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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

1 files changed, 179 insertions, 27 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index bdd7eac..27aed1a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -216,6 +216,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	},
 	.use_oif_addrs_only	= 0,
 	.ignore_routes_with_linkdown = 0,
+	.keep_addr_on_down	= 0,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	},
 	.use_oif_addrs_only	= 0,
 	.ignore_routes_with_linkdown = 0,
+	.keep_addr_on_down	= 0,
 };
 
 /* Check if a valid qdisc is available */
@@ -471,18 +473,21 @@ static int inet6_netconf_msgsize_devconf(int type)
 {
 	int size =  NLMSG_ALIGN(sizeof(struct netconfmsg))
 		    + nla_total_size(4);	/* NETCONFA_IFINDEX */
+	bool all = false;
 
-	/* type -1 is used for ALL */
-	if (type == -1 || type == NETCONFA_FORWARDING)
+	if (type == NETCONFA_ALL)
+		all = true;
+
+	if (all || type == NETCONFA_FORWARDING)
 		size += nla_total_size(4);
 #ifdef CONFIG_IPV6_MROUTE
-	if (type == -1 || type == NETCONFA_MC_FORWARDING)
+	if (all || type == NETCONFA_MC_FORWARDING)
 		size += nla_total_size(4);
 #endif
-	if (type == -1 || type == NETCONFA_PROXY_NEIGH)
+	if (all || type == NETCONFA_PROXY_NEIGH)
 		size += nla_total_size(4);
 
-	if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
+	if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
 		size += nla_total_size(4);
 
 	return size;
@@ -495,33 +500,36 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 {
 	struct nlmsghdr  *nlh;
 	struct netconfmsg *ncm;
+	bool all = false;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg),
 			flags);
 	if (!nlh)
 		return -EMSGSIZE;
 
+	if (type == NETCONFA_ALL)
+		all = true;
+
 	ncm = nlmsg_data(nlh);
 	ncm->ncm_family = AF_INET6;
 
 	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
 		goto nla_put_failure;
 
-	/* type -1 is used for ALL */
-	if ((type == -1 || type == NETCONFA_FORWARDING) &&
+	if ((all || type == NETCONFA_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0)
 		goto nla_put_failure;
 #ifdef CONFIG_IPV6_MROUTE
-	if ((type == -1 || type == NETCONFA_MC_FORWARDING) &&
+	if ((all || type == NETCONFA_MC_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
 			devconf->mc_forwarding) < 0)
 		goto nla_put_failure;
 #endif
-	if ((type == -1 || type == NETCONFA_PROXY_NEIGH) &&
+	if ((all || type == NETCONFA_PROXY_NEIGH) &&
 	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0)
 		goto nla_put_failure;
 
-	if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) &&
+	if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) &&
 	    nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 			devconf->ignore_routes_with_linkdown) < 0)
 		goto nla_put_failure;
@@ -607,14 +615,14 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	}
 
 	err = -ENOBUFS;
-	skb = nlmsg_new(inet6_netconf_msgsize_devconf(-1), GFP_ATOMIC);
+	skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC);
 	if (!skb)
 		goto errout;
 
 	err = inet6_netconf_fill_devconf(skb, ifindex, devconf,
 					 NETLINK_CB(in_skb).portid,
 					 nlh->nlmsg_seq, RTM_NEWNETCONF, 0,
-					 -1);
+					 NETCONFA_ALL);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -658,7 +666,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 						       cb->nlh->nlmsg_seq,
 						       RTM_NEWNETCONF,
 						       NLM_F_MULTI,
-						       -1) < 0) {
+						       NETCONFA_ALL) < 0) {
 				rcu_read_unlock();
 				goto done;
 			}
@@ -674,7 +682,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) < 0)
+					       NETCONFA_ALL) < 0)
 			goto done;
 		else
 			h++;
@@ -685,7 +693,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) < 0)
+					       NETCONFA_ALL) < 0)
 			goto done;
 		else
 			h++;
@@ -3168,6 +3176,81 @@ static void addrconf_gre_config(struct net_device *dev)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+/* If the host route is cached on the addr struct make sure it is associated
+ * with the proper table. e.g., enslavement can change and if so the cached
+ * host route needs to move to the new table.
+ */
+static void l3mdev_check_host_rt(struct inet6_dev *idev,
+				  struct inet6_ifaddr *ifp)
+{
+	if (ifp->rt) {
+		u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
+
+		if (tb_id != ifp->rt->rt6i_table->tb6_id) {
+			ip6_del_rt(ifp->rt);
+			ifp->rt = NULL;
+		}
+	}
+}
+#else
+static void l3mdev_check_host_rt(struct inet6_dev *idev,
+				  struct inet6_ifaddr *ifp)
+{
+}
+#endif
+
+static int fixup_permanent_addr(struct inet6_dev *idev,
+				struct inet6_ifaddr *ifp)
+{
+	l3mdev_check_host_rt(idev, ifp);
+
+	if (!ifp->rt) {
+		struct rt6_info *rt;
+
+		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
+		if (unlikely(IS_ERR(rt)))
+			return PTR_ERR(rt);
+
+		ifp->rt = rt;
+	}
+
+	if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
+		addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+				      idev->dev, 0, 0);
+	}
+
+	addrconf_dad_start(ifp);
+
+	return 0;
+}
+
+static void addrconf_permanent_addr(struct net_device *dev)
+{
+	struct inet6_ifaddr *ifp, *tmp;
+	struct inet6_dev *idev;
+
+	idev = __in6_dev_get(dev);
+	if (!idev)
+		return;
+
+	write_lock_bh(&idev->lock);
+
+	list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) {
+		if ((ifp->flags & IFA_F_PERMANENT) &&
+		    fixup_permanent_addr(idev, ifp) < 0) {
+			write_unlock_bh(&idev->lock);
+			ipv6_del_addr(ifp);
+			write_lock_bh(&idev->lock);
+
+			net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n",
+					     idev->dev->name, &ifp->addr);
+		}
+	}
+
+	write_unlock_bh(&idev->lock);
+}
+
 static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			   void *ptr)
 {
@@ -3253,6 +3336,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			run_pending = 1;
 		}
 
+		/* restore routes for permanent addresses */
+		addrconf_permanent_addr(dev);
+
 		switch (dev->type) {
 #if IS_ENABLED(CONFIG_IPV6_SIT)
 		case ARPHRD_SIT:
@@ -3356,7 +3442,10 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 {
 	struct net *net = dev_net(dev);
 	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifa;
+	struct inet6_ifaddr *ifa, *tmp;
+	struct list_head del_list;
+	int _keep_addr;
+	bool keep_addr;
 	int state, i;
 
 	ASSERT_RTNL();
@@ -3383,6 +3472,16 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
 	}
 
+	/* aggregate the system setting and interface setting */
+	_keep_addr = net->ipv6.devconf_all->keep_addr_on_down;
+	if (!_keep_addr)
+		_keep_addr = idev->cnf.keep_addr_on_down;
+
+	/* combine the user config with event to determine if permanent
+	 * addresses are to be removed from address hash table
+	 */
+	keep_addr = !(how || _keep_addr <= 0);
+
 	/* Step 2: clear hash table */
 	for (i = 0; i < IN6_ADDR_HSIZE; i++) {
 		struct hlist_head *h = &inet6_addr_lst[i];
@@ -3391,9 +3490,15 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 restart:
 		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
 			if (ifa->idev == idev) {
-				hlist_del_init_rcu(&ifa->addr_lst);
 				addrconf_del_dad_work(ifa);
-				goto restart;
+				/* combined flag + permanent flag decide if
+				 * address is retained on a down event
+				 */
+				if (!keep_addr ||
+				    !(ifa->flags & IFA_F_PERMANENT)) {
+					hlist_del_init_rcu(&ifa->addr_lst);
+					goto restart;
+				}
 			}
 		}
 		spin_unlock_bh(&addrconf_hash_lock);
@@ -3427,31 +3532,53 @@ restart:
 		write_lock_bh(&idev->lock);
 	}
 
-	while (!list_empty(&idev->addr_list)) {
-		ifa = list_first_entry(&idev->addr_list,
-				       struct inet6_ifaddr, if_list);
-		addrconf_del_dad_work(ifa);
+	/* re-combine the user config with event to determine if permanent
+	 * addresses are to be removed from the interface list
+	 */
+	keep_addr = (!how && _keep_addr > 0);
 
-		list_del(&ifa->if_list);
+	INIT_LIST_HEAD(&del_list);
+	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
+		addrconf_del_dad_work(ifa);
 
 		write_unlock_bh(&idev->lock);
-
 		spin_lock_bh(&ifa->lock);
-		state = ifa->state;
-		ifa->state = INET6_IFADDR_STATE_DEAD;
+
+		if (keep_addr && (ifa->flags & IFA_F_PERMANENT)) {
+			/* set state to skip the notifier below */
+			state = INET6_IFADDR_STATE_DEAD;
+			ifa->state = 0;
+			if (!(ifa->flags & IFA_F_NODAD))
+				ifa->flags |= IFA_F_TENTATIVE;
+		} else {
+			state = ifa->state;
+			ifa->state = INET6_IFADDR_STATE_DEAD;
+
+			list_del(&ifa->if_list);
+			list_add(&ifa->if_list, &del_list);
+		}
+
 		spin_unlock_bh(&ifa->lock);
 
 		if (state != INET6_IFADDR_STATE_DEAD) {
 			__ipv6_ifa_notify(RTM_DELADDR, ifa);
 			inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
 		}
-		in6_ifa_put(ifa);
 
 		write_lock_bh(&idev->lock);
 	}
 
 	write_unlock_bh(&idev->lock);
 
+	/* now clean up addresses to be removed */
+	while (!list_empty(&del_list)) {
+		ifa = list_first_entry(&del_list,
+				       struct inet6_ifaddr, if_list);
+		list_del(&ifa->if_list);
+
+		in6_ifa_put(ifa);
+	}
+
 	/* Step 5: Discard anycast and multicast list */
 	if (how) {
 		ipv6_ac_destroy_dev(idev);
@@ -4714,6 +4841,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown;
 	/* we omit DEVCONF_STABLE_SECRET for now */
 	array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only;
+	array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast;
+	array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na;
+	array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -5788,6 +5918,28 @@ static struct addrconf_sysctl_table
 			.proc_handler	= addrconf_sysctl_ignore_routes_with_linkdown,
 		},
 		{
+			.procname	= "drop_unicast_in_l2_multicast",
+			.data		= &ipv6_devconf.drop_unicast_in_l2_multicast,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
+			.procname	= "drop_unsolicited_na",
+			.data		= &ipv6_devconf.drop_unsolicited_na,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
+			.procname       = "keep_addr_on_down",
+			.data           = &ipv6_devconf.keep_addr_on_down,
+			.maxlen         = sizeof(int),
+			.mode           = 0644,
+			.proc_handler   = proc_dointvec,
+
+		},
+		{
 			/* sentinel */
 		}
 	},