1 files changed, 218 insertions, 171 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dd142f444659..b1ed55141d8a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -53,6 +53,7 @@
 #include <net/fib_rules.h>
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
+#include <net/netdev_lock.h>
 #include <net/devlink.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/addrconf.h>
@@ -80,11 +81,15 @@ void rtnl_lock(void)
 }
 EXPORT_SYMBOL(rtnl_lock);
 
+int rtnl_lock_interruptible(void)
+{
+	return mutex_lock_interruptible(&rtnl_mutex);
+}
+
 int rtnl_lock_killable(void)
 {
 	return mutex_lock_killable(&rtnl_mutex);
 }
-EXPORT_SYMBOL(rtnl_lock_killable);
 
 static struct sk_buff *defer_kfree_skb_list;
 void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail)
@@ -221,6 +226,16 @@ int rtnl_net_trylock(struct net *net)
 }
 EXPORT_SYMBOL(rtnl_net_trylock);
 
+int rtnl_net_lock_killable(struct net *net)
+{
+	int ret = rtnl_lock_killable();
+
+	if (!ret)
+		__rtnl_net_lock(net);
+
+	return ret;
+}
+
 static int rtnl_net_cmp_locks(const struct net *net_a, const struct net *net_b)
 {
 	if (net_eq(net_a, net_b))
@@ -463,7 +478,7 @@ static int rtnl_unregister(int protocol, int msgtype)
  * rtnl_unregister_all - Unregister all rtnetlink message type of a protocol
  * @protocol : Protocol family or PF_UNSPEC
  *
- * Identical to calling rtnl_unregster() for all registered message types
+ * Identical to calling rtnl_unregister() for all registered message types
  * of a certain protocol family.
  */
 void rtnl_unregister_all(int protocol)
@@ -1011,9 +1026,11 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
 		.rta_error = error,
 		.rta_id =  id,
 	};
+	unsigned long delta;
 
 	if (dst) {
-		ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse);
+		delta = jiffies - READ_ONCE(dst->lastuse);
+		ci.rta_lastuse = jiffies_delta_to_clock_t(delta);
 		ci.rta_used = dst->__use;
 		ci.rta_clntref = rcuref_read(&dst->__rcuref);
 	}
@@ -1028,7 +1045,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
 }
 EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
 
-void netdev_set_operstate(struct net_device *dev, int newstate)
+void netif_set_operstate(struct net_device *dev, int newstate)
 {
 	unsigned int old = READ_ONCE(dev->operstate);
 
@@ -1037,9 +1054,9 @@ void netdev_set_operstate(struct net_device *dev, int newstate)
 			return;
 	} while (!try_cmpxchg(&dev->operstate, &old, newstate));
 
-	netdev_state_change(dev);
+	netif_state_change(dev);
 }
-EXPORT_SYMBOL(netdev_set_operstate);
+EXPORT_SYMBOL(netif_set_operstate);
 
 static void set_operstate(struct net_device *dev, unsigned char transition)
 {
@@ -1065,7 +1082,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
 		break;
 	}
 
-	netdev_set_operstate(dev, operstate);
+	netif_set_operstate(dev, operstate);
 }
 
 static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
@@ -1162,6 +1179,9 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 				 /* IFLA_VF_STATS_TX_DROPPED */
 				 nla_total_size_64bit(sizeof(__u64)));
 		}
+		if (dev->netdev_ops->ndo_get_vf_guid)
+			size += num_vfs * 2 *
+				nla_total_size(sizeof(struct ifla_vf_guid));
 		return size;
 	} else
 		return 0;
@@ -1250,13 +1270,13 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev)
 static noinline size_t if_nlmsg_size(const struct net_device *dev,
 				     u32 ext_filter_mask)
 {
-	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+	size_t size;
+
+	size = NLMSG_ALIGN(sizeof(struct ifinfomsg))
 	       + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
 	       + nla_total_size(IFALIASZ) /* IFLA_IFALIAS */
 	       + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */
 	       + nla_total_size_64bit(sizeof(struct rtnl_link_ifmap))
-	       + nla_total_size(sizeof(struct rtnl_link_stats))
-	       + nla_total_size_64bit(sizeof(struct rtnl_link_stats64))
 	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
 	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */
 	       + nla_total_size(4) /* IFLA_TXQLEN */
@@ -1278,6 +1298,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
+	       + nla_total_size(1) /* IFLA_NETNS_IMMUTABLE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
 	       + nla_total_size(4) /* IFLA_GROUP */
@@ -1305,7 +1326,15 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_devlink_port_size(dev)
 	       + rtnl_dpll_pin_size(dev)
 	       + nla_total_size(8)  /* IFLA_MAX_PACING_OFFLOAD_HORIZON */
+	       + nla_total_size(2)  /* IFLA_HEADROOM */
+	       + nla_total_size(2)  /* IFLA_TAILROOM */
 	       + 0;
+
+	if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS))
+		size += nla_total_size(sizeof(struct rtnl_link_stats)) +
+			nla_total_size_64bit(sizeof(struct rtnl_link_stats64));
+
+	return size;
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1427,7 +1456,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
 	struct netdev_phys_item_id ppid = { };
 	int err;
 
-	err = dev_get_port_parent_id(dev, &ppid, false);
+	err = netif_get_port_parent_id(dev, &ppid, false);
 	if (err) {
 		if (err == -EOPNOTSUPP)
 			return 0;
@@ -2017,7 +2046,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	ifm->__ifi_pad = 0;
 	ifm->ifi_type = READ_ONCE(dev->type);
 	ifm->ifi_index = READ_ONCE(dev->ifindex);
-	ifm->ifi_flags = dev_get_flags(dev);
+	ifm->ifi_flags = netif_get_flags(dev);
 	ifm->ifi_change = change;
 
 	if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
@@ -2032,6 +2061,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 		       netif_running(dev) ? READ_ONCE(dev->operstate) :
 					    IF_OPER_DOWN) ||
 	    nla_put_u8(skb, IFLA_LINKMODE, READ_ONCE(dev->link_mode)) ||
+	    nla_put_u8(skb, IFLA_NETNS_IMMUTABLE, dev->netns_immutable) ||
 	    nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) ||
 	    nla_put_u32(skb, IFLA_MIN_MTU, READ_ONCE(dev->min_mtu)) ||
 	    nla_put_u32(skb, IFLA_MAX_MTU, READ_ONCE(dev->max_mtu)) ||
@@ -2069,7 +2099,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_CARRIER_UP_COUNT,
 			atomic_read(&dev->carrier_up_count)) ||
 	    nla_put_u32(skb, IFLA_CARRIER_DOWN_COUNT,
-			atomic_read(&dev->carrier_down_count)))
+			atomic_read(&dev->carrier_down_count)) ||
+	    nla_put_u16(skb, IFLA_HEADROOM,
+			READ_ONCE(dev->needed_headroom)) ||
+	    nla_put_u16(skb, IFLA_TAILROOM,
+			READ_ONCE(dev->needed_tailroom)))
 		goto nla_put_failure;
 
 	if (rtnl_fill_proto_down(skb, dev))
@@ -2095,7 +2129,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	if (rtnl_phys_switch_id_fill(skb, dev))
 		goto nla_put_failure;
 
-	if (rtnl_fill_stats(skb, dev))
+	if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS) &&
+	    rtnl_fill_stats(skb, dev))
 		goto nla_put_failure;
 
 	if (rtnl_fill_vf(skb, dev, ext_filter_mask))
@@ -2220,6 +2255,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_ALLMULTI]		= { .type = NLA_REJECT },
 	[IFLA_GSO_IPV4_MAX_SIZE]	= NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
 	[IFLA_GRO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
+	[IFLA_NETNS_IMMUTABLE]	= { .type = NLA_REJECT },
+	[IFLA_HEADROOM]		= { .type = NLA_REJECT },
+	[IFLA_TAILROOM]		= { .type = NLA_REJECT },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2369,12 +2407,12 @@ static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
 	if (strict_check) {
 		struct ifinfomsg *ifm;
 
-		if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+		ifm = nlmsg_payload(nlh, sizeof(*ifm));
+		if (!ifm) {
 			NL_SET_ERR_MSG(extack, "Invalid header for link dump");
 			return -EINVAL;
 		}
 
-		ifm = nlmsg_data(nlh);
 		if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 		    ifm->ifi_change) {
 			NL_SET_ERR_MSG(extack, "Invalid values in header for link dump request");
@@ -2442,7 +2480,9 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
 			if (IS_ERR(tgt_net)) {
 				NL_SET_ERR_MSG(extack, "Invalid target network namespace id");
-				return PTR_ERR(tgt_net);
+				err = PTR_ERR(tgt_net);
+				netnsid = -1;
+				goto out;
 			}
 			break;
 		case IFLA_EXT_MASK:
@@ -2457,7 +2497,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		default:
 			if (cb->strict_check) {
 				NL_SET_ERR_MSG(extack, "Unsupported attribute in link dump request");
-				return -EINVAL;
+				err = -EINVAL;
+				goto out;
 			}
 		}
 	}
@@ -2479,11 +2520,14 @@ walk_entries:
 			break;
 	}
 
-	if (kind_ops)
-		rtnl_link_ops_put(kind_ops, ops_srcu_index);
 
 	cb->seq = tgt_net->dev_base_seq;
 	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+
+out:
+
+	if (kind_ops)
+		rtnl_link_ops_put(kind_ops, ops_srcu_index);
 	if (netnsid >= 0)
 		put_net(tgt_net);
 
@@ -2889,12 +2933,19 @@ static int do_set_master(struct net_device *dev, int ifindex,
 	const struct net_device_ops *ops;
 	int err;
 
+	/* Release the lower lock, the upper is responsible for locking
+	 * the lower if needed. None of the existing upper devices
+	 * use netdev instance lock, so don't grab it.
+	 */
+
 	if (upper_dev) {
 		if (upper_dev->ifindex == ifindex)
 			return 0;
 		ops = upper_dev->netdev_ops;
 		if (ops->ndo_del_slave) {
+			netdev_unlock_ops(dev);
 			err = ops->ndo_del_slave(upper_dev, dev);
+			netdev_lock_ops(dev);
 			if (err)
 				return err;
 		} else {
@@ -2908,7 +2959,9 @@ static int do_set_master(struct net_device *dev, int ifindex,
 			return -EINVAL;
 		ops = upper_dev->netdev_ops;
 		if (ops->ndo_add_slave) {
+			netdev_unlock_ops(dev);
 			err = ops->ndo_add_slave(upper_dev, dev, extack);
+			netdev_lock_ops(dev);
 			if (err)
 				return err;
 		} else {
@@ -2958,7 +3011,7 @@ static int do_set_proto_down(struct net_device *dev,
 		if (pdreason[IFLA_PROTO_DOWN_REASON_MASK])
 			mask = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_MASK]);
 
-		dev_change_proto_down_reason(dev, mask, value);
+		netdev_change_proto_down_reason_locked(dev, mask, value);
 	}
 
 	if (nl_proto_down) {
@@ -2969,8 +3022,7 @@ static int do_set_proto_down(struct net_device *dev,
 			NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons");
 			return -EBUSY;
 		}
-		err = dev_change_proto_down(dev,
-					    proto_down);
+		err = netif_change_proto_down(dev, proto_down);
 		if (err)
 			return err;
 	}
@@ -2992,7 +3044,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 
 	err = validate_linkmsg(dev, tb, extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	if (tb[IFLA_IFNAME])
 		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
@@ -3005,13 +3057,16 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 
 		new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0);
 
-		err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex);
+		err = __dev_change_net_namespace(dev, tgt_net, pat,
+						 new_ifindex, extack);
 		if (err)
-			goto errout;
+			return err;
 
 		status |= DO_SETLINK_MODIFIED;
 	}
 
+	netdev_lock_ops(dev);
+
 	if (tb[IFLA_MAP]) {
 		struct rtnl_link_ifmap *u_map;
 		struct ifmap k_map;
@@ -3042,35 +3097,35 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (tb[IFLA_ADDRESS]) {
-		struct sockaddr *sa;
-		int len;
-
-		len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len,
-						  sizeof(*sa));
-		sa = kmalloc(len, GFP_KERNEL);
-		if (!sa) {
-			err = -ENOMEM;
+		struct sockaddr_storage ss = { };
+
+		netdev_unlock_ops(dev);
+
+		/* dev_addr_sem is an outer lock, enforce proper ordering */
+		down_write(&dev_addr_sem);
+		netdev_lock_ops(dev);
+
+		ss.ss_family = dev->type;
+		memcpy(ss.__data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len);
+		err = netif_set_mac_address(dev, &ss, extack);
+		if (err) {
+			up_write(&dev_addr_sem);
 			goto errout;
 		}
-		sa->sa_family = dev->type;
-		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
-		       dev->addr_len);
-		err = dev_set_mac_address_user(dev, sa, extack);
-		kfree(sa);
-		if (err)
-			goto errout;
 		status |= DO_SETLINK_MODIFIED;
+
+		up_write(&dev_addr_sem);
 	}
 
 	if (tb[IFLA_MTU]) {
-		err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
+		err = netif_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
 		if (err < 0)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
 	}
 
 	if (tb[IFLA_GROUP]) {
-		dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
+		netif_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
 		status |= DO_SETLINK_NOTIFY;
 	}
 
@@ -3080,15 +3135,15 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	 * requested.
 	 */
 	if (ifm->ifi_index > 0 && ifname[0]) {
-		err = dev_change_name(dev, ifname);
+		err = netif_change_name(dev, ifname);
 		if (err < 0)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
 	}
 
 	if (tb[IFLA_IFALIAS]) {
-		err = dev_set_alias(dev, nla_data(tb[IFLA_IFALIAS]),
-				    nla_len(tb[IFLA_IFALIAS]));
+		err = netif_set_alias(dev, nla_data(tb[IFLA_IFALIAS]),
+				      nla_len(tb[IFLA_IFALIAS]));
 		if (err < 0)
 			goto errout;
 		status |= DO_SETLINK_NOTIFY;
@@ -3100,8 +3155,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (ifm->ifi_flags || ifm->ifi_change) {
-		err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
-				       extack);
+		err = netif_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
+					 extack);
 		if (err < 0)
 			goto errout;
 	}
@@ -3114,7 +3169,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (tb[IFLA_CARRIER]) {
-		err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
+		err = netif_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
@@ -3123,7 +3178,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	if (tb[IFLA_TXQLEN]) {
 		unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);
 
-		err = dev_change_tx_queue_len(dev, value);
+		err = netif_change_tx_queue_len(dev, value);
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
@@ -3347,13 +3402,15 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 errout:
 	if (status & DO_SETLINK_MODIFIED) {
 		if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
-			netdev_state_change(dev);
+			netif_state_change(dev);
 
 		if (err < 0)
 			net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
 					     dev->name);
 	}
 
+	netdev_unlock_ops(dev);
+
 	return err;
 }
 
@@ -3417,6 +3474,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		err = -ENODEV;
 
 	rtnl_nets_unlock(&rtnl_nets);
+	rtnl_nets_destroy(&rtnl_nets);
 errout:
 	return err;
 }
@@ -3528,7 +3586,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
 int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm,
 			u32 portid, const struct nlmsghdr *nlh)
 {
-	unsigned int old_flags;
+	unsigned int old_flags, changed;
 	int err;
 
 	old_flags = dev->flags;
@@ -3539,12 +3597,13 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm,
 			return err;
 	}
 
-	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
-		__dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags), portid, nlh);
-	} else {
-		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-		__dev_notify_flags(dev, old_flags, ~0U, portid, nlh);
+	changed = old_flags ^ dev->flags;
+	if (dev->rtnl_link_initializing) {
+		dev->rtnl_link_initializing = false;
+		changed = ~0U;
 	}
+
+	__dev_notify_flags(dev, old_flags, changed, portid, nlh);
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
@@ -3602,7 +3661,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 
 	dev_net_set(dev, net);
 	dev->rtnl_link_ops = ops;
-	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
+	dev->rtnl_link_initializing = true;
 
 	if (tb[IFLA_MTU]) {
 		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
@@ -3629,7 +3688,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	if (tb[IFLA_LINKMODE])
 		dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
 	if (tb[IFLA_GROUP])
-		dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
+		netif_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
 	if (tb[IFLA_GSO_MAX_SIZE])
 		netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE]));
 	if (tb[IFLA_GSO_MAX_SEGS])
@@ -3740,12 +3799,19 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 			       const struct rtnl_link_ops *ops,
 			       struct net *tgt_net, struct net *link_net,
+			       struct net *peer_net,
 			       const struct nlmsghdr *nlh,
 			       struct nlattr **tb, struct nlattr **data,
 			       struct netlink_ext_ack *extack)
 {
 	unsigned char name_assign_type = NET_NAME_USER;
-	struct net *net = sock_net(skb->sk);
+	struct rtnl_newlink_params params = {
+		.src_net = sock_net(skb->sk),
+		.link_net = link_net,
+		.peer_net = peer_net,
+		.tb = tb,
+		.data = data,
+	};
 	u32 portid = NETLINK_CB(skb).portid;
 	struct net_device *dev;
 	char ifname[IFNAMSIZ];
@@ -3761,8 +3827,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 		name_assign_type = NET_NAME_ENUM;
 	}
 
-	dev = rtnl_create_link(link_net ? : tgt_net, ifname,
-			       name_assign_type, ops, tb, extack);
+	dev = rtnl_create_link(tgt_net, ifname, name_assign_type, ops, tb,
+			       extack);
 	if (IS_ERR(dev)) {
 		err = PTR_ERR(dev);
 		goto out;
@@ -3771,7 +3837,7 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 	dev->ifindex = ifm->ifi_index;
 
 	if (ops->newlink)
-		err = ops->newlink(link_net ? : net, dev, tb, data, extack);
+		err = ops->newlink(dev, &params, extack);
 	else
 		err = register_netdevice(dev);
 	if (err < 0) {
@@ -3779,22 +3845,22 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 		goto out;
 	}
 
+	netdev_lock_ops(dev);
+
 	err = rtnl_configure_link(dev, ifm, portid, nlh);
 	if (err < 0)
 		goto out_unregister;
-	if (link_net) {
-		err = dev_change_net_namespace(dev, tgt_net, ifname);
-		if (err < 0)
-			goto out_unregister;
-	}
 	if (tb[IFLA_MASTER]) {
 		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
 		if (err)
 			goto out_unregister;
 	}
+
+	netdev_unlock_ops(dev);
 out:
 	return err;
 out_unregister:
+	netdev_unlock_ops(dev);
 	if (ops->newlink) {
 		LIST_HEAD(list_kill);
 
@@ -3806,60 +3872,60 @@ out_unregister:
 	goto out;
 }
 
-static int rtnl_add_peer_net(struct rtnl_nets *rtnl_nets,
-			     const struct rtnl_link_ops *ops,
-			     struct nlattr *data[],
-			     struct netlink_ext_ack *extack)
+static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops,
+				     struct nlattr *tbp[],
+				     struct nlattr *data[],
+				     struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[IFLA_MAX + 1];
-	struct net *net;
 	int err;
 
 	if (!data || !data[ops->peer_type])
-		return 0;
+		return rtnl_link_get_net_ifla(tbp);
 
 	err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack);
 	if (err < 0)
-		return err;
+		return ERR_PTR(err);
 
 	if (ops->validate) {
 		err = ops->validate(tb, NULL, extack);
 		if (err < 0)
-			return err;
+			return ERR_PTR(err);
 	}
 
-	net = rtnl_link_get_net_ifla(tb);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
-	if (net)
-		rtnl_nets_add(rtnl_nets, net);
-
-	return 0;
+	return rtnl_link_get_net_ifla(tb);
 }
 
 static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  const struct rtnl_link_ops *ops,
 			  struct net *tgt_net, struct net *link_net,
+			  struct net *peer_net,
 			  struct rtnl_newlink_tbs *tbs,
 			  struct nlattr **data,
 			  struct netlink_ext_ack *extack)
 {
 	struct nlattr ** const tb = tbs->tb;
 	struct net *net = sock_net(skb->sk);
+	struct net *device_net;
 	struct net_device *dev;
 	struct ifinfomsg *ifm;
 	bool link_specified;
 
+	/* When creating, lookup for existing device in target net namespace */
+	device_net = (nlh->nlmsg_flags & NLM_F_CREATE) &&
+		     (nlh->nlmsg_flags & NLM_F_EXCL) ?
+		     tgt_net : net;
+
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifi_index > 0) {
 		link_specified = true;
-		dev = __dev_get_by_index(net, ifm->ifi_index);
+		dev = __dev_get_by_index(device_net, ifm->ifi_index);
 	} else if (ifm->ifi_index < 0) {
 		NL_SET_ERR_MSG(extack, "ifindex can't be negative");
 		return -EINVAL;
 	} else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
 		link_specified = true;
-		dev = rtnl_dev_get(net, tb);
+		dev = rtnl_dev_get(device_net, tb);
 	} else {
 		link_specified = false;
 		dev = NULL;
@@ -3888,14 +3954,15 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EOPNOTSUPP;
 	}
 
-	return rtnl_newlink_create(skb, ifm, ops, tgt_net, link_net, nlh, tb, data, extack);
+	return rtnl_newlink_create(skb, ifm, ops, tgt_net, link_net, peer_net, nlh,
+				   tb, data, extack);
 }
 
 static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
+	struct net *tgt_net, *link_net = NULL, *peer_net = NULL;
 	struct nlattr **tb, **linkinfo, **data = NULL;
-	struct net *tgt_net, *link_net = NULL;
 	struct rtnl_link_ops *ops = NULL;
 	struct rtnl_newlink_tbs *tbs;
 	struct rtnl_nets rtnl_nets;
@@ -3965,9 +4032,13 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 
 		if (ops->peer_type) {
-			ret = rtnl_add_peer_net(&rtnl_nets, ops, data, extack);
-			if (ret < 0)
+			peer_net = rtnl_get_peer_net(ops, tb, data, extack);
+			if (IS_ERR(peer_net)) {
+				ret = PTR_ERR(peer_net);
 				goto put_ops;
+			}
+			if (peer_net)
+				rtnl_nets_add(&rtnl_nets, peer_net);
 		}
 	}
 
@@ -3998,7 +4069,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	rtnl_nets_lock(&rtnl_nets);
-	ret = __rtnl_newlink(skb, nlh, ops, tgt_net, link_net, tbs, data, extack);
+	ret = __rtnl_newlink(skb, nlh, ops, tgt_net, link_net, peer_net, tbs, data, extack);
 	rtnl_nets_unlock(&rtnl_nets);
 
 put_net:
@@ -4019,7 +4090,8 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
 	struct ifinfomsg *ifm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for get link");
 		return -EINVAL;
 	}
@@ -4028,7 +4100,6 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
 					      ifla_policy, extack);
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 	    ifm->ifi_change) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for get link request");
@@ -4651,9 +4722,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 	u16 vid;
 
-	if (!netlink_capable(skb, CAP_NET_ADMIN))
-		return -EPERM;
-
 	if (!del_bulk) {
 		err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX,
 					     NULL, extack);
@@ -4754,15 +4822,16 @@ static int nlmsg_populate_fdb(struct sk_buff *skb,
 			      int *idx,
 			      struct netdev_hw_addr_list *list)
 {
+	struct ndo_fdb_dump_context *ctx = (void *)cb->ctx;
 	struct netdev_hw_addr *ha;
-	int err;
 	u32 portid, seq;
+	int err;
 
 	portid = NETLINK_CB(cb->skb).portid;
 	seq = cb->nlh->nlmsg_seq;
 
 	list_for_each_entry(ha, &list->list, list) {
-		if (*idx < cb->args[2])
+		if (*idx < ctx->fdb_idx)
 			goto skip;
 
 		err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0,
@@ -4818,12 +4887,12 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh,
 	struct ndmsg *ndm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+	ndm = nlmsg_payload(nlh, sizeof(*ndm));
+	if (!ndm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for fdb dump request");
 		return -EINVAL;
 	}
 
-	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
 	    ndm->ndm_flags || ndm->ndm_type) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request");
@@ -4901,18 +4970,16 @@ static int valid_fdb_dump_legacy(const struct nlmsghdr *nlh,
 
 static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct net_device *dev;
-	struct net_device *br_dev = NULL;
-	const struct net_device_ops *ops = NULL;
-	const struct net_device_ops *cops = NULL;
+	const struct net_device_ops *ops = NULL, *cops = NULL;
+	struct ndo_fdb_dump_context *ctx = (void *)cb->ctx;
+	struct net_device *dev, *br_dev = NULL;
 	struct net *net = sock_net(skb->sk);
-	struct hlist_head *head;
 	int brport_idx = 0;
 	int br_idx = 0;
-	int h, s_h;
-	int idx = 0, s_idx;
-	int err = 0;
 	int fidx = 0;
+	int err;
+
+	NL_ASSERT_CTX_FITS(struct ndo_fdb_dump_context);
 
 	if (cb->strict_check)
 		err = valid_fdb_dump_strict(cb->nlh, &br_idx, &brport_idx,
@@ -4931,70 +4998,51 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		ops = br_dev->netdev_ops;
 	}
 
-	s_h = cb->args[0];
-	s_idx = cb->args[1];
-
-	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
-		idx = 0;
-		head = &net->dev_index_head[h];
-		hlist_for_each_entry(dev, head, index_hlist) {
-
-			if (brport_idx && (dev->ifindex != brport_idx))
-				continue;
-
-			if (!br_idx) { /* user did not specify a specific bridge */
-				if (netif_is_bridge_port(dev)) {
-					br_dev = netdev_master_upper_dev_get(dev);
-					cops = br_dev->netdev_ops;
-				}
-			} else {
-				if (dev != br_dev &&
-				    !netif_is_bridge_port(dev))
-					continue;
+	for_each_netdev_dump(net, dev, ctx->ifindex) {
+		if (brport_idx && (dev->ifindex != brport_idx))
+			continue;
 
-				if (br_dev != netdev_master_upper_dev_get(dev) &&
-				    !netif_is_bridge_master(dev))
-					continue;
-				cops = ops;
+		if (!br_idx) { /* user did not specify a specific bridge */
+			if (netif_is_bridge_port(dev)) {
+				br_dev = netdev_master_upper_dev_get(dev);
+				cops = br_dev->netdev_ops;
 			}
+		} else {
+			if (dev != br_dev &&
+			    !netif_is_bridge_port(dev))
+				continue;
 
-			if (idx < s_idx)
-				goto cont;
+			if (br_dev != netdev_master_upper_dev_get(dev) &&
+			    !netif_is_bridge_master(dev))
+				continue;
+			cops = ops;
+		}
 
-			if (netif_is_bridge_port(dev)) {
-				if (cops && cops->ndo_fdb_dump) {
-					err = cops->ndo_fdb_dump(skb, cb,
-								br_dev, dev,
-								&fidx);
-					if (err == -EMSGSIZE)
-						goto out;
-				}
+		if (netif_is_bridge_port(dev)) {
+			if (cops && cops->ndo_fdb_dump) {
+				err = cops->ndo_fdb_dump(skb, cb, br_dev, dev,
+							&fidx);
+				if (err == -EMSGSIZE)
+					break;
 			}
+		}
 
-			if (dev->netdev_ops->ndo_fdb_dump)
-				err = dev->netdev_ops->ndo_fdb_dump(skb, cb,
-								    dev, NULL,
-								    &fidx);
-			else
-				err = ndo_dflt_fdb_dump(skb, cb, dev, NULL,
-							&fidx);
-			if (err == -EMSGSIZE)
-				goto out;
+		if (dev->netdev_ops->ndo_fdb_dump)
+			err = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL,
+							    &fidx);
+		else
+			err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, &fidx);
+		if (err == -EMSGSIZE)
+			break;
 
-			cops = NULL;
+		cops = NULL;
 
-			/* reset fdb offset to 0 for rest of the interfaces */
-			cb->args[2] = 0;
-			fidx = 0;
-cont:
-			idx++;
-		}
+		/* reset fdb offset to 0 for rest of the interfaces */
+		ctx->fdb_idx = 0;
+		fidx = 0;
 	}
 
-out:
-	cb->args[0] = h;
-	cb->args[1] = idx;
-	cb->args[2] = fidx;
+	ctx->fdb_idx = fidx;
 
 	return skb->len;
 }
@@ -5007,12 +5055,12 @@ static int valid_fdb_get_strict(const struct nlmsghdr *nlh,
 	struct ndmsg *ndm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+	ndm = nlmsg_payload(nlh, sizeof(*ndm));
+	if (!ndm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for fdb get request");
 		return -EINVAL;
 	}
 
-	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
 	    ndm->ndm_type) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for fdb get request");
@@ -5191,7 +5239,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	ifm->__ifi_pad = 0;
 	ifm->ifi_type = dev->type;
 	ifm->ifi_index = dev->ifindex;
-	ifm->ifi_flags = dev_get_flags(dev);
+	ifm->ifi_flags = netif_get_flags(dev);
 	ifm->ifi_change = 0;
 
 
@@ -5279,12 +5327,12 @@ static int valid_bridge_getlink_req(const struct nlmsghdr *nlh,
 	if (strict_check) {
 		struct ifinfomsg *ifm;
 
-		if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+		ifm = nlmsg_payload(nlh, sizeof(*ifm));
+		if (!ifm) {
 			NL_SET_ERR_MSG(extack, "Invalid header for bridge link dump");
 			return -EINVAL;
 		}
 
-		ifm = nlmsg_data(nlh);
 		if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 		    ifm->ifi_change || ifm->ifi_index) {
 			NL_SET_ERR_MSG(extack, "Invalid values in header for bridge link dump request");
@@ -6176,7 +6224,8 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check,
 {
 	struct if_stats_msg *ifsm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) {
+	ifsm = nlmsg_payload(nlh, sizeof(*ifsm));
+	if (!ifsm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
 		return -EINVAL;
 	}
@@ -6184,8 +6233,6 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check,
 	if (!strict_check)
 		return 0;
 
-	ifsm = nlmsg_data(nlh);
-
 	/* only requests using strict checks can pass data to influence
 	 * the dump. The legacy exception is filter_mask.
 	 */
@@ -6413,12 +6460,12 @@ static int rtnl_mdb_valid_dump_req(const struct nlmsghdr *nlh,
 {
 	struct br_port_msg *bpm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*bpm))) {
+	bpm = nlmsg_payload(nlh, sizeof(*bpm));
+	if (!bpm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for mdb dump request");
 		return -EINVAL;
 	}
 
-	bpm = nlmsg_data(nlh);
 	if (bpm->ifindex) {
 		NL_SET_ERR_MSG(extack, "Filtering by device index is not supported for mdb dump request");
 		return -EINVAL;