net/ipv4: inconsistent lock state in tcp_conn_request/inet_ehash_insert

[Andrey Konovalov]

Hi,

I've got the following error report while fuzzing the kernel with syzkaller.

On commit e5d56efc97f8240d0b5d66c03949382b6d7e5570 (Feb 26).

A reproducer and .config are attached.

=================================
[ INFO: inconsistent lock state ]
4.10.0+ #60 Not tainted
---------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
syz-executor0/5090 [HC0[0]:SC0[0]:HE1:SE1] takes:
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] spin_lock include/linux/spinlock.h:299 [inline]
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] inet_ehash_insert+0x240/0xad0
net/ipv4/inet_hashtables.c:407
{IN-SOFTIRQ-W} state was registered at:
  mark_irqflags kernel/locking/lockdep.c:2923 [inline]
  __lock_acquire+0xbcf/0x3270 kernel/locking/lockdep.c:3295
  lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
  __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
  _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
  spin_lock include/linux/spinlock.h:299 [inline]
  inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
  reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
  inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
  tcp_conn_request+0x25cc/0x3310 net/ipv4/tcp_input.c:6399
  tcp_v4_conn_request+0x157/0x220 net/ipv4/tcp_ipv4.c:1262
  tcp_rcv_state_process+0x802/0x4130 net/ipv4/tcp_input.c:5889
  tcp_v4_do_rcv+0x56b/0x940 net/ipv4/tcp_ipv4.c:1433
  tcp_v4_rcv+0x2e12/0x3210 net/ipv4/tcp_ipv4.c:1711
  ip_local_deliver_finish+0x4ce/0xc40 net/ipv4/ip_input.c:216
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_local_deliver+0x1ce/0x710 net/ipv4/ip_input.c:257
  dst_input include/net/dst.h:492 [inline]
  ip_rcv_finish+0xb1d/0x2110 net/ipv4/ip_input.c:396
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_rcv+0xd90/0x19c0 net/ipv4/ip_input.c:487
  __netif_receive_skb_core+0x1ad1/0x3400 net/core/dev.c:4179
  __netif_receive_skb+0x2a/0x170 net/core/dev.c:4217
  netif_receive_skb_internal+0x1d6/0x430 net/core/dev.c:4245
  napi_skb_finish net/core/dev.c:4602 [inline]
  napi_gro_receive+0x4e6/0x680 net/core/dev.c:4636
  e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4033 [inline]
  e1000_clean_rx_irq+0x5e0/0x1490
drivers/net/ethernet/intel/e1000/e1000_main.c:4489
  e1000_clean+0xb9a/0x2910 drivers/net/ethernet/intel/e1000/e1000_main.c:3834
  napi_poll net/core/dev.c:5171 [inline]
  net_rx_action+0xe70/0x1900 net/core/dev.c:5236
  __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
  invoke_softirq kernel/softirq.c:364 [inline]
  irq_exit+0x19e/0x1d0 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:658 [inline]
  do_IRQ+0x81/0x1a0 arch/x86/kernel/irq.c:250
  ret_from_intr+0x0/0x20
  native_safe_halt+0x6/0x10 arch/x86/include/asm/irqflags.h:53
  arch_safe_halt arch/x86/include/asm/paravirt.h:98 [inline]
  default_idle+0x8f/0x410 arch/x86/kernel/process.c:271
  arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:262
  default_idle_call+0x36/0x60 kernel/sched/idle.c:96
  cpuidle_idle_call kernel/sched/idle.c:154 [inline]
  do_idle+0x348/0x440 kernel/sched/idle.c:243
  cpu_startup_entry+0x18/0x20 kernel/sched/idle.c:345
  start_secondary+0x344/0x440 arch/x86/kernel/smpboot.c:272
  verify_cpu+0x0/0xfc
irq event stamp: 1741
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160
[inline]
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
_raw_spin_unlock_irqrestore+0xf7/0x1a0 kernel/locking/spinlock.c:191
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
_raw_spin_lock_irqsave+0xa2/0x110 kernel/locking/spinlock.c:159
softirqs last  enabled at (1738): [<ffffffff84d4deff>]
__do_softirq+0x7cf/0xb7d kernel/softirq.c:310
softirqs last disabled at (1571): [<ffffffff84d4b92c>]
do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&(&hashinfo->ehash_locks[i])->rlock);
  <Interrupt>
    lock(&(&hashinfo->ehash_locks[i])->rlock);

 *** DEADLOCK ***

1 lock held by syz-executor0/5090:
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>] lock_sock
include/net/sock.h:1460 [inline]
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>]
sock_setsockopt+0x233/0x1e40 net/core/sock.c:683

stack backtrace:
CPU: 1 PID: 5090 Comm: syz-executor0 Not tainted 4.10.0+ #60
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 print_usage_bug+0x3ef/0x450 kernel/locking/lockdep.c:2387
 valid_state kernel/locking/lockdep.c:2400 [inline]
 mark_lock_irq kernel/locking/lockdep.c:2602 [inline]
 mark_lock+0xf30/0x1410 kernel/locking/lockdep.c:3065
 mark_irqflags kernel/locking/lockdep.c:2941 [inline]
 __lock_acquire+0x6dc/0x3270 kernel/locking/lockdep.c:3295
 lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:299 [inline]
 inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
 inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
 dccp_v6_conn_request+0xada/0x11b0 net/dccp/ipv6.c:380
 dccp_rcv_state_process+0x51e/0x1660 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:896 [inline]
 __release_sock+0x127/0x3a0 net/core/sock.c:2052
 release_sock+0xa5/0x2b0 net/core/sock.c:2539
 sock_setsockopt+0x60f/0x1e40 net/core/sock.c:1016
 SYSC_setsockopt net/socket.c:1782 [inline]
 SyS_setsockopt+0x2fb/0x3a0 net/socket.c:1765
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007fe8b26c2b58 EFLAGS: 00000292 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 00000000004458b9
RDX: 000000000000001a RSI: 0000000000000001 RDI: 0000000000000006
RBP: 00000000006e2110 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000208c3000 R11: 0000000000000292 R12: 0000000000708000
R13: 0000000020000000 R14: 0000000000001000 R15: 0000000000000000
// autogenerated by syzkaller (http://github.com/google/syzkaller)

#ifndef __NR_listen
#define __NR_listen 50
#endif
#ifndef __NR_setsockopt
#define __NR_setsockopt 54
#endif
#ifndef __NR_connect
#define __NR_connect 42
#endif
#ifndef __NR_mmap
#define __NR_mmap 9
#endif
#ifndef __NR_socket
#define __NR_socket 41
#endif
#ifndef __NR_bind
#define __NR_bind 49
#endif

#define _GNU_SOURCE

#include <sys/ioctl.h>
#include <sys/mman.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 <linux/capability.h>
#include <linux/if.h>
#include <linux/if_tun.h>
#include <linux/kvm.h>
#include <linux/sched.h>
#include <net/if_arp.h>

#include <assert.h>
#include <dirent.h>
#include <errno.h>
#include <fcntl.h>
#include <grp.h>
#include <pthread.h>
#include <setjmp.h>
#include <signal.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stddef.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>

const int kFailStatus = 67;
const int kErrorStatus = 68;
const int kRetryStatus = 69;

__attribute__((noreturn)) void doexit(int status)
{
  volatile unsigned i;
  syscall(__NR_exit_group, status);
  for (i = 0;; i++) {
  }
}

__attribute__((noreturn)) void fail(const char* msg, ...)
{
  int e = errno;
  fflush(stdout);
  va_list args;
  va_start(args, msg);
  vfprintf(stderr, msg, args);
  va_end(args);
  fprintf(stderr, " (errno %d)\n", e);
  doexit(e == ENOMEM ? kRetryStatus : kFailStatus);
}

__attribute__((noreturn)) void exitf(const char* msg, ...)
{
  int e = errno;
  fflush(stdout);
  va_list args;
  va_start(args, msg);
  vfprintf(stderr, msg, args);
  va_end(args);
  fprintf(stderr, " (errno %d)\n", e);
  doexit(kRetryStatus);
}

static int flag_debug;

void debug(const char* msg, ...)
{
  if (!flag_debug)
    return;
  va_list args;
  va_start(args, msg);
  vfprintf(stdout, msg, args);
  va_end(args);
  fflush(stdout);
}

__thread int skip_segv;
__thread jmp_buf segv_env;

static void segv_handler(int sig, siginfo_t* info, void* uctx)
{
  uintptr_t addr = (uintptr_t)info->si_addr;
  const uintptr_t prog_start = 1 << 20;
  const uintptr_t prog_end = 100 << 20;
  if (__atomic_load_n(&skip_segv, __ATOMIC_RELAXED) &&
      (addr < prog_start || addr > prog_end)) {
    debug("SIGSEGV on %p, skipping\n", addr);
    _longjmp(segv_env, 1);
  }
  debug("SIGSEGV on %p, exiting\n", addr);
  doexit(sig);
  for (;;) {
  }
}

static void install_segv_handler()
{
  struct sigaction sa;
  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(...)                                                \
  {                                                                    \
    __atomic_fetch_add(&skip_segv, 1, __ATOMIC_SEQ_CST);               \
    if (_setjmp(segv_env) == 0) {                                      \
      __VA_ARGS__;                                                     \
    }                                                                  \
    __atomic_fetch_sub(&skip_segv, 1, __ATOMIC_SEQ_CST);               \
  }

#define BITMASK_LEN(type, bf_len) (type)((1ull << (bf_len)) - 1)

#define BITMASK_LEN_OFF(type, bf_off, bf_len)                          \
  (type)(BITMASK_LEN(type, (bf_len)) << (bf_off))

#define STORE_BY_BITMASK(type, addr, val, bf_off, bf_len)              \
  if ((bf_off) == 0 && (bf_len) == 0) {                                \
    *(type*)(addr) = (type)(val);                                      \
  } else {                                                             \
    type new_val = *(type*)(addr);                                     \
    new_val &= ~BITMASK_LEN_OFF(type, (bf_off), (bf_len));             \
    new_val |= ((type)(val)&BITMASK_LEN(type, (bf_len))) << (bf_off);  \
    *(type*)(addr) = new_val;                                          \
  }

static uintptr_t execute_syscall(int nr, uintptr_t a0, uintptr_t a1,
                                 uintptr_t a2, uintptr_t a3,
                                 uintptr_t a4, uintptr_t a5,
                                 uintptr_t a6, uintptr_t a7,
                                 uintptr_t a8)
{
  switch (nr) {
  default:
    return syscall(nr, a0, a1, a2, a3, a4, a5);
  }
}

static void setup_main_process()
{
  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);
  install_segv_handler();

  char tmpdir_template[] = "./syzkaller.XXXXXX";
  char* tmpdir = mkdtemp(tmpdir_template);
  if (!tmpdir)
    fail("failed to mkdtemp");
  if (chmod(tmpdir, 0777))
    fail("failed to chmod");
  if (chdir(tmpdir))
    fail("failed to chdir");
}

static void loop();

static void sandbox_common()
{
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setpgrp();
  setsid();

  struct rlimit rlim;
  rlim.rlim_cur = rlim.rlim_max = 128 << 20;
  setrlimit(RLIMIT_AS, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 1 << 20;
  setrlimit(RLIMIT_FSIZE, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 1 << 20;
  setrlimit(RLIMIT_STACK, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 0;
  setrlimit(RLIMIT_CORE, &rlim);

  unshare(CLONE_NEWNS);
  unshare(CLONE_NEWIPC);
  unshare(CLONE_IO);
}

static int do_sandbox_none(int executor_pid, bool enable_tun)
{
  int pid = fork();
  if (pid)
    return pid;

  sandbox_common();

  loop();
  doexit(1);
}

static void remove_dir(const char* dir)
{
  DIR* dp;
  struct dirent* ep;
  int iter = 0;
retry:
  dp = opendir(dir);
  if (dp == NULL) {
    if (errno == EMFILE) {
      exitf("opendir(%s) failed due to NOFILE, exiting");
    }
    exitf("opendir(%s) failed", dir);
  }
  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);
    struct stat st;
    if (lstat(filename, &st))
      exitf("lstat(%s) failed", filename);
    if (S_ISDIR(st.st_mode)) {
      remove_dir(filename);
      continue;
    }
    int i;
    for (i = 0;; i++) {
      debug("unlink(%s)\n", filename);
      if (unlink(filename) == 0)
        break;
      if (errno == EROFS) {
        debug("ignoring EROFS\n");
        break;
      }
      if (errno != EBUSY || i > 100)
        exitf("unlink(%s) failed", filename);
      debug("umount(%s)\n", filename);
      if (umount2(filename, MNT_DETACH))
        exitf("umount(%s) failed", filename);
    }
  }
  closedir(dp);
  int i;
  for (i = 0;; i++) {
    debug("rmdir(%s)\n", dir);
    if (rmdir(dir) == 0)
      break;
    if (i < 100) {
      if (errno == EROFS) {
        debug("ignoring EROFS\n");
        break;
      }
      if (errno == EBUSY) {
        debug("umount(%s)\n", dir);
        if (umount2(dir, MNT_DETACH))
          exitf("umount(%s) failed", dir);
        continue;
      }
      if (errno == ENOTEMPTY) {
        if (iter < 100) {
          iter++;
          goto retry;
        }
      }
    }
    exitf("rmdir(%s) failed", dir);
  }
}

static uint64_t current_time_ms()
{
  struct timespec ts;

  if (clock_gettime(CLOCK_MONOTONIC, &ts))
    fail("clock_gettime failed");
  return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
}

static void test();

void loop()
{
  int iter;
  for (iter = 0;; iter++) {
    char cwdbuf[256];
    sprintf(cwdbuf, "./%d", iter);
    if (mkdir(cwdbuf, 0777))
      fail("failed to mkdir");
    int pid = fork();
    if (pid < 0)
      fail("clone failed");
    if (pid == 0) {
      prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
      setpgrp();
      if (chdir(cwdbuf))
        fail("failed to chdir");
      test();
      doexit(0);
    }
    int status = 0;
    uint64_t start = current_time_ms();
    for (;;) {
      int res = waitpid(-1, &status, __WALL | WNOHANG);
      if (res == pid)
        break;
      usleep(1000);
      if (current_time_ms() - start > 5 * 1000) {
        kill(-pid, SIGKILL);
        kill(pid, SIGKILL);
        while (waitpid(-1, &status, __WALL) != pid) {
        }
        break;
      }
    }
    remove_dir(cwdbuf);
  }
}

long r[25];
void* thr(void* arg)
{
  switch ((long)arg) {
  case 0:
    r[0] =
        execute_syscall(__NR_mmap, 0x20000000ul, 0xe69000ul, 0x3ul,
                        0x32ul, 0xfffffffffffffffful, 0x0ul, 0, 0, 0);
    break;
  case 1:
    r[1] = execute_syscall(__NR_socket, 0xaul, 0x6ul, 0x0ul, 0, 0, 0, 0,
                           0, 0);
    break;
  case 2:
    r[2] = execute_syscall(__NR_socket, 0xaul, 0x6ul, 0x0ul, 0, 0, 0, 0,
                           0, 0);
    break;
  case 3:
    NONFAILING(*(uint16_t*)0x20e62fe0 = (uint16_t)0xa);
    NONFAILING(*(uint16_t*)0x20e62fe2 = (uint16_t)0x224e);
    NONFAILING(*(uint32_t*)0x20e62fe4 = (uint32_t)0x0);
    NONFAILING(*(uint64_t*)0x20e62fe8 = (uint64_t)0x0);
    NONFAILING(*(uint64_t*)0x20e62ff0 = (uint64_t)0x100000000000000);
    NONFAILING(*(uint32_t*)0x20e62ff8 = (uint32_t)0x0);
    r[9] = execute_syscall(__NR_bind, r[2], 0x20e62fe0ul, 0x20ul, 0, 0,
                           0, 0, 0, 0);
    break;
  case 4:
    r[10] =
        execute_syscall(__NR_listen, r[2], 0x5ul, 0, 0, 0, 0, 0, 0, 0);
    break;
  case 5:
    NONFAILING(*(uint16_t*)0x208c3000 = (uint16_t)0x1);
    NONFAILING(*(uint64_t*)0x208c3008 = (uint64_t)0x20c58000);
    NONFAILING(*(uint16_t*)0x20c58000 = (uint16_t)0x6);
    NONFAILING(*(uint8_t*)0x20c58002 = (uint8_t)0x3);
    NONFAILING(*(uint8_t*)0x20c58003 = (uint8_t)0xfe9);
    NONFAILING(*(uint32_t*)0x20c58004 = (uint32_t)0x6);
    r[17] = execute_syscall(__NR_setsockopt, r[2], 0x1ul, 0x1aul,
                            0x208c3000ul, 0x10ul, 0, 0, 0, 0);
    break;
  case 6:
    NONFAILING(*(uint16_t*)0x20e5afe0 = (uint16_t)0xa);
    NONFAILING(*(uint16_t*)0x20e5afe2 = (uint16_t)0x224e);
    NONFAILING(*(uint32_t*)0x20e5afe4 = (uint32_t)0x0);
    NONFAILING(*(uint64_t*)0x20e5afe8 = (uint64_t)0x0);
    NONFAILING(*(uint64_t*)0x20e5aff0 = (uint64_t)0x100000000000000);
    NONFAILING(*(uint32_t*)0x20e5aff8 = (uint32_t)0x0);
    r[24] = execute_syscall(__NR_connect, r[1], 0x20e5afe0ul, 0x20ul, 0,
                            0, 0, 0, 0, 0);
    break;
  }
  return 0;
}

void test()
{
  long i;
  pthread_t th[14];

  memset(r, -1, sizeof(r));
  srand(getpid());
  for (i = 0; i < 7; i++) {
    pthread_create(&th[i], 0, thr, (void*)i);
    usleep(10000);
  }
  usleep(100000);
}

int main()
{
  int i;
  for (i = 0; i < 8; i++) {
    if (fork() == 0) {
      setup_main_process();
      int pid = do_sandbox_none(i, false);
      int status = 0;
      while (waitpid(pid, &status, __WALL) != pid) {
      }
      return 0;
    }
  }
  sleep(1000000);
  return 0;
}

Attachment: .config
Description: Binary data