aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/skbuff.c
diff options
context:
space:
mode:
authorSoheil Hassas Yeganeh <soheil@google.com>2016-11-30 14:01:08 -0500
committerDavid S. Miller <davem@davemloft.net>2016-12-02 10:55:39 -0500
commit83a1a1a70e87f676fbb6086b26b6ac7f7fdd107d (patch)
tree3e7c0360a53899abcb4e850e8fa96476cbb944e9 /net/core/skbuff.c
parentMerge branch 'lwt-bpf' (diff)
downloadlinux-dev-83a1a1a70e87f676fbb6086b26b6ac7f7fdd107d.tar.xz
linux-dev-83a1a1a70e87f676fbb6086b26b6ac7f7fdd107d.zip
sock: reset sk_err for ICMP packets read from error queue
Only when ICMP packets are enqueued onto the error queue, sk_err is also set. Before f5f99309fa74 (sock: do not set sk_err in sock_dequeue_err_skb), a subsequent error queue read would set sk_err to the next error on the queue, or 0 if empty. As no error types other than ICMP set this field, sk_err should not be modified upon dequeuing them. Only for ICMP errors, reset the (racy) sk_err. Some applications, like traceroute, rely on it and go into a futile busy POLLERR loop otherwise. In principle, sk_err has to be set while an ICMP error is queued. Testing is_icmp_err_skb(skb_next) approximates this without requiring a full queue walk. Applications that receive both ICMP and other errors cannot rely on this legacy behavior, as other errors do not set sk_err in the first place. Fixes: f5f99309fa74 (sock: do not set sk_err in sock_dequeue_err_skb) Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core/skbuff.c')
-rw-r--r--net/core/skbuff.c17
1 files changed, 13 insertions, 4 deletions
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ea6fa954c7a0..b45cd1494243 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3714,20 +3714,29 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_queue_err_skb);
+static bool is_icmp_err_skb(const struct sk_buff *skb)
+{
+ return skb && (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+ SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP6);
+}
+
struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
{
struct sk_buff_head *q = &sk->sk_error_queue;
- struct sk_buff *skb, *skb_next;
+ struct sk_buff *skb, *skb_next = NULL;
+ bool icmp_next = false;
unsigned long flags;
- int err = 0;
spin_lock_irqsave(&q->lock, flags);
skb = __skb_dequeue(q);
if (skb && (skb_next = skb_peek(q)))
- err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
+ icmp_next = is_icmp_err_skb(skb_next);
spin_unlock_irqrestore(&q->lock, flags);
- if (err)
+ if (is_icmp_err_skb(skb) && !icmp_next)
+ sk->sk_err = 0;
+
+ if (skb_next)
sk->sk_error_report(sk);
return skb;