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

Pull networking fixes from David Miller:

 1) Must teardown SR-IOV before unregistering netdev in igb driver, from
    Alex Williamson.

 2) Fix ipv6 route unreachable crash in IPVS, from Alex Gartrell.

 3) Default route selection in ipv4 should take the prefix length, table
    ID, and TOS into account, from Julian Anastasov.

 4) sch_plug must have a reset method in order to purge all buffered
    packets when the qdisc is reset, likewise for sch_choke, from WANG
    Cong.

 5) Fix deadlock and races in slave_changelink/br_setport in bridging.
    From Nikolay Aleksandrov.

 6) mlx4 bug fixes (wrong index in port even propagation to VFs,
    overzealous BUG_ON assertion, etc.) from Ido Shamay, Jack
    Morgenstein, and Or Gerlitz.

 7) Turn off klog message about SCTP userspace interface compat that
    makes no sense at all, from Daniel Borkmann.

 8) Fix unbounded restarts of inet frag eviction process, causing NMI
    watchdog soft lockup messages, from Florian Westphal.

 9) Suspend/resume fixes for r8152 from Hayes Wang.

10) Fix busy loop when MSG_WAITALL|MSG_PEEK is used in TCP recv, from
    Sabrina Dubroca.

11) Fix performance regression when removing a lot of routes from the
    ipv4 routing tables, from Alexander Duyck.

12) Fix device leak in AF_PACKET, from Lars Westerhoff.

13) AF_PACKET also has a header length comparison bug due to signedness,
    from Alexander Drozdov.

14) Fix bug in EBPF tail call generation on x86, from Daniel Borkmann.

15) Memory leaks, TSO stats, watchdog timeout and other fixes to
    thunderx driver from Sunil Goutham and Thanneeru Srinivasulu.

16) act_bpf can leak memory when replacing programs, from Daniel
    Borkmann.

17) WOL packet fixes in gianfar driver, from Claudiu Manoil.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
  stmmac: fix missing MODULE_LICENSE in stmmac_platform
  gianfar: Enable device wakeup when appropriate
  gianfar: Fix suspend/resume for wol magic packet
  gianfar: Fix warning when CONFIG_PM off
  act_pedit: check binding before calling tcf_hash_release()
  net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket
  net: sched: fix refcount imbalance in actions
  r8152: reset device when tx timeout
  r8152: add pre_reset and post_reset
  qlcnic: Fix corruption while copying
  act_bpf: fix memory leaks when replacing bpf programs
  net: thunderx: Fix for crash while BGX teardown
  net: thunderx: Add PCI driver shutdown routine
  net: thunderx: Fix crash when changing rss with mutliple traffic flows
  net: thunderx: Set watchdog timeout value
  net: thunderx: Wakeup TXQ only if CQE_TX are processed
  net: thunderx: Suppress alloc_pages() failure warnings
  net: thunderx: Fix TSO packet statistic
  net: thunderx: Fix memory leak when changing queue count
  net: thunderx: Fix RQ_DROP miscalculation
  ...

43 files changed, 402 insertions, 228 deletions

diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 3d0f7d2a0616..ad82324f710f 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2312,6 +2312,10 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 		return 1;
 
 	chan = conn->smp;
+	if (!chan) {
+		BT_ERR("SMP security requested but not available");
+		return 1;
+	}
 
 	if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED))
 		return 1;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 0ff6e1bbca91..fa7bfced888e 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -37,15 +37,30 @@ static inline int should_deliver(const struct net_bridge_port *p,
 
 int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb)
 {
-	if (!is_skb_forwardable(skb->dev, skb)) {
-		kfree_skb(skb);
-	} else {
-		skb_push(skb, ETH_HLEN);
-		br_drop_fake_rtable(skb);
-		skb_sender_cpu_clear(skb);
-		dev_queue_xmit(skb);
+	if (!is_skb_forwardable(skb->dev, skb))
+		goto drop;
+
+	skb_push(skb, ETH_HLEN);
+	br_drop_fake_rtable(skb);
+	skb_sender_cpu_clear(skb);
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    (skb->protocol == htons(ETH_P_8021Q) ||
+	     skb->protocol == htons(ETH_P_8021AD))) {
+		int depth;
+
+		if (!__vlan_get_protocol(skb, skb->protocol, &depth))
+			goto drop;
+
+		skb_set_network_header(skb, depth);
 	}
 
+	dev_queue_xmit(skb);
+
+	return 0;
+
+drop:
+	kfree_skb(skb);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 1198a3dbad95..c94321955db7 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -445,6 +445,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 		if (p->port->state == BR_STATE_DISABLED)
 			goto unlock;
 
+		entry->state = p->state;
 		rcu_assign_pointer(*pp, p->next);
 		hlist_del_init(&p->mglist);
 		del_timer(&p->timer);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 79db489cdade..0b39dcc65b94 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1416,8 +1416,7 @@ br_multicast_leave_group(struct net_bridge *br,
 
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) ||
-	    (port && port->state == BR_STATE_DISABLED) ||
-	    timer_pending(&other_query->timer))
+	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
 	mdb = mlock_dereference(br->mdb, br);
@@ -1425,6 +1424,31 @@ br_multicast_leave_group(struct net_bridge *br,
 	if (!mp)
 		goto out;
 
+	if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
+		struct net_bridge_port_group __rcu **pp;
+
+		for (pp = &mp->ports;
+		     (p = mlock_dereference(*pp, br)) != NULL;
+		     pp = &p->next) {
+			if (p->port != port)
+				continue;
+
+			rcu_assign_pointer(*pp, p->next);
+			hlist_del_init(&p->mglist);
+			del_timer(&p->timer);
+			call_rcu_bh(&p->rcu, br_multicast_free_pg);
+			br_mdb_notify(br->dev, port, group, RTM_DELMDB);
+
+			if (!mp->ports && !mp->mglist &&
+			    netif_running(br->dev))
+				mod_timer(&mp->timer, jiffies);
+		}
+		goto out;
+	}
+
+	if (timer_pending(&other_query->timer))
+		goto out;
+
 	if (br->multicast_querier) {
 		__br_multicast_send_query(br, port, &mp->addr);
 
@@ -1450,28 +1474,6 @@ br_multicast_leave_group(struct net_bridge *br,
 		}
 	}
 
-	if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
-		struct net_bridge_port_group __rcu **pp;
-
-		for (pp = &mp->ports;
-		     (p = mlock_dereference(*pp, br)) != NULL;
-		     pp = &p->next) {
-			if (p->port != port)
-				continue;
-
-			rcu_assign_pointer(*pp, p->next);
-			hlist_del_init(&p->mglist);
-			del_timer(&p->timer);
-			call_rcu_bh(&p->rcu, br_multicast_free_pg);
-			br_mdb_notify(br->dev, port, group, RTM_DELMDB);
-
-			if (!mp->ports && !mp->mglist &&
-			    netif_running(br->dev))
-				mod_timer(&mp->timer, jiffies);
-		}
-		goto out;
-	}
-
 	now = jiffies;
 	time = now + br->multicast_last_member_count *
 		     br->multicast_last_member_interval;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 364bdc98bd9b..3da5525eb8a2 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -693,9 +693,17 @@ static int br_port_slave_changelink(struct net_device *brdev,
 				    struct nlattr *tb[],
 				    struct nlattr *data[])
 {
+	struct net_bridge *br = netdev_priv(brdev);
+	int ret;
+
 	if (!data)
 		return 0;
-	return br_setport(br_port_get_rtnl(dev), data);
+
+	spin_lock_bh(&br->lock);
+	ret = br_setport(br_port_get_rtnl(dev), data);
+	spin_unlock_bh(&br->lock);
+
+	return ret;
 }
 
 static int br_port_fill_slave_info(struct sk_buff *skb,
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index b4b6dab9c285..ed74ffaa851f 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -209,8 +209,9 @@ void br_transmit_config(struct net_bridge_port *p)
 		br_send_config_bpdu(p, &bpdu);
 		p->topology_change_ack = 0;
 		p->config_pending = 0;
-		mod_timer(&p->hold_timer,
-			  round_jiffies(jiffies + BR_HOLD_TIME));
+		if (p->br->stp_enabled == BR_KERNEL_STP)
+			mod_timer(&p->hold_timer,
+				  round_jiffies(jiffies + BR_HOLD_TIME));
 	}
 }
 
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index a2730e7196cd..4ca449a16132 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -48,7 +48,8 @@ void br_stp_enable_bridge(struct net_bridge *br)
 	struct net_bridge_port *p;
 
 	spin_lock_bh(&br->lock);
-	mod_timer(&br->hello_timer, jiffies + br->hello_time);
+	if (br->stp_enabled == BR_KERNEL_STP)
+		mod_timer(&br->hello_timer, jiffies + br->hello_time);
 	mod_timer(&br->gc_timer, jiffies + HZ/10);
 
 	br_config_bpdu_generation(br);
@@ -127,6 +128,7 @@ static void br_stp_start(struct net_bridge *br)
 	int r;
 	char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL };
 	char *envp[] = { NULL };
+	struct net_bridge_port *p;
 
 	r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
 
@@ -140,6 +142,10 @@ static void br_stp_start(struct net_bridge *br)
 	if (r == 0) {
 		br->stp_enabled = BR_USER_STP;
 		br_debug(br, "userspace STP started\n");
+		/* Stop hello and hold timers */
+		del_timer(&br->hello_timer);
+		list_for_each_entry(p, &br->port_list, list)
+			del_timer(&p->hold_timer);
 	} else {
 		br->stp_enabled = BR_KERNEL_STP;
 		br_debug(br, "using kernel STP\n");
@@ -156,12 +162,17 @@ static void br_stp_stop(struct net_bridge *br)
 	int r;
 	char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL };
 	char *envp[] = { NULL };
+	struct net_bridge_port *p;
 
 	if (br->stp_enabled == BR_USER_STP) {
 		r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
 		br_info(br, "userspace STP stopped, return code %d\n", r);
 
 		/* To start timers on any ports left in blocking */
+		mod_timer(&br->hello_timer, jiffies + br->hello_time);
+		list_for_each_entry(p, &br->port_list, list)
+			mod_timer(&p->hold_timer,
+				  round_jiffies(jiffies + BR_HOLD_TIME));
 		spin_lock_bh(&br->lock);
 		br_port_state_selection(br);
 		spin_unlock_bh(&br->lock);
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 7caf7fae2d5b..5f0f5af0ec35 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -40,7 +40,9 @@ static void br_hello_timer_expired(unsigned long arg)
 	if (br->dev->flags & IFF_UP) {
 		br_config_bpdu_generation(br);
 
-		mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time));
+		if (br->stp_enabled != BR_USER_STP)
+			mod_timer(&br->hello_timer,
+				  round_jiffies(jiffies + br->hello_time));
 	}
 	spin_unlock(&br->lock);
 }
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 1f2a126f4ffa..6441f47b1a8f 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -23,7 +23,8 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state
 
 struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 {
-	return css_cls_state(task_css(p, net_cls_cgrp_id));
+	return css_cls_state(task_css_check(p, net_cls_cgrp_id,
+					    rcu_read_lock_bh_held()));
 }
 EXPORT_SYMBOL_GPL(task_cls_state);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 08f16db46070..193901d09757 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1497,7 +1497,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		sock_copy(newsk, sk);
 
 		/* SANITY */
-		get_net(sock_net(newsk));
+		if (likely(newsk->sk_net_refcnt))
+			get_net(sock_net(newsk));
 		sk_node_init(&newsk->sk_node);
 		sock_lock_init(newsk);
 		bh_lock_sock(newsk);
@@ -1967,20 +1968,21 @@ static void __release_sock(struct sock *sk)
  * sk_wait_data - wait for data to arrive at sk_receive_queue
  * @sk:    sock to wait on
  * @timeo: for how long
+ * @skb:   last skb seen on sk_receive_queue
  *
  * Now socket state including sk->sk_err is changed only under lock,
  * hence we may omit checks after joining wait queue.
  * We check receive queue before schedule() only as optimization;
  * it is very likely that release_sock() added new data.
  */
-int sk_wait_data(struct sock *sk, long *timeo)
+int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
 {
 	int rc;
 	DEFINE_WAIT(wait);
 
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
-	rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
+	rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
 	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	finish_wait(sk_sleep(sk), &wait);
 	return rc;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 52a94016526d..b5cf13a28009 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -886,7 +886,7 @@ verify_sock_status:
 			break;
 		}
 
-		sk_wait_data(sk, &timeo);
+		sk_wait_data(sk, &timeo, NULL);
 		continue;
 	found_ok_skb:
 		if (len > skb->len)
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index f46e4d1306f2..214d44aef35b 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -207,7 +207,7 @@ found:
 	} else {
 		fq->q.meat += skb->len;
 	}
-	add_frag_mem_limit(&fq->q, skb->truesize);
+	add_frag_mem_limit(fq->q.net, skb->truesize);
 
 	if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
 	    fq->q.meat == fq->q.len) {
@@ -287,7 +287,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
 		clone->data_len = clone->len;
 		head->data_len -= clone->len;
 		head->len -= clone->len;
-		add_frag_mem_limit(&fq->q, clone->truesize);
+		add_frag_mem_limit(fq->q.net, clone->truesize);
 	}
 
 	WARN_ON(head == NULL);
@@ -310,7 +310,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
 		}
 		fp = next;
 	}
-	sub_frag_mem_limit(&fq->q, sum_truesize);
+	sub_frag_mem_limit(fq->q.net, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 933a92820d26..6c8b1fbafce8 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1017,14 +1017,16 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 
 	neigh = neigh_lookup(&arp_tbl, &ip, dev);
 	if (neigh) {
-		read_lock_bh(&neigh->lock);
-		memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
-		r->arp_flags = arp_state_to_flags(neigh);
-		read_unlock_bh(&neigh->lock);
-		r->arp_ha.sa_family = dev->type;
-		strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+		if (!(neigh->nud_state & NUD_NOARP)) {
+			read_lock_bh(&neigh->lock);
+			memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+			r->arp_flags = arp_state_to_flags(neigh);
+			read_unlock_bh(&neigh->lock);
+			r->arp_ha.sa_family = dev->type;
+			strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+			err = 0;
+		}
 		neigh_release(neigh);
-		err = 0;
 	}
 	return err;
 }
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e813196c91c7..2d9cb1748f81 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -882,7 +882,6 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 		queue_delayed_work(system_power_efficient_wq,
 				&check_lifetime_work, 0);
 		rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
-		blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
 	}
 	return 0;
 }
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c6211ed60b03..9c02920725db 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -13,6 +13,7 @@ struct fib_alias {
 	u8			fa_state;
 	u8			fa_slen;
 	u32			tb_id;
+	s16			fa_default;
 	struct rcu_head		rcu;
 };
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c7358ea4ae93..3a06586b170c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1202,23 +1202,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
 }
 
 /* Must be invoked inside of an RCU protected region.  */
-void fib_select_default(struct fib_result *res)
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 {
 	struct fib_info *fi = NULL, *last_resort = NULL;
 	struct hlist_head *fa_head = res->fa_head;
 	struct fib_table *tb = res->table;
+	u8 slen = 32 - res->prefixlen;
 	int order = -1, last_idx = -1;
-	struct fib_alias *fa;
+	struct fib_alias *fa, *fa1 = NULL;
+	u32 last_prio = res->fi->fib_priority;
+	u8 last_tos = 0;
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
 
+		if (fa->fa_slen != slen)
+			continue;
+		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+			continue;
+		if (fa->tb_id != tb->tb_id)
+			continue;
+		if (next_fi->fib_priority > last_prio &&
+		    fa->fa_tos == last_tos) {
+			if (last_tos)
+				continue;
+			break;
+		}
+		if (next_fi->fib_flags & RTNH_F_DEAD)
+			continue;
+		last_tos = fa->fa_tos;
+		last_prio = next_fi->fib_priority;
+
 		if (next_fi->fib_scope != res->scope ||
 		    fa->fa_type != RTN_UNICAST)
 			continue;
-
-		if (next_fi->fib_priority > res->fi->fib_priority)
-			break;
 		if (!next_fi->fib_nh[0].nh_gw ||
 		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
 			continue;
@@ -1228,10 +1245,11 @@ void fib_select_default(struct fib_result *res)
 		if (!fi) {
 			if (next_fi != res->fi)
 				break;
+			fa1 = fa;
 		} else if (!fib_detect_death(fi, order, &last_resort,
-					     &last_idx, tb->tb_default)) {
+					     &last_idx, fa1->fa_default)) {
 			fib_result_assign(res, fi);
-			tb->tb_default = order;
+			fa1->fa_default = order;
 			goto out;
 		}
 		fi = next_fi;
@@ -1239,20 +1257,21 @@ void fib_select_default(struct fib_result *res)
 	}
 
 	if (order <= 0 || !fi) {
-		tb->tb_default = -1;
+		if (fa1)
+			fa1->fa_default = -1;
 		goto out;
 	}
 
 	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
-				tb->tb_default)) {
+			      fa1->fa_default)) {
 		fib_result_assign(res, fi);
-		tb->tb_default = order;
+		fa1->fa_default = order;
 		goto out;
 	}
 
 	if (last_idx >= 0)
 		fib_result_assign(res, last_resort);
-	tb->tb_default = last_idx;
+	fa1->fa_default = last_idx;
 out:
 	return;
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 15d32612e3c6..37c4bb89a708 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			new_fa->fa_state = state & ~FA_S_ACCESSED;
 			new_fa->fa_slen = fa->fa_slen;
 			new_fa->tb_id = tb->tb_id;
+			new_fa->fa_default = -1;
 
 			err = switchdev_fib_ipv4_add(key, plen, fi,
 						     new_fa->fa_tos,
@@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 	new_fa->fa_state = 0;
 	new_fa->fa_slen = slen;
 	new_fa->tb_id = tb->tb_id;
+	new_fa->fa_default = -1;
 
 	/* (Optionally) offload fib entry to switch hardware. */
 	err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
@@ -1791,8 +1793,6 @@ void fib_table_flush_external(struct fib_table *tb)
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 }
@@ -1862,8 +1862,6 @@ int fib_table_flush(struct fib_table *tb)
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 
@@ -1990,7 +1988,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias)
 		return NULL;
 
 	tb->tb_id = id;
-	tb->tb_default = -1;
 	tb->tb_num_default = 0;
 	tb->tb_data = (alias ? alias->__data : tb->__data);
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 5e346a082e5f..d0a7c0319e3d 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -131,34 +131,22 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
 	unsigned int evicted = 0;
 	HLIST_HEAD(expired);
 
-evict_again:
 	spin_lock(&hb->chain_lock);
 
 	hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
 		if (!inet_fragq_should_evict(fq))
 			continue;
 
-		if (!del_timer(&fq->timer)) {
-			/* q expiring right now thus increment its refcount so
-			 * it won't be freed under us and wait until the timer
-			 * has finished executing then destroy it
-			 */
-			atomic_inc(&fq->refcnt);
-			spin_unlock(&hb->chain_lock);
-			del_timer_sync(&fq->timer);
-			inet_frag_put(fq, f);
-			goto evict_again;
-		}
+		if (!del_timer(&fq->timer))
+			continue;
 
-		fq->flags |= INET_FRAG_EVICTED;
-		hlist_del(&fq->list);
-		hlist_add_head(&fq->list, &expired);
+		hlist_add_head(&fq->list_evictor, &expired);
 		++evicted;
 	}
 
 	spin_unlock(&hb->chain_lock);
 
-	hlist_for_each_entry_safe(fq, n, &expired, list)
+	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
 		f->frag_expire((unsigned long) fq);
 
 	return evicted;
@@ -240,18 +228,20 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	int i;
 
 	nf->low_thresh = 0;
-	local_bh_disable();
 
 evict_again:
+	local_bh_disable();
 	seq = read_seqbegin(&f->rnd_seqlock);
 
 	for (i = 0; i < INETFRAGS_HASHSZ ; i++)
 		inet_evict_bucket(f, &f->hash[i]);
 
-	if (read_seqretry(&f->rnd_seqlock, seq))
-		goto evict_again;
-
 	local_bh_enable();
+	cond_resched();
+
+	if (read_seqretry(&f->rnd_seqlock, seq) ||
+	    percpu_counter_sum(&nf->mem))
+		goto evict_again;
 
 	percpu_counter_destroy(&nf->mem);
 }
@@ -284,8 +274,8 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
 	struct inet_frag_bucket *hb;
 
 	hb = get_frag_bucket_locked(fq, f);
-	if (!(fq->flags & INET_FRAG_EVICTED))
-		hlist_del(&fq->list);
+	hlist_del(&fq->list);
+	fq->flags |= INET_FRAG_COMPLETE;
 	spin_unlock(&hb->chain_lock);
 }
 
@@ -297,7 +287,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
 		fq_unlink(fq, f);
 		atomic_dec(&fq->refcnt);
-		fq->flags |= INET_FRAG_COMPLETE;
 	}
 }
 EXPORT_SYMBOL(inet_frag_kill);
@@ -330,11 +319,12 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 		fp = xp;
 	}
 	sum = sum_truesize + f->qsize;
-	sub_frag_mem_limit(q, sum);
 
 	if (f->destructor)
 		f->destructor(q);
 	kmem_cache_free(f->frags_cachep, q);
+
+	sub_frag_mem_limit(nf, sum);
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
@@ -390,7 +380,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 
 	q->net = nf;
 	f->constructor(q, arg);
-	add_frag_mem_limit(q, f->qsize);
+	add_frag_mem_limit(nf, f->qsize);
 
 	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
 	spin_lock_init(&q->lock);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 31f71b15cfba..921138f6c97c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -202,7 +202,7 @@ static void ip_expire(unsigned long arg)
 	ipq_kill(qp);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 
-	if (!(qp->q.flags & INET_FRAG_EVICTED)) {
+	if (!inet_frag_evicting(&qp->q)) {
 		struct sk_buff *head = qp->q.fragments;
 		const struct iphdr *iph;
 		int err;
@@ -309,7 +309,7 @@ static int ip_frag_reinit(struct ipq *qp)
 		kfree_skb(fp);
 		fp = xp;
 	} while (fp);
-	sub_frag_mem_limit(&qp->q, sum_truesize);
+	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;
@@ -455,7 +455,7 @@ found:
 				qp->q.fragments = next;
 
 			qp->q.meat -= free_it->len;
-			sub_frag_mem_limit(&qp->q, free_it->truesize);
+			sub_frag_mem_limit(qp->q.net, free_it->truesize);
 			kfree_skb(free_it);
 		}
 	}
@@ -479,7 +479,7 @@ found:
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb-&