Re: KASAN: use-after-free Read in cma_cancel_operation, rdma_listen

[Hao Sun]

Jason Gunthorpe <jgg@xxxxxxxx> 于2021年4月13日周二 下午9:45写道：
>
> On Tue, Apr 13, 2021 at 09:42:43PM +0800, Hao Sun wrote:
> > Jason Gunthorpe <jgg@xxxxxxxx> 于2021年4月13日周二 下午9:34写道：
> > >
> > > On Tue, Apr 13, 2021 at 11:36:41AM +0800, Hao Sun wrote:
> > > > Hi
> > > >
> > > > When using Healer(https://github.com/SunHao-0/healer/tree/dev) to fuzz
> > > > the Linux kernel, I found two use-after-free bugs which have been
> > > > reported a long time ago by Syzbot.
> > > > Although the corresponding patches have been merged into upstream,
> > > > these two bugs can still be triggered easily.
> > > > The original information about Syzbot report can be found here:
> > > > https://syzkaller.appspot.com/bug?id=8dc0bcd9dd6ec915ba10b3354740eb420884acaa
> > > > https://syzkaller.appspot.com/bug?id=95f89b8fb9fdc42e28ad586e657fea074e4e719b
> > >
> > > Then why hasn't syzbot seen this in a year's time? Seems strange
> > >
> >
> > Seems strange to me too, but the fact is that the reproduction program
> > in attachment can trigger these two bugs quickly.
>
> Do you have this in the C format?
>

Just tried to use syz-prog2c to convert the repro-prog to C format.
The repro program of  rdma_listen was successfully reproduced
(uploaded in attachment), the other one failed. it looks like
syz-prog2c may not be able to do the equivalent conversion.
You can use syz-execprog to execute the reprogram directly, this
method can reproduce both crashes, I have tried it.

For reproduction prog of  cma_cancel_operation,  using syz-execprog
can run this reproduction program directly:
 ./syz-execprog  -threaded -repeat 0 -procs 2 -slowdown 1 -enable tun
-enable netdev -enable resetnet -enable cgroups -enable binfmt-misc
-enable close_fds -enable devlinkpci -enable usb -enable vhci -enable
wifi -enable ieee802154 -enable sysctl repro.prog
// autogenerated by syzkaller (https://github.com/google/syzkaller)

#define _GNU_SOURCE

#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.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/mount.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>

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;
  int skip = __atomic_load_n(&skip_segv, __ATOMIC_RELAXED) != 0;
  int valid = addr < prog_start || addr > prog_end;
  if (skip && valid) {
    _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(...)                                                        \
  ({                                                                           \
    int ok = 1;                                                                \
    __atomic_fetch_add(&skip_segv, 1, __ATOMIC_SEQ_CST);                       \
    if (_setjmp(segv_env) == 0) {                                              \
      __VA_ARGS__;                                                             \
    } else                                                                     \
      ok = 0;                                                                  \
    __atomic_fetch_sub(&skip_segv, 1, __ATOMIC_SEQ_CST);                       \
    ok;                                                                        \
  })

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 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 FS_IOC_SETFLAGS _IOW('f', 2, long)
static void remove_dir(const char* dir)
{
  int iter = 0;
  DIR* dp = 0;
retry:
  while (umount2(dir, MNT_DETACH) == 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, 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);
  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, 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);
  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");
}

static void execute_one(void);

#define WAIT_FLAGS __WALL

static void loop(void)
{
  int iter = 0;
  for (;; iter++) {
    char cwdbuf[32];
    sprintf(cwdbuf, "./%d", iter);
    if (mkdir(cwdbuf, 0777))
      exit(1);
    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 (;;) {
      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;
    }
    remove_dir(cwdbuf);
  }
}

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

void execute_one(void)
{
  intptr_t res = 0;
  NONFAILING(memcpy((void*)0x20000040, "/dev/infiniband/rdma_cm\000", 24));
  res = syscall(__NR_openat, 0xffffffffffffff9cul, 0x20000040ul, 2ul, 0ul);
  if (res != -1)
    r[0] = res;
  NONFAILING(*(uint32_t*)0x20000300 = 0);
  NONFAILING(*(uint16_t*)0x20000304 = 0x18);
  NONFAILING(*(uint16_t*)0x20000306 = 0xfa00);
  NONFAILING(*(uint64_t*)0x20000308 = 1);
  NONFAILING(*(uint64_t*)0x20000310 = 0x200002c0);
  NONFAILING(*(uint16_t*)0x20000318 = 2);
  NONFAILING(*(uint8_t*)0x2000031a = 6);
  NONFAILING(*(uint8_t*)0x2000031b = 0);
  NONFAILING(*(uint8_t*)0x2000031c = 0);
  NONFAILING(*(uint8_t*)0x2000031d = 0);
  NONFAILING(*(uint8_t*)0x2000031e = 0);
  NONFAILING(*(uint8_t*)0x2000031f = 0);
  res = syscall(__NR_write, r[0], 0x20000300ul, 0x20ul);
  if (res != -1)
    NONFAILING(r[1] = *(uint32_t*)0x200002c0);
  NONFAILING(*(uint32_t*)0x20000380 = 3);
  NONFAILING(*(uint16_t*)0x20000384 = 0x40);
  NONFAILING(*(uint16_t*)0x20000386 = 0xfa00);
  NONFAILING(*(uint16_t*)0x20000388 = 0xa);
  NONFAILING(*(uint16_t*)0x2000038a = htobe16(0x4e22));
  NONFAILING(*(uint32_t*)0x2000038c = htobe32(0xa66f187b));
  NONFAILING(*(uint64_t*)0x20000390 = htobe64(0));
  NONFAILING(*(uint64_t*)0x20000398 = htobe64(1));
  NONFAILING(*(uint32_t*)0x200003a0 = 0x4dd0205c);
  NONFAILING(*(uint16_t*)0x200003a4 = 0xa);
  NONFAILING(*(uint16_t*)0x200003a6 = htobe16(0x4e24));
  NONFAILING(*(uint32_t*)0x200003a8 = htobe32(0xc7e2a46b));
  NONFAILING(*(uint8_t*)0x200003ac = 0xfc);
  NONFAILING(*(uint8_t*)0x200003ad = 2);
  NONFAILING(*(uint8_t*)0x200003ae = 0);
  NONFAILING(*(uint8_t*)0x200003af = 0);
  NONFAILING(*(uint8_t*)0x200003b0 = 0);
  NONFAILING(*(uint8_t*)0x200003b1 = 0);
  NONFAILING(*(uint8_t*)0x200003b2 = 0);
  NONFAILING(*(uint8_t*)0x200003b3 = 0);
  NONFAILING(*(uint8_t*)0x200003b4 = 0);
  NONFAILING(*(uint8_t*)0x200003b5 = 0);
  NONFAILING(*(uint8_t*)0x200003b6 = 0);
  NONFAILING(*(uint8_t*)0x200003b7 = 0);
  NONFAILING(*(uint8_t*)0x200003b8 = 0);
  NONFAILING(*(uint8_t*)0x200003b9 = 0);
  NONFAILING(*(uint8_t*)0x200003ba = 0);
  NONFAILING(*(uint8_t*)0x200003bb = 0);
  NONFAILING(*(uint32_t*)0x200003bc = 0xa4649c8a);
  NONFAILING(*(uint32_t*)0x200003c0 = r[1]);
  NONFAILING(*(uint32_t*)0x200003c4 = 0x6747ef83);
  syscall(__NR_write, r[0], 0x20000380ul, 0x48ul);
  NONFAILING(*(uint32_t*)0x20000000 = 7);
  NONFAILING(*(uint16_t*)0x20000004 = 8);
  NONFAILING(*(uint16_t*)0x20000006 = 0xfa00);
  NONFAILING(*(uint32_t*)0x20000008 = r[1]);
  NONFAILING(*(uint32_t*)0x2000000c = 0x59a6b2e3);
  syscall(__NR_write, r[0], 0x20000000ul, 0x10ul);
  NONFAILING(*(uint32_t*)0x200001c0 = 7);
  NONFAILING(*(uint16_t*)0x200001c4 = 8);
  NONFAILING(*(uint16_t*)0x200001c6 = 0xfa00);
  NONFAILING(*(uint32_t*)0x200001c8 = r[1]);
  NONFAILING(*(uint32_t*)0x200001cc = 1);
  syscall(__NR_write, r[0], 0x200001c0ul, 0x10ul);
}
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);
  install_segv_handler();
  use_temporary_dir();
  loop();
  return 0;
}