net: Do delayed neigh confirmation.

When a dst_confirm() happens, mark the confirmation as pending in the
dst.  Then on the next packet out, when we have the neigh in-hand, do
the update.

This removes the dependency in dst_confirm() of dst's having an
attached neigh.

While we're here, remove the explicit 'dst' NULL check, all except 2
or 3 call sites ensure it's not NULL.  So just fix those cases up.

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 17 insertions, 9 deletions

diff --git a/net/core/dst.c b/net/core/dst.c
index 43d94cedbf7..a6e19a23a74 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -152,7 +152,7 @@ EXPORT_SYMBOL(dst_discard);
 const u32 dst_default_metrics[RTAX_MAX];
 
 void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
-		int initial_ref, int initial_obsolete, int flags)
+		int initial_ref, int initial_obsolete, unsigned short flags)
 {
 	struct dst_entry *dst;
 
@@ -188,6 +188,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 	dst->__use = 0;
 	dst->lastuse = jiffies;
 	dst->flags = flags;
+	dst->pending_confirm = 0;
 	dst->next = NULL;
 	if (!(flags & DST_NOCOUNT))
 		dst_entries_add(ops, 1);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e9a266a053..cc52679790b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -198,7 +198,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	if (unlikely(!neigh))
 		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
 	if (neigh) {
-		int res = neigh_output(neigh, skb);
+		int res = dst_neigh_output(dst, neigh, skb);
 
 		rcu_read_unlock_bh();
 		return res;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8416f8a68e6..ca0d0e7c977 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -740,13 +740,13 @@ void tcp_update_metrics(struct sock *sk)
 	if (sysctl_tcp_nometrics_save)
 		return;
 
-	dst_confirm(dst);
-
 	if (dst && (dst->flags & DST_HOST)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
 		int m;
 		unsigned long rtt;
 
+		dst_confirm(dst);
+
 		if (icsk->icsk_backoff || !tp->srtt) {
 			/* This session failed to estimate rtt. Why?
 			 * Probably, no packets returned in time.
@@ -3869,9 +3869,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 			tcp_cong_avoid(sk, ack, prior_in_flight);
 	}
 
-	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
-		dst_confirm(__sk_dst_get(sk));
-
+	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) {
+		struct dst_entry *dst = __sk_dst_get(sk);
+		if (dst)
+			dst_confirm(dst);
+	}
 	return 1;
 
 no_queue:
@@ -6140,9 +6142,14 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
 		case TCP_FIN_WAIT1:
 			if (tp->snd_una == tp->write_seq) {
+				struct dst_entry *dst;
+
 				tcp_set_state(sk, TCP_FIN_WAIT2);
 				sk->sk_shutdown |= SEND_SHUTDOWN;
-				dst_confirm(__sk_dst_get(sk));
+
+				dst = __sk_dst_get(sk);
+				if (dst)
+					dst_confirm(dst);
 
 				if (!sock_flag(sk, SOCK_DEAD))
 					/* Wake up lingering close() */
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a233a7ccbc3..c94e4aabe11 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -125,7 +125,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	rcu_read_lock();
 	neigh = dst_get_neighbour_noref(dst);
 	if (neigh) {
-		int res = neigh_output(neigh, skb);
+		int res = dst_neigh_output(dst, neigh, skb);
 
 		rcu_read_unlock();
 		return res;