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

Pull networking updates from Davic Miller:

 1) Support busy polling generically, for all NAPI drivers.  From Eric
    Dumazet.

 2) Add byte/packet counter support to nft_ct, from Floriani Westphal.

 3) Add RSS/XPS support to mvneta driver, from Gregory Clement.

 4) Implement IPV6_HDRINCL socket option for raw sockets, from Hannes
    Frederic Sowa.

 5) Add support for T6 adapter to cxgb4 driver, from Hariprasad Shenai.

 6) Add support for VLAN device bridging to mlxsw switch driver, from
    Ido Schimmel.

 7) Add driver for Netronome NFP4000/NFP6000, from Jakub Kicinski.

 8) Provide hwmon interface to mlxsw switch driver, from Jiri Pirko.

 9) Reorganize wireless drivers into per-vendor directories just like we
    do for ethernet drivers.  From Kalle Valo.

10) Provide a way for administrators "destroy" connected sockets via the
    SOCK_DESTROY socket netlink diag operation.  From Lorenzo Colitti.

11) Add support to add/remove multicast routes via netlink, from Nikolay
    Aleksandrov.

12) Make TCP keepalive settings per-namespace, from Nikolay Borisov.

13) Add forwarding and packet duplication facilities to nf_tables, from
    Pablo Neira Ayuso.

14) Dead route support in MPLS, from Roopa Prabhu.

15) TSO support for thunderx chips, from Sunil Goutham.

16) Add driver for IBM's System i/p VNIC protocol, from Thomas Falcon.

17) Rationalize, consolidate, and more completely document the checksum
    offloading facilities in the networking stack.  From Tom Herbert.

18) Support aborting an ongoing scan in mac80211/cfg80211, from
    Vidyullatha Kanchanapally.

19) Use per-bucket spinlock for bpf hash facility, from Tom Leiming.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1375 commits)
  net: bnxt: always return values from _bnxt_get_max_rings
  net: bpf: reject invalid shifts
  phonet: properly unshare skbs in phonet_rcv()
  dwc_eth_qos: Fix dma address for multi-fragment skbs
  phy: remove an unneeded condition
  mdio: remove an unneed condition
  mdio_bus: NULL dereference on allocation error
  net: Fix typo in netdev_intersect_features
  net: freescale: mac-fec: Fix build error from phy_device API change
  net: freescale: ucc_geth: Fix build error from phy_device API change
  bonding: Prevent IPv6 link local address on enslaved devices
  IB/mlx5: Add flow steering support
  net/mlx5_core: Export flow steering API
  net/mlx5_core: Make ipv4/ipv6 location more clear
  net/mlx5_core: Enable flow steering support for the IB driver
  net/mlx5_core: Initialize namespaces only when supported by device
  net/mlx5_core: Set priority attributes
  net/mlx5_core: Connect flow tables
  net/mlx5_core: Introduce modify flow table command
  net/mlx5_core: Managing root flow table
  ...

1 files changed, 157 insertions, 28 deletions

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c32fc411a911..b18c5ed42d95 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -98,22 +98,15 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 }
 EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
 
-static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
-					     struct sk_buff *skb, bool bos)
+static u32 mpls_multipath_hash(struct mpls_route *rt,
+			       struct sk_buff *skb, bool bos)
 {
 	struct mpls_entry_decoded dec;
 	struct mpls_shim_hdr *hdr;
 	bool eli_seen = false;
 	int label_index;
-	int nh_index = 0;
 	u32 hash = 0;
 
-	/* No need to look further into packet if there's only
-	 * one path
-	 */
-	if (rt->rt_nhn == 1)
-		goto out;
-
 	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
 	     label_index++) {
 		if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
@@ -167,7 +160,38 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 		}
 	}
 
-	nh_index = hash % rt->rt_nhn;
+	return hash;
+}
+
+static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
+					     struct sk_buff *skb, bool bos)
+{
+	int alive = ACCESS_ONCE(rt->rt_nhn_alive);
+	u32 hash = 0;
+	int nh_index = 0;
+	int n = 0;
+
+	/* No need to look further into packet if there's only
+	 * one path
+	 */
+	if (rt->rt_nhn == 1)
+		goto out;
+
+	if (alive <= 0)
+		return NULL;
+
+	hash = mpls_multipath_hash(rt, skb, bos);
+	nh_index = hash % alive;
+	if (alive == rt->rt_nhn)
+		goto out;
+	for_nexthops(rt) {
+		if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+			continue;
+		if (n == nh_index)
+			return nh;
+		n++;
+	} endfor_nexthops(rt);
+
 out:
 	return &rt->rt_nh[nh_index];
 }
@@ -373,6 +397,7 @@ static struct mpls_route *mpls_rt_alloc(int num_nh, u8 max_alen)
 		     GFP_KERNEL);
 	if (rt) {
 		rt->rt_nhn = num_nh;
+		rt->rt_nhn_alive = num_nh;
 		rt->rt_max_alen = max_alen_aligned;
 	}
 
@@ -548,6 +573,16 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
 
 	RCU_INIT_POINTER(nh->nh_dev, dev);
 
+	if (!(dev->flags & IFF_UP)) {
+		nh->nh_flags |= RTNH_F_DEAD;
+	} else {
+		unsigned int flags;
+
+		flags = dev_get_flags(dev);
+		if (!(flags & (IFF_RUNNING | IFF_LOWER_UP)))
+			nh->nh_flags |= RTNH_F_LINKDOWN;
+	}
+
 	return 0;
 
 errout:
@@ -582,6 +617,9 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
 	if (err)
 		goto errout;
 
+	if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+		rt->rt_nhn_alive--;
+
 	return 0;
 
 errout:
@@ -589,8 +627,8 @@ errout:
 }
 
 static int mpls_nh_build(struct net *net, struct mpls_route *rt,
-			 struct mpls_nh *nh, int oif,
-			 struct nlattr *via, struct nlattr *newdst)
+			 struct mpls_nh *nh, int oif, struct nlattr *via,
+			 struct nlattr *newdst)
 {
 	int err = -ENOMEM;
 
@@ -694,11 +732,13 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg,
 		}
 
 		err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
-				    rtnh->rtnh_ifindex, nla_via,
-				    nla_newdst);
+				    rtnh->rtnh_ifindex, nla_via, nla_newdst);
 		if (err)
 			goto errout;
 
+		if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+			rt->rt_nhn_alive--;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 		nhs++;
 	} endfor_nexthops(rt);
@@ -888,34 +928,74 @@ free:
 	return ERR_PTR(err);
 }
 
-static void mpls_ifdown(struct net_device *dev)
+static void mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	struct mpls_dev *mdev;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+
 		if (!rt)
 			continue;
-		for_nexthops(rt) {
+
+		change_nexthops(rt) {
 			if (rtnl_dereference(nh->nh_dev) != dev)
 				continue;
-			nh->nh_dev = NULL;
+			switch (event) {
+			case NETDEV_DOWN:
+			case NETDEV_UNREGISTER:
+				nh->nh_flags |= RTNH_F_DEAD;
+				/* fall through */
+			case NETDEV_CHANGE:
+				nh->nh_flags |= RTNH_F_LINKDOWN;
+				ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+				break;
+			}
+			if (event == NETDEV_UNREGISTER)
+				RCU_INIT_POINTER(nh->nh_dev, NULL);
 		} endfor_nexthops(rt);
 	}
 
-	mdev = mpls_dev_get(dev);
-	if (!mdev)
-		return;
 
-	mpls_dev_sysctl_unregister(mdev);
+	return;
+}
+
+static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
+{
+	struct mpls_route __rcu **platform_label;
+	struct net *net = dev_net(dev);
+	unsigned index;
+	int alive;
+
+	platform_label = rtnl_dereference(net->mpls.platform_label);
+	for (index = 0; index < net->mpls.platform_labels; index++) {
+		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+
+		if (!rt)
+			continue;
+
+		alive = 0;
+		change_nexthops(rt) {
+			struct net_device *nh_dev =
+				rtnl_dereference(nh->nh_dev);
+
+			if (!(nh->nh_flags & nh_flags)) {
+				alive++;
+				continue;
+			}
+			if (nh_dev != dev)
+				continue;
+			alive++;
+			nh->nh_flags &= ~nh_flags;
+		} endfor_nexthops(rt);
 
-	RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+		ACCESS_ONCE(rt->rt_nhn_alive) = alive;
+	}
 
-	kfree_rcu(mdev, rcu);
+	return;
 }
 
 static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
@@ -923,9 +1003,9 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct mpls_dev *mdev;
+	unsigned int flags;
 
-	switch(event) {
-	case NETDEV_REGISTER:
+	if (event == NETDEV_REGISTER) {
 		/* For now just support ethernet devices */
 		if ((dev->type == ARPHRD_ETHER) ||
 		    (dev->type == ARPHRD_LOOPBACK)) {
@@ -933,10 +1013,39 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 			if (IS_ERR(mdev))
 				return notifier_from_errno(PTR_ERR(mdev));
 		}
-		break;
+		return NOTIFY_OK;
+	}
 
+	mdev = mpls_dev_get(dev);
+	if (!mdev)
+		return NOTIFY_OK;
+
+	switch (event) {
+	case NETDEV_DOWN:
+		mpls_ifdown(dev, event);
+		break;
+	case NETDEV_UP:
+		flags = dev_get_flags(dev);
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
+		else
+			mpls_ifup(dev, RTNH_F_DEAD);
+		break;
+	case NETDEV_CHANGE:
+		flags = dev_get_flags(dev);
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
+		else
+			mpls_ifdown(dev, event);
+		break;
 	case NETDEV_UNREGISTER:
-		mpls_ifdown(dev);
+		mpls_ifdown(dev, event);
+		mdev = mpls_dev_get(dev);
+		if (mdev) {
+			mpls_dev_sysctl_unregister(mdev);
+			RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+			kfree_rcu(mdev, rcu);
+		}
 		break;
 	case NETDEV_CHANGENAME:
 		mdev = mpls_dev_get(dev);
@@ -1252,9 +1361,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		dev = rtnl_dereference(nh->nh_dev);
 		if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
 			goto nla_put_failure;
+		if (nh->nh_flags & RTNH_F_LINKDOWN)
+			rtm->rtm_flags |= RTNH_F_LINKDOWN;
+		if (nh->nh_flags & RTNH_F_DEAD)
+			rtm->rtm_flags |= RTNH_F_DEAD;
 	} else {
 		struct rtnexthop *rtnh;
 		struct nlattr *mp;
+		int dead = 0;
+		int linkdown = 0;
 
 		mp = nla_nest_start(skb, RTA_MULTIPATH);
 		if (!mp)
@@ -1268,6 +1383,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			dev = rtnl_dereference(nh->nh_dev);
 			if (dev)
 				rtnh->rtnh_ifindex = dev->ifindex;
+			if (nh->nh_flags & RTNH_F_LINKDOWN) {
+				rtnh->rtnh_flags |= RTNH_F_LINKDOWN;
+				linkdown++;
+			}
+			if (nh->nh_flags & RTNH_F_DEAD) {
+				rtnh->rtnh_flags |= RTNH_F_DEAD;
+				dead++;
+			}
+
 			if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST,
 							    nh->nh_labels,
 							    nh->nh_label))
@@ -1282,6 +1406,11 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
 		} endfor_nexthops(rt);
 
+		if (linkdown == rt->rt_nhn)
+			rtm->rtm_flags |= RTNH_F_LINKDOWN;
+		if (dead == rt->rt_nhn)
+			rtm->rtm_flags |= RTNH_F_DEAD;
+
 		nla_nest_end(skb, mp);
 	}