net: fix socket refcounting in skb_complete_wifi_ack()

TX skbs do not necessarily hold a reference on skb->sk->sk_refcnt
By the time TX completion happens, sk_refcnt might be already 0.

sock_hold()/sock_put() would then corrupt critical state, like
sk_wmem_alloc.

Fixes: bf7fa551e0ce ("mac80211: Resolve sk_refcnt/sk_wmem_alloc issue in wifi ack path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f3557958e9bf147631a90b51fef0630920acd97b..e2f37a560ec43ccf60a71f190423bd265eccf594 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3893,7 +3893,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 {
        struct sock *sk = skb->sk;
        struct sock_exterr_skb *serr;
-       int err;
+       int err = 1;
 
        skb->wifi_acked_valid = 1;
        skb->wifi_acked = acked;
@@ -3903,14 +3903,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
        serr->ee.ee_errno = ENOMSG;
        serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
-       /* take a reference to prevent skb_orphan() from freeing the socket */
-       sock_hold(sk);
-
-       err = sock_queue_err_skb(sk, skb);
+       /* Take a reference to prevent skb_orphan() from freeing the socket,
+        * but only if the socket refcount is not zero.
+        */
+       if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+               err = sock_queue_err_skb(sk, skb);
+               sock_put(sk);
+       }
        if (err)
                kfree_skb(skb);
-
-       sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);