Re: [syzbot] [bpf?] [trace?] possible deadlock in dev_watchdog

[xingwei lee]

hello
I reproduced this bug with repro.c and repro.txt

=* repro.txt =*
r0 = syz_clone(0x0, 0x0, 0x0, 0x0, 0x0, 0x0)
ptrace(0x10, r0)
r1 = bpf$BPF_PROG_RAW_TRACEPOINT_LOAD(0x5, &(0x7f0000000200)={0x18,
0x4, &(0x7f00000002c0)=ANY=[@ANYBLOB="180100001c00000000000000120000f1850000006d00000095"],
&(0x7f0000000000)='GPL\x00', 0x0, 0x0, 0x0, 0x0, 0x0, '\x00', 0x0,
0x2}, 0x80)
bpf$BPF_RAW_TRACEPOINT_OPEN(0x11,
&(0x7f0000000200)={&(0x7f0000000340)='kfree\x00', r1}, 0x10)

=* repro.c =*
// autogenerated by syzkaller (https://github.com/google/syzkaller)

#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.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/prctl.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>

#ifndef __NR_bpf
#define __NR_bpf 321
#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 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;
}

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_test() {
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setpgrp();
  write_file("/proc/self/oom_score_adj", "1000");
}

#define USLEEP_FORKED_CHILD (3 * 50 * 1000)

static long handle_clone_ret(long ret) {
  if (ret != 0) {
    return ret;
  }
  usleep(USLEEP_FORKED_CHILD);
  syscall(__NR_exit, 0);
  while (1) {
  }
}

static long syz_clone(volatile long flags, volatile long stack,
                      volatile long stack_len, volatile long ptid,
                      volatile long ctid, volatile long tls) {
  long sp = (stack + stack_len) & ~15;
  long ret = (long)syscall(__NR_clone, flags & ~CLONE_VM, sp, ptid, ctid, tls);
  return handle_clone_ret(ret);
}

static void execute_one(void);

#define WAIT_FLAGS __WALL

static void loop(void) {
  int iter = 0;
  for (;; iter++) {
    int pid = fork();
    if (pid < 0) exit(1);
    if (pid == 0) {
      setup_test();
      execute_one();
      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 < 5000) continue;
      kill_and_wait(pid, &status);
      break;
    }
  }
}

uint64_t r[2] = {0x0, 0xffffffffffffffff};

void execute_one(void) {
  intptr_t res = 0;
  res = -1;
  res = syz_clone(/*flags=*/0, /*stack=*/0, /*stack_len=*/0, /*parentid=*/0,
                  /*childtid=*/0, /*tls=*/0);
  if (res != -1) r[0] = res;
  syscall(__NR_ptrace, /*req=*/0x10ul, /*pid=*/r[0], 0, 0);
  *(uint32_t*)0x20000200 = 0x18;
  *(uint32_t*)0x20000204 = 4;
  *(uint64_t*)0x20000208 = 0x200002c0;
  memcpy((void*)0x200002c0,
         "\x18\x01\x00\x00\x1c\x00\x00\x00\x00\x00\x00\x00\x12\x00\x00\xf1\x85"
         "\x00\x00\x00\x6d\x00\x00\x00\x95",
         25);
  *(uint64_t*)0x20000210 = 0x20000000;
  memcpy((void*)0x20000000, "GPL\000", 4);
  *(uint32_t*)0x20000218 = 0;
  *(uint32_t*)0x2000021c = 0;
  *(uint64_t*)0x20000220 = 0;
  *(uint32_t*)0x20000228 = 0;
  *(uint32_t*)0x2000022c = 0;
  memset((void*)0x20000230, 0, 16);
  *(uint32_t*)0x20000240 = 0;
  *(uint32_t*)0x20000244 = 2;
  *(uint32_t*)0x20000248 = -1;
  *(uint32_t*)0x2000024c = 8;
  *(uint64_t*)0x20000250 = 0;
  *(uint32_t*)0x20000258 = 0;
  *(uint32_t*)0x2000025c = 0x10;
  *(uint64_t*)0x20000260 = 0;
  *(uint32_t*)0x20000268 = 0;
  *(uint32_t*)0x2000026c = 0;
  *(uint32_t*)0x20000270 = 0;
  *(uint32_t*)0x20000274 = 0;
  *(uint64_t*)0x20000278 = 0;
  *(uint64_t*)0x20000280 = 0;
  *(uint32_t*)0x20000288 = 0x10;
  *(uint32_t*)0x2000028c = 0;
  res = syscall(__NR_bpf, /*cmd=*/5ul, /*arg=*/0x20000200ul, /*size=*/0x80ul);
  if (res != -1) r[1] = res;
  *(uint64_t*)0x20000200 = 0x20000340;
  memcpy((void*)0x20000340, "kfree\000", 6);
  *(uint32_t*)0x20000208 = r[1];
  syscall(__NR_bpf, /*cmd=*/0x11ul, /*arg=*/0x20000200ul, /*size=*/0x10ul);
}
int main(void) {
  syscall(__NR_mmap, /*addr=*/0x1ffff000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=*/0x32ul, /*fd=*/-1, /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0x1000000ul, /*prot=*/7ul,
          /*flags=*/0x32ul, /*fd=*/-1, /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x21000000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=*/0x32ul, /*fd=*/-1, /*offset=*/0ul);
  loop();
  return 0;
}

and also https://gist.github.com/xrivendell7/569542ed0113dc5f98753ea8c5305912