Merge tag 'v4.9.144' into 4.9-2.3.x-imx

This is the 4.9.144 stable release

96 files changed, 1721 insertions, 1317 deletions

diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 79f1fa22509a..23654f1902f3 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -745,6 +745,7 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev,
 		hdr.hop_limit, &hdr.daddr);
 
 	skb_push(skb, sizeof(hdr));
+	skb_reset_mac_header(skb);
 	skb_reset_network_header(skb);
 	skb_copy_to_linear_data(skb, &hdr, sizeof(hdr));
 
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 16d287565987..145f80518064 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -46,10 +46,15 @@ p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
 void p9stat_free(struct p9_wstat *stbuf)
 {
 	kfree(stbuf->name);
+	stbuf->name = NULL;
 	kfree(stbuf->uid);
+	stbuf->uid = NULL;
 	kfree(stbuf->gid);
+	stbuf->gid = NULL;
 	kfree(stbuf->muid);
+	stbuf->muid = NULL;
 	kfree(stbuf->extension);
+	stbuf->extension = NULL;
 }
 EXPORT_SYMBOL(p9stat_free);
 
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index ee08540ce503..5d79004de25c 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -243,6 +243,7 @@ static void batadv_v_elp_periodic_work(struct work_struct *work)
 	struct batadv_priv *bat_priv;
 	struct sk_buff *skb;
 	u32 elp_interval;
+	bool ret;
 
 	bat_v = container_of(work, struct batadv_hard_iface_bat_v, elp_wq.work);
 	hard_iface = container_of(bat_v, struct batadv_hard_iface, bat_v);
@@ -304,8 +305,11 @@ static void batadv_v_elp_periodic_work(struct work_struct *work)
 		 * may sleep and that is not allowed in an rcu protected
 		 * context. Therefore schedule a task for that.
 		 */
-		queue_work(batadv_event_workqueue,
-			   &hardif_neigh->bat_v.metric_work);
+		ret = queue_work(batadv_event_workqueue,
+				 &hardif_neigh->bat_v.metric_work);
+
+		if (!ret)
+			batadv_hardif_neigh_put(hardif_neigh);
 	}
 	rcu_read_unlock();
 
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 582e27698bf0..8b6f654bc85d 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1767,6 +1767,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
 {
 	struct batadv_bla_backbone_gw *backbone_gw;
 	struct ethhdr *ethhdr;
+	bool ret;
 
 	ethhdr = eth_hdr(skb);
 
@@ -1790,8 +1791,13 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	if (unlikely(!backbone_gw))
 		return true;
 
-	queue_work(batadv_event_workqueue, &backbone_gw->report_work);
-	/* backbone_gw is unreferenced in the report work function function */
+	ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work);
+
+	/* backbone_gw is unreferenced in the report work function function
+	 * if queue_work() call was successful
+	 */
+	if (!ret)
+		batadv_backbone_gw_put(backbone_gw);
 
 	return true;
 }
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index e3baf697a35c..a7b5cf08d363 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -845,16 +845,27 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv,
 	spinlock_t *lock; /* Used to lock list selected by "int in_coding" */
 	struct list_head *list;
 
+	/* Select ingoing or outgoing coding node */
+	if (in_coding) {
+		lock = &orig_neigh_node->in_coding_list_lock;
+		list = &orig_neigh_node->in_coding_list;
+	} else {
+		lock = &orig_neigh_node->out_coding_list_lock;
+		list = &orig_neigh_node->out_coding_list;
+	}
+
+	spin_lock_bh(lock);
+
 	/* Check if nc_node is already added */
 	nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding);
 
 	/* Node found */
 	if (nc_node)
-		return nc_node;
+		goto unlock;
 
 	nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC);
 	if (!nc_node)
-		return NULL;
+		goto unlock;
 
 	/* Initialize nc_node */
 	INIT_LIST_HEAD(&nc_node->list);
@@ -863,22 +874,14 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv,
 	kref_get(&orig_neigh_node->refcount);
 	nc_node->orig_node = orig_neigh_node;
 
-	/* Select ingoing or outgoing coding node */
-	if (in_coding) {
-		lock = &orig_neigh_node->in_coding_list_lock;
-		list = &orig_neigh_node->in_coding_list;
-	} else {
-		lock = &orig_neigh_node->out_coding_list_lock;
-		list = &orig_neigh_node->out_coding_list;
-	}
-
 	batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n",
 		   nc_node->addr, nc_node->orig_node->orig);
 
 	/* Add nc_node to orig_node */
-	spin_lock_bh(lock);
 	kref_get(&nc_node->refcount);
 	list_add_tail_rcu(&nc_node->list, list);
+
+unlock:
 	spin_unlock_bh(lock);
 
 	return nc_node;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 84c1b388d9ed..05bc176decf0 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -565,15 +565,20 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 	struct batadv_softif_vlan *vlan;
 	int err;
 
+	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
+
 	vlan = batadv_softif_vlan_get(bat_priv, vid);
 	if (vlan) {
 		batadv_softif_vlan_put(vlan);
+		spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
 		return -EEXIST;
 	}
 
 	vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC);
-	if (!vlan)
+	if (!vlan) {
+		spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
 		return -ENOMEM;
+	}
 
 	vlan->bat_priv = bat_priv;
 	vlan->vid = vid;
@@ -581,17 +586,23 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 
 	atomic_set(&vlan->ap_isolation, 0);
 
+	kref_get(&vlan->refcount);
+	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
+	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+
+	/* batadv_sysfs_add_vlan cannot be in the spinlock section due to the
+	 * sleeping behavior of the sysfs functions and the fs_reclaim lock
+	 */
 	err = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan);
 	if (err) {
-		kfree(vlan);
+		/* ref for the function */
+		batadv_softif_vlan_put(vlan);
+
+		/* ref for the list */
+		batadv_softif_vlan_put(vlan);
 		return err;
 	}
 
-	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
-	kref_get(&vlan->refcount);
-	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
-	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
-
 	/* add a new TT local entry. This one will be marked with the NOPURGE
 	 * flag
 	 */
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 02d96f224c60..31d7e239a1fd 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -187,7 +187,8 @@ ssize_t batadv_store_##_name(struct kobject *kobj,			\
 									\
 	return __batadv_store_uint_attr(buff, count, _min, _max,	\
 					_post_func, attr,		\
-					&bat_priv->_var, net_dev);	\
+					&bat_priv->_var, net_dev,	\
+					NULL);	\
 }
 
 #define BATADV_ATTR_SIF_SHOW_UINT(_name, _var)				\
@@ -261,7 +262,9 @@ ssize_t batadv_store_##_name(struct kobject *kobj,			\
 									\
 	length = __batadv_store_uint_attr(buff, count, _min, _max,	\
 					  _post_func, attr,		\
-					  &hard_iface->_var, net_dev);	\
+					  &hard_iface->_var,		\
+					  hard_iface->soft_iface,	\
+					  net_dev);			\
 									\
 	batadv_hardif_put(hard_iface);				\
 	return length;							\
@@ -355,10 +358,12 @@ __batadv_store_bool_attr(char *buff, size_t count,
 
 static int batadv_store_uint_attr(const char *buff, size_t count,
 				  struct net_device *net_dev,
+				  struct net_device *slave_dev,
 				  const char *attr_name,
 				  unsigned int min, unsigned int max,
 				  atomic_t *attr)
 {
+	char ifname[IFNAMSIZ + 3] = "";
 	unsigned long uint_val;
 	int ret;
 
@@ -384,8 +389,11 @@ static int batadv_store_uint_attr(const char *buff, size_t count,
 	if (atomic_read(attr) == uint_val)
 		return count;
 
-	batadv_info(net_dev, "%s: Changing from: %i to: %lu\n",
-		    attr_name, atomic_read(attr), uint_val);
+	if (slave_dev)
+		snprintf(ifname, sizeof(ifname), "%s: ", slave_dev->name);
+
+	batadv_info(net_dev, "%s: %sChanging from: %i to: %lu\n",
+		    attr_name, ifname, atomic_read(attr), uint_val);
 
 	atomic_set(attr, uint_val);
 	return count;
@@ -396,12 +404,13 @@ static ssize_t __batadv_store_uint_attr(const char *buff, size_t count,
 					void (*post_func)(struct net_device *),
 					const struct attribute *attr,
 					atomic_t *attr_store,
-					struct net_device *net_dev)
+					struct net_device *net_dev,
+					struct net_device *slave_dev)
 {
 	int ret;
 
-	ret = batadv_store_uint_attr(buff, count, net_dev, attr->name, min, max,
-				     attr_store);
+	ret = batadv_store_uint_attr(buff, count, net_dev, slave_dev,
+				     attr->name, min, max, attr_store);
 	if (post_func && ret)
 		post_func(net_dev);
 
@@ -570,7 +579,7 @@ static ssize_t batadv_store_gw_sel_class(struct kobject *kobj,
 	return __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE,
 					batadv_post_gw_reselect, attr,
 					&bat_priv->gw.sel_class,
-					bat_priv->soft_iface);
+					bat_priv->soft_iface, NULL);
 }
 
 static ssize_t batadv_show_gw_bwidth(struct kobject *kobj,
@@ -1084,8 +1093,9 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj,
 	if (old_tp_override == tp_override)
 		goto out;
 
-	batadv_info(net_dev, "%s: Changing from: %u.%u MBit to: %u.%u MBit\n",
-		    "throughput_override",
+	batadv_info(hard_iface->soft_iface,
+		    "%s: %s: Changing from: %u.%u MBit to: %u.%u MBit\n",
+		    "throughput_override", net_dev->name,
 		    old_tp_override / 10, old_tp_override % 10,
 		    tp_override / 10, tp_override % 10);
 
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 0dc85eb1cb7a..b9f9a310eb78 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1550,6 +1550,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global,
 {
 	struct batadv_tt_orig_list_entry *orig_entry;
 
+	spin_lock_bh(&tt_global->list_lock);
+
 	orig_entry = batadv_tt_global_orig_entry_find(tt_global, orig_node);
 	if (orig_entry) {
 		/* refresh the ttvn: the current value could be a bogus one that
@@ -1570,16 +1572,16 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global,
 	orig_entry->ttvn = ttvn;
 	kref_init(&orig_entry->refcount);
 
-	spin_lock_bh(&tt_global->list_lock);
 	kref_get(&orig_entry->refcount);
 	hlist_add_head_rcu(&orig_entry->list,
 			   &tt_global->orig_list);
-	spin_unlock_bh(&tt_global->list_lock);
 	atomic_inc(&tt_global->orig_list_count);
 
 out:
 	if (orig_entry)
 		batadv_tt_orig_list_entry_put(orig_entry);
+
+	spin_unlock_bh(&tt_global->list_lock);
 }
 
 /**
diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c
index 77654f055f24..8e91a26e9b00 100644
--- a/net/batman-adv/tvlv.c
+++ b/net/batman-adv/tvlv.c
@@ -528,15 +528,20 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
 {
 	struct batadv_tvlv_handler *tvlv_handler;
 
+	spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
+
 	tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version);
 	if (tvlv_handler) {
+		spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
 		batadv_tvlv_handler_put(tvlv_handler);
 		return;
 	}
 
 	tvlv_handler = kzalloc(sizeof(*tvlv_handler), GFP_ATOMIC);
-	if (!tvlv_handler)
+	if (!tvlv_handler) {
+		spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
 		return;
+	}
 
 	tvlv_handler->ogm_handler = optr;
 	tvlv_handler->unicast_handler = uptr;
@@ -546,7 +551,6 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
 	kref_init(&tvlv_handler->refcount);
 	INIT_HLIST_NODE(&tvlv_handler->list);
 
-	spin_lock_bh(&bat_priv->tvlv.handler_list_lock);
 	kref_get(&tvlv_handler->refcount);
 	hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list);
 	spin_unlock_bh(&bat_priv->tvlv.handler_list_lock);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1fba2a03f8ae..ba24f613c0fc 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2298,9 +2298,8 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	/* LE address type */
 	addr_type = le_addr_type(cp->addr.type);
 
-	hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type);
-
-	err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type);
+	/* Abort any ongoing SMP pairing. Removes ltk and irk if they exist. */
+	err = smp_cancel_and_remove_pairing(hdev, &cp->addr.bdaddr, addr_type);
 	if (err < 0) {
 		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
 					MGMT_STATUS_NOT_PAIRED, &rp,
@@ -2314,8 +2313,6 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto done;
 	}
 
-	/* Abort any ongoing SMP pairing */
-	smp_cancel_pairing(conn);
 
 	/* Defer clearing up the connection parameters until closing to
 	 * give a chance of keeping them if a repairing happens.
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index ead4d1baeaa6..1abfbcd8090a 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2353,30 +2353,51 @@ unlock:
 	return ret;
 }
 
-void smp_cancel_pairing(struct hci_conn *hcon)
+int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				  u8 addr_type)
 {
-	struct l2cap_conn *conn = hcon->l2cap_data;
+	struct hci_conn *hcon;
+	struct l2cap_conn *conn;
 	struct l2cap_chan *chan;
 	struct smp_chan *smp;
+	int err;
+
+	err = hci_remove_ltk(hdev, bdaddr, addr_type);
+	hci_remove_irk(hdev, bdaddr, addr_type);
+
+	hcon = hci_conn_hash_lookup_le(hdev, bdaddr, addr_type);
+	if (!hcon)
+		goto done;
 
+	conn = hcon->l2cap_data;
 	if (!conn)
-		return;
+		goto done;
 
 	chan = conn->smp;
 	if (!chan)
-		return;
+		goto done;
 
 	l2cap_chan_lock(chan);
 
 	smp = chan->data;
 	if (smp) {
+		/* Set keys to NULL to make sure smp_failure() does not try to
+		 * remove and free already invalidated rcu list entries. */
+		smp->ltk = NULL;
+		smp->slave_ltk = NULL;
+		smp->remote_irk = NULL;
+
 		if (test_bit(SMP_FLAG_COMPLETE, &smp->flags))
 			smp_failure(conn, 0);
 		else
 			smp_failure(conn, SMP_UNSPECIFIED);
+		err = 0;
 	}
 
 	l2cap_chan_unlock(chan);
+
+done:
+	return err;
 }
 
 static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb)
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index ffcc70b6b199..993cbd7bcfe7 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -180,7 +180,8 @@ enum smp_key_pref {
 };
 
 /* SMP Commands */
-void smp_cancel_pairing(struct hci_conn *hcon);
+int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				  u8 addr_type);
 bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
 			     enum smp_key_pref key_pref);
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 2136e45f5277..4bd57507b9a4 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1287,7 +1287,14 @@ static void br_multicast_query_received(struct net_bridge *br,
 		return;
 
 	br_multicast_update_query_timer(br, query, max_delay);
-	br_multicast_mark_router(br, port);
+
+	/* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules,
+	 * the arrival port for IGMP Queries where the source address
+	 * is 0.0.0.0 should not be added to router port list.
+	 */
+	if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
+	    saddr->proto == htons(ETH_P_IPV6))
+		br_multicast_mark_router(br, port);
 }
 
 static int br_ip4_multicast_query(struct net_bridge *br,
diff --git a/net/bridge/netfilter/ebt_arpreply.c b/net/bridge/netfilter/ebt_arpreply.c
index 070cf134a22f..f2660c1b29e4 100644
--- a/net/bridge/netfilter/ebt_arpreply.c
+++ b/net/bridge/netfilter/ebt_arpreply.c
@@ -67,6 +67,9 @@ static int ebt_arpreply_tg_check(const struct xt_tgchk_param *par)
 	if (e->ethproto != htons(ETH_P_ARP) ||
 	    e->invflags & EBT_IPROTO)
 		return -EINVAL;
+	if (ebt_invalid_target(info->target))
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index c822b3ae1bd3..8e79dca81748 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -314,14 +314,30 @@ int ceph_auth_update_authorizer(struct ceph_auth_client *ac,
 }
 EXPORT_SYMBOL(ceph_auth_update_authorizer);
 
+int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
+				       struct ceph_authorizer *a,
+				       void *challenge_buf,
+				       int challenge_buf_len)
+{
+	int ret = 0;
+
+	mutex_lock(&ac->mutex);
+	if (ac->ops && ac->ops->add_authorizer_challenge)
+		ret = ac->ops->add_authorizer_challenge(ac, a, challenge_buf,
+							challenge_buf_len);
+	mutex_unlock(&ac->mutex);
+	return ret;
+}
+EXPORT_SYMBOL(ceph_auth_add_authorizer_challenge);
+
 int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
-				      struct ceph_authorizer *a, size_t len)
+				      struct ceph_authorizer *a)
 {
 	int ret = 0;
 
 	mutex_lock(&ac->mutex);
 	if (ac->ops && ac->ops->verify_authorizer_reply)
-		ret = ac->ops->verify_authorizer_reply(ac, a, len);
+		ret = ac->ops->verify_authorizer_reply(ac, a);
 	mutex_unlock(&ac->mutex);
 	return ret;
 }
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index b216131915e7..29e23b5cb2ed 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -8,6 +8,7 @@
 
 #include <linux/ceph/decode.h>
 #include <linux/ceph/auth.h>
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/libceph.h>
 #include <linux/ceph/messenger.h>
 
@@ -69,25 +70,40 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret, void *buf,
 	return sizeof(u32) + ciphertext_len;
 }
 
+static int __ceph_x_decrypt(struct ceph_crypto_key *secret, void *p,
+			    int ciphertext_len)
+{
+	struct ceph_x_encrypt_header *hdr = p;
+	int plaintext_len;
+	int ret;
+
+	ret = ceph_crypt(secret, false, p, ciphertext_len, ciphertext_len,
+			 &plaintext_len);
+	if (ret)
+		return ret;
+
+	if (le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC) {
+		pr_err("%s bad magic\n", __func__);
+		return -EINVAL;
+	}
+
+	return plaintext_len - sizeof(*hdr);
+}
+
 static int ceph_x_decrypt(struct ceph_crypto_key *secret, void **p, void *end)
 {
-	struct ceph_x_encrypt_header *hdr = *p + sizeof(u32);
-	int ciphertext_len, plaintext_len;
+	int ciphertext_len;
 	int ret;
 
 	ceph_decode_32_safe(p, end, ciphertext_len, e_inval);
 	ceph_decode_need(p, end, ciphertext_len, e_inval);
 
-	ret = ceph_crypt(secret, false, *p, end - *p, ciphertext_len,
-			 &plaintext_len);
-	if (ret)
+	ret = __ceph_x_decrypt(secret, *p, ciphertext_len);
+	if (ret < 0)
 		return ret;
 
-	if (hdr->struct_v != 1 || le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC)
-		return -EPERM;
-
 	*p += ciphertext_len;
-	return plaintext_len - sizeof(struct ceph_x_encrypt_header);
+	return ret;
 
 e_inval:
 	return -EINVAL;
@@ -271,6 +287,51 @@ bad:
 	return -EINVAL;
 }
 
+/*
+ * Encode and encrypt the second part (ceph_x_authorize_b) of the
+ * authorizer.  The first part (ceph_x_authorize_a) should already be
+ * encoded.
+ */
+static int encrypt_authorizer(struct ceph_x_authorizer *au,
+			      u64 *server_challenge)
+{
+	struct ceph_x_authorize_a *msg_a;
+	struct ceph_x_authorize_b *msg_b;
+	void *p, *end;
+	int ret;
+
+	msg_a = au->buf->vec.iov_base;
+	WARN_ON(msg_a->ticket_blob.secret_id != cpu_to_le64(au->secret_id));
+	p = (void *)(msg_a + 1) + le32_to_cpu(msg_a->ticket_blob.blob_len);
+	end = au->buf->vec.iov_base + au->buf->vec.iov_len;
+
+	msg_b = p + ceph_x_encrypt_offset();
+	msg_b->struct_v = 2;
+	msg_b->nonce = cpu_to_le64(au->nonce);
+	if (server_challenge) {
+		msg_b->have_challenge = 1;
+		msg_b->server_challenge_plus_one =
+		    cpu_to_le64(*server_challenge + 1);
+	} else {
+		msg_b->have_challenge = 0;
+		msg_b->server_challenge_plus_one = 0;
+	}
+
+	ret = ceph_x_encrypt(&au->session_key, p, end - p, sizeof(*msg_b));
+	if (ret < 0)
+		return ret;
+
+	p += ret;
+	if (server_challenge) {
+		WARN_ON(p != end);
+	} else {
+		WARN_ON(p > end);
+		au->buf->vec.iov_len = p - au->buf->vec.iov_base;
+	}
+
+	return 0;
+}
+
 static void ceph_x_authorizer_cleanup(struct ceph_x_authorizer *au)
 {
 	ceph_crypto_key_destroy(&au->session_key);
@@ -287,7 +348,6 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	int maxlen;
 	struct ceph_x_authorize_a *msg_a;
 	struct ceph_x_authorize_b *msg_b;
-	void *p, *end;
 	int ret;
 	int ticket_blob_len =
 		(th->ticket_blob ? th->ticket_blob->vec.iov_len : 0);
@@ -331,21 +391,13 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	dout(" th %p secret_id %lld %lld\n", th, th->secret_id,
 	     le64_to_cpu(msg_a->ticket_blob.secret_id));
 
-	p = msg_a + 1;
-	p += ticket_blob_len;
-	end = au->buf->vec.iov_base + au->buf->vec.iov_len;
-
-	msg_b = p + ceph_x_encrypt_offset();
-	msg_b->struct_v = 1;
 	get_random_bytes(&au->nonce, sizeof(au->nonce));
-	msg_b->nonce = cpu_to_le64(au->nonce);
-	ret = ceph_x_encrypt(&au->session_key, p, end - p, sizeof(*msg_b));
-	if (ret < 0)
+	ret = encrypt_authorizer(au, NULL);
+	if (ret) {
+		pr_err("failed to encrypt authorizer: %d", ret);
 		goto out_au;
+	}
 
-	p += ret;
-	WARN_ON(p > end);
-	au->buf->vec.iov_len = p - au->buf->vec.iov_base;
 	dout(" built authorizer nonce %llx len %d\n", au->nonce,
 	     (int)au->buf->vec.iov_len);
 	return 0;
@@ -622,8 +674,56 @@ static int ceph_x_update_authorizer(
 	return 0;
 }
 
+static int decrypt_authorize_challenge(struct ceph_x_authorizer *au,
+				       void *challenge_buf,
+				       int challenge_buf_len,
+				       u64 *server_challenge)
+{
+	struct ceph_x_authorize_challenge *ch =
+	    challenge_buf + sizeof(struct ceph_x_encrypt_header);
+	int ret;
+
+	/* no leading len */
+	ret = __ceph_x_decrypt(&au->session_key, challenge_buf,
+			       challenge_buf_len);
+	if (ret < 0)
+		return ret;
+	if (ret < sizeof(*ch)) {
+		pr_err("bad size %d for ceph_x_authorize_challenge\n", ret);
+		return -EINVAL;
+	}
+
+	*server_challenge = le64_to_cpu(ch->server_challenge);
+	return 0;
+}
+
+static int ceph_x_add_authorizer_challenge(struct ceph_auth_client *ac,
+					   struct ceph_authorizer *a,
+					   void *challenge_buf,
+					   int challenge_buf_len)
+{
+	struct ceph_x_authorizer *au = (void *)a;
+	u64 server_challenge;
+	int ret;
+
+	ret = decrypt_authorize_challenge(au, challenge_buf, challenge_buf_len,
+					  &server_challenge);
+	if (ret) {
+		pr_err("failed to decrypt authorize challenge: %d", ret);
+		return ret;
+	}
+
+	ret = encrypt_authorizer(au, &server_challenge);
+	if (ret) {
+		pr_err("failed to encrypt authorizer w/ challenge: %d", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
-					  struct ceph_authorizer *a, size_t len)
+					  struct ceph_authorizer *a)
 {
 	struct ceph_x_authorizer *au = (void *)a;
 	void *p = au->enc_buf;
@@ -633,8 +733,10 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
 	ret = ceph_x_decrypt(&au->session_key, &p, p + CEPHX_AU_ENC_BUF_LEN);
 	if (ret < 0)
 		return ret;
-	if (ret != sizeof(*reply))
-		return -EPERM;
+	if (ret < sizeof(*reply)) {
+		pr_err("bad size %d for ceph_x_authorize_reply\n", ret);
+		return -EINVAL;
+	}
 
 	if (au->nonce + 1 != le64_to_cpu(reply->nonce_plus_one))
 		ret = -EPERM;
@@ -700,26 +802,64 @@ static int calc_signature(struct ceph_x_authorizer *au, struct ceph_msg *msg,
 			  __le64 *psig)
 {
 	void *enc_buf = au->enc_buf;
-	struct {
-		__le32 len;
-		__le32 header_crc;
-		__le32 front_crc;
-		__le32 middle_crc;
-		__le32 data_crc;
-	} __packed *sigblock = enc_buf + ceph_x_encrypt_offset();
 	int ret;
 
-	sigblock->len = cpu_to_le32(4*sizeof(u32));
-	sigblock->header_crc = msg->hdr.crc;
-	sigblock->front_crc = msg->footer.front_crc;
-	sigblock->middle_crc = msg->footer.middle_crc;
-	sigblock->data_crc =  msg->footer.data_crc;
-	ret = ceph_x_encrypt(&au->session_key, enc_buf, CEPHX_AU_ENC_BUF_LEN,
-			     sizeof(*sigblock));
-	if (ret < 0)
-		return ret;
+	if (msg->con->peer_features & CEPH_FEATURE_CEPHX_V2) {
+		struct {
+			__le32 len;
+			__le32 header_crc;
+			__le32 front_crc;
+			__le32 middle_crc;
+			__le32 data_crc;
+		} __packed *sigblock = enc_buf + ceph_x_encrypt_offset();
+
+		sigblock->len = cpu_to_le32(4*sizeof(u32));
+		sigblock->header_crc = msg->hdr.crc;
+		sigblock->front_crc = msg->footer.front_crc;
+		sigblock->middle_crc = msg->footer.middle_crc;
+		sigblock->data_crc =  msg->footer.data_crc;
+
+		ret = ceph_x_encrypt(&au->session_key, enc_buf,
+				     CEPHX_AU_ENC_BUF_LEN, sizeof(*sigblock));
+		if (ret < 0)
+			return ret;
+
+		*psig = *(__le64 *)(enc_buf + sizeof(u32));
+	} else {
+		struct {
+			__le32 header_crc;
+			__le32 front_crc;
+			__le32 front_len;
+			__le32 middle_crc;
+			__le32 middle_len;
+			__le32 data_crc;
+			__le32 data_len;
+			__le32 seq_lower_word;
+		} __packed *sigblock = enc_buf;
+		struct {
+			__le64 a, b, c, d;
+		} __packed *penc = enc_buf;
+		int ciphertext_len;
+
+		sigblock->header_crc = msg->hdr.crc;
+		sigblock->front_crc = msg->footer.front_crc;
+		sigblock->front_len = msg->hdr.front_len;
+		sigblock->middle_crc = msg->footer.middle_crc;
+		sigblock->middle_len = msg->hdr.middle_len;
+		sigblock->data_crc =  msg->footer.data_crc;
+		sigblock->data_len = msg->hdr.data_len;
+		sigblock->seq_lower_word = *(__le32 *)&msg->hdr.seq;
+
+		/* no leading len, no ceph_x_encrypt_header */
+		ret = ceph_crypt(&au->session_key, true, enc_buf,
+				 CEPHX_AU_ENC_BUF_LEN, sizeof(*sigblock),
+				 &ciphertext_len);
+		if (ret)
+			return ret;
+
+		*psig = penc->a ^ penc->b ^ penc->c ^ penc->d;
+	}
 
-	*psig = *(__le64 *)(enc_buf + sizeof(u32));
 	return 0;
 }
 
@@ -774,6 +914,7 @@ static const struct ceph_auth_client_ops ceph_x_ops = {
 	.handle_reply = ceph_x_handle_reply,
 	.create_authorizer = ceph_x_create_authorizer,
 	.update_authorizer = ceph_x_update_authorizer,
+	.add_authorizer_challenge = ceph_x_add_authorizer_challenge,
 	.verify_authorizer_reply = ceph_x_verify_authorizer_reply,
 	.invalidate_authorizer = ceph_x_invalidate_authorizer,
 	.reset =  ceph_x_reset,
diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
index 671d30576c4f..a7cd203aacc2 100644
--- a/net/ceph/auth_x_protocol.h
+++ b/net/ceph/auth_x_protocol.h
@@ -69,6 +69,13 @@ struct ceph_x_authorize_a {
 struct ceph_x_authorize_b {
 	__u8 struct_v;
 	__le64 nonce;
+	__u8 have_challenge;
+	__le64 server_challenge_plus_one;
+} __attribute__ ((packed));
+
+struct ceph_x_authorize_challenge {
+	__u8 struct_v;
+	__le64 server_challenge;
 } __attribute__ ((packed));
 
 struct ceph_x_authorize_reply {
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 98ea28dc03f9..5a8075d9f2e7 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -588,9 +588,15 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	int ret;
 	struct kvec iov;
 
-	/* sendpage cannot properly handle pages with page_count == 0,
-	 * we need to fallback to sendmsg if that's the case */
-	if (page_count(page) >= 1)
+	/*
+	 * sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fall back to sendmsg if that's the case.
+	 *
+	 * Same goes for slab pages: skb_can_coalesce() allows
+	 * coalescing neighboring slab objects into a single frag which
+	 * triggers one of hardened usercopy checks.
+	 */
+	if (page_count(page) >= 1 && !PageSlab(page))
 		return __ceph_tcp_sendpage(sock, page, offset, size, more);
 
 	iov.iov_base = kmap(page) + offset;
@@ -1388,30 +1394,26 @@ static void prepare_write_keepalive(struct ceph_connection *con)
  * Connection negotiation.
  */
 
-static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection *con,
-						int *auth_proto)
+static int get_connect_authorizer(struct ceph_connection *con)
 {
 	struct ceph_auth_handshake *auth;
+	int auth_proto;
 
 	if (!con->ops->get_authorizer) {
+		con->auth = NULL;
 		con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
 		con->out_connect.authorizer_len = 0;
-		return NULL;
+		return 0;
 	}
 
-	/* Can't hold the mutex while getting authorizer */
-	mutex_unlock(&con->mutex);
-	auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry);
-	mutex_lock(&con->mutex);
-
+	auth = con->ops->get_authorizer(con, &auth_proto, con->auth_retry);
 	if (IS_ERR(auth))
-		return auth;
-	if (con->state != CON_STATE_NEGOTIATING)
-		return ERR_PTR(-EAGAIN);
+		return PTR_ERR(auth);
 
-	con->auth_reply_buf = auth->authorizer_reply_buf;
-	con->auth_reply_buf_len = auth->authorizer_reply_buf_len;
-	return auth;
+	con->auth = auth;
+	con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
+	con->out_connect.authorizer_len = cpu_to_le32(auth->authorizer_buf_len);
+	return 0;
 }
 
 /*
@@ -1427,12 +1429,22 @@ static void prepare_write_banner(struct ceph_connection *con)
 	con_flag_set(con, CON_FLAG_WRITE_PENDING);
 }
 
+static void __prepare_write_connect(struct ceph_connection *con)
+{
+	con_out_kvec_add(con, sizeof(con->out_connect), &con->out_connect);
+	if (con->auth)
+		con_out_kvec_add(con, con->auth->authorizer_buf_len,
+				 con->auth->authorizer_buf);
+
+	con->out_more = 0;
+	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+}
+
 static int prepare_write_connect(struct ceph_connection *con)
 {
 	unsigned int global_seq = get_global_seq(con->msgr, 0);
 	int proto;
-	int auth_proto;
-	struct ceph_auth_handshake *auth;
+	int ret;
 
 	switch (con->peer_name.type) {
 	case CEPH_ENTITY_TYPE_MON:
@@ -1459,24 +1471,11 @@ static int prepare_write_connect(struct ceph_connection *con)
 	con->out_connect.protocol_version = cpu_to_le32(proto);
 	con->out_connect.flags = 0;
 
-	auth_proto = CEPH_AUTH_UNKNOWN;
-	auth = get_connect_authorizer(con, &auth_proto);
-	if (IS_ERR(auth))
-		return PTR_ERR(auth);
-
-	con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
-	con->out_connect.authorizer_len = auth ?
-		cpu_to_le32(auth->authorizer_buf_len) : 0;
-
-	con_out_kvec_add(con, sizeof (con->out_connect),
-					&con->out_connect);
-	if (auth && auth->authorizer_buf_len)
-		con_out_kvec_add(con, auth->authorizer_buf_len,
-					auth->authorizer_buf);
-
-	con->out_more = 0;
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+	ret = get_connect_authorizer(con);
+	if (ret)
+		return ret;
 
+	__prepare_write_connect(con);
 	return 0;
 }
 
@@ -1737,11 +1736,21 @@ static int read_partial_connect(struct ceph_connection *con)
 	if (ret <= 0)
 		goto out;
 
-	size = le32_to_cpu(con->in_reply.authorizer_len);
-	end += size;
-	ret = read_partial(con, end, size, con->auth_reply_buf);
-	if (ret <= 0)
-		goto out;
+	if (con->auth) {
+		size = le32_to_cpu(con->in_reply.authorizer_len);
+		if (size > con->auth->authorizer_reply_buf_len) {
+			pr_err("authorizer reply too big: %d > %zu\n", size,
+			       con->auth->authorizer_reply_buf_len);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		end += size;
+		ret = read_partial(con, end, size,
+				   con->auth->authorizer_reply_buf);
+		if (ret <= 0)
+			goto out;
+	}
 
 	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
 	     con, (int)con->in_reply.tag,
@@ -1749,7 +1758,6 @@ static int read_partial_connect(struct ceph_connection *con)
 	     le32_to_cpu(con->in_reply.global_seq));
 out:
 	return ret;
-
 }
 
 /*
@@ -2033,13 +2041,28 @@ static int process_connect(struct ceph_connection *con)
 
 	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
 
-	if (con->auth_reply_buf) {
+	if (con->auth) {
 		/*
 		 * Any connection that defines ->get_authorizer()
-		 * should also define ->verify_authorizer_reply().
+		 * should also define ->add_authorizer_challenge() and
+		 * ->verify_authorizer_reply().
+		 *
 		 * See get_connect_authorizer().
 		 */
-		ret = con->ops->verify_authorizer_reply(con, 0);
+		if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
+			ret = con->ops->add_authorizer_challenge(
+				    con, con->auth->authorizer_reply_buf,
+				    le32_to_cpu(con->in_reply.authorizer_len));
+			if (ret < 0)
+				return ret;
+
+			con_out_kvec_reset(con);
+			__prepare_write_connect(con);
+			prepare_read_connect(con);
+			return 0;
+		}
+
+		ret = con->ops->verify_authorizer_reply(con);
 		if (ret < 0) {
 			con->error_msg = "bad authorize reply";
 			return ret;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 0ffeb60cfe67..70ccb0716fc5 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -4478,14 +4478,24 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
 	return auth;
 }
 
+static int add_authorizer_challenge(struct ceph_connection *con,
+				    void *challenge_buf, int challenge_buf_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_osd_client *osdc = o->o_osdc;
+	struct ceph_auth_client *ac = osdc->client->monc.auth;
+
+	return ceph_auth_add_authorizer_challenge(ac, o->o_auth.authorizer,
+					    challenge_buf, challenge_buf_len);
+}
 
-static int verify_authorizer_reply(struct ceph_connection *con, int len)
+static int verify_authorizer_reply(struct ceph_connection *con)
 {
 	struct ceph_osd *o = con->private;
 	struct ceph_osd_client *osdc = o->o_osdc;
 	struct ceph_auth_client *ac = osdc->client->monc.auth;
 
-	return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer, len);
+	return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer);
 }
 
 static int invalidate_authorizer(struct ceph_connection *con)
@@ -4519,6 +4529,7 @@ static const struct ceph_connection_operations osd_con_ops = {
 	.put = put_osd_con,
 	.dispatch = dispatch,
 	.get_authorizer = get_authorizer,
+	.add_authorizer_challenge = add_authorizer_challenge,
 	.verify_authorizer_reply = verify_authorizer_reply,
 	.invalidate_authorizer = invalidate_authorizer,
 	.alloc_msg = alloc_msg,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4fa4011feec1..146502f310ce 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -754,8 +754,9 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 			return -EINVAL;
 		}
 
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
-			netdev_rx_csum_fault(skb->dev);
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(NULL);
 	}
 	return 0;
 fault:
diff --git a/net/core/dev.c b/net/core/dev.c
index b85e789044d5..071c589f7994 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1664,6 +1664,28 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
+/**
+ *	call_netdevice_notifiers_mtu - call all network notifier blocks
+ *	@val: value passed unmodified to notifier function
+ *	@dev: net_device pointer passed unmodified to notifier function
+ *	@arg: additional u32 argument passed to the notifier function
+ *
+ *	Call all network notifier blocks.  Parameters and return value
+ *	are as for raw_notifier_call_chain().
+ */
+static int call_netdevice_notifiers_mtu(unsigned long val,
+					struct net_device *dev, u32 arg)
+{
+	struct netdev_notifier_info_ext info = {
+		.info.dev = dev,
+		.ext.mtu = arg,
+	};
+
+	BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0);
+
+	return call_netdevice_notifiers_info(val, dev, &info.info);
+}
+
 #ifdef CONFIG_NET_INGRESS
 static struct static_key ingress_needed __read_mostly;
 
@@ -4734,6 +4756,10 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+
+	/* eth_type_trans() assumes pkt_type is PACKET_HOST */
+	skb->pkt_type = PACKET_HOST;
+
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
@@ -6589,14 +6615,16 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 	err = __dev_set_mtu(dev, new_mtu);
 
 	if (!err) {
-		err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+		err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
+						   orig_mtu);
 		err = notifier_to_errno(err);
 		if (err) {
 			/* setting mtu back and notifying everyone again,
 			 * so that they have a chance to revert changes.
 			 */
 			__dev_set_mtu(dev, orig_mtu);
-			call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+			call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
+						     new_mtu);
 		}
 	}
 	return err;
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 7913771ec474..a8a9938aeceb 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -2397,13 +2397,17 @@ roll_back:
 	return ret;
 }
 
-static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr)
+static int ethtool_set_per_queue(struct net_device *dev,
+				 void __user *useraddr, u32 sub_cmd)
 {
 	struct ethtool_per_queue_op per_queue_opt;
 
 	if (copy_from_user(&per_queue_opt, useraddr, sizeof(per_queue_opt)))
 		return -EFAULT;
 
+	if (per_queue_opt.sub_command != sub_cmd)
+		return -EINVAL;
+
 	switch (per_queue_opt.sub_command) {
 	case ETHTOOL_GCOALESCE:
 		return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt);
@@ -2669,7 +2673,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 		rc = ethtool_get_phy_stats(dev, useraddr);
 		break;
 	case ETHTOOL_PERQUEUE:
-		rc = ethtool_set_per_queue(dev, useraddr);
+		rc = ethtool_set_per_queue(dev, useraddr, sub_cmd);
 		break;
 	case ETHTOOL_GLINKSETTINGS:
 		rc = ethtool_get_link_ksettings(dev, useraddr);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 862d63ec56e4..ab7c50026cae 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -538,8 +538,8 @@ ip_proto_again:
 		break;
 	}
 
-	if (dissector_uses_key(flow_dissector,
-			       FLOW_DISSECTOR_KEY_PORTS)) {
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) &&
+	    !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) {
 		key_ports = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_PORTS,
 						      target_container);
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 46e8830c1979..2e4eef71471d 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -104,6 +104,7 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 		iterate_fd(p->files, 0, update_classid_sock,
 			   (void *)(unsigned long)cs->classid);
 		task_unlock(p);
+		cond_resched();
 	}
 	css_task_iter_end(&it);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 194e844e1021..928a0b84469d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2368,6 +2368,12 @@ struct net_device *rtnl_create_link(struct net *net,
 	else if (ops->get_num_rx_queues)
 		num_rx_queues = ops->get_num_rx_queues();
 
+	if (num_tx_queues < 1 || num_tx_queues > 4096)
+		return ERR_PTR(-EINVAL);
+
+	if (num_rx_queues < 1 || num_rx_queues > 4096)
+		return ERR_PTR(-EINVAL);
+
 	err = -ENOMEM;
 	dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
 			       ops->setup, num_tx_queues, num_rx_queues);
@@ -2981,6 +2987,11 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		pr_info("PF_BRIDGE: FDB add only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
@@ -3084,6 +3095,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		pr_info("PF_BRIDGE: FDB delete only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 84c731aef0d8..dca1fed0d7da 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1578,6 +1578,21 @@ done:
 }
 EXPORT_SYMBOL(___pskb_trim);
 
+/* Note : use pskb_trim_rcsum() instead of calling this directly
+ */
+int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		int delta = skb->len - len;
+
+		skb->csum = csum_block_sub(skb->csum,
+					   skb_checksum(skb, len, delta, 0),
+					   len);
+	}
+	return __pskb_trim(skb, len);
+}
+EXPORT_SYMBOL(pskb_trim_rcsum_slow);
+
 /**
  *	__pskb_pull_tail - advance tail of skb header
  *	@skb: buffer to reallocate
@@ -2425,20 +2440,27 @@ EXPORT_SYMBOL(skb_queue_purge);
 /**
  *	skb_rbtree_purge - empty a skb rbtree
  *	@root: root of the rbtree to empty
+ *	Return value: the sum of truesizes of all purged skbs.
  *
  *	Delete all buffers on an &sk_buff rbtree. Each buffer is removed from
  *	the list and one reference dropped. This function does not take
  *	any lock. Synchronization should be handled by the caller (e.g., TCP
  *	out-of-order queue is protected by the socket lock).
  */
-void skb_rbtree_purge(struct rb_root *root)
+unsigned int skb_rbtree_purge(struct rb_root *root)
 {
-	struct sk_buff *skb, *next;
+	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
 
-	rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
-		kfree_skb(skb);
+	while (p) {
+		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
 
-	*root = RB_ROOT;
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, root);
+		sum += skb->truesize;
+		kfree_skb(skb);
+	}
+	return sum;
 }
 
 /**
@@ -4399,6 +4421,10 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 4a05d7876850..84ff43acd427 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -605,11 +605,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	if (sk->sk_state == DCCP_LISTEN) {
 		if (dh->dccph_type == DCCP_PKT_REQUEST) {
 			/* It is possible that we process SYN packets from backlog,
-			 * so we need to make sure to disable BH right there.
+			 * so we need to make sure to disable BH and RCU right there.
 			 */
+			rcu_read_lock();
 			local_bh_disable();
 			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
 			local_bh_enable();
+			rcu_read_unlock();
 			if (!acceptable)
 				return 1;
 			consume_skb(skb);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 6697b180e122..28ad6f187e19 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -493,9 +493,11 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 
 		dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
 							      ireq->ir_rmt_addr);
+		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq_opt_deref(ireq));
+					    rcu_dereference(ireq->ireq_opt));
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index 5ac778962e4e..78916c510d9a 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -16,37 +16,19 @@ typedef unsigned __bitwise__ lowpan_rx_result;
 #define LOWPAN_DISPATCH_FRAG1           0xc0
 #define LOWPAN_DISPATCH_FRAGN           0xe0
 
-struct lowpan_create_arg {
+struct frag_lowpan_compare_key {
 	u16 tag;
 	u16 d_size;
-	const struct ieee802154_addr *src;
-	const struct ieee802154_addr *dst;
+	struct ieee802154_addr src;
+	struct ieee802154_addr dst;
 };
 
-/* Equivalent of ipv4 struct ip
+/* Equivalent of ipv4 struct ipq
  */
 struct lowpan_frag_queue {
 	struct inet_frag_queue	q;
-
-	u16			tag;
-	u16			d_size;
-	struct ieee802154_addr	saddr;
-	struct ieee802154_addr	daddr;
 };
 
-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
-{
-	switch (a->mode) {
-	case IEEE802154_ADDR_LONG:
-		return (((__force u64)a->extended_addr) >> 32) ^
-			(((__force u64)a->extended_addr) & 0xffffffff);
-	case IEEE802154_ADDR_SHORT:
-		return (__force u32)(a->short_addr + (a->pan_id << 16));
-	default:
-		return 0;
-	}
-}
-
 int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
 void lowpan_net_frag_exit(void);
 int lowpan_net_frag_init(void);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index f85b08baff16..aab1e2dfdfca 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
 static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
 			     struct sk_buff *prev, struct net_device *ldev);
 
-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
-				     const struct ieee802154_addr *saddr,
-				     const struct ieee802154_addr *daddr)
-{
-	net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
-	return jhash_3words(ieee802154_addr_hash(saddr),
-			    ieee802154_addr_hash(daddr),
-			    (__force u32)(tag + (d_size << 16)),
-			    lowpan_frags.rnd);
-}
-
-static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
-{
-	const struct lowpan_frag_queue *fq;
-
-	fq = container_of(q, struct lowpan_frag_queue, q);
-	return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
-}
-
-static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct lowpan_frag_queue *fq;
-	const struct lowpan_create_arg *arg = a;
-
-	fq = container_of(q, struct lowpan_frag_queue, q);
-	return	fq->tag == arg->tag && fq->d_size == arg->d_size &&
-		ieee802154_addr_equal(&fq->saddr, arg->src) &&
-		ieee802154_addr_equal(&fq->daddr, arg->dst);
-}
-
 static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
 {
-	const struct lowpan_create_arg *arg = a;
+	const struct frag_lowpan_compare_key *key = a;
 	struct lowpan_frag_queue *fq;
 
 	fq = container_of(q, struct lowpan_frag_queue, q);
 
-	fq->tag = arg->tag;
-	fq->d_size = arg->d_size;
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
+	BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
+	memcpy(&q->key, key, sizeof(*key));
 }
 
 static void lowpan_frag_expire(unsigned long data)
@@ -93,10 +61,10 @@ static void lowpan_frag_expire(unsigned long data)
 	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
-	inet_frag_kill(&fq->q, &lowpan_frags);
+	inet_frag_kill(&fq->q);
 out:
 	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q, &lowpan_frags);
+	inet_frag_put(&fq->q);
 }
 
 static inline struct lowpan_frag_queue *
@@ -104,25 +72,20 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
 	const struct ieee802154_addr *src,
 	const struct ieee802154_addr *dst)
 {
-	struct inet_frag_queue *q;
-	struct lowpan_create_arg arg;
-	unsigned int hash;
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
+	struct frag_lowpan_compare_key key = {};
+	struct inet_frag_queue *q;
 
-	arg.tag = cb->d_tag;
-	arg.d_size = cb->d_size;
-	arg.src = src;
-	arg.dst = dst;
-
-	hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
+	key.tag = cb->d_tag;
+	key.d_size = cb->d_size;
+	key.src = *src;
+	key.dst = *dst;
 
-	q = inet_frag_find(&ieee802154_lowpan->frags,
-			   &lowpan_frags, &arg, hash);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	q = inet_frag_find(&ieee802154_lowpan->frags, &key);
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct lowpan_frag_queue, q);
 }
 
@@ -229,7 +192,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
 	struct sk_buff *fp, *head = fq->q.fragments;
 	int sum_truesize;
 
-	inet_frag_kill(&fq->q, &lowpan_frags);
+	inet_frag_kill(&fq->q);
 
 	/* Make the one we just received the head. */
 	if (prev) {
@@ -408,7 +371,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 	struct lowpan_frag_queue *fq;
 	struct net *net = dev_net(skb->dev);
 	struct lowpan_802154_cb *cb = lowpan_802154_cb(skb);
-	struct ieee802154_hdr hdr;
+	struct ieee802154_hdr hdr = {};
 	int err;
 
 	if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0)
@@ -437,7 +400,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 		ret = lowpan_frag_queue(fq, skb, frag_type);
 		spin_unlock(&fq->q.lock);
 
-		inet_frag_put(&fq->q, &lowpan_frags);
+		inet_frag_put(&fq->q);
 		return ret;
 	}
 
@@ -447,24 +410,22 @@ err:
 }
 
 #ifdef CONFIG_SYSCTL
-static int zero;
 
 static struct ctl_table lowpan_frags_ns_ctl_table[] = {
 	{
 		.procname	= "6lowpanfrag_high_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ieee802154_lowpan.frags.low_thresh
 	},
 	{
 		.procname	= "6lowpanfrag_low_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra2		= &init_net.ieee802154_lowpan.frags.high_thresh
 	},
 	{
@@ -580,14 +541,20 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
+	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+	ieee802154_lowpan->frags.f = &lowpan_frags;
 
-	inet_frags_init_net(&ieee802154_lowpan->frags);
-
-	return lowpan_frags_ns_sysctl_register(net);
+	res = inet_frags_init_net(&ieee802154_lowpan->frags);
+	if (res < 0)
+		return res;
+	res = lowpan_frags_ns_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&ieee802154_lowpan->frags);
+	return res;
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
@@ -596,7 +563,7 @@ static void __net_exit lowpan_frags_exit_net(struct net *net)
 		net_ieee802154_lowpan(net);
 
 	lowpan_frags_ns_sysctl_unregister(net);
-	inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+	inet_frags_exit_net(&ieee802154_lowpan->frags);
 }
 
 static struct pernet_operations lowpan_frags_ops = {
@@ -604,32 +571,63 @@ static struct pernet_operations lowpan_frags_ops = {
 	.exit = lowpan_frags_exit_net,
 };
 
-int __init lowpan_net_frag_init(void)
+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
 {
-	int ret;
+	return jhash2(data,
+		      sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
 
-	ret = lowpan_frags_sysctl_register();
-	if (ret)
-		return ret;
+static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
 
-	ret = register_pernet_subsys(&lowpan_frags_ops);
-	if (ret)
-		goto err_pernet;
+	return jhash2((const u32 *)&fq->key,
+		      sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_lowpan_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params lowpan_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= lowpan_key_hashfn,
+	.obj_hashfn		= lowpan_obj_hashfn,
+	.obj_cmpfn		= lowpan_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+
+int __init lowpan_net_frag_init(void)
+{
+	int ret;
 
-	lowpan_frags.hashfn = lowpan_hashfn;
 	lowpan_frags.constructor = lowpan_frag_init;
 	lowpan_frags.destructor = NULL;
 	lowpan_frags.qsize = sizeof(struct frag_queue);
-	lowpan_frags.match = lowpan_frag_match;
 	lowpan_frags.frag_expire = lowpan_frag_expire;
 	lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
+	lowpan_frags.rhash_params = lowpan_rhash_params;
 	ret = inet_frags_init(&lowpan_frags);
 	if (ret)
-		goto err_pernet;
+		goto out;
 
+	ret = lowpan_frags_sysctl_register();
+	if (ret)
+		goto err_sysctl;
+
+	ret = register_pernet_subsys(&lowpan_frags_ops);
+	if (ret)
+		goto err_pernet;
+out:
 	return ret;
 err_pernet:
 	lowpan_frags_sysctl_unregister();
+err_sysctl:
+	inet_frags_fini(&lowpan_frags);
 	return ret;
 }
 
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 65a15889d432..571d079e262f 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1512,7 +1512,7 @@ static int cipso_v4_parsetag_loc(const struct cipso_v4_doi *doi_def,
  *
  * Description:
  * Parse the packet's IP header looking for a CIPSO option.  Returns a pointer
- * to the start of the CIPSO option on success, NULL if one if not found.
+ * to the start of the CIPSO option on success, NULL if one is not found.
  *
  */
 unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
@@ -1522,10 +1522,8 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
 	int optlen;
 	int taglen;
 
-	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) {
+	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 1; ) {
 		switch (optptr[0]) {
-		case IPOPT_CIPSO:
-			return optptr;
 		case IPOPT_END:
 			return NULL;
 		case IPOPT_NOOP:
@@ -1534,6 +1532,11 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
 		default:
 			taglen = optptr[1];
 		}
+		if (!taglen || taglen > optlen)
+			return NULL;
+		if (optptr[0] == IPOPT_CIPSO)
+			return optptr;
+
 		optlen -= taglen;
 		optptr += taglen;
 	}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6a2ef162088d..9364c39d0555 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1171,7 +1171,8 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct netdev_notifier_changeupper_info *info;
+	struct netdev_notifier_changeupper_info *upper_info = ptr;
+	struct netdev_notifier_info_ext *info_ext = ptr;
 	struct in_device *in_dev;
 	struct net *net = dev_net(dev);
 	unsigned int flags;
@@ -1206,16 +1207,19 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 			fib_sync_up(dev, RTNH_F_LINKDOWN);
 		else
 			fib_sync_down_dev(dev, event, false);
-		/* fall through */
+		rt_cache_flush(net);
+		break;
 	case NETDEV_CHANGEMTU:
+		fib_sync_mtu(dev, info_ext->ext.mtu);
 		rt_cache_flush(net);
 		break;
 	case NETDEV_CHANGEUPPER:
-		info = ptr;
+		upper_info = ptr;
 		/* flush all routes if dev is linked to or unlinked from
 		 * an L3 master device (e.g., VRF)
 		 */
-		if (info->upper_dev && netif_is_l3_master(info->upper_dev))
+		if (upper_info->upper_dev &&
+		    netif_is_l3_master(upper_info->upper_dev))
 			fib_disable_ip(dev, NETDEV_DOWN, true);
 		break;
 	}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index a88dab33cdf6..90c654012510 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1377,6 +1377,56 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 	return ret;
 }
 
+/* Update the PMTU of exceptions when:
+ * - the new MTU of the first hop becomes smaller than the PMTU
+ * - the old MTU was the same as the PMTU, and it limited discovery of
+ *   larger MTUs on the path. With that limit raised, we can now
+ *   discover larger MTUs
+ * A special case is locked exceptions, for which the PMTU is smaller
+ * than the minimal accepted PMTU:
+ * - if the new MTU is greater than the PMTU, don't make any change
+ * - otherwise, unlock and set PMTU
+ */
+static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
+{
+	struct fnhe_hash_bucket *bucket;
+	int i;
+
+	bucket = rcu_dereference_protected(nh->nh_exceptions, 1);
+	if (!bucket)
+		return;
+
+	for (i = 0; i < FNHE_HASH_SIZE; i++) {
+		struct fib_nh_exception *fnhe;
+
+		for (fnhe = rcu_dereference_protected(bucket[i].chain, 1);
+		     fnhe;
+		     fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) {
+			if (fnhe->fnhe_mtu_locked) {
+				if (new <= fnhe->fnhe_pmtu) {
+					fnhe->fnhe_pmtu = new;
+					fnhe->fnhe_mtu_locked = false;
+				}
+			} else if (new < fnhe->fnhe_pmtu ||
+				   orig == fnhe->fnhe_pmtu) {
+				fnhe->fnhe_pmtu = new;
+			}
+		}
+	}
+}
+
+void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
+{
+	unsigned int hash = fib_devindex_hashfn(dev->ifindex);
+	struct hlist_head *head = &fib_info_devhash[hash];
+	struct fib_nh *nh;
+
+	hlist_for_each_entry(nh, head, nh_hash) {
+		if (nh->nh_dev == dev)
+			nh_update_mtu(nh, dev->mtu, orig_mtu);
+	}
+}
+
 /* Event              force Flags           Description
  * NETDEV_CHANGE      0     LINKDOWN        Carrier OFF, not for scope host
  * NETDEV_DOWN        0     LINKDOWN|DEAD   Link down, not for scope host
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d1cab49393e2..528a6777cda0 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -410,7 +410,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
-	opt = ireq_opt_deref(ireq);
+	rcu_read_lock();
+	opt = rcu_dereference(ireq->ireq_opt);
 
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
@@ -424,11 +425,13 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 		goto no_route;
 	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
+	rcu_read_unlock();
 	return &rt->dst;
 
 route_err:
 	ip_rt_put(rt);
 no_route:
+	rcu_read_unlock();
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index f8b41aaac76f..5a8c26c9872d 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -25,12 +25,6 @@
 #include <net/inet_frag.h>
 #include <net/inet_ecn.h>
 
-#define INETFRAGS_EVICT_BUCKETS   128
-#define INETFRAGS_EVICT_MAX	  512
-
-/* don't rebuild inetfrag table with new secret more often than this */
-#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
-
 /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
  * Value : 0xff if frame should be dropped.
  *         0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = {
 };
 EXPORT_SYMBOL(ip_frag_ecn_table);
 
-static unsigned int
-inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
-{
-	return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
-}
-
-static bool inet_frag_may_rebuild(struct inet_frags *f)
-{
-	return time_after(jiffies,
-	       f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
-}
-
-static void inet_frag_secret_rebuild(struct inet_frags *f)
-{
-	int i;
-
-	write_seqlock_bh(&f->rnd_seqlock);
-
-	if (!inet_frag_may_rebuild(f))
-		goto out;
-
-	get_random_bytes(&f->rnd, sizeof(u32));
-
-	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
-		struct inet_frag_bucket *hb;
-		struct inet_frag_queue *q;
-		struct hlist_node *n;
-
-		hb = &f->hash[i];
-		spin_lock(&hb->chain_lock);
-
-		hlist_for_each_entry_safe(q, n, &hb->chain, list) {
-			unsigned int hval = inet_frag_hashfn(f, q);
-
-			if (hval != i) {
-				struct inet_frag_bucket *hb_dest;
-
-				hlist_del(&q->list);
-
-				/* Relink to new hash chain. */
-				hb_dest = &f->hash[hval];
-
-				/* This is the only place where we take
-				 * another chain_lock while already holding
-				 * one.  As this will not run concurrently,
-				 * we cannot deadlock on hb_dest lock below, if its
-				 * already locked it will be released soon since
-				 * other caller cannot be waiting for hb lock
-				 * that we've taken above.
-				 */
-				spin_lock_nested(&hb_dest->chain_lock,
-						 SINGLE_DEPTH_NESTING);
-				hlist_add_head(&q->list, &hb_dest->chain);
-				spin_unlock(&hb_dest->chain_lock);
-			}
-		}
-		spin_unlock(&hb->chain_lock);
-	}
-
-	f->rebuild = false;
-	f->last_rebuild_jiffies = jiffies;
-out:
-	write_sequnlock_bh(&f->rnd_seqlock);
-}
-
-static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
-{
-	if (!hlist_unhashed(&q->list_evictor))
-		return false;
-
-	return q->net->low_thresh == 0 ||
-	       frag_mem_limit(q->net) >= q->net->low_thresh;
-}
-
-static unsigned int
-inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
-{
-	struct inet_frag_queue *fq;
-	struct hlist_node *n;
-	unsigned int evicted = 0;
-	HLIST_HEAD(expired);
-
-	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))
-			continue;
-
-		hlist_add_head(&fq->list_evictor, &expired);
-		++evicted;
-	}
-
-	spin_unlock(&hb->chain_lock);
-
-	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
-		f->frag_expire((unsigned long) fq);
-
-	return evicted;
-}
-
-static void inet_frag_worker(struct work_struct *work)
-{
-	unsigned int budget = INETFRAGS_EVICT_BUCKETS;
-	unsigned int i, evicted = 0;
-	struct inet_frags *f;
-
-	f = container_of(work, struct inet_frags, frags_work);
-
-	BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
-
-	local_bh_disable();
-
-	for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) {
-		evicted += inet_evict_bucket(f, &f->hash[i]);
-		i = (i + 1) & (INETFRAGS_HASHSZ - 1);
-		if (evicted > INETFRAGS_EVICT_MAX)
-			break;
-	}
-
-	f->next_bucket = i;
-
-	local_bh_enable();
-
-	if (f->rebuild && inet_frag_may_rebuild(f))
-		inet_frag_secret_rebuild(f);
-}
-
-static void inet_frag_schedule_worker(struct inet_frags *f)
-{
-	if (unlikely(!work_pending(&f->frags_work)))
-		schedule_work(&f->frags_work);
-}
-
 int inet_frags_init(struct inet_frags *f)
 {
-	int i;
-
-	INIT_WORK(&f->frags_work, inet_frag_worker);
-
-	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
-		struct inet_frag_bucket *hb = &f->hash[i];
-
-		spin_lock_init(&hb->chain_lock);
-		INIT_HLIST_HEAD(&hb->chain);
-	}
-
-	seqlock_init(&f->rnd_seqlock);
-	f->last_rebuild_jiffies = 0;
 	f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
 					    NULL);
 	if (!f->frags_cachep)
@@ -214,83 +59,75 @@ EXPORT_SYMBOL(inet_frags_init);
 
 void inet_frags_fini(struct inet_frags *f)
 {
-	cancel_work_sync(&f->frags_work);
+	/* We must wait that all inet_frag_destroy_rcu() have completed. */
+	rcu_barrier();
+
 	kmem_cache_destroy(f->frags_cachep);
+	f->frags_cachep = NULL;
 }
 EXPORT_SYMBOL(inet_frags_fini);
 
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
+static void inet_frags_free_cb(void *ptr, void *arg)
 {
-	unsigned int seq;
-	int i;
+	struct inet_frag_queue *fq = ptr;
 
-	nf->low_thresh = 0;
-
-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]);
-
-	local_bh_enable();
-	cond_resched();
-
-	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    sum_frag_mem_limit(nf))
-		goto evict_again;
-}
-EXPORT_SYMBOL(inet_frags_exit_net);
-
-static struct inet_frag_bucket *
-get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
-__acquires(hb->chain_lock)
-{
-	struct inet_frag_bucket *hb;
-	unsigned int seq, hash;
-
- restart:
-	seq = read_seqbegin(&f->rnd_seqlock);
-
-	hash = inet_frag_hashfn(f, fq);
-	hb = &f->hash[hash];
+	/* If we can not cancel the timer, it means this frag_queue
+	 * is already disappearing, we have nothing to do.
+	 * Otherwise, we own a refcount until the end of this function.
+	 */
+	if (!del_timer(&fq->timer))
+		return;
 
-	spin_lock(&hb->chain_lock);
-	if (read_seqretry(&f->rnd_seqlock, seq)) {
-		spin_unlock(&hb->chain_lock);
-		goto restart;
+	spin_lock_bh(&fq->lock);
+	if (!(fq->flags & INET_FRAG_COMPLETE)) {
+		fq->flags |= INET_FRAG_COMPLETE;
+		atomic_dec(&fq->refcnt);
 	}
+	spin_unlock_bh(&fq->lock);
 
-	return hb;
+	inet_frag_put(fq);
 }
 
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frags_exit_net(struct netns_frags *nf)
 {
-	struct inet_frag_bucket *hb;
+	nf->low_thresh = 0; /* prevent creation of new frags */
 
-	hb = get_frag_bucket_locked(fq, f);
-	hlist_del(&fq->list);
-	fq->flags |= INET_FRAG_COMPLETE;
-	spin_unlock(&hb->chain_lock);
+	rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
 }
+EXPORT_SYMBOL(inet_frags_exit_net);
 
-void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frag_kill(struct inet_frag_queue *fq)
 {
 	if (del_timer(&fq->timer))
 		atomic_dec(&fq->refcnt);
 
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
-		fq_unlink(fq, f);
+		struct netns_frags *nf = fq->net;
+
+		fq->flags |= INET_FRAG_COMPLETE;
+		rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
 		atomic_dec(&fq->refcnt);
 	}
 }
 EXPORT_SYMBOL(inet_frag_kill);
 
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
+static void inet_frag_destroy_rcu(struct rcu_head *head)
+{
+	struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
+						 rcu);
+	struct inet_frags *f = q->net->f;
+
+	if (f->destructor)
+		f->destructor(q);
+	kmem_cache_free(f->frags_cachep, q);
+}
+
+void inet_frag_destroy(struct inet_frag_queue *q)
 {
 	struct sk_buff *fp;
 	struct netns_frags *nf;
 	unsigned int sum, sum_truesize = 0;
+	struct inet_frags *f;
 
 	WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
 	WARN_ON(del_timer(&q->timer) != 0);
@@ -298,64 +135,35 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 	/* Release all fragment data. */
 	fp = q->fragments;
 	nf = q->net;
-	while (fp) {
-		struct sk_buff *xp = fp->next;
-
-		sum_truesize += fp->truesize;
-		kfree_skb(fp);
-		fp = xp;
+	f = nf->f;
+	if (fp) {
+		do {
+			struct sk_buff *xp = fp->next;
+
+			sum_truesize += fp->truesize;
+			kfree_skb(fp);
+			fp = xp;
+		} while (fp);
+	} else {
+		sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments);
 	}
 	sum = sum_truesize + f->qsize;
 
-	if (f->destructor)
-		f->destructor(q);
-	kmem_cache_free(f->frags_cachep, q);
+	call_rcu(&q->rcu, inet_frag_destroy_rcu);
 
 	sub_frag_mem_limit(nf, sum);
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
-static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
-						struct inet_frag_queue *qp_in,
-						struct inet_frags *f,
-						void *arg)
-{
-	struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
-	struct inet_frag_queue *qp;
-
-#ifdef CONFIG_SMP
-	/* With SMP race we have to recheck hash table, because
-	 * such entry could have been created on other cpu before
-	 * we acquired hash bucket lock.
-	 */
-	hlist_for_each_entry(qp, &hb->chain, list) {
-		if (qp->net == nf && f->match(qp, arg)) {
-			atomic_inc(&qp->refcnt);
-			spin_unlock(&hb->chain_lock);
-			qp_in->flags |= INET_FRAG_COMPLETE;
-			inet_frag_put(qp_in, f);
-			return qp;
-		}
-	}
-#endif
-	qp = qp_in;
-	if (!mod_timer(&qp->timer, jiffies + nf->timeout))
-		atomic_inc(&qp->refcnt);
-
-	atomic_inc(&qp->refcnt);
-	hlist_add_head(&qp->list, &hb->chain);
-
-	spin_unlock(&hb->chain_lock);
-
-	return qp;
-}
-
 static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 					       struct inet_frags *f,
 					       void *arg)
 {
 	struct inet_frag_queue *q;
 
+	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
+		return NULL;
+
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
 	if (!q)
 		return NULL;
@@ -366,75 +174,52 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 
 	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
 	spin_lock_init(&q->lock);
-	atomic_set(&q->refcnt, 1);
+	atomic_set(&q->refcnt, 3);
 
 	return q;
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						struct inet_frags *f,
-						void *arg)
+						void *arg,
+						struct inet_frag_queue **prev)
 {
+	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
 
 	q = inet_frag_alloc(nf, f, arg);
-	if (!q)
-		return NULL;
-
-	return inet_frag_intern(nf, q, f, arg);
-}
-
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
-				       struct inet_frags *f, void *key,
-				       unsigned int hash)
-{
-	struct inet_frag_bucket *hb;
-	struct inet_frag_queue *q;
-	int depth = 0;
-
-	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
-		inet_frag_schedule_worker(f);
+	if (!q) {
+		*prev = ERR_PTR(-ENOMEM);
 		return NULL;
 	}
-
-	if (frag_mem_limit(nf) > nf->low_thresh)
-		inet_frag_schedule_worker(f);
-
-	hash &= (INETFRAGS_HASHSZ - 1);
-	hb = &f->hash[hash];
-
-	spin_lock(&hb->chain_lock);
-	hlist_for_each_entry(q, &hb->chain, list) {
-		if (q->net == nf && f->match(q, key)) {
-			atomic_inc(&q->refcnt);
-			spin_unlock(&hb->chain_lock);
-			return q;
-		}
-		depth++;
-	}
-	spin_unlock(&hb->chain_lock);
-
-	if (depth <= INETFRAGS_MAXDEPTH)
-		return inet_frag_create(nf, f, key);
-
-	if (inet_frag_may_rebuild(f)) {
-		if (!f->rebuild)
-			f->rebuild = true;
-		inet_frag_schedule_worker(f);
+	mod_timer(&q->timer, jiffies + nf->timeout);
+
+	*prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
+						 &q->node, f->rhash_params);
+	if (*prev) {
+		q->flags |= INET_FRAG_COMPLETE;
+		inet_frag_kill(q);
+		inet_frag_destroy(q);
+		return NULL;
 	}
-
-	return ERR_PTR(-ENOBUFS);
+	return q;
 }
-EXPORT_SYMBOL(inet_frag_find);
+EXPORT_SYMBOL(inet_frag_create);
 
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
-				   const char *prefix)
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
-	static const char msg[] = "inet_frag_find: Fragment hash bucket"
-		" list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
-		". Dropping fragment.\n";
+	struct inet_frag_queue *fq = NULL, *prev;
 
-	if (PTR_ERR(q) == -ENOBUFS)
-		net_dbg_ratelimited("%s%s", prefix, msg);
+	rcu_read_lock();
+	prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+	if (!prev)
+		fq = inet_frag_create(nf, key, &prev);
+	if (prev && !IS_ERR(prev)) {
+		fq = prev;
+		if (!atomic_inc_not_zero(&fq->refcnt))
+			fq = NULL;
+	}
+	rcu_read_unlock();
+	return fq;
 }
-EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
+EXPORT_SYMBOL(inet_frag_find);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 752711cd4834..80e48f40c3a8 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -56,27 +56,64 @@
  */
 static const char ip_frag_cache_name[] = "ip4-frags";
 
-struct ipfrag_skb_cb
-{
+/* Use skb->cb to track consecutive/adjacent fragments coming at
+ * the end of the queue. Nodes in the rb-tree queue will
+ * contain "runs" of one or more adjacent fragments.
+ *
+ * Invariants:
+ * - next_frag is NULL at the tail of a "run";
+ * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
+ */
+struct ipfrag_skb_cb {
 	struct inet_skb_parm	h;
-	int			offset;
+	struct sk_buff		*next_frag;
+	int			frag_run_len;
 };
 
-#define FRAG_CB(skb)	((struct ipfrag_skb_cb *)((skb)->cb))
+#define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))
+
+static void ip4_frag_init_run(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
+
+	FRAG_CB(skb)->next_frag = NULL;
+	FRAG_CB(skb)->frag_run_len = skb->len;
+}
+
+/* Append skb to the last "run". */
+static void ip4_frag_append_to_last_run(struct inet_frag_queue *q,
+					struct sk_buff *skb)
+{
+	RB_CLEAR_NODE(&skb->rbnode);
+	FRAG_CB(skb)->next_frag = NULL;
+
+	FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
+	FRAG_CB(q->fragments_tail)->next_frag = skb;
+	q->fragments_tail = skb;
+}
+
+/* Create a new "run" with the skb. */
+static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb)
+{
+	if (q->last_run_head)
+		rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
+			     &q->last_run_head->rbnode.rb_right);
+	else
+		rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
+	rb_insert_color(&skb->rbnode, &q->rb_fragments);
+
+	ip4_frag_init_run(skb);
+	q->fragments_tail = skb;
+	q->last_run_head = skb;
+}
 
 /* Describe an entry in the "incomplete datagrams" queue. */
 struct ipq {
 	struct inet_frag_queue q;
 
-	u32		user;
-	__be32		saddr;
-	__be32		daddr;
-	__be16		id;
-	u8		protocol;
 	u8		ecn; /* RFC3168 support */
 	u16		max_df_size; /* largest frag with DF set seen */
 	int             iif;
-	int             vif;   /* L3 master device index */
 	unsigned int    rid;
 	struct inet_peer *peer;
 };
@@ -88,49 +125,9 @@ static u8 ip4_frag_ecn(u8 tos)
 
 static struct inet_frags ip4_frags;
 
-int ip_frag_mem(struct net *net)
-{
-	return sum_frag_mem_limit(&net->ipv4.frags);
-}
+static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
+			 struct sk_buff *prev_tail, struct net_device *dev);
 
-static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
-			 struct net_device *dev);
-
-struct ip4_create_arg {
-	struct iphdr *iph;
-	u32 user;
-	int vif;
-};
-
-static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
-{
-	net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
-	return jhash_3words((__force u32)id << 16 | prot,
-			    (__force u32)saddr, (__force u32)daddr,
-			    ip4_frags.rnd);
-}
-
-static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
-{
-	const struct ipq *ipq;
-
-	ipq = container_of(q, struct ipq, q);
-	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
-}
-
-static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct ipq *qp;
-	const struct ip4_create_arg *arg = a;
-
-	qp = container_of(q, struct ipq, q);
-	return	qp->id == arg->iph->id &&
-		qp->saddr == arg->iph->saddr &&
-		qp->daddr == arg->iph->daddr &&
-		qp->protocol == arg->iph->protocol &&
-		qp->user == arg->user &&
-		qp->vif == arg->vif;
-}
 
 static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 {
@@ -139,17 +136,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 					       frags);
 	struct net *net = container_of(ipv4, struct net, ipv4);
 
-	const struct ip4_create_arg *arg = a;
+	const struct frag_v4_compare_key *key = a;
 
-	qp->protocol = arg->iph->protocol;
-	qp->id = arg->iph->id;
-	qp->ecn = ip4_frag_ecn(arg->iph->tos);
-	qp->saddr = arg->iph->saddr;
-	qp->daddr = arg->iph->daddr;
-	qp->vif = arg->vif;
-	qp->user = arg->user;
+	q->key.v4 = *key;
+	qp->ecn = 0;
 	qp->peer = q->net->max_dist ?
-		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+		inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
 		NULL;
 }
 
@@ -167,7 +159,7 @@ static void ip4_frag_free(struct inet_frag_queue *q)
 
 static void ipq_put(struct ipq *ipq)
 {
-	inet_frag_put(&ipq->q, &ip4_frags);
+	inet_frag_put(&ipq->q);
 }
 
 /* Kill ipq entry. It is not destroyed immediately,
@@ -175,7 +167,7 @@ static void ipq_put(struct ipq *ipq)
  */
 static void ipq_kill(struct ipq *ipq)
 {
-	inet_frag_kill(&ipq->q, &ip4_frags);
+	inet_frag_kill(&ipq->q);
 }
 
 static bool frag_expire_skip_icmp(u32 user)
@@ -192,8 +184,11 @@ static bool frag_expire_skip_icmp(u32 user)
  */
 static void ip_expire(unsigned long arg)
 {
-	struct ipq *qp;
+	const struct iphdr *iph;
+	struct sk_buff *head = NULL;
 	struct net *net;
+	struct ipq *qp;
+	int err;
 
 	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -206,51 +201,65 @@ static void ip_expire(unsigned long arg)
 
 	ipq_kill(qp);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
+	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
-	if (!inet_frag_evicting(&qp->q)) {
-		struct sk_buff *clone, *head = qp->q.fragments;
-		const struct iphdr *iph;
-		int err;
-
-		__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
+	if (!(qp->q.flags & INET_FRAG_FIRST_IN))
+		goto out;
 
-		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
+	/* sk_buff::dev and sk_buff::rbnode are unionized. So we
+	 * pull the head out of the tree in order to be able to
+	 * deal with head->dev.
+	 */
+	if (qp->q.fragments) {
+		head = qp->q.fragments;
+		qp->q.fragments = head->next;
+	} else {
+		head = skb_rb_first(&qp->q.rb_fragments);
+		if (!head)
 			goto out;
+		if (FRAG_CB(head)->next_frag)
+			rb_replace_node(&head->rbnode,
+					&FRAG_CB(head)->next_frag->rbnode,
+					&qp->q.rb_fragments);
+		else
+			rb_erase(&head->rbnode, &qp->q.rb_fragments);
+		memset(&head->rbnode, 0, sizeof(head->rbnode));
+		barrier();
+	}
+	if (head == qp->q.fragments_tail)
+		qp->q.fragments_tail = NULL;
 
-		head->dev = dev_get_by_index_rcu(net, qp->iif);
-		if (!head->dev)
-			goto out;
+	sub_frag_mem_limit(qp->q.net, head->truesize);
+
+	head->dev = dev_get_by_index_rcu(net, qp->iif);
+	if (!head->dev)
+		goto out;
 
 
-		/* skb has no dst, perform route lookup again */
-		iph = ip_hdr(head);
-		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+	/* skb has no dst, perform route lookup again */
+	iph = ip_hdr(head);
+	err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
-		if (err)
-			goto out;
+	if (err)
+		goto out;
 
-		/* Only an end host needs to send an ICMP
-		 * "Fragment Reassembly Timeout" message, per RFC792.
-		 */
-		if (frag_expire_skip_icmp(qp->user) &&
-		    (skb_rtable(head)->rt_type != RTN_LOCAL))
-			goto out;
+	/* Only an end host needs to send an ICMP
+	 * "Fragment Reassembly Timeout" message, per RFC792.
+	 */
+	if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
+	    (skb_rtable(head)->rt_type != RTN_LOCAL))
+		goto out;
 
-		clone = skb_clone(head, GFP_ATOMIC);
+	spin_unlock(&qp->q.lock);
+	icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
+	goto out_rcu_unlock;
 
-		/* Send an ICMP "Fragment Reassembly Timeout" message. */
-		if (clone) {
-			spin_unlock(&qp->q.lock);
-			icmp_send(clone, ICMP_TIME_EXCEEDED,
-				  ICMP_EXC_FRAGTIME, 0);
-			consume_skb(clone);
-			goto out_rcu_unlock;
-		}
-	}
 out:
 	spin_unlock(&qp->q.lock);
 out_rcu_unlock:
 	rcu_read_unlock();
+	if (head)
+		kfree_skb(head);
 	ipq_put(qp);
 }
 
@@ -260,21 +269,20 @@ out_rcu_unlock:
 static struct ipq *ip_find(struct net *net, struct iphdr *iph,
 			   u32 user, int vif)
 {
+	struct frag_v4_compare_key key = {
+		.saddr = iph->saddr,
+		.daddr = iph->daddr,
+		.user = user,
+		.vif = vif,
+		.id = iph->id,
+		.protocol = iph->protocol,
+	};
 	struct inet_frag_queue *q;
-	struct ip4_create_arg arg;
-	unsigned int hash;
 
-	arg.iph = iph;
-	arg.user = user;
-	arg.vif = vif;
-
-	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
-
-	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	q = inet_frag_find(&net->ipv4.frags, &key);
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct ipq, q);
 }
 
@@ -294,7 +302,7 @@ static int ip_frag_too_far(struct ipq *qp)
 	end = atomic_inc_return(&peer->rid);
 	qp->rid = end;
 
-	rc = qp->q.fragments && (end - start) > max;
+	rc = qp->q.fragments_tail && (end - start) > max;
 
 	if (rc) {
 		struct net *net;
@@ -308,7 +316,6 @@ static int ip_frag_too_far(struct ipq *qp)
 
 static int ip_frag_reinit(struct ipq *qp)
 {
-	struct sk_buff *fp;
 	unsigned int sum_truesize = 0;
 
 	if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
@@ -316,21 +323,16 @@ static int ip_frag_reinit(struct ipq *qp)
 		return -ETIMEDOUT;
 	}
 
-	fp = qp->q.fragments;
-	do {
-		struct sk_buff *xp = fp->next;
-
-		sum_truesize += fp->truesize;
-		kfree_skb(fp);
-		fp = xp;
-	} while (fp);
+	sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments);
 	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;
 	qp->q.meat = 0;
 	qp->q.fragments = NULL;
+	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
+	qp->q.last_run_head = NULL;
 	qp->iif = 0;
 	qp->ecn = 0;
 
@@ -340,7 +342,9 @@ static int ip_frag_reinit(struct ipq *qp)
 /* Add new segment to existing queue. */
 static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 {
-	struct sk_buff *prev, *next;
+	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
+	struct rb_node **rbn, *parent;
+	struct sk_buff *skb1, *prev_tail;
 	struct net_device *dev;
 	unsigned int fragsize;
 	int flags, offset;
@@ -403,99 +407,61 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	if (err)
 		goto err;
 
-	/* Find out which fragments are in front and at the back of us
-	 * in the chain of fragments so far.  We must know where to put
-	 * this fragment, right?
-	 */
-	prev = qp->q.fragments_tail;
-	if (!prev || FRAG_CB(prev)->offset < offset) {
-		next = NULL;
-		goto found;
-	}
-	prev = NULL;
-	for (next = qp->q.fragments; next != NULL; next = next->next) {
-		if (FRAG_CB(next)->offset >= offset)
-			break;	/* bingo! */
-		prev = next;
-	}
-
-found:
-	/* We found where to put this one.  Check for overlap with
-	 * preceding fragment, and, if needed, align things so that
-	 * any overlaps are eliminated.
+	/* Note : skb->rbnode and skb->dev share the same location. */
+	dev = skb->dev;
+	/* Makes sure compiler wont do silly aliasing games */
+	barrier();
+
+	/* RFC5722, Section 4, amended by Errata ID : 3089
+	 *                          When reassembling an IPv6 datagram, if
+	 *   one or more its constituent fragments is determined to be an
+	 *   overlapping fragment, the entire datagram (and any constituent
+	 *   fragments) MUST be silently discarded.
+	 *
+	 * We do the same here for IPv4 (and increment an snmp counter).
 	 */
-	if (prev) {
-		int i = (FRAG_CB(prev)->offset + prev->len) - offset;
 
-		if (i > 0) {
-			offset += i;
-			err = -EINVAL;
-			if (end <= offset)
-				goto err;
-			err = -ENOMEM;
-			if (!pskb_pull(skb, i))
-				goto err;
-			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-				skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
-
-	err = -ENOMEM;
-
-	while (next && FRAG_CB(next)->offset < end) {
-		int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
-
-		if (i < next->len) {
-			int delta = -next->truesize;
-
-			/* Eat head of the next overlapped fragment
-			 * and leave the loop. The next ones cannot overlap.
-			 */
-			if (!pskb_pull(next, i))
-				goto err;
-			delta += next->truesize;
-			if (delta)
-				add_frag_mem_limit(qp->q.net, delta);
-			FRAG_CB(next)->offset += i;
-			qp->q.meat -= i;
-			if (next->ip_summed != CHECKSUM_UNNECESSARY)
-				next->ip_summed = CHECKSUM_NONE;
-			break;
-		} else {
-			struct sk_buff *free_it = next;
-
-			/* Old fragment is completely overridden with
-			 * new one drop it.
-			 */
-			next = next->next;
-
-			if (prev)
-				prev->next = next;
-			else
-				qp->q.fragments = next;
-
-			qp->q.meat -= free_it->len;
-			sub_frag_mem_limit(qp->q.net, free_it->truesize);
-			kfree_skb(free_it);
-		}
+	/* Find out where to put this fragment.  */
+	prev_tail = qp->q.fragments_tail;
+	if (!prev_tail)
+		ip4_frag_create_run(&qp->q, skb);  /* First fragment. */
+	else if (prev_tail->ip_defrag_offset + prev_tail->len < end) {
+		/* This is the common case: skb goes to the end. */
+		/* Detect and discard overlaps. */
+		if (offset < prev_tail->ip_defrag_offset + prev_tail->len)
+			goto discard_qp;
+		if (offset == prev_tail->ip_defrag_offset + prev_tail->len)
+			ip4_frag_append_to_last_run(&qp->q, skb);
+		else
+			ip4_frag_create_run(&qp->q, skb);
+	} else {
+		/* Binary search. Note that skb can become the first fragment,
+		 * but not the last (covered above).
+		 */
+		rbn = &qp->q.rb_fragments.rb_node;
+		do {
+			parent = *rbn;
+			skb1 = rb_to_skb(parent);
+			if (end <= skb1->ip_defrag_offset)
+				rbn = &parent->rb_left;
+			else if (offset >= skb1->ip_defrag_offset +
+						FRAG_CB(skb1)->frag_run_len)
+				rbn = &parent->rb_right;
+			else /* Found an overlap with skb1. */
+				goto discard_qp;
+		} while (*rbn);
+		/* Here we have parent properly set, and rbn pointing to
+		 * one of its NULL left/right children. Insert skb.
+		 */
+		ip4_frag_init_run(skb);
+		rb_link_node(&skb->rbnode, parent, rbn);
+		rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
 	}
 
-	FRAG_CB(skb)->offset = offset;
-
-	/* Insert this fragment in the chain of fragments. */
-	skb->next = next;
-	if (!next)
-		qp->q.fragments_tail = skb;
-	if (prev)
-		prev->next = skb;
-	else
-		qp->q.fragments = skb;
-
-	dev = skb->dev;
-	if (dev) {
+	if (dev)
 		qp->iif = dev->ifindex;
-		skb->dev = NULL;
-	}
+	skb->ip_defrag_offset = offset;
+
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
@@ -517,7 +483,7 @@ found:
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = ip_frag_reasm(qp, prev, dev);
+		err = ip_frag_reasm(qp, skb, prev_tail, dev);
 		skb->_skb_refdst = orefdst;
 		return err;
 	}
@@ -525,20 +491,24 @@ found:
 	skb_dst_drop(skb);
 	return -EINPROGRESS;
 
+discard_qp:
+	inet_frag_kill(&qp->q);
+	err = -EINVAL;
+	__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
 err:
 	kfree_skb(skb);
 	return err;
 }
 
-
 /* Build a new IP datagram from all its fragments. */
-
-static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
-			 struct net_device *dev)
+static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
+			 struct sk_buff *prev_tail, struct net_device *dev)
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct iphdr *iph;
-	struct sk_buff *fp, *head = qp->q.fragments;
+	struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments);
+	struct sk_buff **nextp; /* To build frag_list. */
+	struct rb_node *rbn;
 	int len;
 	int ihlen;
 	int err;
@@ -552,26 +522,27 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		goto out_fail;
 	}
 	/* Make the one we just received the head. */
-	if (prev) {
-		head = prev->next;
-		fp = skb_clone(head, GFP_ATOMIC);
+	if (head != skb) {
+		fp = skb_clone(skb, GFP_ATOMIC);
 		if (!fp)
 			goto out_nomem;
-
-		fp->next = head->next;
-		if (!fp->next)
+		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
+		if (RB_EMPTY_NODE(&skb->rbnode))
+			FRAG_CB(prev_tail)->next_frag = fp;
+		else
+			rb_replace_node(&skb->rbnode, &fp->rbnode,
+					&qp->q.rb_fragments);
+		if (qp->q.fragments_tail == skb)
 			qp->q.fragments_tail = fp;
-		prev->next = fp;
-
-		skb_morph(head, qp->q.fragments);
-		head->next = qp->q.fragments->next;
-
-		consume_skb(qp->q.fragments);
-		qp->q.fragments = head;
+		skb_morph(skb, head);
+		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
+		rb_replace_node(&head->rbnode, &skb->rbnode,
+				&qp->q.rb_fragments);
+		consume_skb(head);
+		head = skb;
 	}
 
-	WARN_ON(!head);
-	WARN_ON(FRAG_CB(head)->offset != 0);
+	WARN_ON(head->ip_defrag_offset != 0);
 
 	/* Allocate a new buffer for the datagram. */
 	ihlen = ip_hdrlen(head);
@@ -595,35 +566,61 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		clone = alloc_skb(0, GFP_ATOMIC);
 		if (!clone)
 			goto out_nomem;
-		clone->next = head->next;
-		head->next = clone;
 		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
 		skb_frag_list_init(head);
 		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
 			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
 		clone->len = clone->data_len = head->data_len - plen;
-		head->data_len -= clone->len;
-		head->len -= clone->len;
+		head->truesize += clone->truesize;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
 		add_frag_mem_limit(qp->q.net, clone->truesize);
+		skb_shinfo(head)->frag_list = clone;
+		nextp = &clone->next;
+	} else {
+		nextp = &skb_shinfo(head)->frag_list;
 	}
 
-	skb_shinfo(head)->frag_list = head->next;
 	skb_push(head, head->data - skb_network_header(head));
 
-	for (fp=head->next; fp; fp = fp->next) {
-		head->data_len += fp->len;
-		head->len += fp->len;
-		if (head->ip_summed != fp->ip_summed)
-			head->ip_summed = CHECKSUM_NONE;
-		else if (head->ip_summed == CHECKSUM_COMPLETE)
-			head->csum = csum_add(head->csum, fp->csum);
-		head->truesize += fp->truesize;
+	/* Traverse the tree in order, to build frag_list. */
+	fp = FRAG_CB(head)->next_frag;
+	rbn = rb_next(&head->rbnode);
+	rb_erase(&head->rbnode, &qp->q.rb_fragments);
+	while (rbn || fp) {
+		/* fp points to the next sk_buff in the current run;
+		 * rbn points to the next run.
+		 */
+		/* Go through the current run. */
+		while (fp) {
+			*nextp = fp;
+			nextp = &fp->next;
+			fp->prev = NULL;
+			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+			fp->sk = NULL;
+			head->data_len += fp->len;
+			head->len += fp->len;
+			if (head->ip_summed != fp->ip_summed)
+				head->ip_summed = CHECKSUM_NONE;
+			else if (head->ip_summed == CHECKSUM_COMPLETE)
+				head->csum = csum_add(head->csum, fp->csum);
+			head->truesize += fp->truesize;
+			fp = FRAG_CB(fp)->next_frag;
+		}
+		/* Move to the next run. */
+		if (rbn) {
+			struct rb_node *rbnext = rb_next(rbn);
+
+			fp = rb_to_skb(rbn);
+			rb_erase(rbn, &qp->q.rb_fragments);
+			rbn = rbnext;
+		}
 	}
 	sub_frag_mem_limit(qp->q.net, head->truesize);
 
+	*nextp = NULL;
 	head->next = NULL;
+	head->prev = NULL;
 	head->dev = dev;
 	head->tstamp = qp->q.stamp;
 	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
@@ -651,7 +648,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
+	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
+	qp->q.last_run_head = NULL;
 	return 0;
 
 out_nomem:
@@ -659,7 +658,7 @@ out_nomem:
 	err = -ENOMEM;
 	goto out_fail;
 out_oversize:
-	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
+	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
 out_fail:
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	return err;
@@ -719,10 +718,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
-				return skb;
-			if (pskb_trim_rcsum(skb, netoff + len))
-				return skb;
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) {
+				kfree_skb(skb);
+				return NULL;
+			}
+			if (pskb_trim_rcsum(skb, netoff + len)) {
+				kfree_skb(skb);
+				return NULL;
+			}
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(net, skb, user))
 				return NULL;
@@ -733,25 +736,46 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_check_defrag);
 
+unsigned int inet_frag_rbtree_purge(struct rb_root *root)
+{
+	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
+
+	while (p) {
+		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, root);
+		while (skb) {
+			struct sk_buff *next = FRAG_CB(skb)->next_frag;
+
+			sum += skb->truesize;
+			kfree_skb(skb);
+			skb = next;
+		}
+	}
+	return sum;
+}
+EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
 #ifdef CONFIG_SYSCTL
-static int zero;
+static int dist_min;
 
 static struct ctl_table ip4_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ipfrag_high_thresh",
 		.data		= &init_net.ipv4.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ipv4.frags.low_thresh
 	},
 	{
 		.procname	= "ipfrag_low_thresh",
 		.data		= &init_net.ipv4.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra2		= &init_net.ipv4.frags.high_thresh
 	},
 	{
@@ -767,7 +791,7 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero
+		.extra1		= &dist_min,
 	},
 	{ }
 };
@@ -849,6 +873,8 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
+	int res;
+
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -873,16 +899,21 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 	net->ipv4.frags.timeout = IP_FRAG_TIME;
 
 	net->ipv4.frags.max_dist = 64;
-
-	inet_frags_init_net(&net->ipv4.frags);
-
-	return ip4_frags_ns_ctl_register(net);
+	net->ipv4.frags.f = &ip4_frags;
+
+	res = inet_frags_init_net(&net->ipv4.frags);
+	if (res < 0)
+		return res;
+	res = ip4_frags_ns_ctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->ipv4.frags);
+	return res;
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
 {
 	ip4_frags_ns_ctl_unregister(net);
-	inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+	inet_frags_exit_net(&net->ipv4.frags);
 }
 
 static struct pernet_operations ip4_frags_ops = {
@@ -890,17 +921,49 @@ static struct pernet_operations ip4_frags_ops = {
 	.exit = ipv4_frags_exit_net,
 };
 
+
+static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v4,
+		      sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v4_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params ip4_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.key_offset		= offsetof(struct inet_frag_queue, key),
+	.key_len		= sizeof(struct frag_v4_compare_key),
+	.hashfn			= ip4_key_hashfn,
+	.obj_hashfn		= ip4_obj_hashfn,
+	.obj_cmpfn		= ip4_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+
 void __init ipfrag_init(void)
 {
-	ip4_frags_ctl_register();
-	register_pernet_subsys(&ip4_frags_ops);
-	ip4_frags.hashfn = ip4_hashfn;
 	ip4_frags.constructor = ip4_frag_init;
 	ip4_frags.destructor = ip4_frag_free;
 	ip4_frags.qsize = sizeof(struct ipq);
-	ip4_frags.match = ip4_frag_match;
 	ip4_frags.frag_expire = ip_expire;
 	ip4_frags.frags_cache_name = ip_frag_cache_name;
+	ip4_frags.rhash_params = ip4_rhash_params;
 	if (inet_frags_init(&ip4_frags))
 		panic("IP: failed to allocate ip4_frags cache\n");
+	ip4_frags_ctl_register();
+	register_pernet_subsys(&ip4_frags_ops);
 }
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b21e435f428c..a5851c0bc278 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -134,7 +134,6 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
-	const struct iphdr *iph = ip_hdr(skb);
 	__be16 *ports;
 	int end;
 
@@ -149,7 +148,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = iph->daddr;
+	sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
 	sin.sin_port = ports[1];
 	memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e1271e75e107..e6ee6acac80c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -261,8 +261,8 @@ static struct net_device *__ip_tunnel_create(struct net *net,
 	} else {
 		if (strlen(ops->kind) > (IFNAMSIZ - 3))
 			goto failed;
-		strlcpy(name, ops->kind, IFNAMSIZ);
-		strncat(name, "%d", 2);
+		strcpy(name, ops->kind);
+		strcat(name, "%d");
 	}
 
 	ASSERT_RTNL();
@@ -627,6 +627,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, u8 protocol)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
+	unsigned int inner_nhdr_len = 0;
 	const struct iphdr *inner_iph;
 	struct flowi4 fl4;
 	u8     tos, ttl;
@@ -636,6 +637,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	__be32 dst;
 	bool connected;
 
+	/* ensure we can access the inner net header, for several users below */
+	if (skb->protocol == htons(ETH_P_IP))
+		inner_nhdr_len = sizeof(struct iphdr);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		inner_nhdr_len = sizeof(struct ipv6hdr);
+	if (unlikely(!pskb_may_pull(skb, inner_nhdr_len)))
+		goto tx_error;
+
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 0fd1976ab63b..2220a1b396af 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -80,7 +80,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 
 	iph->version	=	4;
 	iph->ihl	=	sizeof(struct iphdr) >> 2;
-	iph->frag_off	=	df;
+	iph->frag_off	=	ip_mtu_locked(&rt->dst) ? 0 : df;
 	iph->protocol	=	proto;
 	iph->tos	=	tos;
 	iph->daddr	=	dst;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 7143ca1a6af9..ec48d8eafc7e 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,6 @@
 static int sockstat_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
-	unsigned int frag_mem;
 	int orphans, sockets;
 
 	local_bh_disable();
@@ -74,8 +73,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
 		   sock_prot_inuse_get(net, &raw_prot));
-	frag_mem = ip_frag_mem(net);
-	seq_printf(seq,  "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
+	seq_printf(seq,  "FRAG: inuse %u memory %lu\n",
+		   atomic_read(&net->ipv4.frags.rhashtable.nelems),
+		   frag_mem_limit(&net->ipv4.frags));
 	return 0;
 }
 
@@ -134,6 +134,7 @@ static const struct snmp_mib snmp4_ipextstats_list[] = {
 	SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
 	SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
 	SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
+	SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9d0b73aa649f..dbb153c6b21a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4406,7 +4406,7 @@ static void tcp_ofo_queue(struct sock *sk)
 
 	p = rb_first(&tp->out_of_order_queue);
 	while (p) {
-		skb = rb_entry(p, struct sk_buff, rbnode);
+		skb = rb_to_skb(p);
 		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
 			break;
 
@@ -4470,7 +4470,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
 static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct rb_node **p, *q, *parent;
+	struct rb_node **p, *parent;
 	struct sk_buff *skb1;
 	u32 seq, end_seq;
 	bool fragstolen;
@@ -4529,7 +4529,7 @@ coalesce_done:
 	parent = NULL;
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(seq, TCP_SKB_CB(skb1)->seq)) {
 			p = &parent->rb_left;
 			continue;
@@ -4574,9 +4574,7 @@ insert:
 
 merge_right:
 	/* Remove other segments covered by skb. */
-	while ((q = rb_next(&skb->rbnode)) != NULL) {
-		skb1 = rb_entry(q, struct sk_buff, rbnode);
-
+	while ((skb1 = skb_rb_next(skb)) != NULL) {
 		if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
 			break;
 		if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
@@ -4591,7 +4589,7 @@ merge_right:
 		tcp_drop(sk, skb1);
 	}
 	/* If there is no skb after us, we are the last_skb ! */
-	if (!q)
+	if (!skb1)
 		tp->ooo_last_skb = skb;
 
 add_sack:
@@ -4792,7 +4790,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li
 	if (list)
 		return !skb_queue_is_last(list, skb) ? skb->next : NULL;
 
-	return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode);
+	return skb_rb_next(skb);
 }
 
 static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
@@ -4821,7 +4819,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
 
 	while (*p) {
 		parent = *p;
-		skb1 = rb_entry(parent, struct sk_buff, rbnode);
+		skb1 = rb_to_skb(parent);
 		if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
 			p = &parent->rb_left;
 		else
@@ -4941,19 +4939,12 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 range_truesize, sum_tiny = 0;
 	struct sk_buff *skb, *head;
-	struct rb_node *p;
 	u32 start, end;
 
-	p = rb_first(&tp->out_of_order_queue);
-	skb = rb_entry_safe(p, struct sk_buff, rbnode);
+	skb = skb_rb_first(&tp->out_of_order_queue);
 new_range:
 	if (!skb) {
-		p = rb_last(&tp->out_of_order_queue);
-		/* Note: This is possible p is NULL here. We do not
-		 * use rb_entry_safe(), as ooo_last_skb is valid only
-		 * if rbtree is not empty.
-		 */
-		tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode);
+		tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue);
 		return;
 	}
 	start = TCP_SKB_CB(skb)->seq;
@@ -4961,7 +4952,7 @@ new_range:
 	range_truesize = skb->truesize;
 
 	for (head = skb;;) {
-		skb = tcp_skb_next(skb, NULL);
+		skb = skb_rb_next(skb);
 
 		/* Range is terminated when we see a gap or when
 		 * we are at the queue end.
@@ -5017,7 +5008,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
 		goal -= rb_to_skb(node)->truesize;
-		tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
+		tcp_drop(sk, rb_to_skb(node));
 		if (!prev || goal <= 0) {
 			sk_mem_reclaim(sk);
 			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
@@ -5027,7 +5018,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 		}
 		node = prev;
 	} while (node);
-	tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
+	tp->ooo_last_skb = rb_to_skb(prev);
 
 	/* Reset SACK state.  A conforming SACK implementation will
 	 * do the same at a timeout based retransmit.  When a connection
@@ -5978,11 +5969,13 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			if (th->fin)
 				goto discard;
 			/* It is possible that we process SYN packets from backlog,
-			 * so we need to make sure to disable BH right there.
+			 * so we need to make sure to disable BH and RCU right there.
 			 */
+			rcu_read_lock();
 			local_bh_disable();
 			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
 			local_bh_enable();
+			rcu_read_unlock();
 
 			if (!acceptable)
 				return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 16dea67792e0..1ea0c91ba994 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -859,9 +859,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
+		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq_opt_deref(ireq));
+					    rcu_dereference(ireq->ireq_opt));
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b9b2a9828d98..5d4b5e0f6b5e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1726,8 +1726,24 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 	/* Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 inet_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							inet_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat it as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 
 /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3a27cf762da1..8f79f0414bc3 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4068,7 +4068,6 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 				p++;
 				continue;
 			}
-			state->offset++;
 			return ifa;
 		}
 
@@ -4092,13 +4091,12 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 		return ifa;
 	}
 
+	state->offset = 0;
 	while (++state->bucket < IN6_ADDR_HSIZE) {
-		state->offset = 0;
 		hlist_for_each_entry_rcu_bh(ifa,
 				     &inet6_addr_lst[state->bucket], addr_lst) {
 			if (!net_eq(dev_net(ifa->idev->dev), net))
 				continue;
-			state->offset++;
 			return ifa;
 		}
 	}
@@ -4723,8 +4721,8 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 
 		/* unicast address incl. temp addr */
 		list_for_each_entry(ifa, &idev->addr_list, if_list) {
-			if (++ip_idx < s_ip_idx)
-				continue;
+			if (ip_idx < s_ip_idx)
+				goto next;
 			err = inet6_fill_ifaddr(skb, ifa,
 						NETLINK_CB(cb->skb).portid,
 						cb->nlh->nlmsg_seq,
@@ -4733,6 +4731,8 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 			if (err < 0)
 				break;
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+next:
+			ip_idx++;
 		}
 		break;
 	}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 421379014995..f7b425615c12 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1045,11 +1045,11 @@ netfilter_fail:
 igmp_fail:
 	ndisc_cleanup();
 ndisc_fail:
-	ip6_mr_cleanup();
+	icmpv6_cleanup();
 icmp_fail:
-	unregister_pernet_subsys(&inet6_net_ops);
+	ip6_mr_cleanup();
 ipmr_fail:
-	icmpv6_cleanup();
+	unregister_pernet_subsys(&inet6_net_ops);
 register_pernet_fail:
 	sock_unregister(PF_INET6);
 	rtnl_unregister_all(PF_INET6);
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index 1dc023ca98fd..9d9a16e219d6 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -87,8 +87,24 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 	 * Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 ip6_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							ip6_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat is as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(udp6_csum_init);
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index cda63426eefb..9c5afa5153ce 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1185,11 +1185,6 @@ route_lookup:
 	}
 	skb_dst_set(skb, dst);
 
-	if (encap_limit >= 0) {
-		init_tel_txopt(&opt, encap_limit);
-		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
-	}
-
 	/* Calculate max headroom for all the headers and adjust
 	 * needed_headroom if necessary.
 	 */
@@ -1202,6 +1197,11 @@ route_lookup:
 	if (err)
 		return err;
 
+	if (encap_limit >= 0) {
+		init_tel_txopt(&opt, encap_limit);
+		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
+	}
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
@@ -1226,7 +1226,7 @@ static inline int
 ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	const struct iphdr  *iph = ip_hdr(skb);
+	const struct iphdr  *iph;
 	int encap_limit = -1;
 	struct flowi6 fl6;
 	__u8 dsfield;
@@ -1234,6 +1234,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
+	/* ensure we can access the full inner ip header */
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		return -1;
+
+	iph = ip_hdr(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 
 	tproto = ACCESS_ONCE(t->parms.proto);
@@ -1253,7 +1258,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowi6_proto = IPPROTO_IPIP;
 		fl6.daddr = key->u.ipv6.dst;
 		fl6.flowlabel = key->label;
-		dsfield = ip6_tclass(key->label);
+		dsfield =  key->tos;
 	} else {
 		if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 			encap_limit = t->parms.encap_limit;
@@ -1293,7 +1298,7 @@ static inline int
 ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	int encap_limit = -1;
 	__u16 offset;
 	struct flowi6 fl6;
@@ -1302,6 +1307,10 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
+	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
+		return -1;
+
+	ipv6h = ipv6_hdr(skb);
 	tproto = ACCESS_ONCE(t->parms.proto);
 	if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
 	    ip6_tnl_addr_conflict(t, ipv6h))
@@ -1320,7 +1329,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowi6_proto = IPPROTO_IPV6;
 		fl6.daddr = key->u.ipv6.dst;
 		fl6.flowlabel = key->label;
-		dsfield = ip6_tclass(key->label);
+		dsfield = key->tos;
 	} else {
 		offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
 		/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 6c54c76847bf..40262abb15db 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2413,17 +2413,17 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 {
 	int err;
 
-	/* callers have the socket lock and rtnl lock
-	 * so no other readers or writers of iml or its sflist
-	 */
+	write_lock_bh(&iml->sflock);
 	if (!iml->sflist) {
 		/* any-source empty exclude case */
-		return ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0);
+		err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0);
+	} else {
+		err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode,
+				iml->sflist->sl_count, iml->sflist->sl_addr, 0);
+		sock_kfree_s(sk, iml->sflist, IP6_SFLSIZE(iml->sflist->sl_max));
+		iml->sflist = NULL;
 	}
-	err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode,
-		iml->sflist->sl_count, iml->sflist->sl_addr, 0);
-	sock_kfree_s(sk, iml->sflist, IP6_SFLSIZE(iml->sflist->sl_max));
-	iml->sflist = NULL;
+	write_unlock_bh(&iml->sflock);
 	return err;
 }
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 21f3bf2125f4..505d048ffff5 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1692,10 +1692,9 @@ int ndisc_rcv(struct sk_buff *skb)
 		return 0;
 	}
 
-	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
-
 	switch (msg->icmph.icmp6_type) {
 	case NDISC_NEIGHBOUR_SOLICITATION:
+		memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
 		ndisc_recv_ns(skb);
 		break;
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index ee33a6743f3b..e46185377981 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -63,7 +63,6 @@ struct nf_ct_frag6_skb_cb
 static struct inet_frags nf_frags;
 
 #ifdef CONFIG_SYSCTL
-static int zero;
 
 static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
@@ -76,18 +75,17 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_frag6_low_thresh",
 		.data		= &init_net.nf_frag.frags.low_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra2		= &init_net.nf_frag.frags.high_thresh
 	},
 	{
 		.procname	= "nf_conntrack_frag6_high_thresh",
 		.data		= &init_net.nf_frag.frags.high_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.nf_frag.frags.low_thresh
 	},
 	{ }
@@ -152,23 +150,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
 }
 
-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
-				 const struct in6_addr *daddr)
-{
-	net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
-	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			    (__force u32)id, nf_frags.rnd);
-}
-
-
-static unsigned int nf_hashfn(const struct inet_frag_queue *q)
-{
-	const struct frag_queue *nq;
-
-	nq = container_of(q, struct frag_queue, q);
-	return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
-}
-
 static void nf_ct_frag6_expire(unsigned long data)
 {
 	struct frag_queue *fq;
@@ -177,34 +158,26 @@ static void nf_ct_frag6_expire(unsigned long data)
 	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, nf_frag.frags);
 
-	ip6_expire_frag_queue(net, fq, &nf_frags);
+	ip6_expire_frag_queue(net, fq);
 }
 
 /* Creation primitives. */
-static inline struct frag_queue *fq_find(struct net *net, __be32 id,
-					 u32 user, struct in6_addr *src,
-					 struct in6_addr *dst, int iif, u8 ecn)
+static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
+				  const struct ipv6hdr *hdr, int iif)
 {
+	struct frag_v6_compare_key key = {
+		.id = id,
+		.saddr = hdr->saddr,
+		.daddr = hdr->daddr,
+		.user = user,
+		.iif = iif,
+	};
 	struct inet_frag_queue *q;
-	struct ip6_create_arg arg;
-	unsigned int hash;
-
-	arg.id = id;
-	arg.user = user;
-	arg.src = src;
-	arg.dst = dst;
-	arg.iif = iif;
-	arg.ecn = ecn;
-
-	local_bh_disable();
-	hash = nf_hash_frag(id, src, dst);
-
-	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
-	local_bh_enable();
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+
+	q = inet_frag_find(&net->nf_frag.frags, &key);
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct frag_queue, q);
 }
 
@@ -263,7 +236,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 			 * this case. -DaveM
 			 */
 			pr_debug("end of fragment not rounded to 8 bytes.\n");
-			inet_frag_kill(&fq->q, &nf_frags);
+			inet_frag_kill(&fq->q);
 			return -EPROTO;
 		}
 		if (end > fq->q.len) {
@@ -356,7 +329,7 @@ found:
 	return 0;
 
 discard_fq:
-	inet_frag_kill(&fq->q, &nf_frags);
+	inet_frag_kill(&fq->q);
 err:
 	return -EINVAL;
 }
@@ -378,7 +351,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 	int    payload_len;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q, &nf_frags);
+	inet_frag_kill(&fq->q);
 
 	WARN_ON(head == NULL);
 	WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
@@ -479,6 +452,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 		else if (head->ip_summed == CHECKSUM_COMPLETE)
 			head->csum = csum_add(head->csum, fp->csum);
 		head->truesize += fp->truesize;
+		fp->sk = NULL;
 	}
 	sub_frag_mem_limit(fq->q.net, head->truesize);
 
@@ -497,6 +471,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 					  head->csum);
 
 	fq->q.fragments = NULL;
+	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 
 	return true;
@@ -591,9 +566,13 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
+	if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
+	    fhdr->frag_off & htons(IP6_MF))
+		return -EINVAL;
+
 	skb_orphan(skb);
-	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
-		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+	fq = fq_find(net, fhdr->identification, user, hdr,
+		     skb->dev ? skb->dev->ifindex : 0);
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		return -ENOMEM;
@@ -618,30 +597,36 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	    fq->q.meat == fq->q.len &&
 	    nf_ct_frag6_reasm(fq, skb, dev))
 		ret = 0;
-	else
-		skb_dst_drop(skb);
 
 out_unlock:
 	spin_unlock_bh(&fq->q.lock);
-	inet_frag_put(&fq->q, &nf_frags);
+	inet_frag_put(&fq->q);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
+	int res;
+
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	inet_frags_init_net(&net->nf_frag.frags);
-
-	return nf_ct_frag6_sysctl_register(net);
+	net->nf_frag.frags.f = &nf_frags;
+
+	res = inet_frags_init_net(&net->nf_frag.frags);
+	if (res < 0)
+		return res;
+	res = nf_ct_frag6_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->nf_frag.frags);
+	return res;
 }
 
 static void nf_ct_net_exit(struct net *net)
 {
 	nf_ct_frags6_sysctl_unregister(net);
-	inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+	inet_frags_exit_net(&net->nf_frag.frags);
 }
 
 static struct pernet_operations nf_ct_net_ops = {
@@ -653,13 +638,12 @@ int nf_ct_frag6_init(void)
 {
 	int ret = 0;
 
-	nf_frags.hashfn = nf_hashfn;
 	nf_frags.constructor = ip6_frag_init;
 	nf_frags.destructor = NULL;
 	nf_frags.qsize = sizeof(struct frag_queue);
-	nf_frags.match = ip6_frag_match;
 	nf_frags.frag_expire = nf_ct_frag6_expire;
 	nf_frags.frags_cache_name = nf_frags_cache_name;
+	nf_frags.rhash_params = ip6_rhash_params;
 	ret = inet_frags_init(&nf_frags);
 	if (ret)
 		goto out;
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index e88bcb8ff0fd..dc04c024986c 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -38,7 +38,6 @@
 static int sockstat6_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
-	unsigned int frag_mem = ip6_frag_mem(net);
 
 	seq_printf(seq, "TCP6: inuse %d\n",
 		       sock_prot_inuse_get(net, &tcpv6_prot));
@@ -48,7 +47,9 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
 			sock_prot_inuse_get(net, &udplitev6_prot));
 	seq_printf(seq, "RAW6: inuse %d\n",
 		       sock_prot_inuse_get(net, &rawv6_prot));
-	seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem);
+	seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
+		   atomic_read(&net->ipv6.frags.rhashtable.nelems),
+		   frag_mem_limit(&net->ipv6.frags));
 	return 0;
 }
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 71ffa526cb23..a4f979ff31b9 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -645,8 +645,6 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
-	skb_dst_set(skb, &rt->dst);
-	*dstp = NULL;
 
 	skb_put(skb, length);
 	skb_reset_network_header(skb);
@@ -656,8 +654,14 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 
 	skb->transport_header = skb->network_header;
 	err = memcpy_from_msg(iph, msg, length);
-	if (err)
-		goto error_fault;
+	if (err) {
+		err = -EFAULT;
+		kfree_skb(skb);
+		goto error;
+	}
+
+	skb_dst_set(skb, &rt->dst);
+	*dstp = NULL;
 
 	/* if egress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -666,21 +670,28 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	if (unlikely(!skb))
 		return 0;
 
+	/* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev
+	 * in the error path. Since skb has been freed, the dst could
+	 * have been queued for deletion.
+	 */
+	rcu_read_lock();
 	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
 	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
 		      NULL, rt->dst.dev, dst_output);
 	if (err > 0)
 		err = net_xmit_errno(err);
-	if (err)
-		goto error;
+	if (err) {
+		IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
+		rcu_read_unlock();
+		goto error_check;
+	}
+	rcu_read_unlock();
 out:
 	return 0;
 
-error_fault:
-	err = -EFAULT;
-	kfree_skb(skb);
 error:
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
+error_check:
 	if (err == -ENOBUFS && !np->recverr)
 		err = 0;
 	return err;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index e585c0a2591c..74ffbcb306a6 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -79,94 +79,58 @@ static struct inet_frags ip6_frags;
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 			  struct net_device *dev);
 
-/*
- * callers should be careful not to use the hash value outside the ipfrag_lock
- * as doing so could race with ipfrag_hash_rnd being recalculated.
- */
-static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
-				    const struct in6_addr *daddr)
-{
-	net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
-	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			    (__force u32)id, ip6_frags.rnd);
-}
-
-static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
-{
-	const struct frag_queue *fq;
-
-	fq = container_of(q, struct frag_queue, q);
-	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
-}
-
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct frag_queue *fq;
-	const struct ip6_create_arg *arg = a;
-
-	fq = container_of(q, struct frag_queue, q);
-	return	fq->id == arg->id &&
-		fq->user == arg->user &&
-		ipv6_addr_equal(&fq->saddr, arg->src) &&
-		ipv6_addr_equal(&fq->daddr, arg->dst) &&
-		(arg->iif == fq->iif ||
-		 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
-					       IPV6_ADDR_LINKLOCAL)));
-}
-EXPORT_SYMBOL(ip6_frag_match);
-
 void ip6_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	struct frag_queue *fq = container_of(q, struct frag_queue, q);
-	const struct ip6_create_arg *arg = a;
+	const struct frag_v6_compare_key *key = a;
 
-	fq->id = arg->id;
-	fq->user = arg->user;
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
-	fq->ecn = arg->ecn;
+	q->key.v6 = *key;
+	fq->ecn = 0;
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
-			   struct inet_frags *frags)
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
 {
 	struct net_device *dev = NULL;
+	struct sk_buff *head;
 
+	rcu_read_lock();
 	spin_lock(&fq->q.lock);
 
 	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
-	inet_frag_kill(&fq->q, frags);
+	inet_frag_kill(&fq->q);
 
-	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, fq->iif);
 	if (!dev)
-		goto out_rcu_unlock;
+		goto out;
 
 	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
-	if (inet_frag_evicting(&fq->q))
-		goto out_rcu_unlock;
-
 	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
 
 	/* Don't send error if the first segment did not arrive. */
-	if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments)
-		goto out_rcu_unlock;
+	head = fq->q.fragments;
+	if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+		goto out;
 
 	/* But use as source device on which LAST ARRIVED
 	 * segment was received. And do not use fq->dev
 	 * pointer directly, device might already disappeared.
 	 */
-	fq->q.fragments->dev = dev;
-	icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
-out_rcu_unlock:
-	rcu_read_unlock();
+	head->dev = dev;
+	skb_get(head);
+	spin_unlock(&fq->q.lock);
+
+	icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+	kfree_skb(head);
+	goto out_rcu_unlock;
+
 out:
 	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q, frags);
+out_rcu_unlock:
+	rcu_read_unlock();
+	inet_frag_put(&fq->q);
 }
 EXPORT_SYMBOL(ip6_expire_frag_queue);
 
@@ -178,31 +142,29 @@ static void ip6_frag_expire(unsigned long data)
 	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, ipv6.frags);
 
-	ip6_expire_frag_queue(net, fq, &ip6_frags);
+	ip6_expire_frag_queue(net, fq);
 }
 
 static struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-	const struct in6_addr *dst, int iif, u8 ecn)
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
 {
+	struct frag_v6_compare_key key = {
+		.id = id,
+		.saddr = hdr->saddr,
+		.daddr = hdr->daddr,
+		.user = IP6_DEFRAG_LOCAL_DELIVER,
+		.iif = iif,
+	};
 	struct inet_frag_queue *q;
-	struct ip6_create_arg arg;
-	unsigned int hash;
 
-	arg.id = id;
-	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
-	arg.src = src;
-	arg.dst = dst;
-	arg.iif = iif;
-	arg.ecn = ecn;
+	if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+					    IPV6_ADDR_LINKLOCAL)))
+		key.iif = 0;
 
-	hash = inet6_hash_frag(id, src, dst);
-
-	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	q = inet_frag_find(&net->ipv6.frags, &key);
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct frag_queue, q);
 }
 
@@ -359,7 +321,7 @@ found:
 	return -1;
 
 discard_fq:
-	inet_frag_kill(&fq->q, &ip6_frags);
+	inet_frag_kill(&fq->q);
 err:
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			IPSTATS_MIB_REASMFAILS);
@@ -386,7 +348,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	int sum_truesize;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q, &ip6_frags);
+	inet_frag_kill(&fq->q);
 
 	ecn = ip_frag_ecn_table[fq->ecn];
 	if (unlikely(ecn == 0xff))
@@ -504,6 +466,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
 	rcu_read_unlock();
 	fq->q.fragments = NULL;
+	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 	return 1;
 
@@ -525,6 +488,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
+	int iif;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
 		goto fail_hdr;
@@ -553,17 +517,22 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
-	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+	if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
+	    fhdr->frag_off & htons(IP6_MF))
+		goto fail_hdr;
+
+	iif = skb->dev ? skb->dev->ifindex : 0;
+	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
 		int ret;
 
 		spin_lock(&fq->q.lock);
 
+		fq->iif = iif;
 		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
 
 		spin_unlock(&fq->q.lock);
-		inet_frag_put(&fq->q, &ip6_frags);
+		inet_frag_put(&fq->q);
 		return ret;
 	}
 
@@ -584,24 +553,22 @@ static const struct inet6_protocol frag_protocol = {
 };
 
 #ifdef CONFIG_SYSCTL
-static int zero;
 
 static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ip6frag_high_thresh",
 		.data		= &init_net.ipv6.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ipv6.frags.low_thresh
 	},
 	{
 		.procname	= "ip6frag_low_thresh",
 		.data		= &init_net.ipv6.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra2		= &init_net.ipv6.frags.high_thresh
 	},
 	{
@@ -644,10 +611,6 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 		table[1].data = &net->ipv6.frags.low_thresh;
 		table[1].extra2 = &net->ipv6.frags.high_thresh;
 		table[2].data = &net->ipv6.frags.timeout;
-
-		/* Don't export sysctls to unprivileged users */
-		if (net->user_ns != &init_user_ns)
-			table[0].procname = NULL;
 	}
 
 	hdr = register_net_sysctl(net, "net/ipv6", table);
@@ -709,19 +672,27 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
+	int res;
+
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+	net->ipv6.frags.f = &ip6_frags;
 
-	inet_frags_init_net(&net->ipv6.frags);
+	res = inet_frags_init_net(&net->ipv6.frags);
+	if (res < 0)
+		return res;
 
-	return ip6_frags_ns_sysctl_register(net);
+	res = ip6_frags_ns_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->ipv6.frags);
+	return res;
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)
 {
 	ip6_frags_ns_sysctl_unregister(net);
-	inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+	inet_frags_exit_net(&net->ipv6.frags);
 }
 
 static struct pernet_operations ip6_frags_ops = {
@@ -729,14 +700,55 @@ static struct pernet_operations ip6_frags_ops = {
 	.exit = ipv6_frags_exit_net,
 };
 
+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v6,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v6_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params ip6_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= ip6_key_hashfn,
+	.obj_hashfn		= ip6_obj_hashfn,
+	.obj_cmpfn		= ip6_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+EXPORT_SYMBOL(ip6_rhash_params);
+
 int __init ipv6_frag_init(void)
 {
 	int ret;
 
-	ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	ip6_frags.constructor = ip6_frag_init;
+	ip6_frags.destructor = NULL;
+	ip6_frags.qsize = sizeof(struct frag_queue);
+	ip6_frags.frag_expire = ip6_frag_expire;
+	ip6_frags.frags_cache_name = ip6_frag_cache_name;
+	ip6_frags.rhash_params = ip6_rhash_params;
+	ret = inet_frags_init(&ip6_frags);
 	if (ret)
 		goto out;
 
+	ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	if (ret)
+		goto err_protocol;
+
 	ret = ip6_frags_sysctl_register();
 	if (ret)
 		goto err_sysctl;
@@ -745,16 +757,6 @@ int __init ipv6_frag_init(void)
 	if (ret)
 		goto err_pernet;
 
-	ip6_frags.hashfn = ip6_hashfn;
-	ip6_frags.constructor = ip6_frag_init;
-	ip6_frags.destructor = NULL;
-	ip6_frags.qsize = sizeof(struct frag_queue);
-	ip6_frags.match = ip6_frag_match;
-	ip6_frags.frag_expire = ip6_frag_expire;
-	ip6_frags.frags_cache_name = ip6_frag_cache_name;
-	ret = inet_frags_init(&ip6_frags);
-	if (ret)
-		goto err_pernet;
 out:
 	return ret;
 
@@ -762,6 +764,8 @@ err_pernet:
 	ip6_frags_sysctl_unregister();
 err_sysctl:
 	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+err_protocol:
+	inet_frags_fini(&ip6_frags);
 	goto out;
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 70fa31e37360..b0a72677b7e5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1439,10 +1439,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
+	int oif = sk->sk_bound_dev_if;
 	struct dst_entry *dst;
 
-	ip6_update_pmtu(skb, sock_net(sk), mtu,
-			sk->sk_bound_dev_if, sk->sk_mark);
+	if (!oif && skb->dev)
+		oif = l3mdev_master_ifindex(skb->dev);
+
+	ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark);
 
 	dst = __sk_dst_get(sk);
 	if (!dst || !dst->obsolete ||
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 4d09ce6fa90e..64862c5084ee 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -165,9 +165,11 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	if (toobig && xfrm6_local_dontfrag(skb)) {
 		xfrm6_local_rxpmtu(skb, mtu);
+		kfree_skb(skb);
 		return -EMSGSIZE;
 	} else if (!skb->ignore_df && toobig && skb->sk) {
 		xfrm_local_error(skb, mtu);
+		kfree_skb(skb);
 		return -EMSGSIZE;
 	}
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a5333f6cb65a..b96dbe38ecad 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -845,10 +845,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		}
 	}
 
-	/* Session data offset is handled differently for L2TPv2 and
-	 * L2TPv3. For L2TPv2, there is an optional 16-bit value in
-	 * the header. For L2TPv3, the offset is negotiated using AVPs
-	 * in the session setup control protocol.
+	/* Session data offset is defined only for L2TPv2 and is
+	 * indicated by an optional 16-bit value in the header.
 	 */
 	if (tunnel->version == L2TP_HDR_VER_2) {
 		/* If offset bit set, skip it. */
@@ -856,8 +854,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 			offset = ntohs(*(__be16 *)ptr);
 			ptr += 2 + offset;
 		}
-	} else
-		ptr += session->offset;
+	}
 
 	offset = ptr - optr;
 	if (!pskb_may_pull(skb, offset))
@@ -1141,8 +1138,6 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
 		}
 		bufp += session->l2specific_len;
 	}
-	if (session->offset)
-		bufp += session->offset;
 
 	return bufp - optr;
 }
@@ -1827,7 +1822,7 @@ void l2tp_session_set_header_len(struct l2tp_session *session, int version)
 		if (session->send_seq)
 			session->hdr_len += 4;
 	} else {
-		session->hdr_len = 4 + session->cookie_len + session->l2specific_len + session->offset;
+		session->hdr_len = 4 + session->cookie_len + session->l2specific_len;
 		if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP)
 			session->hdr_len += 4;
 	}
@@ -1878,7 +1873,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 			session->recv_seq = cfg->recv_seq;
 			session->lns_mode = cfg->lns_mode;
 			session->reorder_timeout = cfg->reorder_timeout;
-			session->offset = cfg->offset;
 			session->l2specific_type = cfg->l2specific_type;
 			session->l2specific_len = cfg->l2specific_len;
 			session->cookie_len = cfg->cookie_len;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 42419f1c24cf..86356a23a0a7 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -68,7 +68,6 @@ struct l2tp_session_cfg {
 	int			debug;		/* bitmask of debug message
 						 * categories */
 	u16			vlan_id;	/* VLAN pseudowire only */
-	u16			offset;		/* offset to payload */
 	u16			l2specific_len;	/* Layer 2 specific length */
 	u16			l2specific_type; /* Layer 2 specific type */
 	u8			cookie[8];	/* optional cookie */
@@ -94,8 +93,6 @@ struct l2tp_session {
 	int			cookie_len;
 	u8			peer_cookie[8];
 	int			peer_cookie_len;
-	u16			offset;		/* offset from end of L2TP header
-						   to beginning of data */
 	u16			l2specific_len;
 	u16			l2specific_type;
 	u16			hdr_len;
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index d100aed3d06f..2d2a73280ec2 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -181,8 +181,8 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
 		   session->lns_mode ? "LNS" : "LAC",
 		   session->debug,
 		   jiffies_to_msecs(session->reorder_timeout));
-	seq_printf(m, "   offset %hu l2specific %hu/%hu\n",
-		   session->offset, session->l2specific_type, session->l2specific_len);
+	seq_printf(m, "   offset 0 l2specific %hu/%hu\n",
+		   session->l2specific_type, session->l2specific_len);
 	if (session->cookie_len) {
 		seq_printf(m, "   cookie %02x%02x%02x%02x",
 			   session->cookie[0], session->cookie[1],
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index ee03bc866d1b..d6fccfdca201 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -536,9 +536,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 	}
 
 	if (tunnel->version > 2) {
-		if (info->attrs[L2TP_ATTR_OFFSET])
-			cfg.offset = nla_get_u16(info->attrs[L2TP_ATTR_OFFSET]);
-
 		if (info->attrs[L2TP_ATTR_DATA_SEQ])
 			cfg.data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]);
 
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 85aae8c84aeb..789e66b0187a 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -726,7 +726,6 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	struct sk_buff *skb = NULL;
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
-	unsigned long cpu_flags;
 	size_t copied = 0;
 	u32 peek_seq = 0;
 	u32 *seq, skb_len;
@@ -851,9 +850,8 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			goto copy_uaddr;
 
 		if (!(flags & MSG_PEEK)) {
-			spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags);
-			sk_eat_skb(sk, skb);
-			spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags);
+			skb_unlink(skb, &sk->sk_receive_queue);
+			kfree_skb(skb);
 			*seq = 0;
 		}
 
@@ -874,9 +872,8 @@ copy_uaddr:
 		llc_cmsg_rcv(msg, skb);
 
 	if (!(flags & MSG_PEEK)) {
-		spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags);
-		sk_eat_skb(sk, skb);
-		spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags);
+		skb_unlink(skb, &sk->sk_receive_queue);
+		kfree_skb(skb);
 		*seq = 0;
 	}
 
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 79c346fd859b..b9290a183a2f 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -734,6 +734,7 @@ void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk)
 	llc_sk(sk)->sap = sap;
 
 	spin_lock_bh(&sap->sk_lock);
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	sap->sk_count++;
 	sk_nulls_add_node_rcu(sk, laddr_hb);
 	hlist_add_head(&llc->dev_hash_node, dev_hb);
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 45319cc01121..80c45567ee3a 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -7,7 +7,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
- * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright(c) 2015-2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -741,46 +741,43 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local,
 	ieee80211_agg_start_txq(sta, tid, true);
 }
 
-void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid)
+void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid,
+			      struct tid_ampdu_tx *tid_tx)
 {
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
-	struct sta_info *sta;
-	struct tid_ampdu_tx *tid_tx;
 
-	trace_api_start_tx_ba_cb(sdata, ra, tid);
+	if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)))
+		return;
+
+	if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state))
+		ieee80211_agg_tx_operational(local, sta, tid);
+}
+
+static struct tid_ampdu_tx *
+ieee80211_lookup_tid_tx(struct ieee80211_sub_if_data *sdata,
+			const u8 *ra, u16 tid, struct sta_info **sta)
+{
+	struct tid_ampdu_tx *tid_tx;
 
 	if (tid >= IEEE80211_NUM_TIDS) {
 		ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n",
 		       tid, IEEE80211_NUM_TIDS);
-		return;
+		return NULL;
 	}
 
-	mutex_lock(&local->sta_mtx);
-	sta = sta_info_get_bss(sdata, ra);
-	if (!sta) {
-		mutex_unlock(&local->sta_mtx);
+	*sta = sta_info_get_bss(sdata, ra);
+	if (!*sta) {
 		ht_dbg(sdata, "Could not find station: %pM\n", ra);
-		return;
+		return NULL;
 	}
 
-	mutex_lock(&sta->ampdu_mlme.mtx);
-	tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
+	tid_tx = rcu_dereference((*sta)->ampdu_mlme.tid_tx[tid]);
 
-	if (WARN_ON(!tid_tx)) {
+	if (WARN_ON(!tid_tx))
 		ht_dbg(sdata, "addBA was not requested!\n");
-		goto unlock;
-	}
 
-	if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)))
-		goto unlock;
-
-	if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state))
-		ieee80211_agg_tx_operational(local, sta, tid);
-
- unlock:
-	mutex_unlock(&sta->ampdu_mlme.mtx);
-	mutex_unlock(&local->sta_mtx);
+	return tid_tx;
 }
 
 void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif,
@@ -788,19 +785,20 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif,
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_ra_tid *ra_tid;
-	struct sk_buff *skb = dev_alloc_skb(0);
+	struct sta_info *sta;
+	struct tid_ampdu_tx *tid_tx;
 
-	if (unlikely(!skb))
-		return;
+	trace_api_start_tx_ba_cb(sdata, ra, tid);
 
-	ra_tid = (struct ieee80211_ra_tid *) &skb->cb;
-	memcpy(&ra_tid->ra, ra, ETH_ALEN);
-	ra_tid->tid = tid;
+	rcu_read_lock();
+	tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta);
+	if (!tid_tx)
+		goto out;
 
-	skb->pkt_type = IEEE80211_SDATA_QUEUE_AGG_START;
-	skb_queue_tail(&sdata->skb_queue, skb);
-	ieee80211_queue_work(&local->hw, &sdata->work);
+	set_bit(HT_AGG_STATE_START_CB, &tid_tx->state);
+	ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work);
+ out:
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe);
 
@@ -860,37 +858,18 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid)
 }
 EXPORT_SYMBOL(ieee80211_stop_tx_ba_session);
 
-void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid)
+void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid,
+			     struct tid_ampdu_tx *tid_tx)
 {
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
-	struct ieee80211_local *local = sdata->local;
-	struct sta_info *sta;
-	struct tid_ampdu_tx *tid_tx;
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	bool send_delba = false;
 
-	trace_api_stop_tx_ba_cb(sdata, ra, tid);
-
-	if (tid >= IEEE80211_NUM_TIDS) {
-		ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n",
-		       tid, IEEE80211_NUM_TIDS);
-		return;
-	}
-
-	ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", ra, tid);
-
-	mutex_lock(&local->sta_mtx);
-
-	sta = sta_info_get_bss(sdata, ra);
-	if (!sta) {
-		ht_dbg(sdata, "Could not find station: %pM\n", ra);
-		goto unlock;
-	}
+	ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n",
+	       sta->sta.addr, tid);
 
-	mutex_lock(&sta->ampdu_mlme.mtx);
 	spin_lock_bh(&sta->lock);
-	tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
 
-	if (!tid_tx || !test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
+	if (!test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
 		ht_dbg(sdata,
 		       "unexpected callback to A-MPDU stop for %pM tid %d\n",
 		       sta->sta.addr, tid);
@@ -906,12 +885,8 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid)
 	spin_unlock_bh(&sta->lock);
 
 	if (send_delba)
-		ieee80211_send_delba(sdata, ra, tid,
+		ieee80211_send_delba(sdata, sta->sta.addr, tid,
 			WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE);
-
-	mutex_unlock(&sta->ampdu_mlme.mtx);
- unlock:
-	mutex_unlock(&local->sta_mtx);
 }
 
 void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif,
@@ -919,19 +894,20 @@ void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif,
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_ra_tid *ra_tid;
-	struct sk_buff *skb = dev_alloc_skb(0);
+	struct sta_info *sta;
+	struct tid_ampdu_tx *tid_tx;
 
-	if (unlikely(!skb))
-		return;
+	trace_api_stop_tx_ba_cb(sdata, ra, tid);
 
-	ra_tid = (struct ieee80211_ra_tid *) &skb->cb;
-	memcpy(&ra_tid->ra, ra, ETH_ALEN);
-	ra_tid->tid = tid;
+	rcu_read_lock();
+	tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta);
+	if (!tid_tx)
+		goto out;
 
-	skb->pkt_type = IEEE80211_SDATA_QUEUE_AGG_STOP;
-	skb_queue_tail(&sdata->skb_queue, skb);
-	ieee80211_queue_work(&local->hw, &sdata->work);
+	set_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state);
+	ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work);
+ out:
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb_irqsafe);
 
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index e63fd12f923a..6ef9d32c34f1 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -386,7 +386,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_AP_VLAN:
 		/* Keys without a station are used for TX only */
-		if (key->sta && test_sta_flag(key->sta, WLAN_STA_MFP))
+		if (sta && test_sta_flag(sta, WLAN_STA_MFP))
 			key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT;
 		break;
 	case NL80211_IFTYPE_ADHOC:
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index f4a528773563..6ca5442b1e03 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -7,6 +7,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
+ * Copyright 2017	Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -289,8 +290,6 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta,
 {
 	int i;
 
-	cancel_work_sync(&sta->ampdu_mlme.work);
-
 	for (i = 0; i <  IEEE80211_NUM_TIDS; i++) {
 		__ieee80211_stop_tx_ba_session(sta, i, reason);
 		__ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT,
@@ -298,6 +297,9 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta,
 					       reason != AGG_STOP_DESTROY_STA &&
 					       reason != AGG_STOP_PEER_REQUEST);
 	}
+
+	/* stopping might queue the work again - so cancel only afterwards */
+	cancel_work_sync(&sta->ampdu_mlme.work);
 }
 
 void ieee80211_ba_session_work(struct work_struct *work)
@@ -352,10 +354,16 @@ void ieee80211_ba_session_work(struct work_struct *work)
 		spin_unlock_bh(&sta->lock);
 
 		tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
-		if (tid_tx && test_and_clear_bit(HT_AGG_STATE_WANT_STOP,
-						 &tid_tx->state))
+		if (!tid_tx)
+			continue;
+
+		if (test_and_clear_bit(HT_AGG_STATE_START_CB, &tid_tx->state))
+			ieee80211_start_tx_ba_cb(sta, tid, tid_tx);
+		if (test_and_clear_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state))
 			___ieee80211_stop_tx_ba_session(sta, tid,
 							AGG_STOP_LOCAL_REQUEST);
+		if (test_and_clear_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state))
+			ieee80211_stop_tx_ba_cb(sta, tid, tid_tx);
 	}
 	mutex_unlock(&sta->ampdu_mlme.mtx);
 }
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index a5acaf1efaab..0c0695eb2609 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -948,8 +948,8 @@ static void ieee80211_rx_mgmt_deauth_ibss(struct ieee80211_sub_if_data *sdata,
 	if (len < IEEE80211_DEAUTH_FRAME_LEN)
 		return;
 
-	ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM BSSID=%pM (reason: %d)\n",
-		 mgmt->sa, mgmt->da, mgmt->bssid, reason);
+	ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da);
+	ibss_dbg(sdata, "\tBSSID=%pM (reason: %d)\n", mgmt->bssid, reason);
 	sta_info_destroy_addr(sdata, mgmt->sa);
 }
 
@@ -967,9 +967,9 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata,
 	auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg);
 	auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction);
 
-	ibss_dbg(sdata,
-		 "RX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=%d)\n",
-		 mgmt->sa, mgmt->da, mgmt->bssid, auth_transaction);
+	ibss_dbg(sdata, "RX Auth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da);
+	ibss_dbg(sdata, "\tBSSID=%pM (auth_transaction=%d)\n",
+		 mgmt->bssid, auth_transaction);
 
 	if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1)
 		return;
@@ -1176,10 +1176,10 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 		rx_timestamp = drv_get_tsf(local, sdata);
 	}
 
-	ibss_dbg(sdata,
-		 "RX beacon SA=%pM BSSID=%pM TSF=0x%llx BCN=0x%llx diff=%lld @%lu\n",
+	ibss_dbg(sdata, "RX beacon SA=%pM BSSID=%pM TSF=0x%llx\n",
 		 mgmt->sa, mgmt->bssid,
-		 (unsigned long long)rx_timestamp,
+		 (unsigned long long)rx_timestamp);
+	ibss_dbg(sdata, "\tBCN=0x%llx diff=%lld @%lu\n",
 		 (unsigned long long)beacon_timestamp,
 		 (unsigned long long)(rx_timestamp - beacon_timestamp),
 		 jiffies);
@@ -1538,9 +1538,9 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata,
 
 	tx_last_beacon = drv_tx_last_beacon(local);
 
-	ibss_dbg(sdata,
-		 "RX ProbeReq SA=%pM DA=%pM BSSID=%pM (tx_last_beacon=%d)\n",
-		 mgmt->sa, mgmt->da, mgmt->bssid, tx_last_beacon);
+	ibss_dbg(sdata, "RX ProbeReq SA=%pM DA=%pM\n", mgmt->sa, mgmt->da);
+	ibss_dbg(sdata, "\tBSSID=%pM (tx_last_beacon=%d)\n",
+		 mgmt->bssid, tx_last_beacon);
 
 	if (!tx_last_beacon && is_multicast_ether_addr(mgmt->da))
 		return;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 7fd544d970d9..8a690ebd7374 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1026,8 +1026,6 @@ struct ieee80211_rx_agg {
 
 enum sdata_queue_type {
 	IEEE80211_SDATA_QUEUE_TYPE_FRAME	= 0,
-	IEEE80211_SDATA_QUEUE_AGG_START		= 1,
-	IEEE80211_SDATA_QUEUE_AGG_STOP		= 2,
 	IEEE80211_SDATA_QUEUE_RX_AGG_START	= 3,
 	IEEE80211_SDATA_QUEUE_RX_AGG_STOP	= 4,
 };
@@ -1416,12 +1414,6 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata)
 	return local->hw.wiphy->bands[band];
 }
 
-/* this struct represents 802.11n's RA/TID combination */
-struct ieee80211_ra_tid {
-	u8 ra[ETH_ALEN];
-	u16 tid;
-};
-
 /* this struct holds the value parsing from channel switch IE  */
 struct ieee80211_csa_ie {
 	struct cfg80211_chan_def chandef;
@@ -1765,8 +1757,10 @@ int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 				   enum ieee80211_agg_stop_reason reason);
 int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 				    enum ieee80211_agg_stop_reason reason);
-void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid);
-void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid);
+void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid,
+			      struct tid_ampdu_tx *tid_tx);
+void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid,
+			     struct tid_ampdu_tx *tid_tx);
 void ieee80211_ba_session_work(struct work_struct *work);
 void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid);
 void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index fa7d757fef95..760ba8ec2944 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1248,7 +1248,6 @@ static void ieee80211_iface_work(struct work_struct *work)
 	struct ieee80211_local *local = sdata->local;
 	struct sk_buff *skb;
 	struct sta_info *sta;
-	struct ieee80211_ra_tid *ra_tid;
 	struct ieee80211_rx_agg *rx_agg;
 
 	if (!ieee80211_sdata_running(sdata))
@@ -1264,15 +1263,7 @@ static void ieee80211_iface_work(struct work_struct *work)
 	while ((skb = skb_dequeue(&sdata->skb_queue))) {
 		struct ieee80211_mgmt *mgmt = (void *)skb->data;
 
-		if (skb->pkt_type == IEEE80211_SDATA_QUEUE_AGG_START) {
-			ra_tid = (void *)&skb->cb;
-			ieee80211_start_tx_ba_cb(&sdata->vif, ra_tid->ra,
-						 ra_tid->tid);
-		} else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_AGG_STOP) {
-			ra_tid = (void *)&skb->cb;
-			ieee80211_stop_tx_ba_cb(&sdata->vif, ra_tid->ra,
-						ra_tid->tid);
-		} else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) {
+		if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) {
 			rx_agg = (void *)&skb->cb;
 			mutex_lock(&local->sta_mtx);
 			sta = sta_info_get_bss(sdata, rx_agg->addr);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 2bb6899854d4..e3bbfb20ae82 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -254,8 +254,27 @@ static void ieee80211_restart_work(struct work_struct *work)
 	     "%s called with hardware scan in progress\n", __func__);
 
 	rtnl_lock();
-	list_for_each_entry(sdata, &local->interfaces, list)
+	list_for_each_entry(sdata, &local->interfaces, list) {
+		/*
+		 * XXX: there may be more work for other vif types and even
+		 * for station mode: a good thing would be to run most of
+		 * the iface type's dependent _stop (ieee80211_mg_stop,
+		 * ieee80211_ibss_stop) etc...
+		 * For now, fix only the specific bug that was seen: race
+		 * between csa_connection_drop_work and us.
+		 */
+		if (sdata->vif.type == NL80211_IFTYPE_STATION) {
+			/*
+			 * This worker is scheduled from the iface worker that
+			 * runs on mac80211's workqueue, so we can't be
+			 * scheduling this worker after the cancel right here.
+			 * The exception is ieee80211_chswitch_done.
+			 * Then we can have a race...
+			 */
+			cancel_work_sync(&sdata->u.mgd.csa_connection_drop_work);
+		}
 		flush_delayed_work(&sdata->dec_tailroom_needed_wk);
+	}
 	ieee80211_scan_cancel(local);
 
 	/* make sure any new ROC will consider local->in_reconfig */
@@ -466,10 +485,7 @@ static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = {
 		cpu_to_le32(IEEE80211_VHT_CAP_RXLDPC |
 			    IEEE80211_VHT_CAP_SHORT_GI_80 |
 			    IEEE80211_VHT_CAP_SHORT_GI_160 |
-			    IEEE80211_VHT_CAP_RXSTBC_1 |
-			    IEEE80211_VHT_CAP_RXSTBC_2 |
-			    IEEE80211_VHT_CAP_RXSTBC_3 |
-			    IEEE80211_VHT_CAP_RXSTBC_4 |
+			    IEEE80211_VHT_CAP_RXSTBC_MASK |
 			    IEEE80211_VHT_CAP_TXSTBC |
 			    IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE |
 			    IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
@@ -1164,6 +1180,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 #if IS_ENABLED(CONFIG_IPV6)
 	unregister_inet6addr_notifier(&local->ifa6_notifier);
 #endif
+	ieee80211_txq_teardown_flows(local);
 
 	rtnl_lock();
 
@@ -1191,7 +1208,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 	skb_queue_purge(&local->skb_queue);
 	skb_queue_purge(&local->skb_queue_unreliable);
 	skb_queue_purge(&local->skb_queue_tdls_chsw);
-	ieee80211_txq_teardown_flows(local);
 
 	destroy_workqueue(local->workqueue);
 	wiphy_unregister(local->hw.wiphy);
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index fed598a202c8..b0acb2961e80 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -563,6 +563,10 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
 		forward = false;
 		reply = true;
 		target_metric = 0;
+
+		if (SN_GT(target_sn, ifmsh->sn))
+			ifmsh->sn = target_sn;
+
 		if (time_after(jiffies, ifmsh->last_sn_update +
 					net_traversal_jiffies(sdata)) ||
 		    time_before(jiffies, ifmsh->last_sn_update)) {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index e6f42d12222e..39451c84c785 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -989,6 +989,10 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 	 */
 
 	if (sdata->reserved_chanctx) {
+		struct ieee80211_supported_band *sband = NULL;
+		struct sta_info *mgd_sta = NULL;
+		enum ieee80211_sta_rx_bandwidth bw = IEEE80211_STA_RX_BW_20;
+
 		/*
 		 * with multi-vif csa driver may call ieee80211_csa_finish()
 		 * many times while waiting for other interfaces to use their
@@ -997,6 +1001,48 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 		if (sdata->reserved_ready)
 			goto out;
 
+		if (sdata->vif.bss_conf.chandef.width !=
+		    sdata->csa_chandef.width) {
+			/*
+			 * For managed interface, we need to also update the AP
+			 * station bandwidth and align the rate scale algorithm
+			 * on the bandwidth change. Here we only consider the
+			 * bandwidth of the new channel definition (as channel
+			 * switch flow does not have the full HT/VHT/HE
+			 * information), assuming that if additional changes are
+			 * required they would be done as part of the processing
+			 * of the next beacon from the AP.
+			 */
+			switch (sdata->csa_chandef.width) {
+			case NL80211_CHAN_WIDTH_20_NOHT:
+			case NL80211_CHAN_WIDTH_20:
+			default:
+				bw = IEEE80211_STA_RX_BW_20;
+				break;
+			case NL80211_CHAN_WIDTH_40:
+				bw = IEEE80211_STA_RX_BW_40;
+				break;
+			case NL80211_CHAN_WIDTH_80:
+				bw = IEEE80211_STA_RX_BW_80;
+				break;
+			case NL80211_CHAN_WIDTH_80P80:
+			case NL80211_CHAN_WIDTH_160:
+				bw = IEEE80211_STA_RX_BW_160;
+				break;
+			}
+
+			mgd_sta = sta_info_get(sdata, ifmgd->bssid);
+			sband =
+				local->hw.wiphy->bands[sdata->csa_chandef.chan->band];
+		}
+
+		if (sdata->vif.bss_conf.chandef.width >
+		    sdata->csa_chandef.width) {
+			mgd_sta->sta.bandwidth = bw;
+			rate_control_rate_update(local, sband, mgd_sta,
+						 IEEE80211_RC_BW_CHANGED);
+		}
+
 		ret = ieee80211_vif_use_reserved_context(sdata);
 		if (ret) {
 			sdata_info(sdata,
@@ -1007,6 +1053,13 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 			goto out;
 		}
 
+		if (sdata->vif.bss_conf.chandef.width <
+		    sdata->csa_chandef.width) {
+			mgd_sta->sta.bandwidth = bw;
+			rate_control_rate_update(local, sband, mgd_sta,
+						 IEEE80211_RC_BW_CHANGED);
+		}
+
 		goto out;
 	}
 
@@ -1229,6 +1282,16 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 					 cbss->beacon_interval));
 	return;
  drop_connection:
+	/*
+	 * This is just so that the disconnect flow will know that
+	 * we were trying to switch channel and failed. In case the
+	 * mode is 1 (we are not allowed to Tx), we will know not to
+	 * send a deauthentication frame. Those two fields will be
+	 * reset when the disconnection worker runs.
+	 */
+	sdata->vif.csa_active = true;
+	sdata->csa_block_tx = csa_ie.mode;
+
 	ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work);
 	mutex_unlock(&local->chanctx_mtx);
 	mutex_unlock(&local->mtx);
@@ -2401,6 +2464,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
+	bool tx;
 
 	sdata_lock(sdata);
 	if (!ifmgd->associated) {
@@ -2408,6 +2472,8 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 		return;
 	}
 
+	tx = !sdata->csa_block_tx;
+
 	/* AP is probably out of range (or not reachable for another reason) so
 	 * remove the bss struct for that AP.
 	 */
@@ -2415,7 +2481,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 
 	ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH,
 			       WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
-			       true, frame_buf);
+			       tx, frame_buf);
 	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
 	ifmgd->csa_waiting_bcn = false;
@@ -2426,7 +2492,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 	}
 	mutex_unlock(&local->mtx);
 
-	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true,
+	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx,
 				    WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY);
 
 	sdata_unlock(sdata);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 15599c70a38f..cc808ac783e5 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -115,6 +115,8 @@ enum ieee80211_sta_info_flags {
 #define HT_AGG_STATE_STOPPING		3
 #define HT_AGG_STATE_WANT_START		4
 #define HT_AGG_STATE_WANT_STOP		5
+#define HT_AGG_STATE_START_CB		6
+#define HT_AGG_STATE_STOP_CB		7
 
 enum ieee80211_agg_stop_reason {
 	AGG_STOP_DECLINED,
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 72fe9bc7a1f9..7892bac21eac 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -472,11 +472,6 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local,
 	if (!skb)
 		return;
 
-	if (dropped) {
-		dev_kfree_skb_any(skb);
-		return;
-	}
-
 	if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) {
 		u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie;
 		struct ieee80211_sub_if_data *sdata;
@@ -498,6 +493,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local,
 		rcu_read_unlock();
 
 		dev_kfree_skb_any(skb);
+	} else if (dropped) {
+		dev_kfree_skb_any(skb);
 	} else {
 		/* consumes skb */
 		skb_complete_wifi_ack(skb, acked);
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index f20dcf1b1830..c64ae68ae4f8 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -16,6 +16,7 @@
 #include "ieee80211_i.h"
 #include "driver-ops.h"
 #include "rate.h"
+#include "wme.h"
 
 /* give usermode some time for retries in setting up the TDLS session */
 #define TDLS_PEER_SETUP_TIMEOUT	(15 * HZ)
@@ -1019,14 +1020,13 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 	switch (action_code) {
 	case WLAN_TDLS_SETUP_REQUEST:
 	case WLAN_TDLS_SETUP_RESPONSE:
-		skb_set_queue_mapping(skb, IEEE80211_AC_BK);
-		skb->priority = 2;
+		skb->priority = 256 + 2;
 		break;
 	default:
-		skb_set_queue_mapping(skb, IEEE80211_AC_VI);
-		skb->priority = 5;
+		skb->priority = 256 + 5;
 		break;
 	}
+	skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, skb));
 
 	/*
 	 * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress.
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 84582998f65f..58fba4e569e6 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1833,7 +1833,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 			sdata->vif.hw_queue[skb_get_queue_mapping(skb)];
 
 	if (invoke_tx_handlers_early(&tx))
-		return false;
+		return true;
 
 	if (ieee80211_queue_skb(local, sdata, tx.sta, tx.skb))
 		return true;
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 9a14c237830f..b259a5814965 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -213,13 +213,13 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_CIDR]) {
 		e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
-		if (!e.cidr[0] || e.cidr[0] > HOST_MASK)
+		if (e.cidr[0] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
 	if (tb[IPSET_ATTR_CIDR2]) {
 		e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
-		if (!e.cidr[1] || e.cidr[1] > HOST_MASK)
+		if (e.cidr[1] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
@@ -492,13 +492,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_CIDR]) {
 		e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
-		if (!e.cidr[0] || e.cidr[0] > HOST_MASK)
+		if (e.cidr[0] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
 	if (tb[IPSET_ATTR_CIDR2]) {
 		e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
-		if (!e.cidr[1] || e.cidr[1] > HOST_MASK)
+		if (e.cidr[1] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index db3586ba1211..19b3f4fbea52 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -918,19 +918,22 @@ static unsigned int early_drop_list(struct net *net,
 	return drops;
 }
 
-static noinline int early_drop(struct net *net, unsigned int _hash)
+static noinline int early_drop(struct net *net, unsigned int hash)
 {
-	unsigned int i;
+	unsigned int i, bucket;
 
 	for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
 		struct hlist_nulls_head *ct_hash;
-		unsigned int hash, hsize, drops;
+		unsigned int hsize, drops;
 
 		rcu_read_lock();
 		nf_conntrack_get_ht(&ct_hash, &hsize);
-		hash = reciprocal_scale(_hash++, hsize);
+		if (!i)
+			bucket = reciprocal_scale(hash, hsize);
+		else
+			bucket = (bucket + 1) % hsize;
 
-		drops = early_drop_list(net, &ct_hash[hash]);
+		drops = early_drop_list(net, &ct_hash[bucket]);
 		rcu_read_unlock();
 
 		if (drops) {
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 624d6e4dcd5c..51b0d832bd07 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -421,7 +421,7 @@ nf_nat_setup_info(struct nf_conn *ct,
 		else
 			ct->status |= IPS_DST_NAT;
 
-		if (nfct_help(ct))
+		if (nfct_help(ct) && !nfct_seqadj(ct))
 			if (!nfct_seqadj_ext_add(ct))
 				return NF_DROP;
 	}
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index bb5d6a058fb7..921c9bd7e1e7 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -116,6 +116,22 @@ static void idletimer_tg_expired(unsigned long data)
 	schedule_work(&timer->work);
 }
 
+static int idletimer_check_sysfs_name(const char *name, unsigned int size)
+{
+	int ret;
+
+	ret = xt_check_proc_name(name, size);
+	if (ret < 0)
+		return ret;
+
+	if (!strcmp(name, "power") ||
+	    !strcmp(name, "subsystem") ||
+	    !strcmp(name, "uevent"))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int idletimer_tg_create(struct idletimer_tg_info *info)
 {
 	int ret;
@@ -126,6 +142,10 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
 		goto out;
 	}
 
+	ret = idletimer_check_sysfs_name(info->label, sizeof(info->label));
+	if (ret < 0)
+		goto out_free_timer;
+
 	sysfs_attr_init(&info->timer->attr.attr);
 	info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL);
 	if (!info->timer->attr.attr.name) {
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index a123d0dc1ef9..053ba8646155 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -787,7 +787,8 @@ static int netlbl_unlabel_addrinfo_get(struct genl_info *info,
 {
 	u32 addr_len;
 
-	if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR]) {
+	if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR] &&
+	    info->attrs[NLBL_UNLABEL_A_IPV4MASK]) {
 		addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]);
 		if (addr_len != sizeof(struct in_addr) &&
 		    addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV4MASK]))
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 169156cfd4c8..96e61eab19bc 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -505,7 +505,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
 		 ic->i_send_cq, ic->i_recv_cq);
 
-	return ret;
+	goto out;
 
 sends_out:
 	vfree(ic->i_sends);
@@ -530,6 +530,7 @@ send_cq_out:
 		ic->i_send_cq = NULL;
 rds_ibdev_out:
 	rds_ib_remove_conn(rds_ibdev, conn);
+out:
 	rds_ib_dev_put(rds_ibdev);
 
 	return ret;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index f3ac85a285a2..a4380e182e6c 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -216,10 +216,11 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb,
 /*
  * Apply a hard ACK by advancing the Tx window.
  */
-static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
+static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 				   struct rxrpc_ack_summary *summary)
 {
 	struct sk_buff *skb, *list = NULL;
+	bool rot_last = false;
 	int ix;
 	u8 annotation;
 
@@ -243,15 +244,17 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 		skb->next = list;
 		list = skb;
 
-		if (annotation & RXRPC_TX_ANNO_LAST)
+		if (annotation & RXRPC_TX_ANNO_LAST) {
 			set_bit(RXRPC_CALL_TX_LAST, &call->flags);
+			rot_last = true;
+		}
 		if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK)
 			summary->nr_rot_new_acks++;
 	}
 
 	spin_unlock(&call->lock);
 
-	trace_rxrpc_transmit(call, (test_bit(RXRPC_CALL_TX_LAST, &call->flags) ?
+	trace_rxrpc_transmit(call, (rot_last ?
 				    rxrpc_transmit_rotate_last :
 				    rxrpc_transmit_rotate));
 	wake_up(&call->waitq);
@@ -262,6 +265,8 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 		skb->next = NULL;
 		rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
 	}
+
+	return rot_last;
 }
 
 /*
@@ -332,11 +337,11 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
 				ktime_get_real());
 	}
 
-	if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags))
-		rxrpc_rotate_tx_window(call, top, &summary);
 	if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
-		rxrpc_proto_abort("TXL", call, top);
-		return false;
+		if (!rxrpc_rotate_tx_window(call, top, &summary)) {
+			rxrpc_proto_abort("TXL", call, top);
+			return false;
+		}
 	}
 	if (!rxrpc_end_tx_phase(call, true, "ETD"))
 		return false;
@@ -803,6 +808,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 				  rxrpc_propose_ack_respond_to_ack);
 	}
 
+	/* Discard any out-of-order or duplicate ACKs. */
+	if (before_eq(sp->hdr.serial, call->acks_latest)) {
+		_debug("discard ACK %d <= %d",
+		       sp->hdr.serial, call->acks_latest);
+		return;
+	}
+	call->acks_latest_ts = skb->tstamp;
+	call->acks_latest = sp->hdr.serial;
+
+	/* Parse rwind and mtu sizes if provided. */
 	ioffset = offset + nr_acks + 3;
 	if (skb->len >= ioffset + sizeof(buf.info)) {
 		if (skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0)
@@ -824,23 +839,18 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 		return;
 	}
 
-	/* Discard any out-of-order or duplicate ACKs. */
-	if (before_eq(sp->hdr.serial, call->acks_latest)) {
-		_debug("discard ACK %d <= %d",
-		       sp->hdr.serial, call->acks_latest);
-		return;
-	}
-	call->acks_latest_ts = skb->tstamp;
-	call->acks_latest = sp->hdr.serial;
-
 	if (before(hard_ack, call->tx_hard_ack) ||
 	    after(hard_ack, call->tx_top))
 		return rxrpc_proto_abort("AKW", call, 0);
 	if (nr_acks > call->tx_top - hard_ack)
 		return rxrpc_proto_abort("AKN", call, 0);
 
-	if (after(hard_ack, call->tx_hard_ack))
-		rxrpc_rotate_tx_window(call, hard_ack, &summary);
+	if (after(hard_ack, call->tx_hard_ack)) {
+		if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
+			rxrpc_end_tx_phase(call, false, "ETA");
+			return;
+		}
+	}
 
 	if (nr_acks > 0) {
 		if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0)
@@ -849,11 +859,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 				      &summary);
 	}
 
-	if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
-		rxrpc_end_tx_phase(call, false, "ETA");
-		return;
-	}
-
 	if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] &
 	    RXRPC_TX_ANNO_LAST &&
 	    summary.nr_acks == call->tx_top - hard_ack &&
@@ -875,8 +880,7 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb)
 
 	_proto("Rx ACKALL %%%u", sp->hdr.serial);
 
-	rxrpc_rotate_tx_window(call, call->tx_top, &summary);
-	if (test_bit(RXRPC_CALL_TX_LAST, &call->flags))
+	if (rxrpc_rotate_tx_window(call, call->tx_top, &summary))
 		rxrpc_end_tx_phase(call, false, "ETL");
 }
 
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 44941e25f3ad..729c0e4eca21 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -411,7 +411,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
 	if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) {
 		if (tb[TCA_GRED_LIMIT] != NULL)
 			sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
-		return gred_change_table_def(sch, opt);
+		return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
 	}
 
 	if (tb[TCA_GRED_PARMS] == NULL ||
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 738c55e994c4..7e127cde1ccc 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -488,8 +488,9 @@ void sctp_assoc_set_primary(struct sctp_association *asoc,
 void sctp_assoc_rm_peer(struct sctp_association *asoc,
 			struct sctp_transport *peer)
 {
-	struct list_head	*pos;
-	struct sctp_transport	*transport;
+	struct sctp_transport *transport;
+	struct list_head *pos;
+	struct sctp_chunk *ch;
 
 	pr_debug("%s: association:%p addr:%pISpc\n",
 		 __func__, asoc, &peer->ipaddr.sa);
@@ -547,7 +548,6 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
 	 */
 	if (!list_empty(&peer->transmitted)) {
 		struct sctp_transport *active = asoc->peer.active_path;
-		struct sctp_chunk *ch;
 
 		/* Reset the transport of each chunk on this list */
 		list_for_each_entry(ch, &peer->transmitted,
@@ -569,6 +569,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
 				sctp_transport_hold(active);
 	}
 
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list)
+		if (ch->transport == peer)
+			ch->transport = NULL;
+
 	asoc->peer.transport_count--;
 
 	sctp_transport_free(peer);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 64d2d9ea2f8c..93e60068800b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -185,13 +185,13 @@ static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
 		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
 			cb(chunk);
 
-	list_for_each_entry(chunk, &q->retransmit, list)
+	list_for_each_entry(chunk, &q->retransmit, transmitted_list)
 		cb(chunk);
 
-	list_for_each_entry(chunk, &q->sacked, list)
+	list_for_each_entry(chunk, &q->sacked, transmitted_list)
 		cb(chunk);
 
-	list_for_each_entry(chunk, &q->abandoned, list)
+	list_for_each_entry(chunk, &q->abandoned, transmitted_list)
 		cb(chunk);
 
 	list_for_each_entry(chunk, &q->out_chunk_list, list)
@@ -248,11 +248,10 @@ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id)
 
 	spin_lock_bh(&sctp_assocs_id_lock);
 	asoc = (struct sctp_association *)idr_find(&sctp_assocs_id, (int)id);
+	if (asoc && (asoc->base.sk != sk || asoc->base.dead))
+		asoc = NULL;
 	spin_unlock_bh(&sctp_assocs_id_lock);
 
-	if (!asoc || (asoc->base.sk != sk) || asoc->base.dead)
-		return NULL;
-
 	return asoc;
 }
 
@@ -3733,32 +3732,16 @@ static int sctp_setsockopt_pr_supported(struct sock *sk,
 					unsigned int optlen)
 {
 	struct sctp_assoc_value params;
-	struct sctp_association *asoc;
-	int retval = -EINVAL;
 
 	if (optlen != sizeof(params))
-		goto out;
-
-	if (copy_from_user(&params, optval, optlen)) {
-		retval = -EFAULT;
-		goto out;
-	}
-
-	asoc = sctp_id2assoc(sk, params.assoc_id);
-	if (asoc) {
-		asoc->prsctp_enable = !!params.assoc_value;
-	} else if (!params.assoc_id) {
-		struct sctp_sock *sp = sctp_sk(sk);
+		return -EINVAL;
 
-		sp->ep->prsctp_enable = !!params.assoc_value;
-	} else {
-		goto out;
-	}
+	if (copy_from_user(&params, optval, optlen))
+		return -EFAULT;
 
-	retval = 0;
+	sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value;
 
-out:
-	return retval;
+	return 0;
 }
 
 static int sctp_setsockopt_default_prinfo(struct sock *sk,
diff --git a/net/socket.c b/net/socket.c
index 35fa349ba274..d9e2989c10c4 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2774,9 +2774,14 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32)
 		    copy_in_user(&rxnfc->fs.ring_cookie,
 				 &compat_rxnfc->fs.ring_cookie,
 				 (void __user *)(&rxnfc->fs.location + 1) -
-				 (void __user *)&rxnfc->fs.ring_cookie) ||
-		    copy_in_user(&rxnfc->rule_cnt, &compat_rxnfc->rule_cnt,
-				 sizeof(rxnfc->rule_cnt)))
+				 (void __user *)&rxnfc->fs.ring_cookie))
+			return -EFAULT;
+		if (ethcmd == ETHTOOL_GRXCLSRLALL) {
+			if (put_user(rule_cnt, &rxnfc->rule_cnt))
+				return -EFAULT;
+		} else if (copy_in_user(&rxnfc->rule_cnt,
+					&compat_rxnfc->rule_cnt,
+					sizeof(rxnfc->rule_cnt)))
 			return -EFAULT;
 	}
 
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index f1df9837f1ac..1ac08dcbf85d 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -281,13 +281,7 @@ static bool generic_key_to_expire(struct rpc_cred *cred)
 {
 	struct auth_cred *acred = &container_of(cred, struct generic_cred,
 						gc_base)->acred;
-	bool ret;
-
-	get_rpccred(cred);
-	ret = test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags);
-	put_rpccred(cred);
-
-	return ret;
+	return test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags);
 }
 
 static const struct rpc_credops generic_credops = {
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 9c9db55a0c1e..064f20bb845a 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1038,7 +1038,7 @@ static void call_xpt_users(struct svc_xprt *xprt)
 	spin_lock(&xprt->xpt_lock);
 	while (!list_empty(&xprt->xpt_users)) {
 		u = list_first_entry(&xprt->xpt_users, struct svc_xpt_user, list);
-		list_del(&u->list);
+		list_del_init(&u->list);
 		u->callback(u);
 	}
 	spin_unlock(&xprt->xpt_lock);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 7f1071e103ca..69846c6574ef 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -512,7 +512,7 @@ EXPORT_SYMBOL_GPL(xdr_commit_encode);
 static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
 		size_t nbytes)
 {
-	static __be32 *p;
+	__be32 *p;
 	int space_left;
 	int frag1bytes, frag2bytes;
 
@@ -639,11 +639,10 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 		WARN_ON_ONCE(xdr->iov);
 		return;
 	}
-	if (fraglen) {
+	if (fraglen)
 		xdr->end = head->iov_base + head->iov_len;
-		xdr->page_ptr--;
-	}
 	/* (otherwise assume xdr->end is already set) */
+	xdr->page_ptr--;
 	head->iov_len = len;
 	buf->len = len;
 	xdr->p = head->iov_base + head->iov_len;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 25bc5c30d7fb..9d3f047305ce 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2277,8 +2277,8 @@ void tipc_sk_reinit(struct net *net)
 
 	do {
 		tsk = ERR_PTR(rhashtable_walk_start(&iter));
-		if (tsk)
-			continue;
+		if (IS_ERR(tsk))
+			goto walk_stop;
 
 		while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
 			spin_lock_bh(&tsk->sk.sk_lock.slock);
@@ -2287,7 +2287,7 @@ void tipc_sk_reinit(struct net *net)
 			msg_set_orignode(msg, tn->own_addr);
 			spin_unlock_bh(&tsk->sk.sk_lock.slock);
 		}
-
+walk_stop:
 		rhashtable_walk_stop(&iter);
 	} while (tsk == ERR_PTR(-EAGAIN));
 }
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 271cd66e4b3b..d62affeb2a38 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -256,7 +256,9 @@ static void tipc_subscrp_delete(struct tipc_subscription *sub)
 static void tipc_subscrp_cancel(struct tipc_subscr *s,
 				struct tipc_subscriber *subscriber)
 {
+	tipc_subscrb_get(subscriber);
 	tipc_subscrb_subscrp_delete(subscriber, s);
+	tipc_subscrb_put(subscriber);
 }
 
 static struct tipc_subscription *tipc_subscrp_create(struct net *net,
@@ -387,7 +389,7 @@ int tipc_topsrv_start(struct net *net)
 	topsrv->tipc_conn_new		= tipc_subscrb_connect_cb;
 	topsrv->tipc_conn_release	= tipc_subscrb_release_cb;
 
-	strncpy(topsrv->name, name, strlen(name) + 1);
+	strscpy(topsrv->name, name, sizeof(topsrv->name));
 	tn->topsrv = topsrv;
 	atomic_set(&tn->subscription_count, 0);
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 6afac189d20f..549d0a4083b3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3422,6 +3422,7 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband,
 			return false;
 
 		/* check availability */
+		ridx = array_index_nospec(ridx, IEEE80211_HT_MCS_MASK_LEN);
 		if (sband->ht_cap.mcs.rx_mask[ridx] & rbit)
 			mcs[ridx] |= rbit;
 		else
@@ -11148,6 +11149,7 @@ static int nl80211_update_ft_ies(struct sk_buff *skb, struct genl_info *info)
 		return -EOPNOTSUPP;
 
 	if (!info->attrs[NL80211_ATTR_MDID] ||
+	    !info->attrs[NL80211_ATTR_IE] ||
 	    !is_valid_ie_attr(info->attrs[NL80211_ATTR_IE]))
 		return -EINVAL;
 
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 11235e2e4d5d..608f6eed9f04 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2298,6 +2298,7 @@ static int regulatory_hint_core(const char *alpha2)
 	request->alpha2[0] = alpha2[0];
 	request->alpha2[1] = alpha2[1];
 	request->initiator = NL80211_REGDOM_SET_BY_CORE;
+	request->wiphy_idx = WIPHY_IDX_INVALID;
 
 	queue_regulatory_request(request);
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 35ad69fd0838..435f904c1be5 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -978,13 +978,23 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 	return NULL;
 }
 
+/*
+ * Update RX channel information based on the available frame payload
+ * information. This is mainly for the 2.4 GHz band where frames can be received
+ * from neighboring channels and the Beacon frames use the DSSS Parameter Set
+ * element to indicate the current (transmitting) channel, but this might also
+ * be needed on other bands if RX frequency does not match with the actual
+ * operating channel of a BSS.
+ */
 static struct ieee80211_channel *
 cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
-			 struct ieee80211_channel *channel)
+			 struct ieee80211_channel *channel,
+			 enum nl80211_bss_scan_width scan_width)
 {
 	const u8 *tmp;
 	u32 freq;
 	int channel_number = -1;
+	struct ieee80211_channel *alt_channel;
 
 	tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen);
 	if (tmp && tmp[1] == 1) {
@@ -998,16 +1008,45 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
 		}
 	}
 
-	if (channel_number < 0)
+	if (channel_number < 0) {
+		/* No channel information in frame payload */
 		return channel;
+	}
 
 	freq = ieee80211_channel_to_frequency(channel_number, channel->band);
-	channel = ieee80211_get_channel(wiphy, freq);
-	if (!channel)
-		return NULL;
-	if (channel->flags & IEEE80211_CHAN_DISABLED)
+	alt_channel = ieee80211_get_channel(wiphy, freq);
+	if (!alt_channel) {
+		if (channel->band == NL80211_BAND_2GHZ) {
+			/*
+			 * Better not allow unexpected channels when that could
+			 * be going beyond the 1-11 range (e.g., discovering
+			 * BSS on channel 12 when radio is configured for
+			 * channel 11.
+			 */
+			return NULL;
+		}
+
+		/* No match for the payload channel number - ignore it */
+		return channel;
+	}
+
+	if (scan_width == NL80211_BSS_CHAN_WIDTH_10 ||
+	    scan_width == NL80211_BSS_CHAN_WIDTH_5) {
+		/*
+		 * Ignore channel number in 5 and 10 MHz channels where there
+		 * may not be an n:1 or 1:n mapping between frequencies and
+		 * channel numbers.
+		 */
+		return channel;
+	}
+
+	/*
+	 * Use the channel determined through the payload channel number
+	 * instead of the RX channel reported by the driver.
+	 */
+	if (alt_channel->flags & IEEE80211_CHAN_DISABLED)
 		return NULL;
-	return channel;
+	return alt_channel;
 }
 
 /* Returned bss is reference counted and must be cleaned up appropriately. */
@@ -1032,7 +1071,8 @@ cfg80211_inform_bss_data(struct wiphy *wiphy,
 		    (data->signal < 0 || data->signal > 100)))
 		return NULL;
 
-	channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan);
+	channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan,
+					   data->scan_width);
 	if (!channel)
 		return NULL;
 
@@ -1130,7 +1170,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 		return NULL;
 
 	channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
-					   ielen, data->chan);
+					   ielen, data->chan, data->scan_width);
 	if (!channel)
 		return NULL;
 
diff --git a/net/wireless/util.c b/net/wireless/util.c
index e04919d67429..42fde4a72516 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1435,7 +1435,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef,
 					  u8 *op_class)
 {
 	u8 vht_opclass;
-	u16 freq = chandef->center_freq1;
+	u32 freq = chandef->center_freq1;
 
 	if (freq >= 2412 && freq <= 2472) {
 		if (chandef->width > NL80211_CHAN_WIDTH_40)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d0dcfc68c043..155b1591b17a 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -659,9 +659,9 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 				break;
 		}
 		if (newpos)
-			hlist_add_behind(&policy->bydst, newpos);
+			hlist_add_behind_rcu(&policy->bydst, newpos);
 		else
-			hlist_add_head(&policy->bydst, chain);
+			hlist_add_head_rcu(&policy->bydst, chain);
 	}
 
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -800,9 +800,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 			break;
 	}
 	if (newpos)
-		hlist_add_behind(&policy->bydst, newpos);
+		hlist_add_behind_rcu(&policy->bydst, newpos);
 	else
-		hlist_add_head(&policy->bydst, chain);
+		hlist_add_head_rcu(&policy->bydst, chain);
 	__xfrm_policy_link(policy, dir);
 	atomic_inc(&net->xfrm.flow_cache_genid);
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 6e768093d7c8..026770884d46 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -151,10 +151,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 	err = -EINVAL;
 	switch (p->family) {
 	case AF_INET:
+		if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
+			goto out;
+
 		break;
 
 	case AF_INET6:
 #if IS_ENABLED(CONFIG_IPV6)
+		if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
+			goto out;
+
 		break;
 #else
 		err = -EAFNOSUPPORT;
@@ -1316,10 +1322,16 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 
 	switch (p->sel.family) {
 	case AF_INET:
+		if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
+			return -EINVAL;
+
 		break;
 
 	case AF_INET6:
 #if IS_ENABLED(CONFIG_IPV6)
+		if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
+			return -EINVAL;
+
 		break;
 #else
 		return  -EAFNOSUPPORT;
@@ -1400,6 +1412,9 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
 		    (ut[i].family != prev_family))
 			return -EINVAL;
 
+		if (ut[i].mode >= XFRM_MODE_MAX)
+			return -EINVAL;
+
 		prev_family = ut[i].family;
 
 		switch (ut[i].family) {