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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 200 insertions, 181 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8a1c846d3df9..a0ae1c9d37df 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -152,11 +152,13 @@ static void ipv6_regen_rndid(struct inet6_dev *idev);
 static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
 
 static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
-static int ipv6_count_addresses(struct inet6_dev *idev);
+static int ipv6_count_addresses(const struct inet6_dev *idev);
 static int ipv6_generate_stable_address(struct in6_addr *addr,
 					u8 dad_count,
 					const struct inet6_dev *idev);
 
+#define IN6_ADDR_HSIZE_SHIFT	8
+#define IN6_ADDR_HSIZE		(1 << IN6_ADDR_HSIZE_SHIFT)
 /*
  *	Configured unicast address hash table
  */
@@ -192,8 +194,6 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
 
 static void inet6_prefix_notify(int event, struct inet6_dev *idev,
 				struct prefix_info *pinfo);
-static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
-			       struct net_device *dev);
 
 static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.forwarding		= 0,
@@ -231,7 +231,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.proxy_ndp		= 0,
 	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
 	.disable_ipv6		= 0,
-	.accept_dad		= 1,
+	.accept_dad		= 0,
 	.suppress_frag_ndisc	= 1,
 	.accept_ra_mtu		= 1,
 	.stable_secret		= {
@@ -303,10 +303,10 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.disable_policy		= 0,
 };
 
-/* Check if a valid qdisc is available */
-static inline bool addrconf_qdisc_ok(const struct net_device *dev)
+/* Check if link is ready: is it up and is a valid qdisc available */
+static inline bool addrconf_link_ready(const struct net_device *dev)
 {
-	return !qdisc_tx_is_noop(dev);
+	return netif_oper_up(dev) && !qdisc_tx_is_noop(dev);
 }
 
 static void addrconf_del_rs_timer(struct inet6_dev *idev)
@@ -451,7 +451,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 
 	ndev->token = in6addr_any;
 
-	if (netif_running(dev) && addrconf_qdisc_ok(dev))
+	if (netif_running(dev) && addrconf_link_ready(dev))
 		ndev->if_flags |= IF_READY;
 
 	ipv6_mc_init_dev(ndev);
@@ -616,23 +616,23 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX+1];
+	struct inet6_dev *in6_dev = NULL;
+	struct net_device *dev = NULL;
 	struct netconfmsg *ncm;
 	struct sk_buff *skb;
 	struct ipv6_devconf *devconf;
-	struct inet6_dev *in6_dev;
-	struct net_device *dev;
 	int ifindex;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
 			  devconf_ipv6_policy, extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
-	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
-		goto errout;
+		return -EINVAL;
 
+	err = -EINVAL;
 	ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]);
 	switch (ifindex) {
 	case NETCONFA_IFINDEX_ALL:
@@ -642,10 +642,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 		devconf = net->ipv6.devconf_dflt;
 		break;
 	default:
-		dev = __dev_get_by_index(net, ifindex);
+		dev = dev_get_by_index(net, ifindex);
 		if (!dev)
-			goto errout;
-		in6_dev = __in6_dev_get(dev);
+			return -EINVAL;
+		in6_dev = in6_dev_get(dev);
 		if (!in6_dev)
 			goto errout;
 		devconf = &in6_dev->cnf;
@@ -653,7 +653,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	}
 
 	err = -ENOBUFS;
-	skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC);
+	skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL);
 	if (!skb)
 		goto errout;
 
@@ -669,6 +669,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	}
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout:
+	if (in6_dev)
+		in6_dev_put(in6_dev);
+	if (dev)
+		dev_put(dev);
 	return err;
 }
 
@@ -945,12 +949,50 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp)
 			break;
 	}
 
-	list_add_tail(&ifp->if_list, p);
+	list_add_tail_rcu(&ifp->if_list, p);
 }
 
-static u32 inet6_addr_hash(const struct in6_addr *addr)
+static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr)
 {
-	return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT);
+	u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+
+	return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
+}
+
+static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
+			       struct net_device *dev, unsigned int hash)
+{
+	struct inet6_ifaddr *ifp;
+
+	hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) {
+		if (!net_eq(dev_net(ifp->idev->dev), net))
+			continue;
+		if (ipv6_addr_equal(&ifp->addr, addr)) {
+			if (!dev || ifp->idev->dev == dev)
+				return true;
+		}
+	}
+	return false;
+}
+
+static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa)
+{
+	unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr);
+	int err = 0;
+
+	spin_lock(&addrconf_hash_lock);
+
+	/* Ignore adding duplicate addresses on an interface */
+	if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) {
+		ADBG("ipv6_add_addr: already assigned\n");
+		err = -EEXIST;
+	} else {
+		hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
+	}
+
+	spin_unlock(&addrconf_hash_lock);
+
+	return err;
 }
 
 /* On success it returns ifp with increased reference count */
@@ -958,13 +1000,13 @@ static u32 inet6_addr_hash(const struct in6_addr *addr)
 static struct inet6_ifaddr *
 ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	      const struct in6_addr *peer_addr, int pfxlen,
-	      int scope, u32 flags, u32 valid_lft, u32 prefered_lft)
+	      int scope, u32 flags, u32 valid_lft, u32 prefered_lft,
+	      bool can_block, struct netlink_ext_ack *extack)
 {
+	gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC;
 	struct net *net = dev_net(idev->dev);
 	struct inet6_ifaddr *ifa = NULL;
-	struct rt6_info *rt;
-	struct in6_validator_info i6vi;
-	unsigned int hash;
+	struct rt6_info *rt = NULL;
 	int err = 0;
 	int addr_type = ipv6_addr_type(addr);
 
@@ -974,42 +1016,33 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	     addr_type & IPV6_ADDR_LOOPBACK))
 		return ERR_PTR(-EADDRNOTAVAIL);
 
-	rcu_read_lock_bh();
-
-	in6_dev_hold(idev);
-
 	if (idev->dead) {
 		err = -ENODEV;			/*XXX*/
-		goto out2;
+		goto out;
 	}
 
 	if (idev->cnf.disable_ipv6) {
 		err = -EACCES;
-		goto out2;
-	}
-
-	i6vi.i6vi_addr = *addr;
-	i6vi.i6vi_dev = idev;
-	rcu_read_unlock_bh();
-
-	err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi);
-
-	rcu_read_lock_bh();
-	err = notifier_to_errno(err);
-	if (err)
-		goto out2;
-
-	spin_lock(&addrconf_hash_lock);
-
-	/* Ignore adding duplicate addresses on an interface */
-	if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) {
-		ADBG("ipv6_add_addr: already assigned\n");
-		err = -EEXIST;
 		goto out;
 	}
 
-	ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC);
+	/* validator notifier needs to be blocking;
+	 * do not call in atomic context
+	 */
+	if (can_block) {
+		struct in6_validator_info i6vi = {
+			.i6vi_addr = *addr,
+			.i6vi_dev = idev,
+			.extack = extack,
+		};
+
+		err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi);
+		err = notifier_to_errno(err);
+		if (err < 0)
+			goto out;
+	}
 
+	ifa = kzalloc(sizeof(*ifa), gfp_flags);
 	if (!ifa) {
 		ADBG("ipv6_add_addr: malloc failed\n");
 		err = -ENOBUFS;
@@ -1019,6 +1052,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	rt = addrconf_dst_alloc(idev, addr, false);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
+		rt = NULL;
 		goto out;
 	}
 
@@ -1049,16 +1083,21 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	ifa->rt = rt;
 
 	ifa->idev = idev;
+	in6_dev_hold(idev);
+
 	/* For caller */
 	refcount_set(&ifa->refcnt, 1);
 
-	/* Add to big hash table */
-	hash = inet6_addr_hash(addr);
+	rcu_read_lock_bh();
 
-	hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
-	spin_unlock(&addrconf_hash_lock);
+	err = ipv6_add_addr_hash(idev->dev, ifa);
+	if (err < 0) {
+		rcu_read_unlock_bh();
+		goto out;
+	}
 
 	write_lock(&idev->lock);
+
 	/* Add to inet6_dev unicast addr list. */
 	ipv6_link_dev_addr(idev, ifa);
 
@@ -1069,21 +1108,23 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
 	in6_ifa_hold(ifa);
 	write_unlock(&idev->lock);
-out2:
+
 	rcu_read_unlock_bh();
 
-	if (likely(err == 0))
-		inet6addr_notifier_call_chain(NETDEV_UP, ifa);
-	else {
-		kfree(ifa);
-		in6_dev_put(idev);
+	inet6addr_notifier_call_chain(NETDEV_UP, ifa);
+out:
+	if (unlikely(err < 0)) {
+		if (rt)
+			ip6_rt_put(rt);
+		if (ifa) {
+			if (ifa->idev)
+				in6_dev_put(ifa->idev);
+			kfree(ifa);
+		}
 		ifa = ERR_PTR(err);
 	}
 
 	return ifa;
-out:
-	spin_unlock(&addrconf_hash_lock);
-	goto out2;
 }
 
 enum cleanup_prefix_rt_t {
@@ -1204,7 +1245,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE))
 		action = check_cleanup_prefix_route(ifp, &expires);
 
-	list_del_init(&ifp->if_list);
+	list_del_rcu(&ifp->if_list);
 	__in6_ifa_put(ifp);
 
 	write_unlock_bh(&ifp->idev->lock);
@@ -1226,7 +1267,9 @@ out:
 	in6_ifa_put(ifp);
 }
 
-static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift)
+static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp,
+				struct inet6_ifaddr *ift,
+				bool block)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct in6_addr addr, *tmpaddr;
@@ -1330,7 +1373,7 @@ retry:
 
 	ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen,
 			    ipv6_addr_scope(&addr), addr_flags,
-			    tmp_valid_lft, tmp_prefered_lft);
+			    tmp_valid_lft, tmp_prefered_lft, block, NULL);
 	if (IS_ERR(ift)) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
@@ -1558,8 +1601,7 @@ static int __ipv6_dev_get_saddr(struct net *net,
 {
 	struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx];
 
-	read_lock_bh(&idev->lock);
-	list_for_each_entry(score->ifa, &idev->addr_list, if_list) {
+	list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) {
 		int i;
 
 		/*
@@ -1609,11 +1651,6 @@ static int __ipv6_dev_get_saddr(struct net *net,
 				}
 				break;
 			} else if (minihiscore < miniscore) {
-				if (hiscore->ifa)
-					in6_ifa_put(hiscore->ifa);
-
-				in6_ifa_hold(score->ifa);
-
 				swap(hiscore, score);
 				hiscore_idx = 1 - hiscore_idx;
 
@@ -1625,7 +1662,6 @@ static int __ipv6_dev_get_saddr(struct net *net,
 		}
 	}
 out:
-	read_unlock_bh(&idev->lock);
 	return hiscore_idx;
 }
 
@@ -1662,6 +1698,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 	int dst_type;
 	bool use_oif_addr = false;
 	int hiscore_idx = 0;
+	int ret = 0;
 
 	dst_type = __ipv6_addr_type(daddr);
 	dst.addr = daddr;
@@ -1737,15 +1774,14 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 	}
 
 out:
-	rcu_read_unlock();
-
 	hiscore = &scores[hiscore_idx];
 	if (!hiscore->ifa)
-		return -EADDRNOTAVAIL;
+		ret = -EADDRNOTAVAIL;
+	else
+		*saddr = hiscore->ifa->addr;
 
-	*saddr = hiscore->ifa->addr;
-	in6_ifa_put(hiscore->ifa);
-	return 0;
+	rcu_read_unlock();
+	return ret;
 }
 EXPORT_SYMBOL(ipv6_dev_get_saddr);
 
@@ -1785,15 +1821,15 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 	return err;
 }
 
-static int ipv6_count_addresses(struct inet6_dev *idev)
+static int ipv6_count_addresses(const struct inet6_dev *idev)
 {
+	const struct inet6_ifaddr *ifp;
 	int cnt = 0;
-	struct inet6_ifaddr *ifp;
 
-	read_lock_bh(&idev->lock);
-	list_for_each_entry(ifp, &idev->addr_list, if_list)
+	rcu_read_lock();
+	list_for_each_entry_rcu(ifp, &idev->addr_list, if_list)
 		cnt++;
-	read_unlock_bh(&idev->lock);
+	rcu_read_unlock();
 	return cnt;
 }
 
@@ -1808,11 +1844,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 			    const struct net_device *dev, int strict,
 			    u32 banned_flags)
 {
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp;
-	unsigned int hash = inet6_addr_hash(addr);
 	u32 ifp_flags;
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
@@ -1826,32 +1862,16 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
 		    !(ifp_flags&banned_flags) &&
 		    (!dev || ifp->idev->dev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
-			rcu_read_unlock_bh();
+			rcu_read_unlock();
 			return 1;
 		}
 	}
 
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	return 0;
 }
 EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
 
-static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
-			       struct net_device *dev)
-{
-	unsigned int hash = inet6_addr_hash(addr);
-	struct inet6_ifaddr *ifp;
-
-	hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) {
-		if (!net_eq(dev_net(ifp->idev->dev), net))
-			continue;
-		if (ipv6_addr_equal(&ifp->addr, addr)) {
-			if (!dev || ifp->idev->dev == dev)
-				return true;
-		}
-	}
-	return false;
-}
 
 /* Compares an address/prefix_len with addresses on device @dev.
  * If one is found it returns true.
@@ -1859,20 +1879,18 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
 	const unsigned int prefix_len, struct net_device *dev)
 {
-	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifa;
+	const struct inet6_ifaddr *ifa;
+	const struct inet6_dev *idev;
 	bool ret = false;
 
 	rcu_read_lock();
 	idev = __in6_dev_get(dev);
 	if (idev) {
-		read_lock_bh(&idev->lock);
-		list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) {
 			ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len);
 			if (ret)
 				break;
 		}
-		read_unlock_bh(&idev->lock);
 	}
 	rcu_read_unlock();
 
@@ -1882,22 +1900,20 @@ EXPORT_SYMBOL(ipv6_chk_custom_prefix);
 
 int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev)
 {
-	struct inet6_dev *idev;
-	struct inet6_ifaddr *ifa;
+	const struct inet6_ifaddr *ifa;
+	const struct inet6_dev *idev;
 	int	onlink;
 
 	onlink = 0;
 	rcu_read_lock();
 	idev = __in6_dev_get(dev);
 	if (idev) {
-		read_lock_bh(&idev->lock);
-		list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) {
 			onlink = ipv6_prefix_equal(addr, &ifa->addr,
 						   ifa->prefix_len);
 			if (onlink)
 				break;
 		}
-		read_unlock_bh(&idev->lock);
 	}
 	rcu_read_unlock();
 	return onlink;
@@ -1907,11 +1923,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
 struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr,
 				     struct net_device *dev, int strict)
 {
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp, *result = NULL;
-	unsigned int hash = inet6_addr_hash(addr);
 
-	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) {
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr)) {
@@ -1923,7 +1939,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
 			}
 		}
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return result;
 }
@@ -1942,7 +1958,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 		if (ifpub) {
 			in6_ifa_hold(ifpub);
 			spin_unlock_bh(&ifp->lock);
-			ipv6_create_tempaddr(ifpub, ifp);
+			ipv6_create_tempaddr(ifpub, ifp, true);
 			in6_ifa_put(ifpub);
 		} else {
 			spin_unlock_bh(&ifp->lock);
@@ -1975,7 +1991,7 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 	return err;
 }
 
-void addrconf_dad_failure(struct inet6_ifaddr *ifp)
+void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net *net = dev_net(ifp->idev->dev);
@@ -1985,8 +2001,8 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 		return;
 	}
 
-	net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n",
-			     ifp->idev->dev->name, &ifp->addr);
+	net_info_ratelimited("%s: IPv6 duplicate address %pI6c used by %pM detected!\n",
+			     ifp->idev->dev->name, &ifp->addr, eth_hdr(skb)->h_source);
 
 	spin_lock_bh(&ifp->lock);
 
@@ -2025,7 +2041,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 
 		ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen,
 				     scope, flags, valid_lft,
-				     preferred_lft);
+				     preferred_lft, false, NULL);
 		if (IS_ERR(ifp2))
 			goto lock_errdad;
 
@@ -2321,24 +2337,24 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	if (!table)
 		return NULL;
 
-	read_lock_bh(&table->tb6_lock);
-	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0);
+	rcu_read_lock();
+	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true);
 	if (!fn)
 		goto out;
 
-	noflags |= RTF_CACHE;
-	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->dst.dev->ifindex != dev->ifindex)
 			continue;
 		if ((rt->rt6i_flags & flags) != flags)
 			continue;
 		if ((rt->rt6i_flags & noflags) != 0)
 			continue;
-		dst_hold(&rt->dst);
+		if (!dst_hold_safe(&rt->dst))
+			rt = NULL;
 		break;
 	}
 out:
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 	return rt;
 }
 
@@ -2442,7 +2458,7 @@ static void manage_tempaddrs(struct inet6_dev *idev,
 		 * no temporary address currently exists.
 		 */
 		read_unlock_bh(&idev->lock);
-		ipv6_create_tempaddr(ifp, NULL);
+		ipv6_create_tempaddr(ifp, NULL, false);
 	} else {
 		read_unlock_bh(&idev->lock);
 	}
@@ -2483,7 +2499,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
 					    pinfo->prefix_len,
 					    addr_type&IPV6_ADDR_SCOPE_MASK,
 					    addr_flags, valid_lft,
-					    prefered_lft);
+					    prefered_lft, false, NULL);
 
 		if (IS_ERR_OR_NULL(ifp))
 			return -1;
@@ -2793,7 +2809,8 @@ static int inet6_addr_add(struct net *net, int ifindex,
 			  const struct in6_addr *pfx,
 			  const struct in6_addr *peer_pfx,
 			  unsigned int plen, __u32 ifa_flags,
-			  __u32 prefered_lft, __u32 valid_lft)
+			  __u32 prefered_lft, __u32 valid_lft,
+			  struct netlink_ext_ack *extack)
 {
 	struct inet6_ifaddr *ifp;
 	struct inet6_dev *idev;
@@ -2852,7 +2869,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
 	}
 
 	ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags,
-			    valid_lft, prefered_lft);
+			    valid_lft, prefered_lft, true, extack);
 
 	if (!IS_ERR(ifp)) {
 		if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
@@ -2937,7 +2954,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
 	rtnl_lock();
 	err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL,
 			     ireq.ifr6_prefixlen, IFA_F_PERMANENT,
-			     INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+			     INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, NULL);
 	rtnl_unlock();
 	return err;
 }
@@ -2967,7 +2984,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
 	ifp = ipv6_add_addr(idev, addr, NULL, plen,
 			    scope, IFA_F_PERMANENT,
-			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME,
+			    true, NULL);
 	if (!IS_ERR(ifp)) {
 		spin_lock_bh(&ifp->lock);
 		ifp->flags &= ~IFA_F_TENTATIVE;
@@ -3067,7 +3085,7 @@ void addrconf_add_linklocal(struct inet6_dev *idev,
 #endif
 
 	ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
-			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL);
 	if (!IS_ERR(ifp)) {
 		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0);
 		addrconf_dad_start(ifp);
@@ -3297,7 +3315,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
 		struct rt6_info *rt, *prev;
 
 		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
-		if (unlikely(IS_ERR(rt)))
+		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 
 		/* ifp->rt can be accessed outside of rtnl */
@@ -3404,7 +3422,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			/* restore routes for permanent addresses */
 			addrconf_permanent_addr(dev);
 
-			if (!addrconf_qdisc_ok(dev)) {
+			if (!addrconf_link_ready(dev)) {
 				/* device is not ready yet. */
 				pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n",
 					dev->name);
@@ -3419,7 +3437,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 				run_pending = 1;
 			}
 		} else if (event == NETDEV_CHANGE) {
-			if (!addrconf_qdisc_ok(dev)) {
+			if (!addrconf_link_ready(dev)) {
 				/* device is still not ready. */
 				break;
 			}
@@ -3563,7 +3581,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	struct net *net = dev_net(dev);
 	struct inet6_dev *idev;
 	struct inet6_ifaddr *ifa, *tmp;
-	struct list_head del_list;
 	int _keep_addr;
 	bool keep_addr;
 	int state, i;
@@ -3655,7 +3672,6 @@ restart:
 	 */
 	keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6);
 
-	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
 		struct rt6_info *rt = NULL;
 		bool keep;
@@ -3664,8 +3680,6 @@ restart:
 
 		keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
 			!addr_is_local(&ifa->addr);
-		if (!keep)
-			list_move(&ifa->if_list, &del_list);
 
 		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
@@ -3699,19 +3713,14 @@ restart:
 		}
 
 		write_lock_bh(&idev->lock);
+		if (!keep) {
+			list_del_rcu(&ifa->if_list);
+			in6_ifa_put(ifa);
+		}
 	}
 
 	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);
@@ -4093,9 +4102,9 @@ struct if6_iter_state {
 
 static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 {
-	struct inet6_ifaddr *ifa = NULL;
 	struct if6_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct inet6_ifaddr *ifa = NULL;
 	int p = 0;
 
 	/* initial bucket if pos is 0 */
@@ -4105,7 +4114,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 	}
 
 	for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) {
-		hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket],
+		hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket],
 					 addr_lst) {
 			if (!net_eq(dev_net(ifa->idev->dev), net))
 				continue;
@@ -4131,7 +4140,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 	struct if6_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 
-	hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) {
+	hlist_for_each_entry_continue_rcu(ifa, addr_lst) {
 		if (!net_eq(dev_net(ifa->idev->dev), net))
 			continue;
 		state->offset++;
@@ -4140,7 +4149,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 
 	while (++state->bucket < IN6_ADDR_HSIZE) {
 		state->offset = 0;
-		hlist_for_each_entry_rcu_bh(ifa,
+		hlist_for_each_entry_rcu(ifa,
 				     &inet6_addr_lst[state->bucket], addr_lst) {
 			if (!net_eq(dev_net(ifa->idev->dev), net))
 				continue;
@@ -4153,9 +4162,9 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 }
 
 static void *if6_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(rcu_bh)
+	__acquires(rcu)
 {
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	return if6_get_first(seq, *pos);
 }
 
@@ -4169,9 +4178,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 }
 
 static void if6_seq_stop(struct seq_file *seq, void *v)
-	__releases(rcu_bh)
+	__releases(rcu)
 {
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 }
 
 static int if6_seq_show(struct seq_file *seq, void *v)
@@ -4240,12 +4249,12 @@ void if6_proc_exit(void)
 /* Check if address is a home address configured on any interface. */
 int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 {
-	int ret = 0;
+	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp = NULL;
-	unsigned int hash = inet6_addr_hash(addr);
+	int ret = 0;
 
-	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) {
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
@@ -4254,7 +4263,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 			break;
 		}
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	return ret;
 }
 #endif
@@ -4344,7 +4353,7 @@ restart:
 						spin_lock(&ifpub->lock);
 						ifpub->regen_count = 0;
 						spin_unlock(&ifpub->lock);
-						ipv6_create_tempaddr(ifpub, ifp);
+						ipv6_create_tempaddr(ifpub, ifp, true);
 						in6_ifa_put(ifpub);
 						in6_ifa_put(ifp);
 						goto restart;
@@ -4580,7 +4589,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx,
 				      ifm->ifa_prefixlen, ifa_flags,
-				      preferred_lft, valid_lft);
+				      preferred_lft, valid_lft, extack);
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_EXCL ||
@@ -4907,17 +4916,15 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
 			  extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
-	if (!addr) {
-		err = -EINVAL;
-		goto errout;
-	}
+	if (!addr)
+		return -EINVAL;
 
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_index)
-		dev = __dev_get_by_index(net, ifm->ifa_index);
+		dev = dev_get_by_index(net, ifm->ifa_index);
 
 	ifa = ipv6_get_ifaddr(net, addr, dev, 1);
 	if (!ifa) {
@@ -4943,6 +4950,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 errout_ifa:
 	in6_ifa_put(ifa);
 errout:
+	if (dev)
+		dev_put(dev);
 	return err;
 }
 
@@ -5050,6 +5059,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad;
 	array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode;
 	array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy;
+	array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -5899,10 +5909,9 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 		spin_lock(&ifa->lock);
 		if (ifa->rt) {
 			struct rt6_info *rt = ifa->rt;
-			struct fib6_table *table = rt->rt6i_table;
 			int cpu;
 
-			read_lock(&table->tb6_lock);
+			rcu_read_lock();
 			addrconf_set_nopolicy(ifa->rt, val);
 			if (rt->rt6i_pcpu) {
 				for_each_possible_cpu(cpu) {
@@ -5912,7 +5921,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 					addrconf_set_nopolicy(*rtp, val);
 				}
 			}
-			read_unlock(&table->tb6_lock);
+			rcu_read_unlock();
 		}
 		spin_unlock(&ifa->lock);
 	}
@@ -5978,6 +5987,7 @@ int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write,
 }
 
 static int minus_one = -1;
+static const int zero = 0;
 static const int one = 1;
 static const int two_five_five = 255;
 
@@ -6349,6 +6359,15 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.proc_handler   = addrconf_sysctl_disable_policy,
 	},
 	{
+		.procname	= "ndisc_tclass",
+		.data		= &ipv6_devconf.ndisc_tclass,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&zero,
+		.extra2		= (void *)&two_five_five,
+	},
+	{
 		/* sentinel */
 	}
 };
@@ -6586,13 +6605,13 @@ int __init addrconf_init(void)
 	__rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0);
 	__rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0);
 	__rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr,
-			inet6_dump_ifaddr, 0);
+			inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED);
 	__rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL,
 			inet6_dump_ifmcaddr, 0);
 	__rtnl_register(PF_INET6, RTM_GETANYCAST, NULL,
 			inet6_dump_ifacaddr, 0);
 	__rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf,
-			inet6_netconf_dump_devconf, 0);
+			inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED);
 
 	ipv6_addr_label_rtnl_register();
 
@@ -6619,9 +6638,9 @@ void addrconf_cleanup(void)
 	unregister_pernet_subsys(&addrconf_ops);
 	ipv6_addr_label_cleanup();
 
-	rtnl_lock();
+	rtnl_af_unregister(&inet6_ops);
 
-	__rtnl_af_unregister(&inet6_ops);
+	rtnl_lock();
 
 	/* clean dev list */
 	for_each_netdev(&init_net, dev) {