kevin/linux
1
Fork 0
Code

netrom: fix possible dead-lock in nr_rt_ioctl()

Browse Source 
syzbot loves netrom, and found a possible deadlock in nr_rt_ioctl [1]

Make sure we always acquire nr_node_list_lock before nr_node_lock(nr_node)

[1]
WARNING: possible circular locking dependency detected
6.9.0-rc7-syzkaller-02147-g654de42f3fc6 #0 Not tainted
------------------------------------------------------
syz-executor350/5129 is trying to acquire lock:
 ffff8880186e2070 (&nr_node->node_lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
 ffff8880186e2070 (&nr_node->node_lock){+...}-{2:2}, at: nr_node_lock include/net/netrom.h:152 [inline]
 ffff8880186e2070 (&nr_node->node_lock){+...}-{2:2}, at: nr_dec_obs net/netrom/nr_route.c:464 [inline]
 ffff8880186e2070 (&nr_node->node_lock){+...}-{2:2}, at: nr_rt_ioctl+0x1bb/0x1090 net/netrom/nr_route.c:697

but task is already holding lock:
 ffffffff8f7053b8 (nr_node_list_lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
 ffffffff8f7053b8 (nr_node_list_lock){+...}-{2:2}, at: nr_dec_obs net/netrom/nr_route.c:462 [inline]
 ffffffff8f7053b8 (nr_node_list_lock){+...}-{2:2}, at: nr_rt_ioctl+0x10a/0x1090 net/netrom/nr_route.c:697

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (nr_node_list_lock){+...}-{2:2}:
        lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754
        __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
        _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178
        spin_lock_bh include/linux/spinlock.h:356 [inline]
        nr_remove_node net/netrom/nr_route.c:299 [inline]
        nr_del_node+0x4b4/0x820 net/netrom/nr_route.c:355
        nr_rt_ioctl+0xa95/0x1090 net/netrom/nr_route.c:683
        sock_do_ioctl+0x158/0x460 net/socket.c:1222
        sock_ioctl+0x629/0x8e0 net/socket.c:1341
        vfs_ioctl fs/ioctl.c:51 [inline]
        __do_sys_ioctl fs/ioctl.c:904 [inline]
        __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:890
        do_syscall_x64 arch/x86/entry/common.c:52 [inline]
        do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #0 (&nr_node->node_lock){+...}-{2:2}:
        check_prev_add kernel/locking/lockdep.c:3134 [inline]
        check_prevs_add kernel/locking/lockdep.c:3253 [inline]
        validate_chain+0x18cb/0x58e0 kernel/locking/lockdep.c:3869
        __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137
        lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754
        __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
        _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178
        spin_lock_bh include/linux/spinlock.h:356 [inline]
        nr_node_lock include/net/netrom.h:152 [inline]
        nr_dec_obs net/netrom/nr_route.c:464 [inline]
        nr_rt_ioctl+0x1bb/0x1090 net/netrom/nr_route.c:697
        sock_do_ioctl+0x158/0x460 net/socket.c:1222
        sock_ioctl+0x629/0x8e0 net/socket.c:1341
        vfs_ioctl fs/ioctl.c:51 [inline]
        __do_sys_ioctl fs/ioctl.c:904 [inline]
        __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:890
        do_syscall_x64 arch/x86/entry/common.c:52 [inline]
        do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(nr_node_list_lock);
                               lock(&nr_node->node_lock);
                               lock(nr_node_list_lock);
  lock(&nr_node->node_lock);

 *** DEADLOCK ***

1 lock held by syz-executor350/5129:
  #0: ffffffff8f7053b8 (nr_node_list_lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
  #0: ffffffff8f7053b8 (nr_node_list_lock){+...}-{2:2}, at: nr_dec_obs net/netrom/nr_route.c:462 [inline]
  #0: ffffffff8f7053b8 (nr_node_list_lock){+...}-{2:2}, at: nr_rt_ioctl+0x10a/0x1090 net/netrom/nr_route.c:697

stack backtrace:
CPU: 0 PID: 5129 Comm: syz-executor350 Not tainted 6.9.0-rc7-syzkaller-02147-g654de42f3fc6 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:88 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
  check_noncircular+0x36a/0x4a0 kernel/locking/lockdep.c:2187
  check_prev_add kernel/locking/lockdep.c:3134 [inline]
  check_prevs_add kernel/locking/lockdep.c:3253 [inline]
  validate_chain+0x18cb/0x58e0 kernel/locking/lockdep.c:3869
  __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137
  lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754
  __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
  _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178
  spin_lock_bh include/linux/spinlock.h:356 [inline]
  nr_node_lock include/net/netrom.h:152 [inline]
  nr_dec_obs net/netrom/nr_route.c:464 [inline]
  nr_rt_ioctl+0x1bb/0x1090 net/netrom/nr_route.c:697
  sock_do_ioctl+0x158/0x460 net/socket.c:1222
  sock_ioctl+0x629/0x8e0 net/socket.c:1341
  vfs_ioctl fs/ioctl.c:51 [inline]
  __do_sys_ioctl fs/ioctl.c:904 [inline]
  __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:890
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240515142934.3708038-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Eric Dumazet 2024-05-15 14:29:34 +00:00 committed by Jakub Kicinski
parent 67708158e7
commit e03e7f20eb
1 changed files with 7 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
net/netrom/nr_route.c
View File

@ -285,22 +285,14 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
return 0;
}
static inline void __nr_remove_node(struct nr_node *nr_node)
static void nr_remove_node_locked(struct nr_node *nr_node)
{
lockdep_assert_held(&nr_node_list_lock);
hlist_del_init(&nr_node->node_node);
nr_node_put(nr_node);
}
#define nr_remove_node_locked(__node) \
__nr_remove_node(__node)
static void nr_remove_node(struct nr_node *nr_node)
{
spin_lock_bh(&nr_node_list_lock);
__nr_remove_node(nr_node);
spin_unlock_bh(&nr_node_list_lock);
}
static inline void __nr_remove_neigh(struct nr_neigh *nr_neigh)
{
hlist_del_init(&nr_neigh->neigh_node);
@ -339,6 +331,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n
return -EINVAL;
}
spin_lock_bh(&nr_node_list_lock);
nr_node_lock(nr_node);
for (i = 0; i < nr_node->count; i++) {
if (nr_node->routes[i].neighbour == nr_neigh) {
@ -352,7 +345,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n
nr_node->count--;
if (nr_node->count == 0) {
nr_remove_node(nr_node);
nr_remove_node_locked(nr_node);
} else {
switch (i) {
case 0:
@ -367,12 +360,14 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n
nr_node_put(nr_node);
}
nr_node_unlock(nr_node);
spin_unlock_bh(&nr_node_list_lock);
return 0;
}
}
nr_neigh_put(nr_neigh);
nr_node_unlock(nr_node);
spin_unlock_bh(&nr_node_list_lock);
nr_node_put(nr_node);
return -EINVAL;