscall(__NR_ioctl, /*fd=*/r[0], /*cmd=*/0xc020aa00, /*arg=*/0x20000080ul);
    break;
  case 3:
    *(uint32_t*)0x20000004 = 0;
    *(uint32_t*)0x20000008 = 0;
    *(uint32_t*)0x2000000c = 0;
    *(uint32_t*)0x20000010 = 0;
    *(uint32_t*)0x20000018 = -1;
    memset((void*)0x2000001c, 0, 12);
    syz_io_uring_setup(/*entries=*/0, /*params=*/0x20000000,
                       /*ring_ptr=*/0x20c57000, /*sqes_ptr=*/0);
    break;
  case 4:
    syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0xff5000ul,
            /*prot=PROT_SEM|PROT_WRITE*/ 0xaul,
            /*flags=MAP_POPULATE|MAP_NORESERVE|MAP_HUGETLB|MAP_FIXED|0x821*/
            0x4c831ul, /*fd=*/-1, /*offset=*/0ul);
    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);
  const char* reason;
  (void)reason;
  loop();
  return 0;
}