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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

8 files changed, 97 insertions, 33 deletions

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index e497dfbee43..3ae2bfd3101 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -108,12 +108,14 @@ void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 	unsigned char *prev_tail;
 
 	prev_tail = skb_tail_pointer(skb);
-	*nlh = NLMSG_NEW(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
-			len, NLM_F_MULTI);
+	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
+			 len, NLM_F_MULTI);
+	if (!*nlh)
+		goto out_nlmsg_trim;
 	(*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail;
-	return NLMSG_DATA(*nlh);
+	return nlmsg_data(*nlh);
 
-nlmsg_failure:
+out_nlmsg_trim:
 	nlmsg_trim(skb, prev_tail);
 	return NULL;
 }
@@ -171,8 +173,11 @@ static void ibnl_rcv(struct sk_buff *skb)
 
 int __init ibnl_init(void)
 {
-	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, 0, ibnl_rcv,
-				    NULL, THIS_MODULE);
+	struct netlink_kernel_cfg cfg = {
+		.input	= ibnl_rcv,
+	};
+
+	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, THIS_MODULE, &cfg);
 	if (!nls) {
 		pr_warn("Failed to create netlink socket\n");
 		return -ENOMEM;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index 740dcc065cf..77b6b182778 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -1374,7 +1374,7 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 		goto reject;
 	}
 	dst = &rt->dst;
-	l2t = t3_l2t_get(tdev, dst, NULL);
+	l2t = t3_l2t_get(tdev, dst, NULL, &req->peer_ip);
 	if (!l2t) {
 		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
 		       __func__);
@@ -1942,7 +1942,8 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		goto fail3;
 	}
 	ep->dst = &rt->dst;
-	ep->l2t = t3_l2t_get(ep->com.tdev, ep->dst, NULL);
+	ep->l2t = t3_l2t_get(ep->com.tdev, ep->dst, NULL,
+			     &cm_id->remote_addr.sin_addr.s_addr);
 	if (!ep->l2t) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
 		err = -ENOMEM;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 3530c41fcd1..a07b774e786 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -718,26 +718,53 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 	return ret;
 }
 
+struct mlx4_ib_steering {
+	struct list_head list;
+	u64 reg_id;
+	union ib_gid gid;
+};
+
 static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
 	int err;
 	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
 	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
+	u64 reg_id;
+	struct mlx4_ib_steering *ib_steering = NULL;
+
+	if (mdev->dev->caps.steering_mode ==
+	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		ib_steering = kmalloc(sizeof(*ib_steering), GFP_KERNEL);
+		if (!ib_steering)
+			return -ENOMEM;
+	}
 
-	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw,
-				    !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
-				    MLX4_PROT_IB_IPV6);
+	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
+				    !!(mqp->flags &
+				       MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
+				    MLX4_PROT_IB_IPV6, &reg_id);
 	if (err)
-		return err;
+		goto err_malloc;
 
 	err = add_gid_entry(ibqp, gid);
 	if (err)
 		goto err_add;
 
+	if (ib_steering) {
+		memcpy(ib_steering->gid.raw, gid->raw, 16);
+		ib_steering->reg_id = reg_id;
+		mutex_lock(&mqp->mutex);
+		list_add(&ib_steering->list, &mqp->steering_rules);
+		mutex_unlock(&mqp->mutex);
+	}
 	return 0;
 
 err_add:
-	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
+	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
+			      MLX4_PROT_IB_IPV6, reg_id);
+err_malloc:
+	kfree(ib_steering);
+
 	return err;
 }
 
@@ -765,9 +792,30 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	u8 mac[6];
 	struct net_device *ndev;
 	struct mlx4_ib_gid_entry *ge;
+	u64 reg_id = 0;
+
+	if (mdev->dev->caps.steering_mode ==
+	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		struct mlx4_ib_steering *ib_steering;
+
+		mutex_lock(&mqp->mutex);
+		list_for_each_entry(ib_steering, &mqp->steering_rules, list) {
+			if (!memcmp(ib_steering->gid.raw, gid->raw, 16)) {
+				list_del(&ib_steering->list);
+				break;
+			}
+		}
+		mutex_unlock(&mqp->mutex);
+		if (&ib_steering->list == &mqp->steering_rules) {
+			pr_err("Couldn't find reg_id for mgid. Steering rule is left attached\n");
+			return -EINVAL;
+		}
+		reg_id = ib_steering->reg_id;
+		kfree(ib_steering);
+	}
 
-	err = mlx4_multicast_detach(mdev->dev,
-				    &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
+	err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
+				    MLX4_PROT_IB_IPV6, reg_id);
 	if (err)
 		return err;
 
@@ -1111,7 +1159,8 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 			sprintf(name, "mlx4-ib-%d-%d@%s",
 				i, j, dev->pdev->bus->name);
 			/* Set IRQ for specific name (per ring) */
-			if (mlx4_assign_eq(dev, name, &ibdev->eq_table[eq])) {
+			if (mlx4_assign_eq(dev, name, NULL,
+					   &ibdev->eq_table[eq])) {
 				/* Use legacy (same as mlx4_en driver) */
 				pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq);
 				ibdev->eq_table[eq] =
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index ff36655d23d..42df4f7a6a5 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -163,6 +163,7 @@ struct mlx4_ib_qp {
 	u8			state;
 	int			mlx_type;
 	struct list_head	gid_list;
+	struct list_head	steering_rules;
 };
 
 struct mlx4_ib_srq {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 8d4ed24aef9..6af19f6c2b1 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -495,6 +495,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 	INIT_LIST_HEAD(&qp->gid_list);
+	INIT_LIST_HEAD(&qp->steering_rules);
 
 	qp->state	 = IB_QPS_RESET;
 	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 014504d8e43..1ca732201f3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1397,7 +1397,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb,
 	int e = skb_queue_empty(&priv->cm.skb_queue);
 
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 3974c290b66..bbee4b2d7a1 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -715,7 +715,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	rcu_read_lock();
 	if (likely(skb_dst(skb))) {
-		n = dst_get_neighbour_noref(skb_dst(skb));
+		n = dst_neigh_lookup_skb(skb_dst(skb), skb);
 		if (!n) {
 			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
@@ -797,6 +797,8 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 unlock:
+	if (n)
+		neigh_release(n);
 	rcu_read_unlock();
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 20ebc6fd1bb..7cecb16d3d4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -658,9 +658,15 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	struct dst_entry *dst = skb_dst(skb);
 	struct ipoib_mcast *mcast;
+	struct neighbour *n;
 	unsigned long flags;
 
+	n = NULL;
+	if (dst)
+		n = dst_neigh_lookup_skb(dst, skb);
+
 	spin_lock_irqsave(&priv->lock, flags);
 
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)		||
@@ -715,29 +721,28 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
 
 out:
 	if (mcast && mcast->ah) {
-		struct dst_entry *dst = skb_dst(skb);
-		struct neighbour *n = NULL;
-
-		rcu_read_lock();
-		if (dst)
-			n = dst_get_neighbour_noref(dst);
-		if (n && !*to_ipoib_neigh(n)) {
-			struct ipoib_neigh *neigh = ipoib_neigh_alloc(n,
-								      skb->dev);
-
-			if (neigh) {
-				kref_get(&mcast->ah->ref);
-				neigh->ah	= mcast->ah;
-				list_add_tail(&neigh->list, &mcast->neigh_list);
+		if (n) {
+			if (!*to_ipoib_neigh(n)) {
+				struct ipoib_neigh *neigh;
+
+				neigh = ipoib_neigh_alloc(n, skb->dev);
+				if (neigh) {
+					kref_get(&mcast->ah->ref);
+					neigh->ah	= mcast->ah;
+					list_add_tail(&neigh->list,
+						      &mcast->neigh_list);
+				}
 			}
+			neigh_release(n);
 		}
-		rcu_read_unlock();
 		spin_unlock_irqrestore(&priv->lock, flags);
 		ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
 		return;
 	}
 
 unlock:
+	if (n)
+		neigh_release(n);
 	spin_unlock_irqrestore(&priv->lock, flags);
 }