xfrm: serialize state GC with device state flush

The deferred-device pass in xfrm_dev_state_flush() finds states under
xfrm_state_dev_gc_lock, but drops the lock before calling
xfrm_dev_state_free() because the driver callback may sleep.  The device
GC list does not hold an xfrm_state reference, so the state GC worker can
destroy the same state concurrently.

The race can proceed as follows:

  CPU 0                               CPU 1
  find x on the device GC list
  drop xfrm_state_dev_gc_lock
  read x->xso.dev
                                      xfrm_state_gc_destroy(x)
                                      xfrm_dev_state_free(x)
                                      xfrm_state_free(x)
  continue xfrm_dev_state_free(x)

Both paths can invoke the driver callback and drop the device reference.
CPU 0 can also access the xfrm_state after CPU 1 has freed it.

KASAN reported:

  BUG: KASAN: slab-use-after-free in xfrm_dev_state_free+0x24c/0x2a0
  Read of size 8 at addr ffff88810bbaa960 by task poc/102

  Call Trace:
   xfrm_dev_state_free+0x24c/0x2a0
   xfrm_dev_state_flush+0x353/0x400
   xfrm_dev_event+0x26d/0x3a0
   notifier_call_chain+0xc0/0x280
   __dev_notify_flags+0x169/0x250
   netif_change_flags+0xe7/0x160
   dev_change_flags+0x96/0x220
   devinet_ioctl+0x7f4/0x1880

  Allocated by task 87:
   xfrm_state_alloc+0x1e/0x5c0
   xfrm_add_sa+0xe7f/0x5820
   xfrm_user_rcv_msg+0x4f3/0x940

  Freed by task 57:
   kmem_cache_free+0xcb/0x3d0
   xfrm_state_gc_task+0x4a8/0x650
   process_one_work+0x63a/0x1070

Serialize xfrm_state destruction against the deferred-device pass with a
mutex.  Keep xfrm_state_dev_gc_lock limited to list operations and retain
the existing callback and device-reference release ordering.

Fixes: 07b87f9eea ("xfrm: Fix unregister netdevice hang on hardware offload.")
Cc: stable@vger.kernel.org
Signed-off-by: Chengfeng Ye <nicoyip.dev@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
This commit is contained in:
Chengfeng Ye 2026-07-30 18:35:43 +08:00 committed by Steffen Klassert
parent d042487dc1
commit 89fefad9f9

View File

@ -226,6 +226,7 @@ static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO];
static DEFINE_SPINLOCK(xfrm_state_gc_lock);
static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock);
static DEFINE_MUTEX(xfrm_state_gc_mutex);
int __xfrm_state_delete(struct xfrm_state *x);
@ -632,8 +633,10 @@ static void xfrm_state_gc_task(struct work_struct *work)
synchronize_rcu();
mutex_lock(&xfrm_state_gc_mutex);
hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
xfrm_state_gc_destroy(x);
mutex_unlock(&xfrm_state_gc_mutex);
}
static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
@ -1000,6 +1003,7 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
out:
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
mutex_lock(&xfrm_state_gc_mutex);
spin_lock_bh(&xfrm_state_dev_gc_lock);
restart_gc:
hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) {
@ -1014,6 +1018,7 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
}
spin_unlock_bh(&xfrm_state_dev_gc_lock);
mutex_unlock(&xfrm_state_gc_mutex);
xfrm_flush_gc();