Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

The dwmac-socfpga.c conflict was a case of a bug fix overlapping
changes in net-next to handle an error pointer differently.

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

9 files changed, 50 insertions, 17 deletions

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 263710259774..af150b43b214 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -886,12 +886,12 @@ EXPORT_SYMBOL(gue_build_header);
 
 #ifdef CONFIG_NET_FOU_IP_TUNNELS
 
-static const struct ip_tunnel_encap_ops __read_mostly fou_iptun_ops = {
+static const struct ip_tunnel_encap_ops fou_iptun_ops = {
 	.encap_hlen = fou_encap_hlen,
 	.build_header = fou_build_header,
 };
 
-static const struct ip_tunnel_encap_ops __read_mostly gue_iptun_ops = {
+static const struct ip_tunnel_encap_ops gue_iptun_ops = {
 	.encap_hlen = gue_encap_hlen,
 	.build_header = gue_build_header,
 };
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index b77f5e84c623..8986e63f3bda 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -113,10 +113,6 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 	int min_headroom;
 	int err;
 
-	skb = udp_tunnel_handle_offloads(skb, csum);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr)
 			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
@@ -131,6 +127,10 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 	if (unlikely(!skb))
 		return -ENOMEM;
 
+	skb = udp_tunnel_handle_offloads(skb, csum);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
 	gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len);
 	geneve_build_header(gnvh, tun_flags, vni, opt_len, opt);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e662d85d1635..8c8d7e06b72f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2994,6 +2994,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	rcu_read_unlock();
 #endif
 
+	/* Do not fool tcpdump (if any), clean our debris */
+	skb->tstamp.tv64 = 0;
 	return skb;
 }
 EXPORT_SYMBOL(tcp_make_synack);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index b53148444e15..ed9d681207fa 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -288,8 +288,7 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p,
 static void vti6_dev_uninit(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct vti6_net *ip6n = net_generic(t->net, vti6_net_id);
 
 	if (dev == ip6n->fb_tnl_dev)
 		RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 378c3a6acf84..14f041398ca1 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -130,7 +130,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	rcu_read_lock();
 	conn = rds_conn_lookup(head, laddr, faddr, trans);
 	if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
-	    !is_outgoing) {
+	    laddr == faddr && !is_outgoing) {
 		/* This is a looped back IB connection, and we're
 		 * called by the code handling the incoming connect.
 		 * We need a second connection object into which we
@@ -193,6 +193,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	}
 
 	atomic_set(&conn->c_state, RDS_CONN_DOWN);
+	conn->c_send_gen = 0;
 	conn->c_reconnect_jiffies = 0;
 	INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker);
 	INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker);
diff --git a/net/rds/rds.h b/net/rds/rds.h
index c3f2855c3d84..0d41155a2258 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -110,6 +110,7 @@ struct rds_connection {
 	void			*c_transport_data;
 
 	atomic_t		c_state;
+	unsigned long		c_send_gen;
 	unsigned long		c_flags;
 	unsigned long		c_reconnect_jiffies;
 	struct delayed_work	c_send_w;
diff --git a/net/rds/send.c b/net/rds/send.c
index 44672befc0ee..e9430f537f9c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -140,8 +140,11 @@ int rds_send_xmit(struct rds_connection *conn)
 	struct scatterlist *sg;
 	int ret = 0;
 	LIST_HEAD(to_be_dropped);
+	int batch_count;
+	unsigned long send_gen = 0;
 
 restart:
+	batch_count = 0;
 
 	/*
 	 * sendmsg calls here after having queued its message on the send
@@ -157,6 +160,17 @@ restart:
 	}
 
 	/*
+	 * we record the send generation after doing the xmit acquire.
+	 * if someone else manages to jump in and do some work, we'll use
+	 * this to avoid a goto restart farther down.
+	 *
+	 * The acquire_in_xmit() check above ensures that only one
+	 * caller can increment c_send_gen at any time.
+	 */
+	conn->c_send_gen++;
+	send_gen = conn->c_send_gen;
+
+	/*
 	 * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT,
 	 * we do the opposite to avoid races.
 	 */
@@ -202,6 +216,16 @@ restart:
 		if (!rm) {
 			unsigned int len;
 
+			batch_count++;
+
+			/* we want to process as big a batch as we can, but
+			 * we also want to avoid softlockups.  If we've been
+			 * through a lot of messages, lets back off and see
+			 * if anyone else jumps in
+			 */
+			if (batch_count >= 1024)
+				goto over_batch;
+
 			spin_lock_irqsave(&conn->c_lock, flags);
 
 			if (!list_empty(&conn->c_send_queue)) {
@@ -357,9 +381,9 @@ restart:
 		}
 	}
 
+over_batch:
 	if (conn->c_trans->xmit_complete)
 		conn->c_trans->xmit_complete(conn);
-
 	release_in_xmit(conn);
 
 	/* Nuke any messages we decided not to retransmit. */
@@ -380,10 +404,15 @@ restart:
 	 * If the transport cannot continue (i.e ret != 0), then it must
 	 * call us when more room is available, such as from the tx
 	 * completion handler.
+	 *
+	 * We have an extra generation check here so that if someone manages
+	 * to jump in after our release_in_xmit, we'll see that they have done
+	 * some work and we will skip our goto
 	 */
 	if (ret == 0) {
 		smp_mb();
-		if (!list_empty(&conn->c_send_queue)) {
+		if (!list_empty(&conn->c_send_queue) &&
+		    send_gen == conn->c_send_gen) {
 			rds_stats_inc(s_send_lock_queue_raced);
 			goto restart;
 		}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 179f1c8c0d8b..956ead2cab9a 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -560,8 +560,8 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 tfifo_dequeue:
 	skb = __skb_dequeue(&sch->q);
 	if (skb) {
-deliver:
 		qdisc_qstats_backlog_dec(sch, skb);
+deliver:
 		qdisc_unthrottled(sch);
 		qdisc_bstats_update(sch, skb);
 		return skb;
@@ -578,6 +578,7 @@ deliver:
 			rb_erase(p, &q->t_root);
 
 			sch->q.qlen--;
+			qdisc_qstats_backlog_dec(sch, skb);
 			skb->next = NULL;
 			skb->prev = NULL;
 			skb->tstamp = netem_skb_cb(skb)->tstamp_save;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 85d1d4764612..526c4feb3b50 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -238,11 +238,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		skb->sp->xvec[skb->sp->len++] = x;
 
-		if (xfrm_tunnel_check(skb, x, family)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
-			goto drop;
-		}
-
 		spin_lock(&x->lock);
 		if (unlikely(x->km.state == XFRM_STATE_ACQ)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
@@ -271,6 +266,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		spin_unlock(&x->lock);
 
+		if (xfrm_tunnel_check(skb, x, family)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+			goto drop;
+		}
+
 		seq_hi = htonl(xfrm_replay_seqhi(x, seq));
 
 		XFRM_SKB_CB(skb)->seq.input.low = seq;