// https://syzkaller.appspot.com/bug?id=ec4a839a1052b68d8b1504d9e4e5d04fa2a714db
// 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>

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 __NR_io_uring_setup 425
static long syz_io_uring_setup(volatile long a0, volatile long a1,
                               volatile long a2, volatile long a3,
                               volatile long a4, volatile long a5)
{
  uint32_t entries = (uint32_t)a0;
  struct io_uring_params* setup_params = (struct io_uring_params*)a1;
  void* vma1 = (void*)a2;
  void* vma2 = (void*)a3;
  void** ring_ptr_out = (void**)a4;
  void** sqes_ptr_out = (void**)a5;
  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(vma1, ring_sz, PROT_READ | PROT_WRITE,
                       MAP_SHARED | MAP_POPULATE | MAP_FIXED, fd_io_uring,
                       IORING_OFF_SQ_RING);
  uint32_t sqes_sz = setup_params->sq_entries * SIZEOF_IO_URING_SQE;
  *sqes_ptr_out =
      mmap(vma2, sqes_sz, PROT_READ | PROT_WRITE,
           MAP_SHARED | MAP_POPULATE | MAP_FIXED, fd_io_uring, IORING_OFF_SQES);
  return fd_io_uring;
}

static long syz_io_uring_submit(volatile long a0, volatile long a1,
                                volatile long a2, volatile long a3)
{
  char* ring_ptr = (char*)a0;
  char* sqes_ptr = (char*)a1;
  char* sqe = (char*)a2;
  uint32_t sqes_index = (uint32_t)a3;
  uint32_t sq_ring_entries = *(uint32_t*)(ring_ptr + SQ_RING_ENTRIES_OFFSET);
  uint32_t cq_ring_entries = *(uint32_t*)(ring_ptr + CQ_RING_ENTRIES_OFFSET);
  uint32_t sq_array_off =
      (CQ_CQES_OFFSET + cq_ring_entries * SIZEOF_IO_URING_CQE + 63) & ~63;
  if (sq_ring_entries)
    sqes_index %= sq_ring_entries;
  char* sqe_dest = sqes_ptr + sqes_index * SIZEOF_IO_URING_SQE;
  memcpy(sqe_dest, sqe, SIZEOF_IO_URING_SQE);
  uint32_t sq_ring_mask = *(uint32_t*)(ring_ptr + SQ_RING_MASK_OFFSET);
  uint32_t* sq_tail_ptr = (uint32_t*)(ring_ptr + SQ_TAIL_OFFSET);
  uint32_t sq_tail = *sq_tail_ptr & sq_ring_mask;
  uint32_t sq_tail_next = *sq_tail_ptr + 1;
  uint32_t* sq_array = (uint32_t*)(ring_ptr + sq_array_off);
  *(sq_array + sq_tail) = sqes_index;
  __atomic_store_n(sq_tail_ptr, sq_tail_next, __ATOMIC_RELEASE);
  return 0;
}

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)
{
  int i, call, thread;
  for (call = 0; call < 11; 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, 45);
      break;
    }
  }
  for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++)
    sleep_ms(1);
}

#ifndef __NR_io_uring_enter
#define __NR_io_uring_enter 426
#endif

uint64_t r[8] = {0xffffffffffffffff,
                 0xffffffffffffffff,
                 0xffffffffffffffff,
                 0xffffffffffffffff,
                 0xffffffffffffffff,
                 0xffffffffffffffff,
                 0x0,
                 0x0};

void execute_call(int call)
{
  intptr_t res = 0;
  switch (call) {
  case 0:
    res = syscall(__NR_pipe, 0x20000480ul);
    if (res != -1) {
      r[0] = *(uint32_t*)0x20000480;
      r[1] = *(uint32_t*)0x20000484;
    }
    break;
  case 1:
    res = syscall(__NR_socket, 2ul, 2ul, 0);
    if (res != -1)
      r[2] = res;
    break;
  case 2:
    syscall(__NR_close, r[2]);
    break;
  case 3:
    syscall(__NR_socket, 0x10ul, 3ul, 0xc);
    break;
  case 4:
    res = syscall(__NR_epoll_create1, 0ul);
    if (res != -1)
      r[3] = res;
    break;
  case 5:
    res = syscall(__NR_fcntl, r[3], 2ul, -1);
    if (res != -1)
      r[4] = res;
    break;
  case 6:
    *(uint32_t*)0x20000144 = 0;
    *(uint32_t*)0x20000148 = 0;
    *(uint32_t*)0x2000014c = 0;
    *(uint32_t*)0x20000150 = 0;
    *(uint32_t*)0x20000158 = r[4];
    *(uint32_t*)0x2000015c = 0;
    *(uint32_t*)0x20000160 = 0;
    *(uint32_t*)0x20000164 = 0;
    res = -1;
    res = syz_io_uring_setup(0x76d1, 0x20000140, 0x20ffc000, 0x20fff000,
                             0x20000000, 0x20000100);
    if (res != -1) {
      r[5] = res;
      r[6] = *(uint64_t*)0x20000000;
      r[7] = *(uint64_t*)0x20000100;
    }
    break;
  case 7:
    *(uint8_t*)0x200000c0 = 6;
    *(uint8_t*)0x200000c1 = 0;
    *(uint16_t*)0x200000c2 = 0;
    *(uint32_t*)0x200000c4 = 3;
    *(uint64_t*)0x200000c8 = 0;
    *(uint64_t*)0x200000d0 = 0;
    *(uint32_t*)0x200000d8 = 0;
    *(uint16_t*)0x200000dc = 0;
    *(uint16_t*)0x200000de = 0;
    *(uint64_t*)0x200000e0 = 0;
    *(uint16_t*)0x200000e8 = 0;
    *(uint16_t*)0x200000ea = 0;
    *(uint8_t*)0x200000ec = 0;
    *(uint8_t*)0x200000ed = 0;
    *(uint8_t*)0x200000ee = 0;
    *(uint8_t*)0x200000ef = 0;
    *(uint8_t*)0x200000f0 = 0;
    *(uint8_t*)0x200000f1 = 0;
    *(uint8_t*)0x200000f2 = 0;
    *(uint8_t*)0x200000f3 = 0;
    *(uint8_t*)0x200000f4 = 0;
    *(uint8_t*)0x200000f5 = 0;
    *(uint8_t*)0x200000f6 = 0;
    *(uint8_t*)0x200000f7 = 0;
    *(uint8_t*)0x200000f8 = 0;
    *(uint8_t*)0x200000f9 = 0;
    *(uint8_t*)0x200000fa = 0;
    *(uint8_t*)0x200000fb = 0;
    *(uint8_t*)0x200000fc = 0;
    *(uint8_t*)0x200000fd = 0;
    *(uint8_t*)0x200000fe = 0;
    *(uint8_t*)0x200000ff = 0;
    syz_io_uring_submit(r[6], r[7], 0x200000c0, 0);
    break;
  case 8:
    syscall(__NR_io_uring_enter, r[5], 1, 0, 0ul, 0ul, 0x100000000000000ul);
    break;
  case 9:
    syscall(__NR_write, r[1], 0x20000000ul, 0xfffffeccul);
    break;
  case 10:
    syscall(__NR_splice, r[0], 0ul, r[2], 0ul, 0x4ffe0ul, 0ul);
    break;
  }
}
int main(void)
{
  syscall(__NR_mmap, 0x1ffff000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul);
  syscall(__NR_mmap, 0x20000000ul, 0x1000000ul, 7ul, 0x32ul, -1, 0ul);
  syscall(__NR_mmap, 0x21000000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul);
  loop();
  return 0;
}