5 files changed, 38 insertions, 6 deletions

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index ff069f6..335e752 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -771,12 +771,12 @@ 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/rds/connection.c b/net/rds/connection.c
index 378c3a6..14f04139 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 c2a5eef..02d8fd5 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 42f65d4..49f77ef 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 179f1c8..956ead2 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;