When same struct dst_entry can be used for many different
neighbours we can not use it for pending confirmations.
Use the new sk_dst_confirm() helper to propagate the
indication from received packets to sock_confirm_neigh().
Reported-by: YueHaibing <yuehaibing@xxxxxxxxxx>
Reported-by: YueHaibing <yuehaibing@xxxxxxxxxx>
Fixes: 5110effee8fd ("net: Do delayed neigh confirmation.")
Fixes: f2bb4bedf35d ("ipv4: Cache output routes in fib_info nexthops.")
Tested-by: YueHaibing <yuehaibing@xxxxxxxxxx>
Signed-off-by: Julian Anastasov <ja@xxxxxx>
Acked-by: Eric Dumazet <edumazet@xxxxxxxxxx>
---
net/ipv4/tcp_input.c | 12 +++---------
net/ipv4/tcp_metrics.c | 7 ++-----
net/ipv4/tcp_output.c | 2 ++
3 files changed, 7 insertions(+), 14 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3de6eba..b3e88bb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3644,11 +3644,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
- if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) {
- struct dst_entry *dst = __sk_dst_get(sk);
- if (dst)
- dst_confirm(dst);
- }
+ if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
+ sk_dst_confirm(sk);
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
@@ -5995,7 +5992,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
break;
case TCP_FIN_WAIT1: {
- struct dst_entry *dst;
int tmo;
/* If we enter the TCP_FIN_WAIT1 state and we are a
@@ -6022,9 +6018,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
tcp_set_state(sk, TCP_FIN_WAIT2);
sk->sk_shutdown |= SEND_SHUTDOWN;
- dst = __sk_dst_get(sk);
- if (dst)
- dst_confirm(dst);
+ sk_dst_confirm(sk);
if (!sock_flag(sk, SOCK_DEAD)) {
/* Wake up lingering close() */
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index b9ed0d5..0f46e5f 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -375,12 +375,10 @@ void tcp_update_metrics(struct sock *sk)
u32 val;
int m;
+ sk_dst_confirm(sk);
if (sysctl_tcp_nometrics_save || !dst)
return;
- if (dst->flags & DST_HOST)
- dst_confirm(dst);
-
rcu_read_lock();
if (icsk->icsk_backoff || !tp->srtt_us) {
/* This session failed to estimate rtt. Why?
@@ -493,11 +491,10 @@ void tcp_init_metrics(struct sock *sk)
struct tcp_metrics_block *tm;
u32 val, crtt = 0; /* cached RTT scaled by 8 */
+ sk_dst_confirm(sk);
if (!dst)
goto reset;
- dst_confirm(dst);
-
rcu_read_lock();
tm = tcp_get_metrics(sk, dst, true);
if (!tm) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 671c695..c1f8a59 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -973,6 +973,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
skb_set_hash_from_sk(skb, sk);
atomic_add(skb->truesize, &sk->sk_wmem_alloc);
+ skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm);
+
/* Build TCP header and checksum it. */
th = (struct tcphdr *)skb->data;
th->source = inet->inet_sport;
--
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
