Merge v7.1.5linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

250 files changed, 4027 insertions, 2005 deletions

diff --git a/net/9p/client.c b/net/9p/client.c
index 4b942d02c29c..7d1535edfce7 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -600,6 +600,8 @@ again:
 
 	if (err == -ERESTARTSYS && c->status == Connected &&
 	    type == P9_TFLUSH) {
+		if (fatal_signal_pending(current))
+			goto recalc_sigpending;
 		sigpending = 1;
 		clear_thread_flag(TIF_SIGPENDING);
 		goto again;
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index aa5bd74d333f..b4274f10fa44 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -128,25 +128,36 @@ p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 {
 	struct p9_client *c = id->context;
 	struct p9_trans_rdma *rdma = c->trans;
+	unsigned long flags;
+
 	switch (event->event) {
 	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		spin_lock_irqsave(&rdma->req_lock, flags);
 		BUG_ON(rdma->state != P9_RDMA_INIT);
 		rdma->state = P9_RDMA_ADDR_RESOLVED;
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
 		break;
 
 	case RDMA_CM_EVENT_ROUTE_RESOLVED:
+		spin_lock_irqsave(&rdma->req_lock, flags);
 		BUG_ON(rdma->state != P9_RDMA_ADDR_RESOLVED);
 		rdma->state = P9_RDMA_ROUTE_RESOLVED;
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
 		break;
 
 	case RDMA_CM_EVENT_ESTABLISHED:
+		spin_lock_irqsave(&rdma->req_lock, flags);
 		BUG_ON(rdma->state != P9_RDMA_ROUTE_RESOLVED);
 		rdma->state = P9_RDMA_CONNECTED;
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
 		break;
 
 	case RDMA_CM_EVENT_DISCONNECTED:
-		if (rdma)
+		if (rdma) {
+			spin_lock_irqsave(&rdma->req_lock, flags);
 			rdma->state = P9_RDMA_CLOSED;
+			spin_unlock_irqrestore(&rdma->req_lock, flags);
+		}
 		c->status = Disconnected;
 		break;
 
@@ -184,6 +195,7 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct p9_req_t *req;
 	int err = 0;
 	int16_t tag;
+	unsigned long flags;
 
 	req = NULL;
 	ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize,
@@ -220,7 +232,10 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
  err_out:
 	p9_debug(P9_DEBUG_ERROR, "req %p err %d status %d\n",
 			req, err, wc->status);
-	rdma->state = P9_RDMA_FLUSHING;
+	spin_lock_irqsave(&rdma->req_lock, flags);
+	if (rdma->state < P9_RDMA_FLUSHING)
+		rdma->state = P9_RDMA_FLUSHING;
+	spin_unlock_irqrestore(&rdma->req_lock, flags);
 	client->status = Disconnected;
 	goto out;
 }
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 4cdab7094b27..b0d0094ec8e2 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -532,6 +532,11 @@ req_retry_pinned:
 	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
 	err = io_wait_event_killable(req->wq,
 				     READ_ONCE(req->status) >= REQ_STATUS_RCVD);
+	/*
+	 * Make sure our req is coherent with regard to updates in other
+	 * threads - echoes to wmb() in the callback
+	 */
+	smp_rmb();
 	// RERROR needs reply (== error string) in static data
 	if (READ_ONCE(req->status) == REQ_STATUS_RCVD &&
 	    unlikely(req->rc.sdata[4] == P9_RERROR))
diff --git a/net/atm/common.c b/net/atm/common.c
index fe77f51f6ce1..6eb78c34c284 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -720,6 +720,8 @@ static int atm_change_qos(struct atm_vcc *vcc, struct atm_qos *qos)
 static int check_tp(const struct atm_trafprm *tp)
 {
 	/* @@@ Should be merged with adjust_tp */
+	if (tp->traffic_class > ATM_ANYCLASS)
+		return -EINVAL;
 	if (!tp->traffic_class || tp->traffic_class == ATM_ANYCLASS)
 		return 0;
 	if (tp->traffic_class != ATM_UBR && !tp->min_pcr && !tp->pcr &&
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 86fb5de5022a..bcfbb39889a1 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -545,7 +545,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
 	 * the one with the lowest address
 	 */
 	if (tmp_max == max && max_orig_node &&
-	    batadv_compare_eth(candidate->orig, max_orig_node->orig))
+	    memcmp(candidate->orig, max_orig_node->orig, ETH_ALEN) >= 0)
 		goto out;
 
 	ret = true;
@@ -1065,6 +1065,9 @@ out:
  * @skb: the buffer containing the packet to extract the VID from
  * @hdr_size: the size of the batman-adv header encapsulating the packet
  *
+ * The caller must ensure that at least @hdr_size + ETH_HLEN bytes are
+ * accessible after skb->data.
+ *
  * Return: If the packet embedded in the skb is vlan tagged this function
  * returns the VID with the BATADV_VLAN_HAS_TAG flag. Otherwise BATADV_NO_FLAGS
  * is returned.
@@ -1147,6 +1150,10 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 	if (!atomic_read(&bat_priv->distributed_arp_table))
 		goto out;
 
+	/* first, find out the vid. */
+	if (!pskb_may_pull(skb, hdr_size + ETH_HLEN))
+		goto out;
+
 	vid = batadv_dat_get_vid(skb, &hdr_size);
 
 	type = batadv_arp_get_type(bat_priv, skb, hdr_size);
@@ -1242,6 +1249,10 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
 	if (!atomic_read(&bat_priv->distributed_arp_table))
 		goto out;
 
+	/* first, find out the vid. */
+	if (!pskb_may_pull(skb, hdr_size + ETH_HLEN))
+		goto out;
+
 	vid = batadv_dat_get_vid(skb, &hdr_size);
 
 	type = batadv_arp_get_type(bat_priv, skb, hdr_size);
@@ -1304,6 +1315,10 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
 	if (!atomic_read(&bat_priv->distributed_arp_table))
 		return;
 
+	/* first, find out the vid. */
+	if (!pskb_may_pull(skb, hdr_size + ETH_HLEN))
+		return;
+
 	vid = batadv_dat_get_vid(skb, &hdr_size);
 
 	type = batadv_arp_get_type(bat_priv, skb, hdr_size);
@@ -1352,6 +1367,10 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
 	if (!atomic_read(&bat_priv->distributed_arp_table))
 		goto out;
 
+	/* first, find out the vid. */
+	if (!pskb_may_pull(skb, hdr_size + ETH_HLEN))
+		goto out;
+
 	vid = batadv_dat_get_vid(skb, &hdr_size);
 
 	type = batadv_arp_get_type(bat_priv, skb, hdr_size);
@@ -1746,6 +1765,7 @@ void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv,
 	struct ethhdr *ethhdr;
 	__be32 ip_src, yiaddr;
 	unsigned short vid;
+	int hdr_size_tmp;
 	__be16 proto;
 	u8 *hw_src;
 
@@ -1762,8 +1782,10 @@ void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv,
 	if (!batadv_dat_check_dhcp_ack(skb, proto, &ip_src, chaddr, &yiaddr))
 		return;
 
+	hdr_size_tmp = hdr_size;
+	vid = batadv_dat_get_vid(skb, &hdr_size_tmp);
+	ethhdr = (struct ethhdr *)(skb->data + hdr_size);
 	hw_src = ethhdr->h_source;
-	vid = batadv_dat_get_vid(skb, &hdr_size);
 
 	batadv_dat_entry_add(bat_priv, yiaddr, chaddr, vid);
 	batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid);
@@ -1803,6 +1825,10 @@ bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv,
 	if (batadv_forw_packet_is_rebroadcast(forw_packet))
 		goto out;
 
+	/* first, find out the vid. */
+	if (!pskb_may_pull(forw_packet->skb, hdr_size + ETH_HLEN))
+		goto out;
+
 	vid = batadv_dat_get_vid(forw_packet->skb, &hdr_size);
 
 	type = batadv_arp_get_type(bat_priv, forw_packet->skb, hdr_size);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 9a5927ecc474..9a8db648f957 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -516,8 +516,10 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 	mtu = min_t(unsigned int, mtu, BATADV_FRAG_MAX_FRAG_SIZE);
 	max_fragment_size = mtu - header_size;
 
-	if (skb->len == 0 || max_fragment_size == 0)
-		return -EINVAL;
+	if (skb->len == 0 || max_fragment_size == 0) {
+		ret = -EINVAL;
+		goto free_skb;
+	}
 
 	num_fragments = (skb->len - 1) / max_fragment_size + 1;
 	max_fragment_size = (skb->len - 1) / num_fragments + 1;
@@ -543,7 +545,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 	 */
 	if (skb_has_frag_list(skb) && __skb_linearize(skb)) {
 		ret = -ENOMEM;
-		goto free_skb;
+		goto put_primary_if;
 	}
 
 	/* Create one header to be copied to all fragments */
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index a9d0346e8332..36137acb6eb2 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -683,12 +683,13 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 	struct batadv_gw_node *gw_node = NULL;
 	struct batadv_gw_node *curr_gw = NULL;
 	struct batadv_neigh_ifinfo *curr_ifinfo, *old_ifinfo;
-	struct ethhdr *ethhdr = (struct ethhdr *)skb->data;
+	struct ethhdr *ethhdr;
 	bool out_of_range = false;
 	u8 curr_tq_avg;
 	unsigned short vid;
 
 	vid = batadv_get_vid(skb, 0);
+	ethhdr = (struct ethhdr *)skb->data;
 
 	if (is_multicast_ether_addr(ethhdr->h_dest))
 		goto out;
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index a4d33ee0fda5..b9b0bef44803 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -245,6 +245,7 @@ err_orig:
 void batadv_mesh_free(struct net_device *mesh_iface)
 {
 	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
+	struct batadv_meshif_vlan *vlan;
 
 	atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
 
@@ -259,6 +260,13 @@ void batadv_mesh_free(struct net_device *mesh_iface)
 
 	batadv_mcast_free(bat_priv);
 
+	/* destroy the "untagged" VLAN */
+	vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS);
+	if (vlan) {
+		batadv_meshif_destroy_vlan(bat_priv, vlan);
+		batadv_meshif_vlan_put(vlan);
+	}
+
 	/* Free the TT and the originator tables only after having terminated
 	 * all the other depending components which may use these structures for
 	 * their purposes.
@@ -354,7 +362,7 @@ void batadv_skb_set_priority(struct sk_buff *skb, int offset)
 
 	switch (ethhdr->h_proto) {
 	case htons(ETH_P_8021Q):
-		vhdr = skb_header_pointer(skb, offset + sizeof(*vhdr),
+		vhdr = skb_header_pointer(skb, offset,
 					  sizeof(*vhdr), &vhdr_tmp);
 		if (!vhdr)
 			return;
@@ -566,6 +574,9 @@ void batadv_recv_handler_unregister(u8 packet_type)
  * @skb: the buffer containing the packet
  * @header_len: length of the batman header preceding the ethernet header
  *
+ * The caller must ensure that at least @header_len + ETH_HLEN bytes are
+ * accessible after skb->data.
+ *
  * Return: VID with the BATADV_VLAN_HAS_TAG flag when the packet embedded in the
  * skb is vlan tagged. Otherwise BATADV_NO_FLAGS.
  */
diff --git a/net/batman-adv/mesh-interface.c b/net/batman-adv/mesh-interface.c
index e7aa45bc6b7a..6f4c8da4fa5d 100644
--- a/net/batman-adv/mesh-interface.c
+++ b/net/batman-adv/mesh-interface.c
@@ -193,6 +193,9 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 	if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
 		goto dropped;
 
+	if (!pskb_may_pull(skb, ETH_HLEN))
+		goto dropped;
+
 	/* reset control block to avoid left overs from previous users */
 	memset(skb->cb, 0, sizeof(struct batadv_skb_cb));
 
@@ -432,6 +435,7 @@ void batadv_interface_rx(struct net_device *mesh_iface,
 		if (!pskb_may_pull(skb, VLAN_ETH_HLEN))
 			goto dropped;
 
+		ethhdr = eth_hdr(skb);
 		vhdr = skb_vlan_eth_hdr(skb);
 
 		/* drop batman-in-batman packets to prevent loops */
@@ -589,8 +593,8 @@ int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
  * @bat_priv: the bat priv with all the mesh interface information
  * @vlan: the object to remove
  */
-static void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv,
-				       struct batadv_meshif_vlan *vlan)
+void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv,
+				struct batadv_meshif_vlan *vlan)
 {
 	/* explicitly remove the associated TT local entry because it is marked
 	 * with the NOPURGE flag
@@ -1085,22 +1089,13 @@ static int batadv_meshif_newlink(struct net_device *dev,
 static void batadv_meshif_destroy_netlink(struct net_device *mesh_iface,
 					  struct list_head *head)
 {
-	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	struct batadv_hard_iface *hard_iface;
-	struct batadv_meshif_vlan *vlan;
 
 	while (!list_empty(&mesh_iface->adj_list.lower)) {
 		hard_iface = netdev_adjacent_get_private(mesh_iface->adj_list.lower.next);
 		batadv_hardif_disable_interface(hard_iface);
 	}
 
-	/* destroy the "untagged" VLAN */
-	vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS);
-	if (vlan) {
-		batadv_meshif_destroy_vlan(bat_priv, vlan);
-		batadv_meshif_vlan_put(vlan);
-	}
-
 	unregister_netdevice_queue(mesh_iface, head);
 }
 
diff --git a/net/batman-adv/mesh-interface.h b/net/batman-adv/mesh-interface.h
index 53756c5a45e0..5e1e83e04ffb 100644
--- a/net/batman-adv/mesh-interface.h
+++ b/net/batman-adv/mesh-interface.h
@@ -21,6 +21,8 @@ void batadv_interface_rx(struct net_device *mesh_iface,
 bool batadv_meshif_is_valid(const struct net_device *net_dev);
 extern struct rtnl_link_ops batadv_link_ops;
 int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid);
+void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv,
+				struct batadv_meshif_vlan *vlan);
 void batadv_meshif_vlan_release(struct kref *ref);
 struct batadv_meshif_vlan *batadv_meshif_vlan_get(struct batadv_priv *bat_priv,
 						  unsigned short vid);
diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c
index b8668a80b94a..1404a3b7adfb 100644
--- a/net/batman-adv/multicast_forw.c
+++ b/net/batman-adv/multicast_forw.c
@@ -927,11 +927,11 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv,
 {
 	struct batadv_tvlv_mcast_tracker *mcast_tracker;
 	struct batadv_neigh_node *neigh_node;
-	unsigned long offset, num_dests_off;
 	struct sk_buff *nexthop_skb;
 	unsigned char *skb_net_hdr;
 	bool local_recv = false;
 	unsigned int tvlv_len;
+	unsigned long offset;
 	bool xmitted = false;
 	u8 *dest, *next_dest;
 	u16 num_dests;
@@ -940,9 +940,8 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv,
 	/* (at least) TVLV part needs to be linearized */
 	SKB_LINEAR_ASSERT(skb);
 
-	/* check if num_dests is within skb length */
-	num_dests_off = offsetof(struct batadv_tvlv_mcast_tracker, num_dests);
-	if (num_dests_off > skb_network_header_len(skb))
+	/* check if batadv_tvlv_mcast_tracker header is within skb length */
+	if (sizeof(*mcast_tracker) > skb_network_header_len(skb))
 		return -EINVAL;
 
 	skb_net_hdr = skb_network_header(skb);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 41951c7a1c50..9de5bc552bfd 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -855,8 +855,8 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv,
 	if (skb_cow(skb, sizeof(*unicast_packet)) < 0)
 		return false;
 
-	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 	vid = batadv_get_vid(skb, hdr_len);
+	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 	ethhdr = (struct ethhdr *)(skb->data + hdr_len);
 
 	/* do not reroute multicast frames in a unicast header */
@@ -1029,6 +1029,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
 							  hdr_size);
 			batadv_orig_node_put(orig_node_gw);
 			if (is_gw) {
+				orig_addr_gw = eth_hdr(skb)->h_source;
 				batadv_dbg(BATADV_DBG_BLA, bat_priv,
 					   "%s(): Dropped unicast pkt received from another backbone gw %pM.\n",
 					   __func__, orig_addr_gw);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 83dfd804a143..877475c68825 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -2963,7 +2963,7 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv,
 out:
 	batadv_hardif_put(primary_if);
 
-	if (ret && tt_req_node) {
+	if (!ret && tt_req_node) {
 		spin_lock_bh(&bat_priv->tt.req_list_lock);
 		if (!hlist_unhashed(&tt_req_node->list)) {
 			hlist_del_init(&tt_req_node->list);
@@ -4025,7 +4025,8 @@ static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv,
 					     u16 tvlv_value_len)
 {
 	struct batadv_tvlv_tt_data *tt_data;
-	u16 tt_vlan_len, tt_num_entries;
+	u16 tt_num_entries;
+	size_t tt_vlan_len;
 	char tt_flag;
 	bool ret;
 
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 4dbbc44a950d..d504a363a30f 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -632,7 +632,7 @@ static struct l2cap_chan *chan_create(void)
 	if (!chan)
 		return NULL;
 
-	l2cap_chan_set_defaults(chan);
+	l2cap_chan_set_defaults(chan, NULL);
 
 	chan->chan_type = L2CAP_CHAN_CONN_ORIENTED;
 	chan->mode = L2CAP_MODE_LE_FLOWCTL;
@@ -745,19 +745,24 @@ static inline void chan_ready_cb(struct l2cap_chan *chan)
 	ifup(dev->netdev);
 }
 
-static inline struct l2cap_chan *chan_new_conn_cb(struct l2cap_chan *pchan)
+static void unregister_dev(struct lowpan_btle_dev *dev)
 {
-	struct l2cap_chan *chan;
-
-	chan = chan_create();
-	if (!chan)
-		return NULL;
-
-	chan->ops = pchan->ops;
-
-	BT_DBG("chan %p pchan %p", chan, pchan);
-
-	return chan;
+	struct hci_dev *hdev = READ_ONCE(dev->hdev);
+
+	/* If netdev holds last reference to hci_dev (its parent device), this
+	 * leads to theoretical cyclic locking on lowpan_unregister_netdev:
+	 *
+	 * rtnl_lock -> put_device(parent) -> hci_release_dev ->
+	 * destroy_workqueue -> hci_rx_work -> l2cap_recv_acldata ->
+	 * chan_ready_cb -> ifup -> rtnl_lock
+	 *
+	 * However, hci_rx_work is disabled in hci_unregister_dev, so this
+	 * should not occur. Make lockdep happy by postponing hdev release after
+	 * netdev put.
+	 */
+	hci_dev_hold(hdev);
+	lowpan_unregister_netdev(dev->netdev);
+	hci_dev_put(hdev);
 }
 
 static void delete_netdev(struct work_struct *work)
@@ -766,7 +771,7 @@ static void delete_netdev(struct work_struct *work)
 						     struct lowpan_btle_dev,
 						     delete_netdev);
 
-	lowpan_unregister_netdev(entry->netdev);
+	unregister_dev(entry);
 
 	/* The entry pointer is deleted by the netdev destructor. */
 }
@@ -869,7 +874,6 @@ static long chan_get_sndtimeo_cb(struct l2cap_chan *chan)
 
 static const struct l2cap_ops bt_6lowpan_chan_ops = {
 	.name			= "L2CAP 6LoWPAN channel",
-	.new_connection		= chan_new_conn_cb,
 	.recv			= chan_recv_cb,
 	.close			= chan_close_cb,
 	.state_change		= chan_state_change_cb,
@@ -997,16 +1001,19 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type,
 
 	hci_dev_lock(hdev);
 	hcon = hci_conn_hash_lookup_le(hdev, addr, le_addr_type);
-	hci_dev_unlock(hdev);
-	hci_dev_put(hdev);
-
-	if (!hcon)
+	if (!hcon) {
+		hci_dev_unlock(hdev);
+		hci_dev_put(hdev);
 		return -ENOENT;
+	}
 
-	*conn = (struct l2cap_conn *)hcon->l2cap_data;
+	*conn = l2cap_conn_hold_unless_zero(hcon->l2cap_data);
 
 	BT_DBG("conn %p dst %pMR type %u", *conn, &hcon->dst, hcon->dst_type);
 
+	hci_dev_unlock(hdev);
+	hci_dev_put(hdev);
+
 	return 0;
 }
 
@@ -1061,23 +1068,15 @@ done:
 	} while (nchans);
 }
 
-struct set_enable {
-	struct work_struct work;
-	bool flag;
-};
-
-static void do_enable_set(struct work_struct *work)
+static void do_enable_set(bool flag)
 {
-	struct set_enable *set_enable = container_of(work,
-						     struct set_enable, work);
-
-	if (!set_enable->flag || enable_6lowpan != set_enable->flag)
+	if (!flag || enable_6lowpan != flag)
 		/* Disconnect existing connections if 6lowpan is
 		 * disabled
 		 */
 		disconnect_all_peers();
 
-	enable_6lowpan = set_enable->flag;
+	enable_6lowpan = flag;
 
 	mutex_lock(&set_lock);
 	if (listen_chan) {
@@ -1089,22 +1088,11 @@ static void do_enable_set(struct work_struct *work)
 
 	listen_chan = bt_6lowpan_listen();
 	mutex_unlock(&set_lock);
-
-	kfree(set_enable);
 }
 
 static int lowpan_enable_set(void *data, u64 val)
 {
-	struct set_enable *set_enable;
-
-	set_enable = kzalloc_obj(*set_enable);
-	if (!set_enable)
-		return -ENOMEM;
-
-	set_enable->flag = !!val;
-	INIT_WORK(&set_enable->work, do_enable_set);
-
-	schedule_work(&set_enable->work);
+	do_enable_set(!!val);
 
 	return 0;
 }
@@ -1153,18 +1141,22 @@ static ssize_t lowpan_control_write(struct file *fp,
 		if (conn) {
 			struct lowpan_peer *peer;
 
-			if (!is_bt_6lowpan(conn->hcon))
+			if (!is_bt_6lowpan(conn->hcon)) {
+				l2cap_conn_put(conn);
 				return -EINVAL;
+			}
 
 			peer = lookup_peer(conn);
 			if (peer) {
 				BT_DBG("6LoWPAN connection already exists");
+				l2cap_conn_put(conn);
 				return -EALREADY;
 			}
 
 			BT_DBG("conn %p dst %pMR type %d user %u", conn,
 			       &conn->hcon->dst, conn->hcon->dst_type,
 			       addr_type);
+			l2cap_conn_put(conn);
 		}
 
 		ret = bt_6lowpan_connect(&addr, addr_type);
@@ -1180,6 +1172,8 @@ static ssize_t lowpan_control_write(struct file *fp,
 			return ret;
 
 		ret = bt_6lowpan_disconnect(conn, addr_type);
+		if (conn)
+			l2cap_conn_put(conn);
 		if (ret < 0)
 			return ret;
 
@@ -1240,6 +1234,7 @@ static void disconnect_devices(void)
 			break;
 
 		new_dev->netdev = entry->netdev;
+		new_dev->hdev = entry->hdev;
 		INIT_LIST_HEAD(&new_dev->list);
 
 		list_add_rcu(&new_dev->list, &devices);
@@ -1251,7 +1246,7 @@ static void disconnect_devices(void)
 		ifdown(entry->netdev);
 		BT_DBG("Unregistering netdev %s %p",
 		       entry->netdev->name, entry->netdev);
-		lowpan_unregister_netdev(entry->netdev);
+		unregister_dev(entry);
 		kfree(entry);
 	}
 }
diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c
index 3f72111ba651..1de5f9df6eec 100644
--- a/net/bluetooth/eir.c
+++ b/net/bluetooth/eir.c
@@ -283,10 +283,12 @@ u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr, u8 size)
 		if (!flags)
 			flags |= mgmt_get_adv_discov_flags(hdev);
 
-		/* If flags would still be empty, then there is no need to
-		 * include the "Flags" AD field".
+		/* Only add the "Flags" if it fits together with the instance
+		 * advertising data; drop it rather than overflow the buffer.
 		 */
-		if (flags && (ad_len + eir_precalc_len(1) <= size)) {
+		if (flags &&
+		    (ad_len + eir_precalc_len(1) +
+		     (adv ? adv->adv_data_len : 0) <= size)) {
 			ptr[0] = 0x02;
 			ptr[1] = EIR_FLAGS;
 			ptr[2] = flags;
diff --git a/net/bluetooth/hci_codec.c b/net/bluetooth/hci_codec.c
index 3cc135bb1d30..5bc5003c387c 100644
--- a/net/bluetooth/hci_codec.c
+++ b/net/bluetooth/hci_codec.c
@@ -100,7 +100,7 @@ static void hci_read_codec_capabilities(struct hci_dev *hdev, __u8 transport,
 				caps = (void *)skb->data;
 				if (skb->len < sizeof(*caps))
 					goto error;
-				if (skb->len < caps->len)
+				if (skb->len < sizeof(caps->len) + caps->len)
 					goto error;
 				len += sizeof(caps->len) + caps->len;
 				skb_pull(skb,  sizeof(caps->len) + caps->len);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 28d7929dc593..1cbc666527c5 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2671,6 +2671,8 @@ void hci_unregister_dev(struct hci_dev *hdev)
 	disable_work_sync(&hdev->tx_work);
 	disable_work_sync(&hdev->power_on);
 	disable_work_sync(&hdev->error_reset);
+	disable_delayed_work_sync(&hdev->cmd_timer);
+	disable_delayed_work_sync(&hdev->ncmd_timer);
 
 	hci_cmd_sync_clear(hdev);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index eea2f810aafa..1cd5f97daafe 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1769,6 +1769,13 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable)
 
 		hci_dev_clear_flag(hdev, HCI_LE_SCAN);
 
+		if (hdev->discovery.type == DISCOV_TYPE_INTERLEAVED &&
+		    hci_test_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY) &&
+		    !test_bit(HCI_INQUIRY, &hdev->flags) &&
+		    hdev->discovery.state == DISCOVERY_FINDING) {
+			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+		}
+
 		/* The HCI_LE_SCAN_INTERRUPTED flag indicates that we
 		 * interrupted scanning due to a connect request. Mark
 		 * therefore discovery as stopped.
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 7186e8d88c75..1d5ce87e6496 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -2539,7 +2539,7 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags)
 	switch (pb) {
 	case ISO_START:
 	case ISO_SINGLE:
-		if (conn->rx_len) {
+		if (conn->rx_skb || conn->rx_len) {
 			BT_ERR("Unexpected start frame (len %d)", skb->len);
 			kfree_skb(conn->rx_skb);
 			conn->rx_skb = NULL;
@@ -2620,12 +2620,14 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags)
 		break;
 
 	case ISO_CONT:
-		BT_DBG("Cont: frag len %d (expecting %d)", skb->len,
+	case ISO_END:
+		BT_DBG("%s: frag len %d (expecting %d)",
+		       (pb == ISO_END) ? "End" : "Cont", skb->len,
 		       conn->rx_len);
 
-		if (!conn->rx_len) {
-			BT_ERR("Unexpected continuation frame (len %d)",
-			       skb->len);
+		if (!conn->rx_skb) {
+			BT_ERR("Unexpected ISO %s frame (len %d)",
+			       (pb == ISO_END) ? "End" : "Cont", skb->len);
 			goto drop;
 		}
 
@@ -2641,17 +2643,9 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags)
 		skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len),
 					  skb->len);
 		conn->rx_len -= skb->len;
-		break;
 
-	case ISO_END:
-		if (!conn->rx_len) {
-			BT_ERR("Unexpected end frame (len %d)", skb->len);
-			goto drop;
-		}
-
-		skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len),
-					  skb->len);
-		conn->rx_len -= skb->len;
+		if (pb == ISO_CONT)
+			break;
 
 		if (!conn->rx_len) {
 			struct sk_buff *rx_skb = conn->rx_skb;
@@ -2662,6 +2656,13 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags)
 			 */
 			conn->rx_skb = NULL;
 			iso_recv_frame(conn, rx_skb);
+		} else {
+			BT_ERR("ISO fragment incomplete (len %d, expected %d)",
+			       skb->len, conn->rx_len);
+			kfree_skb(conn->rx_skb);
+			conn->rx_skb = NULL;
+			conn->rx_len = 0;
+			goto drop;
 		}
 		break;
 	}
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 32f0c8b73b17..189085000c73 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -525,7 +525,10 @@ void l2cap_chan_put(struct l2cap_chan *c)
 }
 EXPORT_SYMBOL_GPL(l2cap_chan_put);
 
-void l2cap_chan_set_defaults(struct l2cap_chan *chan)
+/* Initialise @chan with default values, inheriting from the parent channel
+ * @pchan when it is given.
+ */
+void l2cap_chan_set_defaults(struct l2cap_chan *chan, struct l2cap_chan *pchan)
 {
 	chan->fcs  = L2CAP_FCS_CRC16;
 	chan->max_tx = L2CAP_DEFAULT_MAX_TX;
@@ -539,6 +542,31 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan)
 	chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO;
 	chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO;
 
+	if (pchan) {
+		BT_DBG("chan %p pchan %p", chan, pchan);
+
+		chan->chan_type = pchan->chan_type;
+		chan->imtu = pchan->imtu;
+		chan->omtu = pchan->omtu;
+		chan->mode = pchan->mode;
+		chan->fcs = pchan->fcs;
+		chan->max_tx = pchan->max_tx;
+		chan->tx_win = pchan->tx_win;
+		chan->tx_win_max = pchan->tx_win_max;
+		chan->sec_level = pchan->sec_level;
+		chan->conf_state = pchan->conf_state;
+		chan->flags = pchan->flags;
+		chan->tx_credits = pchan->tx_credits;
+		chan->rx_credits = pchan->rx_credits;
+
+		if (chan->chan_type == L2CAP_CHAN_FIXED) {
+			chan->scid = pchan->scid;
+			chan->dcid = pchan->scid;
+		}
+
+		return;
+	}
+
 	chan->conf_state = 0;
 	set_bit(CONF_NOT_COMPLETE, &chan->conf_state);
 
@@ -4027,6 +4055,38 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn,
 	return 0;
 }
 
+/* Allocate and initialise a channel for an incoming connection.
+ *
+ * The channel inherits its configuration from @pchan and is linked into @conn
+ * before ->new_connection() runs, so the conn list reference keeps it alive if
+ * the callback exposes it (e.g. via the socket accept queue) before this
+ * returns. The l2cap_chan_create() reference is taken over by the subsystem on
+ * success and dropped here on failure.
+ */
+static struct l2cap_chan *l2cap_new_connection(struct l2cap_conn *conn,
+					       struct l2cap_chan *pchan)
+{
+	struct l2cap_chan *chan;
+
+	chan = l2cap_chan_create();
+	if (!chan)
+		return NULL;
+
+	l2cap_chan_set_defaults(chan, pchan);
+	chan->ops = pchan->ops;
+
+	__l2cap_chan_add(conn, chan);
+
+	if (pchan->ops->new_connection &&
+	    pchan->ops->new_connection(pchan, chan) < 0) {
+		l2cap_chan_del(chan, 0);
+		l2cap_chan_put(chan);
+		return NULL;
+	}
+
+	return chan;
+}
+
 static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
 			  u8 *data, u8 rsp_code)
 {
@@ -4073,7 +4133,7 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
 		goto response;
 	}
 
-	chan = pchan->ops->new_connection(pchan);
+	chan = l2cap_new_connection(conn, pchan);
 	if (!chan)
 		goto response;
 
@@ -4091,8 +4151,6 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
 	chan->psm  = psm;
 	chan->dcid = scid;
 
-	__l2cap_chan_add(conn, chan);
-
 	dcid = chan->scid;
 
 	__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
@@ -4824,6 +4882,7 @@ static void l2cap_put_ident(struct l2cap_conn *conn, u8 code, u8 id)
 	case L2CAP_ECHO_RSP:
 	case L2CAP_INFO_RSP:
 	case L2CAP_CONN_PARAM_UPDATE_RSP:
+	case L2CAP_LE_CONN_RSP:
 	case L2CAP_ECRED_CONN_RSP:
 	case L2CAP_ECRED_RECONF_RSP:
 		/* First do a lookup since the remote may send bogus ids that
@@ -4975,7 +5034,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
 		goto response_unlock;
 	}
 
-	chan = pchan->ops->new_connection(pchan);
+	chan = l2cap_new_connection(conn, pchan);
 	if (!chan) {
 		result = L2CAP_CR_LE_NO_MEM;
 		goto response_unlock;
@@ -4990,8 +5049,6 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
 	chan->omtu = mtu;
 	chan->remote_mps = mps;
 
-	__l2cap_chan_add(conn, chan);
-
 	l2cap_le_flowctl_init(chan, __le16_to_cpu(req->credits));
 
 	dcid = chan->scid;
@@ -5199,7 +5256,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 			continue;
 		}
 
-		chan = pchan->ops->new_connection(pchan);
+		chan = l2cap_new_connection(conn, pchan);
 		if (!chan) {
 			result = L2CAP_CR_LE_NO_MEM;
 			continue;
@@ -5214,8 +5271,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 		chan->omtu = mtu;
 		chan->remote_mps = mps;
 
-		__l2cap_chan_add(conn, chan);
-
 		l2cap_ecred_init(chan, __le16_to_cpu(req->credits));
 
 		/* Init response */
@@ -6721,6 +6776,7 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan)
 	struct l2cap_conn *conn = chan->conn;
 	struct l2cap_le_credits pkt;
 	u16 return_credits = l2cap_le_rx_credits(chan);
+	int ident;
 
 	if (chan->mode != L2CAP_MODE_LE_FLOWCTL &&
 	    chan->mode != L2CAP_MODE_EXT_FLOWCTL)
@@ -6738,9 +6794,18 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan)
 	pkt.cid     = cpu_to_le16(chan->scid);
 	pkt.credits = cpu_to_le16(return_credits);
 
-	chan->ident = l2cap_get_ident(conn);
+	ident = l2cap_get_ident(conn);
+
+	l2cap_send_cmd(conn, ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt);
 
-	l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt);
+	/* L2CAP_LE_CREDITS has no response so the ident is never released by
+	 * l2cap_put_ident() - release it right away, otherwise the tx_ida
+	 * range is exhausted after 254 packets and from then on credits are
+	 * sent with the invalid ident 0, which some remote stacks ignore,
+	 * stalling the channel.
+	 */
+	if (ident > 0)
+		ida_free(&conn->tx_ida, ident);
 }
 
 void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail)
@@ -7490,14 +7555,12 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 			goto next;
 
 		l2cap_chan_lock(pchan);
-		chan = pchan->ops->new_connection(pchan);
+		chan = l2cap_new_connection(conn, pchan);
 		if (chan) {
 			bacpy(&chan->src, &hcon->src);
 			bacpy(&chan->dst, &hcon->dst);
 			chan->src_type = bdaddr_src_type(hcon);
 			chan->dst_type = dst_type;
-
-			__l2cap_chan_add(conn, chan);
 		}
 
 		l2cap_chan_unlock(pchan);
@@ -7714,6 +7777,7 @@ struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *c)
 
 	return c;
 }
+EXPORT_SYMBOL(l2cap_conn_hold_unless_zero);
 
 int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle,
 		       struct sk_buff *skb, u16 flags)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1e93de155987..d8cbe2784437 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -45,7 +45,8 @@ static struct bt_sock_list l2cap_sk_list = {
 static const struct proto_ops l2cap_sock_ops;
 static void l2cap_sock_init(struct sock *sk, struct sock *parent);
 static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
-				     int proto, gfp_t prio, int kern);
+				     int proto, gfp_t prio, int kern,
+				     struct l2cap_chan *chan);
 static void l2cap_sock_cleanup_listen(struct sock *parent);
 
 bool l2cap_is_socket(struct socket *sock)
@@ -1274,6 +1275,23 @@ done:
 	return err;
 }
 
+/* Release the sock's ref on chan and clear the pointer so that the ref is
+ * dropped exactly once even if both l2cap_sock_kill() and
+ * l2cap_sock_destruct() run. Setting chan->data to NULL first stops any other
+ * task from dereferencing the now-dead sock pointer.
+ */
+static void l2cap_sock_put_chan(struct sock *sk)
+{
+	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
+
+	if (!chan)
+		return;
+
+	chan->data = NULL;
+	l2cap_pi(sk)->chan = NULL;
+	l2cap_chan_put(chan);
+}
+
 /* Kill socket (only if zapped and orphan)
  * Must be called on unlocked socket, with l2cap channel lock.
  */
@@ -1284,13 +1302,9 @@ static void l2cap_sock_kill(struct sock *sk)
 
 	BT_DBG("sk %p state %s", sk, state_to_string(sk->sk_state));
 
-	/* Sock is dead, so set chan data to NULL, avoid other task use invalid
-	 * sock pointer.
-	 */
-	l2cap_pi(sk)->chan->data = NULL;
-	/* Kill poor orphan */
+	l2cap_sock_put_chan(sk);
 
-	l2cap_chan_put(l2cap_pi(sk)->chan);
+	/* Kill poor orphan */
 	sock_set_flag(sk, SOCK_DEAD);
 	sock_put(sk);
 }
@@ -1533,12 +1547,13 @@ static void l2cap_sock_cleanup_listen(struct sock *parent)
 	}
 }
 
-static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
+static int l2cap_sock_new_connection_cb(struct l2cap_chan *chan,
+					struct l2cap_chan *new_chan)
 {
 	struct sock *sk, *parent = chan->data;
 
 	if (!parent)
-		return NULL;
+		return -EINVAL;
 
 	lock_sock(parent);
 
@@ -1546,25 +1561,28 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
 	if (sk_acceptq_is_full(parent)) {
 		BT_DBG("backlog full %d", parent->sk_ack_backlog);
 		release_sock(parent);
-		return NULL;
+		return -ENOBUFS;
 	}
 
 	sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
-			      GFP_ATOMIC, 0);
+			      GFP_ATOMIC, 0, new_chan);
 	if (!sk) {
 		release_sock(parent);
-		return NULL;
-        }
+		return -ENOMEM;
+	}
 
 	bt_sock_reclassify_lock(sk, BTPROTO_L2CAP);
 
 	l2cap_sock_init(sk, parent);
 
+	/* The conn list reference taken by l2cap_new_connection() keeps new_chan
+	 * alive once release_sock() lets another task free this socket.
+	 */
 	bt_accept_enqueue(parent, sk, false);
 
 	release_sock(parent);
 
-	return l2cap_pi(sk)->chan;
+	return 0;
 }
 
 static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
@@ -1861,10 +1879,7 @@ static void l2cap_sock_destruct(struct sock *sk)
 
 	BT_DBG("sk %p", sk);
 
-	if (l2cap_pi(sk)->chan) {
-		l2cap_pi(sk)->chan->data = NULL;
-		l2cap_chan_put(l2cap_pi(sk)->chan);
-	}
+	l2cap_sock_put_chan(sk);
 
 	list_for_each_entry_safe(rx_busy, next, &l2cap_pi(sk)->rx_busy, list) {
 		kfree_skb(rx_busy->skb);
@@ -1897,30 +1912,12 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 	BT_DBG("sk %p", sk);
 
 	if (parent) {
-		struct l2cap_chan *pchan = l2cap_pi(parent)->chan;
-
 		sk->sk_type = parent->sk_type;
 		bt_sk(sk)->flags = bt_sk(parent)->flags;
 
-		chan->chan_type = pchan->chan_type;
-		chan->imtu = pchan->imtu;
-		chan->omtu = pchan->omtu;
-		chan->conf_state = pchan->conf_state;
-		chan->mode = pchan->mode;
-		chan->fcs  = pchan->fcs;
-		chan->max_tx = pchan->max_tx;
-		chan->tx_win = pchan->tx_win;
-		chan->tx_win_max = pchan->tx_win_max;
-		chan->sec_level = pchan->sec_level;
-		chan->flags = pchan->flags;
-		chan->tx_credits = pchan->tx_credits;
-		chan->rx_credits = pchan->rx_credits;
-
-		if (chan->chan_type == L2CAP_CHAN_FIXED) {
-			chan->scid = pchan->scid;
-			chan->dcid = pchan->scid;
-		}
-
+		/* Channel configuration is inherited from the parent by
+		 * l2cap_new_connection().
+		 */
 		security_sk_clone(parent, sk);
 	} else {
 		switch (sk->sk_type) {
@@ -1946,7 +1943,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 			chan->mode = L2CAP_MODE_BASIC;
 		}
 
-		l2cap_chan_set_defaults(chan);
+		l2cap_chan_set_defaults(chan, NULL);
 	}
 
 	/* Default config options */
@@ -1965,10 +1962,10 @@ static struct proto l2cap_proto = {
 };
 
 static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
-				     int proto, gfp_t prio, int kern)
+				     int proto, gfp_t prio, int kern,
+				     struct l2cap_chan *chan)
 {
 	struct sock *sk;
-	struct l2cap_chan *chan;
 
 	sk = bt_sock_alloc(net, sock, &l2cap_proto, proto, prio, kern);
 	if (!sk)
@@ -1979,16 +1976,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 
 	INIT_LIST_HEAD(&l2cap_pi(sk)->rx_busy);
 
-	chan = l2cap_chan_create();
-	if (!chan) {
-		sk_free(sk);
-		if (sock)
-			sock->sk = NULL;
-		return NULL;
-	}
-
-	l2cap_chan_hold(chan);
-
+	/* The sock takes ownership of the caller's reference on chan. */
 	l2cap_pi(sk)->chan = chan;
 
 	return sk;
@@ -1998,6 +1986,7 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol,
 			     int kern)
 {
 	struct sock *sk;
+	struct l2cap_chan *chan;
 
 	BT_DBG("sock %p", sock);
 
@@ -2012,10 +2001,16 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol,
 
 	sock->ops = &l2cap_sock_ops;
 
-	sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern);
-	if (!sk)
+	chan = l2cap_chan_create();
+	if (!chan)
 		return -ENOMEM;
 
+	sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern, chan);
+	if (!sk) {
+		l2cap_chan_put(chan);
+		return -ENOMEM;
+	}
+
 	l2cap_sock_init(sk, NULL);
 	bt_sock_link(&l2cap_sk_list, sk);
 	return 0;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7c164a17ef59..e8544194a524 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5378,6 +5378,8 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev,
 		if (monitor->state == ADV_MONITOR_STATE_NOT_REGISTERED)
 			monitor->state = ADV_MONITOR_STATE_REGISTERED;
 		hci_update_passive_scan(hdev);
+	} else {
+		hci_free_adv_monitor(hdev, monitor);
 	}
 
 	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c
index 2f008167cbaa..d7badce8746c 100644
--- a/net/bluetooth/msft.c
+++ b/net/bluetooth/msft.c
@@ -291,7 +291,7 @@ static int msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode,
 	monitor->state = ADV_MONITOR_STATE_OFFLOADED;
 
 unlock:
-	if (status)
+	if (status && msft->resuming)
 		hci_free_adv_monitor(hdev, monitor);
 
 	hci_dev_unlock(hdev);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 140869e5b2df..b2c51f3ebc40 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -572,10 +572,23 @@ static void __sco_sock_close(struct sock *sk)
 /* Must be called on unlocked socket. */
 static void sco_sock_close(struct sock *sk)
 {
+	struct sco_conn *conn;
+
+	lock_sock(sk);
+	conn = sco_pi(sk)->conn;
+	if (conn)
+		sco_conn_hold(conn);
+	release_sock(sk);
+
+	if (conn)
+		disable_delayed_work_sync(&conn->timeout_work);
+
 	lock_sock(sk);
-	sco_sock_clear_timer(sk);
 	__sco_sock_close(sk);
 	release_sock(sk);
+
+	if (conn)
+		sco_conn_put(conn);
 }
 
 static void sco_sock_init(struct sock *sk, struct sock *parent)
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 98f1da4f5f55..4787f8cd29e4 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -3234,34 +3234,19 @@ static const struct l2cap_ops smp_chan_ops = {
 	.get_sndtimeo		= l2cap_chan_no_get_sndtimeo,
 };
 
-static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan)
+static inline int smp_new_conn_cb(struct l2cap_chan *chan,
+				  struct l2cap_chan *new_chan)
 {
-	struct l2cap_chan *chan;
-
-	BT_DBG("pchan %p", pchan);
-
-	chan = l2cap_chan_create();
-	if (!chan)
-		return NULL;
-
-	chan->chan_type	= pchan->chan_type;
-	chan->ops	= &smp_chan_ops;
-	chan->scid	= pchan->scid;
-	chan->dcid	= chan->scid;
-	chan->imtu	= pchan->imtu;
-	chan->omtu	= pchan->omtu;
-	chan->mode	= pchan->mode;
+	new_chan->ops = &smp_chan_ops;
 
 	/* Other L2CAP channels may request SMP routines in order to
 	 * change the security level. This means that the SMP channel
 	 * lock must be considered in its own category to avoid lockdep
 	 * warnings.
 	 */
-	atomic_set(&chan->nesting, L2CAP_NESTING_SMP);
-
-	BT_DBG("created chan %p", chan);
+	atomic_set(&new_chan->nesting, L2CAP_NESTING_SMP);
 
-	return chan;
+	return 0;
 }
 
 static const struct l2cap_ops smp_root_chan_ops = {
@@ -3332,7 +3317,7 @@ create_chan:
 
 	l2cap_add_scid(chan, cid);
 
-	l2cap_chan_set_defaults(chan);
+	l2cap_chan_set_defaults(chan, NULL);
 
 	if (cid == L2CAP_CID_SMP) {
 		u8 bdaddr_type;
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 2bc04feadfab..f15c613aaa4e 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -453,12 +453,8 @@ static int bpf_test_finish(const union bpf_attr *kattr,
 	}
 
 	if (data_out) {
-		int len = sinfo ? copy_size - frag_size : copy_size;
-
-		if (len < 0) {
-			err = -ENOSPC;
-			goto out;
-		}
+		u32 head_len = size - frag_size;
+		u32 len = min(copy_size, head_len);
 
 		if (copy_to_user(data_out, data, len))
 			goto out;
diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c
index 118c7ea48c35..dea56fffa1c1 100644
--- a/net/bridge/br_cfm.c
+++ b/net/bridge/br_cfm.c
@@ -805,6 +805,12 @@ int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
 		goto save;
 	}
 
+	if (!interval_to_us(mep->cc_config.exp_interval)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid CCM interval");
+		return -EINVAL;
+	}
+
 	/* Start delayed work to transmit CCM frames. It is done with zero delay
 	 * to send first frame immediately
 	 */
diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c
index 2faab44652e7..91b9922dc3f2 100644
--- a/net/bridge/br_cfm_netlink.c
+++ b/net/bridge/br_cfm_netlink.c
@@ -34,7 +34,9 @@ br_cfm_cc_config_policy[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1] = {
 	[IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC]	 = { .type = NLA_REJECT },
 	[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]	 = { .type = NLA_U32 },
 	[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]	 = { .type = NLA_U32 },
-	[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL] = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL] =
+		NLA_POLICY_RANGE(NLA_U32, BR_CFM_CCM_INTERVAL_3_3_MS,
+				 BR_CFM_CCM_INTERVAL_10_MIN),
 	[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID]	 = {
 	.type = NLA_BINARY, .len = CFM_MAID_LENGTH },
 };
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index d39571e13744..ec773e4ab92e 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -391,6 +391,9 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
 
 	br_fdb_delete_by_port(br, NULL, 0, 1);
 
+	timer_shutdown_sync(&br->hello_timer);
+	timer_shutdown_sync(&br->topology_change_timer);
+	timer_shutdown_sync(&br->tcn_timer);
 	cancel_delayed_work_sync(&br->gc_work);
 
 	br_sysfs_delbr(br->dev);
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 024210f95468..76a2df165ffc 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -371,7 +371,8 @@ void br_topology_change_detection(struct net_bridge *br)
 {
 	int isroot = br_is_root_bridge(br);
 
-	if (br->stp_enabled != BR_KERNEL_STP)
+	if (br->stp_enabled != BR_KERNEL_STP ||
+	    !(br->dev->flags & IFF_UP))
 		return;
 
 	br_info(br, "topology change detected, %s\n",
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index 219c40680260..e4c9aa1f64e2 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -44,7 +44,9 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
 		if (!br_dev || !br_vlan_enabled(br_dev))
 			goto err;
 
-		br_vlan_get_pvid_rcu(in, &p_pvid);
+		if (br_vlan_get_pvid_rcu(in, &p_pvid))
+			goto err;
+
 		nft_reg_store16(dest, p_pvid);
 		return;
 	}
@@ -107,12 +109,30 @@ static int nft_meta_bridge_get_init(const struct nft_ctx *ctx,
 					NULL, NFT_DATA_VALUE, len);
 }
 
+static int nft_meta_bridge_get_validate(const struct nft_ctx *ctx,
+					const struct nft_expr *expr)
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	unsigned int hooks;
+
+	switch (priv->key) {
+	case NFT_META_BRI_IIFHWADDR:
+		hooks = 1 << NF_BR_PRE_ROUTING;
+		break;
+	default:
+		return nft_meta_get_validate(ctx, expr);
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
+}
+
 static struct nft_expr_type nft_meta_bridge_type;
 static const struct nft_expr_ops nft_meta_bridge_get_ops = {
 	.type		= &nft_meta_bridge_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
 	.eval		= nft_meta_bridge_get_eval,
 	.init		= nft_meta_bridge_get_init,
+	.validate	= nft_meta_bridge_get_validate,
 	.dump		= nft_meta_get_dump,
 };
 
@@ -168,7 +188,6 @@ static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx,
 
 	switch (priv->key) {
 	case NFT_META_BRI_BROUTE:
-	case NFT_META_BRI_IIFHWADDR:
 		hooks = 1 << NF_BR_PRE_ROUTING;
 		break;
 	default:
diff --git a/net/can/bcm.c b/net/can/bcm.c
index a4bef2c48a55..3d637a1e0ac1 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -58,6 +58,7 @@
 #include <linux/can/skb.h>
 #include <linux/can/bcm.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 #include <linux/spinlock.h>
 #include <net/can.h>
 #include <net/sock.h>
@@ -92,6 +93,8 @@ MODULE_ALIAS("can-proto-2");
 
 #define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
 
+static struct workqueue_struct *bcm_wq;
+
 /*
  * easy access to the first 64 bit of can(fd)_frame payload. cp->data is
  * 64 bit aligned so the offset has to be multiples of 8 which is ensured
@@ -105,14 +108,16 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset)
 struct bcm_op {
 	struct list_head list;
 	struct rcu_head rcu;
+	struct work_struct work;
 	int ifindex;
 	canid_t can_id;
 	u32 flags;
-	unsigned long frames_abs, frames_filtered;
+	atomic_long_t frames_abs, frames_filtered;
 	struct bcm_timeval ival1, ival2;
 	struct hrtimer timer, thrtimer;
 	ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
 	int rx_ifindex;
+	int if_detected; /* first received ifindex in ANYDEV rx_op mode */
 	int cfsiz;
 	u32 count;
 	u32 nframes;
@@ -124,7 +129,9 @@ struct bcm_op {
 	struct canfd_frame last_sframe;
 	struct sock *sk;
 	struct net_device *rx_reg_dev;
-	spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */
+	netdevice_tracker rx_reg_dev_tracker;
+	spinlock_t bcm_tx_lock; /* protect tx data and timer updates */
+	spinlock_t bcm_rx_update_lock; /* protect filter/timer data updates */
 };
 
 struct bcm_sock {
@@ -224,10 +231,13 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 
 	list_for_each_entry_rcu(op, &bo->rx_ops, list) {
 
-		unsigned long reduction;
+		long reduction, frames_filtered, frames_abs;
+
+		frames_filtered = atomic_long_read(&op->frames_filtered);
+		frames_abs = atomic_long_read(&op->frames_abs);
 
 		/* print only active entries & prevent division by zero */
-		if (!op->frames_abs)
+		if (!frames_abs)
 			continue;
 
 		seq_printf(m, "rx_op: %03X %-5s ", op->can_id,
@@ -249,15 +259,15 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 				   (long long)ktime_to_us(op->kt_ival2));
 
 		seq_printf(m, "# recv %ld (%ld) => reduction: ",
-			   op->frames_filtered, op->frames_abs);
+			   frames_filtered, frames_abs);
 
-		reduction = 100 - (op->frames_filtered * 100) / op->frames_abs;
+		reduction = 100 - (frames_filtered * 100) / frames_abs;
 
 		seq_printf(m, "%s%ld%%\n",
 			   (reduction == 100) ? "near " : "", reduction);
 	}
 
-	list_for_each_entry(op, &bo->tx_ops, list) {
+	list_for_each_entry_rcu(op, &bo->tx_ops, list) {
 
 		seq_printf(m, "tx_op: %03X %s ", op->can_id,
 			   bcm_proc_getifname(net, ifname, op->ifindex));
@@ -275,7 +285,8 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 			seq_printf(m, "t2=%lld ",
 				   (long long)ktime_to_us(op->kt_ival2));
 
-		seq_printf(m, "# sent %ld\n", op->frames_abs);
+		seq_printf(m, "# sent %ld\n",
+			   atomic_long_read(&op->frames_abs));
 	}
 	seq_putc(m, '\n');
 
@@ -285,26 +296,50 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 }
 #endif /* CONFIG_PROC_FS */
 
+static void bcm_update_rx_stats(struct bcm_op *op)
+{
+	/* prevent overflow of the reduction% calculation in bcm_proc_show() */
+	if (atomic_long_inc_return(&op->frames_abs) > LONG_MAX / 100) {
+		atomic_long_set(&op->frames_filtered, 0);
+		atomic_long_set(&op->frames_abs, 0);
+	}
+}
+
+static void bcm_update_tx_stats(struct bcm_op *op)
+{
+	/* tx_op has no reduction% calculation - use the full range and
+	 * just keep the displayed counter non-negative on overflow
+	 */
+	if (atomic_long_inc_return(&op->frames_abs) == LONG_MAX)
+		atomic_long_set(&op->frames_abs, 0);
+}
+
 /*
  * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface
  *              of the given bcm tx op
  */
-static void bcm_can_tx(struct bcm_op *op)
+static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf)
 {
 	struct sk_buff *skb;
 	struct can_skb_ext *csx;
 	struct net_device *dev;
-	struct canfd_frame *cf;
+	struct canfd_frame cframe;
+	bool cyclic = !cf;
+	unsigned int idx = 0;
 	int err;
 
 	/* no target device? => exit */
 	if (!op->ifindex)
 		return;
 
-	/* read currframe under lock protection */
-	spin_lock_bh(&op->bcm_tx_lock);
-	cf = op->frames + op->cfsiz * op->currframe;
-	spin_unlock_bh(&op->bcm_tx_lock);
+	if (cyclic) {
+		/* read currframe under lock protection */
+		spin_lock_bh(&op->bcm_tx_lock);
+		idx = op->currframe;
+		memcpy(&cframe, op->frames + op->cfsiz * idx, op->cfsiz);
+		cf = &cframe;
+		spin_unlock_bh(&op->bcm_tx_lock);
+	}
 
 	dev = dev_get_by_index(sock_net(op->sk), op->ifindex);
 	if (!dev) {
@@ -335,16 +370,22 @@ static void bcm_can_tx(struct bcm_op *op)
 	spin_lock_bh(&op->bcm_tx_lock);
 
 	if (!err)
-		op->frames_abs++;
+		bcm_update_tx_stats(op);
 
-	op->currframe++;
+	/* only advance the cyclic sequence if nothing reset currframe while
+	 * we were sending - a concurrent TX_RESET_MULTI_IDX means this
+	 * frame's bookkeeping belongs to a sequence that no longer exists
+	 */
+	if (!cyclic || op->currframe == idx) {
+		op->currframe++;
 
-	/* reached last frame? */
-	if (op->currframe >= op->nframes)
-		op->currframe = 0;
+		/* reached last frame? */
+		if (op->currframe >= op->nframes)
+			op->currframe = 0;
 
-	if (op->count > 0)
-		op->count--;
+		if (op->count > 0)
+			op->count--;
+	}
 
 	spin_unlock_bh(&op->bcm_tx_lock);
 out:
@@ -433,12 +474,18 @@ static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt)
 {
 	ktime_t ival;
 
+	spin_lock_bh(&op->bcm_tx_lock);
+
 	if (op->kt_ival1 && op->count)
 		ival = op->kt_ival1;
-	else if (op->kt_ival2)
+	else if (op->kt_ival2) {
 		ival = op->kt_ival2;
-	else
+	} else {
+		spin_unlock_bh(&op->bcm_tx_lock);
 		return false;
+	}
+
+	spin_unlock_bh(&op->bcm_tx_lock);
 
 	hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival));
 	return true;
@@ -455,26 +502,48 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 {
 	struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
 	struct bcm_msg_head msg_head;
+	bool tx_ival1, tx_ival2;
+
+	/* snapshot kt_ival1/kt_ival2/count under lock to avoid torn
+	 * ktime_t reads racing with concurrent bcm_tx_setup() updates
+	 */
+	spin_lock_bh(&op->bcm_tx_lock);
+	tx_ival1 = op->kt_ival1 && (op->count > 0);
+	tx_ival2 = !!op->kt_ival2;
+	spin_unlock_bh(&op->bcm_tx_lock);
 
-	if (op->kt_ival1 && (op->count > 0)) {
-		bcm_can_tx(op);
-		if (!op->count && (op->flags & TX_COUNTEVT)) {
+	if (tx_ival1) {
+		u32 flags, count;
+		struct bcm_timeval ival1, ival2;
 
+		bcm_can_tx(op, NULL);
+
+		/* snapshot variables under lock to avoid torn reads racing
+		 * with concurrent bcm_tx_setup() updates
+		 */
+		spin_lock_bh(&op->bcm_tx_lock);
+		flags = op->flags;
+		count = op->count;
+		ival1 = op->ival1;
+		ival2 = op->ival2;
+		spin_unlock_bh(&op->bcm_tx_lock);
+
+		if (!count && (flags & TX_COUNTEVT)) {
 			/* create notification to user */
 			memset(&msg_head, 0, sizeof(msg_head));
 			msg_head.opcode  = TX_EXPIRED;
-			msg_head.flags   = op->flags;
-			msg_head.count   = op->count;
-			msg_head.ival1   = op->ival1;
-			msg_head.ival2   = op->ival2;
+			msg_head.flags   = flags;
+			msg_head.count   = count;
+			msg_head.ival1   = ival1;
+			msg_head.ival2   = ival2;
 			msg_head.can_id  = op->can_id;
 			msg_head.nframes = 0;
 
 			bcm_send_to_user(op, &msg_head, NULL, 0);
 		}
 
-	} else if (op->kt_ival2) {
-		bcm_can_tx(op);
+	} else if (tx_ival2) {
+		bcm_can_tx(op, NULL);
 	}
 
 	return bcm_tx_set_expiry(op, &op->timer) ?
@@ -488,12 +557,9 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data)
 {
 	struct bcm_msg_head head;
 
-	/* update statistics */
-	op->frames_filtered++;
-
-	/* prevent statistics overflow */
-	if (op->frames_filtered > ULONG_MAX/100)
-		op->frames_filtered = op->frames_abs = 0;
+	/* update statistics (frames_filtered <= frames_abs) */
+	if (atomic_long_read(&op->frames_abs))
+		atomic_long_inc(&op->frames_filtered);
 
 	/* this element is not throttled anymore */
 	data->flags &= ~RX_THR;
@@ -618,6 +684,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 	struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
 	struct bcm_msg_head msg_head;
 
+	spin_lock_bh(&op->bcm_rx_update_lock);
+
 	/* if user wants to be informed, when cyclic CAN-Messages come back */
 	if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) {
 		/* clear received CAN frames to indicate 'nothing received' */
@@ -634,6 +702,8 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 	msg_head.can_id  = op->can_id;
 	msg_head.nframes = 0;
 
+	spin_unlock_bh(&op->bcm_rx_update_lock);
+
 	bcm_send_to_user(op, &msg_head, NULL, 0);
 
 	return HRTIMER_NORESTART;
@@ -682,15 +752,26 @@ static int bcm_rx_thr_flush(struct bcm_op *op)
 static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer)
 {
 	struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer);
+	enum hrtimer_restart ret;
+
+	spin_lock_bh(&op->bcm_rx_update_lock);
 
-	if (bcm_rx_thr_flush(op)) {
+	/* kt_ival2 may have been concurrently cleared by bcm_rx_setup()
+	 * before it cancels this timer - never forward with a zero
+	 * interval in that case.
+	 */
+	if (bcm_rx_thr_flush(op) && op->kt_ival2) {
 		hrtimer_forward_now(hrtimer, op->kt_ival2);
-		return HRTIMER_RESTART;
+		ret = HRTIMER_RESTART;
 	} else {
 		/* rearm throttle handling */
 		op->kt_lastmsg = 0;
-		return HRTIMER_NORESTART;
+		ret = HRTIMER_NORESTART;
 	}
+
+	spin_unlock_bh(&op->bcm_rx_update_lock);
+
+	return ret;
 }
 
 /*
@@ -700,8 +781,10 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 {
 	struct bcm_op *op = (struct bcm_op *)data;
 	const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data;
+	struct canfd_frame rtrframe;
 	unsigned int i;
 	unsigned char traffic_flags;
+	bool rtr_frame;
 
 	if (op->can_id != rxframe->can_id)
 		return;
@@ -715,22 +798,59 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 			return;
 	}
 
+	/* An ANYDEV op with an active RX timeout and/or throttle timer
+	 * tracks a single source interface: claim the first interface that
+	 * delivers a matching frame and reject frames from any other one,
+	 * before hrtimer_cancel() below can touch op->timer - this avoids
+	 * racing bcm_rx_timeout_handler() across concurrent interfaces.
+	 * RX_RTR_FRAME ops are excluded, as kt_ival1/kt_ival2 may briefly
+	 * hold a stale value from an earlier non-RTR configuration.
+	 */
+	if (!op->ifindex) {
+		spin_lock_bh(&op->bcm_rx_update_lock);
+
+		if (!(op->flags & RX_RTR_FRAME) &&
+		    (op->kt_ival1 || op->kt_ival2)) {
+			/* don't claim to vanishing interface */
+			if (!op->if_detected &&
+			    READ_ONCE(skb->dev->reg_state) == NETREG_REGISTERED)
+				op->if_detected = skb->dev->ifindex;
+
+			if (op->if_detected != skb->dev->ifindex) {
+				spin_unlock_bh(&op->bcm_rx_update_lock);
+				return;
+			}
+		}
+
+		spin_unlock_bh(&op->bcm_rx_update_lock);
+	}
+
 	/* disable timeout */
 	hrtimer_cancel(&op->timer);
 
-	/* save rx timestamp */
-	op->rx_stamp = skb->tstamp;
-	/* save originator for recvfrom() */
-	op->rx_ifindex = skb->dev->ifindex;
-	/* update statistics */
-	op->frames_abs++;
+	/* op->flags/op->frames may be updated concurrently by bcm_rx_setup() */
+	spin_lock_bh(&op->bcm_rx_update_lock);
+
+	rtr_frame = op->flags & RX_RTR_FRAME;
+	if (rtr_frame) {
+		bcm_update_rx_stats(op);
+		/* snapshot RTR content under lock */
+		memcpy(&rtrframe, op->frames, op->cfsiz);
+		spin_unlock_bh(&op->bcm_rx_update_lock);
 
-	if (op->flags & RX_RTR_FRAME) {
 		/* send reply for RTR-request (placed in op->frames[0]) */
-		bcm_can_tx(op);
+		bcm_can_tx(op, &rtrframe);
 		return;
 	}
 
+	/* update statistics in the same critical section as bcm_rx_changed()
+	 * below: frames_filtered must never be checked/incremented against a
+	 * frames_abs snapshot from a concurrent bcm_rx_handler() call on
+	 * another CPU for the same (wildcard) op, or frames_filtered can end
+	 * up larger than frames_abs.
+	 */
+	bcm_update_rx_stats(op);
+
 	/* compute flags to distinguish between own/local/remote CAN traffic */
 	traffic_flags = 0;
 	if (skb->sk) {
@@ -739,6 +859,13 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 			traffic_flags |= RX_OWN;
 	}
 
+	/* save rx timestamp and originator for recvfrom() under lock: an
+	 * ANYDEV op without an active timer can still run concurrently on
+	 * different CPUs, so content and meta data must be bundled here.
+	 */
+	op->rx_stamp = skb->tstamp;
+	op->rx_ifindex = skb->dev->ifindex;
+
 	if (op->flags & RX_FILTER_ID) {
 		/* the easiest case */
 		bcm_rx_update_and_send(op, op->last_frames, rxframe,
@@ -774,6 +901,8 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 
 rx_starttimer:
 	bcm_rx_starttimer(op);
+
+	spin_unlock_bh(&op->bcm_rx_update_lock);
 }
 
 /*
@@ -793,9 +922,12 @@ static struct bcm_op *bcm_find_op(struct list_head *ops,
 	return NULL;
 }
 
-static void bcm_free_op_rcu(struct rcu_head *rcu_head)
+static void bcm_free_op_work(struct work_struct *work)
 {
-	struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu);
+	struct bcm_op *op = container_of(work, struct bcm_op, work);
+
+	hrtimer_cancel(&op->timer);
+	hrtimer_cancel(&op->thrtimer);
 
 	if ((op->frames) && (op->frames != &op->sframe))
 		kfree(op->frames);
@@ -803,9 +935,23 @@ static void bcm_free_op_rcu(struct rcu_head *rcu_head)
 	if ((op->last_frames) && (op->last_frames != &op->last_sframe))
 		kfree(op->last_frames);
 
+	/* the last possible access to op->timer/op->thrtimer has now
+	 * happened above via hrtimer_cancel() - op->sk is no longer
+	 * needed by any pending timer callback, so drop our reference
+	 */
+	sock_put(op->sk);
+
 	kfree(op);
 }
 
+static void bcm_free_op_rcu(struct rcu_head *rcu_head)
+{
+	struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu);
+
+	INIT_WORK(&op->work, bcm_free_op_work);
+	queue_work(bcm_wq, &op->work);
+}
+
 static void bcm_remove_op(struct bcm_op *op)
 {
 	hrtimer_cancel(&op->timer);
@@ -822,6 +968,7 @@ static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
 
 		/* mark as removed subscription */
 		op->rx_reg_dev = NULL;
+		netdev_put(dev, &op->rx_reg_dev_tracker);
 	} else
 		printk(KERN_ERR "can-bcm: bcm_rx_unreg: registered device "
 		       "mismatch %p %p\n", op->rx_reg_dev, dev);
@@ -852,17 +999,14 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 				 * Only remove subscriptions that had not
 				 * been removed due to NETDEV_UNREGISTER
 				 * in bcm_notifier()
+				 *
+				 * op->rx_reg_dev is a tracked reference taken
+				 * when the subscription was registered, so it
+				 * stays valid here even if a concurrent
+				 * NETDEV_UNREGISTER already unlisted the dev.
 				 */
-				if (op->rx_reg_dev) {
-					struct net_device *dev;
-
-					dev = dev_get_by_index(sock_net(op->sk),
-							       op->ifindex);
-					if (dev) {
-						bcm_rx_unreg(dev, op);
-						dev_put(dev);
-					}
-				}
+				if (op->rx_reg_dev)
+					bcm_rx_unreg(op->rx_reg_dev, op);
 			} else
 				can_rx_unregister(sock_net(op->sk), NULL,
 						  op->can_id,
@@ -930,6 +1074,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	struct bcm_sock *bo = bcm_sk(sk);
 	struct bcm_op *op;
 	struct canfd_frame *cf;
+	bool add_op_to_list = false;
 	unsigned int i;
 	int err;
 
@@ -948,6 +1093,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	/* check the given can_id */
 	op = bcm_find_op(&bo->tx_ops, msg_head, ifindex);
 	if (op) {
+		void *new_frames;
+
 		/* update existing BCM operation */
 
 		/*
@@ -958,11 +1105,23 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (msg_head->nframes > op->nframes)
 			return -E2BIG;
 
-		/* update CAN frames content */
+		/* get new CAN frames content into a staging buffer before
+		 * locking: validate and normalize the frames there so that
+		 * bcm_can_tx() / bcm_tx_timeout_handler() never observe a
+		 * partially updated or unvalidated frame in op->frames
+		 */
+		new_frames = kmalloc(msg_head->nframes * op->cfsiz, GFP_KERNEL);
+		if (!new_frames)
+			return -ENOMEM;
+
 		for (i = 0; i < msg_head->nframes; i++) {
 
-			cf = op->frames + op->cfsiz * i;
+			cf = new_frames + op->cfsiz * i;
 			err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+			if (err < 0) {
+				kfree(new_frames);
+				return err;
+			}
 
 			if (op->flags & CAN_FD_FRAME) {
 				if (cf->len > 64)
@@ -972,36 +1131,38 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 					err = -EINVAL;
 			}
 
-			if (err < 0)
+			if (err < 0) {
+				kfree(new_frames);
 				return err;
+			}
 
 			if (msg_head->flags & TX_CP_CAN_ID) {
 				/* copy can_id into frame */
 				cf->can_id = msg_head->can_id;
 			}
 		}
+
+		spin_lock_bh(&op->bcm_tx_lock);
+
+		/* update CAN frames content */
+		memcpy(op->frames, new_frames, msg_head->nframes * op->cfsiz);
+
 		op->flags = msg_head->flags;
 
-		/* only lock for unlikely count/nframes/currframe changes */
 		if (op->nframes != msg_head->nframes ||
-		    op->flags & TX_RESET_MULTI_IDX ||
-		    op->flags & SETTIMER) {
-
-			spin_lock_bh(&op->bcm_tx_lock);
+		    op->flags & TX_RESET_MULTI_IDX) {
+			/* potentially update changed nframes */
+			op->nframes = msg_head->nframes;
+			/* restart multiple frame transmission */
+			op->currframe = 0;
+		}
 
-			if (op->nframes != msg_head->nframes ||
-			    op->flags & TX_RESET_MULTI_IDX) {
-				/* potentially update changed nframes */
-				op->nframes = msg_head->nframes;
-				/* restart multiple frame transmission */
-				op->currframe = 0;
-			}
+		if (op->flags & SETTIMER)
+			op->count = msg_head->count;
 
-			if (op->flags & SETTIMER)
-				op->count = msg_head->count;
+		spin_unlock_bh(&op->bcm_tx_lock);
 
-			spin_unlock_bh(&op->bcm_tx_lock);
-		}
+		kfree(new_frames);
 
 	} else {
 		/* insert new BCM operation for the given can_id */
@@ -1060,6 +1221,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
 		op->sk = sk;
+		sock_hold(sk);
 		op->ifindex = ifindex;
 
 		/* initialize uninitialized (kzalloc) structure */
@@ -1070,17 +1232,18 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		hrtimer_setup(&op->thrtimer, hrtimer_dummy_timeout, CLOCK_MONOTONIC,
 			      HRTIMER_MODE_REL_SOFT);
 
-		/* add this bcm_op to the list of the tx_ops */
-		list_add(&op->list, &bo->tx_ops);
+		add_op_to_list = true;
 
 	} /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */
 
 	if (op->flags & SETTIMER) {
 		/* set timer values */
+		spin_lock_bh(&op->bcm_tx_lock);
 		op->ival1 = msg_head->ival1;
 		op->ival2 = msg_head->ival2;
 		op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
 		op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+		spin_unlock_bh(&op->bcm_tx_lock);
 
 		/* disable an active timer due to zero values? */
 		if (!op->kt_ival1 && !op->kt_ival2)
@@ -1093,8 +1256,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		op->flags |= TX_ANNOUNCE;
 	}
 
+	/* add this bcm_op to the list of the tx_ops? */
+	if (add_op_to_list)
+		list_add_rcu(&op->list, &bo->tx_ops);
+
 	if (op->flags & TX_ANNOUNCE)
-		bcm_can_tx(op);
+		bcm_can_tx(op, NULL);
 
 	if (op->flags & STARTTIMER)
 		bcm_tx_start_timer(op);
@@ -1108,6 +1275,39 @@ free_op:
 	return err;
 }
 
+static int bcm_rx_setup_rtr_check(struct bcm_msg_head *msg_head,
+				  struct bcm_op *op, void *new_frames)
+{
+	struct canfd_frame *frame0 = new_frames;
+
+	if (!(msg_head->flags & RX_RTR_FRAME))
+		return 0;
+
+	/* this frame is sent out as-is by bcm_can_tx() whenever a matching
+	 * remote request is received, so validate its length the same way
+	 * bcm_tx_setup() validates TX_SETUP frames before installing it
+	 */
+	if (msg_head->flags & CAN_FD_FRAME) {
+		if (frame0->len > 64)
+			return -EINVAL;
+	} else {
+		if (frame0->len > 8)
+			return -EINVAL;
+	}
+
+	/* funny feature in RX(!)_SETUP only for RTR-mode:
+	 * copy can_id into frame BUT without RTR-flag to
+	 * prevent a full-load-loopback-test ... ;-]
+	 * normalize this on the staged buffer, before it is
+	 * ever installed into op->frames.
+	 */
+	if ((msg_head->flags & TX_CP_CAN_ID) ||
+	    frame0->can_id == op->can_id)
+		frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
+
+	return 0;
+}
+
 /*
  * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg)
  */
@@ -1117,6 +1317,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	struct bcm_sock *bo = bcm_sk(sk);
 	struct bcm_op *op;
 	int do_rx_register;
+	int new_op = 0;
 	int err = 0;
 
 	if ((msg_head->flags & RX_FILTER_ID) || (!(msg_head->nframes))) {
@@ -1142,6 +1343,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	/* check the given can_id */
 	op = bcm_find_op(&bo->rx_ops, msg_head, ifindex);
 	if (op) {
+		void *new_frames = NULL;
+
 		/* update existing BCM operation */
 
 		/*
@@ -1153,21 +1356,62 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			return -E2BIG;
 
 		if (msg_head->nframes) {
-			/* update CAN frames content */
-			err = memcpy_from_msg(op->frames, msg,
+			/* get new CAN frames content before locking */
+			new_frames = kmalloc(msg_head->nframes * op->cfsiz,
+					     GFP_KERNEL);
+			if (!new_frames)
+				return -ENOMEM;
+
+			err = memcpy_from_msg(new_frames, msg,
 					      msg_head->nframes * op->cfsiz);
-			if (err < 0)
+			if (err < 0) {
+				kfree(new_frames);
 				return err;
+			}
 
-			/* clear last_frames to indicate 'nothing received' */
-			memset(op->last_frames, 0, msg_head->nframes * op->cfsiz);
+			err = bcm_rx_setup_rtr_check(msg_head, op, new_frames);
+			if (err < 0) {
+				kfree(new_frames);
+				return err;
+			}
 		}
 
+		spin_lock_bh(&op->bcm_rx_update_lock);
 		op->nframes = msg_head->nframes;
 		op->flags = msg_head->flags;
 
-		/* Only an update -> do not call can_rx_register() */
-		do_rx_register = 0;
+		if (msg_head->nframes) {
+			/* update CAN frames content */
+			memcpy(op->frames, new_frames,
+			       msg_head->nframes * op->cfsiz);
+
+			/* clear last_frames to indicate 'nothing received' */
+			memset(op->last_frames, 0,
+			       msg_head->nframes * op->cfsiz);
+		}
+
+		if (msg_head->flags & SETTIMER) {
+			op->ival1 = msg_head->ival1;
+			op->ival2 = msg_head->ival2;
+			op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
+			op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+			op->kt_lastmsg = 0;
+			op->if_detected = 0; /* reclaim ifindex in ANYDEV mode */
+		}
+		spin_unlock_bh(&op->bcm_rx_update_lock);
+
+		/* free temporary frames / kfree(NULL) is safe */
+		kfree(new_frames);
+
+		/* Don't register a new CAN filter for the rx_op update unless
+		 * a concurrent NETDEV_UNREGISTER notifier already tore down
+		 * the previous registration. In this case the receiver needs
+		 * to be re-registered here so that this update doesn't
+		 * silently stop delivering frames for the given ifindex.
+		 * Ops with ifindex = 0 (all CAN interfaces) never carry a
+		 * tracked rx_reg_dev and stay registered as-is.
+		 */
+		do_rx_register = (ifindex && !op->rx_reg_dev) ? 1 : 0;
 
 	} else {
 		/* insert new BCM operation for the given can_id */
@@ -1176,6 +1420,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			return -ENOMEM;
 
 		spin_lock_init(&op->bcm_tx_lock);
+		spin_lock_init(&op->bcm_rx_update_lock);
 		op->can_id = msg_head->can_id;
 		op->nframes = msg_head->nframes;
 		op->cfsiz = CFSIZ(msg_head->flags);
@@ -1209,18 +1454,17 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (msg_head->nframes) {
 			err = memcpy_from_msg(op->frames, msg,
 					      msg_head->nframes * op->cfsiz);
-			if (err < 0) {
-				if (op->frames != &op->sframe)
-					kfree(op->frames);
-				if (op->last_frames != &op->last_sframe)
-					kfree(op->last_frames);
-				kfree(op);
-				return err;
-			}
+			if (err < 0)
+				goto free_op;
+
+			err = bcm_rx_setup_rtr_check(msg_head, op, op->frames);
+			if (err < 0)
+				goto free_op;
 		}
 
 		/* bcm_can_tx / bcm_tx_timeout_handler needs this */
 		op->sk = sk;
+		sock_hold(sk);
 		op->ifindex = ifindex;
 
 		/* ifindex for timeout events w/o previous frame reception */
@@ -1232,40 +1476,31 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		hrtimer_setup(&op->thrtimer, bcm_rx_thr_handler, CLOCK_MONOTONIC,
 			      HRTIMER_MODE_REL_SOFT);
 
-		/* add this bcm_op to the list of the rx_ops */
-		list_add(&op->list, &bo->rx_ops);
-
 		/* call can_rx_register() */
 		do_rx_register = 1;
+		new_op = 1;
 
 	} /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */
 
 	/* check flags */
 
 	if (op->flags & RX_RTR_FRAME) {
-		struct canfd_frame *frame0 = op->frames;
-
 		/* no timers in RTR-mode */
 		hrtimer_cancel(&op->thrtimer);
 		hrtimer_cancel(&op->timer);
-
-		/*
-		 * funny feature in RX(!)_SETUP only for RTR-mode:
-		 * copy can_id into frame BUT without RTR-flag to
-		 * prevent a full-load-loopback-test ... ;-]
-		 */
-		if ((op->flags & TX_CP_CAN_ID) ||
-		    (frame0->can_id == op->can_id))
-			frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
-
 	} else {
 		if (op->flags & SETTIMER) {
 
-			/* set timer value */
-			op->ival1 = msg_head->ival1;
-			op->ival2 = msg_head->ival2;
-			op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
-			op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+			/* set timers (locked) for newly created op */
+			if (new_op) {
+				spin_lock_bh(&op->bcm_rx_update_lock);
+				op->ival1 = msg_head->ival1;
+				op->ival2 = msg_head->ival2;
+				op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
+				op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
+				op->kt_lastmsg = 0;
+				spin_unlock_bh(&op->bcm_rx_update_lock);
+			}
 
 			/* disable an active timer due to zero value? */
 			if (!op->kt_ival1)
@@ -1275,9 +1510,11 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			 * In any case cancel the throttle timer, flush
 			 * potentially blocked msgs and reset throttle handling
 			 */
-			op->kt_lastmsg = 0;
 			hrtimer_cancel(&op->thrtimer);
+
+			spin_lock_bh(&op->bcm_rx_update_lock);
 			bcm_rx_thr_flush(op);
+			spin_unlock_bh(&op->bcm_rx_update_lock);
 		}
 
 		if ((op->flags & STARTTIMER) && op->kt_ival1)
@@ -1285,7 +1522,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				      HRTIMER_MODE_REL_SOFT);
 	}
 
-	/* now we can register for can_ids, if we added a new bcm_op */
+	/* now we can register for can_ids, if we added a new bcm_op
+	 * or need to re-register after a NETDEV_UNREGISTER tore down
+	 * the previous registration of an existing op
+	 */
 	if (do_rx_register) {
 		if (ifindex) {
 			struct net_device *dev;
@@ -1298,23 +1538,62 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 						      bcm_rx_handler, op,
 						      "bcm", sk);
 
-				op->rx_reg_dev = dev;
+				/* keep a tracked reference so that a later
+				 * unregister can safely reach the device even
+				 * if a concurrent NETDEV_UNREGISTER has
+				 * already unlisted it by ifindex
+				 */
+				if (!err) {
+					op->rx_reg_dev = dev;
+					netdev_hold(dev,
+						    &op->rx_reg_dev_tracker,
+						    GFP_KERNEL);
+				}
 				dev_put(dev);
+			} else {
+				/* the requested device is gone - do not
+				 * silently succeed without registering
+				 */
+				err = -ENODEV;
 			}
 
-		} else
+		} else {
 			err = can_rx_register(sock_net(sk), NULL, op->can_id,
 					      REGMASK(op->can_id),
 					      bcm_rx_handler, op, "bcm", sk);
+		}
+
 		if (err) {
-			/* this bcm rx op is broken -> remove it */
-			list_del_rcu(&op->list);
-			bcm_remove_op(op);
+			/* newly created bcm rx op is broken -> remove it */
+			if (new_op) {
+				bcm_remove_op(op);
+				return err;
+			}
+
+			/* an existing op just stays unregistered.
+			 * Cancel op->timer and (defensively) op->thrtimer.
+			 * Other settings can't be reached until the next
+			 * successful RX_SETUP.
+			 */
+			hrtimer_cancel(&op->timer);
+			hrtimer_cancel(&op->thrtimer);
 			return err;
 		}
+
+		/* add a new bcm_op to the list of the rx_ops */
+		if (new_op)
+			list_add_rcu(&op->list, &bo->rx_ops);
 	}
 
 	return msg_head->nframes * op->cfsiz + MHSIZ;
+
+free_op:
+	if (op->frames != &op->sframe)
+		kfree(op->frames);
+	if (op->last_frames != &op->last_sframe)
+		kfree(op->last_frames);
+	kfree(op);
+	return err;
 }
 
 /*
@@ -1373,12 +1652,13 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 {
 	struct sock *sk = sock->sk;
 	struct bcm_sock *bo = bcm_sk(sk);
-	int ifindex = bo->ifindex; /* default ifindex for this bcm_op */
+	int ifindex;
 	struct bcm_msg_head msg_head;
 	int cfsiz;
 	int ret; /* read bytes or error codes as return value */
 
-	if (!bo->bound)
+	/* Lockless fast-path check for bound socket */
+	if (!READ_ONCE(bo->bound))
 		return -ENOTCONN;
 
 	/* check for valid message length from userspace */
@@ -1394,17 +1674,38 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if ((size - MHSIZ) % cfsiz)
 		return -EINVAL;
 
+	lock_sock(sk);
+
+	/* Re-validate under the socket lock: a concurrent bcm_notify()
+	 * may have unbound this socket (device removal) after the
+	 * lockless fast-path check above. bo->ifindex is only ever
+	 * mutated under lock_sock(), so reading it here - instead of
+	 * before taking the lock - guarantees it can't be observed
+	 * torn against bo->bound.
+	 */
+	if (!bo->bound) {
+		ret = -ENOTCONN;
+		goto out_release;
+	}
+
+	/* default ifindex for this bcm_op */
+	ifindex = bo->ifindex;
+
 	/* check for alternative ifindex for this bcm_op */
 
 	if (!ifindex && msg->msg_name) {
 		/* no bound device as default => check msg_name */
 		DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
 
-		if (msg->msg_namelen < BCM_MIN_NAMELEN)
-			return -EINVAL;
+		if (msg->msg_namelen < BCM_MIN_NAMELEN) {
+			ret = -EINVAL;
+			goto out_release;
+		}
 
-		if (addr->can_family != AF_CAN)
-			return -EINVAL;
+		if (addr->can_family != AF_CAN) {
+			ret = -EINVAL;
+			goto out_release;
+		}
 
 		/* ifindex from sendto() */
 		ifindex = addr->can_ifindex;
@@ -1413,20 +1714,21 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			struct net_device *dev;
 
 			dev = dev_get_by_index(sock_net(sk), ifindex);
-			if (!dev)
-				return -ENODEV;
+			if (!dev) {
+				ret = -ENODEV;
+				goto out_release;
+			}
 
 			if (dev->type != ARPHRD_CAN) {
 				dev_put(dev);
-				return -ENODEV;
+				ret = -ENODEV;
+				goto out_release;
 			}
 
 			dev_put(dev);
 		}
 	}
 
-	lock_sock(sk);
-
 	switch (msg_head.opcode) {
 
 	case TX_SETUP:
@@ -1476,6 +1778,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		break;
 	}
 
+out_release:
 	release_sock(sk);
 
 	return ret;
@@ -1499,11 +1802,30 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
 	case NETDEV_UNREGISTER:
 		lock_sock(sk);
 
-		/* remove device specific receive entries */
-		list_for_each_entry(op, &bo->rx_ops, list)
+		/* rx_ops: remove device specific receive entries */
+		list_for_each_entry(op, &bo->rx_ops, list) {
 			if (op->rx_reg_dev == dev)
 				bcm_rx_unreg(dev, op);
 
+			/* release an ANYDEV op's claim (see bcm_rx_handler())
+			 * on this now confirmed-gone interface.
+			 */
+			if (!op->ifindex) {
+				spin_lock_bh(&op->bcm_rx_update_lock);
+				if (op->if_detected == dev->ifindex)
+					op->if_detected = 0;
+				spin_unlock_bh(&op->bcm_rx_update_lock);
+			}
+		}
+
+		/* tx_ops: stop device specific cyclic transmissions on the
+		 * vanishing ifindex. Cancelling the timer is enough to stop
+		 * cyclic bcm_can_tx() calls as there is no re-arming.
+		 */
+		list_for_each_entry(op, &bo->tx_ops, list)
+			if (op->ifindex == dev->ifindex)
+				hrtimer_cancel(&op->timer);
+
 		/* remove device reference, if this is our bound device */
 		if (bo->bound && bo->ifindex == dev->ifindex) {
 #if IS_ENABLED(CONFIG_PROC_FS)
@@ -1512,7 +1834,12 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
 				bo->bcm_proc_read = NULL;
 			}
 #endif
-			bo->bound   = 0;
+			/* Paired with the lockless fast-path check in
+			 * bcm_sendmsg(); bo->ifindex itself is only ever
+			 * accessed under lock_sock() so it needs no
+			 * annotation.
+			 */
+			WRITE_ONCE(bo->bound, 0);
 			bo->ifindex = 0;
 			notify_enodev = 1;
 		}
@@ -1616,8 +1943,10 @@ static int bcm_release(struct socket *sock)
 		remove_proc_entry(bo->procname, net->can.bcmproc_dir);
 #endif /* CONFIG_PROC_FS */
 
-	list_for_each_entry_safe(op, next, &bo->tx_ops, list)
+	list_for_each_entry_safe(op, next, &bo->tx_ops, list) {
+		list_del_rcu(&op->list);
 		bcm_remove_op(op);
+	}
 
 	list_for_each_entry_safe(op, next, &bo->rx_ops, list) {
 		/*
@@ -1629,16 +1958,14 @@ static int bcm_release(struct socket *sock)
 			 * Only remove subscriptions that had not
 			 * been removed due to NETDEV_UNREGISTER
 			 * in bcm_notifier()
+			 *
+			 * op->rx_reg_dev is a tracked reference taken
+			 * when the subscription was registered, so it
+			 * stays valid here even if a concurrent
+			 * NETDEV_UNREGISTER already unlisted the device.
 			 */
-			if (op->rx_reg_dev) {
-				struct net_device *dev;
-
-				dev = dev_get_by_index(net, op->ifindex);
-				if (dev) {
-					bcm_rx_unreg(dev, op);
-					dev_put(dev);
-				}
-			}
+			if (op->rx_reg_dev)
+				bcm_rx_unreg(op->rx_reg_dev, op);
 		} else
 			can_rx_unregister(net, NULL, op->can_id,
 					  REGMASK(op->can_id),
@@ -1648,12 +1975,14 @@ static int bcm_release(struct socket *sock)
 
 	synchronize_rcu();
 
-	list_for_each_entry_safe(op, next, &bo->rx_ops, list)
+	list_for_each_entry_safe(op, next, &bo->rx_ops, list) {
+		list_del_rcu(&op->list);
 		bcm_remove_op(op);
+	}
 
 	/* remove device reference */
 	if (bo->bound) {
-		bo->bound   = 0;
+		WRITE_ONCE(bo->bound, 0);
 		bo->ifindex = 0;
 	}
 
@@ -1723,7 +2052,10 @@ static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int
 	}
 #endif /* CONFIG_PROC_FS */
 
-	bo->bound = 1;
+	/* bo->ifindex above is fully assigned before this point; pairs
+	 * with the lockless fast-path check in bcm_sendmsg()
+	 */
+	WRITE_ONCE(bo->bound, 1);
 
 fail:
 	release_sock(sk);
@@ -1839,11 +2171,15 @@ static int __init bcm_module_init(void)
 {
 	int err;
 
+	bcm_wq = alloc_workqueue("can-bcm-wq", WQ_UNBOUND, 0);
+	if (!bcm_wq)
+		return -ENOMEM;
+
 	pr_info("can: broadcast manager protocol\n");
 
 	err = register_pernet_subsys(&canbcm_pernet_ops);
 	if (err)
-		return err;
+		goto register_pernet_failed;
 
 	err = register_netdevice_notifier(&canbcm_notifier);
 	if (err)
@@ -1861,6 +2197,8 @@ register_proto_failed:
 	unregister_netdevice_notifier(&canbcm_notifier);
 register_notifier_failed:
 	unregister_pernet_subsys(&canbcm_pernet_ops);
+register_pernet_failed:
+	destroy_workqueue(bcm_wq);
 	return err;
 }
 
@@ -1869,6 +2207,8 @@ static void __exit bcm_module_exit(void)
 	can_proto_unregister(&bcm_can_proto);
 	unregister_netdevice_notifier(&canbcm_notifier);
 	unregister_pernet_subsys(&canbcm_pernet_ops);
+	rcu_barrier();
+	destroy_workqueue(bcm_wq);
 }
 
 module_init(bcm_module_init);
diff --git a/net/can/isotp.c b/net/can/isotp.c
index c48b4a818297..54becaf6898f 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -152,11 +152,13 @@ struct isotp_sock {
 	struct sock sk;
 	int bound;
 	int ifindex;
+	struct net_device *dev;
+	netdevice_tracker dev_tracker;
 	canid_t txid;
 	canid_t rxid;
 	ktime_t tx_gap;
 	ktime_t lastrxcf_tstamp;
-	struct hrtimer rxtimer, txtimer, txfrtimer;
+	struct hrtimer rxtimer, txtimer, txfrtimer, echotimer;
 	struct can_isotp_options opt;
 	struct can_isotp_fc_options rxfc, txfc;
 	struct can_isotp_ll_options ll;
@@ -164,6 +166,7 @@ struct isotp_sock {
 	u32 force_tx_stmin;
 	u32 force_rx_stmin;
 	u32 cfecho; /* consecutive frame echo tag */
+	u32 tx_gen; /* generation, bumped per new tx transfer */
 	struct tpcon rx, tx;
 	struct list_head notifier;
 	wait_queue_head_t wait;
@@ -376,6 +379,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)
 
 	hrtimer_cancel(&so->txtimer);
 
+	/* isotp_tx_timeout() may have given up on this job while
+	 * hrtimer_cancel() above waited for it to finish; so->rx_lock
+	 * (held by our caller isotp_rcv()) rules out a concurrent claim,
+	 * so a plain recheck is enough here.
+	 */
+	if (so->tx.state != ISOTP_WAIT_FC &&
+	    so->tx.state != ISOTP_WAIT_FIRST_FC)
+		return 1;
+
 	if ((cf->len < ae + FC_CONTENT_SZ) ||
 	    ((so->opt.flags & ISOTP_CHECK_PADDING) &&
 	     check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) {
@@ -422,7 +434,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)
 		so->tx.bs = 0;
 		so->tx.state = ISOTP_SENDING;
 		/* send CF frame and enable echo timeout handling */
-		hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
+		hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
 			      HRTIMER_MODE_REL_SOFT);
 		isotp_send_cframe(so);
 		break;
@@ -575,6 +587,14 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,
 
 	hrtimer_cancel(&so->rxtimer);
 
+	/* isotp_rx_timer_handler() may have raced us for so->rx.state
+	 * while hrtimer_cancel() above waited for it to finish, already
+	 * reporting ETIMEDOUT and resetting the reception; don't process
+	 * this CF into a reassembly that has already been given up on.
+	 */
+	if (so->rx.state != ISOTP_WAIT_DATA)
+		return 1;
+
 	/* CFs are never longer than the FF */
 	if (cf->len > so->rx.ll_dl)
 		return 1;
@@ -870,20 +890,36 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
 
 	/* only handle my own local echo CF/SF skb's (no FF!) */
-	if (skb->sk != sk || so->cfecho != *(u32 *)cf->data)
+	if (skb->sk != sk)
 		return;
 
+	/* unlike isotp_rcv_fc()/isotp_rcv_cf(), not already under so->rx_lock
+	 * (no isotp_rcv() caller here), so take it ourselves
+	 */
+	spin_lock(&so->rx_lock);
+
+	/* so->cfecho may since belong to a new transfer; recheck under lock */
+	if (so->cfecho != *(u32 *)cf->data)
+		goto out_unlock;
+
 	/* cancel local echo timeout */
-	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->echotimer);
 
 	/* local echo skb with consecutive frame has been consumed */
 	so->cfecho = 0;
 
+	/* claiming a transfer also takes so->rx_lock, so a plain recheck
+	 * is enough: so->tx.state can't have flipped to ISOTP_SENDING for
+	 * a new claim while we're still in here
+	 */
+	if (so->tx.state != ISOTP_SENDING)
+		goto out_unlock;
+
 	if (so->tx.idx >= so->tx.len) {
 		/* we are done */
 		so->tx.state = ISOTP_IDLE;
 		wake_up_interruptible(&so->wait);
-		return;
+		goto out_unlock;
 	}
 
 	if (so->txfc.bs && so->tx.bs >= so->txfc.bs) {
@@ -891,53 +927,83 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data)
 		so->tx.state = ISOTP_WAIT_FC;
 		hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0),
 			      HRTIMER_MODE_REL_SOFT);
-		return;
+		goto out_unlock;
 	}
 
 	/* no gap between data frames needed => use burst mode */
 	if (!so->tx_gap) {
 		/* enable echo timeout handling */
-		hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
+		hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
 			      HRTIMER_MODE_REL_SOFT);
 		isotp_send_cframe(so);
-		return;
+		goto out_unlock;
 	}
 
 	/* start timer to send next consecutive frame with correct delay */
 	hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT);
+
+out_unlock:
+	spin_unlock(&so->rx_lock);
 }
 
-static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
+/* shared by so->txtimer's and so->echotimer's callbacks. Both timers get
+ * cancelled under so->rx_lock elsewhere, so this must stay lock-free to
+ * avoid deadlocking with that; uses so->tx_gen instead to avoid tainting
+ * a new transfer with an error from the one that just timed out.
+ */
+static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so)
 {
-	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
-					     txtimer);
 	struct sock *sk = &so->sk;
+	u32 gen = READ_ONCE(so->tx_gen);
+	u32 old_state = READ_ONCE(so->tx.state);
 
 	/* don't handle timeouts in IDLE or SHUTDOWN state */
-	if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN)
+	if (old_state == ISOTP_IDLE || old_state == ISOTP_SHUTDOWN)
+		return HRTIMER_NORESTART;
+
+	/* only claim the timeout if the state is still unchanged */
+	if (cmpxchg(&so->tx.state, old_state, ISOTP_IDLE) != old_state)
 		return HRTIMER_NORESTART;
 
 	/* we did not get any flow control or echo frame in time */
 
-	/* report 'communication error on send' */
-	sk->sk_err = ECOMM;
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk_error_report(sk);
+	if (READ_ONCE(so->tx_gen) == gen) {
+		/* report 'communication error on send' */
+		sk->sk_err = ECOMM;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk_error_report(sk);
+	}
 
-	/* reset tx state */
-	so->tx.state = ISOTP_IDLE;
 	wake_up_interruptible(&so->wait);
 
 	return HRTIMER_NORESTART;
 }
 
+/* so->txtimer: fires when a Flow Control frame does not arrive in time */
+static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     txtimer);
+
+	return isotp_tx_timeout(so);
+}
+
+/* so->echotimer: fires when a sent CF/SF's local echo does not arrive */
+static enum hrtimer_restart isotp_echo_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     echotimer);
+
+	return isotp_tx_timeout(so);
+}
+
 static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer)
 {
 	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
 					     txfrtimer);
 
 	/* start echo timeout handling and cover below protocol error */
-	hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
+	hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
 		      HRTIMER_MODE_REL_SOFT);
 
 	/* cfecho should be consumed by isotp_rcv_echo() here */
@@ -958,13 +1024,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
 	int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0;
 	s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT;
+	struct hrtimer *tx_hrt = &so->echotimer;
+	u32 new_state = ISOTP_SENDING;
 	int off;
 	int err;
 
 	if (!so->bound || so->tx.state == ISOTP_SHUTDOWN)
 		return -EADDRNOTAVAIL;
 
-	while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) {
+	/* claim the socket under so->rx_lock: this serializes the claim
+	 * with the RX path and with sendmsg()'s own error paths below, so
+	 * none of them can ever see a transfer mid-claim
+	 */
+	for (;;) {
+		spin_lock_bh(&so->rx_lock);
+		if (READ_ONCE(so->tx.state) == ISOTP_IDLE)
+			break;
+		spin_unlock_bh(&so->rx_lock);
+
 		/* we do not support multiple buffers - for now */
 		if (msg->msg_flags & MSG_DONTWAIT)
 			return -EAGAIN;
@@ -973,9 +1050,29 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			return -EADDRNOTAVAIL;
 
 		/* wait for complete transmission of current pdu */
-		err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+		err = wait_event_interruptible(so->wait,
+					       so->tx.state == ISOTP_IDLE);
 		if (err)
-			goto err_event_drop;
+			return err;
+	}
+
+	/* new transfer: bump so->tx_gen and drain the old one's timers,
+	 * still under the so->rx_lock we just claimed the socket with
+	 */
+	WRITE_ONCE(so->tx.state, ISOTP_SENDING);
+	WRITE_ONCE(so->tx_gen, READ_ONCE(so->tx_gen) + 1);
+	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->echotimer);
+	hrtimer_cancel(&so->txfrtimer);
+	so->cfecho = 0;
+	spin_unlock_bh(&so->rx_lock);
+
+	/* so->bound is only checked once above - a wakeup may have
+	 * unbound/rebound the socket meanwhile, so re-validate it
+	 */
+	if (!so->bound) {
+		err = -EADDRNOTAVAIL;
+		goto err_out_drop;
 	}
 
 	/* PDU size > default => try max_pdu_size */
@@ -1086,18 +1183,33 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			so->cfecho = *(u32 *)cf->data;
 		} else {
 			/* standard flow control check */
-			so->tx.state = ISOTP_WAIT_FIRST_FC;
+			new_state = ISOTP_WAIT_FIRST_FC;
 
 			/* start timeout for FC */
 			hrtimer_sec = ISOTP_FC_TIMEOUT;
+			tx_hrt = &so->txtimer;
 
 			/* no CF echo tag for isotp_rcv_echo() (FF-mode) */
 			so->cfecho = 0;
 		}
 	}
 
-	hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0),
+	spin_lock_bh(&so->rx_lock);
+	if (so->tx.state == ISOTP_SHUTDOWN) {
+		/* isotp_release() has since taken over and already drained
+		 * our timers - don't send into a socket that's going away
+		 */
+		spin_unlock_bh(&so->rx_lock);
+		kfree_skb(skb);
+		dev_put(dev);
+		wake_up_interruptible(&so->wait);
+		return -EADDRNOTAVAIL;
+	}
+	/* WAIT_FIRST_FC for standard FF, else stays ISOTP_SENDING */
+	so->tx.state = new_state;
+	hrtimer_start(tx_hrt, ktime_set(hrtimer_sec, 0),
 		      HRTIMER_MODE_REL_SOFT);
+	spin_unlock_bh(&so->rx_lock);
 
 	/* send the first or only CAN frame */
 	cf->flags = so->ll.tx_flags;
@@ -1110,13 +1222,10 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
 			       __func__, ERR_PTR(err));
 
+		spin_lock_bh(&so->rx_lock);
 		/* no transmission -> no timeout monitoring */
-		hrtimer_cancel(&so->txtimer);
-
-		/* reset consecutive frame echo tag */
-		so->cfecho = 0;
-
-		goto err_out_drop;
+		hrtimer_cancel(tx_hrt);
+		goto err_out_drop_locked;
 	}
 
 	if (wait_tx_done) {
@@ -1132,14 +1241,21 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 
 	return size;
 
+err_out_drop:
+	/* claimed but nothing sent yet - no timer to cancel */
+	spin_lock_bh(&so->rx_lock);
+	goto err_out_drop_locked;
 err_event_drop:
-	/* got signal: force tx state machine to be idle */
-	so->tx.state = ISOTP_IDLE;
+	/* interrupted waiting on our own transfer - drain its timers */
+	spin_lock_bh(&so->rx_lock);
 	hrtimer_cancel(&so->txfrtimer);
 	hrtimer_cancel(&so->txtimer);
-err_out_drop:
-	/* drop this PDU and unlock a potential wait queue */
+	hrtimer_cancel(&so->echotimer);
+err_out_drop_locked:
+	/* release the claim; so->rx_lock still held from above */
+	so->cfecho = 0;
 	so->tx.state = ISOTP_IDLE;
+	spin_unlock_bh(&so->rx_lock);
 	wake_up_interruptible(&so->wait);
 
 	return err;
@@ -1201,13 +1317,20 @@ static int isotp_release(struct socket *sock)
 	so = isotp_sk(sk);
 	net = sock_net(sk);
 
-	/* wait for complete transmission of current pdu */
-	while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 &&
-	       cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE)
+	/* best-effort: wait for a running pdu to finish, but don't block on
+	 * it forever - give up after the first signal
+	 */
+	while (so->tx.state != ISOTP_IDLE &&
+	       wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0)
 		;
 
-	/* force state machines to be idle also when a signal occurred */
+	/* claim the socket under so->rx_lock like sendmsg() does, so its
+	 * claim can't race the forced ISOTP_SHUTDOWN below; force it
+	 * unconditionally, even when a signal cut the wait above short
+	 */
+	spin_lock_bh(&so->rx_lock);
 	so->tx.state = ISOTP_SHUTDOWN;
+	spin_unlock_bh(&so->rx_lock);
 	so->rx.state = ISOTP_IDLE;
 
 	spin_lock(&isotp_notifier_lock);
@@ -1219,36 +1342,43 @@ static int isotp_release(struct socket *sock)
 	list_del(&so->notifier);
 	spin_unlock(&isotp_notifier_lock);
 
+	rtnl_lock();
 	lock_sock(sk);
 
-	/* remove current filters & unregister */
-	if (so->bound) {
-		if (so->ifindex) {
-			struct net_device *dev;
-
-			dev = dev_get_by_index(net, so->ifindex);
-			if (dev) {
-				if (isotp_register_rxid(so))
-					can_rx_unregister(net, dev, so->rxid,
-							  SINGLE_MASK(so->rxid),
-							  isotp_rcv, sk);
-
-				can_rx_unregister(net, dev, so->txid,
-						  SINGLE_MASK(so->txid),
-						  isotp_rcv_echo, sk);
-				dev_put(dev);
-				synchronize_rcu();
-			}
-		}
+	/* remove current filters & unregister
+	 * tracked reference so->dev is taken at bind() time with rtnl_lock
+	 */
+	if (so->bound && so->dev) {
+		if (isotp_register_rxid(so))
+			can_rx_unregister(net, so->dev, so->rxid,
+					  SINGLE_MASK(so->rxid),
+					  isotp_rcv, sk);
+
+		can_rx_unregister(net, so->dev, so->txid,
+				  SINGLE_MASK(so->txid),
+				  isotp_rcv_echo, sk);
+		netdev_put(so->dev, &so->dev_tracker);
 	}
 
+	so->ifindex = 0;
+	so->bound = 0;
+	so->dev = NULL;
+
+	rtnl_unlock();
+
+	/* Always wait for a grace period before touching the timers below.
+	 * A concurrent NETDEV_UNREGISTER may have already unregistered our
+	 * filters and cleared so->bound in isotp_notify() without waiting
+	 * for in-flight isotp_rcv() callers to finish, so this call must not
+	 * be skipped just because so->bound is already 0 here.
+	 */
+	synchronize_rcu();
+
 	hrtimer_cancel(&so->txfrtimer);
 	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->echotimer);
 	hrtimer_cancel(&so->rxtimer);
 
-	so->ifindex = 0;
-	so->bound = 0;
-
 	sock_orphan(sk);
 	sock->sk = NULL;
 
@@ -1303,6 +1433,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	if (!addr->can_ifindex)
 		return -ENODEV;
 
+	rtnl_lock();
 	lock_sock(sk);
 
 	if (so->bound) {
@@ -1310,6 +1441,17 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 		goto out;
 	}
 
+	/* A transmission or reception that outlived a previous binding
+	 * (unbound by NETDEV_UNREGISTER) may still be draining; the FC/echo
+	 * and RX watchdog timers bound how long this takes. Checked together
+	 * with so->bound in the same lock_sock() section above, so there is
+	 * no window in which a concurrent isotp_notify() could be missed.
+	 */
+	if (so->tx.state != ISOTP_IDLE || so->rx.state != ISOTP_IDLE) {
+		err = -EAGAIN;
+		goto out;
+	}
+
 	/* ensure different CAN IDs when the rx_id is to be registered */
 	if (isotp_register_rxid(so) && rx_id == tx_id) {
 		err = -EADDRNOTAVAIL;
@@ -1322,14 +1464,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 		goto out;
 	}
 	if (dev->type != ARPHRD_CAN) {
-		dev_put(dev);
 		err = -ENODEV;
-		goto out;
+		goto out_put_dev;
 	}
 	if (READ_ONCE(dev->mtu) < so->ll.mtu) {
-		dev_put(dev);
 		err = -EINVAL;
-		goto out;
+		goto out_put_dev;
 	}
 	if (!(dev->flags & IFF_UP))
 		notify_enetdown = 1;
@@ -1347,16 +1487,25 @@ static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int l
 	can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id),
 			isotp_rcv_echo, sk, "isotpe", sk);
 
-	dev_put(dev);
-
 	/* switch to new settings */
 	so->ifindex = ifindex;
 	so->rxid = rx_id;
 	so->txid = tx_id;
 	so->bound = 1;
 
+	/* bind() ok -> hold a reference for so->dev so that isotp_release()
+	 * can safely reach the device later, even if a concurrent
+	 * NETDEV_UNREGISTER has already unlisted it by ifindex.
+	 */
+	so->dev = dev;
+	netdev_hold(so->dev, &so->dev_tracker, GFP_KERNEL);
+
+out_put_dev:
+	/* remove potential reference from dev_get_by_index() */
+	dev_put(dev);
 out:
 	release_sock(sk);
+	rtnl_unlock();
 
 	if (notify_enetdown) {
 		sk->sk_err = ENETDOWN;
@@ -1559,7 +1708,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return;
 
-	if (so->ifindex != dev->ifindex)
+	if (so->dev != dev)
 		return;
 
 	switch (msg) {
@@ -1575,10 +1724,12 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg,
 			can_rx_unregister(dev_net(dev), dev, so->txid,
 					  SINGLE_MASK(so->txid),
 					  isotp_rcv_echo, sk);
+			netdev_put(so->dev, &so->dev_tracker);
 		}
 
 		so->ifindex = 0;
 		so->bound  = 0;
+		so->dev = NULL;
 		release_sock(sk);
 
 		sk->sk_err = ENODEV;
@@ -1638,6 +1789,7 @@ static int isotp_init(struct sock *sk)
 
 	so->ifindex = 0;
 	so->bound = 0;
+	so->dev = NULL;
 
 	so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS;
 	so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS;
@@ -1664,10 +1816,14 @@ static int isotp_init(struct sock *sk)
 	so->rx.buflen = ARRAY_SIZE(so->rx.sbuf);
 	so->tx.buflen = ARRAY_SIZE(so->tx.sbuf);
 
-	hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	hrtimer_setup(&so->txtimer, isotp_tx_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
-	hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler, CLOCK_MONOTONIC,
-		      HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->rxtimer, isotp_rx_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->txtimer, isotp_tx_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->echotimer, isotp_echo_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	hrtimer_setup(&so->txfrtimer, isotp_txfr_timer_handler,
+		      CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
 
 	init_waitqueue_head(&so->wait);
 	spin_lock_init(&so->rx_lock);
diff --git a/net/core/dev.c b/net/core/dev.c
index 0c6c270d9f7d..f81ce83fb325 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5381,8 +5381,6 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	u32 tail;
 
 	reason = SKB_DROP_REASON_DEV_READY;
-	if (unlikely(!netif_running(skb->dev)))
-		goto bad_dev;
 
 	sd = &per_cpu(softnet_data, cpu);
 
@@ -5394,6 +5392,10 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	backlog_lock_irq_save(sd, &flags);
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (likely(qlen <= max_backlog)) {
+		if (unlikely(!netif_running(skb->dev))) {
+			backlog_unlock_irq_restore(sd, flags);
+			goto bad_dev;
+		}
 		if (!qlen) {
 			/* Schedule NAPI for backlog device. We can use
 			 * non atomic operation as we own the queue lock.
@@ -11217,7 +11219,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 
 	netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
 	spin_lock_init(&dev->tx_global_lock);
-
+	spin_lock_init(&dev->watchdog_lock);
+	dev->watchdog_ref_held = false;
 	return 0;
 }
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 8ca634964e36..cf374c208732 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -349,7 +349,7 @@ jumped:
 
 		if (err != -EAGAIN) {
 			if ((arg->flags & FIB_LOOKUP_NOREF) ||
-			    likely(refcount_inc_not_zero(&rule->refcnt))) {
+			    likely(fib_rule_get_safe(rule))) {
 				arg->rule = rule;
 				goto out;
 			}
@@ -410,8 +410,12 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
 	if (!ops)
 		return -EAFNOSUPPORT;
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+		if (!fib_rule_get_safe(rule))
+			continue;
+
 		err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD,
 					     rule, family, extack);
+		fib_rule_put(rule);
 		if (err)
 			break;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index 40037413dd4e..f21aeff99cc9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2834,6 +2834,9 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 	if (!space || (space == 1 && start != offset))
 		copy = msg->sg.data[i].length;
 
+	if (unlikely(copy + len < copy))
+		return -EINVAL;
+
 	page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP,
 			   get_order(copy + len));
 	if (unlikely(!page))
@@ -2997,8 +3000,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 	   u32, len, u64, flags)
 {
 	u32 i = 0, l = 0, space, offset = 0;
-	u64 last = start + len;
-	int pop;
+	u64 last = (u64)start + len;
+	u32 pop;
 
 	if (unlikely(flags))
 		return -EINVAL;
@@ -4430,7 +4433,7 @@ u32 xdp_master_redirect(struct xdp_buff *xdp)
 	struct net_device *master, *slave;
 
 	master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev);
-	if (unlikely(!(master->flags & IFF_UP)))
+	if (unlikely(!master || !(master->flags & IFF_UP)))
 		return XDP_ABORTED;
 	slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp);
 	if (slave && slave != xdp->rxq->dev) {
@@ -5571,11 +5574,24 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 				 KERNEL_SOCKPTR(optval), *optlen);
 }
 
+static bool sk_allows_sol_ip_sockopt(struct sock *sk)
+{
+	switch (sk->sk_family) {
+	case AF_INET:
+		return true;
+	case AF_INET6:
+		/* Allow getting/setting sockopt for possible ipv4-mapped ipv6 socket. */
+		return sk->sk_type != SOCK_RAW && !ipv6_only_sock(sk);
+	default:
+		return false;
+	}
+}
+
 static int sol_ip_sockopt(struct sock *sk, int optname,
 			  char *optval, int *optlen,
 			  bool getopt)
 {
-	if (sk->sk_family != AF_INET)
+	if (!sk_allows_sol_ip_sockopt(sk))
 		return -EINVAL;
 
 	switch (optname) {
@@ -6166,7 +6182,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct in_device *in_dev;
 	struct net_device *dev;
 	struct fib_result res;
-	struct flowi4 fl4;
+	struct flowi4 fl4 = {};
 	u32 mtu = 0;
 	int err;
 
@@ -6306,7 +6322,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct neighbour *neigh;
 	struct net_device *dev;
 	struct inet6_dev *idev;
-	struct flowi6 fl6;
+	struct flowi6 fl6 = {};
 	int strict = 0;
 	int oif, err;
 	u32 mtu = 0;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2a98f5fa74eb..8aa4f9b4df81 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1173,13 +1173,21 @@ bool __skb_flow_dissect(const struct net *net,
 
 	if (dissector_uses_key(flow_dissector,
 			       FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct ethhdr *eth = eth_hdr(skb);
 		struct flow_dissector_key_eth_addrs *key_eth_addrs;
 
 		key_eth_addrs = skb_flow_dissector_target(flow_dissector,
 							  FLOW_DISSECTOR_KEY_ETH_ADDRS,
 							  target_container);
-		memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs));
+		/* TC filter blocks can be shared across devices with
+		 * different link types, so we cannot validate this
+		 * when the filter is installed -- check at dissect time.
+		 */
+		if (skb && skb->dev &&
+		    skb->dev->type == ARPHRD_ETHER &&
+		    skb_mac_header_was_set(skb))
+			memcpy(key_eth_addrs, eth_hdr(skb), sizeof(*key_eth_addrs));
+		else
+			memset(key_eth_addrs, 0, sizeof(*key_eth_addrs));
 	}
 
 	if (dissector_uses_key(flow_dissector,
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index f71ef82a5f3d..bf588f508b79 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -599,6 +599,7 @@ static int handle_gso_encap(struct sk_buff *skb, bool ipv4, int encap_len)
 
 int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
 {
+	bool is_udp_tunnel;
 	struct iphdr *iph;
 	bool ipv4;
 	int err;
@@ -612,10 +613,16 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
 		ipv4 = true;
 		if (unlikely(len < iph->ihl * 4))
 			return -EINVAL;
+		is_udp_tunnel = iph->protocol == IPPROTO_UDP;
+		if (unlikely(is_udp_tunnel && len < iph->ihl * 4 + sizeof(struct udphdr)))
+			return -EINVAL;
 	} else if (iph->version == 6) {
 		ipv4 = false;
 		if (unlikely(len < sizeof(struct ipv6hdr)))
 			return -EINVAL;
+		is_udp_tunnel = ((struct ipv6hdr *)iph)->nexthdr == NEXTHDR_UDP;
+		if (unlikely(is_udp_tunnel && len < sizeof(struct ipv6hdr) + sizeof(struct udphdr)))
+			return -EINVAL;
 	} else {
 		return -EINVAL;
 	}
@@ -637,6 +644,11 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
 	if (ingress)
 		skb_postpush_rcsum(skb, iph, len);
 	skb_reset_network_header(skb);
+	if (is_udp_tunnel) {
+		size_t iph_sz = ipv4 ? iph->ihl * 4 : sizeof(struct ipv6hdr);
+
+		skb_set_transport_header(skb, skb_network_offset(skb) + iph_sz);
+	}
 	memcpy(skb_network_header(skb), hdr, len);
 	bpf_compute_data_pointers(skb);
 	skb_clear_hash(skb);
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index f9d76d85d04f..b01a395d9a96 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -350,6 +350,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
 	if (likely(ops && ops->output)) {
+		/* Encap pushes outer headers over the metadata; drop it. */
+		skb_metadata_clear(skb);
 		dev_xmit_recursion_inc();
 		ret = ops->output(net, sk, skb);
 		dev_xmit_recursion_dec();
@@ -404,6 +406,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
 	if (likely(ops && ops->xmit)) {
+		/* Encap pushes outer headers over the metadata; drop it. */
+		skb_metadata_clear(skb);
 		dev_xmit_recursion_inc();
 		ret = ops->xmit(skb);
 		dev_xmit_recursion_dec();
@@ -455,6 +459,8 @@ int lwtunnel_input(struct sk_buff *skb)
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
 	if (likely(ops && ops->input)) {
+		/* Encap pushes outer headers over the metadata; drop it. */
+		skb_metadata_clear(skb);
 		dev_xmit_recursion_inc();
 		ret = ops->input(skb);
 		dev_xmit_recursion_dec();
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 119eaa6501d5..ed76544b2d45 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -2,6 +2,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
+#include <linux/pid_namespace.h>
 #include <linux/rtnetlink.h>
 #include <net/busy_poll.h>
 #include <net/net_namespace.h>
@@ -189,7 +190,8 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 		goto nla_put_failure;
 
 	if (napi->thread) {
-		pid = task_pid_nr(napi->thread);
+		pid = task_pid_nr_ns(napi->thread,
+				     task_active_pid_ns(current));
 		if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
 			goto nla_put_failure;
 	}
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index de4dac4c88b3..00a7011eb4d5 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -338,12 +338,12 @@ void __netif_mp_uninstall_rxq(struct netdev_rx_queue *rxq,
 void netif_rxq_cleanup_unlease(struct netdev_rx_queue *phys_rxq,
 			       struct netdev_rx_queue *virt_rxq)
 {
-	struct pp_memory_provider_params *p = &phys_rxq->mp_params;
 	unsigned int rxq_idx = get_netdev_rx_queue_index(phys_rxq);
+	struct pp_memory_provider_params p = phys_rxq->mp_params;
 
-	if (!p->mp_ops)
+	if (!p.mp_ops)
 		return;
 
-	__netif_mp_uninstall_rxq(virt_rxq, p);
-	__netif_mp_close_rxq(phys_rxq->dev, rxq_idx, p);
+	__netif_mp_close_rxq(phys_rxq->dev, rxq_idx, &p);
+	__netif_mp_uninstall_rxq(virt_rxq, &p);
 }
diff --git a/net/devlink/rate.c b/net/devlink/rate.c
index 41be2d6c2954..533d21b028a7 100644
--- a/net/devlink/rate.c
+++ b/net/devlink/rate.c
@@ -486,16 +486,19 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
 		devlink_rate->tx_weight = weight;
 	}
 
-	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
-	if (nla_parent) {
-		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
-						      nla_parent);
+	if (attrs[DEVLINK_ATTR_RATE_TC_BWS]) {
+		err = devlink_nl_rate_tc_bw_set(devlink_rate, info);
 		if (err)
 			return err;
 	}
 
-	if (attrs[DEVLINK_ATTR_RATE_TC_BWS]) {
-		err = devlink_nl_rate_tc_bw_set(devlink_rate, info);
+	/* Keep parent setting last because it takes a reference. This function
+	 * has no rollback, so failing after taking the ref would leak it.
+	 */
+	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
+	if (nla_parent) {
+		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
+						      nla_parent);
 		if (err)
 			return err;
 	}
@@ -725,11 +728,6 @@ devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
 	if (!rate_node)
 		return ERR_PTR(-ENOMEM);
 
-	if (parent) {
-		rate_node->parent = parent;
-		refcount_inc(&rate_node->parent->refcnt);
-	}
-
 	rate_node->type = DEVLINK_RATE_TYPE_NODE;
 	rate_node->devlink = devlink;
 	rate_node->priv = priv;
@@ -740,6 +738,11 @@ devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (parent) {
+		rate_node->parent = parent;
+		refcount_inc(&rate_node->parent->refcnt);
+	}
+
 	refcount_set(&rate_node->refcnt, 1);
 	list_add(&rate_node->list, &devlink->rate_list);
 	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index fd2198e45d2b..733fb3c3a63a 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -116,6 +116,34 @@ static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr,
 }
 
 /**
+ * ethnl_update_u8_u32() - update u8 value from an NLA_U32 attribute
+ * @dst:  value to update
+ * @attr: netlink attribute with new value or null
+ * @mod:  pointer to bool for modification tracking
+ *
+ * Some attributes are NLA_U32 on the wire but are stored in a u8. Read the
+ * full 32-bit value from NLA_U32 netlink attribute @attr and narrow it into
+ * the u8 pointed to by @dst; do nothing if @attr is null.
+ * Bool pointed to by @mod is set to true if this function changed the value
+ * of *dst, otherwise it is left as is.
+ */
+static inline void ethnl_update_u8_u32(u8 *dst, const struct nlattr *attr,
+				       bool *mod)
+{
+	u32 val;
+
+	if (!attr)
+		return;
+	val = nla_get_u32(attr);
+	DEBUG_NET_WARN_ON_ONCE(val > U8_MAX);
+	if (*dst == val)
+		return;
+
+	*dst = val;
+	*mod = true;
+}
+
+/**
  * ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute
  * @dst:  value to update
  * @attr: netlink attribute with new value or null
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 53792f53f922..ca6ed152c2be 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -574,7 +574,7 @@ static const struct nla_policy ethnl_rss_flows_policy[] = {
 const struct nla_policy ethnl_rss_set_policy[ETHTOOL_A_RSS_FLOW_HASH + 1] = {
 	[ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32, },
-	[ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_MIN(NLA_U32, 1),
+	[ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_RANGE(NLA_U32, 1, U8_MAX),
 	[ETHTOOL_A_RSS_INDIR] = { .type = NLA_BINARY, },
 	[ETHTOOL_A_RSS_HKEY] = NLA_POLICY_MIN(NLA_BINARY, 1),
 	[ETHTOOL_A_RSS_INPUT_XFRM] =
@@ -855,7 +855,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info)
 	indir_mod = !!tb[ETHTOOL_A_RSS_INDIR];
 
 	rxfh.hfunc = data.hfunc;
-	ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod);
+	ethnl_update_u8_u32(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod);
 	if (rxfh.hfunc == data.hfunc)
 		rxfh.hfunc = ETH_RSS_HASH_NO_CHANGE;
 
@@ -864,7 +864,8 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info)
 		goto exit_free_indir;
 
 	rxfh.input_xfrm = data.input_xfrm;
-	ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod);
+	ethnl_update_u8_u32(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM],
+			    &mod);
 	xfrm_sym = rxfh.input_xfrm || data.input_xfrm;
 	if (rxfh.input_xfrm == data.input_xfrm)
 		rxfh.input_xfrm = RXH_XFRM_NO_CHANGE;
@@ -938,7 +939,7 @@ const struct ethnl_request_ops ethnl_rss_request_ops = {
 const struct nla_policy ethnl_rss_create_policy[ETHTOOL_A_RSS_INPUT_XFRM + 1] = {
 	[ETHTOOL_A_RSS_HEADER]	= NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_RSS_CONTEXT]	= NLA_POLICY_MIN(NLA_U32, 1),
-	[ETHTOOL_A_RSS_HFUNC]	= NLA_POLICY_MIN(NLA_U32, 1),
+	[ETHTOOL_A_RSS_HFUNC]	= NLA_POLICY_RANGE(NLA_U32, 1, U8_MAX),
 	[ETHTOOL_A_RSS_INDIR]	= NLA_POLICY_MIN(NLA_BINARY, 1),
 	[ETHTOOL_A_RSS_HKEY]	= NLA_POLICY_MIN(NLA_BINARY, 1),
 	[ETHTOOL_A_RSS_INPUT_XFRM] =
@@ -1054,14 +1055,15 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info)
 		goto exit_clean_data;
 	indir_user_size = ret;
 
-	ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod);
+	ethnl_update_u8_u32(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod);
 
 	ret = rss_set_prep_hkey(dev, info, &data, &rxfh, &mod);
 	if (ret)
 		goto exit_free_indir;
 
 	rxfh.input_xfrm = RXH_XFRM_NO_CHANGE;
-	ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod);
+	ethnl_update_u8_u32(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM],
+			    &mod);
 
 	ctx = ethtool_rxfh_ctx_alloc(ops, data.indir_size, data.hkey_size);
 	if (!ctx) {
diff --git a/net/handshake/genl.c b/net/handshake/genl.c
index 4b20cd9cdd0e..feac1ad063ee 100644
--- a/net/handshake/genl.c
+++ b/net/handshake/genl.c
@@ -38,7 +38,7 @@ static const struct genl_split_ops handshake_nl_ops[] = {
 		.doit		= handshake_nl_done_doit,
 		.policy		= handshake_done_nl_policy,
 		.maxattr	= HANDSHAKE_A_DONE_REMOTE_AUTH,
-		.flags		= GENL_CMD_CAP_DO,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 };
 
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 89b671b12600..c0b8712018a1 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -228,36 +228,43 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 			continue;
 		wpan_dev->netdev->netns_immutable = false;
 		err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d");
-		if (err)
+		if (err) {
+			WARN_ON(err && err != -ENOMEM);
 			break;
+		}
 		wpan_dev->netdev->netns_immutable = true;
 	}
 
-	if (err) {
-		/* failed -- clean up to old netns */
-		net = wpan_phy_net(&rdev->wpan_phy);
-
-		list_for_each_entry_continue_reverse(wpan_dev,
-						     &rdev->wpan_dev_list,
-						     list) {
-			if (!wpan_dev->netdev)
-				continue;
-			wpan_dev->netdev->netns_immutable = false;
-			err = dev_change_net_namespace(wpan_dev->netdev, net,
-						       "wpan%d");
-			WARN_ON(err);
-			wpan_dev->netdev->netns_immutable = true;
-		}
+	if (err)
+		goto errout;
 
-		return err;
-	}
+	err = device_rename(&rdev->wpan_phy.dev, dev_name(&rdev->wpan_phy.dev));
+	WARN_ON(err && err != -ENOMEM);
 
-	wpan_phy_net_set(&rdev->wpan_phy, net);
+	if (err)
+		goto errout;
 
-	err = device_rename(&rdev->wpan_phy.dev, dev_name(&rdev->wpan_phy.dev));
-	WARN_ON(err);
+	wpan_phy_net_set(&rdev->wpan_phy, net);
 
 	return 0;
+
+errout:
+	/* failed -- clean up to old netns */
+	net = wpan_phy_net(&rdev->wpan_phy);
+
+	list_for_each_entry_continue_reverse(wpan_dev,
+					     &rdev->wpan_dev_list,
+					     list) {
+		if (!wpan_dev->netdev)
+			continue;
+		wpan_dev->netdev->netns_immutable = false;
+		err = dev_change_net_namespace(wpan_dev->netdev, net,
+					       "wpan%d");
+		WARN_ON(err && err != -ENOMEM);
+		wpan_dev->netdev->netns_immutable = true;
+	}
+
+	return err;
 }
 
 void cfg802154_dev_free(struct cfg802154_registered_device *rdev)
@@ -351,7 +358,7 @@ static void __net_exit cfg802154_pernet_exit(struct net *net)
 	rtnl_lock();
 	list_for_each_entry(rdev, &cfg802154_rdev_list, list) {
 		if (net_eq(wpan_phy_net(&rdev->wpan_phy), net))
-			WARN_ON(cfg802154_switch_netns(rdev, &init_net));
+			cfg802154_switch_netns(rdev, &init_net);
 	}
 	rtnl_unlock();
 }
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
index 41a556be1017..a9f0c8df5ae4 100644
--- a/net/ieee802154/header_ops.c
+++ b/net/ieee802154/header_ops.c
@@ -173,10 +173,13 @@ ieee802154_hdr_get_addr(const u8 *buf, int mode, bool omit_pan,
 {
 	int pos = 0;
 
-	addr->mode = mode;
-
-	if (mode == IEEE802154_ADDR_NONE)
+	if (mode == IEEE802154_ADDR_NONE) {
+		memset(addr, 0, sizeof(*addr));
+		addr->mode = IEEE802154_ADDR_NONE;
 		return 0;
+	}
+
+	addr->mode = mode;
 
 	if (!omit_pan) {
 		memcpy(&addr->pan_id, buf + pos, 2);
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index c5d91f78301a..e765adc4b88f 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -16,6 +16,15 @@ void ieee802154_nl_exit(void);
 		.flags	= GENL_ADMIN_PERM,		\
 	}
 
+#define IEEE802154_OP_RELAXED(_cmd, _func)		\
+	{						\
+		.cmd		= _cmd,			\
+		.doit		= _func,		\
+		.dumpit		= NULL,			\
+		.flags		= GENL_ADMIN_PERM,	\
+		.validate	= GENL_DONT_VALIDATE_STRICT,\
+	}
+
 #define IEEE802154_DUMP(_cmd, _func, _dump)		\
 	{						\
 		.cmd	= _cmd,				\
@@ -23,6 +32,14 @@ void ieee802154_nl_exit(void);
 		.dumpit	= _dump,			\
 	}
 
+#define IEEE802154_DUMP_PRIV(_cmd, _func, _dump)	\
+	{						\
+		.cmd	= _cmd,				\
+		.doit	= _func,			\
+		.dumpit	= _dump,			\
+		.flags	= GENL_ADMIN_PERM,		\
+	}
+
 struct genl_info;
 
 struct sk_buff *ieee802154_nl_create(int flags, u8 req);
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 7d2de4ee6992..cacad21347ec 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -98,24 +98,24 @@ static const struct genl_small_ops ieee802154_ops[] = {
 	IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams),
 	IEEE802154_OP(IEEE802154_LLSEC_GETPARAMS, ieee802154_llsec_getparams),
 	IEEE802154_OP(IEEE802154_LLSEC_SETPARAMS, ieee802154_llsec_setparams),
-	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_KEY, NULL,
-			ieee802154_llsec_dump_keys),
-	IEEE802154_OP(IEEE802154_LLSEC_ADD_KEY, ieee802154_llsec_add_key),
-	IEEE802154_OP(IEEE802154_LLSEC_DEL_KEY, ieee802154_llsec_del_key),
-	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEV, NULL,
-			ieee802154_llsec_dump_devs),
-	IEEE802154_OP(IEEE802154_LLSEC_ADD_DEV, ieee802154_llsec_add_dev),
-	IEEE802154_OP(IEEE802154_LLSEC_DEL_DEV, ieee802154_llsec_del_dev),
-	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEVKEY, NULL,
-			ieee802154_llsec_dump_devkeys),
-	IEEE802154_OP(IEEE802154_LLSEC_ADD_DEVKEY, ieee802154_llsec_add_devkey),
-	IEEE802154_OP(IEEE802154_LLSEC_DEL_DEVKEY, ieee802154_llsec_del_devkey),
-	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_SECLEVEL, NULL,
-			ieee802154_llsec_dump_seclevels),
-	IEEE802154_OP(IEEE802154_LLSEC_ADD_SECLEVEL,
-		      ieee802154_llsec_add_seclevel),
-	IEEE802154_OP(IEEE802154_LLSEC_DEL_SECLEVEL,
-		      ieee802154_llsec_del_seclevel),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_KEY, NULL,
+			     ieee802154_llsec_dump_keys),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_KEY, ieee802154_llsec_add_key),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_KEY, ieee802154_llsec_del_key),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_DEV, NULL,
+			     ieee802154_llsec_dump_devs),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_DEV, ieee802154_llsec_add_dev),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_DEV, ieee802154_llsec_del_dev),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_DEVKEY, NULL,
+			     ieee802154_llsec_dump_devkeys),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_DEVKEY, ieee802154_llsec_add_devkey),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_DEVKEY, ieee802154_llsec_del_devkey),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_SECLEVEL, NULL,
+			     ieee802154_llsec_dump_seclevels),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_SECLEVEL,
+			      ieee802154_llsec_add_seclevel),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_SECLEVEL,
+			      ieee802154_llsec_del_seclevel),
 };
 
 static const struct genl_multicast_group ieee802154_mcgrps[] = {
diff --git a/net/ife/ife.c b/net/ife/ife.c
index be05b690b9ef..7a75947a31e3 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -79,7 +79,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
 	if (unlikely(ifehdrln < 2))
 		return NULL;
 
-	if (unlikely(!pskb_may_pull(skb, total_pull)))
+	if (unlikely(!pskb_may_pull(skb, total_pull + ETH_HLEN)))
 		return NULL;
 
 	ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1308213791f1..dac543c1d686 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2172,10 +2172,14 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb,
 		if (fa->fa_slen == last_slen)
 			continue;
 
+		if (!fib_info_hold_safe(fa->fa_info))
+			continue;
+
 		last_slen = fa->fa_slen;
 		err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE,
 					      l->key, KEYLENGTH - fa->fa_slen,
 					      fa, extack);
+		fib_info_put(fa->fa_info);
 		if (err)
 			return err;
 	}
diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
index 5bae3cf7fe76..6bed0e1dbe0e 100644
--- a/net/ipv4/fou_core.c
+++ b/net/ipv4/fou_core.c
@@ -558,11 +558,8 @@ static int fou_add_to_port_list(struct net *net, struct fou *fou,
 
 static void fou_release(struct fou *fou)
 {
-	struct socket *sock = fou->sock;
-
 	list_del(&fou->list);
-	udp_tunnel_sock_release(sock);
-
+	udp_tunnel_sock_release(fou->sock->sk);
 	kfree_rcu(fou, rcu);
 }
 
@@ -618,7 +615,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 		goto error;
 	}
 
-	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
+	setup_udp_tunnel_sock(net, sk, &tunnel_cfg);
 
 	sk->sk_allocation = GFP_ATOMIC;
 
@@ -634,7 +631,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 error:
 	kfree(fou);
 	if (sock)
-		udp_tunnel_sock_release(sock);
+		udp_tunnel_sock_release(sock->sk);
 
 	return err;
 }
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 523aecb3c9be..f22fbc17f15b 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -217,13 +217,18 @@ static void ip_sf_list_clear_all(struct ip_sf_list *psf)
 
 static void igmp_stop_timer(struct ip_mc_list *im)
 {
+	bool put = false;
+
 	spin_lock_bh(&im->lock);
 	if (timer_delete(&im->timer))
-		refcount_dec(&im->refcnt);
-	im->tm_running = 0;
-	im->reporter = 0;
+		put = true;
+	WRITE_ONCE(im->tm_running, 0);
+	WRITE_ONCE(im->reporter, 0);
 	im->unsolicit_count = 0;
 	spin_unlock_bh(&im->lock);
+
+	if (put)
+		ip_ma_put(im);
 }
 
 /* It must be called with locked im->lock */
@@ -231,7 +236,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 {
 	int tv = get_random_u32_below(max_delay);
 
-	im->tm_running = 1;
+	WRITE_ONCE(im->tm_running, 1);
 	if (refcount_inc_not_zero(&im->refcnt)) {
 		if (mod_timer(&im->timer, jiffies + tv + 2))
 			ip_ma_put(im);
@@ -248,33 +253,42 @@ static void igmp_gq_start_timer(struct in_device *in_dev)
 		return;
 
 	in_dev->mr_gq_running = 1;
-	if (!mod_timer(&in_dev->mr_gq_timer, exp))
-		in_dev_hold(in_dev);
+	if (in_dev_hold_safe(in_dev)) {
+		if (mod_timer(&in_dev->mr_gq_timer, exp))
+			in_dev_put(in_dev);
+	}
 }
 
 static void igmp_ifc_start_timer(struct in_device *in_dev, int delay)
 {
-	int tv = get_random_u32_below(delay);
+	if (in_dev_hold_safe(in_dev)) {
+		int tv = get_random_u32_below(delay);
 
-	if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2))
-		in_dev_hold(in_dev);
+		if (mod_timer(&in_dev->mr_ifc_timer, jiffies + tv + 2))
+			in_dev_put(in_dev);
+	}
 }
 
 static void igmp_mod_timer(struct ip_mc_list *im, int max_delay)
 {
+	bool put = false;
+
 	spin_lock_bh(&im->lock);
 	im->unsolicit_count = 0;
 	if (timer_delete(&im->timer)) {
 		if ((long)(im->timer.expires-jiffies) < max_delay) {
 			add_timer(&im->timer);
-			im->tm_running = 1;
+			WRITE_ONCE(im->tm_running, 1);
 			spin_unlock_bh(&im->lock);
 			return;
 		}
-		refcount_dec(&im->refcnt);
+		put = true;
 	}
 	igmp_start_timer(im, max_delay);
 	spin_unlock_bh(&im->lock);
+
+	if (put)
+		ip_ma_put(im);
 }
 
 
@@ -857,12 +871,12 @@ static void igmp_timer_expire(struct timer_list *t)
 	struct in_device *in_dev = im->interface;
 
 	spin_lock(&im->lock);
-	im->tm_running = 0;
+	WRITE_ONCE(im->tm_running, 0);
 
 	if (im->unsolicit_count && --im->unsolicit_count)
 		igmp_start_timer(im, unsolicited_report_interval(in_dev));
 
-	im->reporter = 1;
+	WRITE_ONCE(im->reporter, 1);
 	spin_unlock(&im->lock);
 
 	if (IGMP_V1_SEEN(in_dev))
@@ -1325,7 +1339,7 @@ static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp)
 	    !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
 		return;
 
-	reporter = im->reporter;
+	reporter = READ_ONCE(im->reporter);
 	igmp_stop_timer(im);
 
 	if (!in_dev->dead) {
@@ -1541,7 +1555,7 @@ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr,
 	}
 
 	if  (im) {
-		im->users++;
+		WRITE_ONCE(im->users, im->users + 1);
 		ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0);
 		goto out;
 	}
@@ -1550,7 +1564,7 @@ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr,
 	if (!im)
 		goto out;
 
-	im->users = 1;
+	WRITE_ONCE(im->users, 1);
 	im->interface = in_dev;
 	in_dev_hold(in_dev);
 	im->multiaddr = addr;
@@ -1784,7 +1798,10 @@ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp)
 	     (i = rtnl_dereference(*ip)) != NULL;
 	     ip = &i->next_rcu) {
 		if (i->multiaddr == addr) {
-			if (--i->users == 0) {
+			int new_users = i->users - 1;
+
+			WRITE_ONCE(i->users, new_users);
+			if (new_users == 0) {
 				ip_mc_hash_remove(in_dev, i);
 				*ip = i->next_rcu;
 				in_dev->mc_count--;
@@ -2960,6 +2977,7 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v)
 		struct ip_mc_list *im = v;
 		struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq);
 		char   *querier;
+		int tm_running;
 		long delta;
 
 #ifdef CONFIG_IP_MULTICAST
@@ -2975,13 +2993,14 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v)
 				   state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier);
 		}
 
-		delta = im->timer.expires - jiffies;
+		tm_running = READ_ONCE(im->tm_running);
+		delta = READ_ONCE(im->timer.expires) - jiffies;
 		seq_printf(seq,
 			   "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n",
-			   im->multiaddr, im->users,
-			   im->tm_running,
-			   im->tm_running ? jiffies_delta_to_clock_t(delta) : 0,
-			   im->reporter);
+			   im->multiaddr, READ_ONCE(im->users),
+			   tm_running,
+			   tm_running ? jiffies_delta_to_clock_t(delta) : 0,
+			   READ_ONCE(im->reporter));
 	}
 	return 0;
 }
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5b934ce8d98a..690f7fb3f029 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1285,6 +1285,7 @@ EXPORT_SYMBOL(inet_csk_destroy_sock);
 void inet_csk_prepare_for_destroy_sock(struct sock *sk)
 {
 	/* The below has to be done to allow calling inet_csk_destroy_sock */
+	tcp_clear_sock_ops_cb_flags(sk);
 	sock_set_flag(sk, SOCK_DEAD);
 	tcp_orphan_count_inc();
 }
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 95b6bb78fcd2..3b80929994a0 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -596,6 +596,9 @@ static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ip_tunnel_parm_kern p;
 	__u32 fwmark = t->fwmark;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	vti_netlink_parms(data, &p, &fwmark);
 	return ip_tunnel_changelink(dev, tb, &p, fwmark);
 }
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index ff95b1b9908e..e7378569bd5b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -494,6 +494,9 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
 	bool collect_md;
 	__u32 fwmark = t->fwmark;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
 		int err = ip_tunnel_encap_setup(t, &ipencap);
 
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 10e1b0837731..183e8a3ff2ba 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -100,6 +100,9 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct,
 	__be16 port;
 	union nf_inet_addr addr;
 
+	if (!info)
+		return -1;
+
 	for (i = 0; i < count; i++) {
 		if (get_h225_addr(ct, *data, &taddr[i], &addr, &port)) {
 			if (addr.ip == ct->tuplehash[dir].tuple.src.u3.ip &&
@@ -184,6 +187,9 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 	int i;
 	u_int16_t nated_port;
 
+	if (!info)
+		return -1;
+
 	/* Set expectations for NAT */
 	rtp_exp->saved_proto.udp.port = rtp_exp->tuple.dst.u.udp.port;
 	rtp_exp->expectfn = nf_nat_follow_master;
@@ -325,6 +331,9 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct,
 	int dir = CTINFO2DIR(ctinfo);
 	u_int16_t nated_port = ntohs(port);
 
+	if (!info)
+		return -1;
+
 	/* Set expectations for NAT */
 	exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
 	exp->expectfn = nf_nat_follow_master;
@@ -404,6 +413,9 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct,
 	u_int16_t nated_port = ntohs(port);
 	union nf_inet_addr addr;
 
+	if (!info)
+		return -1;
+
 	/* Set expectations for NAT */
 	exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
 	exp->expectfn = ip_nat_q931_expect;
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index fab357cc8559..fed5249001a4 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -53,11 +53,13 @@ static void pptp_nat_expected(struct nf_conn *ct,
 	struct nf_conn_nat *nat;
 
 	nat = nf_ct_nat_ext_add(ct);
-	if (WARN_ON_ONCE(!nat))
+	if (!nat)
 		return;
 
 	nat_pptp_info = &nat->help.nat_pptp_info;
 	ct_pptp_info = nfct_help_data(master);
+	if (!ct_pptp_info)
+		return;
 
 	/* And here goes the grand finale of corrosion... */
 	if (exp->dir == IP_CT_DIR_ORIGINAL) {
@@ -132,11 +134,13 @@ pptp_outbound_pkt(struct sk_buff *skb,
 	__be16 new_callid;
 	unsigned int cid_off;
 
-	if (WARN_ON_ONCE(!nat))
+	if (!nat)
 		return NF_DROP;
 
 	nat_pptp_info = &nat->help.nat_pptp_info;
 	ct_pptp_info = nfct_help_data(ct);
+	if (!ct_pptp_info)
+		return NF_DROP;
 
 	new_callid = ct_pptp_info->pns_call_id;
 
@@ -204,11 +208,13 @@ pptp_exp_gre(struct nf_conntrack_expect *expect_orig,
 	struct nf_ct_pptp_master *ct_pptp_info;
 	struct nf_nat_pptp *nat_pptp_info;
 
-	if (WARN_ON_ONCE(!nat))
+	if (!nat)
 		return;
 
 	nat_pptp_info = &nat->help.nat_pptp_info;
 	ct_pptp_info = nfct_help_data(ct);
+	if (!ct_pptp_info)
+		return;
 
 	/* save original PAC call ID in nat_info */
 	nat_pptp_info->pac_call_id = ct_pptp_info->pac_call_id;
@@ -241,7 +247,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
 	__be16 new_pcid;
 	unsigned int pcid_off;
 
-	if (WARN_ON_ONCE(!nat))
+	if (!nat)
 		return NF_DROP;
 
 	nat_pptp_info = &nat->help.nat_pptp_info;
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
index 717b726504fe..0ede138dfd29 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c
@@ -202,29 +202,34 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = {
 	.timeout	= 180,
 };
 
-static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
-	.me			= THIS_MODULE,
-	.help			= help,
-	.expect_policy		= &snmp_exp_policy,
-	.name			= "snmp_trap",
-	.tuple.src.l3num	= AF_INET,
-	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_TRAP_PORT),
-	.tuple.dst.protonum	= IPPROTO_UDP,
-};
+static struct nf_conntrack_helper snmp_trap_helper __read_mostly;
+static struct nf_conntrack_helper *snmp_trap_helper_ptr __read_mostly;
 
 static int __init nf_nat_snmp_basic_init(void)
 {
+	int err;
+
 	BUG_ON(nf_nat_snmp_hook != NULL);
 	RCU_INIT_POINTER(nf_nat_snmp_hook, help);
 
-	return nf_conntrack_helper_register(&snmp_trap_helper);
+	nf_ct_helper_init(&snmp_trap_helper, AF_INET, IPPROTO_UDP,
+			  "snmp_trap", SNMP_TRAP_PORT, SNMP_TRAP_PORT, SNMP_TRAP_PORT,
+			  &snmp_exp_policy, 0, help, NULL, THIS_MODULE);
+
+	err = nf_conntrack_helper_register(&snmp_trap_helper, &snmp_trap_helper_ptr);
+	if (err < 0) {
+		RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+		return err;
+	}
+
+	return 0;
 }
 
 static void __exit nf_nat_snmp_basic_fini(void)
 {
 	RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
 	synchronize_rcu();
-	nf_conntrack_helper_unregister(&snmp_trap_helper);
+	nf_conntrack_helper_unregister(snmp_trap_helper_ptr);
 }
 
 module_init(nf_nat_snmp_basic_init);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index fecf6621f679..4626dc46808f 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -89,7 +89,7 @@ static bool nf_skb_is_icmp_unreach(const struct sk_buff *skb)
 	if (iph->protocol != IPPROTO_ICMP)
 		return false;
 
-	thoff = skb_network_offset(skb) + sizeof(*iph);
+	thoff = skb_network_offset(skb) + ip_hdrlen(skb);
 
 	tp = skb_header_pointer(skb,
 				thoff + offsetof(struct icmphdr, type),
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index aec7805b1d37..82378a2bfd1e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /* Bottleneck Bandwidth and RTT (BBR) congestion control
  *
  * BBR congestion control computes the sending rate based on the delivery
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fdc81150ff6c..bfdabad01fa7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1467,9 +1467,9 @@ void tcp_clear_md5_list(struct sock *sk)
 	md5sig = rcu_dereference_protected(tp->md5sig_info, 1);
 
 	hlist_for_each_entry_safe(key, n, &md5sig->head, node) {
-		hlist_del(&key->node);
+		hlist_del_rcu(&key->node);
 		atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
-		kfree(key);
+		kfree_rcu(key, rcu);
 	}
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 193637a58dcc..a88c7eb72b96 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4328,9 +4328,13 @@ int tcp_connect(struct sock *sk)
 		if (needs_md5) {
 			tcp_ao_destroy_sock(sk, false);
 		} else if (needs_ao) {
+			struct tcp_md5sig_info *md5sig;
+
 			tcp_clear_md5_list(sk);
-			kfree(rcu_replace_pointer(tp->md5sig_info, NULL,
-						  lockdep_sock_is_held(sk)));
+			md5sig = rcu_replace_pointer(tp->md5sig_info, NULL,
+						     lockdep_sock_is_held(sk));
+			kfree_rcu(md5sig, rcu);
+			static_branch_slow_dec_deferred(&tcp_md5_needed);
 		}
 	}
 #endif
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 9f33b07b1481..ad57c4c9eaab 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -50,7 +50,9 @@ static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 	ret = udp_msg_has_data(sk, psock);
 	if (!ret) {
+		release_sock(sk);
 		wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+		lock_sock(sk);
 		ret = udp_msg_has_data(sk, psock);
 	}
 	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
@@ -79,6 +81,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		goto out;
 	}
 
+	lock_sock(sk);
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
@@ -90,11 +93,17 @@ msg_bytes_ready:
 		if (data) {
 			if (psock_has_data(psock))
 				goto msg_bytes_ready;
+
+			release_sock(sk);
+
 			ret = sk_udp_recvmsg(sk, msg, len, flags);
 			goto out;
 		}
 		copied = -EAGAIN;
 	}
+
+	release_sock(sk);
+
 	ret = copied;
 out:
 	sk_psock_put(sk, psock);
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index b1f667c52cb2..3090b4745d47 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -68,11 +68,9 @@ static bool sk_saddr_any(struct sock *sk)
 #endif
 }
 
-void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+void setup_udp_tunnel_sock(struct net *net, struct sock *sk,
 			   struct udp_tunnel_sock_cfg *cfg)
 {
-	struct sock *sk = sock->sk;
-
 	/* Disable multicast loopback */
 	inet_clear_bit(MC_LOOP, sk);
 
@@ -195,9 +193,11 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
 
-void udp_tunnel_sock_release(struct socket *sock)
+void udp_tunnel_sock_release(struct sock *sk)
 {
-	rcu_assign_sk_user_data(sock->sk, NULL);
+	struct socket *sock = sk->sk_socket;
+
+	rcu_assign_sk_user_data(sk, NULL);
 	synchronize_rcu();
 	kernel_sock_shutdown(sock, SHUT_RDWR);
 	sock_release(sock);
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index 9944ed923ddf..3b32a0afa979 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -301,7 +301,7 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)
 static void
 udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
-	if (!utn->need_sync)
+	if (!utn->need_sync || utn->work_pending)
 		return;
 
 	queue_work(udp_tunnel_nic_workqueue, &utn->work);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index c2eac844bcdb..f6f2a8ef3f88 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -76,8 +76,6 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
 		dev_net(dev), NULL, skb, dev, NULL,
 		xfrm4_rcv_encap_finish);
-	if (async)
-		dev_put(dev);
 	return 0;
 }
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c9e5d3e48ab9..defa4277e783 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -913,7 +913,7 @@ static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int
 
 	if (newf)
 		rt6_purge_dflt_routers(net);
-	return 1;
+	return 0;
 }
 
 static void addrconf_linkdown_change(struct net *net, __s32 newf)
@@ -955,11 +955,7 @@ static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int ne
 						     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
-		rtnl_net_unlock(net);
-		return 0;
-	}
-
-	if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) {
+	} else if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) {
 		WRITE_ONCE(net->ipv6.devconf_dflt->ignore_routes_with_linkdown, newf);
 		addrconf_linkdown_change(net, newf);
 		if ((!newf) ^ (!old))
@@ -968,11 +964,21 @@ static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int ne
 						     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
+	} else {
+		if (!newf ^ !old) {
+			struct inet6_dev *idev = table->extra1;
+
+			inet6_netconf_notify_devconf(net,
+						     RTM_NEWNETCONF,
+						     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+						     idev->dev->ifindex,
+						     &idev->cnf);
+		}
 	}
 
 	rtnl_net_unlock(net);
 
-	return 1;
+	return 0;
 }
 
 #endif
@@ -2168,16 +2174,18 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
 	struct net *net = dev_net(idev->dev);
 	int max_addresses;
 
-	if (addrconf_dad_end(ifp)) {
+	spin_lock_bh(&ifp->lock);
+
+	if (ifp->state != INET6_IFADDR_STATE_DAD) {
+		spin_unlock_bh(&ifp->lock);
 		in6_ifa_put(ifp);
 		return;
 	}
+	ifp->state = INET6_IFADDR_STATE_POSTDAD;
 
 	net_info_ratelimited("%s: IPv6 duplicate address %pI6c used by %pM detected!\n",
 			     ifp->idev->dev->name, &ifp->addr, eth_hdr(skb)->h_source);
 
-	spin_lock_bh(&ifp->lock);
-
 	if (ifp->flags & IFA_F_STABLE_PRIVACY) {
 		struct in6_addr new_addr;
 		struct inet6_ifaddr *ifp2;
@@ -2225,6 +2233,11 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
 		in6_ifa_put(ifp2);
 lock_errdad:
 		spin_lock_bh(&ifp->lock);
+		if (ifp->state != INET6_IFADDR_STATE_POSTDAD) {
+			spin_unlock_bh(&ifp->lock);
+			in6_ifa_put(ifp);
+			return;
+		}
 	}
 
 errdad:
@@ -6355,6 +6368,8 @@ static int addrconf_sysctl_forward(const struct ctl_table *ctl, int write,
 	lctl.data = &val;
 
 	ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
 
 	if (write)
 		ret = addrconf_fixup_forwarding(ctl, valp, val);
@@ -6452,6 +6467,8 @@ static int addrconf_sysctl_disable(const struct ctl_table *ctl, int write,
 	lctl.data = &val;
 
 	ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
 
 	if (write)
 		ret = addrconf_disable_ipv6(ctl, valp, val);
@@ -6463,20 +6480,19 @@ static int addrconf_sysctl_disable(const struct ctl_table *ctl, int write,
 static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct net *net = ctl->extra2;
 	int *valp = ctl->data;
-	int ret;
 	int old, new;
+	int ret;
+
+	if (write && !rtnl_net_trylock(net))
+		return restart_syscall();
 
 	old = *valp;
 	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
 	new = *valp;
 
 	if (write && old != new) {
-		struct net *net = ctl->extra2;
-
-		if (!rtnl_net_trylock(net))
-			return restart_syscall();
-
 		if (valp == &net->ipv6.devconf_dflt->proxy_ndp) {
 			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
 						     NETCONFA_PROXY_NEIGH,
@@ -6495,8 +6511,9 @@ static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write,
 						     idev->dev->ifindex,
 						     &idev->cnf);
 		}
-		rtnl_net_unlock(net);
 	}
+	if (write)
+		rtnl_net_unlock(net);
 
 	return ret;
 }
@@ -6654,6 +6671,8 @@ int addrconf_sysctl_ignore_routes_with_linkdown(const struct ctl_table *ctl,
 	lctl.data = &val;
 
 	ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
 
 	if (write)
 		ret = addrconf_fixup_linkdown(ctl, valp, val);
@@ -6748,6 +6767,8 @@ static int addrconf_sysctl_disable_policy(const struct ctl_table *ctl, int write
 	lctl = *ctl;
 	lctl.data = &val;
 	ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
 
 	if (write && (*valp != val))
 		ret = addrconf_disable_policy(ctl, valp, val);
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index b9f6d892a566..cfb2c41634a0 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -35,7 +35,7 @@ struct ioam6_lwt_freq {
 };
 
 struct ioam6_lwt {
-	struct dst_entry null_dst;
+	struct rt6_info null_rt;
 	struct dst_cache cache;
 	struct ioam6_lwt_freq freq;
 	atomic_t pkt_cnt;
@@ -176,7 +176,7 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
 	 * it is stored in the cache. Then, +1/-1 each time we read the cache
 	 * and release it. Long story short, we're fine.
 	 */
-	dst_init(&ilwt->null_dst, NULL, NULL, DST_OBSOLETE_NONE, DST_NOCOUNT);
+	dst_init(&ilwt->null_rt.dst, NULL, NULL, DST_OBSOLETE_NONE, DST_NOCOUNT);
 
 	atomic_set(&ilwt->pkt_cnt, 0);
 	ilwt->freq.k = freq_k;
@@ -360,7 +360,7 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	/* This is how we notify that the destination does not change after
 	 * transformation and that we need to use orig_dst instead of the cache
 	 */
-	if (dst == &ilwt->null_dst) {
+	if (dst == &ilwt->null_rt.dst) {
 		dst_release(dst);
 
 		dst = orig_dst;
@@ -429,7 +429,7 @@ do_encap:
 		local_bh_disable();
 		if (orig_dst->lwtstate == dst->lwtstate)
 			dst_cache_set_ip6(&ilwt->cache,
-					  &ilwt->null_dst, &fl6.saddr);
+					  &ilwt->null_rt.dst, &fl6.saddr);
 		else
 			dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
 		local_bh_enable();
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b897b3c5023b..414fc3c56736 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -637,12 +637,12 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	};
 	const struct nlmsghdr *nlh = cb->nlh;
 	struct net *net = sock_net(skb->sk);
-	unsigned int e = 0, s_e;
 	struct hlist_head *head;
 	struct fib6_walker *w;
 	struct fib6_table *tb;
 	unsigned int h, s_h;
 	int err = 0;
+	u32 s_id;
 
 	rcu_read_lock();
 	if (cb->strict_check) {
@@ -702,23 +702,22 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 
 	s_h = cb->args[0];
-	s_e = cb->args[1];
+	s_id = cb->args[1];
 
-	for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) {
-		e = 0;
+	for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_id = 0) {
 		head = &net->ipv6.fib_table_hash[h];
 		hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
-			if (e < s_e)
-				goto next;
+			if (s_id && tb->tb6_id != s_id)
+				continue;
+
+			s_id = 0;
+			cb->args[1] = tb->tb6_id;
 			err = fib6_dump_table(tb, skb, cb);
 			if (err != 0)
 				goto out;
-next:
-			e++;
 		}
 	}
 out:
-	cb->args[1] = e;
 	cb->args[0] = h;
 
 unlock:
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 365b4059eb20..8ebc99a299c9 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2047,6 +2047,9 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 	struct __ip6_tnl_parm p;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	t = ip6gre_changelink_common(dev, tb, data, &p, extack);
 	if (IS_ERR(t))
 		return PTR_ERR(t);
@@ -2266,6 +2269,9 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct __ip6_tnl_parm p;
 	struct ip6gre_net *ign;
 
+	if (!rtnl_dev_link_net_capable(dev, t->net))
+		return -EPERM;
+
 	ign = net_generic(t->net, ip6gre_net_id);
 	t = ip6gre_changelink_common(dev, tb, data, &p, extack);
 	if (IS_ERR(t))
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9d1037ac082f..95da1f087294 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1850,6 +1850,13 @@ static int ip6_tnl_fill_forward_path(struct net_device_path_ctx *ctx,
 	struct dst_entry *dst;
 	int err;
 
+	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) {
+		/* encaplimit option is currently not supported is
+		 * sw-acceleration path.
+		 */
+		return -EOPNOTSUPP;
+	}
+
 	dst = ip6_route_output(dev_net(ctx->dev), NULL, &fl6);
 	if (!dst->error) {
 		path->type = DEV_PATH_TUN;
@@ -2102,6 +2109,9 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct ip_tunnel_encap ipencap;
 
+	if (!rtnl_dev_link_net_capable(dev, net))
+		return -EPERM;
+
 	if (dev == ip6n->fb_tnl_dev) {
 		if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
 			/* iproute2 always sets TUNNEL_ENCAP_FLAG_CSUM6, so
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index d871cab6938d..ab94b3a4ba9c 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1046,6 +1046,9 @@ static int vti6_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct __ip6_tnl_parm p;
 	struct vti6_net *ip6n;
 
+	if (!rtnl_dev_link_net_capable(dev, net))
+		return -EPERM;
+
 	ip6n = net_generic(net, vti6_net_id);
 	if (dev == ip6n->fb_tnl_dev)
 		return -EINVAL;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index d9b855d5191b..2a5e76a38002 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1080,8 +1080,10 @@ static void mld_gq_start_work(struct inet6_dev *idev)
 	mc_assert_locked(idev);
 
 	idev->mc_gq_running = 1;
-	if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2))
-		in6_dev_hold(idev);
+	if (in6_dev_hold_safe(idev)) {
+		if (mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2))
+			in6_dev_put(idev);
+	}
 }
 
 static void mld_gq_stop_work(struct inet6_dev *idev)
@@ -1099,8 +1101,10 @@ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay)
 
 	mc_assert_locked(idev);
 
-	if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2))
-		in6_dev_hold(idev);
+	if (in6_dev_hold_safe(idev)) {
+		if (mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2))
+			in6_dev_put(idev);
+	}
 }
 
 static void mld_ifc_stop_work(struct inet6_dev *idev)
@@ -1118,8 +1122,10 @@ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay)
 
 	mc_assert_locked(idev);
 
-	if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2))
-		in6_dev_hold(idev);
+	if (in6_dev_hold_safe(idev)) {
+		if (mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2))
+			in6_dev_put(idev);
+	}
 }
 
 static void mld_dad_stop_work(struct inet6_dev *idev)
@@ -1405,18 +1411,23 @@ static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld,
 void igmp6_event_query(struct sk_buff *skb)
 {
 	struct inet6_dev *idev = __in6_dev_get(skb->dev);
+	bool put = false;
 
 	if (!idev || idev->dead)
 		goto out;
 
 	spin_lock_bh(&idev->mc_query_lock);
-	if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) {
+	if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS &&
+	    in6_dev_hold_safe(idev)) {
 		__skb_queue_tail(&idev->mc_query_queue, skb);
-		if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0))
-			in6_dev_hold(idev);
+		if (mod_delayed_work(mld_wq, &idev->mc_query_work, 0))
+			put = true;
 		skb = NULL;
 	}
 	spin_unlock_bh(&idev->mc_query_lock);
+
+	if (put)
+		in6_dev_put(idev);
 out:
 	kfree_skb(skb);
 }
@@ -1573,18 +1584,23 @@ static void mld_query_work(struct work_struct *work)
 void igmp6_event_report(struct sk_buff *skb)
 {
 	struct inet6_dev *idev = __in6_dev_get(skb->dev);
+	bool put = false;
 
 	if (!idev || idev->dead)
 		goto out;
 
 	spin_lock_bh(&idev->mc_report_lock);
-	if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) {
+	if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS &&
+	    in6_dev_hold_safe(idev)) {
 		__skb_queue_tail(&idev->mc_report_queue, skb);
-		if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0))
-			in6_dev_hold(idev);
+		if (mod_delayed_work(mld_wq, &idev->mc_report_work, 0))
+			put = true;
 		skb = NULL;
 	}
 	spin_unlock_bh(&idev->mc_report_lock);
+
+	if (put)
+		in6_dev_put(idev);
 out:
 	kfree_skb(skb);
 }
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e7ad13c5bd26..f867ec8d3d90 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -967,10 +967,8 @@ out:
 	return reason;
 }
 
-static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr)
+static int accept_untracked_na(struct inet6_dev *idev, struct in6_addr *saddr)
 {
-	struct inet6_dev *idev = __in6_dev_get(dev);
-
 	switch (READ_ONCE(idev->cnf.accept_untracked_na)) {
 	case 0: /* Don't accept untracked na (absent in neighbor cache) */
 		return 0;
@@ -980,7 +978,7 @@ static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr)
 		 * same subnet as an address configured on the interface that
 		 * received the na
 		 */
-		return !!ipv6_chk_prefix(saddr, dev);
+		return !!ipv6_chk_prefix(saddr, idev->dev);
 	default:
 		return 0;
 	}
@@ -1078,7 +1076,7 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb)
 	 */
 	new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE;
 	if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) {
-		if (accept_untracked_na(dev, saddr)) {
+		if (accept_untracked_na(idev, saddr)) {
 			neigh = neigh_create(&nd_tbl, &msg->target, dev);
 			new_state = NUD_STALE;
 		}
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d80f85e55fa..a7025ec87035 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -120,7 +120,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	ktime_t tstamp = skb->tstamp;
 	struct ip6_frag_state state;
 	u8 *prevhdr, nexthdr = 0;
-	unsigned int mtu, hlen;
+	unsigned int mtu, hlen, nexthdr_offset;
 	int hroom, err = 0;
 	__be32 frag_id;
 
@@ -129,6 +129,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		goto blackhole;
 	hlen = err;
 	nexthdr = *prevhdr;
+	nexthdr_offset = prevhdr - skb_network_header(skb);
 
 	mtu = skb->dev->mtu;
 	if (frag_max_size > mtu ||
@@ -147,6 +148,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	    (err = skb_checksum_help(skb)))
 		goto blackhole;
 
+	prevhdr = skb_network_header(skb) + nexthdr_offset;
 	hroom = LL_RESERVED_SPACE(skb->dev);
 	if (skb_has_frag_list(skb)) {
 		unsigned int first_len = skb_pagelen(skb);
diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c
index 70da2f2ce064..1258783ed876 100644
--- a/net/ipv6/netfilter/ip6t_ah.c
+++ b/net/ipv6/netfilter/ip6t_ah.c
@@ -56,6 +56,11 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 	}
 
 	hdrlen = ipv6_authlen(ah);
+	if (skb->len - ptr < hdrlen) {
+		/* Packet smaller than its length field */
+		par->hotdrop = true;
+		return false;
+	}
 
 	pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen);
 	pr_debug("RES %04X ", ah->reserved);
diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c
index 450dd53846a2..6d1a5d2026a6 100644
--- a/net/ipv6/netfilter/ip6t_hbh.c
+++ b/net/ipv6/netfilter/ip6t_hbh.c
@@ -75,6 +75,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 	hdrlen = ipv6_optlen(oh);
 	if (skb->len - ptr < hdrlen) {
 		/* Packet smaller than it's length field */
+		par->hotdrop = true;
 		return false;
 	}
 
diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c
index 5561bd9cea81..278b52752f36 100644
--- a/net/ipv6/netfilter/ip6t_rt.c
+++ b/net/ipv6/netfilter/ip6t_rt.c
@@ -56,7 +56,8 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 
 	hdrlen = ipv6_optlen(rh);
 	if (skb->len - ptr < hdrlen) {
-		/* Pcket smaller than its length field */
+		/* Packet smaller than its length field */
+		par->hotdrop = true;
 		return false;
 	}
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 7edca05dbfc9..599c49bf0a0a 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -348,7 +348,8 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0];
 	memmove(skb->head + sizeof(struct frag_hdr), skb->head,
 		(skb->data - skb->head) - sizeof(struct frag_hdr));
-	skb->mac_header += sizeof(struct frag_hdr);
+	if (skb_mac_header_was_set(skb))
+		skb->mac_header += sizeof(struct frag_hdr);
 	skb->network_header += sizeof(struct frag_hdr);
 
 	skb_reset_transport_header(skb);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 636f0120d7e3..88b46967bb67 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3275,11 +3275,11 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 	/*
 	 * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
 	 * corresponding MSS is IPV6_MAXPLEN - tcp_header_size.
-	 * IPV6_MAXPLEN is also valid and means: "any MSS,
-	 * rely only on pmtu discovery"
+	 * Limit the default MSS to GSO_BY_FRAGS - 1 to avoid
+	 * collision with the GSO_BY_FRAGS magic value (0xFFFF).
 	 */
 	if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr))
-		mtu = IPV6_MAXPLEN;
+		mtu = min_t(unsigned int, IPV6_MAXPLEN, GSO_BY_FRAGS - 1);
 	return mtu;
 }
 
@@ -5053,6 +5053,9 @@ static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg)
 		struct inet6_dev *idev = __in6_dev_get(arg->dev);
 		u32 mtu = f6i->fib6_pmtu;
 
+		if (!idev)
+			return 0;
+
 		if (mtu >= arg->mtu ||
 		    (mtu < arg->mtu && mtu == idev->cnf.mtu6))
 			fib6_metric_set(f6i, RTAX_MTU, arg->mtu);
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 1c3ad25700c4..62a7eb779202 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -29,6 +29,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced)
 	int max_last_entry;
 	int trailing;
 
+	if (len < sizeof(*srh))
+		return false;
+
 	if (srh->type != IPV6_SRCRT_TYPE_4)
 		return false;
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b41e231a669b..34db8b886bd2 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1611,6 +1611,9 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 	__u32 fwmark = t->fwmark;
 	int err;
 
+	if (!rtnl_dev_link_net_capable(dev, net))
+		return -EPERM;
+
 	if (dev == sitn->fb_tunnel_dev)
 		return -EINVAL;
 
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 699a001ac166..89d0443b5307 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -71,8 +71,6 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
 		dev_net(dev), NULL, skb, dev, NULL,
 		xfrm6_transport_finish2);
-	if (async)
-		dev_put(dev);
 	return 0;
 }
 
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 3912e75079f5..a998336840c3 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1304,8 +1304,8 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	psock->save_write_space = csk->sk_write_space;
 	psock->save_state_change = csk->sk_state_change;
 	csk->sk_user_data = psock;
-	csk->sk_data_ready = psock_data_ready;
-	csk->sk_write_space = psock_write_space;
+	WRITE_ONCE(csk->sk_data_ready, psock_data_ready);
+	WRITE_ONCE(csk->sk_write_space, psock_write_space);
 	csk->sk_state_change = psock_state_change;
 
 	write_unlock_bh(&csk->sk_callback_lock);
@@ -1381,8 +1381,8 @@ static void kcm_unattach(struct kcm_psock *psock)
 	 */
 	write_lock_bh(&csk->sk_callback_lock);
 	csk->sk_user_data = NULL;
-	csk->sk_data_ready = psock->save_data_ready;
-	csk->sk_write_space = psock->save_write_space;
+	WRITE_ONCE(csk->sk_data_ready, psock->save_data_ready);
+	WRITE_ONCE(csk->sk_write_space, psock->save_write_space);
 	csk->sk_state_change = psock->save_state_change;
 	strp_stop(&psock->strp);
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 9419c8555d22..f940914959b1 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1684,7 +1684,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			.encap_destroy = l2tp_udp_encap_destroy,
 		};
 
-		setup_udp_tunnel_sock(net, sock, &udp_cfg);
+		setup_udp_tunnel_sock(net, sock->sk, &udp_cfg);
 	}
 
 	sk->sk_allocation = GFP_ATOMIC;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 1b210db3119e..f4e20d1218e9 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -317,6 +317,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 	/* assign new connection to its SAP */
 	llc_sap_add_socket(sap, sk);
 	sock_reset_flag(sk, SOCK_ZAPPED);
+	llc_sap_put(sap);
 	rc = 0;
 out:
 	dev_put(dev);
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 5c0ac243b248..b4d732baafb8 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -773,7 +773,6 @@ static struct sock *llc_create_incoming_sock(struct sock *sk,
 	newllc->dev = dev;
 	dev_hold(dev);
 	llc_sap_add_socket(llc->sap, newsk);
-	llc_sap_hold(llc->sap);
 out:
 	return newsk;
 }
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index f47dd58770ad..dba66dd964af 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1599,7 +1599,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		sband = kmemdup(sband, sizeof(*sband), GFP_KERNEL);
 		if (!sband) {
 			result = -ENOMEM;
-			goto fail_rate;
+			goto fail_band;
 		}
 
 		wiphy_dbg(hw->wiphy, "copying sband (band %d) due to VHT EXT NSS BW flag\n",
@@ -1675,6 +1675,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 #endif
 	wiphy_unregister(local->hw.wiphy);
  fail_wiphy_register:
+ fail_band:
 	rtnl_lock();
 	rate_control_deinitialize(local);
 	ieee80211_remove_interfaces(local);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3fb40449c6c5..fe583636d326 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1526,6 +1526,9 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx)
 	if (status->flag & RX_FLAG_DUP_VALIDATED)
 		return RX_CONTINUE;
 
+	if (ieee80211_is_ext(hdr->frame_control))
+		return RX_CONTINUE;
+
 	/*
 	 * Drop duplicate 802.11 retransmissions
 	 * (IEEE 802.11-2012: 9.3.2.10 "Duplicate detection and recovery")
@@ -4487,12 +4490,16 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type);
-	bool multicast = is_multicast_ether_addr(hdr->addr1) ||
-			 ieee80211_is_s1g_beacon(hdr->frame_control);
+	bool multicast;
 	static const u8 nan_network_id[ETH_ALEN] __aligned(2) = {
 		0x51, 0x6F, 0x9A, 0x01, 0x00, 0x00
 	};
 
+	if (ieee80211_is_s1g_beacon(hdr->frame_control))
+		return sdata->vif.type == NL80211_IFTYPE_STATION && bssid;
+
+	multicast = is_multicast_ether_addr(hdr->addr1);
+
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_STATION:
 		if (!bssid && !sdata->u.mgd.use_4addr)
@@ -5174,6 +5181,11 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
 		hdr = (struct ieee80211_hdr *)rx->skb->data;
 	}
 
+	if (ieee80211_is_s1g_beacon(hdr->frame_control)) {
+		ieee80211_invoke_rx_handlers(rx);
+		return true;
+	}
+
 	/* Store a copy of the pre-translated link addresses for SW crypto */
 	if (unlikely(is_unicast_ether_addr(hdr->addr1) &&
 		     !ieee80211_is_data(hdr->frame_control)))
@@ -5263,6 +5275,13 @@ static bool ieee80211_rx_for_interface(struct ieee80211_rx_data *rx,
 	struct sta_info *sta;
 	int link_id = -1;
 
+	if (ieee80211_is_s1g_beacon(hdr->frame_control)) {
+		if (!ieee80211_rx_data_set_sta(rx, NULL, -1))
+			return false;
+
+		return ieee80211_prepare_and_rx_handle(rx, skb, consume);
+	}
+
 	/*
 	 * Look up link station first, in case there's a
 	 * chance that they might have a link address that
@@ -5338,6 +5357,17 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
 			err = -ENOBUFS;
 		else
 			err = skb_linearize(skb);
+	} else if (ieee80211_is_s1g_beacon(fc)) {
+		size_t s1g_hdr_len = offsetof(struct ieee80211_ext,
+					      u.s1g_beacon.variable) +
+				     ieee80211_s1g_optional_len(fc);
+
+		if (skb->len < s1g_hdr_len)
+			err = -ENOBUFS;
+		else
+			err = skb_linearize(skb);
+	} else if (ieee80211_is_ext(fc)) {
+		err = -EINVAL;
 	} else {
 		err = !pskb_may_pull(skb, ieee80211_hdrlen(fc));
 	}
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index ea7f63e1fc17..8e7f43ee10e5 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2597,6 +2597,18 @@ static u16 ieee80211_store_ack_skb(struct ieee80211_local *local,
 	return info_id;
 }
 
+static void ieee80211_remove_ack_skb(struct ieee80211_local *local, u16 info_id)
+{
+	struct sk_buff *ack_skb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&local->ack_status_lock, flags);
+	ack_skb = idr_remove(&local->ack_status_frames, info_id);
+	spin_unlock_irqrestore(&local->ack_status_lock, flags);
+
+	kfree_skb(ack_skb);
+}
+
 /**
  * ieee80211_build_hdr - build 802.11 header in the given frame
  * @sdata: virtual interface to build the header for
@@ -2972,7 +2984,8 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 		if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) {
 			ieee80211_free_txskb(&local->hw, skb);
 			skb = NULL;
-			return ERR_PTR(-ENOMEM);
+			ret = -ENOMEM;
+			goto free;
 		}
 	}
 
@@ -3040,6 +3053,8 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 
 	return skb;
  free:
+	if (info_id)
+		ieee80211_remove_ack_skb(local, info_id);
 	kfree_skb(skb);
 	return ERR_PTR(ret);
 }
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 2529b01e2cd5..5bc719222a87 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -73,6 +73,9 @@ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
 	if (ieee80211_is_s1g_beacon(fc)) {
 		struct ieee80211_ext *ext = (void *) hdr;
 
+		if (len < offsetofend(struct ieee80211_ext, u.s1g_beacon.sa))
+			return NULL;
+
 		return ext->u.s1g_beacon.sa;
 	}
 
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 000be60d9580..b823720630e7 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -703,7 +703,7 @@ void ieee802154_remove_interfaces(struct ieee802154_local *local)
 
 	mutex_lock(&local->iflist_mtx);
 	list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) {
-		list_del(&sdata->list);
+		list_del_rcu(&sdata->list);
 
 		unregister_netdevice(sdata->dev);
 	}
diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c
index 0a31ac8d8415..300d4584533e 100644
--- a/net/mac802154/scan.c
+++ b/net/mac802154/scan.c
@@ -594,6 +594,7 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata,
 			 "Negative ASSOC RESP received from %8phC: %s\n", &ceaddr,
 			 local->assoc_status == IEEE802154_PAN_AT_CAPACITY ?
 			 "PAN at capacity" : "access denied");
+		goto clear_assoc;
 	}
 
 	ret = 0;
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 798c7993635e..bb9b5bed10e1 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -165,6 +165,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		ip_set_init_skbinfo(ext_skbinfo(x, set), ext);
 
 	/* Activate element */
+	smp_mb__before_atomic();
 	set_bit(e->id, map->members);
 	set->elements++;
 
@@ -219,7 +220,7 @@ mtype_list(const struct ip_set *set,
 		cond_resched_rcu();
 		id = cb->args[IPSET_CB_ARG0];
 		x = get_ext(set, map, id);
-		if (!test_bit(id, map->members) ||
+		if (!test_bit_acquire(id, map->members) ||
 		    (SET_WITH_TIMEOUT(set) &&
 #ifdef IP_SET_BITMAP_STORED_TIMEOUT
 		     mtype_is_filled(x) &&
@@ -278,6 +279,7 @@ mtype_gc(struct timer_list *t)
 			x = get_ext(set, map, id);
 			if (ip_set_timeout_expired(ext_timeout(x, set))) {
 				clear_bit(id, map->members);
+				smp_mb__after_atomic();
 				ip_set_ext_destroy(set, x);
 				set->elements--;
 			}
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index 5988b9bb9029..ac7febce074f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -67,7 +67,7 @@ static int
 bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e,
 		  struct bitmap_ip *map, size_t dsize)
 {
-	return !!test_bit(e->id, map->members);
+	return !!test_bit_acquire(e->id, map->members);
 }
 
 static int
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 752f59ef8744..5921fd9d2dca 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -86,7 +86,7 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
 {
 	const struct bitmap_ipmac_elem *elem;
 
-	if (!test_bit(e->id, map->members))
+	if (!test_bit_acquire(e->id, map->members))
 		return 0;
 	elem = get_const_elem(map->extensions, e->id, dsize);
 	if (e->add_mac && elem->filled == MAC_FILLED)
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 7138e080def4..ca875c982424 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -58,7 +58,7 @@ static int
 bitmap_port_do_test(const struct bitmap_port_adt_elem *e,
 		    const struct bitmap_port *map, size_t dsize)
 {
-	return !!test_bit(e->id, map->members);
+	return !!test_bit_acquire(e->id, map->members);
 }
 
 static int
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 955556513eeb..6cfad152d7d1 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -351,8 +351,8 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
 
 	if (unlikely(c)) {
 		set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
-		kfree_rcu(c, rcu);
 		rcu_assign_pointer(comment->c, NULL);
+		kfree_rcu(c, rcu);
 	}
 	if (!len)
 		return;
@@ -393,8 +393,8 @@ ip_set_comment_free(struct ip_set *set, void *ptr)
 	if (unlikely(!c))
 		return;
 	set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
-	kfree_rcu(c, rcu);
 	rcu_assign_pointer(comment->c, NULL);
+	kfree_rcu(c, rcu);
 }
 
 typedef void (*destroyer)(struct ip_set *, void *);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 04e4627ddfc1..dedf59b661dd 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -606,7 +606,7 @@ mtype_cancel_gc(struct ip_set *set)
 	struct htype *h = set->data;
 
 	if (SET_WITH_TIMEOUT(set))
-		cancel_delayed_work_sync(&h->gc.dwork);
+		disable_delayed_work_sync(&h->gc.dwork);
 }
 
 static int
@@ -689,7 +689,7 @@ retry:
 				continue;
 			pos = smp_load_acquire(&n->pos);
 			for (j = 0; j < pos; j++) {
-				if (!test_bit(j, n->used))
+				if (!test_bit_acquire(j, n->used))
 					continue;
 				data = ahash_data(n, j, dsize);
 				if (SET_ELEM_EXPIRED(set, data))
@@ -826,7 +826,7 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size)
 				continue;
 			pos = smp_load_acquire(&n->pos);
 			for (j = 0; j < pos; j++) {
-				if (!test_bit(j, n->used))
+				if (!test_bit_acquire(j, n->used))
 					continue;
 				data = ahash_data(n, j, set->dsize);
 				if (!SET_ELEM_EXPIRED(set, data))
@@ -1201,7 +1201,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
 			continue;
 		pos = smp_load_acquire(&n->pos);
 		for (i = 0; i < pos; i++) {
-			if (!test_bit(i, n->used))
+			if (!test_bit_acquire(i, n->used))
 				continue;
 			data = ahash_data(n, i, set->dsize);
 			if (!mtype_data_equal(data, d, &multi))
@@ -1259,7 +1259,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	}
 	pos = smp_load_acquire(&n->pos);
 	for (i = 0; i < pos; i++) {
-		if (!test_bit(i, n->used))
+		if (!test_bit_acquire(i, n->used))
 			continue;
 		data = ahash_data(n, i, set->dsize);
 		if (!mtype_data_equal(data, d, &multi))
@@ -1396,7 +1396,7 @@ mtype_list(const struct ip_set *set,
 			continue;
 		pos = smp_load_acquire(&n->pos);
 		for (i = 0; i < pos; i++) {
-			if (!test_bit(i, n->used))
+			if (!test_bit_acquire(i, n->used))
 				continue;
 			e = ahash_data(n, i, set->dsize);
 			if (SET_ELEM_EXPIRED(set, e))
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index d54d7da58334..b0e00be85cb1 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -361,14 +361,13 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
 				  struct ip_vs_iphdr *ipvsh)
 {
 	int diff;
-	const unsigned int tcp_offset = ip_hdrlen(skb);
 	struct tcphdr *th;
 	__u32 seq;
 
-	if (skb_ensure_writable(skb, tcp_offset + sizeof(*th)))
+	if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th)))
 		return 0;
 
-	th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset);
+	th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len);
 
 	/*
 	 *	Remember seq number in case this pkt gets resized
@@ -438,14 +437,13 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
 				 struct ip_vs_iphdr *ipvsh)
 {
 	int diff;
-	const unsigned int tcp_offset = ip_hdrlen(skb);
 	struct tcphdr *th;
 	__u32 seq;
 
-	if (skb_ensure_writable(skb, tcp_offset + sizeof(*th)))
+	if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th)))
 		return 0;
 
-	th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset);
+	th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len);
 
 	/*
 	 *	Remember seq number in case this pkt gets resized
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 9ea6b4fa78bf..b457dd2f6bc8 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1411,8 +1411,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 	cp->app = NULL;
 	cp->app_data = NULL;
 	/* reset struct ip_vs_seq */
-	cp->in_seq.delta = 0;
-	cp->out_seq.delta = 0;
+	memset(&cp->in_seq, 0, sizeof(cp->in_seq));
+	memset(&cp->out_seq, 0, sizeof(cp->out_seq));
 
 	atomic_inc(&ipvs->conn_count);
 	if (unlikely(flags & IP_VS_CONN_F_NO_CPORT)) {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d40b404c1bf6..bafab93451d0 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -398,10 +398,10 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 static inline void
 ip_vs_set_state(struct ip_vs_conn *cp, int direction,
 		const struct sk_buff *skb,
-		struct ip_vs_proto_data *pd)
+		struct ip_vs_proto_data *pd, unsigned int iph_len)
 {
 	if (likely(pd->pp->state_transition))
-		pd->pp->state_transition(cp, direction, skb, pd);
+		pd->pp->state_transition(cp, direction, skb, pd, iph_len);
 }
 
 static inline int
@@ -803,7 +803,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_in_stats(cp, skb);
 
 		/* set state */
-		ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
+		ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph->len);
 
 		/* transmit the first SYN packet */
 		ret = cp->packet_xmit(skb, cp, pd->pp, iph);
@@ -1219,8 +1219,7 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
 	snet.in6 = ciph.saddr.in6;
 	offset = ciph.len;
 	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
-				    pp, offset, sizeof(struct ipv6hdr),
-				    hooknum);
+				    pp, offset, ipvsh->len, hooknum);
 }
 #endif
 
@@ -1484,7 +1483,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 
 after_nat:
 	ip_vs_out_stats(cp, skb);
-	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
+	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd, iph->len);
 	skb->ipvs_property = 1;
 	if (!(cp->flags & IP_VS_CONN_F_NFCT))
 		ip_vs_notrack(skb);
@@ -1767,6 +1766,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	bool tunnel, new_cp = false;
 	union nf_inet_addr *raddr;
 	char *outer_proto = "IPIP";
+	unsigned int hlen_ipip;
+	int ulen = 0;
 
 	*related = 1;
 
@@ -1803,9 +1804,10 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	/* Now find the contained IP header */
 	offset += sizeof(_icmph);
 	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
-	if (cih == NULL)
+	if (!(cih && cih->version == 4 && cih->ihl >= 5))
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 	raddr = (union nf_inet_addr *)&cih->daddr;
+	hlen_ipip = cih->ihl * 4;
 
 	/* Special case for errors for IPIP/UDP/GRE tunnel packets */
 	tunnel = false;
@@ -1821,9 +1823,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 		/* Only for known tunnel */
 		if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP)
 			return NF_ACCEPT;
-		offset += cih->ihl * 4;
+		offset += hlen_ipip;
 		cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
-		if (cih == NULL)
+		if (!(cih && cih->version == 4 && cih->ihl >= 5))
 			return NF_ACCEPT; /* The packet looks wrong, ignore */
 		tunnel = true;
 	} else if ((cih->protocol == IPPROTO_UDP ||	/* Can be UDP encap */
@@ -1831,12 +1833,11 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 		   /* Error for our tunnel must arrive at LOCAL_IN */
 		   (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) {
 		__u8 iproto;
-		int ulen;
 
 		/* Non-first fragment has no UDP/GRE header */
 		if (unlikely(cih->frag_off & htons(IP_OFFSET)))
 			return NF_ACCEPT;
-		offset2 = offset + cih->ihl * 4;
+		offset2 = offset + hlen_ipip;
 		if (cih->protocol == IPPROTO_UDP) {
 			ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET,
 					      raddr, &iproto);
@@ -1905,6 +1906,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	}
 
 	if (tunnel) {
+		unsigned int hlen_orig = cih->ihl * 4;
 		__be32 info = ic->un.gateway;
 		__u8 type = ic->type;
 		__u8 code = ic->code;
@@ -1921,6 +1923,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 				goto ignore_tunnel;
 			offset2 -= ihl + sizeof(_icmph);
 			skb_reset_network_header(skb);
+			/* Ensure the IP header is present in headroom */
+			if (!pskb_may_pull(skb, hlen_ipip))
+				goto ignore_tunnel;
 			IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n",
 				  outer_proto, &ip_hdr(skb)->saddr,
 				  &ip_hdr(skb)->daddr, mtu);
@@ -1936,8 +1941,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 				if (dest_dst)
 					mtu = dst_mtu(dest_dst->dst_cache);
 			}
-			if (mtu > 68 + sizeof(struct iphdr))
-				mtu -= sizeof(struct iphdr);
+			if (mtu > 68 + hlen_ipip + ulen)
+				mtu -= hlen_ipip + ulen;
 			info = htonl(mtu);
 		}
 		/* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of
@@ -1946,6 +1951,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 		if (pskb_pull(skb, offset2) == NULL)
 			goto ignore_tunnel;
 		skb_reset_network_header(skb);
+		/* Ensure the IP header is present in headroom */
+		if (!pskb_may_pull(skb, hlen_orig))
+			goto ignore_tunnel;
 		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
 			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
 			type, code, ntohl(info));
@@ -2233,7 +2241,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 	IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet");
 
 	ip_vs_in_stats(cp, skb);
-	ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
+	ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph.len);
 	if (cp->packet_xmit)
 		ret = cp->packet_xmit(skb, cp, pp, &iph);
 		/* do not touch skb anymore */
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 63c78a1f3918..c67317be17df 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -372,20 +372,15 @@ static const char *sctp_state_name(int state)
 
 static inline void
 set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
-		int direction, const struct sk_buff *skb)
+		int direction, const struct sk_buff *skb,
+		unsigned int iph_len)
 {
 	struct sctp_chunkhdr _sctpch, *sch;
 	unsigned char chunk_type;
 	int event, next_state;
-	int ihl, cofs;
+	int cofs;
 
-#ifdef CONFIG_IP_VS_IPV6
-	ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
-#else
-	ihl = ip_hdrlen(skb);
-#endif
-
-	cofs = ihl + sizeof(struct sctphdr);
+	cofs = iph_len + sizeof(struct sctphdr);
 	sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch);
 	if (sch == NULL)
 		return;
@@ -468,10 +463,11 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 
 static void
 sctp_state_transition(struct ip_vs_conn *cp, int direction,
-		const struct sk_buff *skb, struct ip_vs_proto_data *pd)
+		const struct sk_buff *skb, struct ip_vs_proto_data *pd,
+		unsigned int iph_len)
 {
 	spin_lock_bh(&cp->lock);
-	set_sctp_state(pd, cp, direction, skb);
+	set_sctp_state(pd, cp, direction, skb, iph_len);
 	spin_unlock_bh(&cp->lock);
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 8cc0a8ce6241..f86b763efcc4 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -579,17 +579,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 static void
 tcp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
-		     struct ip_vs_proto_data *pd)
+		     struct ip_vs_proto_data *pd,
+		     unsigned int iph_len)
 {
 	struct tcphdr _tcph, *th;
 
-#ifdef CONFIG_IP_VS_IPV6
-	int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
-#else
-	int ihl = ip_hdrlen(skb);
-#endif
-
-	th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph);
+	th = skb_header_pointer(skb, iph_len, sizeof(_tcph), &_tcph);
 	if (th == NULL)
 		return;
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index f9de632e38cd..58f9e255927e 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -444,7 +444,8 @@ static const char * udp_state_name(int state)
 static void
 udp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
-		     struct ip_vs_proto_data *pd)
+		     struct ip_vs_proto_data *pd,
+		     unsigned int iph_len)
 {
 	if (unlikely(!pd)) {
 		pr_err("UDP no ns data\n");
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index ce542ed4b013..9fef4335da13 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -736,13 +736,11 @@ int
 ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
-	struct iphdr  *iph = ip_hdr(skb);
-
-	if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, iph->daddr,
+	if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, ip_hdr(skb)->daddr,
 			       IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0)
 		goto tx_error;
 
-	ip_send_check(iph);
+	ip_send_check(ip_hdr(skb));
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 00eed5b4d1b1..495c4a779d22 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -179,17 +179,16 @@ static int __nf_conncount_add(struct net *net,
 		return -ENOENT;
 
 	if (ct && nf_ct_is_confirmed(ct)) {
-		/* local connections are confirmed in postrouting so confirmation
-		 * might have happened before hitting connlimit
+		/* Connection is confirmed but might still be in the setup phase.
+		 * Only skip the tracking if it is fully assured. This guarantees
+		 * that setup packets or retransmissions are properly counted and
+		 * deduplicated.
 		 */
-		if (skb->skb_iif != LOOPBACK_IFINDEX) {
+		if (test_bit(IPS_ASSURED_BIT, &ct->status)) {
 			err = -EEXIST;
 			goto out_put;
 		}
 
-		/* this is likely a local connection, skip optimization to avoid
-		 * adding duplicates from a 'packet train'
-		 */
 		goto check_connections;
 	}
 
@@ -208,8 +207,8 @@ check_connections:
 			/* Not found, but might be about to be confirmed */
 			if (PTR_ERR(found) == -EAGAIN) {
 				if (nf_ct_tuple_equal(&conn->tuple, &tuple) &&
-				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
-				    nf_ct_zone_id(zone, zone->dir))
+				    nf_ct_zone_id(&conn->zone, IP_CT_DIR_ORIGINAL) ==
+				    nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL))
 					goto out_put; /* already exists */
 			} else {
 				collect++;
@@ -220,7 +219,7 @@ check_connections:
 		found_ct = nf_ct_tuplehash_to_ctrack(found);
 
 		if (nf_ct_tuple_equal(&conn->tuple, &tuple) &&
-		    nf_ct_zone_equal(found_ct, zone, zone->dir)) {
+		    nf_ct_zone_equal(found_ct, zone, IP_CT_DIR_ORIGINAL)) {
 			/*
 			 * We should not see tuples twice unless someone hooks
 			 * this into a table without "-p tcp --syn".
@@ -499,7 +498,7 @@ count_tree(struct net *net,
 	hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
 	root = &data->root[hash];
 
-	parent = rcu_dereference_raw(root->rb_node);
+	parent = rcu_dereference(root->rb_node);
 	while (parent) {
 		int diff;
 
@@ -507,9 +506,9 @@ count_tree(struct net *net,
 
 		diff = key_diff(key, rbconn->key, data->keylen);
 		if (diff < 0) {
-			parent = rcu_dereference_raw(parent->rb_left);
+			parent = rcu_dereference(parent->rb_left);
 		} else if (diff > 0) {
-			parent = rcu_dereference_raw(parent->rb_right);
+			parent = rcu_dereference(parent->rb_right);
 		} else {
 			int ret;
 
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index d2c09e8dd872..ddafbdfc96dc 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -169,35 +169,15 @@ static const struct nf_conntrack_expect_policy amanda_exp_policy = {
 	.timeout		= 180,
 };
 
-static struct nf_conntrack_helper amanda_helper[2] __read_mostly = {
-	{
-		.name			= HELPER_NAME,
-		.me			= THIS_MODULE,
-		.help			= amanda_help,
-		.tuple.src.l3num	= AF_INET,
-		.tuple.src.u.udp.port	= cpu_to_be16(10080),
-		.tuple.dst.protonum	= IPPROTO_UDP,
-		.expect_policy		= &amanda_exp_policy,
-		.nat_mod_name		= NF_NAT_HELPER_NAME(HELPER_NAME),
-	},
-	{
-		.name			= "amanda",
-		.me			= THIS_MODULE,
-		.help			= amanda_help,
-		.tuple.src.l3num	= AF_INET6,
-		.tuple.src.u.udp.port	= cpu_to_be16(10080),
-		.tuple.dst.protonum	= IPPROTO_UDP,
-		.expect_policy		= &amanda_exp_policy,
-		.nat_mod_name		= NF_NAT_HELPER_NAME(HELPER_NAME),
-	},
-};
+static struct nf_conntrack_helper amanda_helper[2] __read_mostly;
+static struct nf_conntrack_helper *amanda_helper_ptr[2] __read_mostly;
 
 static void __exit nf_conntrack_amanda_fini(void)
 {
 	int i;
 
-	nf_conntrack_helpers_unregister(amanda_helper,
-					ARRAY_SIZE(amanda_helper));
+	nf_conntrack_helpers_unregister(amanda_helper_ptr,
+					ARRAY_SIZE(amanda_helper_ptr));
 	for (i = 0; i < ARRAY_SIZE(search); i++)
 		textsearch_destroy(search[i].ts);
 }
@@ -217,8 +197,17 @@ static int __init nf_conntrack_amanda_init(void)
 			goto err1;
 		}
 	}
+
+	nf_ct_helper_init(&amanda_helper[0], AF_INET, IPPROTO_UDP,
+			  HELPER_NAME, 10080, 10080, 10080,
+			  &amanda_exp_policy, 0, amanda_help, NULL, THIS_MODULE);
+	nf_ct_helper_init(&amanda_helper[1], AF_INET6, IPPROTO_UDP,
+			  HELPER_NAME, 10080, 10080, 10080,
+			  &amanda_exp_policy, 0, amanda_help, NULL, THIS_MODULE);
+
 	ret = nf_conntrack_helpers_register(amanda_helper,
-					    ARRAY_SIZE(amanda_helper));
+					    ARRAY_SIZE(amanda_helper),
+					    amanda_helper_ptr);
 	if (ret < 0)
 		goto err1;
 	return 0;
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index 40c261cd0af3..f98d1d4b42c3 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -65,6 +65,15 @@ enum {
 	NF_BPF_CT_OPTS_SZ = 16,
 };
 
+static void *bpf_ct_opts_result(struct bpf_ct_opts *opts, u32 opts__sz, void *ret)
+{
+	if (!IS_ERR(ret))
+		return ret;
+	if (opts__sz >= offsetofend(struct bpf_ct_opts, error))
+		opts->error = PTR_ERR(ret);
+	return NULL;
+}
+
 static int bpf_nf_ct_tuple_parse(struct bpf_sock_tuple *bpf_tuple,
 				 u32 tuple_len, u8 protonum, u8 dir,
 				 struct nf_conntrack_tuple *tuple)
@@ -297,12 +306,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
 
 	nfct = __bpf_nf_ct_alloc_entry(dev_net(ctx->rxq->dev), bpf_tuple, tuple__sz,
 				       opts, opts__sz, 10);
-	if (IS_ERR(nfct)) {
-		opts->error = PTR_ERR(nfct);
-		return NULL;
-	}
-
-	return (struct nf_conn___init *)nfct;
+	return (struct nf_conn___init *)bpf_ct_opts_result(opts, opts__sz, nfct);
 }
 
 /* bpf_xdp_ct_lookup - Lookup CT entry for the given tuple, and acquire a
@@ -331,11 +335,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
 
 	caller_net = dev_net(ctx->rxq->dev);
 	nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts, opts__sz);
-	if (IS_ERR(nfct)) {
-		opts->error = PTR_ERR(nfct);
-		return NULL;
-	}
-	return nfct;
+	return bpf_ct_opts_result(opts, opts__sz, nfct);
 }
 
 /* bpf_skb_ct_alloc - Allocate a new CT entry
@@ -363,12 +363,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
 
 	net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk);
 	nfct = __bpf_nf_ct_alloc_entry(net, bpf_tuple, tuple__sz, opts, opts__sz, 10);
-	if (IS_ERR(nfct)) {
-		opts->error = PTR_ERR(nfct);
-		return NULL;
-	}
-
-	return (struct nf_conn___init *)nfct;
+	return (struct nf_conn___init *)bpf_ct_opts_result(opts, opts__sz, nfct);
 }
 
 /* bpf_skb_ct_lookup - Lookup CT entry for the given tuple, and acquire a
@@ -397,11 +392,7 @@ bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
 
 	caller_net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk);
 	nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts, opts__sz);
-	if (IS_ERR(nfct)) {
-		opts->error = PTR_ERR(nfct);
-		return NULL;
-	}
-	return nfct;
+	return bpf_ct_opts_result(opts, opts__sz, nfct);
 }
 
 /* bpf_ct_insert_entry - Add the provided entry into a CT map
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index 75e53fde6b29..bf78828c7549 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -29,6 +29,9 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 	struct nf_conn_help *help = nfct_help(ct);
 	__be32 mask = 0;
 
+	if (!help)
+		goto out;
+
 	/* we're only interested in locally generated packets */
 	if (skb->sk == NULL || !net_eq(nf_ct_net(ct), sock_net(skb->sk)))
 		goto out;
@@ -59,6 +62,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 	if (exp == NULL)
 		goto out;
 
+	exp->master_tuple	  = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
 	exp->tuple                = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
 
 	helper = rcu_dereference(help->helper);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index b521b5ebd664..1f7b0d5a55ec 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -562,9 +562,23 @@ static void destroy_gre_conntrack(struct nf_conn *ct)
 {
 #ifdef CONFIG_NF_CT_PROTO_GRE
 	struct nf_conn *master = ct->master;
+	struct nf_conn_help *help;
+
+	if (!master)
+		return;
+
+	help = nfct_help(master);
+	if (help) {
+		struct nf_conntrack_helper *helper;
 
-	if (master)
-		nf_ct_gre_keymap_destroy(master);
+		rcu_read_lock();
+		helper = rcu_dereference(help->helper);
+		/* Only pptp helper has a destroy callback. */
+		if (helper && helper->destroy)
+			nf_ct_gre_keymap_destroy(master);
+
+		rcu_read_unlock();
+	}
 #endif
 }
 
@@ -840,33 +854,6 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct,
 			   &nf_conntrack_hash[reply_hash]);
 }
 
-static bool nf_ct_ext_valid_pre(const struct nf_ct_ext *ext)
-{
-	/* if ext->gen_id is not equal to nf_conntrack_ext_genid, some extensions
-	 * may contain stale pointers to e.g. helper that has been removed.
-	 *
-	 * The helper can't clear this because the nf_conn object isn't in
-	 * any hash and synchronize_rcu() isn't enough because associated skb
-	 * might sit in a queue.
-	 */
-	return !ext || ext->gen_id == atomic_read(&nf_conntrack_ext_genid);
-}
-
-static bool nf_ct_ext_valid_post(struct nf_ct_ext *ext)
-{
-	if (!ext)
-		return true;
-
-	if (ext->gen_id != atomic_read(&nf_conntrack_ext_genid))
-		return false;
-
-	/* inserted into conntrack table, nf_ct_iterate_cleanup()
-	 * will find it.  Disable nf_ct_ext_find() id check.
-	 */
-	WRITE_ONCE(ext->gen_id, 0);
-	return true;
-}
-
 int
 nf_conntrack_hash_check_insert(struct nf_conn *ct)
 {
@@ -882,9 +869,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 
 	zone = nf_ct_zone(ct);
 
-	if (!nf_ct_ext_valid_pre(ct->ext))
-		return -EAGAIN;
-
 	local_bh_disable();
 	do {
 		sequence = read_seqcount_begin(&nf_conntrack_generation);
@@ -918,18 +902,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 			goto chaintoolong;
 	}
 
-	/* If genid has changed, we can't insert anymore because ct
-	 * extensions could have stale pointers and nf_ct_iterate_destroy
-	 * might have completed its table scan already.
-	 *
-	 * Increment of the ext genid right after this check is fine:
-	 * nf_ct_iterate_destroy blocks until locks are released.
-	 */
-	if (!nf_ct_ext_valid_post(ct->ext)) {
-		err = -EAGAIN;
-		goto out;
-	}
-
 	smp_wmb();
 	/* The caller holds a reference to this object */
 	refcount_set(&ct->ct_general.use, 2);
@@ -1257,11 +1229,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		return NF_DROP;
 	}
 
-	if (!nf_ct_ext_valid_pre(ct->ext)) {
-		NF_CT_STAT_INC(net, insert_failed);
-		goto dying;
-	}
-
 	/* We have to check the DYING flag after unlink to prevent
 	 * a race against nf_ct_get_next_corpse() possibly called from
 	 * user context, else we insert an already 'dead' hash, blocking
@@ -1324,16 +1291,6 @@ chaintoolong:
 	nf_conntrack_double_unlock(hash, reply_hash);
 	local_bh_enable();
 
-	/* ext area is still valid (rcu read lock is held,
-	 * but will go out of scope soon, we need to remove
-	 * this conntrack again.
-	 */
-	if (!nf_ct_ext_valid_post(ct->ext)) {
-		nf_ct_kill(ct);
-		NF_CT_STAT_INC_ATOMIC(net, drop);
-		return NF_DROP;
-	}
-
 	help = nfct_help(ct);
 	if (help && help->helper)
 		nf_conntrack_event_cache(IPCT_HELPER, ct);
@@ -1514,6 +1471,31 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
 	return false;
 }
 
+static void nf_ct_help_gc(struct nf_conn *ct)
+{
+	struct nf_conn_help *help;
+
+	if (!refcount_inc_not_zero(&ct->ct_general.use))
+		return;
+
+	/* load ->status after refcount increase */
+	smp_acquire__after_ctrl_dep();
+
+	if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct)) {
+		nf_ct_put(ct);
+		return;
+	}
+
+	/* re-check helper due to SLAB_TYPESAFE_BY_RCU */
+	if (test_bit(IPS_HELPER_BIT, &ct->status)) {
+		help = nfct_help(ct);
+		if (help)
+			nf_ct_expectation_gc(help);
+	}
+
+	nf_ct_put(ct);
+}
+
 static void gc_worker(struct work_struct *work)
 {
 	unsigned int i, hashsz, nf_conntrack_max95 = 0;
@@ -1586,7 +1568,13 @@ static void gc_worker(struct work_struct *work)
 			expires = (expires - (long)next_run) / ++count;
 			next_run += expires;
 
-			if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
+			if (gc_worker_skip_ct(tmp))
+				continue;
+
+			if (test_bit(IPS_HELPER_BIT, &tmp->status))
+				nf_ct_help_gc(tmp);
+
+			if (nf_conntrack_max95 == 0)
 				continue;
 
 			net = nf_ct_net(tmp);
@@ -1737,16 +1725,18 @@ void nf_conntrack_free(struct nf_conn *ct)
 	 */
 	WARN_ON(refcount_read(&ct->ct_general.use) != 0);
 
+	rcu_read_lock();
 	if (ct->status & IPS_SRC_NAT_DONE) {
 		const struct nf_nat_hook *nat_hook;
 
-		rcu_read_lock();
 		nat_hook = rcu_dereference(nf_nat_hook);
 		if (nat_hook)
 			nat_hook->remove_nat_bysrc(ct);
-		rcu_read_unlock();
 	}
 
+	nf_ct_timeout_put(ct);
+	rcu_read_unlock();
+
 	kfree(ct->ext);
 	kmem_cache_free(nf_conntrack_cachep, ct);
 	cnet = nf_ct_pernet(net);
@@ -2213,6 +2203,7 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct,
 {
 	const struct nf_conntrack_helper *helper;
 	const struct nf_conn_help *help;
+	unsigned int helper_flags;
 	int protoff;
 
 	help = nfct_help(ct);
@@ -2223,7 +2214,8 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct,
 	if (!helper)
 		return NF_ACCEPT;
 
-	if (!(helper->flags & NF_CT_HELPER_F_USERSPACE))
+	helper_flags = READ_ONCE(helper->flags);
+	if (!(helper_flags & NF_CT_HELPER_F_USERSPACE))
 		return NF_ACCEPT;
 
 	switch (nf_ct_l3num(ct)) {
@@ -2436,13 +2428,11 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data)
 	 */
 	synchronize_net();
 
-	nf_ct_ext_bump_genid();
 	iter_data.data = data;
 	nf_ct_iterate_cleanup(iter, &iter_data);
 
 	/* Another cpu might be in a rcu read section with
-	 * rcu protected pointer cleared in iter callback
-	 * or hidden via nf_ct_ext_bump_genid() above.
+	 * rcu protected pointer cleared in iter callback.
 	 *
 	 * Wait until those are done.
 	 */
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index 9df159448b89..cc8d8e85169f 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -77,7 +77,7 @@ next:
 		hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
 		hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &evicted_list);
 
-		if (time_after(stop, jiffies)) {
+		if (time_after(jiffies, stop)) {
 			ret = STATE_RESTART;
 			break;
 		}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 8e943efbdf0a..38630c5e006f 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -43,6 +43,24 @@ unsigned int nf_ct_expect_max __read_mostly;
 static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
 static siphash_aligned_key_t nf_ct_expect_hashrnd;
 
+void nf_ct_expectation_gc(struct nf_conn_help *master_help)
+{
+	struct nf_conntrack_expect *exp;
+	struct hlist_node *next;
+
+	if (hlist_empty(&master_help->expectations))
+		return;
+
+	spin_lock_bh(&nf_conntrack_expect_lock);
+	hlist_for_each_entry_safe(exp, next, &master_help->expectations, lnode) {
+		if (!nf_ct_exp_is_expired(exp))
+			continue;
+
+		nf_ct_unlink_expect(exp);
+	}
+	spin_unlock_bh(&nf_conntrack_expect_lock);
+}
+
 /* nf_conntrack_expect helper functions */
 void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 				u32 portid, int report)
@@ -52,8 +70,6 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 	struct nf_conntrack_net *cnet;
 
 	lockdep_nfct_expect_lock_held();
-	WARN_ON(!master_help);
-	WARN_ON(timer_pending(&exp->timeout));
 
 	hlist_del_rcu(&exp->hnode);
 
@@ -61,7 +77,8 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 	cnet->expect_count--;
 
 	hlist_del_rcu(&exp->lnode);
-	master_help->expecting[exp->class]--;
+	if (master_help)
+		master_help->expecting[exp->class]--;
 
 	nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
 	nf_ct_expect_put(exp);
@@ -70,16 +87,6 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 }
 EXPORT_SYMBOL_GPL(nf_ct_unlink_expect_report);
 
-static void nf_ct_expectation_timed_out(struct timer_list *t)
-{
-	struct nf_conntrack_expect *exp = timer_container_of(exp, t, timeout);
-
-	spin_lock_bh(&nf_conntrack_expect_lock);
-	nf_ct_unlink_expect(exp);
-	spin_unlock_bh(&nf_conntrack_expect_lock);
-	nf_ct_expect_put(exp);
-}
-
 static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple)
 {
 	struct {
@@ -117,19 +124,6 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
 	       nf_ct_exp_zone_equal_any(i, zone);
 }
 
-bool nf_ct_remove_expect(struct nf_conntrack_expect *exp)
-{
-	lockdep_nfct_expect_lock_held();
-
-	if (timer_delete(&exp->timeout)) {
-		nf_ct_unlink_expect(exp);
-		nf_ct_expect_put(exp);
-		return true;
-	}
-	return false;
-}
-EXPORT_SYMBOL_GPL(nf_ct_remove_expect);
-
 struct nf_conntrack_expect *
 __nf_ct_expect_find(struct net *net,
 		    const struct nf_conntrack_zone *zone,
@@ -144,6 +138,8 @@ __nf_ct_expect_find(struct net *net,
 
 	h = nf_ct_expect_dst_hash(net, tuple);
 	hlist_for_each_entry_rcu(i, &nf_ct_expect_hash[h], hnode) {
+		if (nf_ct_exp_is_expired(i))
+			continue;
 		if (nf_ct_exp_equal(tuple, i, zone, net))
 			return i;
 	}
@@ -178,6 +174,7 @@ nf_ct_find_expectation(struct net *net,
 {
 	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_conntrack_expect *i, *exp = NULL;
+	struct hlist_node *next;
 	unsigned int h;
 
 	lockdep_nfct_expect_lock_held();
@@ -186,7 +183,11 @@ nf_ct_find_expectation(struct net *net,
 		return NULL;
 
 	h = nf_ct_expect_dst_hash(net, tuple);
-	hlist_for_each_entry(i, &nf_ct_expect_hash[h], hnode) {
+	hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
+		if (nf_ct_exp_is_expired(i)) {
+			nf_ct_unlink_expect(i);
+			continue;
+		}
 		if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
 		    nf_ct_exp_equal(tuple, i, zone, net)) {
 			exp = i;
@@ -196,13 +197,16 @@ nf_ct_find_expectation(struct net *net,
 	if (!exp)
 		return NULL;
 
+	if (!refcount_inc_not_zero(&exp->use))
+		return NULL;
+
 	/* If master is not in hash table yet (ie. packet hasn't left
 	   this machine yet), how can other end know about expected?
 	   Hence these are not the droids you are looking for (if
 	   master ct never got confirmed, we'd hold a reference to it
 	   and weird things would happen to future packets). */
 	if (!nf_ct_is_confirmed(exp->master))
-		return NULL;
+		goto err_release_exp;
 
 	/* Avoid race with other CPUs, that for exp->master ct, is
 	 * about to invoke ->destroy(), or nf_ct_delete() via timeout
@@ -214,18 +218,17 @@ nf_ct_find_expectation(struct net *net,
 	 */
 	if (unlikely(nf_ct_is_dying(exp->master) ||
 		     !refcount_inc_not_zero(&exp->master->ct_general.use)))
-		return NULL;
+		goto err_release_exp;
 
-	if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink) {
-		refcount_inc(&exp->use);
+	if (exp->flags & NF_CT_EXPECT_PERMANENT || !unlink)
 		return exp;
-	} else if (timer_delete(&exp->timeout)) {
-		nf_ct_unlink_expect(exp);
-		return exp;
-	}
-	/* Undo exp->master refcnt increase, if timer_delete() failed */
-	nf_ct_put(exp->master);
 
+	nf_ct_unlink_expect(exp);
+
+	return exp;
+
+err_release_exp:
+	nf_ct_expect_put(exp);
 	return NULL;
 }
 
@@ -241,9 +244,8 @@ void nf_ct_remove_expectations(struct nf_conn *ct)
 		return;
 
 	spin_lock_bh(&nf_conntrack_expect_lock);
-	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
-		nf_ct_remove_expect(exp);
-	}
+	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode)
+		nf_ct_unlink_expect(exp);
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_remove_expectations);
@@ -292,7 +294,7 @@ static bool master_matches(const struct nf_conntrack_expect *a,
 void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
 {
 	spin_lock_bh(&nf_conntrack_expect_lock);
-	nf_ct_remove_expect(exp);
+	WRITE_ONCE(exp->flags, exp->flags | NF_CT_EXPECT_DEAD);
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_unexpect_related);
@@ -308,6 +310,7 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me)
 	if (!new)
 		return NULL;
 
+	new->timeout = nfct_time_stamp;
 	new->master = me;
 	refcount_set(&new->use, 1);
 	return new;
@@ -352,6 +355,8 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 	exp->tuple.src.l3num = family;
 	exp->tuple.dst.protonum = proto;
 
+	exp->master_tuple = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+
 	if (saddr) {
 		memcpy(&exp->tuple.src.u3, saddr, len);
 		if (sizeof(exp->tuple.src.u3) > len)
@@ -405,25 +410,20 @@ void nf_ct_expect_put(struct nf_conntrack_expect *exp)
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_put);
 
-static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
+static void nf_ct_expect_insert(struct nf_conntrack_expect *exp,
+				struct nf_conn_help *master_help)
 {
 	struct nf_conntrack_net *cnet;
-	struct nf_conn_help *master_help = nfct_help(exp->master);
 	struct nf_conntrack_helper *helper;
 	struct net *net = nf_ct_exp_net(exp);
 	unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple);
 
-	/* two references : one for hash insert, one for the timer */
-	refcount_add(2, &exp->use);
+	refcount_inc(&exp->use);
 
-	timer_setup(&exp->timeout, nf_ct_expectation_timed_out, 0);
 	helper = rcu_dereference_protected(master_help->helper,
 					   lockdep_is_held(&nf_conntrack_expect_lock));
-	if (helper) {
-		exp->timeout.expires = jiffies +
-			helper->expect_policy[exp->class].timeout * HZ;
-	}
-	add_timer(&exp->timeout);
+	if (helper)
+		exp->timeout += helper->expect_policy[exp->class].timeout * HZ;
 
 	hlist_add_head_rcu(&exp->lnode, &master_help->expectations);
 	master_help->expecting[exp->class]++;
@@ -435,30 +435,35 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	NF_CT_STAT_INC(net, expect_create);
 }
 
-/* Race with expectations being used means we could have none to find; OK. */
-static void evict_oldest_expect(struct nf_conn *master,
-				struct nf_conntrack_expect *new)
+static void evict_oldest_expect(struct nf_conn_help *master_help,
+				struct nf_conntrack_expect *new,
+				const struct nf_conntrack_expect_policy *p)
 {
-	struct nf_conn_help *master_help = nfct_help(master);
 	struct nf_conntrack_expect *exp, *last = NULL;
+	struct hlist_node *next;
 
-	hlist_for_each_entry(exp, &master_help->expectations, lnode) {
+	hlist_for_each_entry_safe(exp, next, &master_help->expectations, lnode) {
+		if (nf_ct_exp_is_expired(exp)) {
+			nf_ct_unlink_expect(exp);
+			continue;
+		}
 		if (exp->class == new->class)
 			last = exp;
 	}
 
-	if (last)
-		nf_ct_remove_expect(last);
+	/* Still worth to evict oldest expectation after garbage collection? */
+	if (last &&
+	    master_help->expecting[last->class] >= p->max_expected)
+		nf_ct_unlink_expect(last);
 }
 
 static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
+				       struct nf_conn_help *master_help,
 				       unsigned int flags)
 {
 	const struct nf_conntrack_expect_policy *p;
 	struct nf_conntrack_expect *i;
 	struct nf_conntrack_net *cnet;
-	struct nf_conn *master = expect->master;
-	struct nf_conn_help *master_help = nfct_help(master);
 	struct nf_conntrack_helper *helper;
 	struct net *net = nf_ct_exp_net(expect);
 	struct hlist_node *next;
@@ -467,20 +472,20 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
 
 	lockdep_nfct_expect_lock_held();
 
-	if (!master_help) {
-		ret = -ESHUTDOWN;
-		goto out;
-	}
 	h = nf_ct_expect_dst_hash(net, &expect->tuple);
 	hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
+		if (nf_ct_exp_is_expired(i)) {
+			nf_ct_unlink_expect(i);
+			continue;
+		}
 		if (master_matches(i, expect, flags) &&
 		    expect_matches(i, expect)) {
 			if (i->class != expect->class ||
 			    i->master != expect->master)
 				return -EALREADY;
 
-			if (nf_ct_remove_expect(i))
-				break;
+			nf_ct_unlink_expect(i);
+			break;
 		} else if (expect_clash(i, expect)) {
 			ret = -EBUSY;
 			goto out;
@@ -491,15 +496,15 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
 					   lockdep_is_held(&nf_conntrack_expect_lock));
 	if (helper) {
 		p = &helper->expect_policy[expect->class];
-		if (p->max_expected &&
-		    master_help->expecting[expect->class] >= p->max_expected) {
-			evict_oldest_expect(master, expect);
-			if (master_help->expecting[expect->class]
-						>= p->max_expected) {
-				ret = -EMFILE;
-				goto out;
-			}
-		}
+		if (master_help->expecting[expect->class] >= p->max_expected)
+			evict_oldest_expect(master_help, expect, p);
+	} else {
+		const struct nf_conntrack_expect_policy default_exp_policy = {
+			.max_expected = NF_CT_EXPECT_MAX_CNT,
+		};
+
+		if (master_help->expecting[expect->class] >= default_exp_policy.max_expected)
+			evict_oldest_expect(master_help, expect, &default_exp_policy);
 	}
 
 	cnet = nf_ct_pernet(net);
@@ -514,14 +519,21 @@ out:
 int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
 				u32 portid, int report, unsigned int flags)
 {
+	struct nf_conn_help *master_help;
 	int ret;
 
 	spin_lock_bh(&nf_conntrack_expect_lock);
-	ret = __nf_ct_expect_check(expect, flags);
+	master_help = nfct_help(expect->master);
+	if (!master_help) {
+		ret = -ESHUTDOWN;
+		goto out;
+	}
+
+	ret = __nf_ct_expect_check(expect, master_help, flags);
 	if (ret < 0)
 		goto out;
 
-	nf_ct_expect_insert(expect);
+	nf_ct_expect_insert(expect, master_help);
 
 	nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
 	spin_unlock_bh(&nf_conntrack_expect_lock);
@@ -546,10 +558,8 @@ void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, vo
 		hlist_for_each_entry_safe(exp, next,
 					  &nf_ct_expect_hash[i],
 					  hnode) {
-			if (iter(exp, data) && timer_delete(&exp->timeout)) {
+			if (iter(exp, data))
 				nf_ct_unlink_expect(exp);
-				nf_ct_expect_put(exp);
-			}
 		}
 	}
 
@@ -576,10 +586,8 @@ void nf_ct_expect_iterate_net(struct net *net,
 			if (!net_eq(nf_ct_exp_net(exp), net))
 				continue;
 
-			if (iter(exp, data) && timer_delete(&exp->timeout)) {
+			if (iter(exp, data))
 				nf_ct_unlink_expect_report(exp, portid, report);
-				nf_ct_expect_put(exp);
-			}
 		}
 	}
 
@@ -656,17 +664,17 @@ static int exp_seq_show(struct seq_file *s, void *v)
 	struct net *net = seq_file_net(s);
 	struct hlist_node *n = v;
 	char *delim = "";
+	__s32 timeout;
 
 	expect = hlist_entry(n, struct nf_conntrack_expect, hnode);
 
 	if (!net_eq(nf_ct_exp_net(expect), net))
 		return 0;
+	if (nf_ct_exp_is_expired(expect))
+		return 0;
 
-	if (expect->timeout.function)
-		seq_printf(s, "%ld ", timer_pending(&expect->timeout)
-			   ? (long)(expect->timeout.expires - jiffies)/HZ : 0);
-	else
-		seq_puts(s, "- ");
+	timeout = (__s32)(READ_ONCE(expect->timeout) - nfct_time_stamp) / HZ;
+	seq_printf(s, "%d ", timeout > 0 ? timeout : 0);
 	seq_printf(s, "l3proto = %u proto=%u ",
 		   expect->tuple.src.l3num,
 		   expect->tuple.dst.protonum);
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index dd62cc12e775..0da105e1ded9 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -27,8 +27,6 @@
 
 #define NF_CT_EXT_PREALLOC	128u /* conntrack events are on by default */
 
-atomic_t nf_conntrack_ext_genid __read_mostly = ATOMIC_INIT(1);
-
 static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = {
 	[NF_CT_EXT_HELPER] = sizeof(struct nf_conn_help),
 #if IS_ENABLED(CONFIG_NF_NAT)
@@ -118,10 +116,8 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 	if (!new)
 		return NULL;
 
-	if (!ct->ext) {
+	if (!ct->ext)
 		memset(new->offset, 0, sizeof(new->offset));
-		new->gen_id = atomic_read(&nf_conntrack_ext_genid);
-	}
 
 	new->offset[id] = newoff;
 	new->len = newlen;
@@ -131,29 +127,3 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 	return (void *)new + newoff;
 }
 EXPORT_SYMBOL(nf_ct_ext_add);
-
-/* Use nf_ct_ext_find wrapper. This is only useful for unconfirmed entries. */
-void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id)
-{
-	unsigned int gen_id = atomic_read(&nf_conntrack_ext_genid);
-	unsigned int this_id = READ_ONCE(ext->gen_id);
-
-	if (!__nf_ct_ext_exist(ext, id))
-		return NULL;
-
-	if (this_id == 0 || ext->gen_id == gen_id)
-		return (void *)ext + ext->offset[id];
-
-	return NULL;
-}
-EXPORT_SYMBOL(__nf_ct_ext_find);
-
-void nf_ct_ext_bump_genid(void)
-{
-	unsigned int value = atomic_inc_return(&nf_conntrack_ext_genid);
-
-	if (value == UINT_MAX)
-		atomic_set(&nf_conntrack_ext_genid, 1);
-
-	msleep(HZ);
-}
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index de83bf9e6c61..6e3c06de8a6e 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -381,6 +381,9 @@ static int help(struct sk_buff *skb,
 	int found = 0, ends_in_nl;
 	nf_nat_ftp_hook_fn *nf_nat_ftp;
 
+	if (!ct_ftp_info)
+		return NF_DROP;
+
 	/* Until there's been traffic both ways, don't look in packets. */
 	if (ctinfo != IP_CT_ESTABLISHED &&
 	    ctinfo != IP_CT_ESTABLISHED_REPLY) {
@@ -542,6 +545,9 @@ static int nf_ct_ftp_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 {
 	struct nf_ct_ftp_master *ftp = nfct_help_data(ct);
 
+	if (!ftp)
+		return -ENOENT;
+
 	/* This conntrack has been injected from user-space, always pick up
 	 * sequence tracking. Otherwise, the first FTP command after the
 	 * failover breaks.
@@ -552,6 +558,7 @@ static int nf_ct_ftp_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 }
 
 static struct nf_conntrack_helper ftp[MAX_PORTS * 2] __read_mostly;
+static struct nf_conntrack_helper *ftp_ptr[MAX_PORTS * 2] __read_mostly;
 
 static const struct nf_conntrack_expect_policy ftp_exp_policy = {
 	.max_expected	= 1,
@@ -560,7 +567,7 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = {
 
 static void __exit nf_conntrack_ftp_fini(void)
 {
-	nf_conntrack_helpers_unregister(ftp, ports_c * 2);
+	nf_conntrack_helpers_unregister(ftp_ptr, ports_c * 2);
 }
 
 static int __init nf_conntrack_ftp_init(void)
@@ -585,7 +592,7 @@ static int __init nf_conntrack_ftp_init(void)
 				  nf_ct_ftp_from_nlattr, THIS_MODULE);
 	}
 
-	ret = nf_conntrack_helpers_register(ftp, ports_c * 2);
+	ret = nf_conntrack_helpers_register(ftp, ports_c * 2, ftp_ptr);
 	if (ret < 0) {
 		pr_err("failed to register helpers\n");
 		return ret;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index b2fe6554b9cf..24931e379985 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -76,6 +76,9 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff,
 	int tpktlen;
 	int tpktoff;
 
+	if (!info)
+		return 0;
+
 	/* Get TCP header */
 	th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
 	if (th == NULL)
@@ -577,14 +580,8 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = {
 	.timeout	= 240,
 };
 
-static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = {
-	.name			= "H.245",
-	.me			= THIS_MODULE,
-	.tuple.src.l3num	= AF_UNSPEC,
-	.tuple.dst.protonum	= IPPROTO_UDP,
-	.help			= h245_help,
-	.expect_policy		= &h245_exp_policy,
-};
+static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly;
+static struct nf_conntrack_helper *nf_conntrack_helper_h245_ptr __read_mostly;
 
 int get_h225_addr(struct nf_conn *ct, unsigned char *data,
 		  TransportAddress *taddr,
@@ -643,7 +640,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
 			  IPPROTO_TCP, NULL, &port);
-	rcu_assign_pointer(exp->assign_helper, &nf_conntrack_helper_h245);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_h245_ptr);
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
 	if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -732,6 +729,9 @@ static int callforward_do_filter(struct net *net,
 
 }
 
+static struct nf_conntrack_helper nf_conntrack_helper_q931[2] __read_mostly;
+static struct nf_conntrack_helper *nf_conntrack_helper_q931_ptr[2] __read_mostly;
+
 static int expect_callforwarding(struct sk_buff *skb,
 				 struct nf_conn *ct,
 				 enum ip_conntrack_info ctinfo,
@@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb,
 	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
-	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
 	if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -1140,27 +1140,6 @@ static const struct nf_conntrack_expect_policy q931_exp_policy = {
 	.timeout		= 240,
 };
 
-static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = {
-	{
-		.name			= "Q.931",
-		.me			= THIS_MODULE,
-		.tuple.src.l3num	= AF_INET,
-		.tuple.src.u.tcp.port	= cpu_to_be16(Q931_PORT),
-		.tuple.dst.protonum	= IPPROTO_TCP,
-		.help			= q931_help,
-		.expect_policy		= &q931_exp_policy,
-	},
-	{
-		.name			= "Q.931",
-		.me			= THIS_MODULE,
-		.tuple.src.l3num	= AF_INET6,
-		.tuple.src.u.tcp.port	= cpu_to_be16(Q931_PORT),
-		.tuple.dst.protonum	= IPPROTO_TCP,
-		.help			= q931_help,
-		.expect_policy		= &q931_exp_policy,
-	},
-};
-
 static unsigned char *get_udp_data(struct sk_buff *skb, unsigned int protoff,
 				   int *datalen)
 {
@@ -1215,6 +1194,9 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
 	union nf_inet_addr addr;
 	struct nf_conntrack_expect *exp;
 
+	if (!info)
+		return -1;
+
 	/* Look for the first related address */
 	for (i = 0; i < count; i++) {
 		if (get_h225_addr(ct, *data, &taddr[i], &addr, &port) &&
@@ -1234,7 +1216,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
 				&ct->tuplehash[!dir].tuple.src.u3 : NULL,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
 			  IPPROTO_TCP, NULL, &port);
-	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
 	exp->flags = NF_CT_EXPECT_PERMANENT;	/* Accept multiple calls */
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1275,6 +1257,9 @@ static int process_grq(struct sk_buff *skb, struct nf_conn *ct,
 	return 0;
 }
 
+static struct nf_conntrack_helper nf_conntrack_helper_ras[2] __read_mostly;
+static struct nf_conntrack_helper *nf_conntrack_helper_ras_ptr[2] __read_mostly;
+
 static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
 		       enum ip_conntrack_info ctinfo,
 		       unsigned int protoff,
@@ -1306,7 +1291,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
 	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_UDP, NULL, &port);
-	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras_ptr[0]);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect RAS ");
@@ -1328,6 +1313,9 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct,
 	const struct nfct_h323_nat_hooks *nathook;
 	int ret;
 
+	if (!info)
+		return -1;
+
 	pr_debug("nf_ct_ras: RRQ\n");
 
 	ret = expect_q931(skb, ct, ctinfo, protoff, data,
@@ -1366,6 +1354,9 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
 	int ret;
 	struct nf_conntrack_expect *exp;
 
+	if (!info)
+		return -1;
+
 	pr_debug("nf_ct_ras: RCF\n");
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1397,8 +1388,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
 				 "timeout to %u seconds for",
 				 info->timeout);
 			nf_ct_dump_tuple(&exp->tuple);
-			mod_timer_pending(&exp->timeout,
-					  jiffies + info->timeout * HZ);
+			WRITE_ONCE(exp->timeout,
+				   nfct_time_stamp + (info->timeout * HZ));
 		}
 		spin_unlock_bh(&nf_conntrack_expect_lock);
 	}
@@ -1416,6 +1407,9 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct,
 	int dir = CTINFO2DIR(ctinfo);
 	int ret;
 
+	if (!info)
+		return -1;
+
 	pr_debug("nf_ct_ras: URQ\n");
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1450,6 +1444,9 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct,
 	__be16 port;
 	union nf_inet_addr addr;
 
+	if (!info)
+		return 0;
+
 	pr_debug("nf_ct_ras: ARQ\n");
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1523,7 +1520,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
 	exp->flags = NF_CT_EXPECT_PERMANENT;
-	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");
@@ -1577,7 +1574,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
 	exp->flags = NF_CT_EXPECT_PERMANENT;
-	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931_ptr[0]);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");
@@ -1711,59 +1708,57 @@ static const struct nf_conntrack_expect_policy ras_exp_policy = {
 	.timeout		= 240,
 };
 
-static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = {
-	{
-		.name			= "RAS",
-		.me			= THIS_MODULE,
-		.tuple.src.l3num	= AF_INET,
-		.tuple.src.u.udp.port	= cpu_to_be16(RAS_PORT),
-		.tuple.dst.protonum	= IPPROTO_UDP,
-		.help			= ras_help,
-		.expect_policy		= &ras_exp_policy,
-	},
-	{
-		.name			= "RAS",
-		.me			= THIS_MODULE,
-		.tuple.src.l3num	= AF_INET6,
-		.tuple.src.u.udp.port	= cpu_to_be16(RAS_PORT),
-		.tuple.dst.protonum	= IPPROTO_UDP,
-		.help			= ras_help,
-		.expect_policy		= &ras_exp_policy,
-	},
-};
-
 static int __init h323_helper_init(void)
 {
 	int ret;
 
-	ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245);
+	nf_ct_helper_init(&nf_conntrack_helper_ras[0], AF_INET, IPPROTO_UDP,
+			  "RAS", RAS_PORT, RAS_PORT, RAS_PORT,
+			  &ras_exp_policy, 0, ras_help, NULL, THIS_MODULE);
+	nf_ct_helper_init(&nf_conntrack_helper_ras[1], AF_INET6, IPPROTO_UDP,
+			  "RAS", RAS_PORT, RAS_PORT, RAS_PORT,
+			  &ras_exp_policy, 0, ras_help, NULL, THIS_MODULE);
+	nf_ct_helper_init(&nf_conntrack_helper_h245, AF_UNSPEC, IPPROTO_UDP,
+			  "H.245", 0, 0, 0,
+			  &h245_exp_policy, 0, h245_help, NULL, THIS_MODULE);
+	nf_ct_helper_init(&nf_conntrack_helper_q931[0], AF_INET, IPPROTO_TCP,
+			  "Q.931", Q931_PORT, Q931_PORT, Q931_PORT,
+			  &q931_exp_policy, 0, q931_help, NULL, THIS_MODULE);
+	nf_ct_helper_init(&nf_conntrack_helper_q931[1], AF_INET6, IPPROTO_TCP,
+			  "Q.931", Q931_PORT, Q931_PORT, Q931_PORT,
+			  &q931_exp_policy, 0, q931_help, NULL, THIS_MODULE);
+
+	ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245,
+					   &nf_conntrack_helper_h245_ptr);
 	if (ret < 0)
 		return ret;
 	ret = nf_conntrack_helpers_register(nf_conntrack_helper_q931,
-					ARRAY_SIZE(nf_conntrack_helper_q931));
+					    ARRAY_SIZE(nf_conntrack_helper_q931),
+					    nf_conntrack_helper_q931_ptr);
 	if (ret < 0)
 		goto err1;
 	ret = nf_conntrack_helpers_register(nf_conntrack_helper_ras,
-					ARRAY_SIZE(nf_conntrack_helper_ras));
+					    ARRAY_SIZE(nf_conntrack_helper_ras),
+					    nf_conntrack_helper_ras_ptr);
 	if (ret < 0)
 		goto err2;
 
 	return 0;
 err2:
-	nf_conntrack_helpers_unregister(nf_conntrack_helper_q931,
-					ARRAY_SIZE(nf_conntrack_helper_q931));
+	nf_conntrack_helpers_unregister(nf_conntrack_helper_q931_ptr,
+					ARRAY_SIZE(nf_conntrack_helper_q931_ptr));
 err1:
-	nf_conntrack_helper_unregister(&nf_conntrack_helper_h245);
+	nf_conntrack_helper_unregister(nf_conntrack_helper_h245_ptr);
 	return ret;
 }
 
 static void __exit h323_helper_exit(void)
 {
-	nf_conntrack_helpers_unregister(nf_conntrack_helper_ras,
+	nf_conntrack_helpers_unregister(nf_conntrack_helper_ras_ptr,
 					ARRAY_SIZE(nf_conntrack_helper_ras));
-	nf_conntrack_helpers_unregister(nf_conntrack_helper_q931,
+	nf_conntrack_helpers_unregister(nf_conntrack_helper_q931_ptr,
 					ARRAY_SIZE(nf_conntrack_helper_q931));
-	nf_conntrack_helper_unregister(&nf_conntrack_helper_h245);
+	nf_conntrack_helper_unregister(nf_conntrack_helper_h245_ptr);
 }
 
 static void __exit nf_conntrack_h323_fini(void)
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 2c5a71735561..d1392b8e09af 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -180,10 +180,10 @@ nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp)
 	struct nf_conn_help *help;
 
 	help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp);
-	if (help)
+	if (help) {
+		__set_bit(IPS_HELPER_BIT, &ct->status);
 		INIT_HLIST_HEAD(&help->expectations);
-	else
-		pr_debug("failed to add helper extension area");
+	}
 	return help;
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add);
@@ -202,10 +202,8 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 		return 0;
 
 	help = nfct_help(tmpl);
-	if (help != NULL) {
+	if (help)
 		helper = rcu_dereference(help->helper);
-		set_bit(IPS_HELPER_BIT, &ct->status);
-	}
 
 	help = nfct_help(ct);
 
@@ -366,22 +364,26 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct,
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_log);
 
-int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
+int __nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 {
 	struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
 	unsigned int h = helper_hash(&me->tuple);
 	struct nf_conntrack_helper *cur;
 	int ret = 0, i;
 
-	BUG_ON(me->expect_policy == NULL);
 	BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
 	BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1);
 
 	if (!nf_ct_helper_hash)
 		return -ENOENT;
 
-	if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
-		return -EINVAL;
+	for (i = 0; i <= me->expect_class_max; i++) {
+		if (!me->expect_policy[i].max_expected)
+			me->expect_policy[i].max_expected = NF_CT_EXPECT_MAX_CNT;
+
+		if (me->expect_policy[i].max_expected > NF_CT_EXPECT_MAX_CNT)
+			return -EINVAL;
+	}
 
 	mutex_lock(&nf_ct_helper_mutex);
 	for (i = 0; i < nf_ct_helper_hsize; i++) {
@@ -413,6 +415,33 @@ out:
 	mutex_unlock(&nf_ct_helper_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__nf_conntrack_helper_register);
+
+int nf_conntrack_helper_register(struct nf_conntrack_helper *me,
+				 struct nf_conntrack_helper **helper_ptr)
+{
+	struct nf_conntrack_helper *new_helper;
+	int err;
+
+	new_helper = kzalloc_obj(*new_helper, GFP_KERNEL_ACCOUNT);
+	if (!new_helper)
+		return -ENOMEM;
+
+	memcpy(new_helper, me, sizeof(*new_helper));
+	*helper_ptr = new_helper;
+
+	err = __nf_conntrack_helper_register(new_helper);
+	if (err < 0)
+		goto err_helper;
+
+	return 0;
+
+err_helper:
+	*helper_ptr = NULL;
+	kfree(new_helper);
+
+	return err;
+}
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_register);
 
 static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
@@ -449,6 +478,7 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 	 * last step, this ensures rcu readers of exp->helper are done.
 	 * No need for another synchronize_rcu() here.
 	 */
+	kfree(me);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 
@@ -464,11 +494,12 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
 					  struct nf_conn *ct),
 		       struct module *module)
 {
+	memset(helper, 0, sizeof(*helper));
+
 	helper->tuple.src.l3num = l3num;
 	helper->tuple.dst.protonum = protonum;
 	helper->tuple.src.u.all = htons(spec_port);
-	helper->expect_policy = exp_pol;
-	helper->expect_class_max = expect_class_max;
+
 	helper->help = help;
 	helper->from_nlattr = from_nlattr;
 	helper->me = module;
@@ -479,34 +510,57 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
 		snprintf(helper->name, sizeof(helper->name), "%s", name);
 	else
 		snprintf(helper->name, sizeof(helper->name), "%s-%u", name, id);
+
+	if (WARN_ON_ONCE(expect_class_max >= NF_CT_MAX_EXPECT_CLASSES))
+		return;
+
+	memcpy(helper->expect_policy, exp_pol,
+	       (expect_class_max + 1) * sizeof(*exp_pol));
+	helper->expect_class_max = expect_class_max;
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_init);
 
 int nf_conntrack_helpers_register(struct nf_conntrack_helper *helper,
-				  unsigned int n)
+				  unsigned int n, struct nf_conntrack_helper **helper_ptr)
 {
+	struct nf_conntrack_helper *new_helper;
 	unsigned int i;
 	int err = 0;
 
 	for (i = 0; i < n; i++) {
-		err = nf_conntrack_helper_register(&helper[i]);
-		if (err < 0)
+		new_helper = kzalloc_obj(*new_helper, GFP_KERNEL_ACCOUNT);
+		if (!new_helper) {
+			err = -ENOMEM;
 			goto err;
+		}
+
+		memcpy(new_helper, &helper[i], sizeof(*new_helper));
+		helper_ptr[i] = new_helper;
+
+		err = __nf_conntrack_helper_register(new_helper);
+		if (err < 0) {
+			helper_ptr[i] = NULL;
+			goto err_helper;
+		}
 	}
 
 	return err;
+err_helper:
+	kfree(new_helper);
 err:
 	if (i > 0)
-		nf_conntrack_helpers_unregister(helper, i);
+		nf_conntrack_helpers_unregister(helper_ptr, i);
 	return err;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helpers_register);
 
-void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper,
-				unsigned int n)
+void nf_conntrack_helpers_unregister(struct nf_conntrack_helper **helper,
+				     unsigned int n)
 {
-	while (n-- > 0)
-		nf_conntrack_helper_unregister(&helper[n]);
+	while (n-- > 0) {
+		nf_conntrack_helper_unregister(helper[n]);
+		helper[n] = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister);
 
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 2ebe4cb47cf6..0c117b8492e9 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -59,7 +59,7 @@ static const char *const dccprotos[] = {
 /* tries to get the ip_addr and port out of a dcc command
  * return value: -1 on failure, 0 on success
  *	data		pointer to first byte of DCC command data
- *	data_end	pointer to last byte of dcc command data
+ *	data_end	one past end of data
  *	ip		returns parsed ip of dcc command
  *	port		returns parsed port of dcc command
  *	ad_beg_p	returns pointer to first byte of addr data
@@ -77,10 +77,10 @@ static int parse_dcc(char *data, const char *data_end, __be32 *ip,
 
 	/* Make sure we have a newline character within the packet boundaries
 	 * because simple_strtoul parses until the first invalid character. */
-	for (tmp = data; tmp <= data_end; tmp++)
+	for (tmp = data; tmp < data_end; tmp++)
 		if (*tmp == '\n')
 			break;
-	if (tmp > data_end || *tmp != '\n')
+	if (tmp >= data_end || *tmp != '\n')
 		return -1;
 
 	*ad_beg_p = data;
@@ -255,6 +255,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 }
 
 static struct nf_conntrack_helper irc[MAX_PORTS] __read_mostly;
+static struct nf_conntrack_helper *irc_ptr[MAX_PORTS] __read_mostly;
 static struct nf_conntrack_expect_policy irc_exp_policy;
 
 static int __init nf_conntrack_irc_init(void)
@@ -289,7 +290,7 @@ static int __init nf_conntrack_irc_init(void)
 				  0, help, NULL, THIS_MODULE);
 	}
 
-	ret = nf_conntrack_helpers_register(&irc[0], ports_c);
+	ret = nf_conntrack_helpers_register(&irc[0], ports_c, irc_ptr);
 	if (ret) {
 		pr_err("failed to register helpers\n");
 		kfree(irc_buffer);
@@ -301,7 +302,7 @@ static int __init nf_conntrack_irc_init(void)
 
 static void __exit nf_conntrack_irc_fini(void)
 {
-	nf_conntrack_helpers_unregister(irc, ports_c);
+	nf_conntrack_helpers_unregister(irc_ptr, ports_c);
 	kfree(irc_buffer);
 }
 
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index 55415f011943..89d1cf7d6512 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -44,27 +44,25 @@ static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff,
 	return nf_conntrack_broadcast_help(skb, ct, ctinfo, timeout);
 }
 
-static struct nf_conntrack_helper helper __read_mostly = {
-	.name			= HELPER_NAME,
-	.tuple.src.l3num	= NFPROTO_IPV4,
-	.tuple.src.u.udp.port	= cpu_to_be16(NMBD_PORT),
-	.tuple.dst.protonum	= IPPROTO_UDP,
-	.me			= THIS_MODULE,
-	.help			= netbios_ns_help,
-	.expect_policy		= &exp_policy,
-};
+static struct nf_conntrack_helper helper __read_mostly;
+static struct nf_conntrack_helper *helper_ptr __read_mostly;
 
 static int __init nf_conntrack_netbios_ns_init(void)
 {
 	NF_CT_HELPER_BUILD_BUG_ON(0);
 
 	exp_policy.timeout = timeout;
-	return nf_conntrack_helper_register(&helper);
+
+	nf_ct_helper_init(&helper, AF_INET, IPPROTO_UDP, HELPER_NAME,
+			  NMBD_PORT, NMBD_PORT, NMBD_PORT,
+			  &exp_policy, 0, netbios_ns_help, NULL, THIS_MODULE);
+
+	return nf_conntrack_helper_register(&helper, &helper_ptr);
 }
 
 static void __exit nf_conntrack_netbios_ns_fini(void)
 {
-	nf_conntrack_helper_unregister(&helper);
+	nf_conntrack_helper_unregister(helper_ptr);
 }
 
 module_init(nf_conntrack_netbios_ns_init);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index d429f9c9546c..b11b8b7f31aa 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3006,8 +3006,7 @@ static int
 ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			  const struct nf_conntrack_expect *exp)
 {
-	struct nf_conn *master = exp->master;
-	long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ;
+	__s32 timeout = (__s32)(READ_ONCE(exp->timeout) - nfct_time_stamp) / HZ;
 	struct nf_conntrack_helper *helper;
 #if IS_ENABLED(CONFIG_NF_NAT)
 	struct nlattr *nest_parms;
@@ -3022,9 +3021,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 		goto nla_put_failure;
 	if (ctnetlink_exp_dump_mask(skb, &exp->tuple, &exp->mask) < 0)
 		goto nla_put_failure;
-	if (ctnetlink_exp_dump_tuple(skb,
-				 &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-				 CTA_EXPECT_MASTER) < 0)
+	if (ctnetlink_exp_dump_tuple(skb, &exp->master_tuple, CTA_EXPECT_MASTER) < 0)
 		goto nla_put_failure;
 
 #if IS_ENABLED(CONFIG_NF_NAT)
@@ -3037,9 +3034,9 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 		if (nla_put_be32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir)))
 			goto nla_put_failure;
 
-		nat_tuple.src.l3num = nf_ct_l3num(master);
+		nat_tuple.src.l3num = exp->master_tuple.src.l3num;
 		nat_tuple.src.u3 = exp->saved_addr;
-		nat_tuple.dst.protonum = nf_ct_protonum(master);
+		nat_tuple.dst.protonum = exp->master_tuple.dst.protonum;
 		nat_tuple.src.u = exp->saved_proto;
 
 		if (ctnetlink_exp_dump_tuple(skb, &nat_tuple,
@@ -3170,6 +3167,9 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 restart:
 		hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]],
 					 hnode) {
+			if (nf_ct_exp_is_expired(exp))
+				continue;
+
 			if (l3proto && exp->tuple.src.l3num != l3proto)
 				continue;
 
@@ -3448,11 +3448,8 @@ static int ctnetlink_del_expect(struct sk_buff *skb,
 		}
 
 		/* after list removal, usage count == 1 */
-		if (timer_delete(&exp->timeout)) {
-			nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid,
-						   nlmsg_report(info->nlh));
-			nf_ct_expect_put(exp);
-		}
+		nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid,
+					   nlmsg_report(info->nlh));
 		spin_unlock_bh(&nf_conntrack_expect_lock);
 		/* have to put what we 'get' above.
 		 * after this line usage count == 0 */
@@ -3476,14 +3473,10 @@ static int
 ctnetlink_change_expect(struct nf_conntrack_expect *x,
 			const struct nlattr * const cda[])
 {
-	if (cda[CTA_EXPECT_TIMEOUT]) {
-		if (!timer_delete(&x->timeout))
-			return -ETIME;
+	if (cda[CTA_EXPECT_TIMEOUT])
+		WRITE_ONCE(x->timeout, nfct_time_stamp +
+			   ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ);
 
-		x->timeout.expires = jiffies +
-			ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ;
-		add_timer(&x->timeout);
-	}
 	return 0;
 }
 
@@ -3585,6 +3578,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 #endif
 	rcu_assign_pointer(exp->helper, helper);
 	rcu_assign_pointer(exp->assign_helper, assign_helper);
+	exp->master_tuple = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
 	exp->tuple = *tuple;
 	exp->mask.src.u3 = mask->src.u3;
 	exp->mask.src.u.all = mask->src.u.all;
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index dc23e4181618..776505a78e64 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -124,65 +124,6 @@ static void pptp_expectfn(struct nf_conn *ct,
 	}
 }
 
-static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct,
-				  const struct nf_conntrack_tuple *t)
-{
-	const struct nf_conntrack_tuple_hash *h;
-	const struct nf_conntrack_zone *zone;
-	struct nf_conntrack_expect *exp;
-	struct nf_conn *sibling;
-
-	pr_debug("trying to timeout ct or exp for tuple ");
-	nf_ct_dump_tuple(t);
-
-	zone = nf_ct_zone(ct);
-	h = nf_conntrack_find_get(net, zone, t);
-	if (h)  {
-		sibling = nf_ct_tuplehash_to_ctrack(h);
-		pr_debug("setting timeout of conntrack %p to 0\n", sibling);
-		sibling->proto.gre.timeout	  = 0;
-		sibling->proto.gre.stream_timeout = 0;
-		nf_ct_kill(sibling);
-		nf_ct_put(sibling);
-		return 1;
-	} else {
-		exp = nf_ct_expect_find_get(net, zone, t);
-		if (exp) {
-			pr_debug("unexpect_related of expect %p\n", exp);
-			nf_ct_unexpect_related(exp);
-			nf_ct_expect_put(exp);
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/* timeout GRE data connections */
-static void pptp_destroy_siblings(struct nf_conn *ct)
-{
-	struct net *net = nf_ct_net(ct);
-	const struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
-	struct nf_conntrack_tuple t;
-
-	nf_ct_gre_keymap_destroy(ct);
-
-	/* try original (pns->pac) tuple */
-	memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t));
-	t.dst.protonum = IPPROTO_GRE;
-	t.src.u.gre.key = ct_pptp_info->pns_call_id;
-	t.dst.u.gre.key = ct_pptp_info->pac_call_id;
-	if (!destroy_sibling_or_exp(net, ct, &t))
-		pr_debug("failed to timeout original pns->pac ct/exp\n");
-
-	/* try reply (pac->pns) tuple */
-	memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t));
-	t.dst.protonum = IPPROTO_GRE;
-	t.src.u.gre.key = ct_pptp_info->pac_call_id;
-	t.dst.u.gre.key = ct_pptp_info->pns_call_id;
-	if (!destroy_sibling_or_exp(net, ct, &t))
-		pr_debug("failed to timeout reply pac->pns ct/exp\n");
-}
-
 /* expect GRE connections (PNS->PAC and PAC->PNS direction) */
 static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid)
 {
@@ -257,6 +198,9 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	u_int16_t msg;
 	__be16 cid = 0, pcid = 0;
 
+	if (!info)
+		return NF_DROP;
+
 	msg = ntohs(ctlh->messageType);
 	pr_debug("inbound control message %s\n", pptp_msg_name(msg));
 
@@ -343,7 +287,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		info->cstate = PPTP_CALL_NONE;
 
 		/* untrack this call id, unexpect GRE packets */
-		pptp_destroy_siblings(ct);
+		gre_pptp_destroy_siblings(ct);
 		break;
 
 	case PPTP_WAN_ERROR_NOTIFY:
@@ -384,6 +328,9 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	u_int16_t msg;
 	__be16 cid = 0, pcid = 0;
 
+	if (!info)
+		return NF_DROP;
+
 	msg = ntohs(ctlh->messageType);
 	pr_debug("outbound control message %s\n", pptp_msg_name(msg));
 
@@ -502,6 +449,9 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff,
 	int ret;
 	u_int16_t msg;
 
+	if (!info)
+		return NF_DROP;
+
 #if IS_ENABLED(CONFIG_NF_NAT)
 	if (!nf_ct_is_confirmed(ct) && (ct->status & IPS_NAT_MASK)) {
 		struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT);
@@ -582,27 +532,25 @@ static const struct nf_conntrack_expect_policy pptp_exp_policy = {
 };
 
 /* control protocol helper */
-static struct nf_conntrack_helper pptp __read_mostly = {
-	.name			= "pptp",
-	.me			= THIS_MODULE,
-	.tuple.src.l3num	= AF_INET,
-	.tuple.src.u.tcp.port	= cpu_to_be16(PPTP_CONTROL_PORT),
-	.tuple.dst.protonum	= IPPROTO_TCP,
-	.help			= conntrack_pptp_help,
-	.destroy		= pptp_destroy_siblings,
-	.expect_policy		= &pptp_exp_policy,
-};
+static struct nf_conntrack_helper pptp __read_mostly;
+static struct nf_conntrack_helper *pptp_ptr __read_mostly;
 
 static int __init nf_conntrack_pptp_init(void)
 {
 	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_pptp_master));
 
-	return nf_conntrack_helper_register(&pptp);
+	nf_ct_helper_init(&pptp, AF_INET, IPPROTO_TCP,
+			  "pptp", PPTP_CONTROL_PORT, PPTP_CONTROL_PORT, PPTP_CONTROL_PORT,
+			  &pptp_exp_policy, 0, conntrack_pptp_help, NULL, THIS_MODULE);
+
+	pptp.destroy = gre_pptp_destroy_siblings;
+
+	return nf_conntrack_helper_register(&pptp, &pptp_ptr);
 }
 
 static void __exit nf_conntrack_pptp_fini(void)
 {
-	nf_conntrack_helper_unregister(&pptp);
+	nf_conntrack_helper_unregister(pptp_ptr);
 }
 
 module_init(nf_conntrack_pptp_init);
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 35e22082d65a..616ab1e2fc5e 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -131,6 +131,9 @@ bool nf_ct_gre_keymap_add(struct nf_conn *ct,
 	struct nf_ct_gre_keymap *km_orig, *km_repl;
 	bool ret = false;
 
+	if (!ct_pptp_info)
+		return false;
+
 	km_orig = kmalloc_obj(*km_orig, GFP_ATOMIC);
 	if (!km_orig)
 		return false;
@@ -187,6 +190,9 @@ void nf_ct_gre_keymap_destroy(struct nf_conn *ct)
 	struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
 	enum ip_conntrack_dir dir;
 
+	if (!ct_pptp_info)
+		return;
+
 	pr_debug("entering for ct %p\n", ct);
 
 	spin_lock_bh(&keymap_lock);
@@ -349,6 +355,70 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = {
 };
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_PPTP)
+static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct,
+				  const struct nf_conntrack_tuple *t)
+{
+	const struct nf_conntrack_tuple_hash *h;
+	const struct nf_conntrack_zone *zone;
+	struct nf_conntrack_expect *exp;
+	struct nf_conn *sibling;
+
+	pr_debug("trying to timeout ct or exp for tuple ");
+	nf_ct_dump_tuple(t);
+
+	zone = nf_ct_zone(ct);
+	h = nf_conntrack_find_get(net, zone, t);
+	if (h)  {
+		sibling = nf_ct_tuplehash_to_ctrack(h);
+		pr_debug("setting timeout of conntrack %p to 0\n", sibling);
+		sibling->proto.gre.timeout        = 0;
+		sibling->proto.gre.stream_timeout = 0;
+		nf_ct_kill(sibling);
+		nf_ct_put(sibling);
+		return 1;
+	} else {
+		exp = nf_ct_expect_find_get(net, zone, t);
+		if (exp) {
+			pr_debug("unexpect_related of expect %p\n", exp);
+			nf_ct_unexpect_related(exp);
+			nf_ct_expect_put(exp);
+			return 1;
+		}
+	}
+	return 0;
+}
+
+void gre_pptp_destroy_siblings(struct nf_conn *ct)
+{
+	struct net *net = nf_ct_net(ct);
+	const struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
+	struct nf_conntrack_tuple t;
+
+	if (!ct_pptp_info)
+		return;
+
+	nf_ct_gre_keymap_destroy(ct);
+
+	/* try original (pns->pac) tuple */
+	memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t));
+	t.dst.protonum = IPPROTO_GRE;
+	t.src.u.gre.key = ct_pptp_info->pns_call_id;
+	t.dst.u.gre.key = ct_pptp_info->pac_call_id;
+	if (!destroy_sibling_or_exp(net, ct, &t))
+		pr_debug("failed to timeout original pns->pac ct/exp\n");
+
+	/* try reply (pac->pns) tuple */
+	memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t));
+	t.dst.protonum = IPPROTO_GRE;
+	t.src.u.gre.key = ct_pptp_info->pac_call_id;
+	t.dst.u.gre.key = ct_pptp_info->pns_call_id;
+	if (!destroy_sibling_or_exp(net, ct, &t))
+		pr_debug("failed to timeout reply pac->pns ct/exp\n");
+}
+EXPORT_SYMBOL_GPL(gre_pptp_destroy_siblings);
+#endif
+
 void nf_conntrack_gre_init_net(struct net *net)
 {
 	struct nf_gre_net *net_gre = gre_pernet(net);
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 13dc421fc4f5..39085acf7a71 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -74,6 +74,9 @@ static int help(struct sk_buff *skb,
 		struct sane_reply_net_start repl;
 	} buf;
 
+	if (!ct_sane_info)
+		return NF_DROP;
+
 	/* Until there's been traffic both ways, don't look in packets. */
 	if (ctinfo != IP_CT_ESTABLISHED &&
 	    ctinfo != IP_CT_ESTABLISHED_REPLY)
@@ -167,6 +170,7 @@ static int help(struct sk_buff *skb,
 }
 
 static struct nf_conntrack_helper sane[MAX_PORTS * 2] __read_mostly;
+static struct nf_conntrack_helper *sane_ptr[MAX_PORTS * 2] __read_mostly;
 
 static const struct nf_conntrack_expect_policy sane_exp_policy = {
 	.max_expected	= 1,
@@ -175,7 +179,7 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = {
 
 static void __exit nf_conntrack_sane_fini(void)
 {
-	nf_conntrack_helpers_unregister(sane, ports_c * 2);
+	nf_conntrack_helpers_unregister(sane_ptr, ports_c * 2);
 }
 
 static int __init nf_conntrack_sane_init(void)
@@ -200,7 +204,7 @@ static int __init nf_conntrack_sane_init(void)
 				  THIS_MODULE);
 	}
 
-	ret = nf_conntrack_helpers_register(sane, ports_c * 2);
+	ret = nf_conntrack_helpers_register(sane, ports_c * 2, sane_ptr);
 	if (ret < 0) {
 		pr_err("failed to register helpers\n");
 		return ret;
diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index 7ab2b25b57bc..220216a4edc5 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -17,12 +17,17 @@ int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 	if (off == 0)
 		return 0;
 
-	set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
-
+	spin_lock_bh(&ct->lock);
 	seqadj = nfct_seqadj(ct);
+	if (!seqadj) {
+		spin_unlock_bh(&ct->lock);
+		return 0;
+	}
+	set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
 	this_way = &seqadj->seq[dir];
 	this_way->offset_before	 = off;
 	this_way->offset_after	 = off;
+	spin_unlock_bh(&ct->lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_ct_seqadj_init);
@@ -37,10 +42,8 @@ int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 	if (off == 0)
 		return 0;
 
-	if (unlikely(!seqadj)) {
-		WARN_ONCE(1, "Missing nfct_seqadj_ext_add() setup call\n");
+	if (unlikely(!seqadj))
 		return 0;
-	}
 
 	set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
 
@@ -123,6 +126,9 @@ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb,
 	struct nf_conn_seqadj *seqadj = nfct_seqadj(ct);
 	unsigned int dir, optoff, optend;
 
+	if (!seqadj)
+		return 0;
+
 	optoff = protoff + sizeof(struct tcphdr);
 	optend = protoff + tcph->doff * 4;
 
@@ -173,6 +179,9 @@ int nf_ct_seq_adjust(struct sk_buff *skb,
 	struct nf_ct_seqadj *this_way, *other_way;
 	int res = 1;
 
+	if (!seqadj)
+		return 0;
+
 	this_way  = &seqadj->seq[dir];
 	other_way = &seqadj->seq[!dir];
 
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index e69941f1a101..f3f90a866338 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -887,6 +887,9 @@ static int refresh_signalling_expectation(struct nf_conn *ct,
 	struct hlist_node *next;
 	int found = 0;
 
+	if (!help)
+		return 0;
+
 	spin_lock_bh(&nf_conntrack_expect_lock);
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
 		if (exp->class != SIP_EXPECT_SIGNALLING ||
@@ -894,11 +897,10 @@ static int refresh_signalling_expectation(struct nf_conn *ct,
 		    exp->tuple.dst.protonum != proto ||
 		    exp->tuple.dst.u.udp.port != port)
 			continue;
-		if (mod_timer_pending(&exp->timeout, jiffies + expires * HZ)) {
-			exp->flags &= ~NF_CT_EXPECT_INACTIVE;
-			found = 1;
-			break;
-		}
+		WRITE_ONCE(exp->timeout, nfct_time_stamp + (expires * HZ));
+		WRITE_ONCE(exp->flags, exp->flags & ~NF_CT_EXPECT_INACTIVE);
+		found = 1;
+		break;
 	}
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 	return found;
@@ -910,12 +912,14 @@ static void flush_expectations(struct nf_conn *ct, bool media)
 	struct nf_conntrack_expect *exp;
 	struct hlist_node *next;
 
+	if (!help)
+		return;
+
 	spin_lock_bh(&nf_conntrack_expect_lock);
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
 		if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media)
 			continue;
-		if (!nf_ct_remove_expect(exp))
-			continue;
+		nf_ct_unlink_expect(exp);
 		if (!media)
 			break;
 	}
@@ -940,6 +944,11 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 	u_int16_t base_port;
 	__be16 rtp_port, rtcp_port;
 	const struct nf_nat_sip_hooks *hooks;
+	struct nf_conn_help *help;
+
+	help = nfct_help(ct);
+	if (!help)
+		return NF_DROP;
 
 	saddr = NULL;
 	if (sip_direct_media) {
@@ -947,7 +956,6 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 			return NF_ACCEPT;
 		saddr = &ct->tuplehash[!dir].tuple.src.u3;
 	} else if (sip_external_media) {
-		struct net_device *dev = skb_dst(skb)->dev;
 		struct dst_entry *dst = NULL;
 		struct flowi fl;
 
@@ -969,7 +977,11 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 		 * through the same interface as the signalling peer.
 		 */
 		if (dst) {
-			bool external_media = (dst->dev == dev);
+			const struct dst_entry *this_dst = skb_dst(skb);
+			bool external_media = false;
+
+			if (this_dst && dst->dev == this_dst->dev)
+				external_media = true;
 
 			dst_release(dst);
 			if (external_media)
@@ -1002,7 +1014,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 		exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple);
 
 		if (!exp || exp->master == ct ||
-		    exp->helper != nfct_help(ct)->helper ||
+		    exp->helper != help->helper ||
 		    exp->class != class)
 			break;
 #if IS_ENABLED(CONFIG_NF_NAT)
@@ -1227,6 +1239,9 @@ static int process_invite_response(struct sk_buff *skb, unsigned int protoff,
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 	struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	if ((code >= 100 && code <= 199) ||
 	    (code >= 200 && code <= 299))
 		return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq);
@@ -1244,6 +1259,9 @@ static int process_update_response(struct sk_buff *skb, unsigned int protoff,
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 	struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	if ((code >= 100 && code <= 199) ||
 	    (code >= 200 && code <= 299))
 		return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq);
@@ -1261,6 +1279,9 @@ static int process_prack_response(struct sk_buff *skb, unsigned int protoff,
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 	struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	if ((code >= 100 && code <= 199) ||
 	    (code >= 200 && code <= 299))
 		return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq);
@@ -1279,6 +1300,9 @@ static int process_invite_request(struct sk_buff *skb, unsigned int protoff,
 	struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
 	unsigned int ret;
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	flush_expectations(ct, true);
 	ret = process_sdp(skb, protoff, dataoff, dptr, datalen, cseq);
 	if (ret == NF_ACCEPT)
@@ -1316,11 +1340,15 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 	union nf_inet_addr *saddr, daddr;
 	const struct nf_nat_sip_hooks *hooks;
 	struct nf_conntrack_helper *helper;
+	struct nf_conn_help *help;
 	__be16 port;
 	u8 proto;
 	unsigned int expires = 0;
 	int ret;
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	/* Expected connections can not register again. */
 	if (ct->status & IPS_EXPECTED)
 		return NF_ACCEPT;
@@ -1366,7 +1394,11 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 		goto store_cseq;
 	}
 
-	helper = rcu_dereference(nfct_help(ct)->helper);
+	help = nfct_help(ct);
+	if (!help)
+		return NF_DROP;
+
+	helper = rcu_dereference(help->helper);
 	if (!helper)
 		return NF_DROP;
 
@@ -1382,7 +1414,6 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 
 	nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct),
 			  saddr, &daddr, proto, NULL, &port);
-	exp->timeout.expires = sip_timeout * HZ;
 	rcu_assign_pointer(exp->assign_helper, helper);
 	exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE;
 
@@ -1421,6 +1452,9 @@ static int process_register_response(struct sk_buff *skb, unsigned int protoff,
 	unsigned int expires = 0;
 	int in_contact = 0, ret;
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	/* According to RFC 3261, "UAs MUST NOT send a new registration until
 	 * they have received a final response from the registrar for the
 	 * previous one or the previous REGISTER request has timed out".
@@ -1550,6 +1584,9 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff,
 	union nf_inet_addr addr;
 	__be16 port;
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	/* Many Cisco IP phones use a high source port for SIP requests, but
 	 * listen for the response on port 5060.  If we are the local
 	 * router for one of these phones, save the port number from the
@@ -1731,6 +1768,7 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff,
 }
 
 static struct nf_conntrack_helper sip[MAX_PORTS * 4] __read_mostly;
+static struct nf_conntrack_helper *sip_ptr[MAX_PORTS * 4] __read_mostly;
 
 static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = {
 	[SIP_EXPECT_SIGNALLING] = {
@@ -1757,7 +1795,7 @@ static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1
 
 static void __exit nf_conntrack_sip_fini(void)
 {
-	nf_conntrack_helpers_unregister(sip, ports_c * 4);
+	nf_conntrack_helpers_unregister(sip_ptr, ports_c * 4);
 }
 
 static int __init nf_conntrack_sip_init(void)
@@ -1788,7 +1826,7 @@ static int __init nf_conntrack_sip_init(void)
 				  NULL, THIS_MODULE);
 	}
 
-	ret = nf_conntrack_helpers_register(sip, ports_c * 4);
+	ret = nf_conntrack_helpers_register(sip, ports_c * 4, sip_ptr);
 	if (ret < 0) {
 		pr_err("failed to register helpers\n");
 		return ret;
diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c
index 7b7eed43c54f..b6fce5703fce 100644
--- a/net/netfilter/nf_conntrack_snmp.c
+++ b/net/netfilter/nf_conntrack_snmp.c
@@ -47,25 +47,24 @@ static struct nf_conntrack_expect_policy exp_policy = {
 	.max_expected	= 1,
 };
 
-static struct nf_conntrack_helper helper __read_mostly = {
-	.name			= "snmp",
-	.tuple.src.l3num	= NFPROTO_IPV4,
-	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_PORT),
-	.tuple.dst.protonum	= IPPROTO_UDP,
-	.me			= THIS_MODULE,
-	.help			= snmp_conntrack_help,
-	.expect_policy		= &exp_policy,
-};
+static struct nf_conntrack_helper helper __read_mostly;
+static struct nf_conntrack_helper *helper_ptr __read_mostly;
 
 static int __init nf_conntrack_snmp_init(void)
 {
 	exp_policy.timeout = timeout;
-	return nf_conntrack_helper_register(&helper);
+
+	nf_ct_helper_init(&helper, AF_INET, IPPROTO_UDP,
+			  "snmp", SNMP_PORT, SNMP_PORT, SNMP_PORT,
+			  &exp_policy, 0, snmp_conntrack_help, NULL,
+			  THIS_MODULE);
+
+	return nf_conntrack_helper_register(&helper, &helper_ptr);
 }
 
 static void __exit nf_conntrack_snmp_fini(void)
 {
-	nf_conntrack_helper_unregister(&helper);
+	nf_conntrack_helper_unregister(helper_ptr);
 }
 
 module_init(nf_conntrack_snmp_init);
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index a2e6833a0bf7..4393c435aa35 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -96,6 +96,7 @@ static int tftp_help(struct sk_buff *skb,
 }
 
 static struct nf_conntrack_helper tftp[MAX_PORTS * 2] __read_mostly;
+static struct nf_conntrack_helper *tftp_ptr[MAX_PORTS * 2] __read_mostly;
 
 static const struct nf_conntrack_expect_policy tftp_exp_policy = {
 	.max_expected	= 1,
@@ -104,7 +105,7 @@ static const struct nf_conntrack_expect_policy tftp_exp_policy = {
 
 static void __exit nf_conntrack_tftp_fini(void)
 {
-	nf_conntrack_helpers_unregister(tftp, ports_c * 2);
+	nf_conntrack_helpers_unregister(tftp_ptr, ports_c * 2);
 }
 
 static int __init nf_conntrack_tftp_init(void)
@@ -127,7 +128,7 @@ static int __init nf_conntrack_tftp_init(void)
 				  THIS_MODULE);
 	}
 
-	ret = nf_conntrack_helpers_register(tftp, ports_c * 2);
+	ret = nf_conntrack_helpers_register(tftp, ports_c * 2, tftp_ptr);
 	if (ret < 0) {
 		pr_err("failed to register helpers\n");
 		return ret;
diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c
index 0cc584d3dbb1..c81becde2afa 100644
--- a/net/netfilter/nf_conntrack_timeout.c
+++ b/net/netfilter/nf_conntrack_timeout.c
@@ -25,17 +25,32 @@
 const struct nf_ct_timeout_hooks __rcu *nf_ct_timeout_hook __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_timeout_hook);
 
+/* nf_ct_iterate_cleanup() holds the conntrack lock. */
 static int untimeout(struct nf_conn *ct, void *timeout)
 {
 	struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct);
 
 	if (timeout_ext) {
-		const struct nf_ct_timeout *t;
+		struct nf_ct_timeout *t;
 
-		t = rcu_access_pointer(timeout_ext->timeout);
+		rcu_read_lock();
+		t = rcu_dereference(timeout_ext->timeout);
+		if (!t) {
+			rcu_read_unlock();
+			return 0;
+		}
 
-		if (!timeout || t == timeout)
+		if (!timeout || t == timeout) {
 			RCU_INIT_POINTER(timeout_ext->timeout, NULL);
+
+			/* No race with nf_conntrack_free() which is called
+			 * only after the conntrack has been removed from
+			 * the hashes.
+			 */
+			if (refcount_dec_and_test(&t->refcnt))
+				kfree_rcu(t, rcu);
+		}
+		rcu_read_unlock();
 	}
 
 	/* We are not intended to delete this conntrack. */
@@ -70,6 +85,8 @@ int nf_ct_set_timeout(struct net *net, struct nf_conn *ct,
 	const char *errmsg = NULL;
 	int ret = 0;
 
+	WARN_ON_ONCE(!nf_ct_is_template(ct));
+
 	rcu_read_lock();
 	h = rcu_dereference(nf_ct_timeout_hook);
 	if (!h) {
@@ -127,6 +144,8 @@ void nf_ct_destroy_timeout(struct nf_conn *ct)
 	struct nf_conn_timeout *timeout_ext;
 	const struct nf_ct_timeout_hooks *h;
 
+	WARN_ON_ONCE(!nf_ct_is_template(ct));
+
 	rcu_read_lock();
 	h = rcu_dereference(nf_ct_timeout_hook);
 
@@ -139,6 +158,8 @@ void nf_ct_destroy_timeout(struct nf_conn *ct)
 			if (t)
 				h->timeout_put(t);
 			RCU_INIT_POINTER(timeout_ext->timeout, NULL);
+			if (t && refcount_dec_and_test(&t->refcnt))
+				kfree_rcu(t, rcu);
 		}
 	}
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c
index 3d88ef927f31..c6bd5c29bed6 100644
--- a/net/netfilter/nf_dup_netdev.c
+++ b/net/netfilter/nf_dup_netdev.c
@@ -16,11 +16,6 @@
 static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
 				enum nf_dev_hooks hook)
 {
-	u8 *nf_dup_skb_recursion = nf_get_nf_dup_skb_recursion();
-
-	if (*nf_dup_skb_recursion > NF_RECURSION_LIMIT)
-		goto err;
-
 	if (hook == NF_NETDEV_INGRESS && skb_mac_header_was_set(skb)) {
 		if (skb_cow_head(skb, skb->mac_len))
 			goto err;
@@ -30,9 +25,15 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
 
 	skb->dev = dev;
 	skb_clear_tstamp(skb);
-	(*nf_dup_skb_recursion)++;
+	local_bh_disable();
+	if (nf_dev_xmit_recursion()) {
+		local_bh_enable();
+		goto err;
+	}
+	nf_dev_xmit_recursion_inc();
 	dev_queue_xmit(skb);
-	(*nf_dup_skb_recursion)--;
+	nf_dev_xmit_recursion_dec();
+	local_bh_enable();
 	return;
 err:
 	kfree_skb(skb);
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index d06ce0848b68..b66e65439341 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -127,12 +127,18 @@ static int flow_offload_fill_route(struct flow_offload *flow,
 
 	switch (route->tuple[dir].xmit_type) {
 	case FLOW_OFFLOAD_XMIT_DIRECT:
+		if (route->tuple[!dir].in.num_tuns) {
+			flow_tuple->dst_cache = dst;
+			flow_tuple->dst_cookie =
+				flow_offload_dst_cookie(flow_tuple);
+		} else {
+			dst_release(dst);
+		}
 		memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest,
 		       ETH_ALEN);
 		memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source,
 		       ETH_ALEN);
 		flow_tuple->out.ifidx = route->tuple[dir].out.ifindex;
-		dst_release(dst);
 		break;
 	case FLOW_OFFLOAD_XMIT_XFRM:
 	case FLOW_OFFLOAD_XMIT_NEIGH:
@@ -152,9 +158,7 @@ static int flow_offload_fill_route(struct flow_offload *flow,
 static void nft_flow_dst_release(struct flow_offload *flow,
 				 enum flow_offload_tuple_dir dir)
 {
-	if (flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH ||
-	    flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)
-		dst_release(flow->tuplehash[dir].tuple.dst_cache);
+	dst_release(flow->tuplehash[dir].tuple.dst_cache);
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 9c05a50d6013..0b78decce8a9 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -299,8 +299,7 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 
 static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple)
 {
-	if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH &&
-	    tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM)
+	if (!tuple->dst_cache)
 		return true;
 
 	return dst_check(tuple->dst_cache, tuple->dst_cookie);
@@ -326,8 +325,10 @@ static bool nf_flow_ip4_tunnel_proto(struct nf_flowtable_ctx *ctx,
 		return false;
 
 	iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset);
-	size = iph->ihl << 2;
+	if (iph->ihl < 5)
+		return false;
 
+	size = iph->ihl << 2;
 	if (ip_is_fragment(iph) || unlikely(ip_has_options(size)))
 		return false;
 
@@ -335,9 +336,9 @@ static bool nf_flow_ip4_tunnel_proto(struct nf_flowtable_ctx *ctx,
 		return false;
 
 	if (iph->protocol == IPPROTO_IPIP) {
-		ctx->tun.proto = IPPROTO_IPIP;
+		ctx->tun.proto = iph->protocol;
 		ctx->tun.hdr_size = size;
-		ctx->offset += size;
+		ctx->offset += ctx->tun.hdr_size;
 	}
 
 	return true;
@@ -347,29 +348,23 @@ static bool nf_flow_ip6_tunnel_proto(struct nf_flowtable_ctx *ctx,
 				     struct sk_buff *skb)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	struct ipv6hdr *ip6h, _ip6h;
-	__be16 frag_off;
-	u8 nexthdr;
-	int hdrlen;
+	struct ipv6hdr *ip6h;
 
-	ip6h = skb_header_pointer(skb, ctx->offset, sizeof(*ip6h), &_ip6h);
-	if (!ip6h)
+	if (!pskb_may_pull(skb, sizeof(*ip6h) + ctx->offset))
 		return false;
 
+	ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset);
 	if (ip6h->hop_limit <= 1)
 		return false;
 
-	nexthdr = ip6h->nexthdr;
-	hdrlen = ipv6_skip_exthdr(skb, sizeof(*ip6h) + ctx->offset, &nexthdr,
-				  &frag_off);
-	if (hdrlen < 0)
+	if (ipv6_ext_hdr(ip6h->nexthdr))
 		return false;
 
-	if (nexthdr == IPPROTO_IPV6) {
-		ctx->tun.hdr_size = hdrlen;
-		ctx->tun.proto = IPPROTO_IPV6;
+	if (ip6h->nexthdr == IPPROTO_IPV6) {
+		ctx->tun.proto = ip6h->nexthdr;
+		ctx->tun.hdr_size = sizeof(*ip6h);
+		ctx->offset += ctx->tun.hdr_size;
 	}
-	ctx->offset += ctx->tun.hdr_size;
 
 	return true;
 #else
@@ -594,10 +589,10 @@ static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id,
 
 static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb,
 				    struct flow_offload_tuple *tuple,
-				    __be32 *ip_daddr)
+				    struct dst_entry *dst, __be32 *ip_daddr)
 {
 	struct iphdr *iph = (struct iphdr *)skb_network_header(skb);
-	struct rtable *rt = dst_rtable(tuple->dst_cache);
+	struct rtable *rt = dst_rtable(dst);
 	u8 tos = iph->tos, ttl = iph->ttl;
 	__be16 frag_off = iph->frag_off;
 	u32 headroom = sizeof(*iph);
@@ -640,33 +635,28 @@ static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb,
 
 static int nf_flow_tunnel_v4_push(struct net *net, struct sk_buff *skb,
 				  struct flow_offload_tuple *tuple,
-				  __be32 *ip_daddr)
+				  struct dst_entry *dst,  __be32 *ip_daddr)
 {
 	if (tuple->tun_num)
-		return nf_flow_tunnel_ipip_push(net, skb, tuple, ip_daddr);
+		return nf_flow_tunnel_ipip_push(net, skb, tuple, dst, ip_daddr);
 
 	return 0;
 }
 
-struct ipv6_tel_txoption {
-	struct ipv6_txoptions ops;
-	__u8 dst_opt[8];
-};
-
 static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb,
 				      struct flow_offload_tuple *tuple,
-				      struct in6_addr **ip6_daddr,
-				      int encap_limit)
+				      struct dst_entry *dst,
+				      struct in6_addr **ip6_daddr)
 {
 	struct ipv6hdr *ip6h = (struct ipv6hdr *)skb_network_header(skb);
-	u8 hop_limit = ip6h->hop_limit, proto = IPPROTO_IPV6;
-	struct rtable *rt = dst_rtable(tuple->dst_cache);
 	__u8 dsfield = ipv6_get_dsfield(ip6h);
+	struct rtable *rt = dst_rtable(dst);
 	struct flowi6 fl6 = {
 		.daddr = tuple->tun.src_v6,
 		.saddr = tuple->tun.dst_v6,
-		.flowi6_proto = proto,
+		.flowi6_proto = IPPROTO_IPV6,
 	};
+	u8 hop_limit = ip6h->hop_limit;
 	int err, mtu;
 	u32 headroom;
 
@@ -674,41 +664,18 @@ static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb,
 	if (err)
 		return err;
 
-	skb_set_inner_ipproto(skb, proto);
+	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
 	headroom = sizeof(*ip6h) + LL_RESERVED_SPACE(rt->dst.dev) +
 		   rt->dst.header_len;
-	if (encap_limit)
-		headroom += 8;
 	err = skb_cow_head(skb, headroom);
 	if (err)
 		return err;
 
 	skb_scrub_packet(skb, true);
 	mtu = dst_mtu(&rt->dst) - sizeof(*ip6h);
-	if (encap_limit)
-		mtu -= 8;
 	mtu = max(mtu, IPV6_MIN_MTU);
 	skb_dst_update_pmtu_no_confirm(skb, mtu);
 
-	if (encap_limit > 0) {
-		struct ipv6_tel_txoption opt = {
-			.dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT,
-			.dst_opt[3] = 1,
-			.dst_opt[4] = encap_limit,
-			.dst_opt[5] = IPV6_TLV_PADN,
-			.dst_opt[6] = 1,
-		};
-		struct ipv6_opt_hdr *hopt;
-
-		opt.ops.dst1opt = (struct ipv6_opt_hdr *)opt.dst_opt;
-		opt.ops.opt_nflen = 8;
-
-		hopt = skb_push(skb, ipv6_optlen(opt.ops.dst1opt));
-		memcpy(hopt, opt.ops.dst1opt, ipv6_optlen(opt.ops.dst1opt));
-		hopt->nexthdr = IPPROTO_IPV6;
-		proto = NEXTHDR_DEST;
-	}
-
 	skb_push(skb, sizeof(*ip6h));
 	skb_reset_network_header(skb);
 
@@ -716,7 +683,7 @@ static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb,
 	ip6_flow_hdr(ip6h, dsfield,
 		     ip6_make_flowlabel(net, skb, fl6.flowlabel, true, &fl6));
 	ip6h->hop_limit = hop_limit;
-	ip6h->nexthdr = proto;
+	ip6h->nexthdr = IPPROTO_IPV6;
 	ip6h->daddr = tuple->tun.src_v6;
 	ip6h->saddr = tuple->tun.dst_v6;
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(*ip6h));
@@ -729,12 +696,11 @@ static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb,
 
 static int nf_flow_tunnel_v6_push(struct net *net, struct sk_buff *skb,
 				  struct flow_offload_tuple *tuple,
-				  struct in6_addr **ip6_daddr,
-				  int encap_limit)
+				  struct dst_entry *dst,
+				  struct in6_addr **ip6_daddr)
 {
 	if (tuple->tun_num)
-		return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, ip6_daddr,
-						  encap_limit);
+		return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, dst, ip6_daddr);
 
 	return 0;
 }
@@ -877,7 +843,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	other_tuple = &flow->tuplehash[!dir].tuple;
 	ip_daddr = other_tuple->src_v4.s_addr;
 
-	if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple, &ip_daddr) < 0)
+	if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple,
+				   tuplehash->tuple.dst_cache, &ip_daddr) < 0)
 		return NF_DROP;
 
 	switch (tuplehash->tuple.xmit_type) {
@@ -1089,7 +1056,7 @@ static int nf_flow_tuple_ipv6(struct nf_flowtable_ctx *ctx, struct sk_buff *skb,
 static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx,
 					struct nf_flowtable *flow_table,
 					struct flow_offload_tuple_rhash *tuplehash,
-					struct sk_buff *skb, int encap_limit)
+					struct sk_buff *skb)
 {
 	enum flow_offload_tuple_dir dir;
 	struct flow_offload *flow;
@@ -1100,11 +1067,8 @@ static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx,
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
 
 	mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset;
-	if (flow->tuplehash[!dir].tuple.tun_num) {
+	if (flow->tuplehash[!dir].tuple.tun_num)
 		mtu -= sizeof(*ip6h);
-		if (encap_limit > 0)
-			mtu -= 8; /* encap limit option */
-	}
 
 	if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
 		return 0;
@@ -1158,7 +1122,6 @@ unsigned int
 nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 			  const struct nf_hook_state *state)
 {
-	int encap_limit = IPV6_DEFAULT_TNL_ENCAP_LIMIT;
 	struct flow_offload_tuple_rhash *tuplehash;
 	struct nf_flowtable *flow_table = priv;
 	struct flow_offload_tuple *other_tuple;
@@ -1177,8 +1140,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	if (tuplehash == NULL)
 		return NF_ACCEPT;
 
-	ret = nf_flow_offload_ipv6_forward(&ctx, flow_table, tuplehash, skb,
-					   encap_limit);
+	ret = nf_flow_offload_ipv6_forward(&ctx, flow_table, tuplehash, skb);
 	if (ret < 0)
 		return NF_DROP;
 	else if (ret == 0)
@@ -1198,7 +1160,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	ip6_daddr = &other_tuple->src_v6;
 
 	if (nf_flow_tunnel_v6_push(state->net, skb, other_tuple,
-				   &ip6_daddr, encap_limit) < 0)
+				   tuplehash->tuple.dst_cache,
+				   &ip6_daddr) < 0)
 		return NF_DROP;
 
 	switch (tuplehash->tuple.xmit_type) {
diff --git a/net/netfilter/nf_flow_table_path.c b/net/netfilter/nf_flow_table_path.c
index 9e88ea6a2eef..14e8a3e4a6f8 100644
--- a/net/netfilter/nf_flow_table_path.c
+++ b/net/netfilter/nf_flow_table_path.c
@@ -53,8 +53,10 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
 	struct neighbour *n;
 	u8 nud_state;
 
-	if (!nft_is_valid_ether_device(dev))
+	if (!nft_is_valid_ether_device(dev)) {
+		eth_zero_addr(ha);
 		goto out;
+	}
 
 	n = dst_neigh_lookup(dst_cache, daddr);
 	if (!n)
@@ -163,10 +165,11 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
 				info->num_encaps++;
 				break;
 			case DEV_PATH_BR_VLAN_UNTAG:
-				if (WARN_ON_ONCE(info->num_encaps-- == 0)) {
+				if (info->num_encaps == 0) {
 					info->indev = NULL;
 					break;
 				}
+				info->num_encaps--;
 				break;
 			case DEV_PATH_BR_VLAN_KEEP:
 				break;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 2bbf5163c0e2..63ff6b4d5d21 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1181,6 +1181,16 @@ int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
 	struct nf_hook_ops *nat_ops;
 	int i, ret;
 
+#ifndef MODULE
+	/* If nf_nat_core is built-in and nf_nat_init() fails, dependent
+	 * modules like nft_chain_nat.ko may still call this function.
+	 * However, nat_net would be invalid, likely pointing to some other
+	 * per-net structure.
+	 */
+	if (WARN_ON_ONCE(!nf_nat_hook))
+		return -EOPNOTSUPP;
+#endif
+
 	if (WARN_ON_ONCE(pf >= ARRAY_SIZE(nat_net->nat_proto_net)))
 		return -EINVAL;
 
diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index 00838c0cc5bb..aea02f6aff09 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -106,6 +106,9 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff,
 	union nf_inet_addr newaddr;
 	__be16 newport;
 
+	if (!ct_sip_info)
+		return 0;
+
 	if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, addr) &&
 	    ct->tuplehash[dir].tuple.src.u.udp.port == port) {
 		newaddr = ct->tuplehash[!dir].tuple.dst.u3;
@@ -158,6 +161,9 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff,
 	__be16 port;
 	int request, in_header;
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	/* Basic rules: requests and responses. */
 	if (strncasecmp(*dptr, "SIP/2.0", strlen("SIP/2.0")) != 0) {
 		if (ct_sip_parse_request(ct, *dptr, *datalen,
@@ -283,13 +289,24 @@ next:
 
 	/* Mangle destination port for Cisco phones, then fix up checksums */
 	if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) {
+		int doff = *dptr - (const char *)skb->data;
 		struct udphdr *uh;
 
+		if (doff <= 0) {
+			DEBUG_NET_WARN_ON_ONCE(1);
+			return NF_DROP;
+		}
+
+		/* ct_sip_info->forced_dport only expected with UDP */
+		if (nf_ct_protonum(ct) != IPPROTO_UDP)
+			return NF_DROP;
+
 		if (skb_ensure_writable(skb, skb->len)) {
 			nf_ct_helper_log(skb, ct, "cannot mangle packet");
 			return NF_DROP;
 		}
 
+		*dptr = skb->data + doff;
 		uh = (void *)skb->data + protoff;
 		uh->dest = ct_sip_info->forced_dport;
 
@@ -326,6 +343,9 @@ static void nf_nat_sip_expected(struct nf_conn *ct,
 	int range_set_for_snat = 0;
 	struct nf_nat_range2 range;
 
+	if (!help)
+		return;
+
 	/* This must be a fresh one. */
 	BUG_ON(ct->status & IPS_NAT_DONE_MASK);
 
@@ -390,6 +410,9 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff,
 	char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")];
 	unsigned int buflen;
 
+	if (!ct_sip_info)
+		return NF_DROP;
+
 	/* Connection will come from reply */
 	if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
 			     &ct->tuplehash[!dir].tuple.dst.u3))
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 57b450024a99..73363ceedebe 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -68,6 +68,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 		nf_queue_sock_put(state->sk);
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	dev_put(entry->bridge_dev);
 	dev_put(entry->physin);
 	dev_put(entry->physout);
 #endif
@@ -84,6 +85,8 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	const struct sk_buff *skb = entry->skb;
+	struct dst_entry *dst = skb_dst(skb);
+	struct net_device *dev = NULL;
 
 	if (nf_bridge_info_exists(skb)) {
 		entry->physin = nf_bridge_get_physindev(skb, entry->state.net);
@@ -92,6 +95,16 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 		entry->physin = NULL;
 		entry->physout = NULL;
 	}
+
+	if (entry->state.pf == NFPROTO_BRIDGE &&
+	    dst && (dst->flags & DST_FAKE_RTABLE))
+		dev = dst_dev_rcu(dst);
+
+	/* Must hold a reference on the bridge device: dst_hold() protects
+	 * the dst itself, but the fake rtable is embedded in bridge-private
+	 * storage that netdevice teardown can free independently.
+	 */
+	entry->bridge_dev = dev;
 #endif
 }
 
@@ -108,6 +121,7 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
 	dev_hold(state->out);
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	dev_hold(entry->bridge_dev);
 	dev_hold(entry->physin);
 	dev_hold(entry->physout);
 #endif
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index ed00114f65f3..acd360515972 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -184,23 +184,23 @@ synproxy_check_timestamp_cookie(struct synproxy_options *opts)
 	opts->options |= opts->tsecr & (1 << 5) ? NF_SYNPROXY_OPT_ECN : 0;
 }
 
-static unsigned int
+static bool
 synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
 		       struct tcphdr *th, struct nf_conn *ct,
 		       enum ip_conntrack_info ctinfo,
 		       const struct nf_conn_synproxy *synproxy)
 {
 	unsigned int optoff, optend;
-	__be32 *ptr, old;
+	u32 new, old;
 
 	if (synproxy->tsoff == 0)
-		return 1;
+		return true;
 
 	optoff = protoff + sizeof(struct tcphdr);
 	optend = protoff + th->doff * 4;
 
 	if (skb_ensure_writable(skb, optend))
-		return 0;
+		return false;
 
 	th = (struct tcphdr *)(skb->data + protoff);
 
@@ -209,7 +209,7 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
 
 		switch (op[0]) {
 		case TCPOPT_EOL:
-			return 1;
+			return true;
 		case TCPOPT_NOP:
 			optoff++;
 			continue;
@@ -217,28 +217,26 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
 			if (optoff + 1 == optend ||
 			    optoff + op[1] > optend ||
 			    op[1] < 2)
-				return 0;
+				return true;
 			if (op[0] == TCPOPT_TIMESTAMP &&
 			    op[1] == TCPOLEN_TIMESTAMP) {
 				if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
-					ptr = (__be32 *)&op[2];
-					old = *ptr;
-					*ptr = htonl(ntohl(*ptr) -
-						     synproxy->tsoff);
+					old = get_unaligned_be32(&op[2]);
+					new = old - synproxy->tsoff;
+					put_unaligned_be32(new, &op[2]);
 				} else {
-					ptr = (__be32 *)&op[6];
-					old = *ptr;
-					*ptr = htonl(ntohl(*ptr) +
-						     synproxy->tsoff);
+					old = get_unaligned_be32(&op[6]);
+					new = old + synproxy->tsoff;
+					put_unaligned_be32(new, &op[6]);
 				}
 				inet_proto_csum_replace4(&th->check, skb,
-							 old, *ptr, false);
-				return 1;
+							 cpu_to_be32(old),
+							 cpu_to_be32(new), false);
 			}
 			optoff += op[1];
 		}
 	}
-	return 1;
+	return true;
 }
 
 #ifdef CONFIG_PROC_FS
@@ -749,7 +747,9 @@ ipv4_synproxy_hook(void *priv, struct sk_buff *skb,
 		break;
 	}
 
-	synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy);
+	if (!synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy))
+		return NF_DROP_REASON(skb, SKB_DROP_REASON_NETFILTER_DROP, ENOMEM);
+
 	return NF_ACCEPT;
 }
 EXPORT_SYMBOL_GPL(ipv4_synproxy_hook);
@@ -1177,7 +1177,9 @@ ipv6_synproxy_hook(void *priv, struct sk_buff *skb,
 		break;
 	}
 
-	synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy);
+	if (!synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy))
+		return NF_DROP_REASON(skb, SKB_DROP_REASON_NETFILTER_DROP, ENOMEM);
+
 	return NF_ACCEPT;
 }
 EXPORT_SYMBOL_GPL(ipv6_synproxy_hook);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 87387adbca65..e1db3e678656 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6559,6 +6559,9 @@ static int nft_get_set_elem(struct nft_ctx *ctx, const struct nft_set *set,
 	if (err < 0)
 		return err;
 
+	if (!elem.priv)
+		return 0;
+
 	err = -ENOMEM;
 	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (skb == NULL)
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 0d16ad82d70c..8710fec30df9 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -32,7 +32,7 @@ MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
 
 struct nfnl_cthelper {
 	struct list_head		list;
-	struct nf_conntrack_helper	helper;
+	struct nf_conntrack_helper	*helper;
 };
 
 static LIST_HEAD(nfnl_cthelper_list);
@@ -41,8 +41,9 @@ static int
 nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
 			struct nf_conn *ct, enum ip_conntrack_info ctinfo)
 {
-	const struct nf_conn_help *help;
 	struct nf_conntrack_helper *helper;
+	const struct nf_conn_help *help;
+	unsigned int helper_flags;
 
 	help = nfct_help(ct);
 	if (help == NULL)
@@ -53,8 +54,10 @@ nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
 	if (helper == NULL)
 		return NF_DROP;
 
+	helper_flags = READ_ONCE(helper->flags);
+
 	/* This is a user-space helper not yet configured, skip. */
-	if ((helper->flags &
+	if ((helper_flags &
 	    (NF_CT_HELPER_F_USERSPACE | NF_CT_HELPER_F_CONFIGURED)) ==
 	     NF_CT_HELPER_F_USERSPACE)
 		return NF_ACCEPT;
@@ -98,6 +101,9 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	struct nf_conn_help *help = nfct_help(ct);
 	const struct nf_conntrack_helper *helper;
 
+	if (!help)
+		return -EINVAL;
+
 	if (attr == NULL)
 		return -EINVAL;
 
@@ -115,6 +121,9 @@ nfnl_cthelper_to_nlattr(struct sk_buff *skb, const struct nf_conn *ct)
 	const struct nf_conn_help *help = nfct_help(ct);
 	const struct nf_conntrack_helper *helper;
 
+	if (!help)
+		return 0;
+
 	helper = rcu_dereference(help->helper);
 	if (helper && helper->data_len &&
 	    nla_put(skb, CTA_HELP_INFO, helper->data_len, &help->data))
@@ -154,6 +163,8 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
 		    tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN);
 	expect_policy->max_expected =
 		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+	if (!expect_policy->max_expected)
+		expect_policy->max_expected = NF_CT_EXPECT_MAX_CNT;
 	if (expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
 		return -EINVAL;
 
@@ -173,7 +184,6 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
 				  const struct nlattr *attr)
 {
 	int i, ret;
-	struct nf_conntrack_expect_policy *expect_policy;
 	struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
 	unsigned int class_max;
 
@@ -192,26 +202,19 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
 	if (class_max > NF_CT_MAX_EXPECT_CLASSES)
 		return -EOVERFLOW;
 
-	expect_policy = kzalloc_objs(struct nf_conntrack_expect_policy,
-				     class_max);
-	if (expect_policy == NULL)
-		return -ENOMEM;
-
 	for (i = 0; i < class_max; i++) {
 		if (!tb[NFCTH_POLICY_SET+i])
 			goto err;
 
-		ret = nfnl_cthelper_expect_policy(&expect_policy[i],
+		ret = nfnl_cthelper_expect_policy(&helper->expect_policy[i],
 						  tb[NFCTH_POLICY_SET+i]);
 		if (ret < 0)
 			goto err;
 	}
 
 	helper->expect_class_max = class_max - 1;
-	helper->expect_policy = expect_policy;
 	return 0;
 err:
-	kfree(expect_policy);
 	return -EINVAL;
 }
 
@@ -227,21 +230,28 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 	if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
 		return -EINVAL;
 
-	nfcth = kzalloc_obj(*nfcth);
+	nfcth = kzalloc_obj(*nfcth, GFP_KERNEL_ACCOUNT);
 	if (nfcth == NULL)
 		return -ENOMEM;
-	helper = &nfcth->helper;
+
+	helper = kzalloc_obj(*helper, GFP_KERNEL_ACCOUNT);
+	if (!helper) {
+		ret = -ENOMEM;
+		goto err_cth;
+	}
+
+	nfcth->helper = helper;
 
 	ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
 	if (ret < 0)
-		goto err1;
+		goto err_helper;
 
 	nla_strscpy(helper->name,
 		    tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
 	size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
 	if (size > sizeof_field(struct nf_conn_help, data)) {
 		ret = -ENOMEM;
-		goto err2;
+		goto err_helper;
 	}
 	helper->data_len = size;
 
@@ -270,15 +280,15 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 		}
 	}
 
-	ret = nf_conntrack_helper_register(helper);
+	ret = __nf_conntrack_helper_register(helper);
 	if (ret < 0)
-		goto err2;
+		goto err_helper;
 
 	list_add_tail(&nfcth->list, &nfnl_cthelper_list);
 	return 0;
-err2:
-	kfree(helper->expect_policy);
-err1:
+err_helper:
+	kfree(helper);
+err_cth:
 	kfree(nfcth);
 	return ret;
 }
@@ -306,6 +316,8 @@ nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy,
 
 	new_policy->max_expected =
 		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+	if (!new_policy->max_expected)
+		new_policy->max_expected = NF_CT_EXPECT_MAX_CNT;
 	if (new_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
 		return -EINVAL;
 
@@ -346,8 +358,8 @@ static int nfnl_cthelper_update_policy_all(struct nlattr *tb[],
 	for (i = 0; i < helper->expect_class_max + 1; i++) {
 		policy = (struct nf_conntrack_expect_policy *)
 				&helper->expect_policy[i];
-		policy->max_expected = new_policy->max_expected;
-		policy->timeout	= new_policy->timeout;
+		policy->max_expected = new_policy[i].max_expected;
+		policy->timeout	= new_policy[i].timeout;
 	}
 
 err:
@@ -404,10 +416,10 @@ nfnl_cthelper_update(const struct nlattr * const tb[],
 
 		switch(status) {
 		case NFCT_HELPER_STATUS_ENABLED:
-			helper->flags |= NF_CT_HELPER_F_CONFIGURED;
+			WRITE_ONCE(helper->flags, helper->flags | NF_CT_HELPER_F_CONFIGURED);
 			break;
 		case NFCT_HELPER_STATUS_DISABLED:
-			helper->flags &= ~NF_CT_HELPER_F_CONFIGURED;
+			WRITE_ONCE(helper->flags, helper->flags & ~NF_CT_HELPER_F_CONFIGURED);
 			break;
 		}
 	}
@@ -436,7 +448,7 @@ static int nfnl_cthelper_new(struct sk_buff *skb, const struct nfnl_info *info,
 		return ret;
 
 	list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
-		cur = &nlcth->helper;
+		cur = nlcth->helper;
 
 		if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
 			continue;
@@ -529,8 +541,8 @@ static int
 nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 			int event, struct nf_conntrack_helper *helper)
 {
-	struct nlmsghdr *nlh;
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
+	struct nlmsghdr *nlh;
 	int status;
 
 	event = nfnl_msg_type(NFNL_SUBSYS_CTHELPER, event);
@@ -554,7 +566,7 @@ nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	if (nla_put_be32(skb, NFCTH_PRIV_DATA_LEN, htonl(helper->data_len)))
 		goto nla_put_failure;
 
-	if (helper->flags & NF_CT_HELPER_F_CONFIGURED)
+	if (READ_ONCE(helper->flags) & NF_CT_HELPER_F_CONFIGURED)
 		status = NFCT_HELPER_STATUS_ENABLED;
 	else
 		status = NFCT_HELPER_STATUS_DISABLED;
@@ -575,6 +587,7 @@ static int
 nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct nf_conntrack_helper *cur, *last;
+	unsigned int helper_flags;
 
 	rcu_read_lock();
 	last = (struct nf_conntrack_helper *)cb->args[1];
@@ -583,8 +596,10 @@ restart:
 		hlist_for_each_entry_rcu(cur,
 				&nf_ct_helper_hash[cb->args[0]], hnode) {
 
+			helper_flags = READ_ONCE(cur->flags);
+
 			/* skip non-userspace conntrack helpers. */
-			if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
+			if (!(helper_flags & NF_CT_HELPER_F_USERSPACE))
 				continue;
 
 			if (cb->args[1]) {
@@ -644,7 +659,7 @@ static int nfnl_cthelper_get(struct sk_buff *skb, const struct nfnl_info *info,
 	}
 
 	list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
-		cur = &nlcth->helper;
+		cur = nlcth->helper;
 		if (helper_name &&
 		    strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
 			continue;
@@ -702,7 +717,7 @@ static int nfnl_cthelper_del(struct sk_buff *skb, const struct nfnl_info *info,
 
 	ret = -ENOENT;
 	list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
-		cur = &nlcth->helper;
+		cur = nlcth->helper;
 		j++;
 
 		if (helper_name &&
@@ -717,7 +732,6 @@ static int nfnl_cthelper_del(struct sk_buff *skb, const struct nfnl_info *info,
 		if (refcount_dec_if_one(&cur->refcnt)) {
 			found = true;
 			nf_conntrack_helper_unregister(cur);
-			kfree(cur->expect_policy);
 
 			list_del(&nlcth->list);
 			kfree(nlcth);
@@ -790,10 +804,9 @@ static void __exit nfnl_cthelper_exit(void)
 	nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
 
 	list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
-		cur = &nlcth->helper;
+		cur = nlcth->helper;
 
 		nf_conntrack_helper_unregister(cur);
-		kfree(cur->expect_policy);
 		kfree(nlcth);
 	}
 }
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index dca6826af7de..170d3db860c5 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -37,11 +37,8 @@ struct ctnl_timeout {
 	struct list_head	head;
 	struct list_head	free_head;
 	struct rcu_head		rcu_head;
-	refcount_t		refcnt;
 	char			name[CTNL_TIMEOUT_NAME_MAX];
-
-	/* must be at the end */
-	struct nf_ct_timeout	timeout;
+	struct nf_ct_timeout	*timeout;
 };
 
 struct nfct_timeout_pernet {
@@ -132,12 +129,12 @@ static int cttimeout_new_timeout(struct sk_buff *skb,
 			/* You cannot replace one timeout policy by another of
 			 * different kind, sorry.
 			 */
-			if (matching->timeout.l3num != l3num ||
-			    matching->timeout.l4proto->l4proto != l4num)
+			if (matching->timeout->l3num != l3num ||
+			    matching->timeout->l4proto->l4proto != l4num)
 				return -EINVAL;
 
-			return ctnl_timeout_parse_policy(&matching->timeout.data,
-							 matching->timeout.l4proto,
+			return ctnl_timeout_parse_policy(&matching->timeout->data,
+							 matching->timeout->l4proto,
 							 info->net,
 							 cda[CTA_TIMEOUT_DATA]);
 		}
@@ -153,26 +150,35 @@ static int cttimeout_new_timeout(struct sk_buff *skb,
 		goto err_proto_put;
 	}
 
-	timeout = kzalloc(sizeof(struct ctnl_timeout) +
-			  l4proto->ctnl_timeout.obj_size, GFP_KERNEL);
+	timeout = kzalloc(sizeof(*timeout), GFP_KERNEL);
 	if (timeout == NULL) {
 		ret = -ENOMEM;
 		goto err_proto_put;
 	}
 
-	ret = ctnl_timeout_parse_policy(&timeout->timeout.data, l4proto,
+	timeout->timeout = kzalloc(sizeof(*timeout->timeout) +
+				   l4proto->ctnl_timeout.obj_size, GFP_KERNEL);
+	if (!timeout->timeout) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = ctnl_timeout_parse_policy(&timeout->timeout->data, l4proto,
 					info->net, cda[CTA_TIMEOUT_DATA]);
 	if (ret < 0)
-		goto err;
+		goto err_free_timeout_policy;
 
 	strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME]));
-	timeout->timeout.l3num = l3num;
-	timeout->timeout.l4proto = l4proto;
-	refcount_set(&timeout->refcnt, 1);
+	timeout->timeout->l3num = l3num;
+	timeout->timeout->l4proto = l4proto;
+	refcount_set(&timeout->timeout->refcnt, 1);
 	__module_get(THIS_MODULE);
 	list_add_tail_rcu(&timeout->head, &pernet->nfct_timeout_list);
 
 	return 0;
+
+err_free_timeout_policy:
+	kfree(timeout->timeout);
 err:
 	kfree(timeout);
 err_proto_put:
@@ -185,7 +191,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 {
 	struct nlmsghdr *nlh;
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
-	const struct nf_conntrack_l4proto *l4proto = timeout->timeout.l4proto;
+	const struct nf_conntrack_l4proto *l4proto = timeout->timeout->l4proto;
 	struct nlattr *nest_parms;
 	int ret;
 
@@ -197,17 +203,17 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 
 	if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) ||
 	    nla_put_be16(skb, CTA_TIMEOUT_L3PROTO,
-			 htons(timeout->timeout.l3num)) ||
+			 htons(timeout->timeout->l3num)) ||
 	    nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto) ||
 	    nla_put_be32(skb, CTA_TIMEOUT_USE,
-			 htonl(refcount_read(&timeout->refcnt))))
+			 htonl(refcount_read(&timeout->timeout->refcnt))))
 		goto nla_put_failure;
 
 	nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA);
 	if (!nest_parms)
 		goto nla_put_failure;
 
-	ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->timeout.data);
+	ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->timeout->data);
 	if (ret < 0)
 		goto nla_put_failure;
 
@@ -307,23 +313,17 @@ static int cttimeout_get_timeout(struct sk_buff *skb,
 	return ret;
 }
 
-/* try to delete object, fail if it is still in use. */
-static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
+static void ctnl_timeout_del(struct net *net, struct ctnl_timeout *timeout)
 {
-	int ret = 0;
+	/* We are protected by nfnl mutex. */
+	list_del_rcu(&timeout->head);
+	nf_ct_untimeout(net, timeout->timeout);
 
-	/* We want to avoid races with ctnl_timeout_put. So only when the
-	 * current refcnt is 1, we decrease it to 0.
-	 */
-	if (refcount_dec_if_one(&timeout->refcnt)) {
-		/* We are protected by nfnl mutex. */
-		list_del_rcu(&timeout->head);
-		nf_ct_untimeout(net, &timeout->timeout);
-		kfree_rcu(timeout, rcu_head);
-	} else {
-		ret = -EBUSY;
-	}
-	return ret;
+	if (refcount_dec_and_test(&timeout->timeout->refcnt))
+		kfree_rcu(timeout->timeout, rcu);
+
+	kfree_rcu(timeout, rcu_head);
+	module_put(THIS_MODULE);
 }
 
 static int cttimeout_del_timeout(struct sk_buff *skb,
@@ -338,7 +338,7 @@ static int cttimeout_del_timeout(struct sk_buff *skb,
 	if (!cda[CTA_TIMEOUT_NAME]) {
 		list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_list,
 					 head)
-			ctnl_timeout_try_del(info->net, cur);
+			ctnl_timeout_del(info->net, cur);
 
 		return 0;
 	}
@@ -348,10 +348,8 @@ static int cttimeout_del_timeout(struct sk_buff *skb,
 		if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0)
 			continue;
 
-		ret = ctnl_timeout_try_del(info->net, cur);
-		if (ret < 0)
-			return ret;
-
+		ctnl_timeout_del(info->net, cur);
+		ret = 0;
 		break;
 	}
 	return ret;
@@ -511,24 +509,22 @@ static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net,
 		if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0)
 			continue;
 
-		if (!refcount_inc_not_zero(&timeout->refcnt))
+		if (!refcount_inc_not_zero(&timeout->timeout->refcnt))
 			goto err;
 		matching = timeout;
+		__module_get(THIS_MODULE);
 		break;
 	}
 err:
-	return matching ? &matching->timeout : NULL;
+	return matching ? matching->timeout : NULL;
 }
 
-static void ctnl_timeout_put(struct nf_ct_timeout *t)
+static void ctnl_timeout_put(struct nf_ct_timeout *timeout)
 {
-	struct ctnl_timeout *timeout =
-		container_of(t, struct ctnl_timeout, timeout);
+	if (refcount_dec_and_test(&timeout->refcnt))
+		kfree_rcu(timeout, rcu);
 
-	if (refcount_dec_and_test(&timeout->refcnt)) {
-		kfree_rcu(timeout, rcu_head);
-		module_put(THIS_MODULE);
-	}
+	module_put(THIS_MODULE);
 }
 
 static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = {
@@ -609,8 +605,11 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 	list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, free_head) {
 		list_del(&cur->free_head);
 
-		if (refcount_dec_and_test(&cur->refcnt))
-			kfree_rcu(cur, rcu_head);
+		if (refcount_dec_and_test(&cur->timeout->refcnt))
+			kfree_rcu(cur->timeout, rcu);
+
+		kfree_rcu(cur, rcu_head);
+		module_put(THIS_MODULE);
 	}
 }
 
@@ -649,24 +648,13 @@ err_out:
 	return ret;
 }
 
-static int untimeout(struct nf_conn *ct, void *timeout)
-{
-	struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct);
-
-	if (timeout_ext)
-		RCU_INIT_POINTER(timeout_ext->timeout, NULL);
-
-	return 0;
-}
-
 static void __exit cttimeout_exit(void)
 {
 	nfnetlink_subsys_unregister(&cttimeout_subsys);
 
 	unregister_pernet_subsys(&cttimeout_ops);
 	RCU_INIT_POINTER(nf_ct_timeout_hook, NULL);
-
-	nf_ct_iterate_destroy(untimeout, NULL);
+	synchronize_net();
 }
 
 module_init(cttimeout_init);
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index acb753ec5697..92002079f8ea 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -95,11 +95,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 
 			switch (*optp) {
 			case OSFOPT_MSS:
-				mss = optp[3];
-				mss <<= 8;
-				mss |= optp[2];
-
-				mss = ntohs((__force __be16)mss);
+				mss = get_unaligned_be16(&optp[2]);
 				break;
 			case OSFOPT_TS:
 				break;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index e0cf9977887f..d4f5003280d7 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1270,6 +1270,9 @@ dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex)
 
 	if (physinif == ifindex || physoutif == ifindex)
 		return 1;
+
+	if (entry->bridge_dev && entry->bridge_dev->ifindex == ifindex)
+		return 1;
 #endif
 	if (entry->skb_dev && entry->skb_dev->ifindex == ifindex)
 		return 1;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 0caa9304d2d0..63864b928259 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -397,6 +397,22 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 	return 0;
 }
 
+static int nft_target_bridge_validate(const struct nft_ctx *ctx,
+				      const struct nft_expr *expr)
+{
+	struct xt_target *target = expr->ops->data;
+
+	/* Do not allow UNSPEC to stand-in for NFPROTO_BRIDGE
+	 * targets: they are incompatible.  ebtables targets return
+	 * EBT_ACCEPT, DROP and so on which are not compatible with
+	 * NF_ACCEPT, NF_DROP and so on.
+	 */
+	if (target->family != NFPROTO_BRIDGE)
+		return -ENOENT;
+
+	return nft_target_validate(ctx, expr);
+}
+
 static void __nft_match_eval(const struct nft_expr *expr,
 			     struct nft_regs *regs,
 			     const struct nft_pktinfo *pkt,
@@ -932,13 +948,15 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	ops->init = nft_target_init;
 	ops->destroy = nft_target_destroy;
 	ops->dump = nft_target_dump;
-	ops->validate = nft_target_validate;
 	ops->data = target;
 
-	if (family == NFPROTO_BRIDGE)
+	if (family == NFPROTO_BRIDGE) {
 		ops->eval = nft_target_eval_bridge;
-	else
+		ops->validate = nft_target_bridge_validate;
+	} else {
 		ops->eval = nft_target_eval_xt;
+		ops->validate = nft_target_validate;
+	}
 
 	return ops;
 err:
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 357513c6dcea..8a79e9c1e1ae 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -897,8 +897,6 @@ static void nft_ct_timeout_obj_eval(struct nft_object *obj,
 		}
 	}
 
-	rcu_assign_pointer(timeout->timeout, priv->timeout);
-
 	/* adjust the timeout as per 'new' state. ct is unconfirmed,
 	 * so the current timestamp must not be added.
 	 */
@@ -949,6 +947,7 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx,
 
 	timeout->l3num = l3num;
 	timeout->l4proto = l4proto;
+	refcount_set(&timeout->refcnt, 1);
 
 	ret = nf_ct_netns_get(ctx->net, ctx->family);
 	if (ret < 0)
@@ -969,10 +968,10 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx,
 	struct nft_ct_timeout_obj *priv = nft_obj_data(obj);
 	struct nf_ct_timeout *timeout = priv->timeout;
 
-	nf_queue_nf_hook_drop(ctx->net);
 	nf_ct_untimeout(ctx->net, timeout);
 	nf_ct_netns_put(ctx->net, ctx->family);
-	kfree_rcu(priv->timeout, rcu);
+	if (refcount_dec_and_test(&timeout->refcnt))
+		kfree_rcu(priv->timeout, rcu);
 }
 
 static int nft_ct_timeout_obj_dump(struct sk_buff *skb,
@@ -1147,7 +1146,6 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj,
 	help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 	if (help) {
 		rcu_assign_pointer(help->helper, to_assign);
-		set_bit(IPS_HELPER_BIT, &ct->status);
 
 		if ((ct->status & IPS_NAT_MASK) && !nfct_seqadj(ct))
 			if (!nfct_seqadj_ext_add(ct))
@@ -1218,11 +1216,23 @@ struct nft_ct_expect_obj {
 	u32		timeout;
 };
 
+static int nft_ct_expect_timeout_get(const struct nlattr *attr, u32 *val)
+{
+	unsigned long jiffies_val = msecs_to_jiffies(nla_get_u32(attr));
+
+	if (jiffies_val > UINT_MAX)
+		return -ERANGE;
+
+	*val = jiffies_val;
+	return 0;
+}
+
 static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 				  const struct nlattr * const tb[],
 				  struct nft_object *obj)
 {
 	struct nft_ct_expect_obj *priv = nft_obj_data(obj);
+	int err;
 
 	if (!tb[NFTA_CT_EXPECT_L4PROTO] ||
 	    !tb[NFTA_CT_EXPECT_DPORT] ||
@@ -1257,8 +1267,11 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 		return -EOPNOTSUPP;
 	}
 
+	err = nft_ct_expect_timeout_get(tb[NFTA_CT_EXPECT_TIMEOUT], &priv->timeout);
+	if (err)
+		return err;
+
 	priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]);
-	priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]);
 	priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]);
 
 	return nf_ct_netns_get(ctx->net, ctx->family);
@@ -1278,7 +1291,7 @@ static int nft_ct_expect_obj_dump(struct sk_buff *skb,
 	if (nla_put_be16(skb, NFTA_CT_EXPECT_L3PROTO, htons(priv->l3num)) ||
 	    nla_put_u8(skb, NFTA_CT_EXPECT_L4PROTO, priv->l4proto) ||
 	    nla_put_be16(skb, NFTA_CT_EXPECT_DPORT, priv->dport) ||
-	    nla_put_u32(skb, NFTA_CT_EXPECT_TIMEOUT, priv->timeout) ||
+	    nla_put_u32(skb, NFTA_CT_EXPECT_TIMEOUT, jiffies_to_msecs(priv->timeout)) ||
 	    nla_put_u8(skb, NFTA_CT_EXPECT_SIZE, priv->size))
 		return -1;
 
@@ -1328,7 +1341,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
 		          &ct->tuplehash[!dir].tuple.src.u3,
 		          &ct->tuplehash[!dir].tuple.dst.u3,
 		          priv->l4proto, NULL, &priv->dport);
-	exp->timeout.expires = jiffies + priv->timeout * HZ;
+	exp->timeout += priv->timeout;
 
 	if (nf_ct_expect_related(exp, 0) != 0)
 		regs->verdict.code = NF_DROP;
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index a1632e308f18..7529f58a6d36 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -31,6 +31,15 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr)
 	const struct nft_fib *priv = nft_expr_priv(expr);
 	unsigned int hooks;
 
+	switch (ctx->family) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
 	case NFT_FIB_RESULT_OIFNAME:
diff --git a/net/netfilter/nft_fib_netdev.c b/net/netfilter/nft_fib_netdev.c
index 3f3478abd845..5774a7544027 100644
--- a/net/netfilter/nft_fib_netdev.c
+++ b/net/netfilter/nft_fib_netdev.c
@@ -50,6 +50,33 @@ static void nft_fib_netdev_eval(const struct nft_expr *expr,
 	regs->verdict.code = NFT_BREAK;
 }
 
+static int nft_fib_netdev_validate(const struct nft_ctx *ctx,
+				   const struct nft_expr *expr)
+{
+	const struct nft_fib *priv = nft_expr_priv(expr);
+	unsigned int hooks;
+
+	switch (priv->result) {
+	case NFT_FIB_RESULT_OIF:
+	case NFT_FIB_RESULT_OIFNAME:
+		hooks = (1 << NF_NETDEV_INGRESS);
+		break;
+	case NFT_FIB_RESULT_ADDRTYPE:
+		if (priv->flags & NFTA_FIB_F_IIF)
+			hooks = (1 << NF_NETDEV_INGRESS);
+		else if (priv->flags & NFTA_FIB_F_OIF)
+			hooks = (1 << NF_NETDEV_EGRESS);
+		else
+			hooks = (1 << NF_NETDEV_INGRESS) |
+				(1 << NF_NETDEV_EGRESS);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
+}
+
 static struct nft_expr_type nft_fib_netdev_type;
 static const struct nft_expr_ops nft_fib_netdev_ops = {
 	.type		= &nft_fib_netdev_type,
@@ -57,7 +84,7 @@ static const struct nft_expr_ops nft_fib_netdev_ops = {
 	.eval		= nft_fib_netdev_eval,
 	.init		= nft_fib_init,
 	.dump		= nft_fib_dump,
-	.validate	= nft_fib_validate,
+	.validate	= nft_fib_netdev_validate,
 };
 
 static struct nft_expr_type nft_fib_netdev_type __read_mostly = {
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index b9e88d7cf308..a48c2f765bba 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -95,7 +95,6 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 			      struct nft_regs *regs,
 			      const struct nft_pktinfo *pkt)
 {
-	u8 *nf_dup_skb_recursion = nf_get_nf_dup_skb_recursion();
 	struct nft_fwd_neigh *priv = nft_expr_priv(expr);
 	void *addr = &regs->data[priv->sreg_addr];
 	int oif = regs->data[priv->sreg_dev];
@@ -154,13 +153,15 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 		goto out;
 	}
 
-	if (*nf_dup_skb_recursion > NF_RECURSION_LIMIT) {
+	dev = dev_get_by_index_rcu(nft_net(pkt), oif);
+	if (!dev) {
 		verdict = NF_DROP;
 		goto out;
 	}
 
-	dev = dev_get_by_index_rcu(nft_net(pkt), oif);
-	if (dev == NULL) {
+	local_bh_disable();
+	if (nf_dev_xmit_recursion()) {
+		local_bh_enable();
 		verdict = NF_DROP;
 		goto out;
 	}
@@ -169,16 +170,18 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
 		skb = skb_expand_head(skb, hh_len);
 		if (!skb) {
-			verdict = NF_STOLEN;
+			local_bh_enable();
 			goto out;
 		}
 	}
 
 	skb->dev = dev;
 	skb_clear_tstamp(skb);
-	(*nf_dup_skb_recursion)++;
+
+	nf_dev_xmit_recursion_inc();
 	neigh_xmit(neigh_table, dev, addr, skb);
-	(*nf_dup_skb_recursion)--;
+	nf_dev_xmit_recursion_dec();
+	local_bh_enable();
 out:
 	regs->verdict.code = verdict;
 }
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 9fafe5afc490..8e2c3601133f 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -103,13 +103,13 @@ void nft_lookup_eval(const struct nft_expr *expr,
 	bool found;
 
 	ext = nft_set_do_lookup(net, set, &regs->data[priv->sreg]);
+	if (!ext)
+		ext = nft_set_catchall_lookup(net, set);
+
 	found = !!ext ^ priv->invert;
 	if (!found) {
-		ext = nft_set_catchall_lookup(net, set);
-		if (!ext) {
-			regs->verdict.code = NFT_BREAK;
-			return;
-		}
+		regs->verdict.code = NFT_BREAK;
+		return;
 	}
 
 	if (ext) {
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 5b25851381e5..db937d66210d 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -635,8 +635,8 @@ static int nft_meta_get_validate_xfrm(const struct nft_ctx *ctx)
 #endif
 }
 
-static int nft_meta_get_validate(const struct nft_ctx *ctx,
-				 const struct nft_expr *expr)
+int nft_meta_get_validate(const struct nft_ctx *ctx,
+			  const struct nft_expr *expr)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 
@@ -652,6 +652,7 @@ static int nft_meta_get_validate(const struct nft_ctx *ctx,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nft_meta_get_validate);
 
 int nft_meta_set_validate(const struct nft_ctx *ctx,
 			  const struct nft_expr *expr)
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 484a5490832e..4438d05f8018 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -224,11 +224,17 @@ static int nft_payload_init(const struct nft_ctx *ctx,
 			    const struct nlattr * const tb[])
 {
 	struct nft_payload *priv = nft_expr_priv(expr);
+	u32 offset;
+	int err;
 
 	priv->base   = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
-	priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
 
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U16_MAX, &offset);
+	if (err < 0)
+		return err;
+	priv->offset = offset;
+
 	return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG],
 					&priv->dreg, NULL, NFT_DATA_VALUE,
 					priv->len);
@@ -621,7 +627,8 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx,
 				  const struct nlattr * const tb[])
 {
 	struct nft_payload *priv = nft_expr_priv(expr);
-	u32 base;
+	u32 base, offset;
+	int err;
 
 	if (!tb[NFTA_PAYLOAD_BASE] || !tb[NFTA_PAYLOAD_OFFSET] ||
 	    !tb[NFTA_PAYLOAD_LEN] || !tb[NFTA_PAYLOAD_DREG])
@@ -639,8 +646,11 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx,
 	}
 
 	priv->base   = base;
-	priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U16_MAX, &offset);
+	if (err < 0)
+		return err;
+	priv->offset = offset;
 
 	return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG],
 					&priv->dreg, NULL, NFT_DATA_VALUE,
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 50d4a4f04309..61b8601ee377 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -342,6 +342,8 @@
 #include "nft_set_pipapo_avx2.h"
 #include "nft_set_pipapo.h"
 
+static void nft_pipapo_abort(const struct nft_set *set);
+
 /**
  * pipapo_refill() - For each set bit, set bits from selected mapping table item
  * @map:	Bitmap to be scanned for set bits
@@ -1296,7 +1298,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	const u8 *start_p, *end_p;
 	int i, bsize_max, err = 0;
 
-	if (!m)
+	if (!m || m->state == NFT_PIPAPO_CLONE_ERR)
 		return -ENOMEM;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END))
@@ -1367,8 +1369,10 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 		else
 			ret = pipapo_expand(f, start, end, f->groups * f->bb);
 
-		if (ret < 0)
-			return ret;
+		if (ret < 0) {
+			err = ret;
+			goto abort;
+		}
 
 		if (f->bsize > bsize_max)
 			bsize_max = f->bsize;
@@ -1384,7 +1388,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
 		err = pipapo_realloc_scratch(m, bsize_max);
 		if (err)
-			return err;
+			goto abort;
 
 		m->bsize_max = bsize_max;
 	} else {
@@ -1396,7 +1400,26 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
 	pipapo_map(m, rulemap, e);
 
+	m->state = NFT_PIPAPO_CLONE_MOD;
 	return 0;
+abort:
+	DEBUG_NET_WARN_ON_ONCE(m->state == NFT_PIPAPO_CLONE_ERR);
+
+	/* Two rollback cases:
+	 * 1) no previous changes.  nft_pipapo_abort is not
+	 * guaranteed to be invoked (there might be no further
+	 * add/delete requests coming after this).
+	 *
+	 * 2) we had previous changes: there are transaction
+	 * records pointing to this set.  Leave the rollback to
+	 * the transaction handling.
+	 */
+	if (m->state == NFT_PIPAPO_CLONE_NEW)
+		nft_pipapo_abort(set); /* releases m */
+	else
+		m->state = NFT_PIPAPO_CLONE_ERR;
+
+	return err;
 }
 
 /**
@@ -1473,6 +1496,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 		dst++;
 	}
 
+	new->state = NFT_PIPAPO_CLONE_NEW;
 	return new;
 
 out_mt:
@@ -1896,7 +1920,7 @@ nft_pipapo_deactivate(const struct net *net, const struct nft_set *set,
 	/* removal must occur on priv->clone, if we are low on memory
 	 * we have no choice and must fail the removal request.
 	 */
-	if (!m)
+	if (!m || m->state == NFT_PIPAPO_CLONE_ERR)
 		return NULL;
 
 	e = pipapo_get(m, (const u8 *)elem->key.val.data,
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index b82abb03576e..a19e980d06ef 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -131,9 +131,16 @@ struct nft_pipapo_scratch {
 	unsigned long __map[];
 };
 
+enum nft_pipapo_clone_state {
+	NFT_PIPAPO_CLONE_NEW,
+	NFT_PIPAPO_CLONE_MOD,
+	NFT_PIPAPO_CLONE_ERR,
+};
+
 /**
  * struct nft_pipapo_match - Data used for lookup and matching
  * @field_count:	Amount of fields in set
+ * @state:		add/delete state; used from control plane
  * @bsize_max:		Maximum lookup table bucket size of all fields, in longs
  * @scratch:		Preallocated per-CPU maps for partial matching results
  * @rcu:		Matching data is swapped on commits
@@ -141,6 +148,7 @@ struct nft_pipapo_scratch {
  */
 struct nft_pipapo_match {
 	u8 field_count;
+	enum nft_pipapo_clone_state state:8;
 	unsigned int bsize_max;
 	struct nft_pipapo_scratch * __percpu *scratch;
 	struct rcu_head rcu;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 560fbe6e3f75..b4b67f48ad64 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -184,10 +184,14 @@ nft_rbtree_get(const struct net *net, const struct nft_set *set,
 	if (!interval || nft_set_elem_expired(interval->from))
 		return ERR_PTR(-ENOENT);
 
-	if (flags & NFT_SET_ELEM_INTERVAL_END)
+	if (flags & NFT_SET_ELEM_INTERVAL_END) {
+		if (!interval->to)
+			return NULL;
+
 		rbe = container_of(interval->to, struct nft_rbtree_elem, ext);
-	else
+	} else {
 		rbe = container_of(interval->from, struct nft_rbtree_elem, ext);
+	}
 
 	return &rbe->priv;
 }
diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c
index 7641f249614c..9ed288c9d168 100644
--- a/net/netfilter/nft_synproxy.c
+++ b/net/netfilter/nft_synproxy.c
@@ -24,14 +24,13 @@ static const struct nla_policy nft_synproxy_policy[NFTA_SYNPROXY_MAX + 1] = {
 static void nft_synproxy_tcp_options(struct synproxy_options *opts,
 				     const struct tcphdr *tcp,
 				     struct synproxy_net *snet,
-				     struct nf_synproxy_info *info,
-				     const struct nft_synproxy *priv)
+				     struct nf_synproxy_info *info)
 {
 	this_cpu_inc(snet->stats->syn_received);
 	if (tcp->ece && tcp->cwr)
 		opts->options |= NF_SYNPROXY_OPT_ECN;
 
-	opts->options &= priv->info.options;
+	opts->options &= info->options;
 	opts->mss_encode = opts->mss_option;
 	opts->mss_option = info->mss;
 	if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP)
@@ -56,7 +55,7 @@ static void nft_synproxy_eval_v4(const struct nft_synproxy *priv,
 
 	if (tcp->syn) {
 		/* Initial SYN from client */
-		nft_synproxy_tcp_options(opts, tcp, snet, &info, priv);
+		nft_synproxy_tcp_options(opts, tcp, snet, &info);
 		synproxy_send_client_synack(net, skb, tcp, opts);
 		consume_skb(skb);
 		regs->verdict.code = NF_STOLEN;
@@ -87,7 +86,7 @@ static void nft_synproxy_eval_v6(const struct nft_synproxy *priv,
 
 	if (tcp->syn) {
 		/* Initial SYN from client */
-		nft_synproxy_tcp_options(opts, tcp, snet, &info, priv);
+		nft_synproxy_tcp_options(opts, tcp, snet, &info);
 		synproxy_send_client_synack_ipv6(net, skb, tcp, opts);
 		consume_skb(skb);
 		regs->verdict.code = NF_STOLEN;
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index d2aeacf94230..b94f004d5f5c 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -284,7 +284,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
 	struct nf_conn_help *help;
 
 	if (ct) {
-		if (info->helper[0] || info->timeout[0])
+		if (info->helper[0])
 			nf_queue_nf_hook_drop(par->net);
 
 		help = nfct_help(ct);
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index 908fd5f2c3c8..eaf2511d63f0 100644
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -107,7 +107,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	}
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL)
+	if (!ct || nf_ct_is_template(ct))
 		return false;
 
 	if (ct->master)
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 4277084de2e7..2cf27f7d59b9 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -112,6 +112,16 @@ static int connmark_tg_check(const struct xt_tgchk_param *par)
 	return ret;
 }
 
+static int connmark_tg_check_v2(const struct xt_tgchk_param *par)
+{
+	const struct xt_connmark_tginfo2 *info = par->targinfo;
+
+	if (info->shift_dir > D_SHIFT_RIGHT || info->shift_bits >= 32)
+		return -EINVAL;
+
+	return connmark_tg_check(par);
+}
+
 static void connmark_tg_destroy(const struct xt_tgdtor_param *par)
 {
 	nf_ct_netns_put(par->net, par->family);
@@ -162,7 +172,7 @@ static struct xt_target connmark_tg_reg[] __read_mostly = {
 		.name           = "CONNMARK",
 		.revision       = 2,
 		.family         = NFPROTO_IPV4,
-		.checkentry     = connmark_tg_check,
+		.checkentry     = connmark_tg_check_v2,
 		.target         = connmark_tg_v2,
 		.targetsize     = sizeof(struct xt_connmark_tginfo2),
 		.destroy        = connmark_tg_destroy,
@@ -183,7 +193,7 @@ static struct xt_target connmark_tg_reg[] __read_mostly = {
 		.name           = "CONNMARK",
 		.revision       = 2,
 		.family         = NFPROTO_IPV6,
-		.checkentry     = connmark_tg_check,
+		.checkentry     = connmark_tg_check_v2,
 		.target         = connmark_tg_v2,
 		.targetsize     = sizeof(struct xt_connmark_tginfo2),
 		.destroy        = connmark_tg_destroy,
diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c
index b4f7bbc3f3ca..51c7f7ce88d9 100644
--- a/net/netfilter/xt_nat.c
+++ b/net/netfilter/xt_nat.c
@@ -26,6 +26,15 @@ static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par)
 
 static int xt_nat_checkentry(const struct xt_tgchk_param *par)
 {
+	switch (par->family) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	return nf_ct_netns_get(par->net, par->family);
 }
 
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index dd98f758176c..a388881c68d4 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -130,11 +130,6 @@ static int physdev_mt_check(const struct xt_mtchk_param *par)
 		if (X(physoutdev))
 			return -ENAMETOOLONG;
 	}
-
-	if (X(in_mask))
-		return -ENAMETOOLONG;
-	if (X(out_mask))
-		return -ENAMETOOLONG;
 #undef X
 
 	if (!brnf_probed) {
diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c
index b1d736c15fcb..7c05b6342578 100644
--- a/net/netfilter/xt_rateest.c
+++ b/net/netfilter/xt_rateest.c
@@ -16,7 +16,7 @@ xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_rateest_match_info *info = par->matchinfo;
 	struct gnet_stats_rate_est64 sample = {0};
-	u_int32_t bps1, bps2, pps1, pps2;
+	u64 bps1, bps2, pps1, pps2;
 	bool ret = true;
 
 	gen_estimator_read(&info->est1->rate_est, &sample);
diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c
index 1ae7f926b0df..dabbaa742874 100644
--- a/net/netfilter/xt_u32.c
+++ b/net/netfilter/xt_u32.c
@@ -106,7 +106,7 @@ static int u32_mt_checkentry(const struct xt_mtchk_param *par)
 {
 	const struct xt_u32 *data = par->matchinfo;
 	const struct xt_u32_test *ct;
-	unsigned int i;
+	unsigned int i, j;
 
 	if (data->ntests > ARRAY_SIZE(data->tests))
 		return -EINVAL;
@@ -117,6 +117,16 @@ static int u32_mt_checkentry(const struct xt_mtchk_param *par)
 		if (ct->nnums > ARRAY_SIZE(ct->location) ||
 		    ct->nvalues > ARRAY_SIZE(ct->value))
 			return -EINVAL;
+
+		for (j = 1; j < ct->nnums; ++j) {
+			switch (ct->location[j].nextop) {
+			case XT_U32_LEFTSH:
+			case XT_U32_RIGHTSH:
+				if (ct->location[j].number >= 32)
+					return -EINVAL;
+				break;
+			}
+		}
 	}
 
 	return 0;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 7c9256572284..c6fd9c424e8f 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1797,10 +1797,10 @@ static int ovs_ct_limit_get_zone_limit(struct net *net,
 		} else {
 			rcu_read_lock();
 			limit = ct_limit_get(info, zone);
-			rcu_read_unlock();
 
 			err = __ovs_ct_limit_get_zone_limit(
 				net, info->data, zone, limit, reply);
+			rcu_read_unlock();
 			if (err)
 				return err;
 		}
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 13052408a132..d8079dee700e 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2496,13 +2496,56 @@ static inline int add_nested_action_start(struct sw_flow_actions **sfa,
 	return used;
 }
 
-static inline void add_nested_action_end(struct sw_flow_actions *sfa,
-					 int st_offset)
+static inline int add_nested_action_end(struct sw_flow_actions *sfa,
+					int st_offset)
 {
-	struct nlattr *a = (struct nlattr *) ((unsigned char *)sfa->actions +
-							       st_offset);
+	struct nlattr *a;
+	u32 attr_len;
+
+	if (WARN_ON_ONCE(st_offset < 0 ||
+			 (u32)st_offset > sfa->actions_len))
+		return -EINVAL;
+
+	attr_len = sfa->actions_len - (u32)st_offset;
+	if (WARN_ON_ONCE(attr_len < NLA_HDRLEN))
+		return -EINVAL;
 
-	a->nla_len = sfa->actions_len - st_offset;
+	if (attr_len > U16_MAX)
+		return -EMSGSIZE;
+
+	a = (struct nlattr *)((u8 *)sfa->actions + st_offset);
+	a->nla_len = attr_len;
+	return 0;
+}
+
+/* Free the generated action-list tail at @start and truncate it.
+ * If @nested, @start points to its containing nlattr header.
+ */
+static void ovs_nla_trim(struct sw_flow_actions *sfa, int start, bool nested)
+{
+	const struct nlattr *actions;
+	u32 len;
+
+	if (start < 0)
+		return;
+
+	if (WARN_ON_ONCE((u32)start > sfa->actions_len))
+		return;
+
+	actions = (const struct nlattr *)((u8 *)sfa->actions + start);
+	len = sfa->actions_len - (u32)start;
+
+	if (nested) {
+		if (len < NLA_HDRLEN)
+			goto out;
+
+		actions = (const struct nlattr *)((u8 *)actions + NLA_HDRLEN);
+		len -= NLA_HDRLEN;
+	}
+
+	ovs_nla_free_nested_actions(actions, len);
+out:
+	sfa->actions_len = start;
 }
 
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
@@ -2522,6 +2565,7 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
 	const struct nlattr *a;
+	int actions_start;
 	int rem, start, err;
 	struct sample_arg arg;
 
@@ -2565,18 +2609,27 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 	err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg),
 				 log);
 	if (err)
-		return err;
+		goto err;
 
+	actions_start = (*sfa)->actions_len;
 	err = __ovs_nla_copy_actions(net, actions, key, sfa,
 				     eth_type, vlan_tci, mpls_label_count, log,
 				     depth + 1);
 
 	if (err)
-		return err;
+		goto err_free;
 
-	add_nested_action_end(*sfa, start);
+	err = add_nested_action_end(*sfa, start);
+	if (err)
+		goto err_free;
 
 	return 0;
+
+err_free:
+	ovs_nla_trim(*sfa, actions_start, false);
+err:
+	(*sfa)->actions_len = start;
+	return err;
 }
 
 static int validate_and_copy_dec_ttl(struct net *net,
@@ -2624,18 +2677,31 @@ static int validate_and_copy_dec_ttl(struct net *net,
 		return start;
 
 	action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log);
-	if (action_start < 0)
-		return action_start;
+	if (action_start < 0) {
+		err = action_start;
+		goto err;
+	}
 
 	err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type,
 				     vlan_tci, mpls_label_count, log,
 				     depth + 1);
 	if (err)
-		return err;
+		goto err_free;
+
+	err = add_nested_action_end(*sfa, action_start);
+	if (err)
+		goto err_free;
 
-	add_nested_action_end(*sfa, action_start);
-	add_nested_action_end(*sfa, start);
+	err = add_nested_action_end(*sfa, start);
+	if (err)
+		goto err_free;
 	return 0;
+
+err_free:
+	ovs_nla_trim(*sfa, action_start, true);
+err:
+	(*sfa)->actions_len = start;
+	return err;
 }
 
 static int validate_and_copy_clone(struct net *net,
@@ -2646,6 +2712,7 @@ static int validate_and_copy_clone(struct net *net,
 				   u32 mpls_label_count, bool log, bool last,
 				   u32 depth)
 {
+	int actions_start;
 	int start, err;
 	u32 exec;
 
@@ -2661,17 +2728,26 @@ static int validate_and_copy_clone(struct net *net,
 	err = ovs_nla_add_action(sfa, OVS_CLONE_ATTR_EXEC, &exec,
 				 sizeof(exec), log);
 	if (err)
-		return err;
+		goto err;
 
+	actions_start = (*sfa)->actions_len;
 	err = __ovs_nla_copy_actions(net, attr, key, sfa,
 				     eth_type, vlan_tci, mpls_label_count, log,
 				     depth + 1);
 	if (err)
-		return err;
+		goto err_free;
 
-	add_nested_action_end(*sfa, start);
+	err = add_nested_action_end(*sfa, start);
+	if (err)
+		goto err_free;
 
 	return 0;
+
+err_free:
+	ovs_nla_trim(*sfa, actions_start, false);
+err:
+	(*sfa)->actions_len = start;
+	return err;
 }
 
 void ovs_match_init(struct sw_flow_match *match,
@@ -2763,20 +2839,20 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL,
 				     GFP_KERNEL);
 
-	if (!tun_dst)
-		return -ENOMEM;
+	if (!tun_dst) {
+		err = -ENOMEM;
+		goto err;
+	}
 
 	err = dst_cache_init(&tun_dst->u.tun_info.dst_cache, GFP_KERNEL);
-	if (err) {
-		dst_release((struct dst_entry *)tun_dst);
-		return err;
-	}
+	if (err)
+		goto err_free_tun_dst;
 
 	a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
 			 sizeof(*ovs_tun), log);
 	if (IS_ERR(a)) {
-		dst_release((struct dst_entry *)tun_dst);
-		return PTR_ERR(a);
+		err = PTR_ERR(a);
+		goto err_free_tun_dst;
 	}
 
 	ovs_tun = nla_data(a);
@@ -2797,8 +2873,16 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	ip_tunnel_info_opts_set(tun_info,
 				TUN_METADATA_OPTS(&key, key.tun_opts_len),
 				key.tun_opts_len, dst_opt_type);
-	add_nested_action_end(*sfa, start);
+	err = add_nested_action_end(*sfa, start);
+	if (WARN_ON_ONCE(err))
+		goto err_free_tun_dst;
+
+	return 0;
 
+err_free_tun_dst:
+	dst_release((struct dst_entry *)tun_dst);
+err:
+	(*sfa)->actions_len = start;
 	return err;
 }
 
@@ -2971,7 +3055,7 @@ static int validate_set(const struct nlattr *a,
 
 	/* Convert non-masked non-tunnel set actions to masked set actions. */
 	if (!masked && key_type != OVS_KEY_ATTR_TUNNEL) {
-		int start, len = key_len * 2;
+		int err, start, len = key_len * 2;
 		struct nlattr *at;
 
 		*skip_copy = true;
@@ -2983,8 +3067,11 @@ static int validate_set(const struct nlattr *a,
 			return start;
 
 		at = __add_action(sfa, key_type, NULL, len, log);
-		if (IS_ERR(at))
-			return PTR_ERR(at);
+		if (IS_ERR(at)) {
+			err = PTR_ERR(at);
+			(*sfa)->actions_len = start;
+			return err;
+		}
 
 		memcpy(nla_data(at), nla_data(ovs_key), key_len); /* Key. */
 		memset(nla_data(at) + key_len, 0xff, key_len);    /* Mask. */
@@ -2994,7 +3081,11 @@ static int validate_set(const struct nlattr *a,
 
 			mask->ipv6_label &= htonl(0x000FFFFF);
 		}
-		add_nested_action_end(*sfa, start);
+		err = add_nested_action_end(*sfa, start);
+		if (WARN_ON_ONCE(err)) {
+			(*sfa)->actions_len = start;
+			return err;
+		}
 	}
 
 	return 0;
@@ -3040,7 +3131,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 	const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
 	struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1];
 	struct check_pkt_len_arg arg;
-	int nested_acts_start;
+	int greater_acts_start = -1;
+	int lesser_acts_start = -1;
 	int start, err;
 
 	err = nla_parse_deprecated_strict(a, OVS_CHECK_PKT_LEN_ATTR_MAX,
@@ -3075,37 +3167,58 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 	err = ovs_nla_add_action(sfa, OVS_CHECK_PKT_LEN_ATTR_ARG, &arg,
 				 sizeof(arg), log);
 	if (err)
-		return err;
+		goto err_free;
 
-	nested_acts_start = add_nested_action_start(sfa,
-		OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL, log);
-	if (nested_acts_start < 0)
-		return nested_acts_start;
+	lesser_acts_start =
+		add_nested_action_start(sfa,
+					OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL,
+					log);
+	if (lesser_acts_start < 0) {
+		err = lesser_acts_start;
+		goto err_free;
+	}
 
 	err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
 				     eth_type, vlan_tci, mpls_label_count, log,
 				     depth + 1);
 
 	if (err)
-		return err;
+		goto err_free;
 
-	add_nested_action_end(*sfa, nested_acts_start);
+	err = add_nested_action_end(*sfa, lesser_acts_start);
+	if (err)
+		goto err_free;
 
-	nested_acts_start = add_nested_action_start(sfa,
-		OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER, log);
-	if (nested_acts_start < 0)
-		return nested_acts_start;
+	greater_acts_start =
+		add_nested_action_start(sfa,
+					OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER,
+					log);
+	if (greater_acts_start < 0) {
+		err = greater_acts_start;
+		goto err_free;
+	}
 
 	err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
 				     eth_type, vlan_tci, mpls_label_count, log,
 				     depth + 1);
 
 	if (err)
-		return err;
+		goto err_free;
+
+	err = add_nested_action_end(*sfa, greater_acts_start);
+	if (err)
+		goto err_free;
 
-	add_nested_action_end(*sfa, nested_acts_start);
-	add_nested_action_end(*sfa, start);
+	err = add_nested_action_end(*sfa, start);
+	if (err)
+		goto err_free;
 	return 0;
+
+err_free:
+	ovs_nla_trim(*sfa, greater_acts_start, true);
+	ovs_nla_trim(*sfa, lesser_acts_start, true);
+	ovs_nla_trim(*sfa, start, false);
+	return err;
 }
 
 static int validate_psample(const struct nlattr *attr)
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 7763662036fb..c112e1f0ccac 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -476,15 +476,17 @@ void psample_sample_packet(struct psample_group *group,
 		goto error;
 
 	if (data_len) {
-		int nla_len = nla_total_size(data_len);
+		int nla_len = nla_attr_size(data_len);
 		struct nlattr *nla;
 
 		nla = skb_put(nl_skb, nla_len);
 		nla->nla_type = PSAMPLE_ATTR_DATA;
-		nla->nla_len = nla_attr_size(data_len);
+		nla->nla_len = nla_len;
 
 		if (skb_copy_bits(skb, 0, nla_data(nla), data_len))
 			goto error;
+
+		skb_put_zero(nl_skb, nla_padlen(data_len));
 	}
 
 #ifdef CONFIG_INET
diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c
index db823177e636..2288159f5b1b 100644
--- a/net/qrtr/af_qrtr.c
+++ b/net/qrtr/af_qrtr.c
@@ -496,7 +496,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 	if (cb->dst_port == QRTR_PORT_CTRL_LEGACY)
 		cb->dst_port = QRTR_PORT_CTRL;
 
-	if (!size || len != ALIGN(size, 4) + hdrlen)
+	if (!size || size > len || len != ALIGN(size, 4) + hdrlen)
 		goto err;
 
 	if ((cb->type == QRTR_TYPE_NEW_SERVER ||
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 98f2165159d7..d2b31d15851b 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -650,7 +650,9 @@ enum rxrpc_call_event {
 enum rxrpc_call_state {
 	RXRPC_CALL_UNINITIALISED,
 	RXRPC_CALL_CLIENT_AWAIT_CONN,	/* - client waiting for connection to become available */
+	RXRPC_CALL_CLIENT_PRE_SEND,	/* - client is connected, but hasn't sent anything yet */
 	RXRPC_CALL_CLIENT_SEND_REQUEST,	/* - client sending request phase */
+	RXRPC_CALL_CLIENT_AWAIT_ACK,	/* - client awaiting ACKs of request */
 	RXRPC_CALL_CLIENT_AWAIT_REPLY,	/* - client awaiting reply */
 	RXRPC_CALL_CLIENT_RECV_REPLY,	/* - client receiving reply phase */
 	RXRPC_CALL_SERVER_PREALLOC,	/* - service preallocation */
@@ -1355,9 +1357,9 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net)
 }
 
 /*
- * out_of_band.c
+ * oob.c
  */
-void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb);
+bool rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb);
 void rxrpc_add_pending_oob(struct rxrpc_sock *rx, struct sk_buff *skb);
 int rxrpc_sendmsg_oob(struct rxrpc_sock *rx, struct msghdr *msg, size_t len);
 
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index ee2d1319e69a..47824120f1da 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -471,13 +471,26 @@ int rxrpc_kernel_charge_accept(struct socket *sock, rxrpc_notify_rx_t notify_rx,
 			       unsigned long user_call_ID, gfp_t gfp,
 			       unsigned int debug_id)
 {
-	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
-	struct rxrpc_backlog *b = rx->backlog;
+	struct rxrpc_backlog *b;
+	struct rxrpc_sock *rx;
+	struct sock *sk;
+	int ret;
 
-	if (sock->sk->sk_state == RXRPC_CLOSE)
-		return -ESHUTDOWN;
+	sk = sock->sk;
+	rx = rxrpc_sk(sk);
+
+	lock_sock(sk);
+	if (sk->sk_state != RXRPC_SERVER_LISTENING || !rx->backlog) {
+		ret = -ESHUTDOWN;
+		goto out;
+	}
+
+	b = rx->backlog;
+	ret = rxrpc_service_prealloc_one(rx, b, notify_rx, user_call_ID,
+					 gfp, debug_id);
 
-	return rxrpc_service_prealloc_one(rx, b, notify_rx, user_call_ID,
-					  gfp, debug_id);
+out:
+	release_sock(sk);
+	return ret;
 }
 EXPORT_SYMBOL(rxrpc_kernel_charge_accept);
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index fec59d9338b9..21be9c86d7a7 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -178,7 +178,7 @@ static void rxrpc_close_tx_phase(struct rxrpc_call *call)
 
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
-		rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY);
+		rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_ACK);
 		break;
 	case RXRPC_CALL_SERVER_SEND_REPLY:
 		rxrpc_set_call_state(call, RXRPC_CALL_SERVER_AWAIT_ACK);
@@ -244,6 +244,8 @@ static void rxrpc_transmit_fresh_data(struct rxrpc_call *call, unsigned int limi
 				break;
 		} while (req.n < limit && before(seq, send_top));
 
+		if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_PRE_SEND)
+			rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST);
 		if (txb->flags & RXRPC_LAST_PACKET) {
 			rxrpc_close_tx_phase(call);
 			tq = NULL;
@@ -267,6 +269,7 @@ void rxrpc_transmit_some_data(struct rxrpc_call *call, unsigned int limit,
 		fallthrough;
 
 	case RXRPC_CALL_SERVER_SEND_REPLY:
+	case RXRPC_CALL_CLIENT_PRE_SEND:
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 		if (!rxrpc_tx_window_space(call))
 			return;
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index fcb9d38bb521..817ed9acb91e 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -18,7 +18,9 @@
 const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = {
 	[RXRPC_CALL_UNINITIALISED]		= "Uninit  ",
 	[RXRPC_CALL_CLIENT_AWAIT_CONN]		= "ClWtConn",
+	[RXRPC_CALL_CLIENT_PRE_SEND]		= "ClPreSnd",
 	[RXRPC_CALL_CLIENT_SEND_REQUEST]	= "ClSndReq",
+	[RXRPC_CALL_CLIENT_AWAIT_ACK]		= "ClAwtAck",
 	[RXRPC_CALL_CLIENT_AWAIT_REPLY]		= "ClAwtRpl",
 	[RXRPC_CALL_CLIENT_RECV_REPLY]		= "ClRcvRpl",
 	[RXRPC_CALL_SERVER_PREALLOC]		= "SvPrealc",
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 9b757798dedd..48519f0de185 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -449,7 +449,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
 	trace_rxrpc_connect_call(call);
 	call->tx_last_sent = ktime_get_real();
 	rxrpc_start_call_timer(call);
-	rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST);
+	rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_PRE_SEND);
 	wake_up(&call->waitq);
 }
 
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index c96ca615b787..611c790bc6d0 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -436,7 +436,7 @@ static bool rxrpc_post_challenge(struct rxrpc_connection *conn,
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_call *call = NULL;
 	struct rxrpc_sock *rx;
-	bool respond = false;
+	bool respond = false, queued = false;
 
 	sp->chall.conn =
 		rxrpc_get_connection(conn, rxrpc_conn_get_challenge_input);
@@ -472,8 +472,13 @@ static bool rxrpc_post_challenge(struct rxrpc_connection *conn,
 	}
 
 	if (call)
-		rxrpc_notify_socket_oob(call, skb);
+		queued = rxrpc_notify_socket_oob(call, skb);
 	rcu_read_unlock();
+	if (call && !queued) {
+		rxrpc_put_connection(conn, rxrpc_conn_put_challenge_input);
+		sp->chall.conn = NULL;
+		return false;
+	}
 
 	if (!call)
 		rxrpc_post_packet_to_conn(conn, skb);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index ce761466b02d..73cafe6bfa9f 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -181,7 +181,8 @@ void rxrpc_congestion_degrade(struct rxrpc_call *call)
 	if (call->cong_ca_state != RXRPC_CA_SLOW_START &&
 	    call->cong_ca_state != RXRPC_CA_CONGEST_AVOIDANCE)
 		return;
-	if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY)
+	if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_ACK ||
+	    __rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY)
 		return;
 
 	rtt = ns_to_ktime(call->srtt_us * (NSEC_PER_USEC / 8));
@@ -236,6 +237,9 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 		call->acks_lowest_nak = to;
 	}
 
+	if (after(seq, to))
+		return false;
+
 	/* We may have a left over fully-consumed buffer at the front that we
 	 * couldn't drop before (rotate_and_keep below).
 	 */
@@ -247,7 +251,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 		tq = call->tx_queue;
 	}
 
-	do {
+	while (before_eq(seq, to)) {
 		unsigned int ix = seq - call->tx_qbase;
 
 		_debug("tq=%x seq=%x i=%d f=%x", tq->qbase, seq, ix, tq->bufs[ix]->flags);
@@ -317,8 +321,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 				break;
 			}
 		}
-
-	} while (before_eq(seq, to));
+	}
 
 	if (trace)
 		trace_rxrpc_rack_update(call, summary);
@@ -356,6 +359,7 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
 
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
+	case RXRPC_CALL_CLIENT_AWAIT_ACK:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
 		if (reply_begun) {
 			rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_RECV_REPLY);
@@ -392,6 +396,14 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
 		trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack);
 	}
 
+	/* Deal with an apparent reply coming in before we've got the request
+	 * queued or transmitted.
+	 */
+	if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
+		rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply);
+		return false;
+	}
+
 	if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
 		if (!rxrpc_rotate_tx_window(call, top, &summary)) {
 			rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply);
@@ -694,6 +706,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
+	case RXRPC_CALL_CLIENT_AWAIT_ACK:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
 		/* Received data implicitly ACKs all of the request
 		 * packets we sent when we're acting as a client.
@@ -1154,10 +1167,12 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (hard_ack + 1 == 0)
 		return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero);
 
-	/* Ignore ACKs unless we are or have just been transmitting. */
+	/* Ignore ACKs unless we are transmitting or are waiting for
+	 * acknowledgement of the packets we've just been transmitting.
+	 */
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
-	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
+	case RXRPC_CALL_CLIENT_AWAIT_ACK:
 	case RXRPC_CALL_SERVER_SEND_REPLY:
 	case RXRPC_CALL_SERVER_AWAIT_ACK:
 		break;
@@ -1215,7 +1230,17 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_ack_summary summary = { 0 };
 
-	if (rxrpc_rotate_tx_window(call, call->tx_top, &summary))
+	switch (__rxrpc_call_state(call)) {
+	case RXRPC_CALL_CLIENT_SEND_REQUEST:
+	case RXRPC_CALL_CLIENT_AWAIT_ACK:
+	case RXRPC_CALL_SERVER_SEND_REPLY:
+	case RXRPC_CALL_SERVER_AWAIT_ACK:
+		break;
+	default:
+		return;
+	}
+
+	if (rxrpc_rotate_tx_window(call, call->tx_transmitted, &summary))
 		rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ackall);
 }
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 111f574fe667..169f9dfdaa77 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -194,7 +194,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 	tuncfg.encap_rcv = rxrpc_encap_rcv;
 	tuncfg.encap_err_rcv = rxrpc_encap_err_rcv;
 	tuncfg.sk_user_data = local;
-	setup_udp_tunnel_sock(net, local->socket, &tuncfg);
+	setup_udp_tunnel_sock(net, local->socket->sk, &tuncfg);
 
 	/* set the socket up */
 	usk = local->socket->sk;
diff --git a/net/rxrpc/oob.c b/net/rxrpc/oob.c
index 05ca9c1faa57..c80ee2487d09 100644
--- a/net/rxrpc/oob.c
+++ b/net/rxrpc/oob.c
@@ -32,11 +32,12 @@ struct rxrpc_oob_params {
  * Post an out-of-band message for attention by the socket or kernel service
  * associated with a reference call.
  */
-void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb)
+bool rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_sock *rx;
 	struct sock *sk;
+	bool queued = false;
 
 	rcu_read_lock();
 
@@ -49,6 +50,7 @@ void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb)
 			skb->skb_mstamp_ns = rx->oob_id_counter++;
 			rxrpc_get_skb(skb, rxrpc_skb_get_post_oob);
 			skb_queue_tail(&rx->recvmsg_oobq, skb);
+			queued = true;
 
 			trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial);
 			if (rx->app_ops)
@@ -56,11 +58,12 @@ void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb)
 		}
 
 		spin_unlock_irq(&rx->recvmsg_lock);
-		if (!rx->app_ops && !sock_flag(sk, SOCK_DEAD))
+		if (queued && !rx->app_ops && !sock_flag(sk, SOCK_DEAD))
 			sk->sk_data_ready(sk);
 	}
 
 	rcu_read_unlock();
+	return queued;
 }
 
 /*
@@ -210,6 +213,11 @@ static int rxrpc_respond_to_oob(struct rxrpc_sock *rx,
 		break;
 	}
 
+	switch (skb->mark) {
+	case RXRPC_OOB_CHALLENGE:
+		rxrpc_put_connection(sp->chall.conn, rxrpc_conn_put_oob);
+		break;
+	}
 	rxrpc_free_skb(skb, rxrpc_skb_put_oob);
 	return ret;
 }
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index c940600117a4..efcba4b2e74f 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -27,8 +27,6 @@ void rxrpc_notify_socket(struct rxrpc_call *call)
 
 	_enter("%d", call->debug_id);
 
-	if (!list_empty(&call->recvmsg_link))
-		return;
 	if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) {
 		rxrpc_see_call(call, rxrpc_call_see_notify_released);
 		return;
@@ -161,7 +159,7 @@ static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb)
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	int ret;
 
-	if (sp->len > call->rx_dec_bsize) {
+	if (sp->len > call->rx_dec_bsize || !call->rx_dec_buffer) {
 		/* Make sure we can hold a 1412-byte jumbo subpacket and make
 		 * sure that the buffer size is aligned to a crypto blocksize.
 		 */
@@ -262,12 +260,13 @@ static int rxrpc_recvmsg_oob(struct socket *sock, struct msghdr *msg,
 		break;
 	}
 
-	if (!(flags & MSG_PEEK))
+	if (!(flags & MSG_PEEK)) {
 		skb_unlink(skb, &rx->recvmsg_oobq);
-	if (need_response)
-		rxrpc_add_pending_oob(rx, skb);
-	else
-		rxrpc_free_skb(skb, rxrpc_skb_put_oob);
+		if (need_response)
+			rxrpc_add_pending_oob(rx, skb);
+		else
+			rxrpc_free_skb(skb, rxrpc_skb_put_oob);
+	}
 	return ret;
 }
 
@@ -437,7 +436,8 @@ try_again:
 		return -EAGAIN;
 	}
 
-	if (list_empty(&rx->recvmsg_q)) {
+	if (list_empty(&rx->recvmsg_q) &&
+	    skb_queue_empty_lockless(&rx->recvmsg_oobq)) {
 		ret = -EWOULDBLOCK;
 		if (timeo == 0) {
 			call = NULL;
@@ -470,7 +470,7 @@ try_again:
 		release_sock(&rx->sk);
 		if (ret == -EAGAIN)
 			goto try_again;
-		goto error_no_call;
+		goto error_trace;
 	}
 
 	/* Find the next call and dequeue it if we're not just peeking.  If we
@@ -529,8 +529,7 @@ try_again:
 	if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) {
 		rxrpc_see_call(call, rxrpc_call_see_already_released);
 		mutex_unlock(&call->user_mutex);
-		if (!(flags & MSG_PEEK))
-			rxrpc_put_call(call, rxrpc_call_put_recvmsg);
+		rxrpc_put_call(call, rxrpc_call_put_recvmsg);
 		goto try_again;
 	}
 
diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c
index a1ee102abae1..77a67ace1d24 100644
--- a/net/rxrpc/rxgk.c
+++ b/net/rxrpc/rxgk.c
@@ -687,16 +687,17 @@ static int rxgk_issue_challenge(struct rxrpc_connection *conn)
 	ret = do_udp_sendmsg(conn->local->socket, &msg, len);
 	if (ret > 0)
 		rxrpc_peer_mark_tx(conn->peer);
-	__free_page(page);
 
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_point_rxgk_challenge);
+		__free_page(page);
 		return -EAGAIN;
 	}
 
 	trace_rxrpc_tx_packet(conn->debug_id, whdr,
 			      rxrpc_tx_point_rxgk_challenge);
+	__free_page(page);
 	_leave(" = 0");
 	return 0;
 }
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index c35de4fd75e3..ed2c9a51005a 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -366,7 +366,8 @@ reload:
 	if (state >= RXRPC_CALL_COMPLETE)
 		goto maybe_error;
 	ret = -EPROTO;
-	if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+	if (state != RXRPC_CALL_CLIENT_PRE_SEND &&
+	    state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
 	    state != RXRPC_CALL_SERVER_ACK_REQUEST &&
 	    state != RXRPC_CALL_SERVER_SEND_REPLY) {
 		/* Request phase complete for this client call */
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 04ea11c90e03..b4a7e1c63cb8 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -148,10 +148,15 @@ static void offload_action_hw_count_dec(struct tc_action *act,
 
 static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act)
 {
-	if (is_tcf_pedit(act))
-		return tcf_pedit_nkeys(act);
-	else
-		return 1;
+	unsigned int count;
+
+	if (is_tcf_pedit(act)) {
+		spin_lock_bh(&act->tcfa_lock);
+		count = tcf_pedit_nkeys_locked(act);
+		spin_unlock_bh(&act->tcfa_lock);
+		return count;
+	}
+	return 1;
 }
 
 static bool tc_act_skip_hw(u32 flags)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index c2b5bc19e091..284800b7d3c5 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -44,7 +44,7 @@ TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb,
 	tcf_lastuse_update(&prog->tcf_tm);
 	bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb);
 
-	filter = rcu_dereference(prog->filter);
+	filter = rcu_dereference_bh(prog->filter);
 	if (at_ingress) {
 		__skb_push(skb, skb->mac_len);
 		filter_res = bpf_prog_run_data_pointers(filter, skb);
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 6158e13c98d3..be535a261fa0 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -844,11 +844,11 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 				   u8 family, u16 zone, bool *defrag)
 {
 	enum ip_conntrack_info ctinfo;
+	struct tc_skb_cb cb;
 	struct nf_conn *ct;
 	int err = 0;
 	bool frag;
 	u8 proto;
-	u16 mru;
 
 	/* Previously seen (loopback)? Ignore. */
 	ct = nf_ct_get(skb, &ctinfo);
@@ -862,12 +862,13 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 	if (err || !frag)
 		return err;
 
-	err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru);
+	cb = *tc_skb_cb(skb);
+	err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &cb.mru);
 	if (err)
 		return err;
 
 	*defrag = true;
-	tc_skb_cb(skb)->mru = mru;
+	*tc_skb_cb(skb) = cb;
 
 	return 0;
 }
@@ -1295,7 +1296,8 @@ static int tcf_ct_fill_params(struct net *net,
 	if (tb[TCA_CT_ZONE]) {
 		if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
 			NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled.");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto err;
 		}
 
 		tcf_ct_set_key_val(tb,
@@ -1308,7 +1310,8 @@ static int tcf_ct_fill_params(struct net *net,
 	tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL);
 	if (!tmpl) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err;
 	}
 	p->tmpl = tmpl;
 	if (tb[TCA_CT_HELPER_NAME]) {
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index bd3b1da3cd63..437a0563786b 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -563,9 +563,18 @@ static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data,
 {
 	if (bind) {
 		struct flow_action_entry *entry = entry_data;
+		int nkeys = tcf_pedit_nkeys_locked(act);
 		int k;
 
-		for (k = 0; k < tcf_pedit_nkeys(act); k++) {
+		/* If the required keys exceed the remaining capacity return
+		 * -ENOSPC to abort the offload and fallback to software.
+		 */
+		if (nkeys > *index_inc) {
+			NL_SET_ERR_MSG_MOD(extack, "Not enough space to offload all pedit keys");
+			return -ENOSPC;
+		}
+
+		for (k = 0; k < nkeys; k++) {
 			switch (tcf_pedit_cmd(act, k)) {
 			case TCA_PEDIT_KEY_EX_CMD_SET:
 				entry->id = FLOW_ACTION_MANGLE;
@@ -602,7 +611,7 @@ static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data,
 			return -EOPNOTSUPP;
 		}
 
-		for (k = 1; k < tcf_pedit_nkeys(act); k++) {
+		for (k = 1; k < tcf_pedit_nkeys_locked(act); k++) {
 			if (cmd != tcf_pedit_cmd(act, k)) {
 				NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload");
 				return -EOPNOTSUPP;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 20f7f9ee0b35..ffeea6db8337 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3886,12 +3886,21 @@ int tc_setup_action(struct flow_action *flow_action,
 
 		entry = &flow_action->entries[j];
 		spin_lock_bh(&act->tcfa_lock);
+
+		/* Abort the offload if we have exhausted the allocated capacity */
+		if (j >= flow_action->num_entries) {
+			NL_SET_ERR_MSG_MOD(extack, "Flow action buffer overflow");
+			err = -ENOSPC;
+			goto err_out_locked;
+		}
+
 		err = tcf_act_get_user_cookie(entry, act);
 		if (err)
 			goto err_out_locked;
 
-		index = 0;
-		err = tc_setup_offload_act(act, entry, &index, extack);
+		index = flow_action->num_entries - j;
+		err = tc_setup_offload_act(act, entry, &index,
+					   extack);
 		if (err)
 			goto err_out_locked;
 
@@ -3945,10 +3954,13 @@ unsigned int tcf_exts_num_actions(struct tcf_exts *exts)
 	int i;
 
 	tcf_exts_for_each_action(i, act, exts) {
-		if (is_tcf_pedit(act))
-			num_acts += tcf_pedit_nkeys(act);
-		else
+		if (is_tcf_pedit(act)) {
+			spin_lock_bh(&act->tcfa_lock);
+			num_acts += tcf_pedit_nkeys_locked(act);
+			spin_unlock_bh(&act->tcfa_lock);
+		} else {
 			num_acts++;
+		}
 	}
 	return num_acts;
 }
@@ -4049,6 +4061,9 @@ struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, stru
 		skb_do_redirect(skb);
 		*ret = __NET_XMIT_STOLEN;
 		return NULL;
+	case TC_ACT_CONSUMED:
+		*ret = __NET_XMIT_STOLEN;
+		return NULL;
 	}
 
 	return skb;
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 9a346b6221b3..001d8c4ebfed 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -142,7 +142,8 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
 
 static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			       struct cls_bpf_prog *oldprog,
-			       struct netlink_ext_ack *extack)
+			       struct netlink_ext_ack *extack,
+			       bool is_rollback)
 {
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_bpf_offload cls_bpf = {};
@@ -177,7 +178,8 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 					  &oldprog->in_hw_count, true);
 
 	if (prog && err) {
-		cls_bpf_offload_cmd(tp, oldprog, prog, extack);
+		if (!is_rollback)
+			cls_bpf_offload_cmd(tp, oldprog, prog, extack, true);
 		return err;
 	}
 
@@ -208,7 +210,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	if (!prog && !oldprog)
 		return 0;
 
-	return cls_bpf_offload_cmd(tp, prog, oldprog, extack);
+	return cls_bpf_offload_cmd(tp, prog, oldprog, extack, false);
 }
 
 static void cls_bpf_stop_offload(struct tcf_proto *tp,
@@ -217,7 +219,7 @@ static void cls_bpf_stop_offload(struct tcf_proto *tp,
 {
 	int err;
 
-	err = cls_bpf_offload_cmd(tp, NULL, prog, extack);
+	err = cls_bpf_offload_cmd(tp, NULL, prog, extack, false);
 	if (err)
 		pr_err("Stopping hardware offload failed: %d\n", err);
 }
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index ab364e4e4686..356c68ebc389 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -21,6 +21,7 @@
 #include <net/inet_sock.h>
 
 #include <net/pkt_cls.h>
+#include <linux/siphash.h>
 #include <net/ip.h>
 #include <net/route.h>
 #include <net/flow_dissector.h>
@@ -57,11 +58,15 @@ struct flow_filter {
 	struct rcu_work		rwork;
 };
 
+static siphash_aligned_key_t flow_keys_secret __read_mostly;
+
 static inline u32 addr_fold(void *addr)
 {
-	unsigned long a = (unsigned long)addr;
-
-	return (a & 0xFFFFFFFF) ^ (BITS_PER_LONG > 32 ? a >> 32 : 0);
+#ifdef CONFIG_64BIT
+	return (u32)siphash_1u64((u64)addr, &flow_keys_secret);
+#else
+	return (u32)siphash_1u32((u32)addr, &flow_keys_secret);
+#endif
 }
 
 static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow)
@@ -596,6 +601,7 @@ static int flow_init(struct tcf_proto *tp)
 		return -ENOBUFS;
 	INIT_LIST_HEAD(&head->filters);
 	rcu_assign_pointer(tp->root, head);
+	net_get_random_once(&flow_keys_secret, sizeof(flow_keys_secret));
 	return 0;
 }
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ed869a5ffc73..0dd3efd86393 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -805,7 +805,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
 			cl = cops->find(sch, parentid);
 			cops->qlen_notify(sch, cl);
 		}
-		sch->q.qlen -= n;
+		WRITE_ONCE(sch->q.qlen, sch->q.qlen - n);
 		sch->qstats.backlog -= len;
 		__qdisc_qstats_drop(sch, drops);
 	}
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 5862933be8d7..07ea175657bb 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1389,10 +1389,7 @@ static u32 cake_calc_overhead(struct cake_sched_data *qd, u32 len, u32 off)
 	if (qd->min_netlen > len)
 		WRITE_ONCE(qd->min_netlen, len);
 
-	len += q->rate_overhead;
-
-	if (len < q->rate_mpu)
-		len = q->rate_mpu;
+	len = max((s32)len + q->rate_overhead, (s32)q->rate_mpu);
 
 	if (q->atm_mode == CAKE_ATM_ATM) {
 		len += 47;
@@ -1612,7 +1609,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 		cake_advance_shaper(q, b, skb, now, true);
 
 	qdisc_drop_reason(skb, sch, to_free, QDISC_DROP_OVERLIMIT);
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 
 	cake_heapify(q, 0);
 
@@ -1822,7 +1819,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 									  segs);
 			flow_queue_add(flow, segs);
 
-			sch->q.qlen++;
+			qdisc_qlen_inc(sch);
 			numsegs++;
 			slen += segs->len;
 			q->buffer_used += segs->truesize;
@@ -1861,7 +1858,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			qdisc_tree_reduce_backlog(sch, 1, ack_pkt_len);
 			consume_skb(ack);
 		} else {
-			sch->q.qlen++;
+			qdisc_qlen_inc(sch);
 			q->buffer_used      += skb->truesize;
 		}
 
@@ -1987,7 +1984,7 @@ static struct sk_buff *cake_dequeue_one(struct Qdisc *sch)
 		WRITE_ONCE(b->tin_backlog, b->tin_backlog - len);
 		sch->qstats.backlog      -= len;
 		q->buffer_used		 -= skb->truesize;
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 
 		if (q->overflow_timeout)
 			cake_heapify(q, b->overflow_idx[q->cur_flow]);
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 0f953bd46b58..0994da70816e 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -97,7 +97,7 @@ static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return err;
 
 	sch->qstats.backlog += len;
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 
 	return NET_XMIT_SUCCESS;
 }
@@ -168,7 +168,7 @@ static struct sk_buff *cbs_child_dequeue(struct Qdisc *sch, struct Qdisc *child)
 
 	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_bstats_update(sch, skb);
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 
 	return skb;
 }
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 2875bcdb18a4..73d3e673dc7b 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -123,7 +123,7 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx,
 	if (idx == q->tail)
 		choke_zap_tail_holes(q);
 
-	--sch->q.qlen;
+	qdisc_qlen_dec(sch);
 	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 	qdisc_drop(skb, sch, to_free);
@@ -271,7 +271,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (sch->q.qlen < q->limit) {
 		q->tab[q->tail] = skb;
 		q->tail = (q->tail + 1) & q->tab_mask;
-		++sch->q.qlen;
+		qdisc_qlen_inc(sch);
 		qdisc_qstats_backlog_inc(sch, skb);
 		return NET_XMIT_SUCCESS;
 	}
@@ -298,7 +298,7 @@ static struct sk_buff *choke_dequeue(struct Qdisc *sch)
 	skb = q->tab[q->head];
 	q->tab[q->head] = NULL;
 	choke_zap_head_holes(q);
-	--sch->q.qlen;
+	qdisc_qlen_dec(sch);
 	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_bstats_update(sch, skb);
 
@@ -396,7 +396,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 				}
 				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
-				--sch->q.qlen;
+				qdisc_qlen_dec(sch);
 				rtnl_qdisc_drop(skb, sch);
 			}
 			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 317aae0ec7bd..7d5076196aff 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -56,7 +56,7 @@ static void drop_func(struct sk_buff *skb, void *ctx)
 	qdisc_qstats_drop(sch);
 }
 
-static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
+static struct sk_buff *__codel_qdisc_dequeue(struct Qdisc *sch)
 {
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
@@ -65,13 +65,51 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 			    &q->stats, qdisc_pkt_len, codel_get_enqueue_time,
 			    drop_func, dequeue_func);
 
+	if (skb)
+		qdisc_bstats_update(sch, skb);
+	return skb;
+}
+
+static void codel_dequeue_drop(struct Qdisc *sch)
+{
+	struct codel_sched_data *q = qdisc_priv(sch);
+
 	if (q->stats.drop_count) {
-		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
+		qdisc_tree_reduce_backlog(sch, q->stats.drop_count,
+					  q->stats.drop_len);
 		q->stats.drop_count = 0;
 		q->stats.drop_len = 0;
 	}
-	if (skb)
-		qdisc_bstats_update(sch, skb);
+}
+
+static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+
+	skb = __codel_qdisc_dequeue(sch);
+
+	codel_dequeue_drop(sch);
+
+	return skb;
+}
+
+static struct sk_buff *codel_peek(struct Qdisc *sch)
+{
+	struct sk_buff *skb = skb_peek(&sch->gso_skb);
+
+	if (!skb) {
+		skb = __codel_qdisc_dequeue(sch);
+
+		if (skb) {
+			__skb_queue_head(&sch->gso_skb, skb);
+			/* it's still part of the queue */
+			qdisc_qstats_backlog_inc(sch, skb);
+			sch->q.qlen++;
+		}
+
+		codel_dequeue_drop(sch);
+	}
+
 	return skb;
 }
 
@@ -257,7 +295,7 @@ static struct Qdisc_ops codel_qdisc_ops __read_mostly = {
 
 	.enqueue	=	codel_qdisc_enqueue,
 	.dequeue	=	codel_qdisc_dequeue,
-	.peek		=	qdisc_peek_dequeued,
+	.peek		=	codel_peek,
 	.init		=	codel_init,
 	.reset		=	codel_reset,
 	.change 	=	codel_change,
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 01335a49e091..2eedd3a4322a 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -270,7 +270,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	memset(&xstats, 0, sizeof(xstats));
 	if (qlen)
-		xstats.deficit = cl->deficit;
+		xstats.deficit = READ_ONCE(cl->deficit);
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
@@ -362,11 +362,11 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	if (!cl_is_active(cl)) {
 		list_add_tail(&cl->alist, &q->active);
-		cl->deficit = cl->quantum;
+		WRITE_ONCE(cl->deficit, cl->quantum);
 	}
 
 	sch->qstats.backlog += len;
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 	return err;
 }
 
@@ -389,7 +389,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 
 		len = qdisc_pkt_len(skb);
 		if (len <= cl->deficit) {
-			cl->deficit -= len;
+			WRITE_ONCE(cl->deficit, cl->deficit - len);
 			skb = qdisc_dequeue_peeked(cl->qdisc);
 			if (unlikely(skb == NULL))
 				goto out;
@@ -399,11 +399,11 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 			bstats_update(&cl->bstats, skb);
 			qdisc_bstats_update(sch, skb);
 			qdisc_qstats_backlog_dec(sch, skb);
-			sch->q.qlen--;
+			qdisc_qlen_dec(sch);
 			return skb;
 		}
 
-		cl->deficit += cl->quantum;
+		WRITE_ONCE(cl->deficit, cl->deficit + cl->quantum);
 		list_move_tail(&cl->alist, &q->active);
 	}
 out:
diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c
index 1ca4d2c03e61..27088760eff4 100644
--- a/net/sched/sch_dualpi2.c
+++ b/net/sched/sch_dualpi2.c
@@ -190,7 +190,7 @@ static bool skb_apply_step(struct sk_buff *skb, struct dualpi2_sched_data *q)
 static bool dualpi2_mark(struct dualpi2_sched_data *q, struct sk_buff *skb)
 {
 	if (INET_ECN_set_ce(skb)) {
-		q->ecn_mark++;
+		WRITE_ONCE(q->ecn_mark, q->ecn_mark + 1);
 		return true;
 	}
 	return false;
@@ -198,7 +198,7 @@ static bool dualpi2_mark(struct dualpi2_sched_data *q, struct sk_buff *skb)
 
 static void dualpi2_reset_c_protection(struct dualpi2_sched_data *q)
 {
-	q->c_protection_credit = q->c_protection_init;
+	WRITE_ONCE(q->c_protection_credit, q->c_protection_init);
 }
 
 /* This computes the initial credit value and WRR weight for the L queue (wl)
@@ -346,6 +346,8 @@ static int dualpi2_skb_classify(struct dualpi2_sched_data *q,
 	struct tcf_proto *fl;
 	int result;
 
+	cb->classified = DUALPI2_C_CLASSIC;
+
 	dualpi2_read_ect(skb);
 	if (cb->ect & q->ecn_mask) {
 		cb->classified = DUALPI2_C_L4S;
@@ -359,10 +361,8 @@ static int dualpi2_skb_classify(struct dualpi2_sched_data *q,
 	}
 
 	fl = rcu_dereference_bh(q->tcf_filters);
-	if (!fl) {
-		cb->classified = DUALPI2_C_CLASSIC;
+	if (!fl)
 		return NET_XMIT_SUCCESS;
-	}
 
 	result = tcf_classify(skb, NULL, fl, &res, false);
 	if (result >= 0) {
@@ -403,28 +403,28 @@ static int dualpi2_enqueue_skb(struct sk_buff *skb, struct Qdisc *sch,
 
 	cb = dualpi2_skb_cb(skb);
 	cb->ts = ktime_get_ns();
-	q->memory_used += skb->truesize;
+	WRITE_ONCE(q->memory_used, q->memory_used + skb->truesize);
 	if (q->memory_used > q->max_memory_used)
-		q->max_memory_used = q->memory_used;
+		WRITE_ONCE(q->max_memory_used, q->memory_used);
 
 	if (qdisc_qlen(sch) > q->maxq)
-		q->maxq = qdisc_qlen(sch);
+		WRITE_ONCE(q->maxq, qdisc_qlen(sch));
 
 	if (skb_in_l_queue(skb)) {
 		/* Apply step thresh if skb is L4S && L-queue len >= min_qlen */
 		dualpi2_skb_cb(skb)->apply_step = skb_apply_step(skb, q);
 
 		/* Keep the overall qdisc stats consistent */
-		++sch->q.qlen;
+		qdisc_qlen_inc(sch);
 		qdisc_qstats_backlog_inc(sch, skb);
-		++q->packets_in_l;
+		WRITE_ONCE(q->packets_in_l, q->packets_in_l + 1);
 		if (!q->l_head_ts)
-			q->l_head_ts = cb->ts;
+			WRITE_ONCE(q->l_head_ts, cb->ts);
 		return qdisc_enqueue_tail(skb, q->l_queue);
 	}
-	++q->packets_in_c;
+	WRITE_ONCE(q->packets_in_c, q->packets_in_c + 1);
 	if (!q->c_head_ts)
-		q->c_head_ts = cb->ts;
+		WRITE_ONCE(q->c_head_ts, cb->ts);
 	return qdisc_enqueue_tail(skb, sch);
 }
 
@@ -529,18 +529,17 @@ static struct sk_buff *dequeue_packet(struct Qdisc *sch,
 		qdisc_qstats_backlog_dec(q->l_queue, skb);
 
 		/* Keep the global queue size consistent */
-		--sch->q.qlen;
-		q->memory_used -= skb->truesize;
+		qdisc_qlen_dec(sch);
 	} else if (c_len) {
 		skb = __qdisc_dequeue_head(&sch->q);
 		WRITE_ONCE(q->c_head_ts, head_enqueue_time(sch));
 		if (qdisc_qlen(q->l_queue))
 			*credit_change = ~((s32)q->c_protection_wl) + 1;
-		q->memory_used -= skb->truesize;
 	} else {
 		dualpi2_reset_c_protection(q);
 		return NULL;
 	}
+	WRITE_ONCE(q->memory_used, q->memory_used - skb->truesize);
 	*credit_change *= qdisc_pkt_len(skb);
 	qdisc_qstats_backlog_dec(sch, skb);
 	return skb;
@@ -563,7 +562,7 @@ static int do_step_aqm(struct dualpi2_sched_data *q, struct sk_buff *skb,
 		}
 
 		if (dualpi2_mark(q, skb))
-			++q->step_marks;
+			WRITE_ONCE(q->step_marks, q->step_marks + 1);
 	}
 	qdisc_bstats_update(q->l_queue, skb);
 	return 0;
@@ -578,7 +577,7 @@ static void drop_and_retry(struct dualpi2_sched_data *q, struct sk_buff *skb,
 	qdisc_qstats_drop(sch);
 }
 
-static struct sk_buff *dualpi2_qdisc_dequeue(struct Qdisc *sch)
+static struct sk_buff *__dualpi2_qdisc_dequeue(struct Qdisc *sch)
 {
 	struct dualpi2_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
@@ -599,17 +598,55 @@ static struct sk_buff *dualpi2_qdisc_dequeue(struct Qdisc *sch)
 			continue;
 		}
 
-		q->c_protection_credit += credit_change;
+		WRITE_ONCE(q->c_protection_credit,
+			   q->c_protection_credit + credit_change);
 		qdisc_bstats_update(sch, skb);
 		break;
 	}
 
+	return skb;
+}
+
+static void dualpi2_dequeue_drop(struct Qdisc *sch)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+
 	if (q->deferred_drops_cnt) {
 		qdisc_tree_reduce_backlog(sch, q->deferred_drops_cnt,
 					  q->deferred_drops_len);
 		q->deferred_drops_cnt = 0;
 		q->deferred_drops_len = 0;
 	}
+}
+
+static struct sk_buff *dualpi2_qdisc_dequeue(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+
+	skb = __dualpi2_qdisc_dequeue(sch);
+
+	dualpi2_dequeue_drop(sch);
+
+	return skb;
+}
+
+static struct sk_buff *dualpi2_peek(struct Qdisc *sch)
+{
+	struct sk_buff *skb = skb_peek(&sch->gso_skb);
+
+	if (!skb) {
+		skb = __dualpi2_qdisc_dequeue(sch);
+
+		if (skb) {
+			__skb_queue_head(&sch->gso_skb, skb);
+			/* it's still part of the queue */
+			qdisc_qstats_backlog_inc(sch, skb);
+			sch->q.qlen++;
+		}
+
+		dualpi2_dequeue_drop(sch);
+	}
+
 	return skb;
 }
 
@@ -875,7 +912,7 @@ static int dualpi2_change(struct Qdisc *sch, struct nlattr *opt,
 				WARN_ON_ONCE(1);
 				break;
 			}
-			q->memory_used -= skb->truesize;
+			WRITE_ONCE(q->memory_used, q->memory_used - skb->truesize);
 			rtnl_qdisc_drop(skb, sch);
 		} else if (qdisc_qlen(q->l_queue)) {
 			skb = qdisc_dequeue_internal(q->l_queue, true);
@@ -887,9 +924,9 @@ static int dualpi2_change(struct Qdisc *sch, struct nlattr *opt,
 			 * l_queue on enqueue; qdisc_dequeue_internal()
 			 * handled l_queue, so we further account for sch.
 			 */
-			--sch->q.qlen;
+			qdisc_qlen_dec(sch);
 			qdisc_qstats_backlog_dec(sch, skb);
-			q->memory_used -= skb->truesize;
+			WRITE_ONCE(q->memory_used, q->memory_used - skb->truesize);
 			rtnl_qdisc_drop(skb, q->l_queue);
 			qdisc_qstats_drop(sch);
 		} else {
@@ -1045,15 +1082,15 @@ static int dualpi2_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 	struct dualpi2_sched_data *q = qdisc_priv(sch);
 	struct tc_dualpi2_xstats st = {
 		.prob			= READ_ONCE(q->pi2_prob),
-		.packets_in_c		= q->packets_in_c,
-		.packets_in_l		= q->packets_in_l,
-		.maxq			= q->maxq,
-		.ecn_mark		= q->ecn_mark,
-		.credit			= q->c_protection_credit,
-		.step_marks		= q->step_marks,
-		.memory_used		= q->memory_used,
-		.max_memory_used	= q->max_memory_used,
-		.memory_limit		= q->memory_limit,
+		.packets_in_c		= READ_ONCE(q->packets_in_c),
+		.packets_in_l		= READ_ONCE(q->packets_in_l),
+		.maxq			= READ_ONCE(q->maxq),
+		.ecn_mark		= READ_ONCE(q->ecn_mark),
+		.credit			= READ_ONCE(q->c_protection_credit),
+		.step_marks		= READ_ONCE(q->step_marks),
+		.memory_used		= READ_ONCE(q->memory_used),
+		.max_memory_used	= READ_ONCE(q->max_memory_used),
+		.memory_limit		= READ_ONCE(q->memory_limit),
 	};
 	u64 qc, ql;
 
@@ -1073,16 +1110,16 @@ static void dualpi2_reset(struct Qdisc *sch)
 
 	qdisc_reset_queue(sch);
 	qdisc_reset_queue(q->l_queue);
-	q->c_head_ts = 0;
-	q->l_head_ts = 0;
-	q->pi2_prob = 0;
-	q->packets_in_c = 0;
-	q->packets_in_l = 0;
-	q->maxq = 0;
-	q->ecn_mark = 0;
-	q->step_marks = 0;
-	q->memory_used = 0;
-	q->max_memory_used = 0;
+	WRITE_ONCE(q->c_head_ts, 0);
+	WRITE_ONCE(q->l_head_ts, 0);
+	WRITE_ONCE(q->pi2_prob, 0);
+	WRITE_ONCE(q->packets_in_c, 0);
+	WRITE_ONCE(q->packets_in_l, 0);
+	WRITE_ONCE(q->maxq, 0);
+	WRITE_ONCE(q->ecn_mark, 0);
+	WRITE_ONCE(q->step_marks, 0);
+	WRITE_ONCE(q->memory_used, 0);
+	WRITE_ONCE(q->max_memory_used, 0);
 	dualpi2_reset_c_protection(q);
 }
 
@@ -1164,7 +1201,7 @@ static struct Qdisc_ops dualpi2_qdisc_ops __read_mostly = {
 	.priv_size	= sizeof(struct dualpi2_sched_data),
 	.enqueue	= dualpi2_qdisc_enqueue,
 	.dequeue	= dualpi2_qdisc_dequeue,
-	.peek		= qdisc_peek_dequeued,
+	.peek		= dualpi2_peek,
 	.init		= dualpi2_init,
 	.destroy	= dualpi2_destroy,
 	.reset		= dualpi2_reset,
@@ -1173,6 +1210,7 @@ static struct Qdisc_ops dualpi2_qdisc_ops __read_mostly = {
 	.dump_stats	= dualpi2_dump_stats,
 	.owner		= THIS_MODULE,
 };
+MODULE_ALIAS_NET_SCH("dualpi2");
 
 static int __init dualpi2_module_init(void)
 {
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index c74d778c32a1..ada87a81da6a 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -189,7 +189,7 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 	rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost);
 
 	qdisc_qstats_backlog_inc(sch, nskb);
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 
 	/* Now we may need to re-arm the qdisc watchdog for the next packet. */
 	reset_watchdog(sch);
@@ -222,7 +222,7 @@ static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb,
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch, &to_free);
 		qdisc_qstats_overlimit(sch);
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 	}
 
 	kfree_skb_list(to_free);
@@ -247,7 +247,7 @@ static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb)
 
 	q->last = skb->tstamp;
 
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 }
 
 static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
@@ -426,7 +426,7 @@ static void timesortedlist_clear(struct Qdisc *sch)
 
 		rb_erase_cached(&skb->rbnode, &q->head);
 		rtnl_kfree_skbs(skb, skb);
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 	}
 }
 
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index a4b07b661b77..c817e0a6c146 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -449,7 +449,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	sch->qstats.backlog += len;
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 	return err;
 }
 
@@ -458,7 +458,7 @@ ets_qdisc_dequeue_skb(struct Qdisc *sch, struct sk_buff *skb)
 {
 	qdisc_bstats_update(sch, skb);
 	qdisc_qstats_backlog_dec(sch, skb);
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 	return skb;
 }
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index f2edcf872981..1e34ac136b15 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -497,7 +497,7 @@ static void fq_dequeue_skb(struct Qdisc *sch, struct fq_flow *flow,
 	fq_erase_head(sch, flow, skb);
 	skb_mark_not_on_list(skb);
 	qdisc_qstats_backlog_dec(sch, skb);
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 	qdisc_bstats_update(sch, skb);
 }
 
@@ -597,7 +597,7 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	flow_queue_add(f, skb);
 
 	qdisc_qstats_backlog_inc(sch, skb);
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 
 	return NET_XMIT_SUCCESS;
 }
@@ -801,7 +801,7 @@ static void fq_reset(struct Qdisc *sch)
 	struct fq_flow *f;
 	unsigned int idx;
 
-	sch->q.qlen = 0;
+	WRITE_ONCE(sch->q.qlen, 0);
 	sch->qstats.backlog = 0;
 
 	fq_flow_purge(&q->internal);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 24db54684e8a..09ab84580160 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -178,7 +178,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets,
 	q->memory_usage -= mem;
 	sch->qstats.drops += i;
 	sch->qstats.backlog -= len;
-	sch->q.qlen -= i;
+	WRITE_ONCE(sch->q.qlen, sch->q.qlen - i);
 	return idx;
 }
 
@@ -215,7 +215,8 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	get_codel_cb(skb)->mem_usage = skb->truesize;
 	q->memory_usage += get_codel_cb(skb)->mem_usage;
 	memory_limited = q->memory_usage > q->memory_limit;
-	if (++sch->q.qlen <= sch->limit && !memory_limited)
+	qdisc_qlen_inc(sch);
+	if (sch->q.qlen <= sch->limit && !memory_limited)
 		return NET_XMIT_SUCCESS;
 
 	prev_backlog = sch->qstats.backlog;
@@ -266,7 +267,7 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx)
 		WRITE_ONCE(q->backlogs[flow - q->flows],
 			   q->backlogs[flow - q->flows] - qdisc_pkt_len(skb));
 		q->memory_usage -= get_codel_cb(skb)->mem_usage;
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 		sch->qstats.backlog -= qdisc_pkt_len(skb);
 	}
 	return skb;
@@ -280,7 +281,7 @@ static void drop_func(struct sk_buff *skb, void *ctx)
 	qdisc_qstats_drop(sch);
 }
 
-static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
+static struct sk_buff *__fq_codel_dequeue(struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
@@ -317,12 +318,49 @@ begin:
 	qdisc_bstats_update(sch, skb);
 	WRITE_ONCE(flow->deficit, flow->deficit - qdisc_pkt_len(skb));
 
+	return skb;
+}
+
+static void fq_codel_dequeue_drop(struct Qdisc *sch)
+{
+	struct fq_codel_sched_data *q = qdisc_priv(sch);
+
 	if (q->cstats.drop_count) {
 		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
 					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
 		q->cstats.drop_len = 0;
 	}
+}
+
+static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+
+	skb =  __fq_codel_dequeue(sch);
+
+	fq_codel_dequeue_drop(sch);
+
+	return skb;
+}
+
+static struct sk_buff *fq_codel_peek(struct Qdisc *sch)
+{
+	struct sk_buff *skb = skb_peek(&sch->gso_skb);
+
+	if (!skb) {
+		skb = __fq_codel_dequeue(sch);
+
+		if (skb) {
+			__skb_queue_head(&sch->gso_skb, skb);
+			/* it's still part of the queue */
+			qdisc_qstats_backlog_inc(sch, skb);
+			sch->q.qlen++;
+		}
+
+		fq_codel_dequeue_drop(sch);
+	}
+
 	return skb;
 }
 
@@ -725,7 +763,7 @@ static struct Qdisc_ops fq_codel_qdisc_ops __read_mostly = {
 	.priv_size	=	sizeof(struct fq_codel_sched_data),
 	.enqueue	=	fq_codel_enqueue,
 	.dequeue	=	fq_codel_dequeue,
-	.peek		=	qdisc_peek_dequeued,
+	.peek		=	fq_codel_peek,
 	.init		=	fq_codel_init,
 	.reset		=	fq_codel_reset,
 	.destroy	=	fq_codel_destroy,
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 7becbf5362b3..0a4eca4ab086 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -185,7 +185,7 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		q->stats.packets_in++;
 		q->memory_usage += skb->truesize;
 		sch->qstats.backlog += pkt_len;
-		sch->q.qlen++;
+		qdisc_qlen_inc(sch);
 		flow_queue_add(sel_flow, skb);
 		if (list_empty(&sel_flow->flowchain)) {
 			list_add_tail(&sel_flow->flowchain, &q->new_flows);
@@ -263,7 +263,7 @@ begin:
 		skb = dequeue_head(flow);
 		pkt_len = qdisc_pkt_len(skb);
 		sch->qstats.backlog -= pkt_len;
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 		qdisc_bstats_update(sch, skb);
 	}
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a93321db8fd7..fe73ac40d409 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -118,7 +118,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 				qdisc_qstats_cpu_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
-				q->q.qlen--;
+				qdisc_qlen_dec(q);
 			}
 		} else {
 			skb = SKB_XOFF_MAGIC;
@@ -159,7 +159,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 		qdisc_qstats_cpu_qlen_inc(q);
 	} else {
 		qdisc_qstats_backlog_inc(q, skb);
-		q->q.qlen++;
+		qdisc_qlen_inc(q);
 	}
 
 	if (lock)
@@ -188,7 +188,7 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 		} else {
 			q->qstats.requeues++;
 			qdisc_qstats_backlog_inc(q, skb);
-			q->q.qlen++;
+			qdisc_qlen_inc(q);
 		}
 
 		skb = next;
@@ -294,7 +294,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 				qdisc_qstats_cpu_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
-				q->q.qlen--;
+				qdisc_qlen_dec(q);
 			}
 		} else {
 			skb = NULL;
@@ -568,16 +568,24 @@ static void dev_watchdog(struct timer_list *t)
 				dev->netdev_ops->ndo_tx_timeout(dev, i);
 				netif_unfreeze_queues(dev);
 			}
-			if (!mod_timer(&dev->watchdog_timer,
-				       round_jiffies(oldest_start +
-						     dev->watchdog_timeo)))
-				release = false;
+			spin_lock(&dev->watchdog_lock);
+			mod_timer(&dev->watchdog_timer,
+				  round_jiffies(oldest_start +
+						dev->watchdog_timeo));
+			release = false;
+			spin_unlock(&dev->watchdog_lock);
 		}
 	}
 	spin_unlock(&dev->tx_global_lock);
 
-	if (release)
+	spin_lock(&dev->watchdog_lock);
+	if (timer_pending(&dev->watchdog_timer))
+		release = false;
+	if (release && dev->watchdog_ref_held) {
 		netdev_put(dev, &dev->watchdog_dev_tracker);
+		dev->watchdog_ref_held = false;
+	}
+	spin_unlock(&dev->watchdog_lock);
 }
 
 void netdev_watchdog_up(struct net_device *dev)
@@ -586,18 +594,31 @@ void netdev_watchdog_up(struct net_device *dev)
 		return;
 	if (dev->watchdog_timeo <= 0)
 		dev->watchdog_timeo = 5*HZ;
+
+	spin_lock_bh(&dev->watchdog_lock);
 	if (!mod_timer(&dev->watchdog_timer,
-		       round_jiffies(jiffies + dev->watchdog_timeo)))
-		netdev_hold(dev, &dev->watchdog_dev_tracker,
-			    GFP_ATOMIC);
+		       round_jiffies(jiffies + dev->watchdog_timeo))) {
+		if (!dev->watchdog_ref_held) {
+			netdev_hold(dev, &dev->watchdog_dev_tracker,
+				    GFP_ATOMIC);
+			dev->watchdog_ref_held = true;
+		}
+	}
+	spin_unlock_bh(&dev->watchdog_lock);
 }
 EXPORT_SYMBOL_GPL(netdev_watchdog_up);
 
 static void netdev_watchdog_down(struct net_device *dev)
 {
 	netif_tx_lock_bh(dev);
-	if (timer_delete(&dev->watchdog_timer))
+
+	spin_lock(&dev->watchdog_lock);
+	if (timer_delete(&dev->watchdog_timer)) {
 		netdev_put(dev, &dev->watchdog_dev_tracker);
+		dev->watchdog_ref_held = false;
+	}
+	spin_unlock(&dev->watchdog_lock);
+
 	netif_tx_unlock_bh(dev);
 }
 
@@ -614,8 +635,6 @@ void netif_carrier_on(struct net_device *dev)
 			return;
 		atomic_inc(&dev->carrier_up_count);
 		linkwatch_fire_event(dev);
-		if (netif_running(dev))
-			netdev_watchdog_up(dev);
 	}
 }
 EXPORT_SYMBOL(netif_carrier_on);
@@ -1059,7 +1078,7 @@ void qdisc_reset(struct Qdisc *qdisc)
 	__skb_queue_purge(&qdisc->gso_skb);
 	__skb_queue_purge(&qdisc->skb_bad_txq);
 
-	qdisc->q.qlen = 0;
+	WRITE_ONCE(qdisc->q.qlen, 0);
 	qdisc->qstats.backlog = 0;
 }
 EXPORT_SYMBOL(qdisc_reset);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 83b2ca2e37fc..50112c8a71e0 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -715,7 +715,7 @@ init_vf(struct hfsc_class *cl, unsigned int len)
 			rtsc_min(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total);
 			cl->cl_vtadj = 0;
 
-			cl->cl_vtperiod++;  /* increment vt period */
+			WRITE_ONCE(cl->cl_vtperiod, cl->cl_vtperiod + 1);  /* increment vt period */
 			cl->cl_parentperiod = cl->cl_parent->cl_vtperiod;
 			if (cl->cl_parent->cl_nactive == 0)
 				cl->cl_parentperiod++;
@@ -753,11 +753,11 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time)
 	u64 f; /* , myf_bound, delta; */
 	int go_passive = 0;
 
-	if (cl->qdisc->q.qlen == 0 && cl->cl_flags & HFSC_FSC)
+	if (cl->qdisc->q.qlen == 0 && cl->cl_flags & HFSC_FSC && cl->cl_nactive)
 		go_passive = 1;
 
 	for (; cl->cl_parent != NULL; cl = cl->cl_parent) {
-		cl->cl_total += len;
+		WRITE_ONCE(cl->cl_total, cl->cl_total + len);
 
 		if (!(cl->cl_flags & HFSC_FSC) || cl->cl_nactive == 0)
 			continue;
@@ -847,7 +847,7 @@ hfsc_adjust_levels(struct hfsc_class *cl)
 			if (p->level >= level)
 				level = p->level + 1;
 		}
-		cl->level = level;
+		WRITE_ONCE(cl->level, level);
 	} while ((cl = cl->cl_parent) != NULL);
 }
 
@@ -1338,10 +1338,10 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	__u32 qlen;
 
 	qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &cl->qstats.backlog);
-	xstats.level   = cl->level;
-	xstats.period  = cl->cl_vtperiod;
-	xstats.work    = cl->cl_total;
-	xstats.rtwork  = cl->cl_cumul;
+	xstats.level   = READ_ONCE(cl->level);
+	xstats.period  = READ_ONCE(cl->cl_vtperiod);
+	xstats.work    = READ_ONCE(cl->cl_total);
+	xstats.rtwork  = READ_ONCE(cl->cl_cumul);
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
@@ -1452,15 +1452,15 @@ hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt,
 static void
 hfsc_reset_class(struct hfsc_class *cl)
 {
-	cl->cl_total        = 0;
-	cl->cl_cumul        = 0;
+	WRITE_ONCE(cl->cl_total, 0);
+	WRITE_ONCE(cl->cl_cumul, 0);
 	cl->cl_d            = 0;
 	cl->cl_e            = 0;
 	cl->cl_vt           = 0;
 	cl->cl_vtadj        = 0;
 	cl->cl_cvtmin       = 0;
 	cl->cl_cvtoff       = 0;
-	cl->cl_vtperiod     = 0;
+	WRITE_ONCE(cl->cl_vtperiod, 0);
 	cl->cl_parentperiod = 0;
 	cl->cl_f            = 0;
 	cl->cl_myf          = 0;
@@ -1561,7 +1561,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 	}
 
 	sch->qstats.backlog += len;
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 
 	if (first && !cl_in_el_or_vttree(cl)) {
 		if (cl->cl_flags & HFSC_RSC)
@@ -1626,7 +1626,7 @@ hfsc_dequeue(struct Qdisc *sch)
 	bstats_update(&cl->bstats, skb);
 	update_vf(cl, qdisc_pkt_len(skb), cur_time);
 	if (realtime)
-		cl->cl_cumul += qdisc_pkt_len(skb);
+		WRITE_ONCE(cl->cl_cumul, cl->cl_cumul + qdisc_pkt_len(skb));
 
 	if (cl->cl_flags & HFSC_RSC) {
 		if (cl->qdisc->q.qlen != 0) {
@@ -1650,7 +1650,7 @@ hfsc_dequeue(struct Qdisc *sch)
 
 	qdisc_bstats_update(sch, skb);
 	qdisc_qstats_backlog_dec(sch, skb);
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 
 	return skb;
 }
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 96021f52d835..d85cb0263b67 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -360,7 +360,7 @@ static unsigned int hhf_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	if (bucket->head) {
 		struct sk_buff *skb = dequeue_head(bucket);
 
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch, to_free);
 	}
@@ -400,7 +400,8 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		}
 		bucket->deficit = weight * q->quantum;
 	}
-	if (++sch->q.qlen <= sch->limit)
+	qdisc_qlen_inc(sch);
+	if (sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
 	prev_backlog = sch->qstats.backlog;
@@ -443,7 +444,7 @@ begin:
 
 	if (bucket->head) {
 		skb = dequeue_head(bucket);
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 		qdisc_qstats_backlog_dec(sch, skb);
 	}
 
@@ -461,12 +462,39 @@ begin:
 	return skb;
 }
 
+static void hhf_reset_classifier(struct hhf_sched_data *q)
+{
+	int i;
+
+	if (!q->hh_flows)
+		return;
+
+	for (i = 0; i < HH_FLOWS_CNT; i++) {
+		struct hh_flow_state *flow, *next;
+		struct list_head *head = &q->hh_flows[i];
+
+		list_for_each_entry_safe(flow, next, head, flowchain) {
+			list_del(&flow->flowchain);
+			kfree(flow);
+		}
+	}
+	WRITE_ONCE(q->hh_flows_current_cnt, 0);
+
+	for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+		if (q->hhf_valid_bits[i])
+			bitmap_zero(q->hhf_valid_bits[i], HHF_ARRAYS_LEN);
+	}
+	q->hhf_arrays_reset_timestamp = hhf_time_stamp();
+}
+
 static void hhf_reset(struct Qdisc *sch)
 {
+	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
 
 	while ((skb = hhf_dequeue(sch)) != NULL)
 		rtnl_kfree_skbs(skb, skb);
+	hhf_reset_classifier(q);
 }
 
 static void hhf_destroy(struct Qdisc *sch)
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index eb12381795ce..ccabafed3fe4 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -568,7 +568,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
 
 	if (new_mode == HTB_CANT_SEND) {
 		cl->overlimits++;
-		q->overlimits++;
+		WRITE_ONCE(q->overlimits, q->overlimits + 1);
 	}
 
 	if (cl->prio_activity) {	/* not necessary: speed optimization */
@@ -628,7 +628,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		/* enqueue to helper queue */
 		if (q->direct_queue.qlen < q->direct_qlen) {
 			__qdisc_enqueue_tail(skb, &q->direct_queue);
-			q->direct_pkts++;
+			WRITE_ONCE(q->direct_pkts, q->direct_pkts + 1);
 		} else {
 			return qdisc_drop(skb, sch, to_free);
 		}
@@ -651,7 +651,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	sch->qstats.backlog += len;
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -951,7 +951,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 ok:
 		qdisc_bstats_update(sch, skb);
 		qdisc_qstats_backlog_dec(sch, skb);
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 		return skb;
 	}
 
@@ -1147,6 +1147,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 	 * parts (especially calling ndo_setup_tc) on errors.
 	 */
 	q->offload = true;
+	sch->flags |= TCQ_F_OFFLOADED;
 
 	return 0;
 }
@@ -1207,17 +1208,12 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct nlattr *nest;
 	struct tc_htb_glob gopt;
 
-	if (q->offload)
-		sch->flags |= TCQ_F_OFFLOADED;
-	else
-		sch->flags &= ~TCQ_F_OFFLOADED;
-
-	sch->qstats.overlimits = q->overlimits;
+	sch->qstats.overlimits = READ_ONCE(q->overlimits);
 	/* Its safe to not acquire qdisc lock. As we hold RTNL,
 	 * no change can happen on the qdisc parameters.
 	 */
 
-	gopt.direct_pkts = q->direct_pkts;
+	gopt.direct_pkts = READ_ONCE(q->direct_pkts);
 	gopt.version = HTB_VER;
 	gopt.rate2quantum = q->rate2quantum;
 	gopt.defcls = q->defcls;
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index a0133a7b9d3b..ec8c91d3fde0 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -143,10 +143,10 @@ EXPORT_SYMBOL_NS_GPL(mq_attach, "NET_SCHED_INTERNAL");
 void mq_dump_common(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct net_device *dev = qdisc_dev(sch);
+	unsigned int qlen = 0;
 	struct Qdisc *qdisc;
 	unsigned int ntx;
 
-	sch->q.qlen = 0;
 	gnet_stats_basic_sync_init(&sch->bstats);
 	memset(&sch->qstats, 0, sizeof(sch->qstats));
 
@@ -163,10 +163,11 @@ void mq_dump_common(struct Qdisc *sch, struct sk_buff *skb)
 				     &qdisc->bstats, false);
 		gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats,
 				     &qdisc->qstats);
-		sch->q.qlen += qdisc_qlen(qdisc);
+		qlen += qdisc_qlen(qdisc);
 
 		spin_unlock_bh(qdisc_lock(qdisc));
 	}
+	WRITE_ONCE(sch->q.qlen, qlen);
 }
 EXPORT_SYMBOL_NS_GPL(mq_dump_common, "NET_SCHED_INTERNAL");
 
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 002add5ce9e0..91a92992cd24 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -555,10 +555,11 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct mqprio_sched *priv = qdisc_priv(sch);
 	struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb);
 	struct tc_mqprio_qopt opt = { 0 };
+	unsigned int qlen = 0;
 	struct Qdisc *qdisc;
 	unsigned int ntx;
 
-	sch->q.qlen = 0;
+	qlen = 0;
 	gnet_stats_basic_sync_init(&sch->bstats);
 	memset(&sch->qstats, 0, sizeof(sch->qstats));
 
@@ -575,10 +576,11 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 				     &qdisc->bstats, false);
 		gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats,
 				     &qdisc->qstats);
-		sch->q.qlen += qdisc_qlen(qdisc);
+		qlen += qdisc_qlen(qdisc);
 
 		spin_unlock_bh(qdisc_lock(qdisc));
 	}
+	WRITE_ONCE(sch->q.qlen, qlen);
 
 	mqprio_qopt_reconstruct(dev, &opt);
 	opt.hw = priv->hw_offload;
@@ -663,12 +665,12 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	__acquires(d->lock)
 {
 	if (cl >= TC_H_MIN_PRIORITY) {
-		int i;
-		__u32 qlen;
-		struct gnet_stats_queue qstats = {0};
-		struct gnet_stats_basic_sync bstats;
 		struct net_device *dev = qdisc_dev(sch);
 		struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK];
+		struct gnet_stats_queue qstats = {0};
+		struct gnet_stats_basic_sync bstats;
+		u32 qlen = 0;
+		int i;
 
 		gnet_stats_basic_sync_init(&bstats);
 		/* Drop lock here it will be reclaimed before touching
@@ -689,11 +691,11 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 					     &qdisc->bstats, false);
 			gnet_stats_add_queue(&qstats, qdisc->cpu_qstats,
 					     &qdisc->qstats);
-			sch->q.qlen += qdisc_qlen(qdisc);
+			qlen += qdisc_qlen(qdisc);
 
 			spin_unlock_bh(qdisc_lock(qdisc));
 		}
-		qlen = qdisc_qlen(sch) + qstats.qlen;
+		qlen = qlen + qstats.qlen;
 
 		/* Reclaim root sleeping lock before completing stats */
 		if (d->lock)
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 9f822fee113d..a467dd122369 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -76,7 +76,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	ret = qdisc_enqueue(skb, qdisc, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
-		sch->q.qlen++;
+		qdisc_qlen_inc(sch);
 		return NET_XMIT_SUCCESS;
 	}
 	if (net_xmit_drop_count(ret))
@@ -103,10 +103,10 @@ static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
 		if (!netif_xmit_stopped(
 		    netdev_get_tx_queue(qdisc_dev(sch), q->curband))) {
 			qdisc = q->queues[q->curband];
-			skb = qdisc->dequeue(qdisc);
+			skb = qdisc_dequeue_peeked(qdisc);
 			if (skb) {
 				qdisc_bstats_update(sch, skb);
-				sch->q.qlen--;
+				qdisc_qlen_dec(sch);
 				return skb;
 			}
 		}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 17a79fe2f091..db44cdb47dce 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -416,7 +416,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		rb_insert_color(&nskb->rbnode, &q->t_root);
 	}
 	q->t_len++;
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 }
 
 /* netem can't properly corrupt a megapacket (like we get from GSO), so instead
@@ -750,19 +750,19 @@ deliver:
 					if (net_xmit_drop_count(err))
 						qdisc_qstats_drop(sch);
 					sch->qstats.backlog -= pkt_len;
-					sch->q.qlen--;
+					qdisc_qlen_dec(sch);
 					qdisc_tree_reduce_backlog(sch, 1, pkt_len);
 				}
 				goto tfifo_dequeue;
 			}
-			sch->q.qlen--;
+			qdisc_qlen_dec(sch);
 			goto deliver;
 		}
 
 		if (q->qdisc) {
 			skb = q->qdisc->ops->dequeue(q->qdisc);
 			if (skb) {
-				sch->q.qlen--;
+				qdisc_qlen_dec(sch);
 				goto deliver;
 			}
 		}
@@ -775,7 +775,7 @@ deliver:
 	if (q->qdisc) {
 		skb = q->qdisc->ops->dequeue(q->qdisc);
 		if (skb) {
-			sch->q.qlen--;
+			qdisc_qlen_dec(sch);
 			goto deliver;
 		}
 	}
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 9e2b9a490db2..fe42ae3d6b69 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -86,7 +86,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 	ret = qdisc_enqueue(skb, qdisc, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->qstats.backlog += len;
-		sch->q.qlen++;
+		qdisc_qlen_inc(sch);
 		return NET_XMIT_SUCCESS;
 	}
 	if (net_xmit_drop_count(ret))
@@ -119,7 +119,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch)
 		if (skb) {
 			qdisc_bstats_update(sch, skb);
 			qdisc_qstats_backlog_dec(sch, skb);
-			sch->q.qlen--;
+			qdisc_qlen_dec(sch);
 			return skb;
 		}
 	}
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 699e45873f86..195c434aae5f 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1152,12 +1152,12 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 	if (!skb)
 		return NULL;
 
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 
 	skb = agg_dequeue(in_serv_agg, cl, len);
 
 	if (!skb) {
-		sch->q.qlen++;
+		qdisc_qlen_inc(sch);
 		return NULL;
 	}
 
@@ -1265,7 +1265,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	_bstats_update(&cl->bstats, len, gso_segs);
 	sch->qstats.backlog += len;
-	++sch->q.qlen;
+	qdisc_qlen_inc(sch);
 
 	agg = cl->agg;
 	/* if the class is active, then done here */
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 4d0e44a2e7c6..0719590dfd73 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -139,7 +139,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		sch->qstats.backlog += len;
-		sch->q.qlen++;
+		qdisc_qlen_inc(sch);
 	} else if (net_xmit_drop_count(ret)) {
 		WRITE_ONCE(q->stats.pdrop,
 			   q->stats.pdrop + 1);
@@ -166,7 +166,7 @@ static struct sk_buff *red_dequeue(struct Qdisc *sch)
 	if (skb) {
 		qdisc_bstats_update(sch, skb);
 		qdisc_qstats_backlog_dec(sch, skb);
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 	} else {
 		if (!red_is_idling(&q->vars))
 			red_start_of_idle_period(&q->vars);
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index d3ee8e5479b3..efd9251c3add 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -416,7 +416,7 @@ enqueue:
 	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		sch->qstats.backlog += len;
-		sch->q.qlen++;
+		qdisc_qlen_inc(sch);
 		increment_qlen(&cb, q);
 	} else if (net_xmit_drop_count(ret)) {
 		WRITE_ONCE(q->stats.childdrop,
@@ -446,7 +446,7 @@ static struct sk_buff *sfb_dequeue(struct Qdisc *sch)
 	if (skb) {
 		qdisc_bstats_update(sch, skb);
 		qdisc_qstats_backlog_dec(sch, skb);
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 		decrement_qlen(skb, q);
 	}
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index f39822babf88..f9807ee2cf6c 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -302,7 +302,7 @@ drop:
 		len = qdisc_pkt_len(skb);
 		WRITE_ONCE(slot->backlog, slot->backlog - len);
 		sfq_dec(q, x);
-		sch->q.qlen--;
+		qdisc_qlen_dec(sch);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop_reason(skb, sch, to_free, QDISC_DROP_OVERLIMIT);
 		return len;
@@ -456,7 +456,8 @@ enqueue:
 		/* We could use a bigger initial quantum for new flows */
 		WRITE_ONCE(slot->allot, q->quantum);
 	}
-	if (++sch->q.qlen <= q->limit)
+	qdisc_qlen_inc(sch);
+	if (sch->q.qlen <= q->limit)
 		return NET_XMIT_SUCCESS;
 
 	qlen = slot->qlen;
@@ -497,7 +498,7 @@ next_slot:
 	skb = slot_dequeue_head(slot);
 	sfq_dec(q, a);
 	qdisc_bstats_update(sch, skb);
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 	qdisc_qstats_backlog_dec(sch, skb);
 	WRITE_ONCE(slot->backlog, slot->backlog - qdisc_pkt_len(skb));
 	/* Is the slot empty? */
@@ -596,7 +597,7 @@ drop:
 			WRITE_ONCE(slot->allot, q->quantum);
 		}
 	}
-	sch->q.qlen -= dropped;
+	WRITE_ONCE(sch->q.qlen, sch->q.qlen - dropped);
 	qdisc_tree_reduce_backlog(sch, dropped, drop_len);
 }
 
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index f485f62ab721..52abfb4015a3 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -93,7 +93,7 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		if (prio < q->lowest_prio)
 			q->lowest_prio = prio;
 
-		sch->q.qlen++;
+		qdisc_qlen_inc(sch);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -145,7 +145,7 @@ static struct sk_buff *skbprio_dequeue(struct Qdisc *sch)
 	if (unlikely(!skb))
 		return NULL;
 
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_bstats_update(sch, skb);
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 45245157e00a..d2d11a127f03 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -574,7 +574,7 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	qdisc_qstats_backlog_inc(sch, skb);
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 
 	return qdisc_enqueue(skb, child, to_free);
 }
@@ -749,13 +749,13 @@ static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq,
 		return NULL;
 
 skip_peek_checks:
-	skb = child->ops->dequeue(child);
+	skb = qdisc_dequeue_peeked(child);
 	if (unlikely(!skb))
 		return NULL;
 
 	qdisc_bstats_update(sch, skb);
 	qdisc_qstats_backlog_dec(sch, skb);
-	sch->q.qlen--;
+	qdisc_qlen_dec(sch);
 
 	return skb;
 }
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index f2340164f579..25edf11a7d67 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -231,7 +231,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
 			len += seg_len;
 		}
 	}
-	sch->q.qlen += nb;
+	WRITE_ONCE(sch->q.qlen, sch->q.qlen + nb);
 	sch->qstats.backlog += len;
 	if (nb > 0) {
 		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
@@ -264,7 +264,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	sch->qstats.backlog += len;
-	sch->q.qlen++;
+	qdisc_qlen_inc(sch);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -309,7 +309,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 			q->tokens = toks;
 			q->ptokens = ptoks;
 			qdisc_qstats_backlog_dec(sch, skb);
-			sch->q.qlen--;
+			qdisc_qlen_dec(sch);
 			qdisc_bstats_update(sch, skb);
 			return skb;
 		}
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index ec4039a201a2..5c42a29a981c 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -52,7 +52,8 @@
 struct teql_master {
 	struct Qdisc_ops qops;
 	struct net_device *dev;
-	struct Qdisc *slaves;
+	struct Qdisc __rcu	*slaves;
+	spinlock_t		slaves_lock; /* serializes writes to ->slaves */
 	struct list_head master_list;
 	unsigned long	tx_bytes;
 	unsigned long	tx_packets;
@@ -61,7 +62,7 @@ struct teql_master {
 };
 
 struct teql_sched_data {
-	struct Qdisc *next;
+	struct Qdisc __rcu	*next;
 	struct teql_master *m;
 	struct sk_buff_head q;
 };
@@ -101,13 +102,15 @@ teql_dequeue(struct Qdisc *sch)
 	if (skb == NULL) {
 		struct net_device *m = qdisc_dev(q);
 		if (m) {
-			dat->m->slaves = sch;
+			spin_lock_bh(&dat->m->slaves_lock);
+			rcu_assign_pointer(dat->m->slaves, sch);
+			spin_unlock_bh(&dat->m->slaves_lock);
 			netif_wake_queue(m);
 		}
 	} else {
 		qdisc_bstats_update(sch, skb);
 	}
-	sch->q.qlen = dat->q.qlen + q->q.qlen;
+	WRITE_ONCE(sch->q.qlen, dat->q.qlen + READ_ONCE(q->q.qlen));
 	return skb;
 }
 
@@ -132,34 +135,49 @@ teql_destroy(struct Qdisc *sch)
 	struct Qdisc *q, *prev;
 	struct teql_sched_data *dat = qdisc_priv(sch);
 	struct teql_master *master = dat->m;
+	struct netdev_queue *txq = NULL;
+	bool reset_master_queue = false;
 
 	if (!master)
 		return;
 
-	prev = master->slaves;
+	spin_lock_bh(&master->slaves_lock);
+	prev = rcu_dereference_protected(master->slaves,
+					 lockdep_is_held(&master->slaves_lock));
 	if (prev) {
 		do {
-			q = NEXT_SLAVE(prev);
-			if (q == sch) {
-				NEXT_SLAVE(prev) = NEXT_SLAVE(q);
-				if (q == master->slaves) {
-					master->slaves = NEXT_SLAVE(q);
-					if (q == master->slaves) {
-						struct netdev_queue *txq;
-
-						txq = netdev_get_tx_queue(master->dev, 0);
-						master->slaves = NULL;
-
-						dev_reset_queue(master->dev,
-								txq, NULL);
-					}
-				}
-				skb_queue_purge(&dat->q);
-				break;
+			struct Qdisc *head, *next;
+
+			q = rcu_dereference_protected(NEXT_SLAVE(prev),
+						      lockdep_is_held(&master->slaves_lock));
+			if (q != sch) {
+				prev = q;
+				continue;
 			}
 
-		} while ((prev = q) != master->slaves);
+			next = rcu_dereference_protected(NEXT_SLAVE(q),
+							 lockdep_is_held(&master->slaves_lock));
+			rcu_assign_pointer(NEXT_SLAVE(prev), next);
+
+			head = rcu_dereference_protected(master->slaves,
+							 lockdep_is_held(&master->slaves_lock));
+			if (q == head) {
+				rcu_assign_pointer(master->slaves, next);
+				if (q == next) {
+					txq = netdev_get_tx_queue(master->dev, 0);
+					rcu_assign_pointer(master->slaves, NULL);
+					reset_master_queue = true;
+				}
+			}
+			skb_queue_purge(&dat->q);
+			break;
+		} while (prev != rcu_dereference_protected(master->slaves,
+							   lockdep_is_held(&master->slaves_lock)));
 	}
+	spin_unlock_bh(&master->slaves_lock);
+
+	if (reset_master_queue)
+		dev_reset_queue(master->dev, txq, NULL);
 }
 
 static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt,
@@ -168,6 +186,7 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt,
 	struct net_device *dev = qdisc_dev(sch);
 	struct teql_master *m = (struct teql_master *)sch->ops;
 	struct teql_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *first;
 
 	if (dev->hard_header_len > m->dev->hard_header_len)
 		return -EINVAL;
@@ -184,7 +203,9 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt,
 
 	skb_queue_head_init(&q->q);
 
-	if (m->slaves) {
+	spin_lock_bh(&m->slaves_lock);
+	first = rcu_dereference_protected(m->slaves, lockdep_is_held(&m->slaves_lock));
+	if (first) {
 		if (m->dev->flags & IFF_UP) {
 			if ((m->dev->flags & IFF_POINTOPOINT &&
 			     !(dev->flags & IFF_POINTOPOINT)) ||
@@ -192,8 +213,10 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt,
 			     !(dev->flags & IFF_BROADCAST)) ||
 			    (m->dev->flags & IFF_MULTICAST &&
 			     !(dev->flags & IFF_MULTICAST)) ||
-			    dev->mtu < m->dev->mtu)
+			    dev->mtu < m->dev->mtu) {
+				spin_unlock_bh(&m->slaves_lock);
 				return -EINVAL;
+			}
 		} else {
 			if (!(dev->flags&IFF_POINTOPOINT))
 				m->dev->flags &= ~IFF_POINTOPOINT;
@@ -204,14 +227,17 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt,
 			if (dev->mtu < m->dev->mtu)
 				m->dev->mtu = dev->mtu;
 		}
-		q->next = NEXT_SLAVE(m->slaves);
-		NEXT_SLAVE(m->slaves) = sch;
+		rcu_assign_pointer(q->next,
+				   rcu_dereference_protected(NEXT_SLAVE(first),
+							     lockdep_is_held(&m->slaves_lock)));
+		rcu_assign_pointer(NEXT_SLAVE(first), sch);
 	} else {
-		q->next = sch;
-		m->slaves = sch;
+		rcu_assign_pointer(q->next, sch);
+		rcu_assign_pointer(m->slaves, sch);
 		m->dev->mtu = dev->mtu;
 		m->dev->flags = (m->dev->flags&~FMASK)|(dev->flags&FMASK);
 	}
+	spin_unlock_bh(&m->slaves_lock);
 	return 0;
 }
 
@@ -285,12 +311,14 @@ static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
 	int subq = skb_get_queue_mapping(skb);
 	struct sk_buff *skb_res = NULL;
 
-	start = master->slaves;
-
 restart:
 	nores = 0;
 	busy = 0;
 
+	rcu_read_lock();
+
+	start = rcu_dereference(master->slaves);
+
 	q = start;
 	if (!q)
 		goto drop;
@@ -317,10 +345,17 @@ restart:
 				    netdev_start_xmit(skb, slave, slave_txq, false) ==
 				    NETDEV_TX_OK) {
 					__netif_tx_unlock(slave_txq);
-					master->slaves = NEXT_SLAVE(q);
+					spin_lock(&master->slaves_lock);
+					if (rcu_dereference_protected(master->slaves,
+								      lockdep_is_held(&master->slaves_lock)) == q)
+						rcu_assign_pointer(master->slaves,
+								   rcu_dereference_protected(NEXT_SLAVE(q),
+											     lockdep_is_held(&master->slaves_lock)));
+					spin_unlock(&master->slaves_lock);
 					netif_wake_queue(dev);
 					master->tx_packets++;
 					master->tx_bytes += length;
+					rcu_read_unlock();
 					return NETDEV_TX_OK;
 				}
 				__netif_tx_unlock(slave_txq);
@@ -329,45 +364,56 @@ restart:
 				busy = 1;
 			break;
 		case 1:
-			master->slaves = NEXT_SLAVE(q);
+			spin_lock(&master->slaves_lock);
+			if (rcu_dereference_protected(master->slaves,
+						      lockdep_is_held(&master->slaves_lock)) == q)
+				rcu_assign_pointer(master->slaves,
+						   rcu_dereference_protected(NEXT_SLAVE(q),
+									     lockdep_is_held(&master->slaves_lock)));
+			spin_unlock(&master->slaves_lock);
+			rcu_read_unlock();
 			return NETDEV_TX_OK;
 		default:
 			nores = 1;
 			break;
 		}
 		__skb_pull(skb, skb_network_offset(skb));
-	} while ((q = NEXT_SLAVE(q)) != start);
+	} while ((q = rcu_dereference(NEXT_SLAVE(q))) != start);
 
 	if (nores && skb_res == NULL) {
 		skb_res = skb;
+		rcu_read_unlock();
 		goto restart;
 	}
 
 	if (busy) {
 		netif_stop_queue(dev);
+		rcu_read_unlock();
 		return NETDEV_TX_BUSY;
 	}
 	master->tx_errors++;
 
 drop:
 	master->tx_dropped++;
+	rcu_read_unlock();
 	dev_kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
 static int teql_master_open(struct net_device *dev)
 {
-	struct Qdisc *q;
+	struct Qdisc *q, *first;
 	struct teql_master *m = netdev_priv(dev);
 	int mtu = 0xFFFE;
 	unsigned int flags = IFF_NOARP | IFF_MULTICAST;
 
-	if (m->slaves == NULL)
+	first = rtnl_dereference(m->slaves);
+	if (!first)
 		return -EUNATCH;
 
 	flags = FMASK;
 
-	q = m->slaves;
+	q = first;
 	do {
 		struct net_device *slave = qdisc_dev(q);
 
@@ -389,7 +435,7 @@ static int teql_master_open(struct net_device *dev)
 			flags &= ~IFF_BROADCAST;
 		if (!(slave->flags&IFF_MULTICAST))
 			flags &= ~IFF_MULTICAST;
-	} while ((q = NEXT_SLAVE(q)) != m->slaves);
+	} while ((q = rtnl_dereference(NEXT_SLAVE(q))) != first);
 
 	m->dev->mtu = mtu;
 	m->dev->flags = (m->dev->flags&~FMASK) | flags;
@@ -417,14 +463,15 @@ static void teql_master_stats64(struct net_device *dev,
 static int teql_master_mtu(struct net_device *dev, int new_mtu)
 {
 	struct teql_master *m = netdev_priv(dev);
-	struct Qdisc *q;
+	struct Qdisc *q, *first;
 
-	q = m->slaves;
+	first = rtnl_dereference(m->slaves);
+	q = first;
 	if (q) {
 		do {
 			if (new_mtu > qdisc_dev(q)->mtu)
 				return -EINVAL;
-		} while ((q = NEXT_SLAVE(q)) != m->slaves);
+		} while ((q = rtnl_dereference(NEXT_SLAVE(q))) != first);
 	}
 
 	WRITE_ONCE(dev->mtu, new_mtu);
@@ -444,6 +491,7 @@ static __init void teql_master_setup(struct net_device *dev)
 	struct teql_master *master = netdev_priv(dev);
 	struct Qdisc_ops *ops = &master->qops;
 
+	spin_lock_init(&master->slaves_lock);
 	master->dev	= dev;
 	ops->priv_size  = sizeof(struct teql_sched_data);
 
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index d758f5c3e06e..c2a0de2adf6f 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -92,6 +92,7 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb,
 		if (!--addrcnt)
 			break;
 	}
+	WARN_ON_ONCE(addrcnt);
 	rcu_read_unlock();
 
 	return 0;
@@ -373,42 +374,39 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p)
 	struct sk_buff *skb = commp->skb;
 	struct netlink_callback *cb = commp->cb;
 	const struct inet_diag_req_v2 *r = commp->r;
-	struct net *net = sock_net(skb->sk);
 	struct inet_sock *inet = inet_sk(sk);
 	int err = 0;
 
-	if (!net_eq(sock_net(sk), net))
+	lock_sock(sk);
+	if (ep->base.dead)
 		goto out;
 
-	if (cb->args[4] < cb->args[1])
-		goto next;
-
-	if (!(r->idiag_states & TCPF_LISTEN) && !list_empty(&ep->asocs))
-		goto next;
+	/* Skip eps with assocs if non-LISTEN states were requested, since
+	 * they'll be dumped by sctp_sock_dump() during assoc traversal.
+	 */
+	if ((r->idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)) &&
+	    !list_empty(&ep->asocs))
+		goto out;
 
 	if (r->sdiag_family != AF_UNSPEC &&
 	    sk->sk_family != r->sdiag_family)
-		goto next;
+		goto out;
 
 	if (r->id.idiag_sport != inet->inet_sport &&
 	    r->id.idiag_sport)
-		goto next;
+		goto out;
 
 	if (r->id.idiag_dport != inet->inet_dport &&
 	    r->id.idiag_dport)
-		goto next;
-
-	if (inet_sctp_diag_fill(sk, NULL, skb, r,
-				sk_user_ns(NETLINK_CB(cb->skb).sk),
-				NETLINK_CB(cb->skb).portid,
-				cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				cb->nlh, commp->net_admin) < 0) {
-		err = 2;
 		goto out;
-	}
-next:
-	cb->args[4]++;
+
+	err = inet_sctp_diag_fill(sk, NULL, skb, r,
+				  sk_user_ns(NETLINK_CB(cb->skb).sk),
+				  NETLINK_CB(cb->skb).portid,
+				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				  cb->nlh, commp->net_admin);
 out:
+	release_sock(sk);
 	return err;
 }
 
@@ -479,41 +477,40 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		.r = r,
 		.net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN),
 	};
-	int pos = cb->args[2];
+	int pos;
 
 	/* eps hashtable dumps
 	 * args:
 	 * 0 : if it will traversal listen sock
 	 * 1 : to record the sock pos of this time's traversal
-	 * 4 : to work as a temporary variable to traversal list
 	 */
 	if (cb->args[0] == 0) {
-		if (!(idiag_states & TCPF_LISTEN))
-			goto skip;
-		if (sctp_for_each_endpoint(sctp_ep_dump, &commp))
-			goto done;
-skip:
+		if (idiag_states & TCPF_LISTEN) {
+			pos = cb->args[1];
+			if (sctp_for_each_endpoint(sctp_ep_dump, net, &pos,
+						   &commp)) {
+				cb->args[1] = pos;
+				return;
+			}
+		}
 		cb->args[0] = 1;
 		cb->args[1] = 0;
-		cb->args[4] = 0;
 	}
 
+	if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
+		return;
+
 	/* asocs by transport hashtable dump
 	 * args:
 	 * 1 : to record the assoc pos of this time's traversal
 	 * 2 : to record the transport pos of this time's traversal
 	 * 3 : to mark if we have dumped the ep info of the current asoc
-	 * 4 : to work as a temporary variable to traversal list
-	 * 5 : to save the sk we get from travelsing the tsp list.
+	 * 4 : to track position within ep->asocs list in sctp_sock_dump()
 	 */
-	if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
-		goto done;
-
+	pos = cb->args[2];
 	sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump,
 					net, &pos, &commp);
 	cb->args[2] = pos;
-
-done:
 	cb->args[1] = cb->args[4];
 	cb->args[4] = 0;
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 5800e7ee7ea0..e95061b672ef 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -663,8 +663,9 @@ static void sctp_free_addr_wq(struct net *net)
 	struct sctp_sockaddr_entry *addrw;
 	struct sctp_sockaddr_entry *temp;
 
+	timer_shutdown_sync(&net->sctp.addr_wq_timer);
+
 	spin_lock_bh(&net->sctp.addr_wq_lock);
-	timer_delete(&net->sctp.addr_wq_timer);
 	list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
 		list_del(&addrw->list);
 		kfree(addrw);
@@ -864,7 +865,7 @@ int sctp_udp_sock_start(struct net *net)
 	tuncfg.encap_type = 1;
 	tuncfg.encap_rcv = sctp_udp_rcv;
 	tuncfg.encap_err_lookup = sctp_udp_v4_err;
-	setup_udp_tunnel_sock(net, sock, &tuncfg);
+	setup_udp_tunnel_sock(net, sock->sk, &tuncfg);
 	net->sctp.udp4_sock = sock->sk;
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -878,7 +879,7 @@ int sctp_udp_sock_start(struct net *net)
 	err = udp_sock_create(net, &udp_conf, &sock);
 	if (err) {
 		pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
-		udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+		udp_tunnel_sock_release(net->sctp.udp4_sock);
 		net->sctp.udp4_sock = NULL;
 		return err;
 	}
@@ -886,7 +887,7 @@ int sctp_udp_sock_start(struct net *net)
 	tuncfg.encap_type = 1;
 	tuncfg.encap_rcv = sctp_udp_rcv;
 	tuncfg.encap_err_lookup = sctp_udp_v6_err;
-	setup_udp_tunnel_sock(net, sock, &tuncfg);
+	setup_udp_tunnel_sock(net, sock->sk, &tuncfg);
 	net->sctp.udp6_sock = sock->sk;
 #endif
 
@@ -896,11 +897,11 @@ int sctp_udp_sock_start(struct net *net)
 void sctp_udp_sock_stop(struct net *net)
 {
 	if (net->sctp.udp4_sock) {
-		udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+		udp_tunnel_sock_release(net->sctp.udp4_sock);
 		net->sctp.udp4_sock = NULL;
 	}
 	if (net->sctp.udp6_sock) {
-		udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
+		udp_tunnel_sock_release(net->sctp.udp6_sock);
 		net->sctp.udp6_sock = NULL;
 	}
 }
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 1741a9f33d8c..8adac9e0cd66 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1761,6 +1761,8 @@ struct sctp_association *sctp_unpack_cookie(
 	bear_cookie = &cookie->c;
 
 	ch = (struct sctp_chunkhdr *)(bear_cookie + 1);
+	if (ch->type != SCTP_CID_INIT)
+		goto malformed;
 	chlen = ntohs(ch->length);
 	if (chlen < sizeof(struct sctp_init_chunk))
 		goto malformed;
@@ -2298,7 +2300,8 @@ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
 	 * VIOLATION error.  We build the ERROR chunk here and let the normal
 	 * error handling code build and send the packet.
 	 */
-	if (param.v != (void *)chunk->chunk_end)
+	if (param.v != (void *)peer_init +
+		       SCTP_PAD4(ntohs(peer_init->chunk_hdr.length)))
 		return sctp_process_inv_paramlength(asoc, param.p, chunk, errp);
 
 	/* The only missing mandatory param possible today is
@@ -2641,6 +2644,9 @@ do_addr_param:
 			goto fall_through;
 
 		addr_param = param.v + sizeof(struct sctp_addip_param);
+		if (ntohs(addr_param->p.length) >
+		    ntohs(param.p->length) - sizeof(struct sctp_addip_param))
+			break;
 
 		af = sctp_get_af_specific(param_type2af(addr_param->p.type));
 		if (!af)
@@ -3039,13 +3045,16 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
 	union sctp_addr	addr;
 	struct sctp_af *af;
 
-	addr_param = (void *)asconf_param + sizeof(*asconf_param);
-
 	if (asconf_param->param_hdr.type != SCTP_PARAM_ADD_IP &&
 	    asconf_param->param_hdr.type != SCTP_PARAM_DEL_IP &&
 	    asconf_param->param_hdr.type != SCTP_PARAM_SET_PRIMARY)
 		return SCTP_ERROR_UNKNOWN_PARAM;
 
+	addr_param = (void *)asconf_param + sizeof(*asconf_param);
+	if (ntohs(addr_param->p.length) >
+	    ntohs(asconf_param->param_hdr.length) - sizeof(*asconf_param))
+		return SCTP_ERROR_PROTO_VIOLATION;
+
 	switch (addr_param->p.type) {
 	case SCTP_PARAM_IPV6_ADDRESS:
 		if (!asoc->peer.ipv6_address)
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 9b23c11cbb9e..3893b44448b3 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -74,7 +74,8 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale(
 					const struct sctp_association *asoc,
 					const union sctp_subtype type,
 					void *arg,
-					struct sctp_cmd_seq *commands);
+					struct sctp_cmd_seq *commands,
+					struct sctp_errhdr *err);
 static enum sctp_disposition sctp_sf_shut_8_4_5(
 					struct net *net,
 					const struct sctp_endpoint *ep,
@@ -415,6 +416,8 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net,
 	/* Update socket peer label if first association. */
 	if (security_sctp_assoc_request(new_asoc, chunk->skb)) {
 		sctp_association_free(new_asoc);
+		if (err_chunk)
+			sctp_chunk_free(err_chunk);
 		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
 	}
 
@@ -705,11 +708,12 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 					 struct sctp_cmd_seq *commands)
 {
 	struct sctp_ulpevent *ev, *ai_ev = NULL, *auth_ev = NULL;
+	struct sctp_chunk *err_chk_p = NULL;
 	struct sctp_association *new_asoc;
 	struct sctp_init_chunk *peer_init;
 	struct sctp_chunk *chunk = arg;
-	struct sctp_chunk *err_chk_p;
 	struct sctp_chunk *repl;
+	enum sctp_cid cid;
 	struct sock *sk;
 	int error = 0;
 
@@ -783,6 +787,19 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 		}
 	}
 
+	peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1);
+	cid = peer_init->chunk_hdr.type;
+	if (!sctp_sk(sk)->cookie_auth_enable &&
+	    !sctp_verify_init(net, ep, asoc, cid, peer_init, chunk,
+			      &err_chk_p)) {
+		sctp_association_free(new_asoc);
+		if (err_chk_p)
+			sctp_chunk_free(err_chk_p);
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+	}
+	if (err_chk_p)
+		sctp_chunk_free(err_chk_p);
+
 	if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) {
 		sctp_association_free(new_asoc);
 		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -796,7 +813,6 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 	/* This is a brand-new association, so these are not yet side
 	 * effects--it is safe to run them here.
 	 */
-	peer_init = (struct sctp_init_chunk *)(chunk->subh.cookie_hdr + 1);
 	if (!sctp_process_init(new_asoc, chunk,
 			       &chunk->subh.cookie_hdr->c.peer_addr,
 			       peer_init, GFP_ATOMIC))
@@ -1606,6 +1622,8 @@ static enum sctp_disposition sctp_sf_do_unexpected_init(
 	/* Update socket peer label if first association. */
 	if (security_sctp_assoc_request(new_asoc, chunk->skb)) {
 		sctp_association_free(new_asoc);
+		if (err_chunk)
+			sctp_chunk_free(err_chunk);
 		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
 	}
 
@@ -1671,6 +1689,7 @@ static enum sctp_disposition sctp_sf_do_unexpected_init(
 		 * parameter type.
 		 */
 		sctp_addto_chunk(repl, len, unk_param);
+		sctp_chunk_free(err_chunk);
 	}
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc));
@@ -2210,10 +2229,12 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
 					void *arg,
 					struct sctp_cmd_seq *commands)
 {
+	struct sctp_chunk *err_chk_p = NULL;
 	struct sctp_association *new_asoc;
+	struct sctp_init_chunk *peer_init;
 	struct sctp_chunk *chunk = arg;
 	enum sctp_disposition retval;
-	struct sctp_chunk *err_chk_p;
+	enum sctp_cid cid;
 	int error = 0;
 	char action;
 
@@ -2282,6 +2303,21 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
 	switch (action) {
 	case 'A': /* Association restart. */
 	case 'B': /* Collision case B. */
+		peer_init = (struct sctp_init_chunk *)
+				(chunk->subh.cookie_hdr + 1);
+		cid = peer_init->chunk_hdr.type;
+		if (!sctp_sk(ep->base.sk)->cookie_auth_enable &&
+		    !sctp_verify_init(net, ep, asoc, cid, peer_init, chunk,
+				      &err_chk_p)) {
+			sctp_association_free(new_asoc);
+			if (err_chk_p)
+				sctp_chunk_free(err_chk_p);
+			return sctp_sf_pdiscard(net, ep, asoc, type, arg,
+						commands);
+		}
+		if (err_chk_p)
+			sctp_chunk_free(err_chk_p);
+		fallthrough;
 	case 'D': /* Collision case D. */
 		/* Update socket peer label if first association. */
 		if (security_sctp_assoc_request((struct sctp_association *)asoc,
@@ -2494,9 +2530,15 @@ enum sctp_disposition sctp_sf_cookie_echoed_err(
 	 * errors.
 	 */
 	sctp_walk_errors(err, chunk->chunk_hdr) {
-		if (SCTP_ERROR_STALE_COOKIE == err->cause)
-			return sctp_sf_do_5_2_6_stale(net, ep, asoc, type,
-							arg, commands);
+		if (err->cause != SCTP_ERROR_STALE_COOKIE)
+			continue;
+		/* The staleness is only meaningful if the cause is long
+		 * enough to hold it; a shorter one is malformed.
+		 */
+		if (ntohs(err->length) < sizeof(*err) + sizeof(__be32))
+			break;
+		return sctp_sf_do_5_2_6_stale(net, ep, asoc, type,
+					      arg, commands, err);
 	}
 
 	/* It is possible to have malformed error causes, and that
@@ -2538,13 +2580,13 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale(
 					const struct sctp_association *asoc,
 					const union sctp_subtype type,
 					void *arg,
-					struct sctp_cmd_seq *commands)
+					struct sctp_cmd_seq *commands,
+					struct sctp_errhdr *err)
 {
 	int attempts = asoc->init_err_counter + 1;
-	struct sctp_chunk *chunk = arg, *reply;
 	struct sctp_cookie_preserve_param bht;
 	struct sctp_bind_addr *bp;
-	struct sctp_errhdr *err;
+	struct sctp_chunk *reply;
 	u32 stale;
 
 	if (attempts > asoc->max_init_attempts) {
@@ -2555,8 +2597,6 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale(
 		return SCTP_DISPOSITION_DELETE_TCB;
 	}
 
-	err = (struct sctp_errhdr *)(chunk->skb->data);
-
 	/* When calculating the time extension, an implementation
 	 * SHOULD use the RTT information measured based on the
 	 * previous COOKIE ECHO / ERROR exchange, and should add no
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 66e12fb0c646..c7b9e325ec1c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4111,8 +4111,9 @@ static int sctp_setsockopt_reset_streams(struct sock *sk,
 	if (optlen < sizeof(*params))
 		return -EINVAL;
 	/* srs_number_streams is u16, so optlen can't be bigger than this. */
-	optlen = min_t(unsigned int, optlen, USHRT_MAX +
-					     sizeof(__u16) * sizeof(*params));
+	optlen = min_t(unsigned int, optlen,
+		       struct_size_t(struct sctp_reset_streams, srs_stream_list,
+				     USHRT_MAX));
 
 	if (params->srs_number_streams * sizeof(__u16) >
 	    optlen - sizeof(*params))
@@ -4598,8 +4599,8 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	if (optlen > 0) {
 		/* Trim it to the biggest size sctp sockopt may need if necessary */
 		optlen = min_t(unsigned int, optlen,
-			       PAGE_ALIGN(USHRT_MAX +
-					  sizeof(__u16) * sizeof(struct sctp_reset_streams)));
+			       PAGE_ALIGN(struct_size_t(struct sctp_reset_streams,
+							srs_stream_list, USHRT_MAX)));
 		kopt = memdup_sockptr(optval, optlen);
 		if (IS_ERR(kopt))
 			return PTR_ERR(kopt);
@@ -5369,24 +5370,39 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net,
 }
 
 int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *),
-			   void *p) {
-	int err = 0;
-	int hash = 0;
-	struct sctp_endpoint *ep;
+			   struct net *net, int *pos, void *p) {
+	int err, hash = 0, idx = 0, start;
 	struct sctp_hashbucket *head;
+	struct sctp_endpoint *ep;
 
 	for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize;
 	     hash++, head++) {
+		start = idx;
+again:
 		read_lock_bh(&head->lock);
 		sctp_for_each_hentry(ep, &head->chain) {
-			err = cb(ep, p);
-			if (err)
+			if (sock_net(ep->base.sk) != net)
+				continue;
+			if (idx++ >= *pos) {
+				sctp_endpoint_hold(ep);
 				break;
+			}
 		}
 		read_unlock_bh(&head->lock);
+
+		if (ep) {
+			err = cb(ep, p);
+			sctp_endpoint_put(ep);
+			if (err)
+				return err;
+			(*pos)++;
+
+			idx = start;
+			goto again;
+		}
 	}
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(sctp_for_each_endpoint);
 
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 619b3bab3824..32d6d03df321 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -470,9 +470,9 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
 {
 	struct smc_link *link = (struct smc_link *)wc->qp->qp_context;
 	struct smc_cdc_msg *cdc = buf;
+	struct smc_sock *smc = NULL;
 	struct smc_connection *conn;
 	struct smc_link_group *lgr;
-	struct smc_sock *smc;
 
 	if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved))
 		return; /* short message */
@@ -483,21 +483,26 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
 	lgr = smc_get_lgr(link);
 	read_lock_bh(&lgr->conns_lock);
 	conn = smc_lgr_find_conn(ntohl(cdc->token), lgr);
-	read_unlock_bh(&lgr->conns_lock);
-	if (!conn || conn->out_of_sync)
+	if (!conn || conn->out_of_sync) {
+		read_unlock_bh(&lgr->conns_lock);
 		return;
+	}
 	smc = container_of(conn, struct smc_sock, conn);
+	sock_hold(&smc->sk);
+	read_unlock_bh(&lgr->conns_lock);
 
 	if (cdc->prod_flags.failover_validation) {
 		smc_cdc_msg_validate(smc, cdc, link);
-		return;
+		goto out;
 	}
 	if (smc_cdc_before(ntohs(cdc->seqno),
 			   conn->local_rx_ctrl.seqno))
 		/* received seqno is old */
-		return;
+		goto out;
 
 	smc_cdc_msg_recv(smc, cdc);
+out:
+	sock_put(&smc->sk);
 }
 
 static struct smc_wr_rx_handler smc_cdc_rx_handlers[] = {
diff --git a/net/socket.c b/net/socket.c
index c2698a1441a7..f51bdcbaa43f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -310,8 +310,10 @@ efault_end:
 
 static struct kmem_cache *sock_inode_cachep __ro_after_init;
 
+static struct simple_xattr_cache sockfs_xa_cache;
+
 struct sockfs_inode {
-	struct simple_xattrs *xattrs;
+	struct list_head xattrs;
 	struct simple_xattr_limits xattr_limits;
 	struct socket_alloc;
 };
@@ -328,7 +330,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 	si = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL);
 	if (!si)
 		return NULL;
-	si->xattrs = NULL;
+	INIT_LIST_HEAD_RCU(&si->xattrs);
 	simple_xattr_limits_init(&si->xattr_limits);
 
 	init_waitqueue_head(&si->socket.wq.wait);
@@ -347,12 +349,8 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 static void sock_evict_inode(struct inode *inode)
 {
 	struct sockfs_inode *si = SOCKFS_I(inode);
-	struct simple_xattrs *xattrs = si->xattrs;
 
-	if (xattrs) {
-		simple_xattrs_free(xattrs, NULL);
-		kfree(xattrs);
-	}
+	simple_xattrs_free(&sockfs_xa_cache, &si->xattrs, NULL);
 	clear_inode(inode);
 }
 
@@ -443,13 +441,9 @@ static int sockfs_user_xattr_get(const struct xattr_handler *handler,
 				 const char *suffix, void *value, size_t size)
 {
 	const char *name = xattr_full_name(handler, suffix);
-	struct simple_xattrs *xattrs;
-
-	xattrs = READ_ONCE(SOCKFS_I(inode)->xattrs);
-	if (!xattrs)
-		return -ENODATA;
+	struct sockfs_inode *si = SOCKFS_I(inode);
 
-	return simple_xattr_get(xattrs, name, value, size);
+	return simple_xattr_get(&sockfs_xa_cache, &si->xattrs, name, value, size);
 }
 
 static int sockfs_user_xattr_set(const struct xattr_handler *handler,
@@ -460,13 +454,8 @@ static int sockfs_user_xattr_set(const struct xattr_handler *handler,
 {
 	const char *name = xattr_full_name(handler, suffix);
 	struct sockfs_inode *si = SOCKFS_I(inode);
-	struct simple_xattrs *xattrs;
-
-	xattrs = simple_xattrs_lazy_alloc(&si->xattrs, value, flags);
-	if (IS_ERR_OR_NULL(xattrs))
-		return PTR_ERR(xattrs);
 
-	return simple_xattr_set_limited(xattrs, &si->xattr_limits,
+	return simple_xattr_set_limited(&sockfs_xa_cache, &si->xattrs, &si->xattr_limits,
 					name, value, size, flags);
 }
 
@@ -635,8 +624,7 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
 	struct sockfs_inode *si = SOCKFS_I(d_inode(dentry));
 	ssize_t len, used;
 
-	len = simple_xattr_list(d_inode(dentry), READ_ONCE(si->xattrs),
-				buffer, size);
+	len = simple_xattr_list(d_inode(dentry), &si->xattrs, buffer, size);
 	if (len < 0)
 		return len;
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index bc8ca470718b..efa26899bc7d 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1026,8 +1026,23 @@ rpc_free_auth(struct rpc_clnt *clnt)
 	return NULL;
 }
 
-/*
- * Release reference to the RPC client
+/**
+ * rpc_hold_client - acquire a reference on an rpc_clnt
+ * @clnt: rpc_clnt to pin
+ *
+ * Pairs with rpc_release_client().
+ */
+void rpc_hold_client(struct rpc_clnt *clnt)
+{
+	refcount_inc(&clnt->cl_count);
+}
+
+/**
+ * rpc_release_client - release a reference on an rpc_clnt
+ * @clnt: rpc_clnt to release
+ *
+ * Pairs with rpc_hold_client(). The rpc_clnt's resources are
+ * freed once its reference count drops to zero.
  */
 void
 rpc_release_client(struct rpc_clnt *clnt)
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 576fa42e7abf..ae9ec4bf34f7 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1598,6 +1598,12 @@ static void svc_release_rqst(struct svc_rqst *rqstp)
 
 	if (procp && procp->pc_release)
 		procp->pc_release(rqstp);
+
+	/*
+	 * A subsequent svc_release_rqst() on this rqstp must not
+	 * re-invoke pc_release against released state.
+	 */
+	rqstp->rq_procinfo = NULL;
 }
 
 /**
@@ -1616,6 +1622,9 @@ void svc_process(struct svc_rqst *rqstp)
 		svc_xprt_deferred_close(rqstp->rq_xprt);
 #endif
 
+	/* Discard a stale release hook from a previous RPC. */
+	rqstp->rq_procinfo = NULL;
+
 	/*
 	 * Setup response xdr_buf.
 	 * Initially it has just one page
@@ -1672,6 +1681,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 	int proc_error;
 
 	/* Build the svc_rqst used by the common processing routine */
+	rqstp->rq_procinfo = NULL;
 	rqstp->rq_xid = req->rq_xid;
 	rqstp->rq_prot = req->rq_xprt->prot;
 	rqstp->rq_bc_net = req->rq_xprt->xprt_net;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 7be3de1a1aed..eb747493db82 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -471,6 +471,7 @@ static void svc_tcp_handshake_done(void *data, int status, key_serial_t peerid)
 	}
 	clear_bit(XPT_HANDSHAKE, &xprt->xpt_flags);
 	complete_all(&svsk->sk_handshake_done);
+	svc_xprt_put(xprt);
 }
 
 /**
@@ -494,9 +495,13 @@ static void svc_tcp_handshake(struct svc_xprt *xprt)
 	clear_bit(XPT_TLS_SESSION, &xprt->xpt_flags);
 	init_completion(&svsk->sk_handshake_done);
 
+	/* Pin the transport across the asynchronous handshake callback. */
+	svc_xprt_get(xprt);
+
 	ret = tls_server_hello_x509(&args, GFP_KERNEL);
 	if (ret) {
 		trace_svc_tls_not_started(xprt);
+		svc_xprt_put(xprt);
 		goto out_failed;
 	}
 
@@ -505,8 +510,13 @@ static void svc_tcp_handshake(struct svc_xprt *xprt)
 	if (ret <= 0) {
 		if (tls_handshake_cancel(sk)) {
 			trace_svc_tls_timed_out(xprt);
+			svc_xprt_put(xprt);
 			goto out_close;
 		}
+		/* Cancellation lost to handshake_complete(): the
+		 * callback is in flight and should finish quickly.
+		 */
+		wait_for_completion(&svsk->sk_handshake_done);
 	}
 
 	if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) {
diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c
index a90480f80154..e638b92b7ad1 100644
--- a/net/sunrpc/sysfs.c
+++ b/net/sunrpc/sysfs.c
@@ -327,7 +327,7 @@ static ssize_t rpc_sysfs_xprt_switch_add_xprt_store(struct kobject *kobj,
 {
 	struct rpc_xprt_switch *xprt_switch =
 		rpc_sysfs_xprt_switch_kobj_get_xprt(kobj);
-	struct xprt_create xprt_create_args;
+	struct xprt_create xprt_create_args = {};
 	struct rpc_xprt *xprt, *new;
 
 	if (!xprt_switch)
@@ -348,7 +348,7 @@ static ssize_t rpc_sysfs_xprt_switch_add_xprt_store(struct kobject *kobj,
 	xprt_create_args.reconnect_timeout = xprt->max_reconnect_timeout;
 
 	new = xprt_create_transport(&xprt_create_args);
-	if (IS_ERR_OR_NULL(new)) {
+	if (IS_ERR(new)) {
 		count = PTR_ERR(new);
 		goto out_put_xprt;
 	}
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index e83d5d0be78b..4c41e83b7ca9 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -152,6 +152,8 @@ unsigned int xdr_buf_to_bvec(struct bio_vec *bvec, unsigned int bvec_size,
 	unsigned int count = 0;
 
 	if (head->iov_len) {
+		if (unlikely(count >= bvec_size))
+			goto bvec_overflow;
 		bvec_set_virt(bvec++, head->iov_base, head->iov_len);
 		++count;
 	}
@@ -165,25 +167,27 @@ unsigned int xdr_buf_to_bvec(struct bio_vec *bvec, unsigned int bvec_size,
 		while (remaining > 0) {
 			len = min_t(unsigned int, remaining,
 				    PAGE_SIZE - offset);
+			if (unlikely(count >= bvec_size))
+				goto bvec_overflow;
 			bvec_set_page(bvec++, *pages++, len, offset);
 			remaining -= len;
 			offset = 0;
-			if (unlikely(++count > bvec_size))
-				goto bvec_overflow;
+			++count;
 		}
 	}
 
 	if (tail->iov_len) {
-		bvec_set_virt(bvec, tail->iov_base, tail->iov_len);
-		if (unlikely(++count > bvec_size))
+		if (unlikely(count >= bvec_size))
 			goto bvec_overflow;
+		bvec_set_virt(bvec, tail->iov_base, tail->iov_len);
+		++count;
 	}
 
 	return count;
 
 bvec_overflow:
 	pr_warn_once("%s: bio_vec array overflow\n", __func__);
-	return count - 1;
+	return count;
 }
 EXPORT_SYMBOL_GPL(xdr_buf_to_bvec);
 
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 2f0f9618dd05..e5b3463da25f 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -159,9 +159,7 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst)
 	rpcrdma_rep_put(&r_xprt->rx_buf, rep);
 	req->rl_reply = NULL;
 
-	spin_lock(&xprt->bc_pa_lock);
-	list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list);
-	spin_unlock(&xprt->bc_pa_lock);
+	rpcrdma_req_put(req);
 	xprt_put(xprt);
 }
 
@@ -203,6 +201,7 @@ create_req:
 	rqst->rq_xprt = xprt;
 	__set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state);
 	xdr_buf_init(&rqst->rq_snd_buf, rdmab_data(req->rl_sendbuf), size);
+	kref_init(&req->rl_kref);
 	return rqst;
 }
 
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 7f79a0a2601e..e5c71cf705a3 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -474,7 +474,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 		++num_wrs;
 	}
 
-	if ((kref_read(&req->rl_kref) > 1) || num_wrs > ep->re_send_count) {
+	if (req->rl_sendctx->sc_unmap_count || num_wrs > ep->re_send_count) {
 		send_wr->send_flags |= IB_SEND_SIGNALED;
 		ep->re_send_count = min_t(unsigned int, ep->re_send_batch,
 					  num_wrs - ep->re_send_count);
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 0e0f21974710..e8b5fc86a01b 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -467,29 +467,11 @@ static int rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 	return 0;
 }
 
-static void rpcrdma_sendctx_done(struct kref *kref)
-{
-	struct rpcrdma_req *req =
-		container_of(kref, struct rpcrdma_req, rl_kref);
-	struct rpcrdma_rep *rep = req->rl_reply;
-
-	rpcrdma_complete_rqst(rep);
-	rep->rr_rxprt->rx_stats.reply_waits_for_send++;
-}
-
-/**
- * rpcrdma_sendctx_unmap - DMA-unmap Send buffer
- * @sc: sendctx containing SGEs to unmap
- *
- */
-void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc)
+static void rpcrdma_sendctx_dma_unmap(struct rpcrdma_sendctx *sc)
 {
 	struct rpcrdma_regbuf *rb = sc->sc_req->rl_sendbuf;
 	struct ib_sge *sge;
 
-	if (!sc->sc_unmap_count)
-		return;
-
 	/* The first two SGEs contain the transport header and
 	 * the inline buffer. These are always left mapped so
 	 * they can be cheaply re-used.
@@ -498,8 +480,29 @@ void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc)
 	     ++sge, --sc->sc_unmap_count)
 		ib_dma_unmap_page(rdmab_device(rb), sge->addr, sge->length,
 				  DMA_TO_DEVICE);
+}
 
-	kref_put(&sc->sc_req->rl_kref, rpcrdma_sendctx_done);
+/**
+ * rpcrdma_sendctx_unmap - DMA-unmap Send buffer and release Send owner
+ * @sc: sendctx containing SGEs to unmap
+ *
+ */
+void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc)
+{
+	struct rpcrdma_req *req = sc->sc_req;
+
+	rpcrdma_sendctx_dma_unmap(sc);
+	sc->sc_req = NULL;
+	rpcrdma_req_put(req);
+}
+
+/* No Send was posted. Release DMA mappings prepared for this
+ * sendctx, but leave the request reference count alone.
+ */
+static void rpcrdma_sendctx_cancel(struct rpcrdma_sendctx *sc)
+{
+	rpcrdma_sendctx_dma_unmap(sc);
+	sc->sc_req = NULL;
 }
 
 /* Prepare an SGE for the RPC-over-RDMA transport header.
@@ -691,8 +694,6 @@ static bool rpcrdma_prepare_noch_mapped(struct rpcrdma_xprt *r_xprt,
 					      tail->iov_len))
 			return false;
 
-	if (req->rl_sendctx->sc_unmap_count)
-		kref_get(&req->rl_kref);
 	return true;
 }
 
@@ -722,7 +723,6 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt,
 		len -= len & 3;
 		if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len))
 			return false;
-		kref_get(&req->rl_kref);
 	}
 
 	return true;
@@ -743,6 +743,7 @@ inline int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt,
 				     struct xdr_buf *xdr,
 				     enum rpcrdma_chunktype rtype)
 {
+	struct rpcrdma_sendctx *sc;
 	int ret;
 
 	ret = -EAGAIN;
@@ -751,7 +752,6 @@ inline int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt,
 		goto out_nosc;
 	req->rl_sendctx->sc_unmap_count = 0;
 	req->rl_sendctx->sc_req = req;
-	kref_init(&req->rl_kref);
 	req->rl_wr.wr_cqe = &req->rl_sendctx->sc_cqe;
 	req->rl_wr.sg_list = req->rl_sendctx->sc_sges;
 	req->rl_wr.num_sge = 0;
@@ -779,10 +779,16 @@ inline int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt,
 		goto out_unmap;
 	}
 
+	/* The Send-side owner releases this reference when the
+	 * Send has completed.
+	 */
+	kref_get(&req->rl_kref);
 	return 0;
 
 out_unmap:
-	rpcrdma_sendctx_unmap(req->rl_sendctx);
+	sc = req->rl_sendctx;
+	rpcrdma_sendctx_cancel(sc);
+	rpcrdma_sendctx_unget_locked(r_xprt, sc);
 out_nosc:
 	trace_xprtrdma_prepsend_failed(&req->rl_slot, ret);
 	return ret;
@@ -1081,6 +1087,8 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 
 	/* Peek at stream contents without advancing. */
 	p = xdr_inline_decode(xdr, 0);
+	if ((char *)xdr->end - (char *)p < 5 * XDR_UNIT)
+		return false;
 
 	/* Chunk lists */
 	if (xdr_item_is_present(p++))
@@ -1105,7 +1113,7 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 	 */
 	p = xdr_inline_decode(xdr, 3 * sizeof(*p));
 	if (unlikely(!p))
-		return true;
+		return false;
 
 	rpcrdma_bc_receive_call(r_xprt, rep);
 	return true;
@@ -1329,6 +1337,11 @@ void rpcrdma_complete_rqst(struct rpcrdma_rep *rep)
 	struct rpc_rqst *rqst = rep->rr_rqst;
 	int status;
 
+	/* I3: every registered MR has been invalidated and
+	 * ib_dma_unmap_sg()'d before complete_rqst runs.
+	 */
+	WARN_ON_ONCE(!list_empty(&rpcr_to_rdmar(rqst)->rl_registered));
+
 	switch (rep->rr_proc) {
 	case rdma_msg:
 		status = rpcrdma_decode_msg(r_xprt, rep, rqst);
@@ -1360,13 +1373,69 @@ out_badheader:
 	goto out;
 }
 
-static void rpcrdma_reply_done(struct kref *kref)
-{
-	struct rpcrdma_req *req =
-		container_of(kref, struct rpcrdma_req, rl_kref);
-
-	rpcrdma_complete_rqst(req->rl_reply);
-}
+/* Reply-side ownership invariants
+ *
+ * I1 (Receive WR ownership).  A struct rpcrdma_rep is owned by the
+ *    HCA between ib_post_recv() and the matching Receive completion.
+ *    After ib_dma_sync_single_for_cpu() in rpcrdma_wc_receive() it is
+ *    owned by the CPU until rpcrdma_rep_put() returns it to
+ *    rb_free_reps; a rep on rb_free_reps is not re-posted until
+ *    rpcrdma_post_recvs() pulls it off.  Asserted: rpcrdma_post_recvs()
+ *    WARNs that a pulled rep has rr_rqst == NULL.
+ *
+ * I2 (rep attachment).  While req->rl_reply == rep, the rep cannot be
+ *    re-posted.  rpcrdma_reply_put() NULLs req->rl_reply before handing
+ *    the rep to rpcrdma_rep_put().  Asserted: rpcrdma_reply_put() WARNs
+ *    that rl_reply is NULL after the put.
+ *
+ * I3 (Registered-MR fence).  On entry to rpcrdma_complete_rqst() every
+ *    MR that was on req->rl_registered has had its rkey invalidated
+ *    (remotely via IB_WC_WITH_INVALIDATE or locally via IB_WR_LOCAL_INV)
+ *    and its pages ib_dma_unmap_sg()'d.  The LocalInv chain is posted
+ *    on a single QP; strong send-queue ordering makes the last
+ *    completion (frwr_wc_localinv_done) observe the
+ *    ib_dma_unmap_sg() that ran from each earlier completion's
+ *    frwr_mr_put() before complete_rqst is called.  The inline
+ *    frwr_reminv() path unmaps its one MR synchronously before
+ *    rpcrdma_reply_handler() reaches complete_rqst.  Asserted:
+ *    rpcrdma_complete_rqst() WARNs that rl_registered is empty.
+ *
+ * I4 (Send-buffer release).  req->rl_kref carries two unconditional
+ *    owners while a Send is outstanding: the RPC-layer reference (set
+ *    at xprt_rdma_alloc_slot / xprt_rdma_bc_rqst_get / rpcrdma_req_release
+ *    pool-entry) and the Send-side reference (kref_get() in
+ *    rpcrdma_prepare_send_sges()).  rpcrdma_req_release() runs only
+ *    after both have dropped, so the req does not return to its free
+ *    pool until rpcrdma_sendctx_unmap() has fired -- the HCA has
+ *    released the send buffer before the req can be reused.  Asserted:
+ *    rpcrdma_req_release() WARNs that rl_sendctx is NULL.
+ *
+ * I5 (req lifecycle).  A req is owned by the RPC layer between slot
+ *    acquisition and the matching xprt_rdma_free_slot() (or, for the
+ *    backchannel, xprt_rdma_bc_free_rqst()).  While owned, rl_kref >= 1.
+ *    The pools (rb_send_bufs, bc_pa_list, backlog wake target) never
+ *    contain a req with outstanding Send-side or Reply-side work.
+ *
+ * Non-hazards.  The following claims have been raised by adversarial
+ * review and are each closed by the invariants above:
+ *
+ *   * "Reply completes the RPC while the HCA still holds the send
+ *     buffer" -- excluded by I4.  The Send-side kref reference is held
+ *     until rpcrdma_sendctx_unmap() runs from Send completion.
+ *
+ *   * "Signal-driven release races the in-flight Send" -- same
+ *     resolution.  xprt_rdma_free() does not touch rl_kref; the
+ *     Send-side reference keeps the req out of its pool until Send
+ *     completion fires.
+ *
+ *   * "Receive completion races rep reuse" -- excluded by I1.  A rep
+ *     is on rb_free_reps only after rpcrdma_rep_put() has been called
+ *     and rpcrdma_post_recvs() owns the next transition back to the HCA.
+ *
+ *   * "Pages still DMA-mapped when call_decode reads them" -- excluded
+ *     by I3.  The matching ib_dma_unmap_sg() for every MR has run on
+ *     the same CPU thread that calls rpcrdma_complete_rqst().
+ */
 
 /**
  * rpcrdma_reply_handler - Process received RPC/RDMA messages
@@ -1402,6 +1471,14 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	credits = be32_to_cpu(*p++);
 	rep->rr_proc = *p++;
 
+	/* The credit grant from the wire is not trustworthy;
+	 * sanitize it before any code path consumes it.
+	 */
+	if (credits == 0)
+		credits = 1;	/* don't deadlock */
+	else if (credits > r_xprt->rx_ep->re_max_requests)
+		credits = r_xprt->rx_ep->re_max_requests;
+
 	if (rep->rr_vers != rpcrdma_version)
 		goto out_badversion;
 
@@ -1418,10 +1495,6 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	xprt_pin_rqst(rqst);
 	spin_unlock(&xprt->queue_lock);
 
-	if (credits == 0)
-		credits = 1;	/* don't deadlock */
-	else if (credits > r_xprt->rx_ep->re_max_requests)
-		credits = r_xprt->rx_ep->re_max_requests;
 	if (buf->rb_credits != credits)
 		rpcrdma_update_cwnd(r_xprt, credits);
 
@@ -1439,7 +1512,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		frwr_unmap_async(r_xprt, req);
 		/* LocalInv completion will complete the RPC */
 	else
-		kref_put(&req->rl_kref, rpcrdma_reply_done);
+		rpcrdma_complete_rqst(rep);
 
 out_post:
 	rpcrdma_post_recvs(r_xprt,
@@ -1454,11 +1527,13 @@ out_norqst:
 
 out_badversion:
 	trace_xprtrdma_reply_vers_err(rep);
-	goto out;
+	rpcrdma_rep_put(buf, rep);
+	credits = buf->rb_credits;
+	goto out_post;
 
 out_shortreply:
 	trace_xprtrdma_reply_short_err(rep);
-
-out:
 	rpcrdma_rep_put(buf, rep);
+	credits = buf->rb_credits;
+	goto out_post;
 }
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 61706df5e485..5ff8e5126a6c 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -279,6 +279,13 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 	cancel_delayed_work_sync(&r_xprt->rx_connect_worker);
 
 	rpcrdma_xprt_disconnect(r_xprt);
+
+	/* The disconnect's sendctx drain can return bc_prealloc reqs
+	 * to bc_pa_list after xprt_destroy_backchannel() emptied it.
+	 */
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
+	xprt_rdma_bc_destroy(xprt, 0);
+#endif
 	rpcrdma_buffer_destroy(&r_xprt->rx_buf);
 
 	xprt_rdma_free_addresses(xprt);
@@ -487,6 +494,50 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 	queue_delayed_work(system_long_wq, &r_xprt->rx_connect_worker, delay);
 }
 
+/* rl_kref has two owners while a Send is outstanding: the rpc_rqst
+ * owner and the sendctx. Replies complete the RPC but do not drop
+ * either reference. The req returns to its free pool only after
+ * xprt_rdma_free_slot() or xprt_rdma_bc_free_rqst() has dropped the
+ * RPC-layer reference and rpcrdma_sendctx_unmap() has dropped the
+ * Send-side reference.
+ */
+static void rpcrdma_req_release(struct kref *kref)
+{
+	struct rpcrdma_req *req =
+		container_of(kref, struct rpcrdma_req, rl_kref);
+	struct rpc_rqst *rqst = &req->rl_slot;
+	struct rpc_xprt *xprt = rqst->rq_xprt;
+	struct rpcrdma_xprt *r_xprt;
+
+	/* I4: both the RPC-layer and Send-side owners have dropped,
+	 * so rpcrdma_sendctx_unmap() has cleared rl_sendctx.
+	 */
+	WARN_ON_ONCE(req->rl_sendctx);
+
+	kref_init(&req->rl_kref);
+
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
+	if (bc_prealloc(rqst)) {
+		spin_lock(&xprt->bc_pa_lock);
+		list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list);
+		spin_unlock(&xprt->bc_pa_lock);
+		return;
+	}
+#endif
+
+	if (xprt_wake_up_backlog(xprt, rqst))
+		return;
+
+	r_xprt = rpcx_to_rdmax(xprt);
+	memset(rqst, 0, sizeof(*rqst));
+	rpcrdma_buffer_put(&r_xprt->rx_buf, req);
+}
+
+void rpcrdma_req_put(struct rpcrdma_req *req)
+{
+	kref_put(&req->rl_kref, rpcrdma_req_release);
+}
+
 /**
  * xprt_rdma_alloc_slot - allocate an rpc_rqst
  * @xprt: controlling RPC transport
@@ -505,6 +556,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
 	req = rpcrdma_buffer_get(&r_xprt->rx_buf);
 	if (!req)
 		goto out_sleep;
+	kref_init(&req->rl_kref);
 	task->tk_rqstp = &req->rl_slot;
 	task->tk_status = 0;
 	return;
@@ -520,6 +572,7 @@ out_sleep:
 	if (req) {
 		struct rpc_rqst *rqst = &req->rl_slot;
 
+		kref_init(&req->rl_kref);
 		if (!xprt_wake_up_backlog(xprt, rqst)) {
 			memset(rqst, 0, sizeof(*rqst));
 			rpcrdma_buffer_put(&r_xprt->rx_buf, req);
@@ -540,10 +593,7 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst)
 		container_of(xprt, struct rpcrdma_xprt, rx_xprt);
 
 	rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
-	if (!xprt_wake_up_backlog(xprt, rqst)) {
-		memset(rqst, 0, sizeof(*rqst));
-		rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
-	}
+	rpcrdma_req_put(rpcr_to_rdmar(rqst));
 }
 
 static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt,
@@ -607,10 +657,10 @@ xprt_rdma_free(struct rpc_task *task)
 		frwr_unmap_sync(rpcx_to_rdmax(rqst->rq_xprt), req);
 	}
 
-	/* XXX: If the RPC is completing because of a signal and
-	 * not because a reply was received, we ought to ensure
-	 * that the Send completion has fired, so that memory
-	 * involved with the Send is not still visible to the NIC.
+	/* The Send-side rl_kref owner keeps req out of its free pool
+	 * until rpcrdma_sendctx_unmap() has fired -- see I4 above
+	 * rpcrdma_reply_handler() -- so signal-driven release here
+	 * does not let the HCA touch a recycled send buffer.
 	 */
 }
 
@@ -716,7 +766,7 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		   r_xprt->rx_stats.mrs_allocated,
 		   r_xprt->rx_stats.local_inv_needed,
 		   r_xprt->rx_stats.empty_sendctx_q,
-		   r_xprt->rx_stats.reply_waits_for_send);
+		   0LU); /* was reply_waits_for_send; column preserved */
 }
 
 static int
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index aecf9c0a153f..0ac82f26bf6e 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -65,6 +65,8 @@
 
 static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt);
 static void rpcrdma_sendctxs_destroy(struct rpcrdma_xprt *r_xprt);
+static unsigned long rpcrdma_sendctx_next(struct rpcrdma_buffer *buf,
+					  unsigned long item);
 static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt,
 				       struct rpcrdma_sendctx *sc);
 static int rpcrdma_reqs_setup(struct rpcrdma_xprt *r_xprt);
@@ -79,6 +81,8 @@ rpcrdma_regbuf_alloc_node(size_t size, enum dma_data_direction direction,
 			  int node);
 static struct rpcrdma_regbuf *
 rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction);
+static bool rpcrdma_regbuf_realloc_node(struct rpcrdma_regbuf *rb,
+					size_t size, gfp_t flags, int node);
 static void rpcrdma_regbuf_dma_unmap(struct rpcrdma_regbuf *rb);
 static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb);
 
@@ -243,8 +247,17 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 		complete(&ep->re_done);
 		return 0;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
-		ep->re_connect_status = -ENODEV;
-		goto disconnected;
+		switch (xchg(&ep->re_connect_status, -ENODEV)) {
+		case 0:
+			goto wake_connect_worker;
+		case 1:
+			/* The later DISCONNECTED event balances the
+			 * ESTABLISHED get; do not put here.
+			 */
+			rpcrdma_force_disconnect(ep);
+			return 0;
+		}
+		return 0;
 	case RDMA_CM_EVENT_ESTABLISHED:
 		rpcrdma_ep_get(ep);
 		ep->re_connect_status = 1;
@@ -267,7 +280,6 @@ wake_connect_worker:
 		return 0;
 	case RDMA_CM_EVENT_DISCONNECTED:
 		ep->re_connect_status = -ECONNABORTED;
-disconnected:
 		rpcrdma_force_disconnect(ep);
 		return rpcrdma_ep_put(ep);
 	default:
@@ -324,6 +336,7 @@ static struct rdma_cm_id *rpcrdma_create_id(struct rpcrdma_xprt *r_xprt,
 	if (rc)
 		goto out;
 
+	ep->re_id = id;
 	rc = rpcrdma_rn_register(id->device, &ep->re_rn, rpcrdma_ep_removal_done);
 	if (rc)
 		goto out;
@@ -396,7 +409,6 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 	}
 	__module_get(THIS_MODULE);
 	device = id->device;
-	ep->re_id = id;
 	reinit_completion(&ep->re_done);
 
 	ep->re_max_requests = r_xprt->rx_xprt.max_reqs;
@@ -539,7 +551,17 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt)
 		goto out;
 	}
 	rpcrdma_mrs_create(r_xprt);
-	frwr_wp_create(r_xprt);
+
+	/*
+	 * rpcrdma_encode_write_list() dereferences the write-pad
+	 * MR with no NULL check, so fail the connect rather than
+	 * publish a transport whose write-pad MR is NULL.
+	 */
+	rc = frwr_wp_create(r_xprt);
+	if (rc) {
+		rc = -ENOTCONN;
+		goto out;
+	}
 
 out:
 	trace_xprtrdma_connect(r_xprt, rc);
@@ -571,9 +593,9 @@ void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt)
 
 	rpcrdma_xprt_drain(r_xprt);
 	rpcrdma_reps_unmap(r_xprt);
+	rpcrdma_sendctxs_destroy(r_xprt);
 	rpcrdma_reqs_reset(r_xprt);
 	rpcrdma_mrs_destroy(r_xprt);
-	rpcrdma_sendctxs_destroy(r_xprt);
 
 	if (rpcrdma_ep_put(ep))
 		rdma_destroy_id(id);
@@ -605,6 +627,25 @@ static void rpcrdma_sendctxs_destroy(struct rpcrdma_xprt *r_xprt)
 
 	if (!buf->rb_sc_ctxs)
 		return;
+
+	/* The QP is drained, but the final unsignaled Sends might not
+	 * have been walked by a signaled Send completion. Release those
+	 * Send owners before request buffers are reset.
+	 *
+	 * Unlike the completion sweep, this walk can visit slots with
+	 * no Send posted: after a partial rpcrdma_sendctxs_create()
+	 * failure on reconnect, rb_sc_head and rb_sc_tail are stale,
+	 * and slots between them can be NULL or have sc_req clear.
+	 */
+	for (i = rpcrdma_sendctx_next(buf, buf->rb_sc_tail);
+	     i != rpcrdma_sendctx_next(buf, buf->rb_sc_head);
+	     i = rpcrdma_sendctx_next(buf, i)) {
+		struct rpcrdma_sendctx *sc = buf->rb_sc_ctxs[i];
+
+		if (sc && sc->sc_req)
+			rpcrdma_sendctx_unmap(sc);
+	}
+
 	for (i = 0; i <= buf->rb_sc_last; i++)
 		kfree(buf->rb_sc_ctxs[i]);
 	kfree(buf->rb_sc_ctxs);
@@ -667,6 +708,12 @@ static unsigned long rpcrdma_sendctx_next(struct rpcrdma_buffer *buf,
 	return likely(item < buf->rb_sc_last) ? item + 1 : 0;
 }
 
+static unsigned long rpcrdma_sendctx_prev(struct rpcrdma_buffer *buf,
+					  unsigned long item)
+{
+	return item > 0 ? item - 1 : buf->rb_sc_last;
+}
+
 /**
  * rpcrdma_sendctx_get_locked - Acquire a send context
  * @r_xprt: controlling transport instance
@@ -724,6 +771,29 @@ out_emptyq:
 }
 
 /**
+ * rpcrdma_sendctx_unget_locked - Release an unposted send context
+ * @r_xprt: controlling transport instance
+ * @sc: send context to release
+ *
+ * Usage: Called when no Send is posted for the sendctx most
+ * recently returned by rpcrdma_sendctx_get_locked().
+ *
+ * The caller serializes calls to this function and to
+ * rpcrdma_sendctx_get_locked() (per transport).
+ */
+void rpcrdma_sendctx_unget_locked(struct rpcrdma_xprt *r_xprt,
+				  struct rpcrdma_sendctx *sc)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+
+	if (WARN_ON_ONCE(buf->rb_sc_ctxs[buf->rb_sc_head] != sc))
+		return;
+
+	buf->rb_sc_head = rpcrdma_sendctx_prev(buf, buf->rb_sc_head);
+	xprt_write_space(&r_xprt->rx_xprt);
+}
+
+/**
  * rpcrdma_sendctx_put_locked - Release a send context
  * @r_xprt: controlling transport instance
  * @sc: send context to release
@@ -739,15 +809,18 @@ static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt,
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	unsigned long next_tail;
 
-	/* Unmap SGEs of previously completed but unsignaled
-	 * Sends by walking up the queue until @sc is found.
+	/* Release previously completed but unsignaled Sends by walking
+	 * up the queue until @sc is found.
 	 */
 	next_tail = buf->rb_sc_tail;
 	do {
+		struct rpcrdma_sendctx *cur;
+
 		next_tail = rpcrdma_sendctx_next(buf, next_tail);
 
 		/* ORDER: item must be accessed _before_ tail is updated */
-		rpcrdma_sendctx_unmap(buf->rb_sc_ctxs[next_tail]);
+		cur = buf->rb_sc_ctxs[next_tail];
+		rpcrdma_sendctx_unmap(cur);
 
 	} while (buf->rb_sc_ctxs[next_tail] != sc);
 
@@ -1211,6 +1284,10 @@ void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req)
 		rpcrdma_rep_put(buffers, req->rl_reply);
 		req->rl_reply = NULL;
 	}
+	/* I2: rl_reply NULL after the put closes the
+	 * 'rep on rb_free_reps still referenced by req' window.
+	 */
+	WARN_ON_ONCE(req->rl_reply);
 }
 
 /**
@@ -1292,9 +1369,15 @@ rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction)
  */
 bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size, gfp_t flags)
 {
+	return rpcrdma_regbuf_realloc_node(rb, size, flags, NUMA_NO_NODE);
+}
+
+static bool rpcrdma_regbuf_realloc_node(struct rpcrdma_regbuf *rb,
+					size_t size, gfp_t flags, int node)
+{
 	void *buf;
 
-	buf = kmalloc(size, flags);
+	buf = kmalloc_node(size, flags, node);
 	if (!buf)
 		return false;
 
@@ -1306,6 +1389,23 @@ bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size, gfp_t flags)
 	return true;
 }
 
+static bool rpcrdma_rep_resize(struct rpcrdma_xprt *r_xprt,
+			       struct rpcrdma_rep *rep)
+{
+	struct rpcrdma_regbuf *rb = rep->rr_rdmabuf;
+	struct rpcrdma_ep *ep = r_xprt->rx_ep;
+	size_t size = ep->re_inline_recv;
+
+	if (likely(rdmab_length(rb) >= size))
+		return true;
+	if (!rpcrdma_regbuf_realloc_node(rb, size, XPRTRDMA_GFP_FLAGS,
+					 ibdev_to_node(ep->re_id->device)))
+		return false;
+
+	xdr_buf_init(&rep->rr_hdrbuf, rdmab_data(rb), rdmab_length(rb));
+	return true;
+}
+
 /**
  * __rpcrdma_regbuf_dma_map - DMA-map a regbuf
  * @r_xprt: controlling transport instance
@@ -1387,6 +1487,12 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
 			rep = rpcrdma_rep_create(r_xprt);
 		if (!rep)
 			break;
+		/* I1: a rep on rb_free_reps must carry no rqst pointer. */
+		WARN_ON_ONCE(rep->rr_rqst);
+		if (!rpcrdma_rep_resize(r_xprt, rep)) {
+			rpcrdma_rep_put(buf, rep);
+			break;
+		}
 		if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) {
 			rpcrdma_rep_put(buf, rep);
 			break;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index f53a77472724..57be5776aaff 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -427,7 +427,6 @@ struct rpcrdma_stats {
 	/* accessed when receiving a reply */
 	unsigned long long	total_rdma_reply;
 	unsigned long long	fixup_copy_count;
-	unsigned long		reply_waits_for_send;
 	unsigned long		local_inv_needed;
 	unsigned long		nomsg_call_count;
 	unsigned long		bcall_count;
@@ -496,6 +495,8 @@ void rpcrdma_req_destroy(struct rpcrdma_req *req);
 int rpcrdma_buffer_create(struct rpcrdma_xprt *);
 void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
 struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_xprt *r_xprt);
+void rpcrdma_sendctx_unget_locked(struct rpcrdma_xprt *r_xprt,
+				  struct rpcrdma_sendctx *sc);
 
 struct rpcrdma_mr *rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt);
 void rpcrdma_mrs_refresh(struct rpcrdma_xprt *r_xprt);
@@ -505,6 +506,7 @@ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers,
 			struct rpcrdma_req *req);
 void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep);
 void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req);
+void rpcrdma_req_put(struct rpcrdma_req *req);
 
 bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size,
 			    gfp_t flags);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 2e1fe6013361..359407aae03e 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2734,8 +2734,11 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work)
 	lower_xprt = rcu_dereference(lower_clnt->cl_xprt);
 	rcu_read_unlock();
 
-	if (wait_on_bit_lock(&lower_xprt->state, XPRT_LOCKED, TASK_KILLABLE))
+	if (wait_on_bit_lock(&lower_xprt->state, XPRT_LOCKED, TASK_KILLABLE)) {
+		/* XPRT_LOCKED was never acquired. */
+		rpc_shutdown_client(lower_clnt);
 		goto out_unlock;
+	}
 
 	status = xs_tls_handshake_sync(lower_xprt, &upper_xprt->xprtsec);
 	if (status) {
@@ -2758,6 +2761,7 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work)
 out_unlock:
 	current_restore_flags(pflags, PF_MEMALLOC);
 	upper_transport->clnt = NULL;
+	rpc_release_client(upper_clnt);
 	xprt_unlock_connect(upper_xprt, upper_transport);
 	return;
 
@@ -2805,7 +2809,15 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 	} else
 		dprintk("RPC:       xs_connect scheduled xprt %p\n", xprt);
 
-	transport->clnt = task->tk_client;
+	/*
+	 * Only the TLS connect_worker reads transport->clnt; pinning
+	 * the upper rpc_clnt unconditionally would form a cycle with
+	 * cl_xprt and prevent xprt destruction.
+	 */
+	if (xprt->xprtsec.policy != RPC_XPRTSEC_NONE) {
+		rpc_hold_client(task->tk_client);
+		transport->clnt = task->tk_client;
+	}
 	queue_delayed_work(xprtiod_workqueue,
 			&transport->connect_worker,
 			delay);
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index a3bd1ef17558..05dcd2f9e887 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -482,6 +482,7 @@ void tipc_disable_l2_media(struct tipc_bearer *b)
 	dev = (struct net_device *)rtnl_dereference(b->media_ptr);
 	dev_remove_pack(&b->pt);
 	RCU_INIT_POINTER(dev->tipc_ptr, NULL);
+	RCU_INIT_POINTER(b->media_ptr, NULL);
 	synchronize_net();
 	dev_put(dev);
 }
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 434e70eabe08..315975c3be81 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -45,6 +45,7 @@
 #include "crypto.h"
 
 #include <linux/module.h>
+#include <linux/wait_bit.h>
 
 /* configurable TIPC parameters */
 unsigned int tipc_net_id __read_mostly;
@@ -118,8 +119,7 @@ static void __net_exit tipc_exit_net(struct net *net)
 #ifdef CONFIG_TIPC_CRYPTO
 	tipc_crypto_stop(&tipc_net(net)->crypto_tx);
 #endif
-	while (atomic_read(&tn->wq_count))
-		cond_resched();
+	wait_var_event(&tn->wq_count, atomic_read(&tn->wq_count) == 0);
 }
 
 static void __net_exit tipc_pernet_pre_exit(struct net *net)
@@ -218,6 +218,11 @@ static void __exit tipc_exit(void)
 	unregister_pernet_device(&tipc_net_ops);
 	tipc_unregister_sysctl();
 
+	/* TODO: Wait for all timers that called call_rcu() to finish before
+	 * calling rcu_barrier().
+	 */
+	rcu_barrier();
+
 	pr_info("Deactivated\n");
 }
 
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 3e54d2df5683..b9d06595b067 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -58,6 +58,7 @@
  * @skb: request message to be (repeatedly) sent
  * @timer: timer governing period between requests
  * @timer_intv: current interval between requests (in ms)
+ * @rcu: RCU head for deferred freeing
  */
 struct tipc_discoverer {
 	u32 bearer_id;
@@ -69,6 +70,7 @@ struct tipc_discoverer {
 	struct sk_buff *skb;
 	struct timer_list timer;
 	unsigned long timer_intv;
+	struct rcu_head rcu;
 };
 
 /**
@@ -382,6 +384,15 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,
 	return 0;
 }
 
+static void tipc_disc_free_rcu(struct rcu_head *rp)
+{
+	struct tipc_discoverer *d = container_of(rp, struct tipc_discoverer,
+						 rcu);
+
+	kfree_skb(d->skb);
+	kfree(d);
+}
+
 /**
  * tipc_disc_delete - destroy object sending periodic link setup requests
  * @d: ptr to link dest structure
@@ -389,8 +400,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,
 void tipc_disc_delete(struct tipc_discoverer *d)
 {
 	timer_shutdown_sync(&d->timer);
-	kfree_skb(d->skb);
-	kfree(d);
+	call_rcu(&d->rcu, tipc_disc_free_rcu);
 }
 
 /**
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 190b49c5cbc3..ba4f4906e13b 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -280,12 +280,21 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
 				u32 node, u32 dtype)
 {
 	struct publication *p = NULL;
+	u32 lower = ntohl(i->lower);
+	u32 upper = ntohl(i->upper);
 	struct tipc_socket_addr sk;
-	struct tipc_uaddr ua;
 	u32 key = ntohl(i->key);
+	struct tipc_uaddr ua;
+
+	/* A peer-advertised binding with lower > upper can never be matched
+	 * or withdrawn and would leak the publication; the local bind path
+	 * rejects such ranges, so reject ranges learned from the network too.
+	 */
+	if (lower > upper)
+		return false;
 
 	tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE,
-		   ntohl(i->type), ntohl(i->lower), ntohl(i->upper));
+		   ntohl(i->type), lower, upper);
 	sk.ref = ntohl(i->port);
 	sk.node = node;
 
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 1a9a5bdaccf4..8336a9664703 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -152,11 +152,13 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_BEARER_DISABLE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_bearer_disable,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_ENABLE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_bearer_enable,
 	},
 	{
@@ -168,11 +170,13 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_BEARER_ADD,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_bearer_add,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_bearer_set,
 	},
 	{
@@ -197,11 +201,13 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_LINK_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_node_set_link,
 	},
 	{
 		.cmd	= TIPC_NL_LINK_RESET_STATS,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit   = tipc_nl_node_reset_link_stats,
 	},
 	{
@@ -213,6 +219,7 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_MEDIA_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_media_set,
 	},
 	{
@@ -228,6 +235,7 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_NET_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_net_set,
 	},
 	{
@@ -238,6 +246,7 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_MON_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_node_set_monitor,
 	},
 	{
@@ -255,6 +264,7 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_PEER_REMOVE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_peer_rm,
 	},
 #ifdef CONFIG_TIPC_MEDIA_UDP
@@ -269,11 +279,13 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_KEY_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_node_set_key,
 	},
 	{
 		.cmd	= TIPC_NL_KEY_FLUSH,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= tipc_nl_node_flush_key,
 	},
 #endif
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 9329919fb07f..490f30899b5a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1362,6 +1362,9 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
 			__skb_queue_tail(xmitq, skb);
 		return;
 	} else if (mtyp == CONN_ACK) {
+		if (tsk->snt_unacked < msg_conn_ack(hdr))
+			goto exit;
+
 		was_cong = tsk_conn_cong(tsk);
 		tipc_sk_push_backlog(tsk, msg_nagle_ack(hdr));
 		tsk->snt_unacked -= msg_conn_ack(hdr);
@@ -2452,17 +2455,17 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 			atomic_set(dcnt, 0);
 		lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
 		if (likely(!sk_add_backlog(sk, skb, lim))) {
-			trace_tipc_sk_overlimit1(sk, skb, TIPC_DUMP_ALL,
+			trace_tipc_sk_overlimit1(sk, skb, TIPC_DUMP_SK_BKLGQ,
 						 "bklg & rcvq >90% allocated!");
 			continue;
 		}
 
-		trace_tipc_sk_dump(sk, skb, TIPC_DUMP_ALL, "err_overload!");
+		trace_tipc_sk_dump(sk, skb, TIPC_DUMP_SK_BKLGQ, "err_overload!");
 		/* Overload => reject message back to sender */
 		onode = tipc_own_addr(sock_net(sk));
 		sk_drops_inc(sk);
 		if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD)) {
-			trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_ALL,
+			trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_SK_BKLGQ,
 					      "@sk_enqueue!");
 			__skb_queue_tail(xmitq, skb);
 		}
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 2c66b356025a..62ae7f5b5840 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -40,6 +40,7 @@
 #include <linux/igmp.h>
 #include <linux/kernel.h>
 #include <linux/workqueue.h>
+#include <linux/wait_bit.h>
 #include <linux/list.h>
 #include <net/sock.h>
 #include <net/ip.h>
@@ -89,14 +90,14 @@ struct udp_replicast {
 /**
  * struct udp_bearer - ip/udp bearer data structure
  * @bearer:	associated generic tipc bearer
- * @ubsock:	bearer associated socket
+ * @sk:		bearer associated socket
  * @ifindex:	local address scope
  * @work:	used to schedule deferred work on a bearer
  * @rcast:	associated udp_replicast container
  */
 struct udp_bearer {
 	struct tipc_bearer __rcu *bearer;
-	struct socket *ubsock;
+	struct sock *sk;
 	u32 ifindex;
 	struct work_struct work;
 	struct udp_replicast rcast;
@@ -194,7 +195,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 		}
 
 		ttl = ip4_dst_hoplimit(&rt->dst);
-		udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr,
+		udp_tunnel_xmit_skb(rt, ub->sk, skb, src->ipv4.s_addr,
 				    dst->ipv4.s_addr, 0, ttl, 0, src->port,
 				    dst->port, false, true, 0);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -206,7 +207,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 				.saddr = src->ipv6,
 				.flowi6_proto = IPPROTO_UDP
 			};
-			ndst = ip6_dst_lookup_flow(net, ub->ubsock->sk,
+			ndst = ip6_dst_lookup_flow(net, ub->sk,
 						   &fl6, NULL);
 			if (IS_ERR(ndst)) {
 				err = PTR_ERR(ndst);
@@ -215,7 +216,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 			dst_cache_set_ip6(cache, ndst, &fl6.saddr);
 		}
 		ttl = ip6_dst_hoplimit(ndst);
-		udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL,
+		udp_tunnel6_xmit_skb(ndst, ub->sk, skb, NULL,
 				     &src->ipv6, &dst->ipv6, 0, ttl, 0,
 				     src->port, dst->port, false, 0);
 #endif
@@ -405,9 +406,9 @@ out:
 
 static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote)
 {
-	int err = 0;
+	struct sock *sk = ub->sk;
 	struct ip_mreqn mreqn;
-	struct sock *sk = ub->ubsock->sk;
+	int err = 0;
 
 	if (ntohs(remote->proto) == ETH_P_IP) {
 		mreqn.imr_multiaddr = remote->ipv4;
@@ -670,6 +671,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 	struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
 	u8 node_id[NODE_ID_LEN] = {0,};
 	struct net_device *dev;
+	struct socket *sock;
 	int rmcast = 0;
 
 	ub = kzalloc_obj(*ub, GFP_ATOMIC);
@@ -764,14 +766,16 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 		goto err;
 	}
 	udp_conf.local_udp_port = local.port;
-	err = udp_sock_create(net, &udp_conf, &ub->ubsock);
+	err = udp_sock_create(net, &udp_conf, &sock);
 	if (err)
 		goto err;
+
+	ub->sk = sock->sk;
 	tuncfg.sk_user_data = ub;
 	tuncfg.encap_type = 1;
 	tuncfg.encap_rcv = tipc_udp_recv;
 	tuncfg.encap_destroy = NULL;
-	setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg);
+	setup_udp_tunnel_sock(net, ub->sk, &tuncfg);
 
 	err = dst_cache_init(&ub->rcast.dst_cache, GFP_ATOMIC);
 	if (err)
@@ -793,12 +797,21 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 
 free:
 	dst_cache_destroy(&ub->rcast.dst_cache);
-	udp_tunnel_sock_release(ub->ubsock);
+	udp_tunnel_sock_release(ub->sk);
+	synchronize_rcu();
 err:
 	kfree(ub);
 	return err;
 }
 
+static void rcast_free_rcu(struct rcu_head *rcu)
+{
+	struct udp_replicast *rcast = container_of(rcu, struct udp_replicast, rcu);
+
+	dst_cache_destroy(&rcast->dst_cache);
+	kfree(rcast);
+}
+
 /* cleanup_bearer - break the socket/bearer association */
 static void cleanup_bearer(struct work_struct *work)
 {
@@ -807,19 +820,19 @@ static void cleanup_bearer(struct work_struct *work)
 	struct tipc_net *tn;
 
 	list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) {
-		dst_cache_destroy(&rcast->dst_cache);
 		list_del_rcu(&rcast->list);
-		kfree_rcu(rcast, rcu);
+		call_rcu_hurry(&rcast->rcu, rcast_free_rcu);
 	}
 
-	tn = tipc_net(sock_net(ub->ubsock->sk));
+	tn = tipc_net(sock_net(ub->sk));
 
-	dst_cache_destroy(&ub->rcast.dst_cache);
-	udp_tunnel_sock_release(ub->ubsock);
+	udp_tunnel_sock_release(ub->sk);
 
-	/* Note: could use a call_rcu() to avoid another synchronize_net() */
 	synchronize_net();
-	atomic_dec(&tn->wq_count);
+
+	dst_cache_destroy(&ub->rcast.dst_cache);
+	if (atomic_dec_and_test(&tn->wq_count))
+		wake_up_var(&tn->wq_count);
 	kfree(ub);
 }
 
@@ -833,11 +846,11 @@ static void tipc_udp_disable(struct tipc_bearer *b)
 		pr_err("UDP bearer instance not found\n");
 		return;
 	}
-	sock_set_flag(ub->ubsock->sk, SOCK_DEAD);
+	sock_set_flag(ub->sk, SOCK_DEAD);
 	RCU_INIT_POINTER(ub->bearer, NULL);
 
 	/* sock_release need to be done outside of rtnl lock */
-	atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count);
+	atomic_inc(&tipc_net(sock_net(ub->sk))->wq_count);
 	INIT_WORK(&ub->work, cleanup_bearer);
 	schedule_work(&ub->work);
 }
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index a47f6a1e2c77..ba95f9d927a3 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2424,6 +2424,17 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
 			goto read_sock_requeue;
 		}
 
+		/* An empty data record (legal in TLS 1.3) gives a zero
+		 * read_actor return, indistinguishable from the consumer
+		 * stalling; the used <= 0 path would requeue it at the
+		 * head of rx_list and block all later records. Consume it
+		 * here instead.
+		 */
+		if (rxm->full_len == 0) {
+			consume_skb(skb);
+			continue;
+		}
+
 		used = read_actor(desc, skb, rxm->offset, rxm->full_len);
 		if (used <= 0) {
 			if (!copied)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 76c537a6e8b5..21e43e08b5d7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5112,7 +5112,7 @@ static int nl80211_validate_key_link_id(struct genl_info *info,
 	if (wdev->valid_links) {
 		if (link_id == -1) {
 			GENL_SET_ERR_MSG(info,
-					 "link ID must for MLO group key");
+					 "link ID must be set for MLO group key");
 			return -EINVAL;
 		}
 		if (!(wdev->valid_links & BIT(link_id))) {
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index d6cd0de64d1f..0ca93fd7d46f 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -195,7 +195,9 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev,
 		return -EOPNOTSUPP;
 	}
 
-	if (out->ftm.rsta && !out->ftm.lmr_feedback) {
+	if (out->ftm.rsta &&
+	    (out->ftm.non_trigger_based || out->ftm.trigger_based) &&
+	    !out->ftm.lmr_feedback) {
 		NL_SET_ERR_MSG_ATTR(info->extack,
 				    tb[NL80211_PMSR_FTM_REQ_ATTR_RSTA],
 				    "FTM: RSTA set without LMR feedback");
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 27a56ee2e8f0..d9f2a77e127c 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -326,8 +326,11 @@ cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
 		/* For ML probe response, match the MLE in the frame body with
 		 * MLD id being 'bssid_index'
 		 */
-		if (parent->id == WLAN_EID_EXTENSION && parent->datalen > 1 &&
+		if (parent->id == WLAN_EID_EXTENSION &&
 		    parent->data[0] == WLAN_EID_EXT_EHT_MULTI_LINK &&
+		    ieee80211_mle_type_ok(parent->data + 1,
+					  IEEE80211_ML_CONTROL_TYPE_BASIC,
+					  parent->datalen - 1) &&
 		    bssid_index == ieee80211_mle_get_mld_id(parent->data + 1)) {
 			if (!cfg80211_copy_elem_with_frags(parent,
 							   ie, ielen,
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index d9035546375e..374e1b964438 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -212,43 +212,23 @@ static int espintcp_sendskmsg_locked(struct sock *sk,
 	struct sk_msg *skmsg = &emsg->skmsg;
 	bool more = flags & MSG_MORE;
 	struct scatterlist *sg;
-	int done = 0;
 	int ret;
 
-	sg = &skmsg->sg.data[skmsg->sg.start];
 	do {
 		struct bio_vec bvec;
-		size_t size = sg->length - emsg->offset;
-		int offset = sg->offset + emsg->offset;
-		struct page *p;
-
-		emsg->offset = 0;
 
+		sg = &skmsg->sg.data[skmsg->sg.start];
 		if (sg_is_last(sg) && !more)
 			msghdr.msg_flags &= ~MSG_MORE;
 
-		p = sg_page(sg);
-retry:
-		bvec_set_page(&bvec, p, size, offset);
-		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
-		ret = tcp_sendmsg_locked(sk, &msghdr, size);
-		if (ret < 0) {
-			emsg->offset = offset - sg->offset;
-			skmsg->sg.start += done;
+		bvec_set_page(&bvec, sg_page(sg), sg->length, sg->offset);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, sg->length);
+		ret = tcp_sendmsg_locked(sk, &msghdr, sg->length);
+		if (ret < 0)
 			return ret;
-		}
-
-		if (ret != size) {
-			offset += ret;
-			size -= ret;
-			goto retry;
-		}
 
-		done++;
-		put_page(p);
-		sk_mem_uncharge(sk, sg->length);
-		sg = sg_next(sg);
-	} while (sg);
+		sk_msg_free_partial(sk, skmsg, ret);
+	} while (skmsg->sg.size);
 
 	memset(emsg, 0, sizeof(*emsg));
 
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index e4c2cd24936d..eecab337bd0a 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -467,6 +467,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 {
 	const struct xfrm_state_afinfo *afinfo;
 	struct net *net = dev_net(skb->dev);
+	struct net_device *dev = skb->dev;
 	int err;
 	__be32 seq;
 	__be32 seq_hi;
@@ -493,7 +494,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 					       LINUX_MIB_XFRMINSTATEINVALID);
 
 			if (encap_type == -1)
-				dev_put(skb->dev);
+				dev_put(dev);
 			goto drop;
 		}
 
@@ -655,16 +656,16 @@ process:
 
 		if (!crypto_done) {
 			spin_unlock(&x->lock);
-			dev_hold(skb->dev);
+			dev_hold(dev);
 
 			nexthdr = x->type->input(x, skb);
 			if (nexthdr == -EINPROGRESS) {
 				if (async)
-					dev_put(skb->dev);
+					dev_put(dev);
 				return 0;
 			}
 
-			dev_put(skb->dev);
+			dev_put(dev);
 			spin_lock(&x->lock);
 		}
 resume:
@@ -699,7 +700,7 @@ resume:
 		err = xfrm_inner_mode_input(x, skb);
 		if (err == -EINPROGRESS) {
 			if (async)
-				dev_put(skb->dev);
+				dev_put(dev);
 			return 0;
 		} else if (err) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
@@ -726,9 +727,12 @@ resume_decapped:
 		crypto_done = false;
 	} while (!err);
 
+	rcu_read_lock();
 	err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
-	if (err)
+	if (err) {
+		rcu_read_unlock();
 		goto drop;
+	}
 
 	nf_reset_ct(skb);
 
@@ -739,8 +743,9 @@ resume_decapped:
 		if (skb_valid_dst(skb))
 			skb_dst_drop(skb);
 		if (async)
-			dev_put(skb->dev);
+			dev_put(dev);
 		gro_cells_receive(&gro_cells, skb);
+		rcu_read_unlock();
 		return 0;
 	} else {
 		xo = xfrm_offload(skb);
@@ -748,23 +753,21 @@ resume_decapped:
 			xfrm_gro = xo->flags & XFRM_GRO;
 
 		err = -EAFNOSUPPORT;
-		rcu_read_lock();
 		afinfo = xfrm_state_afinfo_get_rcu(x->props.family);
 		if (likely(afinfo))
 			err = afinfo->transport_finish(skb, xfrm_gro || async);
-		rcu_read_unlock();
 		if (xfrm_gro) {
 			sp = skb_sec_path(skb);
 			if (sp)
 				sp->olen = 0;
 			if (skb_valid_dst(skb))
 				skb_dst_drop(skb);
-			if (async)
-				dev_put(skb->dev);
 			gro_cells_receive(&gro_cells, skb);
-			return err;
 		}
 
+		if (async)
+			dev_put(dev);
+		rcu_read_unlock();
 		return err;
 	}
 
@@ -772,7 +775,7 @@ drop_unlock:
 	spin_unlock(&x->lock);
 drop:
 	if (async)
-		dev_put(skb->dev);
+		dev_put(dev);
 	xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
 	kfree_skb(skb);
 	return 0;
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 330a05286a56..688306bf62c5 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -869,6 +869,9 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct net *net = xi->net;
 	struct xfrm_if_parms p = {};
 
+	if (!rtnl_dev_link_net_capable(dev, net))
+		return -EPERM;
+
 	xfrmi_netlink_parms(data, &p);
 	if (!p.if_id) {
 		NL_SET_ERR_MSG(extack, "if_id must be non zero");
diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c
index 458931062a04..eb1b6f67739e 100644
--- a/net/xfrm/xfrm_nat_keepalive.c
+++ b/net/xfrm/xfrm_nat_keepalive.c
@@ -55,8 +55,10 @@ static int nat_keepalive_send_ipv4(struct sk_buff *skb,
 			   ka->encap_sport, sock_net_uid(net, NULL));
 
 	rt = ip_route_output_key(net, &fl4);
-	if (IS_ERR(rt))
+	if (IS_ERR(rt)) {
+		kfree_skb(skb);
 		return PTR_ERR(rt);
+	}
 
 	skb_dst_set(skb, &rt->dst);
 
@@ -101,6 +103,7 @@ static int nat_keepalive_send_ipv6(struct sk_buff *skb,
 	dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL);
 	if (IS_ERR(dst)) {
 		local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
+		kfree_skb(skb);
 		return PTR_ERR(dst);
 	}
 
@@ -118,7 +121,6 @@ static void nat_keepalive_send(struct nat_keepalive *ka)
 					sizeof(struct ipv6hdr)) +
 				    sizeof(struct udphdr);
 	const u8 nat_ka_payload = 0xFF;
-	int err = -EAFNOSUPPORT;
 	struct sk_buff *skb;
 	struct udphdr *uh;
 
@@ -140,16 +142,17 @@ static void nat_keepalive_send(struct nat_keepalive *ka)
 
 	switch (ka->family) {
 	case AF_INET:
-		err = nat_keepalive_send_ipv4(skb, ka);
+		nat_keepalive_send_ipv4(skb, ka);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		err = nat_keepalive_send_ipv6(skb, ka, uh);
+		nat_keepalive_send_ipv6(skb, ka, uh);
 		break;
 #endif
-	}
-	if (err)
+	default:
 		kfree_skb(skb);
+		break;
+	}
 }
 
 struct nat_keepalive_work_ctx {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 959544425692..639934f30016 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -242,6 +242,9 @@ __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
 			 unsigned short family)
 {
+	if (family != sel->family && sel->family != AF_UNSPEC)
+		return false;
+
 	switch (family) {
 	case AF_INET:
 		return __xfrm4_selector_match(sel, fl);
@@ -685,7 +688,7 @@ static void xfrm_byidx_resize(struct net *net)
 
 static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total)
 {
-	unsigned int cnt = net->xfrm.policy_count[dir];
+	unsigned int cnt = READ_ONCE(net->xfrm.policy_count[dir]);
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
 
 	if (total)
@@ -711,12 +714,12 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total)
 
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
 {
-	si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
-	si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
-	si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
-	si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX];
-	si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX];
-	si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
+	si->incnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN]);
+	si->outcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]);
+	si->fwdcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD]);
+	si->inscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]);
+	si->outscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]);
+	si->fwdscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]);
 	si->spdhcnt = net->xfrm.policy_idx_hmask;
 	si->spdhmcnt = xfrm_policy_hashmax;
 }
@@ -2318,7 +2321,7 @@ static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
 	}
 
 	list_add(&pol->walk.all, &net->xfrm.policy_all);
-	net->xfrm.policy_count[dir]++;
+	WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] + 1);
 	xfrm_pol_hold(pol);
 }
 
@@ -2337,7 +2340,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 	}
 
 	list_del_init(&pol->walk.all);
-	net->xfrm.policy_count[dir]--;
+	WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] - 1);
 
 	return pol;
 }
@@ -3222,7 +3225,7 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
 
 		/* To accelerate a bit...  */
 		if (!if_id && ((dst_orig->flags & DST_NOXFRM) ||
-			       !net->xfrm.policy_count[XFRM_POLICY_OUT]))
+			       !READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT])))
 			goto nopol;
 
 		xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id);
@@ -3296,7 +3299,7 @@ ok:
 
 nopol:
 	if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
-	    net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+	    READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) {
 		err = -EPERM;
 		goto error;
 	}
@@ -3750,7 +3753,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		const bool is_crypto_offload = sp &&
 			(xfrm_input_state(skb)->xso.type == XFRM_DEV_OFFLOAD_CRYPTO);
 
-		if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+		if (READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
 			return 0;
 		}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 589c3b6e4679..ec9ecf72c76b 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1207,9 +1207,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 	struct hlist_head *state_cache_input;
 	struct xfrm_state *x = NULL;
 
+	/* BH is always disabled on the input path. */
+	lockdep_assert_in_softirq();
+
 	state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input);
 
-	rcu_read_lock();
 	hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) {
 		if (x->props.family != family ||
 		    x->id.spi       != spi ||
@@ -1227,20 +1229,25 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 	xfrm_hash_ptrs_get(net, &state_ptrs);
 
 	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
-
-	if (x && x->km.state == XFRM_STATE_VALID) {
-		spin_lock_bh(&net->xfrm.xfrm_state_lock);
-		if (hlist_unhashed(&x->state_cache_input)) {
+	if (x) {
+		spin_lock(&net->xfrm.xfrm_state_lock);
+		if (x->km.state != XFRM_STATE_VALID) {
+			/*
+			 * The state is about to be destroyed.
+			 *
+			 * Don't add it to the cache but still
+			 * return it to the caller.
+			 */
+		} else if (hlist_unhashed(&x->state_cache_input)) {
 			hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
 		} else {
 			hlist_del_rcu(&x->state_cache_input);
 			hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
 		}
-		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		spin_unlock(&net->xfrm.xfrm_state_lock);
 	}
 
 out:
-	rcu_read_unlock();
 	return x;
 }
 EXPORT_SYMBOL(xfrm_input_state_lookup);
@@ -2020,6 +2027,8 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig,
 
 		if (!x->encap)
 			goto error;
+		x->mapping_maxage = orig->mapping_maxage;
+		x->nat_keepalive_interval = orig->nat_keepalive_interval;
 	}
 
 	if (orig->security)
@@ -2054,7 +2063,6 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig,
 	x->km.seq = orig->km.seq;
 	x->replay = orig->replay;
 	x->preplay = orig->preplay;
-	x->mapping_maxage = orig->mapping_maxage;
 	x->lastused = orig->lastused;
 	x->new_mapping = 0;
 	x->new_mapping_sport = 0;
@@ -2976,7 +2984,7 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
-	if (in_compat_syscall()) {
+	if (IS_ENABLED(CONFIG_COMPAT_FOR_U64_ALIGNMENT) && in_compat_syscall()) {
 		struct xfrm_translator *xtr = xfrm_get_translator();
 
 		if (!xtr) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 71a4b7278eba..61eb5de33b87 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2485,9 +2485,9 @@ static int xfrm_notify_userpolicy(struct net *net)
 	}
 
 	up = nlmsg_data(nlh);
-	up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
-	up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
-	up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
+	up->in = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN]);
+	up->fwd = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD]);
+	up->out = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]);
 
 	nlmsg_end(skb, nlh);
 
@@ -2511,13 +2511,13 @@ static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_userpolicy_default *up = nlmsg_data(nlh);
 
 	if (xfrm_userpolicy_is_valid(up->in))
-		net->xfrm.policy_default[XFRM_POLICY_IN] = up->in;
+		WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN], up->in);
 
 	if (xfrm_userpolicy_is_valid(up->fwd))
-		net->xfrm.policy_default[XFRM_POLICY_FWD] = up->fwd;
+		WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD], up->fwd);
 
 	if (xfrm_userpolicy_is_valid(up->out))
-		net->xfrm.policy_default[XFRM_POLICY_OUT] = up->out;
+		WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT], up->out);
 
 	rt_genid_bump_all(net);
 
@@ -2547,9 +2547,9 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	r_up = nlmsg_data(r_nlh);
-	r_up->in = net->xfrm.policy_default[XFRM_POLICY_IN];
-	r_up->fwd = net->xfrm.policy_default[XFRM_POLICY_FWD];
-	r_up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
+	r_up->in = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN]);
+	r_up->fwd = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD]);
+	r_up->out = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]);
 	nlmsg_end(r_skb, r_nlh);
 
 	return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, portid);
@@ -3472,7 +3472,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (in_compat_syscall()) {
+	if (IS_ENABLED(CONFIG_COMPAT_FOR_U64_ALIGNMENT) && in_compat_syscall()) {
 		struct xfrm_translator *xtr = xfrm_get_translator();
 
 		if (!xtr)