net: Fix for dst_negative_advice

dst_negative_advice() should check for changed dst and reset
sk_tx_queue_mapping accordingly. Pass sock to the callers of
dst_negative_advice.

(sk_reset_txq is defined just for use by dst_negative_advice. The
only way I could find to get around this is to move dst_negative_()
from dst.h to dst.c, include sock.h in dst.c, etc)

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 21 insertions, 7 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index 5a900ddcf10d..720d90653a8e 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -222,11 +222,19 @@ static inline void dst_confirm(struct dst_entry *dst)
                 neigh_confirm(dst->neighbour);
 }
 
-static inline void dst_negative_advice(struct dst_entry **dst_p)
+static inline void dst_negative_advice(struct dst_entry **dst_p,
+                                       struct sock *sk)
 {
         struct dst_entry * dst = *dst_p;
-        if (dst && dst->ops->negative_advice)
+        if (dst && dst->ops->negative_advice) {
                 *dst_p = dst->ops->negative_advice(dst);
+
+                if (dst != *dst_p) {
+                        extern void sk_reset_txq(struct sock *sk);
+
+                        sk_reset_txq(sk);
+                }
+        }
 }
 
 static inline void dst_link_failure(struct sk_buff *skb)
diff --git a/net/core/sock.c b/net/core/sock.c
index 934d9673f084..5a51512f638a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -352,6 +352,12 @@ discard_and_relse:
 }
 EXPORT_SYMBOL(sk_receive_skb);
 
+void sk_reset_txq(struct sock *sk)
+{
+        sk_tx_queue_clear(sk);
+}
+EXPORT_SYMBOL(sk_reset_txq);
+
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
 {
         struct dst_entry *dst = sk->sk_dst_cache;
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 162d1e683c39..bbfeb5eae46a 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -38,7 +38,7 @@ static int dccp_write_timeout(struct sock *sk)
 
         if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) {
                 if (icsk->icsk_retransmits != 0)
-                        dst_negative_advice(&sk->sk_dst_cache);
+                        dst_negative_advice(&sk->sk_dst_cache, sk);
                 retry_until = icsk->icsk_syn_retries ?
                             : sysctl_dccp_request_retries;
         } else {
@@ -63,7 +63,7 @@ static int dccp_write_timeout(struct sock *sk)
                            Golden words :-).
                    */
 
-                        dst_negative_advice(&sk->sk_dst_cache);
+                        dst_negative_advice(&sk->sk_dst_cache, sk);
                 }
 
                 retry_until = sysctl_dccp_retries2;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 4d3060660a14..664965c87e16 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1955,7 +1955,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock,
         }
 
         if ((flags & MSG_TRYHARD) && sk->sk_dst_cache)
-                dst_negative_advice(&sk->sk_dst_cache);
+                dst_negative_advice(&sk->sk_dst_cache, sk);
 
         mss = scp->segsize_rem;
         fctype = scp->services_rem & NSP_FC_MASK;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6e8996cb79d0..8353a538cd4c 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -141,14 +141,14 @@ static int tcp_write_timeout(struct sock *sk)
 
         if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
                 if (icsk->icsk_retransmits)
-                        dst_negative_advice(&sk->sk_dst_cache);
+                        dst_negative_advice(&sk->sk_dst_cache, sk);
                 retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
         } else {
                 if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
                         /* Black hole detection */
                         tcp_mtu_probing(icsk, sk);
 
-                        dst_negative_advice(&sk->sk_dst_cache);
+                        dst_negative_advice(&sk->sk_dst_cache, sk);
                 }
 
                 retry_until = sysctl_tcp_retries2;