Add new skbuff flag to allow protocols to confirm neighbour.
When same struct dst_entry can be used for many different
neighbours we can not use it for pending confirmations.
Add sock_confirm_neigh() helper to confirm the neighbour and
use it for IPv4, IPv6 and VRF before dst_neigh_output.
Signed-off-by: Julian Anastasov <ja@xxxxxx>
Acked-by: Eric Dumazet <edumazet@xxxxxxxxxx>
---
drivers/net/vrf.c | 5 ++++-
include/linux/skbuff.h | 12 ++++++++++++
include/net/sock.h | 14 ++++++++++++++
net/ipv4/ip_output.c | 5 ++++-
net/ipv6/ip6_output.c | 1 +
5 files changed, 35 insertions(+), 2 deletions(-)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 264fc15..630eafd 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -378,6 +378,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk,
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
if (!IS_ERR(neigh)) {
+ sock_confirm_neigh(skb, neigh);
ret = dst_neigh_output(dst, neigh, skb);
rcu_read_unlock_bh();
return ret;
@@ -574,8 +575,10 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
- if (!IS_ERR(neigh))
+ if (!IS_ERR(neigh)) {
+ sock_confirm_neigh(skb, neigh);
ret = dst_neigh_output(dst, neigh, skb);
+ }
rcu_read_unlock_bh();
err:
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6f63b7e..3ac3c3b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -613,6 +613,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1,
* @wifi_acked_valid: wifi_acked was set
* @wifi_acked: whether frame was acked on wifi or not
* @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS
+ * @dst_pending_confirm: need to confirm neighbour
* @napi_id: id of the NAPI struct this skb came from
* @secmark: security marking
* @mark: Generic packet mark
@@ -743,6 +744,7 @@ struct sk_buff {
__u8 csum_level:2;
__u8 csum_bad:1;
+ __u8 dst_pending_confirm:1;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
@@ -3694,6 +3696,16 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb)
return skb->queue_mapping != 0;
}
+static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val)
+{
+ skb->dst_pending_confirm = val;
+}
+
+static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb)
+{
+ return skb->dst_pending_confirm != 0;
+}
+
static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
{
#ifdef CONFIG_XFRM
diff --git a/include/net/sock.h b/include/net/sock.h
index e113786..1bc821e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1821,6 +1821,20 @@ static inline void sk_dst_confirm(struct sock *sk)
sk->sk_dst_pending_confirm = 1;
}
+static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n)
+{
+ if (skb_get_dst_pending_confirm(skb)) {
+ struct sock *sk = skb->sk;
+ unsigned long now = jiffies;
+
+ /* avoid dirtying neighbour */
+ if (n->confirmed != now)
+ n->confirmed = now;
+ if (sk && sk->sk_dst_pending_confirm)
+ sk->sk_dst_pending_confirm = 0;
+ }
+}
+
bool sk_mc_loop(struct sock *sk);
static inline bool sk_can_gso(const struct sock *sk)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fac275c4..27f1db7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -222,7 +222,10 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
if (!IS_ERR(neigh)) {
- int res = dst_neigh_output(dst, neigh, skb);
+ int res;
+
+ sock_confirm_neigh(skb, neigh);
+ res = dst_neigh_output(dst, neigh, skb);
rcu_read_unlock_bh();
return res;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 38122d0..7d90cab 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -119,6 +119,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
if (!IS_ERR(neigh)) {
+ sock_confirm_neigh(skb, neigh);
ret = dst_neigh_output(dst, neigh, skb);
rcu_read_unlock_bh();
return ret;
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
